mirror of
https://github.com/BigBodyCobain/Shadowbroker.git
synced 2026-06-16 02:50:12 +02:00
Compare commits
53 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 5ede669a12 | |||
| 8fcb01276c | |||
| 10dc9450be | |||
| bef462cdcf | |||
| 5135b771f5 | |||
| 7151563a41 | |||
| 52a28967a0 | |||
| 96182fe66d | |||
| 174031479c | |||
| f1cd9eb4b9 | |||
| c266c5ff5e | |||
| 52a0968092 | |||
| 89d6bb8fb9 | |||
| d48a0cdace | |||
| df76f6f147 | |||
| 776c89bfcf | |||
| d3006df57a | |||
| e78e4d186d | |||
| d1e1be4016 | |||
| 0afb85e241 | |||
| 039a0f9d0c | |||
| b9b99c1fa8 | |||
| a8fd33a758 | |||
| 7346129d0e | |||
| eb8f39f84e | |||
| 00f9e3f1fd | |||
| ffdfe0426b | |||
| 1583fd5715 | |||
| af9b3d08cc | |||
| b64b9e0962 | |||
| 76f4deb3a7 | |||
| 49d90eaf69 | |||
| 079ff7b737 | |||
| bd81a940ff | |||
| 9a0a9a116a | |||
| 80a01275ff | |||
| 3ac8442e4b | |||
| 5f322b0a79 | |||
| 363b5a49c8 | |||
| a3e5c98cd0 | |||
| 6a098e1c5f | |||
| f08781bdc9 | |||
| c3dd95f6a9 | |||
| 10a8c7b5be | |||
| f03ebbba11 | |||
| a16f22ed34 | |||
| 41e35e4da2 | |||
| be3ab5823a | |||
| ef52bd03d2 | |||
| 017f383096 | |||
| 41799f9891 | |||
| a1af9c3595 | |||
| c8a8fc56f8 |
+38
-2
@@ -10,6 +10,23 @@ OPENSKY_CLIENT_ID=
|
||||
OPENSKY_CLIENT_SECRET=
|
||||
AIS_API_KEY=
|
||||
|
||||
# Global Fishing Watch — fishing vessel activity events (Fishing Activity map layer).
|
||||
# Free API token from https://globalfishingwatch.org/our-apis/tokens
|
||||
# Without this the fishing_activity layer stays empty.
|
||||
# GFW_API_TOKEN=
|
||||
# Optional tuning — GFW can return 40k+ global events; defaults cap fetch for map paint.
|
||||
# GFW_EVENTS_PAGE_SIZE=500
|
||||
# GFW_EVENTS_MAX_PAGES=10
|
||||
# GFW_EVENTS_LOOKBACK_DAYS=7
|
||||
# GFW_EVENTS_TIMEOUT_S=90
|
||||
|
||||
# Windy Webcams global CCTV layer — free key from https://api.windy.com/webcams/docs
|
||||
# WINDY_API_KEY=
|
||||
|
||||
# Telegram OSINT map layer — scrapes public t.me/s channel previews (no bot token).
|
||||
# TELEGRAM_OSINT_ENABLED=true
|
||||
# TELEGRAM_OSINT_CHANNELS=osintdefender,insiderpaper,aljazeeraenglish,nexta_live,war_monitor
|
||||
|
||||
# Admin key to protect sensitive endpoints (settings, updates).
|
||||
# If blank, loopback/localhost requests still work for local single-host dev.
|
||||
# Remote/non-loopback admin access requires ADMIN_KEY, or ALLOW_INSECURE_ADMIN=true in debug-only setups.
|
||||
@@ -39,8 +56,8 @@ ADMIN_KEY=
|
||||
# NUFORC_MAPBOX_TOKEN=
|
||||
|
||||
# Optional startup-risk controls.
|
||||
# On Windows, external curl fallback and the Playwright LiveUAMap scraper are
|
||||
# disabled by default so blocked upstream feeds cannot interrupt start.bat.
|
||||
# On Windows, external curl fallback is off by default. LiveUAMap uses UI consent
|
||||
# when you enable Global Incidents (or set SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER=true).
|
||||
# SHADOWBROKER_ENABLE_WINDOWS_CURL_FALLBACK=false
|
||||
# SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER=false
|
||||
# AIS starts by default when AIS_API_KEY is set. Set to 0/false to force-disable.
|
||||
@@ -77,6 +94,19 @@ ADMIN_KEY=
|
||||
# pip install earthengine-api
|
||||
# GEE_SERVICE_ACCOUNT_KEY=
|
||||
|
||||
# Copernicus CDSE — Sentinel-2 imagery (Settings → Imagery, or backend .env).
|
||||
# Free OAuth app at https://dataspace.copernicus.eu/
|
||||
# SENTINEL_CLIENT_ID=
|
||||
# SENTINEL_CLIENT_SECRET=
|
||||
|
||||
# Sentinel-2 road corridor freight trends (DrishX engine port — opt-in slow layer).
|
||||
# pip install -e backend[road-corridor] (or uv sync --extra road-corridor)
|
||||
# ROAD_CORRIDOR_SAT_ENABLED=false
|
||||
# ROAD_CORRIDOR_SCHEDULED_PRESETS=laredo_i35
|
||||
# ROAD_CORRIDOR_MONTHS=2
|
||||
# ROAD_CORRIDOR_MAX_FRAMES=6
|
||||
# ROAD_CORRIDOR_REFRESH_HOURS=24
|
||||
|
||||
# Override the backend URL the frontend uses (leave blank for auto-detect)
|
||||
# NEXT_PUBLIC_API_URL=http://192.168.1.50:8000
|
||||
|
||||
@@ -128,8 +158,14 @@ ADMIN_KEY=
|
||||
# MESH_DM_ROOT_TRANSPARENCY_LEDGER_READBACK_URI=backend/../ops/root_transparency_ledger.json
|
||||
|
||||
# ── Self Update ────────────────────────────────────────────────
|
||||
# Optional ZIP updater digest pin. The updater checks this first, then
|
||||
# backend/data/release_digests.json, then the release SHA256SUMS.txt asset.
|
||||
# MESH_UPDATE_SHA256=
|
||||
|
||||
# Optional strict nonce-only frontend CSP. Leave unset unless the exact build
|
||||
# has been verified to hydrate cleanly in your deployment.
|
||||
# SHADOWBROKER_STRICT_CSP=1
|
||||
|
||||
# ── Wormhole (Local Agent) ─────────────────────────────────────
|
||||
# WORMHOLE_URL=http://127.0.0.1:8787
|
||||
# WORMHOLE_TRANSPORT=direct
|
||||
|
||||
@@ -0,0 +1,13 @@
|
||||
## Summary
|
||||
|
||||
<!-- What changed and why (1–3 bullets). -->
|
||||
|
||||
## Test plan
|
||||
|
||||
- [ ] <!-- How you verified the change -->
|
||||
|
||||
## Production hardening (data path / fetchers / unattended deploys only)
|
||||
|
||||
If this PR touches the data path, fetchers, or live-data APIs, walk through [docs/production-hardening.md](https://github.com/BigBodyCobain/Shadowbroker/blob/main/docs/production-hardening.md) and note any N/A items here.
|
||||
|
||||
- [ ] Checklist reviewed (or N/A — explain why)
|
||||
+12
@@ -109,6 +109,9 @@ backend/data/*
|
||||
# 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
|
||||
# DrishX RF model weights (MIT — see backend/third_party/drishx/NOTICE.md)
|
||||
!backend/data/drishx/
|
||||
!backend/data/drishx/rf_model.pickle
|
||||
|
||||
# OS generated files
|
||||
.DS_Store
|
||||
@@ -174,6 +177,8 @@ frontend/eslint-report.json
|
||||
.git_backup/
|
||||
local-artifacts/
|
||||
release-secrets/
|
||||
release-staging/
|
||||
.tmp-release-inspect/
|
||||
shadowbroker_repo/
|
||||
frontend/src/components.bak/
|
||||
frontend/src/components/map/icons/backups/
|
||||
@@ -198,6 +203,8 @@ graphify-out/
|
||||
# Internal docs & brainstorming (never commit)
|
||||
# ========================
|
||||
docs/*
|
||||
!docs/OUTBOUND_DATA.md
|
||||
!docs/production-hardening.md
|
||||
!docs/mesh/
|
||||
docs/mesh/*
|
||||
!docs/mesh/threat-model.md
|
||||
@@ -256,6 +263,11 @@ frontend/.desktop-export-stash-*/
|
||||
backend/data/wormhole_stderr.log
|
||||
backend/data/wormhole_stdout.log
|
||||
|
||||
# Hermes Agent (operator-local runtime install — not project source)
|
||||
.hermes/
|
||||
**/.hermes/
|
||||
hermes-agent/
|
||||
|
||||
# Runtime caches that already slip through the backend/data/* blanket
|
||||
# (these are caught by the wildcard but listing for clarity)
|
||||
|
||||
|
||||
+42
-12
@@ -13,13 +13,22 @@
|
||||
# 2. Reverse-mirrors main back to GitHub (only if commits land directly
|
||||
# on GitLab) so the two sources stay in sync.
|
||||
#
|
||||
# Pipelines on this repo were instant-failing for free-tier accounts until
|
||||
# identity verification was added — the May 2026 bump in this comment is
|
||||
# the marker commit that confirms runner allocation after verification.
|
||||
#
|
||||
# Auth notes:
|
||||
# - The image build/push uses $CI_JOB_TOKEN, which GitLab provides
|
||||
# automatically. No credentials need to be configured.
|
||||
# - The reverse mirror requires a GitHub personal access token stored
|
||||
# as the GitLab CI/CD variable GITHUB_MIRROR_TOKEN (Protected + Masked).
|
||||
# Scope: public_repo (or repo for private). If the variable isn't
|
||||
# set the mirror job is skipped — image builds still run.
|
||||
# - The reverse mirror authenticates to GitHub via a per-repo SSH
|
||||
# deploy key. The private half is stored as the File-type GitLab
|
||||
# CI/CD variable GITHUB_MIRROR_SSH_KEY (Protected). The matching
|
||||
# public key is added to github.com/BigBodyCobain/Shadowbroker/
|
||||
# settings/keys with write access. This is a tighter-scoped
|
||||
# replacement for a personal access token: it can ONLY push to
|
||||
# Shadowbroker, never expires, and rotating it is a one-click
|
||||
# delete on GitHub's deploy-keys page. If the variable isn't set,
|
||||
# the mirror job is skipped — image builds still run.
|
||||
|
||||
stages:
|
||||
- build
|
||||
@@ -48,7 +57,11 @@ variables:
|
||||
- docker info
|
||||
- docker login -u "$CI_REGISTRY_USER" -p "$CI_JOB_TOKEN" "$CI_REGISTRY"
|
||||
- docker run --privileged --rm tonistiigi/binfmt --install all
|
||||
- docker buildx create --use --name multiarch --driver docker-container
|
||||
# buildx --driver docker-container can't read TLS from the env vars
|
||||
# the GitLab dind service exports. Wrap them in a docker context and
|
||||
# bind buildx to it. See https://docs.gitlab.com/ee/ci/docker/using_docker_build.html#use-docker-buildx
|
||||
- docker context create tls-env
|
||||
- docker buildx create --use --name multiarch --driver docker-container tls-env
|
||||
|
||||
# ── Backend image ────────────────────────────────────────────────────────
|
||||
build-backend:
|
||||
@@ -93,18 +106,35 @@ build-frontend:
|
||||
- .gitlab-ci.yml
|
||||
|
||||
# ── Reverse mirror to GitHub ─────────────────────────────────────────────
|
||||
# Pushes refs/heads/main to github.com/BigBodyCobain/Shadowbroker.
|
||||
# Fast-forward-only — if GitLab main and GitHub main have diverged, this
|
||||
# fails loudly rather than silently overwriting either side.
|
||||
# Pushes refs/heads/main to github.com/BigBodyCobain/Shadowbroker via SSH
|
||||
# using a per-repo deploy key. Fast-forward-only by default — if GitLab
|
||||
# main and GitHub main have diverged, the push fails loudly rather than
|
||||
# silently overwriting either side.
|
||||
#
|
||||
# Only runs if GITHUB_MIRROR_TOKEN is set as a CI/CD variable. See the
|
||||
# header comment of this file for setup instructions.
|
||||
# Only runs if GITHUB_MIRROR_SSH_KEY is set as a File-type CI/CD variable.
|
||||
# See the header comment of this file for setup instructions.
|
||||
mirror-to-github:
|
||||
stage: mirror
|
||||
image: alpine:3.20
|
||||
needs: []
|
||||
before_script:
|
||||
- apk add --no-cache git openssh-client ca-certificates
|
||||
- mkdir -p ~/.ssh
|
||||
- chmod 700 ~/.ssh
|
||||
# Install the deploy key. File-type CI variable exposes the path; copy
|
||||
# to ~/.ssh/id_ed25519 with restrictive perms so ssh accepts it.
|
||||
- cp "$GITHUB_MIRROR_SSH_KEY" ~/.ssh/id_ed25519
|
||||
- chmod 600 ~/.ssh/id_ed25519
|
||||
# Pin github.com's current host keys so we never trust a man-in-the-
|
||||
# middle. Sourced from https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/githubs-ssh-key-fingerprints
|
||||
# (rotated 2023-03-24 after the previous RSA key leak).
|
||||
- |
|
||||
cat > ~/.ssh/known_hosts <<'EOF'
|
||||
github.com ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIOMqqnkVzrm0SdG6UOoqKLsabgH5C9okWi0dh2l9GKJl
|
||||
github.com ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBEmKSENjQEezOmxkZMy7opKgwFB9nkt5YRrYMjNuG5N87uRgg6CLrbo5wAdT/y6v0mKV0U2w0WZ2YB/++Tpockg=
|
||||
github.com ssh-rsa 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
|
||||
EOF
|
||||
- chmod 644 ~/.ssh/known_hosts
|
||||
script:
|
||||
- git config --global user.email "ci-mirror@gitlab.com"
|
||||
- git config --global user.name "GitLab CI Mirror"
|
||||
@@ -115,7 +145,7 @@ mirror-to-github:
|
||||
- cd repo
|
||||
- >
|
||||
git push
|
||||
"https://x-access-token:${GITHUB_MIRROR_TOKEN}@github.com/BigBodyCobain/Shadowbroker.git"
|
||||
"git@github.com:BigBodyCobain/Shadowbroker.git"
|
||||
"${CI_COMMIT_SHA}:refs/heads/main"
|
||||
rules:
|
||||
- if: $CI_COMMIT_BRANCH == "main" && $GITHUB_MIRROR_TOKEN
|
||||
- if: $CI_COMMIT_BRANCH == "main" && $GITHUB_MIRROR_SSH_KEY
|
||||
|
||||
+2
-1
@@ -44,7 +44,8 @@ These sources have their own terms; consult each link before redistributing.
|
||||
| aisstream.io | https://aisstream.io | Free-tier API terms (attribution required) | AIS vessel positions |
|
||||
| Global Fishing Watch | https://globalfishingwatch.org | CC BY 4.0 (for public data) | Fishing activity events |
|
||||
| Microsoft Planetary Computer | https://planetarycomputer.microsoft.com | Sentinel-2 / ESA Copernicus terms | Sentinel-2 imagery |
|
||||
| Copernicus CDSE (Sentinel Hub) | https://dataspace.copernicus.eu | ESA Copernicus open data terms | SAR + optical imagery |
|
||||
| Copernicus CDSE (Sentinel Hub) | https://dataspace.copernicus.eu | ESA Copernicus open data terms | SAR + optical imagery, optional road-corridor truck trends |
|
||||
| DrishX / Fisser et al. 2022 | https://github.com/sparkyniner/DRISH-X-Satellite-powered-freight-intelligence- | MIT (engine); research methodology attribution | Sentinel-2 motion-smear truck detection on major roads (opt-in) |
|
||||
| Shodan | https://www.shodan.io | Operator-supplied API key, Shodan ToS | Internet device search |
|
||||
| Smithsonian GVP | https://volcano.si.edu | Attribution required | Volcanoes |
|
||||
| OpenAQ | https://openaq.org | CC BY 4.0 | Air quality stations |
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
|
||||
**ShadowBroker** is a decentralized intelligence platform that aggregates real-time, multi-domain OSINT telemetry from 60+ live intelligence feeds into a single dark-ops map interface. Aircraft, ships, satellites, conflict zones, CCTV networks, GPS jamming, internet-connected devices, police scanners, mesh radio nodes, and breaking geopolitical events — all updating in real time on one screen as well as an obfuscated communications protocol and information exchange infrastructure.
|
||||
|
||||
Built with **Next.js**, **MapLibre GL**, **FastAPI**, and **Python**. 35+ toggleable data layers, including SAR ground-change detection. Multiple visual modes (DEFAULT / SATELLITE / FLIR / NVG / CRT). Right-click any point on Earth for a country dossier, head-of-state lookup, and the latest Sentinel-2 satellite photo. No user data is collected or transmitted — the dashboard runs entirely in your browser against a self-hosted backend.
|
||||
Built with **Next.js**, **MapLibre GL**, **FastAPI**, and **Python**. 40+ toggleable data layers, including SAR ground-change detection, **Telegram OSINT** (public channel previews geoparsed onto the map), a **server-side recon toolkit** (DNS, WHOIS, sanctions, BGP, IP sweep, and more), supply-chain risk overlays, and malware/C2 + CISA KEV cyber threat feeds. Multiple visual modes (DEFAULT / SATELLITE / FLIR / NVG / CRT). Right-click any point on Earth for a country dossier, head-of-state lookup, entity-graph expansion, and the latest Sentinel-2 satellite photo. ShadowBroker has no accounts, product telemetry, or analytics; the dashboard talks to your self-hosted backend. Sensitive recon and Shodan queries never hit third-party APIs from the browser — they are proxied through the backend with SSRF guards and local-operator auth. The **OpenClaw / agent command channel** exposes the same recon backends plus full telemetry search — no separate API integration required.
|
||||
|
||||
Designed for analysts, researchers, radio operators, and anyone who wants to see what the world looks like when every public signal is on the same map.
|
||||
|
||||
@@ -28,18 +28,20 @@ Designed for analysts, researchers, radio operators, and anyone who wants to see
|
||||
|
||||
A surprising amount of global telemetry is already public — aircraft ADS-B broadcasts, maritime AIS signals, satellite orbital data, earthquake sensors, mesh radio networks, police scanner feeds, environmental monitoring stations, internet infrastructure telemetry, and more. This data is scattered across dozens of tools and APIs. ShadowBroker combines all of it into a single interface.
|
||||
|
||||
The project does not introduce new surveillance capabilities — it aggregates and visualizes existing public datasets. It is fully open-source so anyone can audit exactly what data is accessed and how. No user data is collected or transmitted — everything runs locally against a self-hosted backend. No telemetry, no analytics, no accounts.
|
||||
The project does not introduce new surveillance capabilities — it aggregates and visualizes existing public datasets. It is fully open-source so anyone can audit exactly what data is accessed and how. ShadowBroker does not include product telemetry, analytics, or accounts. Operator-supplied keys stay in your local deployment, but live OSINT features necessarily make outbound requests to the public data providers you enable or query.
|
||||
|
||||
### Shodan Connector
|
||||
### Shodan & Recon (security-first)
|
||||
|
||||
ShadowBroker includes an optional Shodan connector for operator-supplied API access. Shodan results are fetched with your own `SHODAN_API_KEY`, rendered as a local investigative overlay (not merged into core feeds), and remain subject to Shodan’s terms of service.
|
||||
ShadowBroker includes an optional **Shodan connector** for operator-supplied API access (`SHODAN_API_KEY`) and a **Recon Toolkit** panel for keyless OSINT lookups. Both run **server-side only**: the browser calls your self-hosted `/api/osint/*` and `/api/tools/shodan/*` routes; outbound requests are made by the backend after SSRF validation. Recon requires **local-operator** access (same trust model as layer toggles and admin routes). Shodan results render as a separate map overlay and remain subject to Shodan’s terms of service.
|
||||
|
||||
> **Not included:** embedded live-news YouTube grids or a built-in Gemini AI analyst panel — use the **OpenClaw / agent channel** for AI-assisted analysis instead.
|
||||
|
||||
---
|
||||
|
||||
## Interesting Use Cases
|
||||
|
||||
* **Track Air Force One**, the private jets of billionaires and dictators, and every military tanker, ISR, and fighter broadcasting ADS-B. Air Force One and all of the accompanying Presidential/Vice Presidential planes are highlighted and monitored from the moment they leave the ground.
|
||||
* **Connect an AI agent as a co-analyst** through ShadowBroker's HMAC-signed agentic command channel — supports OpenClaw and any other agent that speaks the protocol (Claude, GPT, LangChain, custom). The agent gets full read/write access to all 35+ data layers, pin placement, map control, SAR ground-change, mesh networking, and alert delivery. It sees everything the operator sees and can take actions on the map in real time.
|
||||
* **Connect an AI agent as a co-analyst** through ShadowBroker's HMAC-signed agentic command channel — supports OpenClaw and any other agent that speaks the protocol (Claude, GPT, LangChain, custom). The agent gets full read/write access to all 40+ data layers, compact cross-layer search (`search_telemetry`, `search_news`), the full recon toolkit (`osint_lookup` for IP/DNS/WHOIS/sanctions/CVE/etc.), entity-graph expansion, pin placement, map control, SAR ground-change, mesh networking, and alert delivery. It sees everything the operator sees and can take actions on the map in real time.
|
||||
* **Communicate on the InfoNet testnet** — The first decentralized intelligence mesh built into an OSINT tool. Obfuscated messaging with gate personas, Dead Drop peer-to-peer exchange, and a built-in terminal CLI. No accounts, no signup. Privacy is not guaranteed yet — this is an experimental testnet — but the protocol is live and being hardened.
|
||||
* **Right-click anywhere on Earth** for a country dossier (head of state, population, languages), Wikipedia summary, and the latest Sentinel-2 satellite photo at 10m resolution
|
||||
* **Click a KiwiSDR node** and tune into live shortwave radio directly in the dashboard. Click a police scanner feed and eavesdrop in one click.
|
||||
@@ -55,6 +57,12 @@ ShadowBroker includes an optional Shodan connector for operator-supplied API acc
|
||||
* **Track trains** across the US (Amtrak) and Europe (DigiTraffic) in real time
|
||||
* **Estimate where US aircraft carriers are** using automated GDELT news scraping — no other open tool does this
|
||||
* **Search internet-connected devices worldwide** via Shodan — cameras, SCADA systems, databases — plotted as a live overlay on the map
|
||||
* **Run a full recon toolkit** from the left sidebar — IP geolocation, DNS, RDAP/WHOIS, certificate transparency, BGP/ASN, OFAC sanctions search, CVE lookup, Tor/OTX threat checks, and subnet sweeps (InternetDB proxied server-side)
|
||||
* **Expand an entity graph** when you select an aircraft, vessel, company, or IP — Wikidata + OFAC + live store cross-links rendered in the Entity Graph panel
|
||||
* **Monitor supply-chain risk** — Tier 1/2 semiconductor and battery fabs scored against nearby earthquakes, wildfires, and conflict events (SCM panel)
|
||||
* **Toggle malware C2 hotspots** — abuse.ch Feodo Tracker + URLhaus feeds mapped by country (opt-in layer)
|
||||
* **Monitor Telegram OSINT channels** — public `t.me/s` war/conflict feeds (OSINTdefender, NEXTA, etc.) scraped hourly, risk-scored, geoparsed to metro anchors, and plotted as clickable map pins with inline media
|
||||
* **Overlay global submarine cables** — static TeleGeography-derived cable routes (opt-in layer)
|
||||
|
||||
|
||||
---
|
||||
@@ -83,6 +91,8 @@ Both paths produce identical containers — same source, same CI, same images by
|
||||
|
||||
Open `http://localhost:3000` to view the dashboard! *(Requires [Docker Desktop](https://www.docker.com/products/docker-desktop/) or Docker Engine)*
|
||||
|
||||
> **Join the private InfoNet swarm (sb-testnet-0):** Click **NODE** in the dashboard, or run `./meshnode.sh` for a headless participant. No manual peer list — fleet defaults discover the seed and pull the signed manifest automatically. Set `MESH_INFONET_FLEET_JOIN=false` in `.env` for a private solo node.
|
||||
|
||||
> **Backend port already in use?** The browser only needs port `3000`, but the backend API is also published on host port `8000` for local diagnostics. If another app already uses `8000`, create or edit `.env` next to `docker-compose.yml` and set `BACKEND_PORT=8001`, then run `docker compose up -d`.
|
||||
|
||||
> **Blank news/UAP/bases/wastewater after several minutes?** Check for backend OOM restarts with `docker events --since 30m --filter container=shadowbroker-backend --filter event=oom`. The default compose file gives the backend 4GB; if your host has less memory, reduce enabled feeds or set `BACKEND_MEMORY_LIMIT=3G` and expect slower/heavier layers to warm more gradually.
|
||||
@@ -113,6 +123,20 @@ That's it. `pull` grabs the latest images, `up -d` restarts the containers.
|
||||
>
|
||||
> Podman users should run the equivalent provider command, for example `podman-compose pull` and `podman-compose up -d`, or use `./compose.sh --engine podman pull` and `./compose.sh --engine podman up -d` from a bash-compatible shell.
|
||||
|
||||
### Update Integrity
|
||||
|
||||
Docker updates are delivered through signed container registries. The legacy ZIP self-updater verifies release archives through this chain, in order:
|
||||
|
||||
* `MESH_UPDATE_SHA256` when an operator pins a digest explicitly.
|
||||
* `backend/data/release_digests.json` for bundled release pins.
|
||||
* The release `SHA256SUMS.txt` asset on GitHub when a bundled pin is not present.
|
||||
|
||||
Release maintainers should run `python backend/scripts/release_helper.py hash <ShadowBroker_vX.Y.Z.zip>` before publishing, then publish `SHA256SUMS.txt` and update `backend/data/release_digests.json` when shipping a ZIP updater target. The updater keeps the operator override path intact instead of failing closed on missing bundled digests, so existing installs do not get stranded by a release-process mistake.
|
||||
|
||||
### CSP Hardening
|
||||
|
||||
The production frontend ships with a hydration-compatible CSP and a strict nonce-only CSP in `Content-Security-Policy-Report-Only`. Set `SHADOWBROKER_STRICT_CSP=1` only after verifying the exact build hydrates correctly in your deployment. Runtime Google Fonts are not required; the bundled Next font pipeline serves the dashboard font from the app build.
|
||||
|
||||
### ⚠️ **Stuck on the old version?**
|
||||
|
||||
**If `git pull` fails or `docker compose up` keeps building from source instead of pulling images**, your clone predates a March 2026 repository migration that rewrote commit history. A normal `git pull` cannot fix this. Run:
|
||||
@@ -219,17 +243,34 @@ The first decentralized intelligence communication and governance layer built di
|
||||
|
||||
**Privacy primitive runway (NEW in v0.9.7):**
|
||||
|
||||
* **Function Keys — Anonymous Citizenship Proof** — A citizen proves "I am an Infonet citizen" without revealing their Infonet identity. 5 of 6 pieces shipped: nullifiers, challenge-response, two-phase commit receipts, enumerated denial codes, batched settlement. Issuance via blind signatures waits on a primitive decision (RSA blind sigs vs BBS+ vs U-Prove vs Idemix).
|
||||
* **Function Keys — Anonymous Credential Scaffolding** — The plumbing is in place for nullifiers, challenge-response, two-phase commit receipts, enumerated denial codes, and batched settlement. Today's challenge-response is an HMAC-based placeholder for integration testing, not a production anonymous or zero-knowledge citizenship proof. True unlinkable issuance still waits on a primitive decision (RSA blind sigs vs BBS+ vs U-Prove vs Idemix).
|
||||
* **Locked Protocol Contracts** — Stable interfaces in `services/infonet/privacy/contracts.py` for ring signatures, stealth addresses, Pedersen commitments, range proofs, and DEX matching. The `privacy-core` Rust crate is the integration target — no caller of the privacy module needs to know which scheme is active.
|
||||
* **Sprint 11+ Path** — When the cryptographic scheme is chosen, primitives wire into the locked Protocols without API churn.
|
||||
|
||||
> **Experimental Testnet — No Privacy Guarantee:** InfoNet messages are obfuscated but NOT end-to-end encrypted. The Mesh network (Meshtastic/APRS) is NOT private — radio transmissions are inherently public. The privacy primitive contracts are scaffolded but not yet wired. Do not send anything sensitive on any channel. Treat all channels as open and public for now.
|
||||
|
||||
### 🔍 Shodan Device Search (NEW in v0.9.6)
|
||||
### 🔍 Recon Toolkit & Shodan (Osiris-derived, security-first)
|
||||
|
||||
* **Internet Device Search** — Query Shodan directly from ShadowBroker. Search by keyword, CVE, port, or service — results plotted as a live overlay on the map
|
||||
Adapted from the [OSIRIS](https://github.com/simplifaisoul/osiris) recon stack (MIT) with ShadowBroker’s proxy model. Attribution: `backend/third_party/osiris/NOTICE.md`.
|
||||
|
||||
**Recon Toolkit** (left sidebar — local operator only):
|
||||
|
||||
* **IP / DNS / WHOIS** — ip-api.com geolocation, Google DNS-over-HTTPS, RDAP registrant data with optional HTTP security header scoring
|
||||
* **Certificates & BGP** — crt.sh subdomain discovery, bgpview.io ASN/prefix lookups
|
||||
* **Threat intel** — AlienVault OTX pulses, Tor exit-node checks, optional per-IP/domain reputation
|
||||
* **Sanctions** — OpenSanctions `us_ofac_sdn` index (CC-BY); cross-checks on WHOIS entities and IP ISP/org strings
|
||||
* **CVE / MAC / GitHub / leaks** — MITRE CVE API, MAC vendor lookup, GitHub profile recon, public breach checks
|
||||
* **IP sweep** — `/api/osint/sweep/scan` geolocates a target /24–/32 and proxies Shodan InternetDB host discovery server-side (browser never contacts InternetDB directly)
|
||||
* **SSRF guard** — Private, loopback, link-local, and metadata hostnames are blocked before any user-supplied fetch
|
||||
|
||||
**Entity graph** — Select any map entity to open the Entity Graph panel (`GET /api/entity/expand`). Resolves aircraft, vessels, companies, persons, IPs, and countries into a node/link graph (Wikidata SPARQL + OFAC + in-memory flight/ship store).
|
||||
|
||||
**OpenClaw / agent access** — The same recon backends are available on the HMAC command channel (no browser local-operator gate): `osint_lookup` (passive IP/DNS/WHOIS/certs/BGP/sanctions/CVE/MAC/GitHub/leaks/threats), `entity_expand` (relationship graph), and `osint_sweep` (active subnet scan — **full** access tier only). Call `osint_tools` to list supported lookup types. Skill package: `openclaw-skills/shadowbroker/` (`SKILL.md` + `sb_query.py`).
|
||||
|
||||
**Shodan overlay** (unchanged):
|
||||
|
||||
* **Internet Device Search** — Query Shodan with your own API key; results plotted as a live overlay
|
||||
* **Configurable Markers** — Shape, color, and size customization for Shodan results
|
||||
* **Operator-Supplied API** — Uses your own `SHODAN_API_KEY`; results rendered as a local investigative overlay
|
||||
|
||||
### 🛩️ Aviation Tracking
|
||||
|
||||
@@ -317,11 +358,12 @@ The first decentralized intelligence communication and governance layer built di
|
||||
|
||||
### 📷 Surveillance
|
||||
|
||||
* **CCTV Mesh** — 11,000+ live traffic cameras from 13 sources across 6 countries:
|
||||
* **CCTV Mesh** — 22,000+ live traffic cameras from 21 ingestors across 10 countries (US, UK, Canada, Australia, Austria, Spain, Singapore, Netherlands when NDW feed is up, plus OSM):
|
||||
* 🇬🇧 Transport for London JamCams
|
||||
* 🇺🇸 NYC DOT, Austin TX (TxDOT)
|
||||
* 🇺🇸 California (12 Caltrans districts), Washington State (WSDOT), Georgia DOT, Illinois DOT, Michigan DOT
|
||||
* 🇪🇸 Spain DGT National (20 cities), Madrid City (357 cameras via KML)
|
||||
* 🇦🇹 Austria ASFINAG motorway webcams
|
||||
* 🇸🇬 Singapore LTA
|
||||
* 🌍 Windy Webcams
|
||||
* **Feed Rendering** — Automatic detection & rendering of video, MJPEG, HLS, embed, satellite tile, and image feeds
|
||||
@@ -342,6 +384,12 @@ The first decentralized intelligence communication and governance layer built di
|
||||
* **Data Center Mapping** — 2,000+ global data centers plotted from a curated dataset. Clustered purple markers with server-rack icons. Click for operator, location, and automatic internet outage cross-referencing by country.
|
||||
* **Military Bases** — Global military installation and missile facility database (NEW)
|
||||
* **Power Plants** — 35,000+ global power plants from the WRI database (NEW)
|
||||
* **Submarine Cables** — Global undersea cable routes from static TeleGeography-derived GeoJSON (`frontend/public/data/submarine-cables.json`). Opt-in line overlay.
|
||||
* **Malware C2 Layer** — Botnet C2 servers (Feodo Tracker) and recent malware URLs (URLhaus) from abuse.ch, refreshed on the slow tier when the layer is enabled.
|
||||
* **SCM Supplier Risk** — Tier 1/2 fabs and battery plants (TSMC, Samsung, CATL, etc.) cross-referenced against earthquakes, FIRMS fires, and GDELT conflict proximity. Alerts in the SCM panel; optional map layer.
|
||||
* **Cyber Threats Feed** — Recent CISA Known Exploited Vulnerabilities (KEV) entries exposed via `/api/cyber-threats` and the layer toggle.
|
||||
* **Country Risk Index** — Static geopolitical risk scores with USGS earthquake enrichment via `/api/country-risk`.
|
||||
* **Telegram OSINT** — Public channel web previews (`t.me/s/*`) from configurable war/OSINT feeds. Hourly incremental merge (no redundant re-scrape), keyword risk scoring, Cyrillic/Arabic place aliases, metro-anchor geocoding (separate from news centroids), inline photo/video via `/api/telegram/media` proxy. Layer key: `telegram_osint`.
|
||||
|
||||
### 🌐 Additional Layers & Tools
|
||||
|
||||
@@ -367,7 +415,9 @@ v0.9.7 turns ShadowBroker from a dashboard a human watches into an intelligence
|
||||
|
||||
**Capabilities:**
|
||||
|
||||
* **Full Telemetry Access** — The agent queries all 35+ data layers: flights, ships, satellites, SIGINT, conflict events, earthquakes, fires, wastewater, prediction markets, and more. Fast and slow tier endpoints return enriched data with geographic coordinates, timestamps, and source attribution.
|
||||
* **Full Telemetry Access** — The agent queries all 40+ data layers: flights, ships, satellites, SIGINT, conflict events, earthquakes, fires, wastewater, **Telegram OSINT**, malware/C2, **CISA KEV cyber threats**, SCM overlays, fishing activity (GFW), prediction markets, and more. Fast and slow tier endpoints return enriched data with geographic coordinates, timestamps, and source attribution.
|
||||
* **Compact Search (preferred over full dumps)** — `get_summary` → `get_layer_slice` with per-layer `since_layer_versions` (SSE `layer_changed` push tells the agent exactly which layers updated). `search_telemetry` is the Google-style cross-layer keyword index. `search_news` covers news, GDELT, CrowdThreat, LiveUAMap, frontlines, and Telegram posts. `entities_near`, `brief_area`, `find_flights`/`find_ships`/`find_entity`, and `correlate_entity` answer targeted questions without multi-megabyte pulls.
|
||||
* **Recon Toolkit on the Channel** — `osint_lookup` runs the same SSRF-guarded backends as the Recon panel (`ip`, `dns`, `whois`, `certs`, `bgp`, `sanctions`, `cve`, `mac`, `github`, `leaks`, `threats`, `sweep_init`). `entity_expand` builds Wikidata + OFAC relationship graphs. `osint_sweep` runs Shodan InternetDB subnet discovery (**full** tier). Layer aliases: `telegram`, `malware`/`botnet`, `cyber`/`cisa`/`kev`, `scm`/`suppliers`, `gfw`/`fishing`.
|
||||
* **AI Intel Pins** — Place color-coded investigation markers directly on the operator's map. 14 pin categories (threat, anomaly, military, maritime, aviation, SIGINT, infrastructure, etc.) with confidence scores, TTL expiry, source URLs, and batch placement up to 100 pins at once.
|
||||
* **Map Control** — Fly the operator's map view to any coordinate, trigger satellite imagery lookups, and open region dossiers. The agent can direct the operator's attention to specific locations in real time.
|
||||
* **SAR Ground-Change** — Query SAR anomaly feeds, inspect pin details, manage AOIs, and fly the map to watch areas. The agent can monitor for ground deformation, flood extent, or damage and promote anomalies to pins.
|
||||
@@ -380,7 +430,7 @@ v0.9.7 turns ShadowBroker from a dashboard a human watches into an intelligence
|
||||
* **Intelligence Reports** — Generate structured reports with summary stats, top military flights, correlations, earthquake activity, SIGINT counts, and pin inventories.
|
||||
* **Auditable** — Every channel call is logged; the operator can introspect what the agent has done.
|
||||
|
||||
**Connect an agent:** Open the AI Intel panel in the left sidebar, click **Connect Agent**, and copy the HMAC secret. From there, point any compatible agent at the channel — for OpenClaw, import `ShadowBrokerClient` from the OpenClaw skill package; for any other agent, use the same HMAC contract documented above (timestamp + nonce + body digest, tier-gated). The channel is the protocol, not the agent.
|
||||
**Connect an agent:** Open the AI Intel panel in the left sidebar, click **Connect Agent**, and copy the HMAC secret. From there, point any compatible agent at the channel — for OpenClaw, import `ShadowBrokerClient` from `openclaw-skills/shadowbroker/sb_query.py` (see `SKILL.md` for examples); for any other agent, use the same HMAC contract documented above (timestamp + nonce + body digest, tier-gated). Discovery: `GET /api/ai/tools` and `GET /api/ai/capabilities`. The channel is the protocol, not the agent.
|
||||
|
||||
### ⏱️ Time Machine — Snapshot Playback (NEW in v0.9.7)
|
||||
|
||||
@@ -529,9 +579,20 @@ ShadowBroker v0.9.7 is composed of three vertically-stacked planes — the **Ope
|
||||
| [GDELT Project](https://www.gdeltproject.org) | Global conflict events | ~6h | No |
|
||||
| [DeepState Map](https://deepstatemap.live) | Ukraine frontline | ~30min | No |
|
||||
| [Shodan](https://www.shodan.io) | Internet-connected device search | On-demand | **Yes** |
|
||||
| [OpenSanctions](https://www.opensanctions.org) | OFAC SDN sanctions index (recon + entity graph) | 24h cache | No |
|
||||
| [abuse.ch Feodo + URLhaus](https://abuse.ch) | Malware C2 / distribution URLs | ~5min (opt-in layer) | No |
|
||||
| [CISA KEV](https://www.cisa.gov/known-exploited-vulnerabilities-catalog) | Known exploited CVEs | ~5min (opt-in layer) | No |
|
||||
| [ip-api.com](https://ip-api.com) | IP geolocation (recon, entity graph) | On-demand | No |
|
||||
| [Google Public DNS](https://dns.google) | DNS-over-HTTPS lookups (recon) | On-demand | No |
|
||||
| [RDAP.org](https://rdap.org) | Domain registration data (recon) | On-demand | No |
|
||||
| [crt.sh](https://crt.sh) | Certificate transparency (recon) | On-demand | No |
|
||||
| [bgpview.io](https://bgpview.io) | BGP/ASN routing (recon) | On-demand | No |
|
||||
| TeleGeography (static) | Submarine cable routes | Static | No |
|
||||
| [ASFINAG](https://www.asfinag.at) | Austria motorway webcams | ~10min | No |
|
||||
| [Amtrak](https://www.amtrak.com) | US train positions | ~60s | No |
|
||||
| [DigiTraffic](https://www.digitraffic.fi) | European rail positions | ~60s | No |
|
||||
| [Global Fishing Watch](https://globalfishingwatch.org) | Fishing vessel activity events | ~10min | No |
|
||||
| [Global Fishing Watch](https://globalfishingwatch.org) | Fishing vessel activity events | ~1hr | **Yes** (`GFW_API_TOKEN`) |
|
||||
| [Telegram public previews](https://t.me/s) | War/OSINT channel posts (`telegram_osint`) | ~1hr | No (optional `TELEGRAM_OSINT_CHANNELS`) |
|
||||
| Transport for London, NYC DOT, TxDOT | CCTV cameras (UK, US) | ~10min | No |
|
||||
| Caltrans, WSDOT, GDOT, IDOT, MDOT | CCTV cameras (5 US states) | ~10min | No |
|
||||
| Spain DGT, Madrid City | CCTV cameras (Spain) | ~10min | No |
|
||||
@@ -563,6 +624,8 @@ ShadowBroker v0.9.7 is composed of three vertically-stacked planes — the **Ope
|
||||
| [OSM Nominatim](https://nominatim.openstreetmap.org) | Place name geocoding (LOCATE bar) | On-demand | No |
|
||||
| [CARTO Basemaps](https://carto.com) | Dark map tiles | Continuous | No |
|
||||
|
||||
**Outbound privacy & audit (#348–#366):** Each self-hosted install uses its own backend IP and per-install User-Agent handle. See [docs/OUTBOUND_DATA.md](docs/OUTBOUND_DATA.md) for what contacts third parties, opt-in/env controls, and accepted tradeoffs (CCTV Referer, basemap CDN, LiveUAMap, etc.).
|
||||
|
||||
---
|
||||
|
||||
## 🚀 Getting Started
|
||||
@@ -584,9 +647,16 @@ Open `http://localhost:3000` to view the dashboard.
|
||||
> **Deploying publicly or on a LAN?** No configuration needed for most setups.
|
||||
> The frontend proxies all API calls through the Next.js server to `BACKEND_URL`,
|
||||
> which defaults to `http://backend:8000` (Docker internal networking).
|
||||
> Host port `8000` is only published for local API/debug access. If it conflicts
|
||||
> with another service, set `BACKEND_PORT=8001` in `.env`; leave `BACKEND_URL`
|
||||
> as `http://backend:8000` because that is the Docker-internal port.
|
||||
> Host port `8000` is only published for local API/debug access (`127.0.0.1:8000`
|
||||
> in `docker-compose.yml`). If it conflicts with another service, set
|
||||
> `BACKEND_PORT=8001` in `.env`; leave `BACKEND_URL` as `http://backend:8000`
|
||||
> because that is the Docker-internal port.
|
||||
>
|
||||
> **Running the backend outside Docker** (`cd backend && python main.py`):
|
||||
> the dev server binds **loopback only** (`127.0.0.1:8000`) so other machines on
|
||||
> your LAN cannot hit admin/local-trust routes with an empty `ADMIN_KEY`. Set
|
||||
> `SHADOWBROKER_DEV_BIND_ALL=true` in `.env` only when you deliberately need
|
||||
> `0.0.0.0` and use a strong `ADMIN_KEY` for any non-local callers.
|
||||
> The backend memory cap is controlled by `BACKEND_MEMORY_LIMIT` and defaults
|
||||
> to `4G`. If Docker reports OOM events, the backend will restart and slow
|
||||
> layers can look empty until they repopulate.
|
||||
@@ -798,7 +868,7 @@ AIS-catcher decodes VHF radio signals on 161.975 MHz and 162.025 MHz and POSTs d
|
||||
|
||||
## 🎛️ Data Layers
|
||||
|
||||
All 37 layers are independently toggleable from the left panel:
|
||||
All 41 layers are independently toggleable from the left panel:
|
||||
|
||||
| Layer | Default | Description |
|
||||
|---|---|---|
|
||||
@@ -840,6 +910,24 @@ All 37 layers are independently toggleable from the left panel:
|
||||
| VIIRS Nightlights | ❌ OFF | Night-time light change detection |
|
||||
| Power Plants | ❌ OFF | 35,000+ global power plants |
|
||||
| Shodan Overlay | ❌ OFF | Internet device search results |
|
||||
| Road Freight Trends | ❌ OFF | Sentinel-2 truck-motion trends on major highways (Analyze Here) |
|
||||
| Submarine Cables | ❌ OFF | Global undersea cable routes (static GeoJSON) |
|
||||
| Malware C2 | ❌ OFF | abuse.ch Feodo + URLhaus threat points |
|
||||
| SCM Suppliers | ❌ OFF | Tier 1/2 supply-chain risk markers + panel alerts |
|
||||
| Cyber Threats | ❌ OFF | Recent CISA KEV entries (stats in slow-tier payload) |
|
||||
| Telegram OSINT | ✅ ON | Public war/OSINT Telegram channels — hourly scrape, geoparsed pins |
|
||||
| SAR | ✅ ON | Synthetic aperture radar catalog + anomaly alerts |
|
||||
|
||||
**Recon & entity tools** (not map layers — left sidebar / selection):
|
||||
|
||||
| Tool | Dashboard access | OpenClaw command | Description |
|
||||
|---|---|---|---|
|
||||
| Recon Toolkit | Local operator (`/api/osint/*`) | `osint_lookup`, `osint_sweep`† | IP, DNS, WHOIS, certs, BGP, sanctions, CVE, MAC, GitHub, leaks, threats, subnet sweep |
|
||||
| Entity Graph | Local operator (`/api/entity/expand`) | `entity_expand` | Wikidata + OFAC + live-store relationship graph |
|
||||
| SCM Risk panel | Local operator (`/api/scm-suppliers`) | `get_layer_slice(["scm_suppliers"])` | Supplier threat rollup + map markers |
|
||||
| Tool discovery | — | `osint_tools` | Lists recon lookup types and entity-expand schemas |
|
||||
|
||||
† `osint_sweep` (active InternetDB scan) requires `OPENCLAW_ACCESS_TIER=full`.
|
||||
|
||||
---
|
||||
|
||||
@@ -863,6 +951,7 @@ The platform is optimized for handling massive real-time datasets:
|
||||
|
||||
```
|
||||
Shadowbroker/
|
||||
├── openclaw-skills/shadowbroker/ # OpenClaw skill — SKILL.md, sb_query.py client, alerts/monitor helpers
|
||||
├── backend/
|
||||
│ ├── main.py # FastAPI app, middleware, API routes (~4,000 lines)
|
||||
│ ├── cctv.db # SQLite CCTV camera database (auto-generated)
|
||||
@@ -872,7 +961,18 @@ Shadowbroker/
|
||||
│ │ ├── data_fetcher.py # Core scheduler — orchestrates all data sources
|
||||
│ │ ├── ais_stream.py # AIS WebSocket client (25K+ vessels)
|
||||
│ │ ├── carrier_tracker.py # OSINT carrier position estimator (GDELT news scraping)
|
||||
│ │ ├── cctv_pipeline.py # 13-source CCTV camera ingestion pipeline
|
||||
│ │ ├── cctv_pipeline.py # 14-source CCTV camera ingestion pipeline
|
||||
│ │ ├── ssrf_guard.py # SSRF validation for operator recon fetches
|
||||
│ │ ├── sanctions/ofac.py # OpenSanctions OFAC SDN index
|
||||
│ │ ├── osint/lookups.py # Server-side recon lookups (Osiris port)
|
||||
│ │ ├── osint/openclaw_recon.py # OpenClaw dispatch for recon + entity_expand
|
||||
│ │ ├── osint_intel/resolve.py # Entity graph resolver (Wikidata + OFAC)
|
||||
│ │ ├── scm/suppliers.py # Supply-chain risk overlay
|
||||
│ │ ├── intel_feeds/ # Country risk index helpers
|
||||
│ │ ├── fetchers/malware.py # abuse.ch Feodo + URLhaus
|
||||
│ │ ├── fetchers/cyber_status.py # CISA KEV feed
|
||||
│ │ ├── fetchers/telegram_osint.py # Public Telegram channel scrape + geoparse
|
||||
│ │ ├── third_party/osiris/ # MIT attribution for Osiris-derived code
|
||||
│ │ ├── geopolitics.py # GDELT + Ukraine frontline + air alerts
|
||||
│ │ ├── region_dossier.py # Right-click country/city intelligence
|
||||
│ │ ├── radio_intercept.py # Police scanner feeds + OpenMHZ
|
||||
@@ -910,7 +1010,14 @@ Shadowbroker/
|
||||
│ │ ├── mesh_reputation.py # Node reputation scoring
|
||||
│ │ ├── mesh_oracle.py # Oracle consensus protocol
|
||||
│ │ └── mesh_secure_storage.py # Secure credential storage
|
||||
│ ├── routers/
|
||||
│ │ ├── osint.py # /api/osint/* recon routes (local operator)
|
||||
│ │ ├── entity_graph.py # /api/entity/expand
|
||||
│ │ ├── scm.py # /api/scm-suppliers
|
||||
│ │ └── intel_feeds.py # /api/malware, /api/cyber-threats, /api/telegram-feed, /api/country-risk
|
||||
├── frontend/
|
||||
│ ├── public/data/
|
||||
│ │ └── submarine-cables.json # Static undersea cable GeoJSON
|
||||
│ ├── src/
|
||||
│ │ ├── app/
|
||||
│ │ │ └── page.tsx # Main dashboard — state, polling, layout
|
||||
@@ -919,7 +1026,12 @@ Shadowbroker/
|
||||
│ │ ├── MeshChat.tsx # InfoNet / Mesh / Dead Drop chat panel
|
||||
│ │ ├── MeshTerminal.tsx # Draggable CLI terminal
|
||||
│ │ ├── NewsFeed.tsx # SIGINT feed + entity detail panels
|
||||
│ │ ├── WorldviewLeftPanel.tsx # Data layer toggles (35+ layers)
|
||||
│ │ ├── WorldviewLeftPanel.tsx # Data layer toggles (40+ layers)
|
||||
│ │ ├── ShodanPanel.tsx # Shodan device search overlay
|
||||
│ │ ├── ReconPanel.tsx # Server-side OSINT recon toolkit
|
||||
│ │ ├── ScmPanel.tsx # Supply-chain risk command panel
|
||||
│ │ ├── EntityGraphPanel.tsx # Entity graph on map selection
|
||||
│ │ ├── MaplibreViewer/popups/TelegramOsintPopup.tsx # Threat-intercept styled Telegram pin popups
|
||||
│ │ ├── WorldviewRightPanel.tsx # Search + filter sidebar
|
||||
│ │ ├── AdvancedFilterModal.tsx # Airport/country/owner filtering
|
||||
│ │ ├── MapLegend.tsx # Dynamic legend with all icons
|
||||
@@ -956,6 +1068,9 @@ MESH_SAR_EARTHDATA_TOKEN= # NASA Earthdata token (paired wit
|
||||
MESH_SAR_COPERNICUS_USER= # Copernicus Data Space user (SAR Mode B — EGMS / EMS)
|
||||
MESH_SAR_COPERNICUS_TOKEN= # Copernicus token (paired with user above)
|
||||
OPENCLAW_ACCESS_TIER=restricted # OpenClaw agent tier: "restricted" (read-only) or "full"
|
||||
GFW_API_TOKEN=your_gfw_token # Global Fishing Watch — fishing_activity layer (Settings → Maritime)
|
||||
TELEGRAM_OSINT_ENABLED=true # Telegram OSINT layer (default on)
|
||||
TELEGRAM_OSINT_CHANNELS=osintdefender,... # Comma-separated public channel slugs (see .env.example)
|
||||
|
||||
# Private-lane privacy-core pinning (required when Arti or RNS is enabled)
|
||||
PRIVACY_CORE_MIN_VERSION=0.1.0
|
||||
|
||||
+73
-14
@@ -18,6 +18,15 @@ AIS_API_KEY= # https://aisstream.io/ — free tier WebSocket key
|
||||
# AISHUB_USERNAME=
|
||||
# AISHUB_POLL_INTERVAL_MINUTES=20
|
||||
|
||||
# `python main.py` (uvicorn reload) binds 127.0.0.1:8000 by default so LAN clients
|
||||
# cannot reach a dev server with empty ADMIN_KEY (#375). Set true only when you
|
||||
# intentionally need 0.0.0.0 and understand the local-trust implications.
|
||||
# SHADOWBROKER_DEV_BIND_ALL=false
|
||||
#
|
||||
# Thread pool for GDELT, LiveUAMap, CCTV ingest, and slow-tier refresh batches.
|
||||
# Keeps heavy jobs from starving fast flight/ship workers (default 2).
|
||||
# SHADOWBROKER_HEAVY_FETCH_WORKERS=2
|
||||
|
||||
# Override allowed CORS origins (comma-separated). Defaults to localhost + LAN auto-detect.
|
||||
# CORS_ORIGINS=http://192.168.1.50:3000,https://my-domain.com
|
||||
|
||||
@@ -31,11 +40,9 @@ AIS_API_KEY= # https://aisstream.io/ — free tier WebSocket key
|
||||
# Requires MESH_DEBUG_MODE=true; do not enable this for ordinary use.
|
||||
# ALLOW_INSECURE_ADMIN=false
|
||||
|
||||
# Per-install operator handle. Round 7a: every outbound third-party API
|
||||
# call (Wikipedia, Wikidata, Nominatim, GDELT, OpenMHz, Broadcastify,
|
||||
# weather.gov, NUFORC, etc.) includes this handle in the User-Agent so
|
||||
# upstreams can rate-limit / contact the specific install instead of
|
||||
# treating every Shadowbroker user as one entity.
|
||||
# Per-install operator handle. Round 7a: outbound third-party API calls send
|
||||
# this handle as the User-Agent (e.g. operator-7f3a92), not a shared app name,
|
||||
# so upstreams rate-limit one install instead of blocking every user.
|
||||
#
|
||||
# Default empty -> a stable pseudonymous handle (e.g. "operator-7f3a92") is
|
||||
# auto-generated on first run and persisted to backend/data/operator_handle.json.
|
||||
@@ -43,10 +50,8 @@ AIS_API_KEY= # https://aisstream.io/ — free tier WebSocket key
|
||||
# set it here. Special characters are sanitized to dashes.
|
||||
# OPERATOR_HANDLE=
|
||||
|
||||
# Default outbound User-Agent for all third-party HTTP fetchers. Operators
|
||||
# who run a public relay and want a completely custom UA can set this; it
|
||||
# bypasses the per-operator helper entirely. Most installs should leave it
|
||||
# unset and use OPERATOR_HANDLE instead.
|
||||
# Full User-Agent override (replaces the operator handle entirely). Rare;
|
||||
# most installs should use OPERATOR_HANDLE only.
|
||||
# SHADOWBROKER_USER_AGENT=
|
||||
|
||||
# Nominatim-specific User-Agent override (OSM usage policy). Leave unset to
|
||||
@@ -66,20 +71,48 @@ AIS_API_KEY= # https://aisstream.io/ — free tier WebSocket key
|
||||
# FIMI_ENABLED=false
|
||||
#
|
||||
# Polymarket + Kalshi — US political/election prediction markets.
|
||||
# Default off; enable from Global Threat Intercept (MKT toggle) or set true here.
|
||||
# PREDICTION_MARKETS_ENABLED=false
|
||||
# When enabled, polls use a jittered schedule (not the fixed 5-minute slow tier):
|
||||
# PREDICTION_MARKETS_INTERVAL_MINUTES=7
|
||||
# PREDICTION_MARKETS_SCHEDULER_JITTER_S=240
|
||||
# PREDICTION_MARKETS_INITIAL_DELAY_MAX_S=180
|
||||
# PREDICTION_MARKETS_PRE_FETCH_JITTER_S=90
|
||||
# PREDICTION_MARKETS_PROVIDER_GAP_JITTER_S=45
|
||||
# MESH_POLYMARKET_PAGE_DELAY_JITTER_S=0.08
|
||||
# MESH_KALSHI_PAGE_DELAY_JITTER_S=0.2
|
||||
#
|
||||
# Finnhub fallback / yfinance — financial market data.
|
||||
# Set FINNHUB_API_KEY to enable Finnhub, or set FINANCIAL_ENABLED=true to allow
|
||||
# the unauthenticated yfinance fallback to call Yahoo Finance.
|
||||
# FINANCIAL_ENABLED=false
|
||||
#
|
||||
# NUFORC UAP sightings — huggingface.co dataset download.
|
||||
# NUFORC UAP map layer — live scrape from nuforc.org (rolling window, default 60 days).
|
||||
# Refreshed weekly (Mon 12:00 UTC); cache reused for up to 7 days between runs.
|
||||
# NUFORC_RECENT_DAYS=60
|
||||
# NUFORC_CACHE_TTL_HOURS=168
|
||||
# On Windows, live scrape uses Python requests by default; optional:
|
||||
# SHADOWBROKER_ENABLE_WINDOWS_CURL_FALLBACK=true
|
||||
# NUFORC enrichment index (HF dataset) is separate — opt-in only:
|
||||
# NUFORC_ENABLED=false
|
||||
#
|
||||
# News RSS aggregator — defaults ON. Set to "false" to disable all
|
||||
# configured news feeds (kill switch for the news layer).
|
||||
# NEWS_ENABLED=true
|
||||
|
||||
# Global Fishing Watch — fishing vessel activity events (Fishing Activity map layer).
|
||||
# Free API token from https://globalfishingwatch.org/our-apis/tokens
|
||||
# Without this the fishing_activity layer stays empty.
|
||||
# GFW_API_TOKEN=
|
||||
# Optional tuning — GFW can return 40k+ global events; defaults cap fetch for map paint.
|
||||
# GFW_EVENTS_PAGE_SIZE=500
|
||||
# GFW_EVENTS_MAX_PAGES=10
|
||||
# GFW_EVENTS_LOOKBACK_DAYS=7
|
||||
# GFW_EVENTS_TIMEOUT_S=90
|
||||
|
||||
# Windy Webcams global CCTV layer — free key from https://api.windy.com/webcams/docs
|
||||
# WINDY_API_KEY=
|
||||
|
||||
# LTA Singapore traffic cameras — leave blank to skip this data source.
|
||||
# LTA_ACCOUNT_KEY=
|
||||
|
||||
@@ -87,6 +120,12 @@ AIS_API_KEY= # https://aisstream.io/ — free tier WebSocket key
|
||||
# Free MAP_KEY from https://firms.modaps.eosdis.nasa.gov/map/#d:24hrs;@0.0,0.0,3.0z
|
||||
# FIRMS_MAP_KEY=
|
||||
|
||||
# Ukraine frontline mirror (GitHub). Default follows cyterat/deepstate-map-data@main.
|
||||
# Pin an immutable commit SHA so ingest cannot silently change if main is force-pushed (#362).
|
||||
# Example (verify on GitHub before use): main @ b479954e94696bc5622c7818fd20a64a699f4fe8
|
||||
# DEEPSTATE_MIRROR_COMMIT=b479954e94696bc5622c7818fd20a64a699f4fe8
|
||||
# DEEPSTATE_MIRROR_REPO=cyterat/deepstate-map-data
|
||||
|
||||
# Ukraine air raid alerts from alerts.in.ua — free token from https://alerts.in.ua/
|
||||
# ALERTS_IN_UA_TOKEN=
|
||||
|
||||
@@ -116,12 +155,16 @@ AIS_API_KEY= # https://aisstream.io/ — free tier WebSocket key
|
||||
# can identify per-install traffic instead of aggregated "ShadowBroker" hits.
|
||||
# Leave blank to send a generic UA. If you set MESHTASTIC_OPERATOR_CALLSIGN,
|
||||
# it is included in outbound headers to meshtastic.org by default so they
|
||||
# can rate-limit per-operator. Set MESHTASTIC_SEND_CALLSIGN_HEADER=false to
|
||||
# suppress the callsign while still using it locally (e.g. for APRS).
|
||||
# can rate-limit per-operator. Callsign is NOT sent upstream unless you opt in.
|
||||
# MESHTASTIC_OPERATOR_CALLSIGN=
|
||||
# MESHTASTIC_SEND_CALLSIGN_HEADER=true
|
||||
# MESHTASTIC_SEND_CALLSIGN_HEADER=false
|
||||
# MESH_MQTT_PSK= # hex-encoded, empty = default LongFast key
|
||||
|
||||
# LiveUAMap Playwright scraper (#348). Linux/macOS: on by default when Global
|
||||
# Incidents layer is active. Windows: off until the operator enables Global
|
||||
# Incidents in the UI (consent dialog) or sets SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER=true.
|
||||
# SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER=false forces off on all platforms.
|
||||
|
||||
# ── Mesh / Reticulum (RNS) ─────────────────────────────────────
|
||||
# Full-node / participant-node posture for public Infonet sync.
|
||||
# MESH_NODE_MODE=participant # participant | relay | perimeter
|
||||
@@ -184,7 +227,23 @@ AIS_API_KEY= # https://aisstream.io/ — free tier WebSocket key
|
||||
# MESH_GATE_SESSION_STREAM_MAX_GATES=16
|
||||
# MESH_BOOTSTRAP_DISABLED=false
|
||||
# MESH_BOOTSTRAP_MANIFEST_PATH=data/bootstrap_peers.json
|
||||
# MESH_BOOTSTRAP_SIGNER_PUBLIC_KEY=
|
||||
# Swarm discovery (signed peer manifest). Participants need only the public key;
|
||||
# the seed operator sets MESH_BOOTSTRAP_SIGNER_PRIVATE_KEY (never commit it).
|
||||
# Generate a fleet keypair: uv run python backend/scripts/bootstrap_manifest_helper.py generate-keypair
|
||||
# Public sb-testnet fleet defaults (auto-used when MESH_INFONET_FLEET_JOIN=true).
|
||||
# MESH_BOOTSTRAP_SIGNER_PUBLIC_KEY=ul1d0kj/ODPIp0OhHzX8eLAVXzJ3CVvzW1vn2IC6q3I=
|
||||
# MESH_INFONET_FLEET_JOIN=true
|
||||
# MESH_INFONET_FLEET_JOIN_DISABLED=false
|
||||
# MESH_BOOTSTRAP_SIGNER_PRIVATE_KEY= # seed only
|
||||
# MESH_BOOTSTRAP_SIGNER_ID=shadowbroker-seed
|
||||
# MESH_PEER_REGISTRY_ENABLED=true # seed only (auto-enabled when private key is set)
|
||||
# Headless relay compose sets MESH_INFONET_RELAY_AUTO_WORMHOLE=true; seed nodes with
|
||||
# MESH_BOOTSTRAP_SIGNER_PRIVATE_KEY also auto-enable Tor wormhole on startup.
|
||||
# MESH_INFONET_RELAY_AUTO_WORMHOLE=false
|
||||
# MESH_INFONET_RELAY_AUTO_WORMHOLE_DISABLED=false
|
||||
# MESH_SWARM_MANIFEST_TTL_S=14400
|
||||
# MESH_SWARM_MANIFEST_PULL_INTERVAL_S=300
|
||||
# MESH_PEER_REGISTRY_STALE_S=604800
|
||||
# Infonet/Wormhole fails closed to onion/RNS by default. Only enable clearnet
|
||||
# sync for local relay development or an explicitly public testnet.
|
||||
# MESH_INFONET_ALLOW_CLEARNET_SYNC=false
|
||||
|
||||
+3
-2
@@ -27,6 +27,7 @@ WORKDIR /app
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
ca-certificates \
|
||||
curl \
|
||||
git \
|
||||
tor \
|
||||
&& curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
|
||||
&& apt-get install -y --no-install-recommends nodejs \
|
||||
@@ -45,7 +46,7 @@ COPY uv.lock /workspace/uv.lock
|
||||
COPY backend/pyproject.toml /workspace/backend/pyproject.toml
|
||||
|
||||
# Install Python dependencies using the lockfile
|
||||
RUN cd /workspace/backend && uv sync --frozen --no-dev \
|
||||
RUN cd /workspace/backend && uv sync --frozen --no-dev --extra road-corridor \
|
||||
&& playwright install --with-deps chromium
|
||||
|
||||
# Copy backend source code
|
||||
@@ -72,7 +73,7 @@ ENV PRIVACY_CORE_LIB=/app/libprivacy_core.so
|
||||
# Create a non-root user for security
|
||||
# Grant write access to /app so the auto-updater can extract files
|
||||
# Pre-create /app/data so mounted volumes inherit correct ownership
|
||||
RUN adduser --system --uid 1001 backenduser \
|
||||
RUN adduser --system --uid 1001 --home /app backenduser \
|
||||
&& mkdir -p /app/data \
|
||||
&& chown -R backenduser /app \
|
||||
&& chmod -R u+w /app
|
||||
|
||||
+54
-30
@@ -113,8 +113,14 @@ def _scoped_admin_tokens() -> dict[str, list[str]]:
|
||||
return normalized
|
||||
|
||||
|
||||
def _request_scope_path(request: Request) -> str:
|
||||
"""Return the ASGI request-line path, not the Host-derived URL path."""
|
||||
scope = getattr(request, "scope", {}) or {}
|
||||
return str(scope.get("path") or "")
|
||||
|
||||
|
||||
def _required_scope_for_request(request: Request) -> str:
|
||||
path = str(request.url.path or "")
|
||||
path = _request_scope_path(request)
|
||||
if path.startswith("/api/wormhole/gate/"):
|
||||
return "gate"
|
||||
if path.startswith("/api/wormhole/dm/"):
|
||||
@@ -443,7 +449,7 @@ async def _verify_openclaw_hmac(request: Request) -> bool:
|
||||
|
||||
# Compute expected signature: HMAC-SHA256(secret, METHOD|path|ts|nonce|body_digest)
|
||||
method = str(request.method or "").upper()
|
||||
path = str(request.url.path or "")
|
||||
path = _request_scope_path(request)
|
||||
message = f"{method}|{path}|{ts_str}|{nonce}|{body_digest}"
|
||||
expected = hmac.new(
|
||||
secret.encode("utf-8"),
|
||||
@@ -515,33 +521,32 @@ _KNOWN_COMPROMISED_PEER_PUSH_SECRET_SHA256 = (
|
||||
def _validate_admin_startup() -> None:
|
||||
admin_key = _current_admin_key()
|
||||
|
||||
if not admin_key or len(admin_key) < 32:
|
||||
import secrets
|
||||
if not admin_key:
|
||||
logger.warning(
|
||||
"ADMIN_KEY is not set. Local-operator/admin endpoints will reject "
|
||||
"remote callers until ADMIN_KEY is configured."
|
||||
)
|
||||
return
|
||||
|
||||
reason = "not set" if not admin_key else f"too short ({len(admin_key)} chars, minimum 32)"
|
||||
new_key = secrets.token_hex(32) # 64-char hex string
|
||||
if len(admin_key) < 32:
|
||||
reason = f"too short ({len(admin_key)} chars, minimum 32)"
|
||||
try:
|
||||
from routers.ai_intel import _write_env_value
|
||||
|
||||
_write_env_value("ADMIN_KEY", new_key)
|
||||
os.environ["ADMIN_KEY"] = new_key
|
||||
logger.info(
|
||||
"ADMIN_KEY was %s — auto-generated a strong 64-character key and "
|
||||
"saved it to .env. Admin/mesh endpoints are now secured.",
|
||||
reason,
|
||||
)
|
||||
# Clear settings cache so the rest of startup picks up the new key
|
||||
try:
|
||||
get_settings.cache_clear()
|
||||
except Exception:
|
||||
pass
|
||||
except Exception as exc:
|
||||
debug_mode = bool(getattr(get_settings(), "MESH_DEBUG_MODE", False))
|
||||
except Exception:
|
||||
debug_mode = False
|
||||
if debug_mode:
|
||||
logger.warning(
|
||||
"ADMIN_KEY is %s and could not auto-generate: %s. "
|
||||
"Admin/mesh endpoints may be unavailable.",
|
||||
"ADMIN_KEY is %s. Debug mode is enabled, so startup will continue, "
|
||||
"but production deployments must use a 32+ character key.",
|
||||
reason,
|
||||
exc,
|
||||
)
|
||||
return
|
||||
logger.error(
|
||||
"ADMIN_KEY is %s. Refusing to start because auto-generating a backend-only "
|
||||
"replacement would desynchronize the frontend and backend containers.",
|
||||
reason,
|
||||
)
|
||||
raise SystemExit(1)
|
||||
|
||||
|
||||
def _validate_insecure_admin_startup() -> None:
|
||||
@@ -744,8 +749,7 @@ def _is_debug_test_request(request: Request) -> bool:
|
||||
if not _debug_mode_enabled():
|
||||
return False
|
||||
client_host = (request.client.host or "").lower() if request.client else ""
|
||||
url_host = (request.url.hostname or "").lower() if request.url else ""
|
||||
return client_host == "test" or url_host == "test"
|
||||
return client_host == "test"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -858,7 +862,9 @@ _ROUTE_TRANSPORT_POLICY: dict[tuple[str, str], RouteTransportPolicy] = {
|
||||
("POST", "/api/wormhole/gate/messages/decrypt"): _local_only_route_policy("private_control_only"),
|
||||
# ── Wormhole DM (strong) ──────────────────────────────────────────
|
||||
("POST", "/api/wormhole/dm/compose"): _local_only_route_policy("private_control_only"),
|
||||
("POST", "/api/wormhole/dm/connect-contact"): _local_only_route_policy("private_control_only"),
|
||||
("POST", "/api/wormhole/dm/decrypt"): _local_only_route_policy("private_control_only"),
|
||||
("POST", "/api/wormhole/dm/mls-key-package"): _local_only_route_policy("private_control_only"),
|
||||
("POST", "/api/wormhole/dm/register-key"): _local_only_route_policy("private_control_only"),
|
||||
("POST", "/api/wormhole/dm/prekey/register"): _local_only_route_policy("private_control_only"),
|
||||
("POST", "/api/wormhole/dm/bootstrap-encrypt"): _local_only_route_policy("private_control_only"),
|
||||
@@ -1397,10 +1403,28 @@ def _peer_hmac_url_from_request(request: Request) -> str:
|
||||
header_url = normalize_peer_url(str(request.headers.get("x-peer-url", "") or ""))
|
||||
if header_url:
|
||||
return header_url
|
||||
if not request.url:
|
||||
return ""
|
||||
base_url = f"{request.url.scheme}://{request.url.netloc}".rstrip("/")
|
||||
return normalize_peer_url(base_url)
|
||||
return ""
|
||||
|
||||
|
||||
def _verify_peer_transport_hmac(request: Request, body_bytes: bytes) -> bool:
|
||||
"""Verify HMAC-SHA256 peer authentication without an allowlist check."""
|
||||
provided = str(request.headers.get("x-peer-hmac", "") or "").strip()
|
||||
if not provided:
|
||||
return False
|
||||
|
||||
peer_url = _peer_hmac_url_from_request(request)
|
||||
if not peer_url:
|
||||
return False
|
||||
peer_key = resolve_peer_key_for_url(peer_url)
|
||||
if not peer_key:
|
||||
return False
|
||||
|
||||
expected = _hmac_mod.new(
|
||||
peer_key,
|
||||
body_bytes,
|
||||
_hashlib_mod.sha256,
|
||||
).hexdigest()
|
||||
return _hmac_mod.compare_digest(provided.lower(), expected.lower())
|
||||
|
||||
|
||||
def _verify_peer_push_hmac(request: Request, body_bytes: bytes) -> bool:
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
},
|
||||
{
|
||||
"name": "BBC",
|
||||
"url": "http://feeds.bbci.co.uk/news/world/rss.xml",
|
||||
"url": "https://feeds.bbci.co.uk/news/world/rss.xml",
|
||||
"weight": 3
|
||||
},
|
||||
{
|
||||
@@ -47,7 +47,7 @@
|
||||
},
|
||||
{
|
||||
"name": "Xinhua",
|
||||
"url": "http://www.news.cn/english/rss/worldrss.xml",
|
||||
"url": "https://www.news.cn/english/rss/worldrss.xml",
|
||||
"weight": 2
|
||||
},
|
||||
{
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:72b69418aa860a0d92ccae398a08722bc85e64a992b5515dd7bf9ae9f79f2fd1
|
||||
size 107194128
|
||||
@@ -46,5 +46,15 @@
|
||||
"ShadowBroker_v0.9.81.zip": "f81f454bdc88e9a32c351df38212b8cfa624704d65764b971bb091eef62259c6",
|
||||
"ShadowBroker_0.9.81_x64-setup.exe": "25e9a95d0d8ce959a7d08fe8e7406772ae24b596652793e81d1de5d02510a5a6",
|
||||
"ShadowBroker_0.9.81_x64_en-US.msi": "34e655fc0c0f195ee4ac978f228a4b2b9d5565253b8771aca9ef4693409e9e70"
|
||||
},
|
||||
"v0.9.82": {
|
||||
"ShadowBroker_v0.9.82.zip": "202ab043465741dcc06de57c19ec8314904332f8e818b891d7174655719d084c",
|
||||
"ShadowBroker_0.9.82_x64-setup.exe": "0eb9f2bda02ab691b39687641abc97e6bfb507b42f48de21970ad7dfb4ea15fc",
|
||||
"ShadowBroker_0.9.82_x64_en-US.msi": "ced08f930171c0c08009a958cc30b0171a09f982230fc217c6808c2ed7ab2e30"
|
||||
},
|
||||
"v0.9.83": {
|
||||
"ShadowBroker_v0.9.83.zip": "53f56631731ad3cdc7be68df09bedd6570ed91ecda6fa57c39651098e15666c7",
|
||||
"ShadowBroker_0.9.83_x64-setup.exe": "d62170af4b9df0b190832b7bb3ad6bfe8a7ac01472f2c7b39cf2a1b61edc7492",
|
||||
"ShadowBroker_0.9.83_x64_en-US.msi": "b664cc0003a29f7ce88b04c2b425643dbe7ed897342fc6e9a2378bc1910c6850"
|
||||
}
|
||||
}
|
||||
|
||||
+550
-485
File diff suppressed because it is too large
Load Diff
+18
-6
@@ -7,15 +7,15 @@ py-modules = []
|
||||
|
||||
[project]
|
||||
name = "backend"
|
||||
version = "0.9.81"
|
||||
version = "0.9.83"
|
||||
requires-python = ">=3.10"
|
||||
dependencies = [
|
||||
"apscheduler==3.10.3",
|
||||
"beautifulsoup4>=4.9.0",
|
||||
"cachetools==5.5.2",
|
||||
"cryptography>=41.0.0",
|
||||
"cryptography>=46.0.7",
|
||||
"defusedxml>=0.7.1",
|
||||
"fastapi==0.115.12",
|
||||
"fastapi==0.136.3",
|
||||
"feedparser==6.0.10",
|
||||
"httpx==0.28.1",
|
||||
"playwright==1.59.0",
|
||||
@@ -24,7 +24,7 @@ dependencies = [
|
||||
"pydantic-settings==2.8.1",
|
||||
"pystac-client==0.8.6",
|
||||
"python-dotenv==1.2.2",
|
||||
"requests==2.31.0",
|
||||
"requests==2.33.0",
|
||||
"PySocks==1.7.1",
|
||||
"reverse-geocoder==1.5.1",
|
||||
"sgp4==2.25",
|
||||
@@ -33,17 +33,29 @@ dependencies = [
|
||||
"paho-mqtt>=1.6.0,<2.0.0",
|
||||
"PyNaCl>=1.5.0",
|
||||
"slowapi==0.1.9",
|
||||
"starlette==1.0.1",
|
||||
"vaderSentiment>=3.3.0",
|
||||
"uvicorn==0.34.0",
|
||||
"yfinance==1.3.0",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
road-corridor = [
|
||||
"geopandas>=1.0.0",
|
||||
"imageio>=2.34.0",
|
||||
"osmnx>=2.0.0",
|
||||
"rasterio>=1.4.0",
|
||||
"scikit-learn>=1.5.0",
|
||||
"sentinelhub>=3.10.0",
|
||||
"shapely>=2.0.0",
|
||||
]
|
||||
|
||||
[dependency-groups]
|
||||
dev = ["pytest>=8.3.4", "pytest-asyncio==0.25.0", "ruff>=0.9.0", "black>=24.0.0"]
|
||||
dev = ["pytest>=9.0.3", "pytest-asyncio>=1.4.0", "ruff>=0.9.0", "black>=24.0.0"]
|
||||
|
||||
[tool.ruff.lint]
|
||||
# The current backend carries historical style debt in large legacy modules.
|
||||
# Keep CI focused on actionable correctness checks for the v0.9.81 release.
|
||||
# Keep CI focused on actionable correctness checks for the v0.9.82 release.
|
||||
ignore = ["E401", "E402", "E701", "E731", "E741", "F401", "F402", "F541", "F811", "F841"]
|
||||
|
||||
[tool.black]
|
||||
|
||||
@@ -0,0 +1,230 @@
|
||||
"""Local-operator PTY WebSocket for the Mesh Chat agent shell."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import fcntl
|
||||
import hmac
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import pty
|
||||
import select
|
||||
import signal
|
||||
import struct
|
||||
import sys
|
||||
import termios
|
||||
from typing import Any
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Query, WebSocket, WebSocketDisconnect
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from auth import (
|
||||
_current_admin_key,
|
||||
_debug_mode_enabled,
|
||||
_is_trusted_local_runtime_host,
|
||||
require_local_operator,
|
||||
)
|
||||
from services.agent_shell_settings import (
|
||||
get_agent_shell_settings,
|
||||
set_agent_shell_working_directory,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
router = APIRouter(tags=["agent-shell"])
|
||||
|
||||
|
||||
class AgentShellSettingsUpdate(BaseModel):
|
||||
working_directory: str = Field(min_length=1)
|
||||
|
||||
|
||||
def _set_winsize(fd: int, rows: int, cols: int) -> None:
|
||||
winsize = struct.pack("HHHH", rows, cols, 0, 0)
|
||||
fcntl.ioctl(fd, termios.TIOCSWINSZ, winsize)
|
||||
|
||||
|
||||
def _published_local_dashboard_ws(ws: WebSocket) -> bool:
|
||||
"""Browser → published Docker port appears as a bridge IP, not loopback.
|
||||
|
||||
For the operator shell only, also accept when the upgrade request clearly
|
||||
targets the local dashboard (Host/Origin on localhost).
|
||||
"""
|
||||
host_header = str(ws.headers.get("host") or "").strip().lower()
|
||||
host_name = host_header.split(":", 1)[0]
|
||||
if host_name in {"127.0.0.1", "localhost", "::1"}:
|
||||
return True
|
||||
|
||||
origin = str(ws.headers.get("origin") or "").strip().lower()
|
||||
if origin.startswith("http://127.0.0.1:") or origin.startswith("http://localhost:"):
|
||||
return True
|
||||
if origin.startswith("https://127.0.0.1:") or origin.startswith("https://localhost:"):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
async def _authorize_agent_shell_ws(ws: WebSocket, admin_key_query: str = "") -> None:
|
||||
host = (ws.client.host or "").lower() if ws.client else ""
|
||||
if (
|
||||
_is_trusted_local_runtime_host(host)
|
||||
or _published_local_dashboard_ws(ws)
|
||||
or (_debug_mode_enabled() and host == "test")
|
||||
):
|
||||
return
|
||||
admin_key = _current_admin_key()
|
||||
presented = str(admin_key_query or ws.headers.get("x-admin-key", "") or "").strip()
|
||||
if admin_key and presented and hmac.compare_digest(presented.encode(), admin_key.encode()):
|
||||
return
|
||||
await ws.close(code=4403, reason="local operator access only")
|
||||
raise WebSocketDisconnect()
|
||||
|
||||
|
||||
def _resolve_shell_cwd(requested: str) -> str:
|
||||
requested = str(requested or "").strip()
|
||||
if requested:
|
||||
resolved = os.path.abspath(os.path.expanduser(requested))
|
||||
if os.path.isdir(resolved):
|
||||
return resolved
|
||||
return get_agent_shell_settings()["working_directory"]
|
||||
|
||||
|
||||
def _default_shell() -> str:
|
||||
if sys.platform == "win32":
|
||||
return os.environ.get("COMSPEC", "cmd.exe")
|
||||
return os.environ.get("SHELL", "/bin/bash")
|
||||
|
||||
|
||||
async def _relay_pty(master_fd: int, proc: asyncio.subprocess.Process, ws: WebSocket) -> None:
|
||||
loop = asyncio.get_running_loop()
|
||||
while True:
|
||||
if proc.returncode is not None:
|
||||
break
|
||||
try:
|
||||
readable, _, _ = await loop.run_in_executor(
|
||||
None, lambda: select.select([master_fd], [], [], 0.05)
|
||||
)
|
||||
except Exception:
|
||||
break
|
||||
if master_fd in readable:
|
||||
try:
|
||||
chunk = os.read(master_fd, 4096)
|
||||
except OSError:
|
||||
break
|
||||
if not chunk:
|
||||
break
|
||||
await ws.send_bytes(chunk)
|
||||
try:
|
||||
message = await asyncio.wait_for(ws.receive(), timeout=0.05)
|
||||
except asyncio.TimeoutError:
|
||||
continue
|
||||
if message.get("type") == "websocket.disconnect":
|
||||
break
|
||||
if message.get("type") != "websocket.receive":
|
||||
continue
|
||||
if message.get("bytes"):
|
||||
os.write(master_fd, message["bytes"])
|
||||
continue
|
||||
text = message.get("text")
|
||||
if not text:
|
||||
continue
|
||||
try:
|
||||
payload = json.loads(text)
|
||||
except json.JSONDecodeError:
|
||||
os.write(master_fd, text.encode("utf-8", errors="replace"))
|
||||
continue
|
||||
if payload.get("type") == "resize":
|
||||
rows = int(payload.get("rows") or 24)
|
||||
cols = int(payload.get("cols") or 80)
|
||||
_set_winsize(master_fd, max(rows, 2), max(cols, 2))
|
||||
|
||||
|
||||
@router.get("/api/agent-shell/settings", dependencies=[Depends(require_local_operator)])
|
||||
async def read_agent_shell_settings() -> dict[str, Any]:
|
||||
return get_agent_shell_settings()
|
||||
|
||||
|
||||
@router.put("/api/agent-shell/settings", dependencies=[Depends(require_local_operator)])
|
||||
async def write_agent_shell_settings(body: AgentShellSettingsUpdate) -> dict[str, Any]:
|
||||
try:
|
||||
return set_agent_shell_working_directory(body.working_directory)
|
||||
except ValueError as exc:
|
||||
detail = str(exc)
|
||||
if detail == "working_directory_not_found":
|
||||
raise HTTPException(status_code=400, detail="Working directory does not exist") from exc
|
||||
raise HTTPException(status_code=400, detail="Working directory is required") from exc
|
||||
|
||||
|
||||
@router.websocket("/api/agent-shell/ws")
|
||||
async def agent_shell_websocket(
|
||||
ws: WebSocket,
|
||||
cwd: str = Query(default=""),
|
||||
cols: int = Query(default=80),
|
||||
rows: int = Query(default=24),
|
||||
admin_key: str = Query(default=""),
|
||||
) -> None:
|
||||
await ws.accept()
|
||||
try:
|
||||
await _authorize_agent_shell_ws(ws, admin_key)
|
||||
except WebSocketDisconnect:
|
||||
return
|
||||
|
||||
if sys.platform == "win32":
|
||||
await ws.send_text(
|
||||
json.dumps(
|
||||
{
|
||||
"type": "error",
|
||||
"message": "Host PTY is not available on Windows backend builds yet. Use the ShadowBroker desktop app or run the backend in Docker/Linux for an embedded shell.",
|
||||
}
|
||||
)
|
||||
)
|
||||
await ws.close(code=1011)
|
||||
return
|
||||
|
||||
shell_cwd = _resolve_shell_cwd(cwd)
|
||||
shell = _default_shell()
|
||||
master_fd, slave_fd = pty.openpty()
|
||||
_set_winsize(master_fd, max(rows, 2), max(cols, 2))
|
||||
|
||||
env = os.environ.copy()
|
||||
env.setdefault("TERM", "xterm-256color")
|
||||
env.setdefault("COLORTERM", "truecolor")
|
||||
home = shell_cwd if os.path.isdir(shell_cwd) else "/app"
|
||||
env["HOME"] = home
|
||||
env["USER"] = env.get("USER") or "operator"
|
||||
path_prefixes = [
|
||||
os.path.join(home, ".local", "bin"),
|
||||
os.path.join(home, ".hermes", "bin"),
|
||||
]
|
||||
path = env.get("PATH", "")
|
||||
for prefix in path_prefixes:
|
||||
if os.path.isdir(prefix):
|
||||
path = f"{prefix}:{path}" if path else prefix
|
||||
env["PATH"] = path
|
||||
|
||||
proc = await asyncio.create_subprocess_exec(
|
||||
shell,
|
||||
stdin=slave_fd,
|
||||
stdout=slave_fd,
|
||||
stderr=slave_fd,
|
||||
cwd=shell_cwd,
|
||||
env=env,
|
||||
preexec_fn=os.setsid,
|
||||
)
|
||||
os.close(slave_fd)
|
||||
|
||||
try:
|
||||
await _relay_pty(master_fd, proc, ws)
|
||||
finally:
|
||||
try:
|
||||
os.close(master_fd)
|
||||
except OSError:
|
||||
pass
|
||||
if proc.returncode is None:
|
||||
try:
|
||||
os.killpg(proc.pid, signal.SIGHUP)
|
||||
except ProcessLookupError:
|
||||
pass
|
||||
try:
|
||||
await asyncio.wait_for(proc.wait(), timeout=2.0)
|
||||
except asyncio.TimeoutError:
|
||||
proc.kill()
|
||||
await proc.wait()
|
||||
@@ -1590,7 +1590,7 @@ async def agent_tool_manifest(request: Request):
|
||||
|
||||
return {
|
||||
"ok": True,
|
||||
"version": "0.9.81",
|
||||
"version": "0.9.82",
|
||||
"access_tier": access_tier,
|
||||
"available_commands": available_commands,
|
||||
"transport": {
|
||||
@@ -1705,11 +1705,12 @@ async def agent_tool_manifest(request: Request):
|
||||
{
|
||||
"name": "search_news",
|
||||
"type": "read",
|
||||
"description": "Search news and event layers server-side by keyword. Includes news, GDELT, CrowdThreat, and major incident/event feeds without pulling the full slow telemetry feed.",
|
||||
"description": "Search news and event layers server-side by keyword. Includes news, GDELT, CrowdThreat, Telegram OSINT, and major incident/event feeds without pulling the full slow telemetry feed.",
|
||||
"parameters": {
|
||||
"query": {"type": "string", "required": True, "description": "Keyword or phrase to search for"},
|
||||
"limit": {"type": "integer", "required": False, "description": "Max results (default 10, max 50)"},
|
||||
"include_gdelt": {"type": "boolean", "required": False, "description": "Include GDELT matches (default true)"},
|
||||
"include_telegram": {"type": "boolean", "required": False, "description": "Include Telegram OSINT channel posts (default true)"},
|
||||
"compact": {"type": "boolean", "required": False, "description": "If true, strips empty/None fields from each result and rounds lat/lng to 3 decimals. Response includes format: 'compressed_v1'."},
|
||||
},
|
||||
"returns": "{results: [{source_layer, title, summary, source, link, lat, lng, risk_score}], version: int, truncated: bool}",
|
||||
@@ -1743,6 +1744,55 @@ async def agent_tool_manifest(request: Request):
|
||||
},
|
||||
"returns": "{center, radius_km, nearby, topic_news, context_layers}",
|
||||
},
|
||||
{
|
||||
"name": "osint_lookup",
|
||||
"type": "read",
|
||||
"description": "Run a passive OSINT recon lookup server-side (same backends as the Recon panel). SSRF-guarded outbound proxies for IP geolocation, DNS, WHOIS, certs, BGP/ASN, sanctions, CVE, MAC vendor, GitHub profile, breach checks, and threat feeds.",
|
||||
"parameters": {
|
||||
"tool": {"type": "string", "required": True, "description": "Lookup type: ip, dns, whois, certs, threats, bgp, sanctions, cve, mac, github, leaks, sweep_init"},
|
||||
"ip": {"type": "string", "required": False, "description": "IPv4/IPv6 for ip or sweep_init"},
|
||||
"domain": {"type": "string", "required": False, "description": "Domain for dns, whois, certs"},
|
||||
"query": {"type": "string", "required": False, "description": "Generic query (BGP ASN, sanctions name, optional threats filter)"},
|
||||
"cve": {"type": "string", "required": False, "description": "CVE id for cve lookup"},
|
||||
"mac": {"type": "string", "required": False, "description": "MAC address for mac lookup"},
|
||||
"username": {"type": "string", "required": False, "description": "GitHub username"},
|
||||
"email": {"type": "string", "required": False, "description": "Email for breach/leak lookup"},
|
||||
"schema": {"type": "string", "required": False, "description": "Sanctions schema filter: Person, Organization, Company, Vessel, Airplane, LegalEntity"},
|
||||
"limit": {"type": "integer", "required": False, "description": "Sanctions result cap (default 25, max 100)"},
|
||||
"cidr": {"type": "integer", "required": False, "description": "CIDR mask for sweep_init (24-32, default 24)"},
|
||||
},
|
||||
"returns": "Tool-specific JSON (geo, DNS records, WHOIS, sanctions hits, CVE details, etc.)",
|
||||
},
|
||||
{
|
||||
"name": "osint_tools",
|
||||
"type": "read",
|
||||
"description": "List available OSINT recon tools, entity-expand types, and sanctions schemas.",
|
||||
"parameters": {},
|
||||
"returns": "{tools: [...], entity_types: [...], sanctions_schemas: [...], notes: {...}}",
|
||||
},
|
||||
{
|
||||
"name": "entity_expand",
|
||||
"type": "read",
|
||||
"description": "Expand an entity relationship graph around an aircraft, vessel, IP, company, person, or country. Same backend as /api/entity/expand.",
|
||||
"parameters": {
|
||||
"type": {"type": "string", "required": True, "description": "Entity type: aircraft, vessel, company, person, ip, country"},
|
||||
"id": {"type": "string", "required": True, "description": "Entity identifier (tail number, MMSI, IP, company name, etc.)"},
|
||||
"registration": {"type": "string", "required": False, "description": "Aircraft registration hint"},
|
||||
"model": {"type": "string", "required": False, "description": "Aircraft model hint"},
|
||||
"icao24": {"type": "string", "required": False, "description": "ICAO24 hex for aircraft"},
|
||||
},
|
||||
"returns": "{nodes: [...], links: [...]}",
|
||||
},
|
||||
{
|
||||
"name": "osint_sweep",
|
||||
"type": "write",
|
||||
"description": "Active subnet device discovery via Shodan InternetDB (ports, vulns, hostnames). Requires full OpenClaw access tier. Private/reserved IPs blocked.",
|
||||
"parameters": {
|
||||
"ip": {"type": "string", "required": True, "description": "Public IPv4 anchor for the sweep"},
|
||||
"cidr": {"type": "integer", "required": False, "description": "Subnet size /24-/32 (default 24)"},
|
||||
},
|
||||
"returns": "{center, target_ip, cidr, subnet, devices, summary, sweep_time_ms}",
|
||||
},
|
||||
{
|
||||
"name": "what_changed",
|
||||
"type": "read",
|
||||
@@ -2194,6 +2244,11 @@ async def agent_tool_manifest(request: Request):
|
||||
"Prefer compact lookups first: search_telemetry, find_flights, find_ships, search_news, entities_near, get_layer_slice. Use get_telemetry/get_slow_telemetry/get_report only when focused commands are insufficient.",
|
||||
"ShadowBroker does expose UAP sightings, wastewater, and tracked_flights/VIP aircraft when those layers are populated. Verify with get_summary or get_layer_slice before claiming a layer is absent.",
|
||||
"ShadowBroker also exposes fishing_activity, which is the fishing-vessel activity layer backed by Global Fishing Watch data when GFW_API_TOKEN is configured. Do not confuse it with the AIS ships layer.",
|
||||
"telegram_osint, malware_threats, cyber_threats, and scm_suppliers are live map layers. Use get_summary or get_layer_slice(['telegram_osint']) before claiming they are absent. Aliases: telegram, malware/botnet, cyber/cisa/kev, scm/suppliers.",
|
||||
"search_telemetry and search_news both index Telegram OSINT posts. For malware C2, botnet IPs, CISA KEV CVEs, or semiconductor suppliers, use search_telemetry or get_layer_slice on the matching layer.",
|
||||
"The Recon toolkit is available via osint_lookup: IP geolocation, DNS, WHOIS, certs, BGP, sanctions, CVE, MAC vendor, GitHub, breach checks, threat feeds. Call osint_tools first to list supported tools.",
|
||||
"entity_expand builds relationship graphs for aircraft, vessels, IPs, companies, people, and countries — use after resolving an entity from telemetry or osint_lookup.",
|
||||
"osint_sweep runs active subnet discovery (Shodan InternetDB) and requires full OpenClaw access tier. Use osint_lookup tool=sweep_init for passive geolocation context only.",
|
||||
"Use search_telemetry as the Google-style entry point whenever the user gives you a person, place, company, topic, owner, nickname, or natural-language phrase and you do not already know the source layer.",
|
||||
"Example: for 'Where is Jerry Jones yacht?' search 'Jerry Jones' across all telemetry first, identify the ship match, then refine with find_ships or raw layer context only if needed.",
|
||||
"For fuzzy natural-language lookups like 'Patriots jet' or 'Jerry Jones yacht', use search_telemetry first and inspect the ranked candidate list before making a hard claim.",
|
||||
@@ -2221,12 +2276,14 @@ async def agent_tool_manifest(request: Request):
|
||||
async def api_capabilities(request: Request):
|
||||
"""Return full API manifest so the agent knows every available endpoint."""
|
||||
from services.openclaw_channel import READ_COMMANDS, WRITE_COMMANDS, detect_tier
|
||||
from services.openclaw_routing import routing_manifest
|
||||
from services.config import get_settings
|
||||
tier = detect_tier()
|
||||
access_tier = str(get_settings().OPENCLAW_ACCESS_TIER or "restricted").strip().lower()
|
||||
return {
|
||||
"ok": True,
|
||||
"version": "0.9.81",
|
||||
"version": "0.9.82",
|
||||
"routing": routing_manifest(),
|
||||
"auth": {
|
||||
"method": "HMAC-SHA256",
|
||||
"headers": ["X-SB-Timestamp", "X-SB-Nonce", "X-SB-Signature"],
|
||||
@@ -2342,8 +2399,16 @@ async def api_capabilities(request: Request):
|
||||
"description": "Compact server-side ship search by MMSI/IMO/name/query, including yacht-owner enrichment.",
|
||||
},
|
||||
"find_entity": {
|
||||
"args": {"query": "str (optional)", "entity_type": "aircraft|ship|person|event|infrastructure (optional)", "callsign": "str (optional)", "registration": "str (optional)", "icao24": "str (optional)", "mmsi": "str (optional)", "imo": "str (optional)", "name": "str (optional)", "owner": "str (optional)", "layers": "list[str] (optional)", "limit": "int (default 10)"},
|
||||
"description": "Exact-first resolver for planes, ships, operators, callsigns, registrations, MMSI/IMO, and named entities. Use before tracking to avoid fuzzy prompt matching.",
|
||||
"args": {"query": "str (optional)", "entity_type": "aircraft|ship|person|event|infrastructure (optional)", "callsign": "str (optional)", "registration": "str (optional)", "icao24": "str (optional)", "mmsi": "str (optional)", "imo": "str (optional)", "name": "str (optional)", "owner": "str (optional)", "layers": "list[str] (optional)", "limit": "int (default 10)", "fallback_search": "bool (default false)", "confirm_fuzzy": "bool (alias for fallback_search)"},
|
||||
"description": "Exact-first resolver for planes, ships, operators, callsigns, registrations, MMSI/IMO, and named entities. Skips fuzzy search unless fallback_search=true or no exact match.",
|
||||
},
|
||||
"route_query": {
|
||||
"args": {"text": "str", "lat": "float (optional)", "lng": "float (optional)", "radius_km": "float (default 50)", "compact": "bool (default true)"},
|
||||
"description": "Deterministic intent router — returns recommended fast command, alternates, and latency estimate. Preferred entry for natural-language reads.",
|
||||
},
|
||||
"run_playbook": {
|
||||
"args": {"name": "str", "query": "str (optional)", "lat": "float (optional)", "lng": "float (optional)"},
|
||||
"description": "Execute a named batch plan (hot_snapshot, morning_brief, monitor_heartbeat, track_snapshot, area_brief, entity_recon).",
|
||||
},
|
||||
"correlate_entity": {
|
||||
"args": {"query": "str (optional)", "entity_type": "str (optional)", "callsign": "str (optional)", "registration": "str (optional)", "icao24": "str (optional)", "mmsi": "str (optional)", "imo": "str (optional)", "name": "str (optional)", "owner": "str (optional)", "radius_km": "float (default 100)", "limit": "int (default 10)"},
|
||||
@@ -2354,13 +2419,29 @@ async def api_capabilities(request: Request):
|
||||
"description": "Universal compact search across telemetry when the entity type or source layer is not obvious.",
|
||||
},
|
||||
"search_news": {
|
||||
"args": {"query": "str", "limit": "int (default 10)", "include_gdelt": "bool (default true)"},
|
||||
"description": "Search news and event layers by keyword without pulling the whole slow feed.",
|
||||
"args": {"query": "str", "limit": "int (default 10)", "include_gdelt": "bool (default true)", "include_telegram": "bool (default true)"},
|
||||
"description": "Search news and event layers by keyword without pulling the whole slow feed. Includes Telegram OSINT when include_telegram is true.",
|
||||
},
|
||||
"entities_near": {
|
||||
"args": {"lat": "float", "lng": "float", "radius_km": "float (default 50)", "entity_types": "list[str] (optional)", "limit": "int (default 25)"},
|
||||
"description": "Compact proximity search around a point across selected layers.",
|
||||
},
|
||||
"osint_lookup": {
|
||||
"args": {"tool": "str (ip|dns|whois|certs|threats|bgp|sanctions|cve|mac|github|leaks|sweep_init)", "...": "tool-specific params"},
|
||||
"description": "Passive OSINT recon lookup — same backends as the Recon panel.",
|
||||
},
|
||||
"osint_tools": {
|
||||
"args": {},
|
||||
"description": "List available recon tools and entity-expand types.",
|
||||
},
|
||||
"entity_expand": {
|
||||
"args": {"type": "str", "id": "str", "registration": "str (optional)", "icao24": "str (optional)"},
|
||||
"description": "Entity relationship graph expansion.",
|
||||
},
|
||||
"osint_sweep": {
|
||||
"args": {"ip": "str", "cidr": "int (default 24)"},
|
||||
"description": "Active subnet scan — requires full access tier.",
|
||||
},
|
||||
"brief_area": {
|
||||
"args": {"lat": "float", "lng": "float", "radius_km": "float (default 50)", "entity_types": "list[str] (optional)", "query": "str (optional)", "limit": "int (default 25)", "context_limit": "int (default 10)"},
|
||||
"description": "One compact area brief: nearby aircraft/ships/entities, optional topic news, and selected context layers.",
|
||||
@@ -2507,7 +2588,8 @@ async def api_capabilities(request: Request):
|
||||
"layers are serialized, unchanged layers transfer zero bytes. The client tracks versions "
|
||||
"automatically from SSE events and previous responses. "
|
||||
"3) Pass compact=true on every read command for compressed_v1 responses (~60-90% smaller). "
|
||||
"4) Use targeted commands first (find_flights, search_telemetry, entities_near). "
|
||||
"4) Use route_query / find_entity / run_playbook before search_telemetry. "
|
||||
"Expensive commands require confirm_expensive=true. "
|
||||
"Reserve get_telemetry/get_slow_telemetry for rare full-context pulls.",
|
||||
"pins": "Pins are server-side, NOT localStorage. Use place_pin command or POST /api/ai/pins. The agent can place and delete pins.",
|
||||
"tracking": "To track a specific aircraft without polling: use add_watch with track_callsign or track_registration. Over SSE, you'll get instant push alerts.",
|
||||
@@ -2637,6 +2719,7 @@ def _connect_info_metadata(settings) -> dict:
|
||||
"get_telemetry", "get_pins", "satellite_images",
|
||||
"news_near", "ai_summary", "ai_report",
|
||||
"timemachine_list", "timemachine_view",
|
||||
"infonet_status", "list_gates", "read_gate_messages", "poll_dms",
|
||||
],
|
||||
},
|
||||
"full": {
|
||||
@@ -2647,6 +2730,8 @@ def _connect_info_metadata(settings) -> dict:
|
||||
"satellite_images", "news_near", "data_injection",
|
||||
"ai_summary", "ai_report", "timemachine_snapshot",
|
||||
"timemachine_list", "timemachine_view", "timemachine_diff",
|
||||
"ensure_infonet_ready", "join_infonet_swarm",
|
||||
"post_gate_message", "cast_vote", "send_dm",
|
||||
],
|
||||
},
|
||||
},
|
||||
|
||||
+36
-2
@@ -47,6 +47,8 @@ _CCTV_PROXY_ALLOWED_HOSTS = {
|
||||
"www.tripcheck.com",
|
||||
"infocar.dgt.es",
|
||||
"informo.madrid.es",
|
||||
"webcams2.asfinag.at",
|
||||
"odo.asfinag.at",
|
||||
"www.windy.com",
|
||||
"imgproxy.windy.com",
|
||||
"www.lakecountypassage.com",
|
||||
@@ -55,6 +57,14 @@ _CCTV_PROXY_ALLOWED_HOSTS = {
|
||||
"www.nps.gov",
|
||||
"home.lewiscounty.com",
|
||||
"www.seattle.gov",
|
||||
"511on.ca",
|
||||
"511.alberta.ca",
|
||||
"fl511.com",
|
||||
"www.fl511.com",
|
||||
"webcams.transport.nsw.gov.au",
|
||||
"www.livetraffic.com",
|
||||
"livetraffic.com",
|
||||
"opendata.ndw.nu",
|
||||
}
|
||||
|
||||
|
||||
@@ -120,7 +130,7 @@ def _cctv_proxy_profile_for_url(target_url: str) -> _CCTVProxyProfile:
|
||||
read_timeout = 18.0 if "/snapshots/" in path else 12.0
|
||||
return _CCTVProxyProfile(name="gdot-snapshot", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, read_timeout), cache_seconds=15,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
"Referer": "http://navigator-c2c.dot.ga.gov/"})
|
||||
"Referer": "https://navigator-c2c.dot.ga.gov/"})
|
||||
if host == "511ga.org":
|
||||
return _CCTVProxyProfile(name="gdot-511ga-image", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 12.0), cache_seconds=15,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
@@ -128,7 +138,7 @@ def _cctv_proxy_profile_for_url(target_url: str) -> _CCTVProxyProfile:
|
||||
if host.startswith("vss") and host.endswith("dot.ga.gov"):
|
||||
return _CCTVProxyProfile(name="gdot-hls", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 20.0), cache_seconds=10,
|
||||
headers={"Accept": "application/vnd.apple.mpegurl,application/x-mpegURL,video/*,*/*;q=0.8",
|
||||
"Referer": "http://navigator-c2c.dot.ga.gov/"})
|
||||
"Referer": "https://navigator-c2c.dot.ga.gov/"})
|
||||
if host in {"gettingaroundillinois.com", "cctv.travelmidwest.com"}:
|
||||
return _CCTVProxyProfile(name="illinois-dot", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 12.0), cache_seconds=30,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8"})
|
||||
@@ -156,10 +166,34 @@ def _cctv_proxy_profile_for_url(target_url: str) -> _CCTVProxyProfile:
|
||||
return _CCTVProxyProfile(name="madrid-city", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 12.0), cache_seconds=30,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
"Referer": "https://informo.madrid.es/"})
|
||||
if host in {"webcams2.asfinag.at", "odo.asfinag.at"}:
|
||||
return _CCTVProxyProfile(name="asfinag-austria", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 15.0), cache_seconds=60,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
"Referer": "https://www.asfinag.at/"})
|
||||
if host in {"www.windy.com", "imgproxy.windy.com"}:
|
||||
return _CCTVProxyProfile(name="windy-webcams", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 12.0), cache_seconds=60,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
"Referer": "https://www.windy.com/"})
|
||||
if host == "511on.ca":
|
||||
return _CCTVProxyProfile(name="ontario-511", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 15.0), cache_seconds=30,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
"Referer": "https://511on.ca/"})
|
||||
if host == "511.alberta.ca":
|
||||
return _CCTVProxyProfile(name="alberta-511", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 15.0), cache_seconds=30,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
"Referer": "https://511.alberta.ca/"})
|
||||
if host in {"fl511.com", "www.fl511.com"}:
|
||||
return _CCTVProxyProfile(name="florida-511", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 15.0), cache_seconds=30,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
"Referer": "https://fl511.com/"})
|
||||
if host == "webcams.transport.nsw.gov.au":
|
||||
return _CCTVProxyProfile(name="nsw-live-traffic", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 12.0), cache_seconds=60,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
"Referer": "https://www.livetraffic.com/"})
|
||||
if host in {"opendata.ndw.nu", "www.ndw.nu"}:
|
||||
return _CCTVProxyProfile(name="ndw-netherlands", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 12.0), cache_seconds=120,
|
||||
headers={"Accept": "image/avif,image/webp,image/apng,image/*,*/*;q=0.8",
|
||||
"Referer": "https://www.ndw.nu/"})
|
||||
return _CCTVProxyProfile(name="generic-cctv", timeout=(_CCTV_PROXY_CONNECT_TIMEOUT_S, 8.0), cache_seconds=30,
|
||||
headers={"Accept": "*/*"})
|
||||
|
||||
|
||||
+167
-7
@@ -1,6 +1,7 @@
|
||||
import asyncio
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import threading
|
||||
from typing import Any
|
||||
from fastapi import APIRouter, Request, Response, Query, Depends
|
||||
@@ -8,7 +9,7 @@ from fastapi.responses import JSONResponse
|
||||
from pydantic import BaseModel
|
||||
from limiter import limiter
|
||||
from auth import require_admin, require_local_operator
|
||||
from services.data_fetcher import get_latest_data, update_all_data
|
||||
from services.data_fetcher import update_all_data
|
||||
import orjson
|
||||
import json as json_mod
|
||||
|
||||
@@ -30,6 +31,14 @@ class LayerUpdate(BaseModel):
|
||||
layers: dict[str, bool]
|
||||
|
||||
|
||||
class LiveUamapOptInUpdate(BaseModel):
|
||||
opted_in: bool
|
||||
|
||||
|
||||
class PredictionMarketsOptInUpdate(BaseModel):
|
||||
opted_in: bool
|
||||
|
||||
|
||||
_LAST_VIEWPORT_UPDATE: tuple | None = None
|
||||
_LAST_VIEWPORT_UPDATE_TS = 0.0
|
||||
_VIEWPORT_UPDATE_LOCK = threading.Lock()
|
||||
@@ -202,6 +211,15 @@ def _sanitize_payload(value):
|
||||
return value
|
||||
|
||||
|
||||
def _live_data_json_bytes(payload: dict) -> bytes:
|
||||
"""Serialize dashboard payloads with the same defensive orjson options everywhere."""
|
||||
return orjson.dumps(
|
||||
_sanitize_payload(payload),
|
||||
default=str,
|
||||
option=orjson.OPT_NON_STR_KEYS,
|
||||
)
|
||||
|
||||
|
||||
def _bbox_filter(items: list, s: float, w: float, n: float, e: float,
|
||||
lat_key: str = "lat", lng_key: str = "lng") -> list:
|
||||
pad_lat = (n - s) * 0.2
|
||||
@@ -386,6 +404,95 @@ async def update_viewport(vp: ViewportUpdate, request: Request): # noqa: ARG001
|
||||
return {"status": "ok"}
|
||||
|
||||
|
||||
@router.get("/api/liveuamap/scraper-status", dependencies=[Depends(require_local_operator)])
|
||||
async def api_liveuamap_scraper_status():
|
||||
"""Whether LiveUAMap Playwright may run (Windows needs UI opt-in unless env forces)."""
|
||||
from services.liveuamap_settings import liveuamap_scraper_status
|
||||
|
||||
return liveuamap_scraper_status()
|
||||
|
||||
|
||||
@router.post("/api/liveuamap/scraper-opt-in", dependencies=[Depends(require_local_operator)])
|
||||
@limiter.limit("10/minute")
|
||||
async def api_liveuamap_scraper_opt_in(body: LiveUamapOptInUpdate, request: Request):
|
||||
"""Persist operator consent for LiveUAMap scraper (#348)."""
|
||||
from services.liveuamap_settings import liveuamap_scraper_status, set_liveuamap_ui_opt_in
|
||||
|
||||
set_liveuamap_ui_opt_in(body.opted_in)
|
||||
if body.opted_in:
|
||||
from services.fetchers._store import is_any_active
|
||||
|
||||
if is_any_active("global_incidents"):
|
||||
threading.Thread(target=_run_liveuamap_refresh, daemon=True).start()
|
||||
return liveuamap_scraper_status()
|
||||
|
||||
|
||||
def _run_liveuamap_refresh() -> None:
|
||||
try:
|
||||
from services.fetchers.geo import update_liveuamap
|
||||
|
||||
update_liveuamap()
|
||||
except Exception as e:
|
||||
logger.warning("LiveUAMap refresh after opt-in failed: %s", e)
|
||||
|
||||
|
||||
@router.get("/api/prediction-markets/status", dependencies=[Depends(require_local_operator)])
|
||||
async def api_prediction_markets_status():
|
||||
"""Whether Polymarket/Kalshi fetches and news market correlation are enabled."""
|
||||
from services.prediction_markets_settings import prediction_markets_status
|
||||
|
||||
return prediction_markets_status()
|
||||
|
||||
|
||||
@router.post("/api/prediction-markets/opt-in", dependencies=[Depends(require_local_operator)])
|
||||
@limiter.limit("10/minute")
|
||||
async def api_prediction_markets_opt_in(body: PredictionMarketsOptInUpdate, request: Request):
|
||||
"""Enable or disable prediction market fetches + intercept story correlation."""
|
||||
from services.config import get_settings
|
||||
from services.prediction_markets_settings import (
|
||||
prediction_markets_status,
|
||||
set_prediction_markets_ui_opt_in,
|
||||
)
|
||||
from routers.ai_intel import _write_env_value
|
||||
|
||||
set_prediction_markets_ui_opt_in(body.opted_in)
|
||||
_write_env_value("PREDICTION_MARKETS_ENABLED", "true" if body.opted_in else "false")
|
||||
os.environ["PREDICTION_MARKETS_ENABLED"] = "true" if body.opted_in else "false"
|
||||
get_settings.cache_clear()
|
||||
|
||||
if body.opted_in:
|
||||
threading.Thread(target=_run_prediction_markets_refresh, daemon=True).start()
|
||||
else:
|
||||
threading.Thread(target=_run_prediction_markets_disable, daemon=True).start()
|
||||
|
||||
return prediction_markets_status()
|
||||
|
||||
|
||||
def _run_prediction_markets_refresh() -> None:
|
||||
try:
|
||||
from services.fetchers.prediction_markets import fetch_prediction_markets
|
||||
from services.fetchers.news import fetch_news
|
||||
|
||||
fetch_prediction_markets()
|
||||
fetch_news()
|
||||
except Exception as e:
|
||||
logger.warning("Prediction markets refresh after opt-in failed: %s", e)
|
||||
|
||||
|
||||
def _run_prediction_markets_disable() -> None:
|
||||
try:
|
||||
from services.fetchers._store import _data_lock, _mark_fresh, latest_data
|
||||
from services.fetchers.news import fetch_news
|
||||
|
||||
with _data_lock:
|
||||
latest_data["prediction_markets"] = []
|
||||
latest_data["trending_markets"] = []
|
||||
_mark_fresh("prediction_markets")
|
||||
fetch_news()
|
||||
except Exception as e:
|
||||
logger.warning("Prediction markets disable cleanup failed: %s", e)
|
||||
|
||||
|
||||
@router.post("/api/layers", dependencies=[Depends(require_local_operator)])
|
||||
@limiter.limit("30/minute")
|
||||
async def update_layers(update: LayerUpdate, request: Request):
|
||||
@@ -395,6 +502,8 @@ async def update_layers(update: LayerUpdate, request: Request):
|
||||
old_mesh = is_any_active("sigint_meshtastic")
|
||||
old_aprs = is_any_active("sigint_aprs")
|
||||
old_viirs = is_any_active("viirs_nightlights")
|
||||
old_datacenters = is_any_active("datacenters")
|
||||
old_fishing = is_any_active("fishing_activity")
|
||||
changed = False
|
||||
for key, value in update.layers.items():
|
||||
if key in active_layers:
|
||||
@@ -407,6 +516,8 @@ async def update_layers(update: LayerUpdate, request: Request):
|
||||
new_mesh = is_any_active("sigint_meshtastic")
|
||||
new_aprs = is_any_active("sigint_aprs")
|
||||
new_viirs = is_any_active("viirs_nightlights")
|
||||
new_datacenters = is_any_active("datacenters")
|
||||
new_fishing = is_any_active("fishing_activity")
|
||||
if old_ships and not new_ships:
|
||||
from services.ais_stream import stop_ais_stream
|
||||
stop_ais_stream()
|
||||
@@ -450,13 +561,33 @@ async def update_layers(update: LayerUpdate, request: Request):
|
||||
if not old_viirs and new_viirs:
|
||||
_queue_viirs_change_refresh()
|
||||
logger.info("VIIRS change refresh queued (layer enabled)")
|
||||
if not old_datacenters and new_datacenters:
|
||||
from services.fetchers.infrastructure import fetch_datacenters
|
||||
|
||||
fetch_datacenters()
|
||||
logger.info("Datacenters loaded (layer enabled)")
|
||||
if not old_fishing and new_fishing:
|
||||
from services.fetchers.geo import fetch_fishing_activity
|
||||
|
||||
fetch_fishing_activity()
|
||||
logger.info("Fishing activity refresh queued (layer enabled)")
|
||||
return {"status": "ok"}
|
||||
|
||||
|
||||
@router.get("/api/live-data")
|
||||
@limiter.limit("120/minute")
|
||||
async def live_data(request: Request):
|
||||
return get_latest_data()
|
||||
etag = _current_etag(prefix="live|full|")
|
||||
if request.headers.get("if-none-match") == etag:
|
||||
return Response(status_code=304, headers={"ETag": etag, "Cache-Control": "no-cache"})
|
||||
from services.fetchers._store import get_latest_data_deepcopy_snapshot
|
||||
|
||||
payload = get_latest_data_deepcopy_snapshot()
|
||||
return Response(
|
||||
content=_live_data_json_bytes(payload),
|
||||
media_type="application/json",
|
||||
headers={"ETag": etag, "Cache-Control": "no-cache"},
|
||||
)
|
||||
|
||||
|
||||
@router.get("/api/bootstrap/critical")
|
||||
@@ -551,7 +682,7 @@ async def bootstrap_critical(request: Request):
|
||||
"bootstrap_payload": True,
|
||||
}
|
||||
return Response(
|
||||
content=orjson.dumps(_sanitize_payload(payload), default=str, option=orjson.OPT_NON_STR_KEYS),
|
||||
content=_live_data_json_bytes(payload),
|
||||
media_type="application/json",
|
||||
headers={"ETag": etag, "Cache-Control": "no-cache"},
|
||||
)
|
||||
@@ -613,8 +744,11 @@ async def live_data_fast(
|
||||
# to the pre-#288 implementation.
|
||||
if _has_full_bbox(s, w, n, e):
|
||||
payload = _apply_bbox_to_payload(payload, _FAST_BBOX_HEAVY_KEYS, s, w, n, e)
|
||||
return Response(content=orjson.dumps(_sanitize_payload(payload)), media_type="application/json",
|
||||
headers={"ETag": etag, "Cache-Control": "no-cache"})
|
||||
return Response(
|
||||
content=_live_data_json_bytes(payload),
|
||||
media_type="application/json",
|
||||
headers={"ETag": etag, "Cache-Control": "no-cache"},
|
||||
)
|
||||
|
||||
|
||||
@router.get("/api/live-data/slow")
|
||||
@@ -638,7 +772,8 @@ async def live_data_slow(
|
||||
"firms_fires", "datacenters", "military_bases", "power_plants", "viirs_change_nodes",
|
||||
"scanners", "weather_alerts", "ukraine_alerts", "air_quality", "volcanoes",
|
||||
"fishing_activity", "psk_reporter", "correlations", "uap_sightings", "wastewater",
|
||||
"crowdthreat", "threat_level", "trending_markets",
|
||||
"crowdthreat", "threat_level", "trending_markets", "road_corridor_trends",
|
||||
"malware_threats", "cyber_threats", "scm_suppliers", "telegram_osint",
|
||||
)
|
||||
freshness = get_source_timestamps_snapshot()
|
||||
payload = {
|
||||
@@ -679,6 +814,31 @@ async def live_data_slow(
|
||||
"uap_sightings": (d.get("uap_sightings") or []) if active_layers.get("uap_sightings", True) else [],
|
||||
"wastewater": (d.get("wastewater") or []) if active_layers.get("wastewater", True) else [],
|
||||
"crowdthreat": (d.get("crowdthreat") or []) if active_layers.get("crowdthreat", True) else [],
|
||||
"road_corridor_trends": (
|
||||
d.get("road_corridor_trends") or {"updated_at": None, "corridors": []}
|
||||
)
|
||||
if active_layers.get("road_corridor_trends", False)
|
||||
else {"updated_at": None, "corridors": []},
|
||||
"malware_threats": (
|
||||
d.get("malware_threats") or {"threats": [], "total": 0}
|
||||
)
|
||||
if active_layers.get("malware_c2", False)
|
||||
else {"threats": [], "total": 0},
|
||||
"cyber_threats": (
|
||||
d.get("cyber_threats") or {"threats": [], "stats": {}}
|
||||
)
|
||||
if active_layers.get("cyber_threats", False)
|
||||
else {"threats": [], "stats": {}},
|
||||
"scm_suppliers": (
|
||||
d.get("scm_suppliers") or {"suppliers": [], "total": 0, "critical_count": 0}
|
||||
)
|
||||
if active_layers.get("scm_suppliers", False)
|
||||
else {"suppliers": [], "total": 0, "critical_count": 0},
|
||||
"telegram_osint": (
|
||||
d.get("telegram_osint") or {"posts": [], "total": 0, "geolocated": 0}
|
||||
)
|
||||
if active_layers.get("telegram_osint", True)
|
||||
else {"posts": [], "total": 0, "geolocated": 0},
|
||||
"freshness": freshness,
|
||||
}
|
||||
# Issue #288: bbox filter heavy/dense layers only when all four bounds
|
||||
@@ -688,7 +848,7 @@ async def live_data_slow(
|
||||
if _has_full_bbox(s, w, n, e):
|
||||
payload = _apply_bbox_to_payload(payload, _SLOW_BBOX_HEAVY_KEYS, s, w, n, e)
|
||||
return Response(
|
||||
content=orjson.dumps(_sanitize_payload(payload), default=str, option=orjson.OPT_NON_STR_KEYS),
|
||||
content=_live_data_json_bytes(payload),
|
||||
media_type="application/json",
|
||||
headers={"ETag": etag, "Cache-Control": "no-cache"},
|
||||
)
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
"""Entity graph expansion (intel layer)."""
|
||||
from __future__ import annotations
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Query, Request
|
||||
|
||||
from auth import require_local_operator
|
||||
from limiter import limiter
|
||||
from services.osint_intel.resolve import resolve_entity
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.get("/api/entity/expand")
|
||||
@limiter.limit("30/minute")
|
||||
async def entity_expand(
|
||||
request: Request,
|
||||
_: None = Depends(require_local_operator),
|
||||
type: str = Query(..., min_length=3, max_length=32),
|
||||
id: str = Query(..., min_length=2, max_length=200),
|
||||
registration: str | None = Query(default=None, max_length=32),
|
||||
model: str | None = Query(default=None, max_length=64),
|
||||
icao24: str | None = Query(default=None, max_length=16),
|
||||
) -> dict:
|
||||
props = {"label": id, "registration": registration, "model": model, "icao24": icao24}
|
||||
try:
|
||||
return resolve_entity(type, id, props)
|
||||
except ValueError as exc:
|
||||
raise HTTPException(status_code=400, detail=str(exc)) from exc
|
||||
except Exception as exc:
|
||||
raise HTTPException(status_code=502, detail="Intelligence layer unavailable") from exc
|
||||
@@ -8,7 +8,7 @@ from services.data_fetcher import get_latest_data
|
||||
from services.schemas import HealthResponse
|
||||
import os
|
||||
|
||||
APP_VERSION = os.environ.get("_HEALTH_APP_VERSION", "0.9.81")
|
||||
APP_VERSION = os.environ.get("_HEALTH_APP_VERSION", "0.9.82")
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@@ -0,0 +1,122 @@
|
||||
"""Malware, cyber threats, and country risk feeds."""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import requests
|
||||
from fastapi import APIRouter, HTTPException, Query, Request
|
||||
from fastapi.responses import StreamingResponse
|
||||
from starlette.background import BackgroundTask
|
||||
|
||||
from limiter import limiter
|
||||
from services.fetchers._store import get_latest_data_subset_refs
|
||||
from services.fetchers.telegram_osint import telegram_media_host_allowed
|
||||
from services.intel_feeds.country_risk import build_country_risk_payload
|
||||
from services.network_utils import outbound_user_agent
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.get("/api/malware")
|
||||
@limiter.limit("60/minute")
|
||||
async def malware_feed(request: Request) -> dict:
|
||||
snap = get_latest_data_subset_refs("malware_threats")
|
||||
payload = snap.get("malware_threats")
|
||||
if isinstance(payload, dict) and payload.get("threats") is not None:
|
||||
return payload
|
||||
return {"threats": [], "total": 0, "timestamp": None, "source": "abuse.ch"}
|
||||
|
||||
|
||||
@router.get("/api/cyber-threats")
|
||||
@limiter.limit("60/minute")
|
||||
async def cyber_threats(request: Request) -> dict:
|
||||
snap = get_latest_data_subset_refs("cyber_threats")
|
||||
return snap.get("cyber_threats") or {"threats": [], "stats": {}}
|
||||
|
||||
|
||||
@router.get("/api/country-risk")
|
||||
@limiter.limit("30/minute")
|
||||
async def country_risk(request: Request) -> dict:
|
||||
return build_country_risk_payload()
|
||||
|
||||
|
||||
@router.get("/api/telegram-feed")
|
||||
@limiter.limit("30/minute")
|
||||
async def telegram_feed(request: Request) -> dict:
|
||||
snap = get_latest_data_subset_refs("telegram_osint")
|
||||
payload = snap.get("telegram_osint")
|
||||
if isinstance(payload, dict) and payload.get("posts") is not None:
|
||||
return payload
|
||||
return {"posts": [], "total": 0, "geolocated": 0, "timestamp": None}
|
||||
|
||||
|
||||
def _infer_telegram_media_type(target_url: str, content_type: str) -> str:
|
||||
clean_type = str(content_type or "").split(";", 1)[0].strip().lower()
|
||||
if clean_type and clean_type not in {"application/octet-stream", "binary/octet-stream"}:
|
||||
return content_type
|
||||
path = str(urlparse(target_url).path or "").lower()
|
||||
if path.endswith((".jpg", ".jpeg")):
|
||||
return "image/jpeg"
|
||||
if path.endswith(".png"):
|
||||
return "image/png"
|
||||
if path.endswith(".webp"):
|
||||
return "image/webp"
|
||||
if path.endswith(".gif"):
|
||||
return "image/gif"
|
||||
if path.endswith(".mp4"):
|
||||
return "video/mp4"
|
||||
if path.endswith(".webm"):
|
||||
return "video/webm"
|
||||
return content_type or "application/octet-stream"
|
||||
|
||||
|
||||
@router.get("/api/telegram/media")
|
||||
@limiter.limit("60/minute")
|
||||
async def telegram_media_proxy(request: Request, url: str = Query(...)) -> StreamingResponse:
|
||||
"""Stream Telegram CDN media for in-app playback (host allowlist only)."""
|
||||
parsed = urlparse(url)
|
||||
if parsed.scheme not in ("http", "https"):
|
||||
raise HTTPException(status_code=400, detail="Invalid scheme")
|
||||
if not telegram_media_host_allowed(parsed.hostname):
|
||||
raise HTTPException(status_code=403, detail="Host not allowed")
|
||||
|
||||
headers = {
|
||||
"User-Agent": (
|
||||
f"Mozilla/5.0 (compatible; {outbound_user_agent('telegram-media')}) "
|
||||
"AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
),
|
||||
"Accept": "*/*",
|
||||
}
|
||||
if range_header := request.headers.get("range"):
|
||||
headers["Range"] = range_header
|
||||
|
||||
try:
|
||||
resp = requests.get(url, stream=True, timeout=(3, 45), headers=headers)
|
||||
except requests.RequestException as exc:
|
||||
logger.warning("Telegram media upstream failure %s: %s", url, exc)
|
||||
raise HTTPException(status_code=502, detail="Upstream fetch failed") from exc
|
||||
|
||||
if resp.status_code >= 400:
|
||||
resp.close()
|
||||
raise HTTPException(status_code=int(resp.status_code), detail=f"Upstream returned {resp.status_code}")
|
||||
|
||||
media_type = _infer_telegram_media_type(url, resp.headers.get("Content-Type", "application/octet-stream"))
|
||||
response_headers = {
|
||||
"Cache-Control": "private, max-age=300",
|
||||
"Accept-Ranges": resp.headers.get("Accept-Ranges", "bytes"),
|
||||
}
|
||||
if content_length := resp.headers.get("Content-Length"):
|
||||
response_headers["Content-Length"] = content_length
|
||||
if content_range := resp.headers.get("Content-Range"):
|
||||
response_headers["Content-Range"] = content_range
|
||||
|
||||
return StreamingResponse(
|
||||
resp.iter_content(chunk_size=65536),
|
||||
status_code=resp.status_code,
|
||||
media_type=media_type,
|
||||
headers=response_headers,
|
||||
background=BackgroundTask(resp.close),
|
||||
)
|
||||
@@ -65,6 +65,10 @@ def _hydrate_dm_relay_from_chain(events: list) -> int:
|
||||
@limiter.limit("30/minute")
|
||||
async def infonet_peer_push(request: Request):
|
||||
"""Accept pushed Infonet events from relay peers (HMAC-authenticated)."""
|
||||
from services.mesh.mesh_fleet_defaults import infonet_fleet_join_enabled
|
||||
|
||||
if not infonet_fleet_join_enabled():
|
||||
return {"ok": True, "accepted": 0, "duplicates": 0, "rejected": [], "skipped": "fleet_join_disabled"}
|
||||
content_length = request.headers.get("content-length")
|
||||
if content_length:
|
||||
try:
|
||||
@@ -154,6 +158,10 @@ async def dm_replicate_envelope(request: Request):
|
||||
@limiter.limit("30/minute")
|
||||
async def gate_peer_push(request: Request):
|
||||
"""Accept pushed gate events from relay peers (private plane)."""
|
||||
from services.mesh.mesh_fleet_defaults import infonet_fleet_join_enabled
|
||||
|
||||
if not infonet_fleet_join_enabled():
|
||||
return {"ok": True, "accepted": 0, "duplicates": 0, "skipped": "fleet_join_disabled"}
|
||||
content_length = request.headers.get("content-length")
|
||||
if content_length:
|
||||
try:
|
||||
|
||||
@@ -0,0 +1,151 @@
|
||||
"""Operator OSINT recon routes (server-side proxies, SSRF guarded)."""
|
||||
from __future__ import annotations
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Query, Request
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from auth import require_local_operator
|
||||
from limiter import limiter
|
||||
from services.osint import lookups
|
||||
|
||||
router = APIRouter(dependencies=[Depends(require_local_operator)])
|
||||
|
||||
_ALLOWED_SCHEMAS = {
|
||||
"Person",
|
||||
"Organization",
|
||||
"Company",
|
||||
"Vessel",
|
||||
"Airplane",
|
||||
"LegalEntity",
|
||||
}
|
||||
|
||||
|
||||
class SweepScanRequest(BaseModel):
|
||||
ip: str = Field(min_length=7, max_length=45)
|
||||
cidr: int = Field(default=24, ge=24, le=32)
|
||||
|
||||
|
||||
def _bad_request(exc: ValueError) -> HTTPException:
|
||||
return HTTPException(status_code=400, detail=str(exc))
|
||||
|
||||
|
||||
@router.get("/api/osint/ip")
|
||||
@limiter.limit("20/minute")
|
||||
async def osint_ip(request: Request, ip: str = Query(..., min_length=7, max_length=45)) -> dict:
|
||||
try:
|
||||
return lookups.lookup_ip(ip)
|
||||
except ValueError as exc:
|
||||
raise _bad_request(exc) from exc
|
||||
|
||||
|
||||
@router.get("/api/osint/dns")
|
||||
@limiter.limit("20/minute")
|
||||
async def osint_dns(request: Request, domain: str = Query(..., min_length=4, max_length=253)) -> dict:
|
||||
try:
|
||||
return lookups.lookup_dns(domain)
|
||||
except ValueError as exc:
|
||||
raise _bad_request(exc) from exc
|
||||
|
||||
|
||||
@router.get("/api/osint/whois")
|
||||
@limiter.limit("20/minute")
|
||||
async def osint_whois(request: Request, domain: str = Query(..., min_length=4, max_length=253)) -> dict:
|
||||
try:
|
||||
return lookups.lookup_whois(domain)
|
||||
except ValueError as exc:
|
||||
raise _bad_request(exc) from exc
|
||||
|
||||
|
||||
@router.get("/api/osint/certs")
|
||||
@limiter.limit("20/minute")
|
||||
async def osint_certs(request: Request, domain: str = Query(..., min_length=4, max_length=253)) -> dict:
|
||||
try:
|
||||
return lookups.lookup_certs(domain)
|
||||
except ValueError as exc:
|
||||
raise _bad_request(exc) from exc
|
||||
|
||||
|
||||
@router.get("/api/osint/threats")
|
||||
@limiter.limit("20/minute")
|
||||
async def osint_threats(request: Request, query: str | None = Query(default=None, max_length=253)) -> dict:
|
||||
return lookups.lookup_threats(query)
|
||||
|
||||
|
||||
@router.get("/api/osint/bgp")
|
||||
@limiter.limit("20/minute")
|
||||
async def osint_bgp(request: Request, query: str = Query(..., min_length=2, max_length=64)) -> dict:
|
||||
try:
|
||||
return lookups.lookup_bgp(query)
|
||||
except ValueError as exc:
|
||||
raise _bad_request(exc) from exc
|
||||
|
||||
|
||||
@router.get("/api/osint/sanctions")
|
||||
@limiter.limit("20/minute")
|
||||
async def osint_sanctions(
|
||||
request: Request,
|
||||
query: str = Query(..., min_length=4, max_length=200),
|
||||
schema: str | None = Query(default=None),
|
||||
limit: int = Query(default=25, ge=1, le=100),
|
||||
) -> dict:
|
||||
if schema and schema not in _ALLOWED_SCHEMAS:
|
||||
raise HTTPException(status_code=400, detail=f"Invalid schema. Allowed: {', '.join(sorted(_ALLOWED_SCHEMAS))}")
|
||||
return lookups.lookup_sanctions(query, schema=schema, limit=limit)
|
||||
|
||||
|
||||
@router.get("/api/osint/cve")
|
||||
@limiter.limit("30/minute")
|
||||
async def osint_cve(request: Request, cve: str = Query(..., min_length=10, max_length=32)) -> dict:
|
||||
try:
|
||||
return lookups.lookup_cve(cve)
|
||||
except ValueError as exc:
|
||||
raise HTTPException(status_code=404 if "not found" in str(exc).lower() else 400, detail=str(exc)) from exc
|
||||
|
||||
|
||||
@router.get("/api/osint/mac")
|
||||
@limiter.limit("20/minute")
|
||||
async def osint_mac(request: Request, mac: str = Query(..., min_length=5, max_length=32)) -> dict:
|
||||
return lookups.lookup_mac(mac)
|
||||
|
||||
|
||||
@router.get("/api/osint/github")
|
||||
@limiter.limit("20/minute")
|
||||
async def osint_github(request: Request, username: str = Query(..., min_length=1, max_length=64)) -> dict:
|
||||
try:
|
||||
return lookups.lookup_github(username)
|
||||
except ValueError as exc:
|
||||
raise HTTPException(status_code=404, detail=str(exc)) from exc
|
||||
|
||||
|
||||
@router.get("/api/osint/leaks")
|
||||
@limiter.limit("10/minute")
|
||||
async def osint_leaks(request: Request, email: str = Query(..., min_length=5, max_length=254)) -> dict:
|
||||
try:
|
||||
return lookups.lookup_leaks(email)
|
||||
except ValueError as exc:
|
||||
raise _bad_request(exc) from exc
|
||||
|
||||
|
||||
@router.get("/api/osint/sweep")
|
||||
@limiter.limit("5/minute")
|
||||
async def osint_sweep_init(
|
||||
request: Request,
|
||||
ip: str = Query(..., min_length=7, max_length=45),
|
||||
cidr: int = Query(default=24, ge=24, le=32),
|
||||
) -> dict:
|
||||
try:
|
||||
return lookups.sweep_init(ip, cidr)
|
||||
except ValueError as exc:
|
||||
raise _bad_request(exc) from exc
|
||||
|
||||
|
||||
@router.post("/api/osint/sweep/scan")
|
||||
@limiter.limit("3/minute")
|
||||
async def osint_sweep_scan(request: Request, payload: SweepScanRequest) -> dict:
|
||||
try:
|
||||
subnet = lookups.subnet_start_for(payload.ip, payload.cidr)
|
||||
scan = lookups.sweep_scan(subnet, payload.cidr)
|
||||
init = lookups.sweep_init(payload.ip, payload.cidr)
|
||||
return {**init, **scan, "subnet": f"{subnet}/{payload.cidr}"}
|
||||
except ValueError as exc:
|
||||
raise _bad_request(exc) from exc
|
||||
@@ -0,0 +1,105 @@
|
||||
"""Road corridor Sentinel-2 freight trend endpoints (opt-in slow layer)."""
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Query, Request
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from limiter import limiter
|
||||
from services.road_corridor_sat.config import optional_deps_available, road_corridor_sat_enabled
|
||||
from services.road_corridor_sat.credentials import sentinel_credentials_configured
|
||||
from services.road_corridor_sat.jobs import enqueue_analyze, get_job, get_latest_job, job_to_dict
|
||||
from services.road_corridor_sat.presets import CORRIDOR_PRESETS, get_preset
|
||||
from services.road_corridor_sat.storage import build_trends_payload, preset_metadata
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def _status_payload() -> dict:
|
||||
latest = get_latest_job()
|
||||
return {
|
||||
"enabled": road_corridor_sat_enabled(),
|
||||
"deps_installed": optional_deps_available(),
|
||||
"credentials_configured": sentinel_credentials_configured(),
|
||||
"preset_count": len(CORRIDOR_PRESETS),
|
||||
"attribution": "backend/third_party/drishx/NOTICE.md",
|
||||
"active_job": job_to_dict(latest) if latest and latest.status in {"queued", "running"} else None,
|
||||
}
|
||||
|
||||
|
||||
def _require_analyze_ready() -> None:
|
||||
if not optional_deps_available():
|
||||
raise HTTPException(
|
||||
status_code=503,
|
||||
detail="Install optional road-corridor dependencies (uv sync --extra road-corridor)",
|
||||
)
|
||||
if not sentinel_credentials_configured():
|
||||
raise HTTPException(
|
||||
status_code=503,
|
||||
detail="Set SENTINEL_CLIENT_ID and SENTINEL_CLIENT_SECRET in Imagery settings",
|
||||
)
|
||||
|
||||
|
||||
class AnalyzeRequest(BaseModel):
|
||||
lat: float = Field(ge=-90, le=90)
|
||||
lon: float = Field(ge=-180, le=180)
|
||||
label: str | None = Field(default=None, max_length=120)
|
||||
|
||||
|
||||
@router.get("/api/road-corridors/status")
|
||||
@limiter.limit("60/minute")
|
||||
async def road_corridors_status(request: Request) -> dict:
|
||||
return {"ok": True, **_status_payload()}
|
||||
|
||||
|
||||
@router.get("/api/road-corridors")
|
||||
@limiter.limit("60/minute")
|
||||
async def list_road_corridors(request: Request) -> dict:
|
||||
return {
|
||||
"ok": True,
|
||||
"status": _status_payload(),
|
||||
"presets": CORRIDOR_PRESETS,
|
||||
"trends": build_trends_payload(),
|
||||
}
|
||||
|
||||
|
||||
@router.post("/api/road-corridors/analyze")
|
||||
@limiter.limit("6/minute")
|
||||
async def analyze_road_corridor_here(request: Request, payload: AnalyzeRequest) -> dict:
|
||||
"""Start an on-demand Sentinel-2 corridor analysis at map center."""
|
||||
_require_analyze_ready()
|
||||
try:
|
||||
job = enqueue_analyze(payload.lat, payload.lon, payload.label)
|
||||
except RuntimeError as exc:
|
||||
if str(exc) == "analysis_already_running":
|
||||
active = get_latest_job()
|
||||
raise HTTPException(
|
||||
status_code=409,
|
||||
detail="Analysis already in progress",
|
||||
headers={"X-Job-Id": active.job_id if active else ""},
|
||||
) from exc
|
||||
raise
|
||||
return {"ok": True, **job_to_dict(job)}
|
||||
|
||||
|
||||
@router.get("/api/road-corridors/analyze/status")
|
||||
@limiter.limit("120/minute")
|
||||
async def analyze_road_corridor_status(
|
||||
request: Request,
|
||||
job_id: str | None = Query(default=None),
|
||||
) -> dict:
|
||||
job = get_job(job_id) if job_id else get_latest_job()
|
||||
if job is None:
|
||||
return {"ok": True, "job": None}
|
||||
return {"ok": True, "job": job_to_dict(job)}
|
||||
|
||||
|
||||
@router.get("/api/road-corridors/{preset_id}")
|
||||
@limiter.limit("60/minute")
|
||||
async def get_road_corridor(preset_id: str, request: Request) -> dict:
|
||||
meta = preset_metadata(preset_id)
|
||||
if meta is None:
|
||||
raise HTTPException(status_code=404, detail="Unknown corridor preset")
|
||||
preset = get_preset(preset_id)
|
||||
if preset is None:
|
||||
# Ad-hoc viewport runs are stored on disk but not in CORRIDOR_PRESETS.
|
||||
return {"ok": True, "preset": None, "result": meta, "status": _status_payload()}
|
||||
return {"ok": True, "preset": preset, "result": meta, "status": _status_payload()}
|
||||
@@ -0,0 +1,16 @@
|
||||
"""Supply-chain risk overlay."""
|
||||
from __future__ import annotations
|
||||
|
||||
from fastapi import APIRouter, Depends, Request
|
||||
|
||||
from auth import require_local_operator
|
||||
from limiter import limiter
|
||||
from services.scm.suppliers import build_scm_payload
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.get("/api/scm-suppliers")
|
||||
@limiter.limit("30/minute")
|
||||
async def scm_suppliers(request: Request, _: None = Depends(require_local_operator)) -> dict:
|
||||
return build_scm_payload()
|
||||
@@ -85,6 +85,39 @@ async def api_geocode_reverse(
|
||||
return await asyncio.to_thread(reverse_geocode, lat, lng, local_only)
|
||||
|
||||
|
||||
# ── Wikimedia proxy (#360) — browser calls these instead of wikipedia.org ───
|
||||
@router.get("/api/wikipedia/summary")
|
||||
@limiter.limit("60/minute")
|
||||
def api_wikipedia_summary(
|
||||
request: Request,
|
||||
title: str = Query(..., min_length=1, max_length=256),
|
||||
):
|
||||
"""Proxy Wikipedia REST summaries through the self-hosted backend."""
|
||||
from services.region_dossier import fetch_wikipedia_page_summary
|
||||
|
||||
summary = fetch_wikipedia_page_summary(title)
|
||||
if summary is None:
|
||||
return JSONResponse(status_code=404, content={"detail": "not_found"})
|
||||
return summary
|
||||
|
||||
|
||||
class WikidataSparqlRequest(BaseModel):
|
||||
query: str
|
||||
|
||||
|
||||
@router.post("/api/wikidata/sparql")
|
||||
@limiter.limit("30/minute")
|
||||
def api_wikidata_sparql(request: Request, body: WikidataSparqlRequest):
|
||||
"""Proxy Wikidata SPARQL so the browser never contacts query.wikidata.org."""
|
||||
from services.region_dossier import fetch_wikidata_sparql_bindings
|
||||
|
||||
q = (body.query or "").strip()
|
||||
if len(q) > 12_000:
|
||||
raise HTTPException(400, "SPARQL query too large")
|
||||
bindings = fetch_wikidata_sparql_bindings(q)
|
||||
return {"bindings": bindings}
|
||||
|
||||
|
||||
# ── Sentinel proxy routes (Issue #299/#300/#301, reported by tg12) ──────────
|
||||
# These three endpoints relay external Sentinel / Planetary Computer
|
||||
# requests through the backend to avoid browser CORS blocks. They are
|
||||
|
||||
@@ -308,6 +308,10 @@ class WormholeDmDecryptRequest(BaseModel):
|
||||
session_welcome: str | None = None
|
||||
|
||||
|
||||
class WormholeDmMlsKeyPackageRequest(BaseModel):
|
||||
alias: str
|
||||
|
||||
|
||||
class WormholeDmResetRequest(BaseModel):
|
||||
peer_id: str | None = None
|
||||
|
||||
@@ -326,6 +330,14 @@ class WormholeDmBootstrapDecryptRequest(BaseModel):
|
||||
ciphertext: str
|
||||
|
||||
|
||||
class WormholeDmConnectContactRequest(BaseModel):
|
||||
lookup_token: str = ""
|
||||
peer_id: str = ""
|
||||
note: str = ""
|
||||
lookup_peer_url: str = ""
|
||||
cached_prekey_bundle: dict[str, Any] | None = None
|
||||
|
||||
|
||||
class WormholeDmInviteImportRequest(BaseModel):
|
||||
invite: dict[str, Any]
|
||||
alias: str = ""
|
||||
@@ -1085,7 +1097,21 @@ async def api_wormhole_dm_bootstrap_decrypt(request: Request, body: WormholeDmBo
|
||||
)
|
||||
|
||||
|
||||
@router.post("/api/wormhole/dm/sender-token", dependencies=[Depends(require_admin)])
|
||||
@router.post("/api/wormhole/dm/connect-contact", dependencies=[Depends(require_local_operator)])
|
||||
@limiter.limit("30/minute")
|
||||
async def api_wormhole_dm_connect_contact(request: Request, body: WormholeDmConnectContactRequest):
|
||||
from services.openclaw_infonet import send_contact_request
|
||||
|
||||
return send_contact_request(
|
||||
lookup_token=str(body.lookup_token or ""),
|
||||
peer_id=str(body.peer_id or ""),
|
||||
note=str(body.note or ""),
|
||||
lookup_peer_url=str(body.lookup_peer_url or ""),
|
||||
cached_prekey_bundle=dict(body.cached_prekey_bundle or {}) if body.cached_prekey_bundle else None,
|
||||
)
|
||||
|
||||
|
||||
@router.post("/api/wormhole/dm/sender-token", dependencies=[Depends(require_local_operator)])
|
||||
@limiter.limit("60/minute")
|
||||
async def api_wormhole_dm_sender_token(request: Request, body: WormholeDmSenderTokenRequest):
|
||||
if _safe_int(body.count or 1, 1) > 1:
|
||||
@@ -1228,6 +1254,23 @@ async def api_wormhole_dm_decrypt(request: Request, body: WormholeDmDecryptReque
|
||||
)
|
||||
|
||||
|
||||
@router.post("/api/wormhole/dm/mls-key-package", dependencies=[Depends(require_admin)])
|
||||
@limiter.limit("60/minute")
|
||||
async def api_wormhole_dm_mls_key_package(request: Request, body: WormholeDmMlsKeyPackageRequest):
|
||||
from services.mesh.mesh_dm_mls import export_dm_key_package_for_alias
|
||||
|
||||
return export_dm_key_package_for_alias(str(body.alias or "").strip())
|
||||
|
||||
|
||||
@router.post("/api/wormhole/dm/mls-reset", dependencies=[Depends(require_admin)])
|
||||
@limiter.limit("30/minute")
|
||||
async def api_wormhole_dm_mls_reset(request: Request):
|
||||
from services.mesh.mesh_dm_mls import reset_dm_mls_state
|
||||
|
||||
reset_dm_mls_state(clear_privacy_core=True, clear_persistence=True)
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
@router.post("/api/wormhole/dm/reset", dependencies=[Depends(require_admin)])
|
||||
@limiter.limit("30/minute")
|
||||
async def api_wormhole_dm_reset(request: Request, body: WormholeDmResetRequest):
|
||||
@@ -1287,7 +1330,25 @@ async def api_wormhole_dm_contact_delete(request: Request, peer_id: str):
|
||||
return {"ok": True, "peer_id": peer_id, "deleted": deleted}
|
||||
|
||||
|
||||
_WORMHOLE_PUBLIC_FIELDS = {"installed", "configured", "running", "ready"}
|
||||
@router.post("/api/wormhole/dm/contact/{peer_id}/sever", dependencies=[Depends(require_admin)])
|
||||
@limiter.limit("60/minute")
|
||||
async def api_wormhole_dm_contact_sever(request: Request, peer_id: str):
|
||||
from services.mesh.mesh_wormhole_contacts import sever_wormhole_dm_contact
|
||||
|
||||
try:
|
||||
body = await request.json()
|
||||
except Exception:
|
||||
body = {}
|
||||
if not isinstance(body, dict):
|
||||
body = {}
|
||||
block = bool(body.get("block", False))
|
||||
try:
|
||||
return sever_wormhole_dm_contact(peer_id, block=block)
|
||||
except ValueError as exc:
|
||||
return {"ok": False, "detail": str(exc)}
|
||||
|
||||
|
||||
_WORMHOLE_PUBLIC_FIELDS = {"installed", "configured", "running", "ready", "arti_ready"}
|
||||
|
||||
|
||||
def _redact_wormhole_status(state: dict[str, Any], authenticated: bool) -> dict[str, Any]:
|
||||
@@ -1308,6 +1369,25 @@ async def api_wormhole_status(request: Request):
|
||||
return await _m.api_wormhole_status(request)
|
||||
|
||||
|
||||
@router.get(
|
||||
"/api/wormhole/private-delivery/{item_id}",
|
||||
dependencies=[Depends(require_local_operator)],
|
||||
)
|
||||
@limiter.limit("120/minute")
|
||||
async def api_wormhole_private_delivery_item(request: Request, item_id: str):
|
||||
from services.mesh.mesh_metadata_exposure import metadata_exposure_for_request
|
||||
from services.mesh.mesh_private_outbox import private_delivery_outbox
|
||||
|
||||
exposure = metadata_exposure_for_request(
|
||||
request,
|
||||
authenticated=True,
|
||||
)
|
||||
item = private_delivery_outbox.get_item(item_id, exposure=exposure)
|
||||
if item is None:
|
||||
raise HTTPException(status_code=404, detail="private_delivery_item_not_found")
|
||||
return {"ok": True, "item": item}
|
||||
|
||||
|
||||
@router.post("/api/wormhole/private-delivery/{item_id}/action", dependencies=[Depends(require_local_operator)])
|
||||
@limiter.limit("30/minute")
|
||||
async def api_wormhole_private_delivery_action(
|
||||
|
||||
@@ -29,7 +29,7 @@ def main() -> None:
|
||||
from services.network_utils import outbound_user_agent
|
||||
ua = outbound_user_agent("release-script-power-plants")
|
||||
except Exception:
|
||||
ua = "Shadowbroker/0.9 (release-script-power-plants; +https://github.com/BigBodyCobain/Shadowbroker/issues)"
|
||||
ua = "operator-release-script (purpose: power-plants)"
|
||||
req = urllib.request.Request(CSV_URL, headers={"User-Agent": ua})
|
||||
with urllib.request.urlopen(req, timeout=60) as resp:
|
||||
raw = resp.read().decode("utf-8")
|
||||
|
||||
@@ -167,6 +167,11 @@ def cmd_hash(args: argparse.Namespace) -> int:
|
||||
print("")
|
||||
print("Updater pin:")
|
||||
print(f"MESH_UPDATE_SHA256={digest}")
|
||||
print("")
|
||||
print("Release checklist:")
|
||||
print(" - add this digest to SHA256SUMS.txt for the GitHub release")
|
||||
print(" - add/update backend/data/release_digests.json for bundled updater verification")
|
||||
print(" - keep MESH_UPDATE_SHA256 available as the operator override path")
|
||||
return 0 if asset_matches else 2
|
||||
|
||||
|
||||
|
||||
@@ -92,18 +92,37 @@ SECRET_REGEX+='pypi-[0-9a-zA-Z-]{50,}' # PyPI token
|
||||
TEXT_FILES=$(grep -ivE '\.(png|jpg|jpeg|gif|ico|svg|woff2?|ttf|eot|pbf|zip|tar|gz|db|sqlite|xlsx|pdf|mp[34]|wav|ogg|webm|webp|avif)$' "$FILELIST" | grep -v 'scan-secrets\.sh$' || true)
|
||||
|
||||
if [[ -n "$TEXT_FILES" ]]; then
|
||||
# Known-public exclusions: lines matching `<host-or-ip> ssh-<algo> <key>`
|
||||
# are SSH known_hosts entries — the host's PUBLIC fingerprint, which is
|
||||
# by definition safe to commit (the whole point of pinning known_hosts
|
||||
# is to publish the fingerprint widely so MITM is detectable). Filter
|
||||
# these out before flagging the file.
|
||||
KNOWN_HOSTS_LINE='^[[:space:]]*[a-zA-Z0-9._:,*-]+([[:space:]]+[a-zA-Z0-9._:,*-]+)?[[:space:]]+(ssh-rsa|ssh-ed25519|ssh-dss|ecdsa-sha2-nistp256|ecdsa-sha2-nistp384|ecdsa-sha2-nistp521)[[:space:]]+AAAA'
|
||||
|
||||
# Use grep with file list, skip missing/binary, limit output
|
||||
CONTENT_HITS=$(echo "$TEXT_FILES" | xargs grep -lE "$SECRET_REGEX" 2>/dev/null || true)
|
||||
if [[ -n "$CONTENT_HITS" ]]; then
|
||||
echo -e "\n${RED}BLOCKED: Embedded secrets/tokens found in:${NC}"
|
||||
echo "$CONTENT_HITS" | while read -r f; do
|
||||
echo -e " ${RED}$f${NC}"
|
||||
# Show first matching line for context
|
||||
grep -nE "$SECRET_REGEX" "$f" 2>/dev/null | head -2 | while read -r line; do
|
||||
echo -e " ${YELLOW}$line${NC}"
|
||||
done
|
||||
done
|
||||
FOUND=1
|
||||
REAL_HITS=""
|
||||
REAL_REPORT=""
|
||||
while IFS= read -r f; do
|
||||
[[ -z "$f" ]] && continue
|
||||
# Re-grep this file, but filter out known_hosts-style lines.
|
||||
FILE_HITS=$(grep -nE "$SECRET_REGEX" "$f" 2>/dev/null | grep -vE "$KNOWN_HOSTS_LINE" || true)
|
||||
if [[ -n "$FILE_HITS" ]]; then
|
||||
REAL_HITS+="$f"$'\n'
|
||||
REAL_REPORT+=" ${RED}$f${NC}"$'\n'
|
||||
# Show first 2 matching lines for context
|
||||
while IFS= read -r line; do
|
||||
[[ -z "$line" ]] && continue
|
||||
REAL_REPORT+=" ${YELLOW}$line${NC}"$'\n'
|
||||
done < <(echo "$FILE_HITS" | head -2)
|
||||
fi
|
||||
done <<< "$CONTENT_HITS"
|
||||
if [[ -n "$REAL_HITS" ]]; then
|
||||
echo -e "\n${RED}BLOCKED: Embedded secrets/tokens found in:${NC}"
|
||||
echo -en "$REAL_REPORT"
|
||||
FOUND=1
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
|
||||
@@ -0,0 +1,54 @@
|
||||
"""Operator settings for the embedded agent shell (working directory)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import threading
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_SETTINGS_FILE = Path(__file__).resolve().parent.parent / "data" / "agent_shell_settings.json"
|
||||
_LOCK = threading.Lock()
|
||||
|
||||
|
||||
def _default_working_directory() -> str:
|
||||
explicit = str(os.environ.get("AGENT_SHELL_DEFAULT_CWD") or "").strip()
|
||||
if explicit and os.path.isdir(explicit):
|
||||
return explicit
|
||||
home = str(os.environ.get("HOME") or "").strip()
|
||||
if home and home != "/nonexistent" and os.path.isdir(home):
|
||||
return home
|
||||
return "/app"
|
||||
|
||||
|
||||
def get_agent_shell_settings() -> dict[str, Any]:
|
||||
with _LOCK:
|
||||
if not _SETTINGS_FILE.exists():
|
||||
return {"working_directory": _default_working_directory()}
|
||||
try:
|
||||
payload = json.loads(_SETTINGS_FILE.read_text(encoding="utf-8"))
|
||||
except Exception:
|
||||
logger.warning("agent_shell_settings_unreadable")
|
||||
return {"working_directory": _default_working_directory()}
|
||||
cwd = str(payload.get("working_directory") or "").strip() or _default_working_directory()
|
||||
return {"working_directory": cwd}
|
||||
|
||||
|
||||
def set_agent_shell_working_directory(path: str) -> dict[str, Any]:
|
||||
normalized = str(path or "").strip()
|
||||
if not normalized:
|
||||
raise ValueError("working_directory_required")
|
||||
resolved = os.path.abspath(os.path.expanduser(normalized))
|
||||
if not os.path.isdir(resolved):
|
||||
raise ValueError("working_directory_not_found")
|
||||
with _LOCK:
|
||||
_SETTINGS_FILE.parent.mkdir(parents=True, exist_ok=True)
|
||||
_SETTINGS_FILE.write_text(
|
||||
json.dumps({"working_directory": resolved}, indent=2) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
return {"working_directory": resolved}
|
||||
@@ -51,6 +51,15 @@ API_REGISTRY = [
|
||||
"url": "https://aisstream.io/",
|
||||
"required": True,
|
||||
},
|
||||
{
|
||||
"id": "gfw_api_token",
|
||||
"env_key": "GFW_API_TOKEN",
|
||||
"name": "Global Fishing Watch",
|
||||
"description": "Bearer token for Global Fishing Watch fishing-vessel activity events (Fishing Activity map layer). Free registration at globalfishingwatch.org.",
|
||||
"category": "Maritime",
|
||||
"url": "https://globalfishingwatch.org/our-apis/",
|
||||
"required": False,
|
||||
},
|
||||
{
|
||||
"id": "adsb_lol",
|
||||
"env_key": None,
|
||||
|
||||
@@ -17,6 +17,9 @@ _KNOWN_CCTV_MEDIA_HOST_ALIASES = {
|
||||
# Trusted upstream occasionally publishes a typo for this Georgia camera
|
||||
# host. Normalize it at ingest so the proxy and client stay consistent.
|
||||
"navigatos-c2c.dot.ga.gov": "navigator-c2c.dot.ga.gov",
|
||||
# TravelIQ staging hosts occasionally appear in 511 catalog metadata.
|
||||
"on.stage.traveliq.co": "511on.ca",
|
||||
"ab.stage.traveliq.co": "511.alberta.ca",
|
||||
}
|
||||
|
||||
_POINT_WKT_RE = re.compile(
|
||||
@@ -40,6 +43,17 @@ def _normalize_cctv_media_url(raw_url: str) -> str:
|
||||
return urlunparse(parsed._replace(netloc=netloc))
|
||||
|
||||
|
||||
def _ensure_https_url(raw_url: str) -> str:
|
||||
"""Upgrade http:// media/catalog URLs to https:// at ingest time."""
|
||||
candidate = _normalize_cctv_media_url(str(raw_url or "").strip())
|
||||
if not candidate:
|
||||
return ""
|
||||
parsed = urlparse(candidate)
|
||||
if parsed.scheme.lower() == "http":
|
||||
return urlunparse(parsed._replace(scheme="https"))
|
||||
return candidate
|
||||
|
||||
|
||||
def _looks_like_direct_cctv_media_url(url: str) -> bool:
|
||||
candidate = str(url or "").strip().lower()
|
||||
if not candidate.startswith(("http://", "https://")):
|
||||
@@ -93,6 +107,165 @@ def _parse_wkt_point(raw_point: str) -> tuple[float | None, float | None]:
|
||||
return lat, lon
|
||||
|
||||
|
||||
def _fetch_traveliq_v2_cameras(
|
||||
*,
|
||||
api_url: str,
|
||||
base_url: str,
|
||||
id_prefix: str,
|
||||
source_agency: str,
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""Parse TravelIQ-style GET /api/v2/get/cameras feeds (Ontario, Alberta)."""
|
||||
resp = fetch_with_curl(
|
||||
api_url,
|
||||
timeout=30,
|
||||
headers={"Accept": "application/json"},
|
||||
)
|
||||
if not resp or resp.status_code != 200:
|
||||
logger.error(
|
||||
"%s CCTV fetch failed: HTTP %s",
|
||||
source_agency,
|
||||
resp.status_code if resp else "no response",
|
||||
)
|
||||
return []
|
||||
|
||||
data = resp.json()
|
||||
if not isinstance(data, list):
|
||||
return []
|
||||
|
||||
cameras: List[Dict[str, Any]] = []
|
||||
for cam in data:
|
||||
if not isinstance(cam, dict):
|
||||
continue
|
||||
try:
|
||||
lat = float(cam.get("Latitude"))
|
||||
lon = float(cam.get("Longitude"))
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
|
||||
site_id = cam.get("Id")
|
||||
location = str(cam.get("Location") or cam.get("Roadway") or "Camera")[:120]
|
||||
views = cam.get("Views") or []
|
||||
if not views:
|
||||
continue
|
||||
|
||||
for view in views:
|
||||
if not isinstance(view, dict):
|
||||
continue
|
||||
status = str(view.get("Status") or "enabled").strip().lower()
|
||||
if status and status not in {"enabled", "active"}:
|
||||
continue
|
||||
media_url = _ensure_https_url(
|
||||
urljoin(base_url, str(view.get("Url") or "").strip())
|
||||
)
|
||||
if not media_url:
|
||||
continue
|
||||
view_id = view.get("Id") or site_id
|
||||
if site_id is None or view_id is None:
|
||||
continue
|
||||
label = str(view.get("Description") or location or "Camera")[:120]
|
||||
cameras.append(
|
||||
{
|
||||
"id": f"{id_prefix}-{site_id}-{view_id}",
|
||||
"source_agency": source_agency,
|
||||
"lat": lat,
|
||||
"lon": lon,
|
||||
"direction_facing": label,
|
||||
"media_url": media_url,
|
||||
"media_type": "image",
|
||||
"refresh_rate_seconds": 60,
|
||||
}
|
||||
)
|
||||
return cameras
|
||||
|
||||
|
||||
def _fetch_511_datatables_cameras(
|
||||
*,
|
||||
list_url: str,
|
||||
base_url: str,
|
||||
id_prefix: str,
|
||||
source_agency: str,
|
||||
referer: str,
|
||||
page_size: int = 500,
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""Parse 511 DataTables POST /List/GetData/Cameras feeds (Georgia, Florida)."""
|
||||
cameras: List[Dict[str, Any]] = []
|
||||
start = 0
|
||||
draw = 1
|
||||
while True:
|
||||
resp = fetch_with_curl(
|
||||
list_url,
|
||||
method="POST",
|
||||
json_data={"draw": draw, "start": start, "length": page_size},
|
||||
timeout=30,
|
||||
headers={
|
||||
"Accept": "application/json",
|
||||
"Referer": referer,
|
||||
"Origin": base_url.rstrip("/"),
|
||||
},
|
||||
)
|
||||
if not resp or resp.status_code != 200:
|
||||
logger.error(
|
||||
"%s CCTV fetch failed: HTTP %s",
|
||||
source_agency,
|
||||
resp.status_code if resp else "no response",
|
||||
)
|
||||
break
|
||||
|
||||
data = resp.json()
|
||||
rows = data.get("data") or []
|
||||
if not rows:
|
||||
break
|
||||
|
||||
for row in rows:
|
||||
if not isinstance(row, dict):
|
||||
continue
|
||||
site_id = row.get("id") or row.get("DT_RowId")
|
||||
location = row.get("location") or row.get("roadway") or source_agency
|
||||
lat_lng = row.get("latLng") or {}
|
||||
geography = lat_lng.get("geography") if isinstance(lat_lng, dict) else {}
|
||||
lat, lon = _parse_wkt_point(
|
||||
geography.get("wellKnownText") if isinstance(geography, dict) else ""
|
||||
)
|
||||
images = row.get("images") or []
|
||||
image = next(
|
||||
(
|
||||
candidate
|
||||
for candidate in images
|
||||
if str(candidate.get("imageUrl") or "").strip()
|
||||
and not bool(candidate.get("blocked"))
|
||||
),
|
||||
None,
|
||||
)
|
||||
if not (site_id and image and lat is not None and lon is not None):
|
||||
continue
|
||||
media_url = _ensure_https_url(
|
||||
urljoin(base_url, str(image.get("imageUrl") or "").strip())
|
||||
)
|
||||
if not media_url:
|
||||
continue
|
||||
cameras.append(
|
||||
{
|
||||
"id": f"{id_prefix}-{site_id}",
|
||||
"source_agency": source_agency,
|
||||
"lat": lat,
|
||||
"lon": lon,
|
||||
"direction_facing": str(location)[:120],
|
||||
"media_url": media_url,
|
||||
"media_type": "image",
|
||||
"refresh_rate_seconds": 60,
|
||||
}
|
||||
)
|
||||
|
||||
start += len(rows)
|
||||
draw += 1
|
||||
total = int(data.get("recordsTotal") or 0)
|
||||
if total and start >= total:
|
||||
break
|
||||
if not total and len(rows) < page_size:
|
||||
break
|
||||
return cameras
|
||||
|
||||
|
||||
def init_db():
|
||||
DB_PATH.parent.mkdir(parents=True, exist_ok=True)
|
||||
conn = sqlite3.connect(str(DB_PATH))
|
||||
@@ -169,7 +342,7 @@ class BaseCCTVIngestor(ABC):
|
||||
cam.get("lat"),
|
||||
cam.get("lon"),
|
||||
cam.get("direction_facing", "Unknown"),
|
||||
cam.get("media_url"),
|
||||
_ensure_https_url(cam.get("media_url", "")),
|
||||
cam.get("media_type", _detect_media_type(cam.get("media_url", ""))),
|
||||
cam.get("refresh_rate_seconds", 60),
|
||||
),
|
||||
@@ -454,77 +627,14 @@ class WSDOTIngestor(BaseCCTVIngestor):
|
||||
class GeorgiaDOTIngestor(BaseCCTVIngestor):
|
||||
"""Georgia cameras via the public 511GA list feed."""
|
||||
|
||||
URL = "https://511ga.org/List/GetData/Cameras"
|
||||
BASE_URL = "https://511ga.org"
|
||||
PAGE_SIZE = 500
|
||||
|
||||
def fetch_data(self) -> List[Dict[str, Any]]:
|
||||
cameras = []
|
||||
start = 0
|
||||
draw = 1
|
||||
while True:
|
||||
resp = fetch_with_curl(
|
||||
self.URL,
|
||||
method="POST",
|
||||
json_data={"draw": draw, "start": start, "length": self.PAGE_SIZE},
|
||||
timeout=30,
|
||||
headers={
|
||||
"Accept": "application/json",
|
||||
"Referer": "https://511ga.org/cctv",
|
||||
"Origin": "https://511ga.org",
|
||||
},
|
||||
)
|
||||
if not resp or resp.status_code != 200:
|
||||
logger.error(
|
||||
"Georgia CCTV fetch failed: HTTP %s",
|
||||
resp.status_code if resp else "no response",
|
||||
)
|
||||
break
|
||||
data = resp.json()
|
||||
rows = data.get("data") or []
|
||||
if not rows:
|
||||
break
|
||||
for row in rows:
|
||||
site_id = row.get("id") or row.get("DT_RowId")
|
||||
location = row.get("location") or row.get("roadway") or "GA Camera"
|
||||
lat_lng = row.get("latLng") or {}
|
||||
geography = lat_lng.get("geography") if isinstance(lat_lng, dict) else {}
|
||||
lat, lon = _parse_wkt_point(geography.get("wellKnownText") if isinstance(geography, dict) else "")
|
||||
images = row.get("images") or []
|
||||
image = next(
|
||||
(
|
||||
candidate
|
||||
for candidate in images
|
||||
if str(candidate.get("imageUrl") or "").strip()
|
||||
and not bool(candidate.get("blocked"))
|
||||
),
|
||||
None,
|
||||
)
|
||||
if not (site_id and image and lat is not None and lon is not None):
|
||||
continue
|
||||
media_url = _normalize_cctv_media_url(
|
||||
urljoin(self.BASE_URL, str(image.get("imageUrl") or "").strip())
|
||||
)
|
||||
cameras.append(
|
||||
{
|
||||
"id": f"GDOT-{site_id}",
|
||||
"source_agency": "Georgia DOT",
|
||||
"lat": lat,
|
||||
"lon": lon,
|
||||
"direction_facing": str(location)[:120],
|
||||
"media_url": media_url,
|
||||
"media_type": "image",
|
||||
"refresh_rate_seconds": 60,
|
||||
}
|
||||
)
|
||||
start += len(rows)
|
||||
draw += 1
|
||||
total = int(data.get("recordsTotal") or 0)
|
||||
if total and start >= total:
|
||||
break
|
||||
if not total and len(rows) < self.PAGE_SIZE:
|
||||
break
|
||||
return cameras
|
||||
return _fetch_511_datatables_cameras(
|
||||
list_url="https://511ga.org/List/GetData/Cameras",
|
||||
base_url="https://511ga.org",
|
||||
id_prefix="GDOT",
|
||||
source_agency="Georgia DOT",
|
||||
referer="https://511ga.org/cctv",
|
||||
)
|
||||
|
||||
|
||||
class IllinoisDOTIngestor(BaseCCTVIngestor):
|
||||
@@ -1009,17 +1119,72 @@ def _extract_img_src(html_fragment: str):
|
||||
return None
|
||||
|
||||
|
||||
class AsfinagIngestor(BaseCCTVIngestor):
|
||||
"""Austria ASFINAG motorway webcams (Osiris port)."""
|
||||
|
||||
API_URL = "https://odo.asfinag.at/odo/rest/sec/resource/001/json/webcams?language=atDE"
|
||||
HEADERS = {
|
||||
"User-Agent": "Shadowbroker-CCTV/1.0",
|
||||
"Accept": "application/json",
|
||||
"Referer": "https://www.asfinag.at/",
|
||||
"Authorization": "Basic bWFwX3dpZGdldDp0ZWdkaXc=",
|
||||
}
|
||||
|
||||
def fetch_data(self) -> List[Dict[str, Any]]:
|
||||
try:
|
||||
response = fetch_with_curl(self.API_URL, timeout=15, headers=self.HEADERS)
|
||||
response.raise_for_status()
|
||||
payload = response.json()
|
||||
except Exception as exc:
|
||||
logger.error("AsfinagIngestor: fetch failed: %s", exc)
|
||||
return []
|
||||
if not isinstance(payload, list):
|
||||
return []
|
||||
cameras: List[Dict[str, Any]] = []
|
||||
for cam in payload:
|
||||
cam_id = cam.get("wcs_id")
|
||||
lat = cam.get("wgs84_lat")
|
||||
lon = cam.get("wgs84_lon")
|
||||
image_url = cam.get("url_campic")
|
||||
if not cam_id or lat is None or lon is None or not image_url:
|
||||
continue
|
||||
if str(cam_id).startswith("Utinform"):
|
||||
continue
|
||||
label = cam.get("position_txt") or cam.get("direction_txt") or "ASFINAG Webcam"
|
||||
secure_url = _ensure_https_url(image_url)
|
||||
if not secure_url:
|
||||
continue
|
||||
cameras.append(
|
||||
{
|
||||
"id": f"ASFINAG-{cam_id}",
|
||||
"source_agency": "ASFINAG Austria",
|
||||
"lat": float(lat),
|
||||
"lon": float(lon),
|
||||
"direction_facing": label,
|
||||
"media_url": secure_url,
|
||||
"media_type": "image",
|
||||
"refresh_rate_seconds": 300,
|
||||
}
|
||||
)
|
||||
logger.info("AsfinagIngestor: parsed %s cameras", len(cameras))
|
||||
return cameras
|
||||
|
||||
|
||||
class MadridCityIngestor(BaseCCTVIngestor):
|
||||
"""Madrid City Hall traffic cameras from datos.madrid.es KML feed."""
|
||||
|
||||
KML_URL = "http://datos.madrid.es/egob/catalogo/202088-0-trafico-camaras.kml"
|
||||
KML_URL = "https://datos.madrid.es/egob/catalogo/202088-0-trafico-camaras.kml"
|
||||
|
||||
def _fetch_kml(self):
|
||||
response = fetch_with_curl(self.KML_URL, timeout=20)
|
||||
response.raise_for_status()
|
||||
return response
|
||||
|
||||
def fetch_data(self) -> List[Dict[str, Any]]:
|
||||
import defusedxml.ElementTree as ET
|
||||
|
||||
try:
|
||||
response = fetch_with_curl(self.KML_URL, timeout=20)
|
||||
response.raise_for_status()
|
||||
response = self._fetch_kml()
|
||||
except Exception as e:
|
||||
logger.error(f"MadridCityIngestor: failed to fetch KML: {e}")
|
||||
return []
|
||||
@@ -1055,6 +1220,9 @@ class MadridCityIngestor(BaseCCTVIngestor):
|
||||
if desc_el is not None and desc_el.text:
|
||||
image_url = _extract_img_src(desc_el.text)
|
||||
|
||||
if not image_url:
|
||||
continue
|
||||
image_url = _ensure_https_url(image_url)
|
||||
if not image_url:
|
||||
continue
|
||||
|
||||
@@ -1076,6 +1244,153 @@ class MadridCityIngestor(BaseCCTVIngestor):
|
||||
return cameras
|
||||
|
||||
|
||||
class Ontario511Ingestor(BaseCCTVIngestor):
|
||||
"""Ontario highway cameras via 511on.ca TravelIQ API."""
|
||||
|
||||
def fetch_data(self) -> List[Dict[str, Any]]:
|
||||
return _fetch_traveliq_v2_cameras(
|
||||
api_url="https://511on.ca/api/v2/get/cameras",
|
||||
base_url="https://511on.ca",
|
||||
id_prefix="ON511",
|
||||
source_agency="511 Ontario",
|
||||
)
|
||||
|
||||
|
||||
class Alberta511Ingestor(BaseCCTVIngestor):
|
||||
"""Alberta highway cameras via 511 Alberta TravelIQ API."""
|
||||
|
||||
def fetch_data(self) -> List[Dict[str, Any]]:
|
||||
return _fetch_traveliq_v2_cameras(
|
||||
api_url="https://511.alberta.ca/api/v2/get/cameras",
|
||||
base_url="https://511.alberta.ca",
|
||||
id_prefix="AB511",
|
||||
source_agency="511 Alberta",
|
||||
)
|
||||
|
||||
|
||||
class Florida511Ingestor(BaseCCTVIngestor):
|
||||
"""Florida cameras via FL511 DataTables feed (~4,800 sites)."""
|
||||
|
||||
def fetch_data(self) -> List[Dict[str, Any]]:
|
||||
return _fetch_511_datatables_cameras(
|
||||
list_url="https://fl511.com/List/GetData/Cameras",
|
||||
base_url="https://fl511.com",
|
||||
id_prefix="FL511",
|
||||
source_agency="Florida 511",
|
||||
referer="https://fl511.com/",
|
||||
)
|
||||
|
||||
|
||||
class AustraliaLiveTrafficIngestor(BaseCCTVIngestor):
|
||||
"""NSW / Australia live traffic cameras via Transport for NSW JSON feed."""
|
||||
|
||||
URL = "https://www.livetraffic.com/datajson/all-feeds-web.json"
|
||||
|
||||
def fetch_data(self) -> List[Dict[str, Any]]:
|
||||
resp = fetch_with_curl(self.URL, timeout=35, headers={"Accept": "application/json"})
|
||||
if not resp or resp.status_code != 200:
|
||||
logger.error(
|
||||
"Australia Live Traffic CCTV fetch failed: HTTP %s",
|
||||
resp.status_code if resp else "no response",
|
||||
)
|
||||
return []
|
||||
|
||||
data = resp.json()
|
||||
if not isinstance(data, list):
|
||||
return []
|
||||
|
||||
cameras: List[Dict[str, Any]] = []
|
||||
for item in data:
|
||||
if not isinstance(item, dict) or item.get("eventType") != "liveCams":
|
||||
continue
|
||||
geometry = item.get("geometry") if isinstance(item.get("geometry"), dict) else {}
|
||||
coords = geometry.get("coordinates") if isinstance(geometry.get("coordinates"), list) else []
|
||||
if len(coords) < 2:
|
||||
continue
|
||||
try:
|
||||
lon = float(coords[0])
|
||||
lat = float(coords[1])
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
|
||||
props = item.get("properties") if isinstance(item.get("properties"), dict) else {}
|
||||
media_url = _ensure_https_url(str(props.get("href") or "").strip())
|
||||
if not media_url:
|
||||
continue
|
||||
|
||||
cam_id = str(item.get("path") or props.get("id") or len(cameras)).strip("/")
|
||||
label = str(props.get("title") or props.get("headline") or "Australia Camera")[:120]
|
||||
cameras.append(
|
||||
{
|
||||
"id": f"AUS-{cam_id}",
|
||||
"source_agency": "NSW Live Traffic",
|
||||
"lat": lat,
|
||||
"lon": lon,
|
||||
"direction_facing": label,
|
||||
"media_url": media_url,
|
||||
"media_type": "image",
|
||||
"refresh_rate_seconds": 120,
|
||||
}
|
||||
)
|
||||
logger.info("AustraliaLiveTrafficIngestor: parsed %s cameras", len(cameras))
|
||||
return cameras
|
||||
|
||||
|
||||
class NetherlandsRWSIngestor(BaseCCTVIngestor):
|
||||
"""Netherlands Rijkswaterstaat cameras from legacy NDW open-data JSON.
|
||||
|
||||
The opendata.ndw.nu/cameras.json feed Osiris used is often offline; when
|
||||
unavailable this ingestor returns an empty set and logs a warning.
|
||||
"""
|
||||
|
||||
URL = "https://opendata.ndw.nu/cameras.json"
|
||||
MAX_CAMERAS = 1200
|
||||
|
||||
def fetch_data(self) -> List[Dict[str, Any]]:
|
||||
resp = fetch_with_curl(self.URL, timeout=25, headers={"Accept": "application/json"})
|
||||
if not resp or resp.status_code != 200:
|
||||
logger.warning(
|
||||
"Netherlands RWS cameras.json unavailable (HTTP %s) — "
|
||||
"NDW retired this open-data endpoint; no cameras ingested",
|
||||
resp.status_code if resp else "no response",
|
||||
)
|
||||
return []
|
||||
|
||||
data = resp.json()
|
||||
if not isinstance(data, list):
|
||||
return []
|
||||
|
||||
cameras: List[Dict[str, Any]] = []
|
||||
for i, cam in enumerate(data[: self.MAX_CAMERAS]):
|
||||
if not isinstance(cam, dict):
|
||||
continue
|
||||
lat = cam.get("lat") if cam.get("lat") is not None else cam.get("latitude")
|
||||
lon = cam.get("lng") if cam.get("lng") is not None else cam.get("longitude")
|
||||
media_url = _ensure_https_url(
|
||||
str(cam.get("imageUrl") or cam.get("feed_url") or cam.get("url") or "").strip()
|
||||
)
|
||||
if lat is None or lon is None or not media_url:
|
||||
continue
|
||||
try:
|
||||
lat_f, lon_f = float(lat), float(lon)
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
cameras.append(
|
||||
{
|
||||
"id": f"NLRWS-{cam.get('id') or i}",
|
||||
"source_agency": "Rijkswaterstaat",
|
||||
"lat": lat_f,
|
||||
"lon": lon_f,
|
||||
"direction_facing": str(cam.get("name") or "Netherlands Camera")[:120],
|
||||
"media_url": media_url,
|
||||
"media_type": "image",
|
||||
"refresh_rate_seconds": 120,
|
||||
}
|
||||
)
|
||||
logger.info("NetherlandsRWSIngestor: parsed %s cameras", len(cameras))
|
||||
return cameras
|
||||
|
||||
|
||||
def _detect_media_type(url: str) -> str:
|
||||
"""Detect the media type from a camera URL for proper frontend rendering."""
|
||||
if not url:
|
||||
@@ -1094,29 +1409,40 @@ def _detect_media_type(url: str) -> str:
|
||||
return "image"
|
||||
|
||||
|
||||
def scheduled_cctv_ingestors() -> List[tuple["BaseCCTVIngestor", str]]:
|
||||
"""Canonical list of CCTV ingestors for startup, scheduler, and DB seeding."""
|
||||
return [
|
||||
(TFLJamCamIngestor(), "cctv_tfl"),
|
||||
(LTASingaporeIngestor(), "cctv_lta"),
|
||||
(AustinTXIngestor(), "cctv_atx"),
|
||||
(NYCDOTIngestor(), "cctv_nyc"),
|
||||
(CaltransIngestor(), "cctv_caltrans"),
|
||||
(ColoradoDOTIngestor(), "cctv_codot"),
|
||||
(WSDOTIngestor(), "cctv_wsdot"),
|
||||
(GeorgiaDOTIngestor(), "cctv_gdot"),
|
||||
(IllinoisDOTIngestor(), "cctv_idot"),
|
||||
(MichiganDOTIngestor(), "cctv_mdot"),
|
||||
(WindyWebcamsIngestor(), "cctv_windy"),
|
||||
(DGTNationalIngestor(), "cctv_dgt"),
|
||||
(MadridCityIngestor(), "cctv_madrid"),
|
||||
(OSMTrafficCameraIngestor(), "cctv_osm"),
|
||||
(AsfinagIngestor(), "cctv_asfinag"),
|
||||
(OSMALPRCameraIngestor(), "cctv_osm_alpr"),
|
||||
(Ontario511Ingestor(), "cctv_on511"),
|
||||
(Alberta511Ingestor(), "cctv_ab511"),
|
||||
(Florida511Ingestor(), "cctv_fl511"),
|
||||
(AustraliaLiveTrafficIngestor(), "cctv_australia"),
|
||||
(NetherlandsRWSIngestor(), "cctv_nl_rws"),
|
||||
]
|
||||
|
||||
|
||||
def run_all_ingestors():
|
||||
"""Run all CCTV ingestors synchronously. Used for first-run DB seeding."""
|
||||
ingestors = [
|
||||
TFLJamCamIngestor(),
|
||||
LTASingaporeIngestor(),
|
||||
AustinTXIngestor(),
|
||||
NYCDOTIngestor(),
|
||||
CaltransIngestor(),
|
||||
ColoradoDOTIngestor(),
|
||||
WSDOTIngestor(),
|
||||
GeorgiaDOTIngestor(),
|
||||
IllinoisDOTIngestor(),
|
||||
MichiganDOTIngestor(),
|
||||
WindyWebcamsIngestor(),
|
||||
OSMTrafficCameraIngestor(),
|
||||
DGTNationalIngestor(),
|
||||
MadridCityIngestor(),
|
||||
]
|
||||
for ing in ingestors:
|
||||
for ingestor, _name in scheduled_cctv_ingestors():
|
||||
try:
|
||||
ing.ingest()
|
||||
ingestor.ingest()
|
||||
except Exception as e:
|
||||
logger.warning(f"Ingestor {ing.__class__.__name__} failed during seed: {e}")
|
||||
logger.warning(f"Ingestor {ingestor.__class__.__name__} failed during seed: {e}")
|
||||
|
||||
|
||||
def get_all_cameras() -> List[Dict[str, Any]]:
|
||||
|
||||
@@ -30,6 +30,10 @@ class Settings(BaseSettings):
|
||||
MESH_MQTT_INCLUDE_DEFAULT_ROOTS: bool = True
|
||||
MESH_RNS_ENABLED: bool = False
|
||||
MESH_ARTI_ENABLED: bool = False
|
||||
# When true, trust wormhole_status.json ready bit if the child process is
|
||||
# alive — avoids transport-tier flapping when /api/health probes time out
|
||||
# under Tor load (common during live DM E2E).
|
||||
MESH_WORMHOLE_TRUST_FILE_READY: bool = False
|
||||
MESH_ARTI_SOCKS_PORT: int = 9050
|
||||
MESH_RELAY_PEERS: str = ""
|
||||
MESH_PUBLIC_PEER_URL: str = ""
|
||||
@@ -43,7 +47,24 @@ class Settings(BaseSettings):
|
||||
MESH_INFONET_ALLOW_CLEARNET_SYNC: bool = False
|
||||
MESH_BOOTSTRAP_DISABLED: bool = False
|
||||
MESH_BOOTSTRAP_MANIFEST_PATH: str = "data/bootstrap_peers.json"
|
||||
MESH_BOOTSTRAP_SIGNER_PUBLIC_KEY: str = ""
|
||||
# Public sb-testnet-0 fleet signer (participants). Seed operator holds the private key.
|
||||
MESH_BOOTSTRAP_SIGNER_PUBLIC_KEY: str = (
|
||||
"ul1d0kj/ODPIp0OhHzX8eLAVXzJ3CVvzW1vn2IC6q3I="
|
||||
)
|
||||
MESH_BOOTSTRAP_SIGNER_PRIVATE_KEY: str = ""
|
||||
# When true, empty MESH_PEER_PUSH_SECRET uses the public fleet HMAC for seed join/announce.
|
||||
MESH_INFONET_FLEET_JOIN: bool = True
|
||||
MESH_INFONET_FLEET_JOIN_DISABLED: bool = False
|
||||
# Headless relay/seed compose: auto-enable Tor wormhole on startup so
|
||||
# docker compose redeploys keep the fleet onion reachable.
|
||||
MESH_INFONET_RELAY_AUTO_WORMHOLE: bool = False
|
||||
MESH_INFONET_RELAY_AUTO_WORMHOLE_DISABLED: bool = False
|
||||
MESH_BOOTSTRAP_SIGNER_ID: str = ""
|
||||
MESH_PEER_REGISTRY_ENABLED: bool = False
|
||||
MESH_PEER_REGISTRY_DISABLED: bool = False
|
||||
MESH_PEER_REGISTRY_STALE_S: int = 604800
|
||||
MESH_SWARM_MANIFEST_TTL_S: int = 14400
|
||||
MESH_SWARM_MANIFEST_PULL_INTERVAL_S: int = 300
|
||||
MESH_NODE_MODE: str = "participant"
|
||||
MESH_SYNC_INTERVAL_S: int = 300
|
||||
MESH_SYNC_FAILURE_BACKOFF_S: int = 60
|
||||
|
||||
@@ -19,6 +19,7 @@ import concurrent.futures
|
||||
import json
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
import threading
|
||||
import time
|
||||
from datetime import datetime, timedelta
|
||||
@@ -75,6 +76,7 @@ from services.fetchers.infrastructure import ( # noqa: F401
|
||||
fetch_tinygs,
|
||||
fetch_psk_reporter,
|
||||
)
|
||||
from services.fetchers.road_corridor_sat import fetch_road_corridor_trends # noqa: F401
|
||||
from services.fetchers.geo import ( # noqa: F401
|
||||
fetch_ships,
|
||||
fetch_airports,
|
||||
@@ -99,6 +101,10 @@ from services.fetchers.crowdthreat import fetch_crowdthreat # noqa: F401
|
||||
from services.fetchers.wastewater import fetch_wastewater # noqa: F401
|
||||
from services.fetchers.sar_catalog import fetch_sar_catalog # noqa: F401
|
||||
from services.fetchers.sar_products import fetch_sar_products # noqa: F401
|
||||
from services.fetchers.malware import fetch_malware_threats # noqa: F401
|
||||
from services.fetchers.telegram_osint import fetch_telegram_osint # noqa: F401
|
||||
from services.fetchers.cyber_status import fetch_cyber_threats # noqa: F401
|
||||
from services.scm.suppliers import fetch_scm_suppliers # noqa: F401
|
||||
from services.ais_stream import prune_stale_vessels # noqa: F401
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -144,13 +150,18 @@ _STARTUP_HEAVY_REFRESH_DELAY_S = float(os.environ.get("SHADOWBROKER_STARTUP_HEAV
|
||||
_STARTUP_HEAVY_REFRESH_STARTED = False
|
||||
_STARTUP_HEAVY_REFRESH_LOCK = threading.Lock()
|
||||
_FETCH_WORKERS = int(os.environ.get("SHADOWBROKER_FETCH_WORKERS", "8"))
|
||||
_HEAVY_FETCH_WORKERS = int(os.environ.get("SHADOWBROKER_HEAVY_FETCH_WORKERS", "2"))
|
||||
_SLOW_FETCH_CONCURRENCY = int(os.environ.get("SHADOWBROKER_SLOW_FETCH_CONCURRENCY", "4"))
|
||||
_STARTUP_HEAVY_CONCURRENCY = int(os.environ.get("SHADOWBROKER_STARTUP_HEAVY_CONCURRENCY", "2"))
|
||||
|
||||
# Shared thread pool — reused across all fetch cycles instead of creating/destroying per tick
|
||||
# Fast-tier pool (flights, ships, sigint, …). Slow / heavy work uses a separate pool
|
||||
# so Playwright, GDELT, CCTV ingest, etc. cannot starve the 60s refresh path (#375).
|
||||
_SHARED_EXECUTOR = concurrent.futures.ThreadPoolExecutor(
|
||||
max_workers=max(2, _FETCH_WORKERS), thread_name_prefix="fetch"
|
||||
)
|
||||
_SLOW_EXECUTOR = concurrent.futures.ThreadPoolExecutor(
|
||||
max_workers=max(1, _HEAVY_FETCH_WORKERS), thread_name_prefix="fetch-slow"
|
||||
)
|
||||
|
||||
|
||||
def _cache_json_safe(value):
|
||||
@@ -319,10 +330,49 @@ def seed_startup_caches() -> None:
|
||||
# ---------------------------------------------------------------------------
|
||||
# Scheduler & Orchestration
|
||||
# ---------------------------------------------------------------------------
|
||||
def _executor_for_task_label(label: str) -> concurrent.futures.ThreadPoolExecutor:
|
||||
if label.startswith(("slow-tier", "startup-heavy")):
|
||||
return _SLOW_EXECUTOR
|
||||
return _SHARED_EXECUTOR
|
||||
|
||||
|
||||
def _run_task_with_health_on_executor(
|
||||
executor: concurrent.futures.ThreadPoolExecutor,
|
||||
func,
|
||||
name: str | None = None,
|
||||
) -> None:
|
||||
"""Run a scheduled job on the given pool so it cannot starve fast-tier workers."""
|
||||
task_name = name or getattr(func, "__name__", "task")
|
||||
future = executor.submit(func)
|
||||
start = time.perf_counter()
|
||||
try:
|
||||
future.result(timeout=_TASK_HARD_TIMEOUT_S)
|
||||
duration = time.perf_counter() - start
|
||||
from services.fetch_health import record_success
|
||||
|
||||
record_success(task_name, duration_s=duration)
|
||||
if duration > _SLOW_FETCH_S:
|
||||
logger.warning("task slow: %s took %.2fs", task_name, duration)
|
||||
except concurrent.futures.TimeoutError:
|
||||
future.cancel()
|
||||
duration = time.perf_counter() - start
|
||||
from services.fetch_health import record_failure
|
||||
|
||||
record_failure(task_name, error=TimeoutError(f"{task_name} timed out"), duration_s=duration)
|
||||
logger.error("task timed out: %s (%.2fs)", task_name, duration)
|
||||
except Exception as e:
|
||||
duration = time.perf_counter() - start
|
||||
from services.fetch_health import record_failure
|
||||
|
||||
record_failure(task_name, error=e, duration_s=duration)
|
||||
logger.exception("task failed: %s", task_name)
|
||||
|
||||
|
||||
def _run_tasks(label: str, funcs: list, *, max_concurrency: int | None = None):
|
||||
"""Run tasks concurrently and log any exceptions (do not fail silently)."""
|
||||
if not funcs:
|
||||
return
|
||||
executor = _executor_for_task_label(label)
|
||||
if max_concurrency is None:
|
||||
if label.startswith("slow-tier"):
|
||||
max_concurrency = _SLOW_FETCH_CONCURRENCY
|
||||
@@ -330,12 +380,13 @@ def _run_tasks(label: str, funcs: list, *, max_concurrency: int | None = None):
|
||||
max_concurrency = _STARTUP_HEAVY_CONCURRENCY
|
||||
else:
|
||||
max_concurrency = len(funcs)
|
||||
max_concurrency = max(1, min(max_concurrency, len(funcs)))
|
||||
pool_workers = getattr(executor, "_max_workers", len(funcs))
|
||||
max_concurrency = max(1, min(max_concurrency, len(funcs), pool_workers))
|
||||
|
||||
remaining_funcs = list(funcs)
|
||||
while remaining_funcs:
|
||||
batch, remaining_funcs = remaining_funcs[:max_concurrency], remaining_funcs[max_concurrency:]
|
||||
futures = {_SHARED_EXECUTOR.submit(func): (func.__name__, time.perf_counter()) for func in batch}
|
||||
futures = {executor.submit(func): (func.__name__, time.perf_counter()) for func in batch}
|
||||
_drain_task_futures(label, futures)
|
||||
|
||||
|
||||
@@ -352,6 +403,13 @@ def _drain_task_futures(label: str, futures: dict):
|
||||
record_success(name, duration_s=duration)
|
||||
if duration > _SLOW_FETCH_S:
|
||||
logger.warning(f"{label} task slow: {name} took {duration:.2f}s")
|
||||
except concurrent.futures.TimeoutError:
|
||||
future.cancel()
|
||||
duration = time.perf_counter() - start
|
||||
from services.fetch_health import record_failure
|
||||
|
||||
record_failure(name, error=TimeoutError(f"{name} timed out"), duration_s=duration)
|
||||
logger.error("%s task timed out: %s (%.2fs)", label, name, duration)
|
||||
except Exception as e:
|
||||
duration = time.perf_counter() - start
|
||||
from services.fetch_health import record_failure
|
||||
@@ -405,7 +463,6 @@ def update_slow_data():
|
||||
logger.info("Slow-tier data update starting...")
|
||||
slow_funcs = [
|
||||
fetch_news,
|
||||
fetch_prediction_markets,
|
||||
fetch_earthquakes,
|
||||
fetch_firms_fires,
|
||||
fetch_firms_country_fires,
|
||||
@@ -427,6 +484,9 @@ def update_slow_data():
|
||||
fetch_fishing_activity,
|
||||
fetch_power_plants,
|
||||
fetch_ukraine_air_raid_alerts,
|
||||
fetch_malware_threats,
|
||||
fetch_cyber_threats,
|
||||
fetch_scm_suppliers,
|
||||
]
|
||||
_run_tasks("slow-tier", slow_funcs)
|
||||
# Run correlation engine after all data is fresh
|
||||
@@ -470,6 +530,15 @@ def _load_cctv_cache_for_startup() -> None:
|
||||
logger.warning("Startup CCTV cache load failed (non-fatal): %s", e)
|
||||
|
||||
|
||||
def _load_static_infrastructure_for_startup() -> None:
|
||||
"""Disk-backed reference layers — instant, no network."""
|
||||
for func in (fetch_datacenters, fetch_military_bases, fetch_power_plants):
|
||||
try:
|
||||
func()
|
||||
except Exception as e:
|
||||
logger.warning("Startup static infrastructure load failed for %s: %s", func.__name__, e)
|
||||
|
||||
|
||||
def _run_delayed_startup_heavy_refresh() -> None:
|
||||
if _STARTUP_HEAVY_REFRESH_DELAY_S > 0:
|
||||
logger.info(
|
||||
@@ -482,6 +551,7 @@ def _run_delayed_startup_heavy_refresh() -> None:
|
||||
"startup-heavy",
|
||||
[
|
||||
update_slow_data,
|
||||
fetch_telegram_osint,
|
||||
fetch_volcanoes,
|
||||
fetch_viirs_change_nodes,
|
||||
fetch_unusual_whales,
|
||||
@@ -520,6 +590,7 @@ def update_all_data(*, startup_mode: bool = False):
|
||||
logger.info("Full data update starting (parallel)...")
|
||||
# Preload Meshtastic map cache immediately (instant, from disk)
|
||||
seed_startup_caches()
|
||||
_load_static_infrastructure_for_startup()
|
||||
with _data_lock:
|
||||
meshtastic_seeded = bool(latest_data.get("meshtastic_map_nodes"))
|
||||
if startup_mode:
|
||||
@@ -596,22 +667,9 @@ def update_all_data(*, startup_mode: bool = False):
|
||||
# (the scheduled job also runs every 10 min for ongoing refresh).
|
||||
if startup_mode:
|
||||
try:
|
||||
from services.cctv_pipeline import (
|
||||
TFLJamCamIngestor, LTASingaporeIngestor, AustinTXIngestor,
|
||||
NYCDOTIngestor, CaltransIngestor, ColoradoDOTIngestor,
|
||||
WSDOTIngestor, GeorgiaDOTIngestor, IllinoisDOTIngestor,
|
||||
MichiganDOTIngestor, WindyWebcamsIngestor, DGTNationalIngestor,
|
||||
MadridCityIngestor, OSMTrafficCameraIngestor, get_all_cameras,
|
||||
)
|
||||
from services.cctv_pipeline import OSMALPRCameraIngestor
|
||||
_startup_ingestors = [
|
||||
TFLJamCamIngestor(), LTASingaporeIngestor(), AustinTXIngestor(),
|
||||
NYCDOTIngestor(), CaltransIngestor(), ColoradoDOTIngestor(),
|
||||
WSDOTIngestor(), GeorgiaDOTIngestor(), IllinoisDOTIngestor(),
|
||||
MichiganDOTIngestor(), WindyWebcamsIngestor(), DGTNationalIngestor(),
|
||||
MadridCityIngestor(), OSMTrafficCameraIngestor(),
|
||||
OSMALPRCameraIngestor(),
|
||||
]
|
||||
from services.cctv_pipeline import get_all_cameras, scheduled_cctv_ingestors
|
||||
|
||||
_startup_ingestors = [ing for ing, _name in scheduled_cctv_ingestors()]
|
||||
logger.info("Running CCTV ingest at startup (%d ingestors)...", len(_startup_ingestors))
|
||||
ingest_futures = {
|
||||
_SHARED_EXECUTOR.submit(ing.ingest): ing.__class__.__name__
|
||||
@@ -747,6 +805,39 @@ def start_scheduler():
|
||||
misfire_grace_time=120,
|
||||
)
|
||||
|
||||
# Telegram OSINT — hourly t.me/s channel scrape (kept off the 5-minute slow tier).
|
||||
_telegram_interval_m = max(15, int(os.environ.get("TELEGRAM_OSINT_INTERVAL_MINUTES", "60")))
|
||||
_scheduler.add_job(
|
||||
lambda: _run_task_with_health(fetch_telegram_osint, "fetch_telegram_osint"),
|
||||
"interval",
|
||||
minutes=_telegram_interval_m,
|
||||
next_run_time=datetime.utcnow() + timedelta(seconds=45),
|
||||
id="telegram_osint",
|
||||
max_instances=1,
|
||||
misfire_grace_time=600,
|
||||
)
|
||||
|
||||
# Prediction markets — own jittered cadence (Polymarket/Kalshi clearnet egress).
|
||||
# Kept off the fixed 5-minute slow tier so poll timing is less fingerprintable.
|
||||
from services.fetchers.prediction_markets import fetch_prediction_markets
|
||||
|
||||
_pm_interval_m = max(5, int(os.environ.get("PREDICTION_MARKETS_INTERVAL_MINUTES", "7")))
|
||||
_pm_jitter_s = max(0, int(os.environ.get("PREDICTION_MARKETS_SCHEDULER_JITTER_S", "240")))
|
||||
_pm_initial_max_s = max(0, int(os.environ.get("PREDICTION_MARKETS_INITIAL_DELAY_MAX_S", "180")))
|
||||
_pm_first_run = datetime.utcnow() + timedelta(
|
||||
seconds=random.randint(30, max(30, _pm_initial_max_s))
|
||||
)
|
||||
_scheduler.add_job(
|
||||
lambda: _run_task_with_health(fetch_prediction_markets, "fetch_prediction_markets"),
|
||||
"interval",
|
||||
minutes=_pm_interval_m,
|
||||
jitter=_pm_jitter_s,
|
||||
next_run_time=_pm_first_run,
|
||||
id="prediction_markets",
|
||||
max_instances=1,
|
||||
misfire_grace_time=300,
|
||||
)
|
||||
|
||||
# Weather alerts — every 5 minutes (time-critical, separate from slow tier)
|
||||
_scheduler.add_job(
|
||||
lambda: _run_task_with_health(fetch_weather_alerts, "fetch_weather_alerts"),
|
||||
@@ -844,7 +935,7 @@ def start_scheduler():
|
||||
|
||||
# GDELT — every 30 minutes (downloads 32 ZIP files per call, avoid rate limits)
|
||||
_scheduler.add_job(
|
||||
lambda: _run_task_with_health(fetch_gdelt, "fetch_gdelt"),
|
||||
lambda: _run_task_with_health_on_executor(_SLOW_EXECUTOR, fetch_gdelt, "fetch_gdelt"),
|
||||
"interval",
|
||||
minutes=30,
|
||||
id="gdelt",
|
||||
@@ -852,7 +943,9 @@ def start_scheduler():
|
||||
misfire_grace_time=120,
|
||||
)
|
||||
_scheduler.add_job(
|
||||
lambda: _run_task_with_health(update_liveuamap, "update_liveuamap"),
|
||||
lambda: _run_task_with_health_on_executor(
|
||||
_SLOW_EXECUTOR, update_liveuamap, "update_liveuamap"
|
||||
),
|
||||
"interval",
|
||||
minutes=30,
|
||||
id="liveuamap",
|
||||
@@ -862,39 +955,9 @@ def start_scheduler():
|
||||
|
||||
# CCTV pipeline refresh — runs all ingestors, then refreshes in-memory data.
|
||||
# Delay the first run slightly so startup serves cached/DB-backed data first.
|
||||
from services.cctv_pipeline import (
|
||||
TFLJamCamIngestor,
|
||||
LTASingaporeIngestor,
|
||||
AustinTXIngestor,
|
||||
NYCDOTIngestor,
|
||||
CaltransIngestor,
|
||||
ColoradoDOTIngestor,
|
||||
WSDOTIngestor,
|
||||
GeorgiaDOTIngestor,
|
||||
IllinoisDOTIngestor,
|
||||
MichiganDOTIngestor,
|
||||
WindyWebcamsIngestor,
|
||||
DGTNationalIngestor,
|
||||
MadridCityIngestor,
|
||||
OSMTrafficCameraIngestor,
|
||||
)
|
||||
from services.cctv_pipeline import scheduled_cctv_ingestors
|
||||
|
||||
_cctv_ingestors = [
|
||||
(TFLJamCamIngestor(), "cctv_tfl"),
|
||||
(LTASingaporeIngestor(), "cctv_lta"),
|
||||
(AustinTXIngestor(), "cctv_atx"),
|
||||
(NYCDOTIngestor(), "cctv_nyc"),
|
||||
(CaltransIngestor(), "cctv_caltrans"),
|
||||
(ColoradoDOTIngestor(), "cctv_codot"),
|
||||
(WSDOTIngestor(), "cctv_wsdot"),
|
||||
(GeorgiaDOTIngestor(), "cctv_gdot"),
|
||||
(IllinoisDOTIngestor(), "cctv_idot"),
|
||||
(MichiganDOTIngestor(), "cctv_mdot"),
|
||||
(WindyWebcamsIngestor(), "cctv_windy"),
|
||||
(DGTNationalIngestor(), "cctv_dgt"),
|
||||
(MadridCityIngestor(), "cctv_madrid"),
|
||||
(OSMTrafficCameraIngestor(), "cctv_osm"),
|
||||
]
|
||||
_cctv_ingestors = scheduled_cctv_ingestors()
|
||||
|
||||
def _run_cctv_ingest_cycle():
|
||||
from services.fetchers._store import is_any_active
|
||||
@@ -913,7 +976,9 @@ def start_scheduler():
|
||||
logger.warning(f"CCTV post-ingest refresh failed: {e}")
|
||||
|
||||
_scheduler.add_job(
|
||||
_run_cctv_ingest_cycle,
|
||||
lambda: _run_task_with_health_on_executor(
|
||||
_SLOW_EXECUTOR, _run_cctv_ingest_cycle, "cctv_ingest_cycle"
|
||||
),
|
||||
"interval",
|
||||
minutes=10,
|
||||
id="cctv_ingest",
|
||||
@@ -983,6 +1048,16 @@ def start_scheduler():
|
||||
misfire_grace_time=600,
|
||||
)
|
||||
|
||||
# Sentinel-2 road corridor freight trends — daily (opt-in, heavy CDSE usage)
|
||||
_scheduler.add_job(
|
||||
lambda: _run_task_with_health(fetch_road_corridor_trends, "fetch_road_corridor_trends"),
|
||||
"interval",
|
||||
hours=24,
|
||||
id="road_corridor_trends",
|
||||
max_instances=1,
|
||||
misfire_grace_time=3600,
|
||||
)
|
||||
|
||||
# FIMI disinformation index — every 12 hours (weekly editorial feed)
|
||||
_scheduler.add_job(
|
||||
lambda: _run_task_with_health(fetch_fimi, "fetch_fimi"),
|
||||
@@ -993,9 +1068,9 @@ def start_scheduler():
|
||||
misfire_grace_time=600,
|
||||
)
|
||||
|
||||
# UAP sightings (NUFORC) — weekly on Mondays at 12:00 UTC. The layer is a
|
||||
# rolling last-60-days digest; refreshing once a week is enough cadence
|
||||
# for human-readable map exploration and keeps load on nuforc.org light.
|
||||
# UAP sightings (NUFORC) — weekly Mondays 12:00 UTC. Rolling ~60-day window;
|
||||
# each self-hosted install pulls live nuforc.org so operators see current
|
||||
# reports (typically ~400–500 mappable pins). Disk cache TTL defaults to 7d.
|
||||
_scheduler.add_job(
|
||||
lambda: _run_task_with_health(
|
||||
lambda: fetch_uap_sightings(force_refresh=True),
|
||||
@@ -1130,7 +1205,10 @@ def start_scheduler():
|
||||
def stop_scheduler():
|
||||
if _scheduler:
|
||||
_scheduler.shutdown(wait=False)
|
||||
_SLOW_EXECUTOR.shutdown(wait=False, cancel_futures=True)
|
||||
|
||||
|
||||
def get_latest_data():
|
||||
return get_latest_data_subset(*latest_data.keys())
|
||||
from services.fetchers._store import get_latest_data_deepcopy_snapshot
|
||||
|
||||
return get_latest_data_deepcopy_snapshot()
|
||||
|
||||
@@ -46,6 +46,7 @@ _CRITICAL_WARN = {
|
||||
|
||||
_OPTIONAL = {
|
||||
"AIS_API_KEY": "AIS vessel streaming (ships layer will be empty without it)",
|
||||
"GFW_API_TOKEN": "Global Fishing Watch fishing-vessel activity (fishing_activity layer)",
|
||||
"LTA_ACCOUNT_KEY": "Singapore LTA traffic cameras (CCTV layer)",
|
||||
"PUBLIC_API_KEY": "Optional client auth for public endpoints (recommended for exposed deployments)",
|
||||
}
|
||||
|
||||
@@ -69,6 +69,11 @@ class DashboardData(TypedDict, total=False):
|
||||
sar_scenes: List[Dict[str, Any]]
|
||||
sar_anomalies: List[Dict[str, Any]]
|
||||
sar_aoi_coverage: List[Dict[str, Any]]
|
||||
road_corridor_trends: Dict[str, Any]
|
||||
malware_threats: Dict[str, Any]
|
||||
cyber_threats: Dict[str, Any]
|
||||
scm_suppliers: Dict[str, Any]
|
||||
telegram_osint: Dict[str, Any]
|
||||
|
||||
|
||||
# In-memory store
|
||||
@@ -119,6 +124,11 @@ latest_data: DashboardData = {
|
||||
"sar_scenes": [],
|
||||
"sar_anomalies": [],
|
||||
"sar_aoi_coverage": [],
|
||||
"road_corridor_trends": {"updated_at": None, "corridors": []},
|
||||
"malware_threats": {"threats": [], "total": 0, "timestamp": None},
|
||||
"cyber_threats": {"threats": [], "stats": {}},
|
||||
"scm_suppliers": {"suppliers": [], "total": 0, "critical_count": 0},
|
||||
"telegram_osint": {"posts": [], "total": 0, "geolocated": 0, "timestamp": None},
|
||||
}
|
||||
|
||||
# Per-source freshness timestamps
|
||||
@@ -230,27 +240,35 @@ _active_layers_version: int = 0
|
||||
def bump_active_layers_version() -> None:
|
||||
"""Increment the active-layer version when frontend toggles change response shape."""
|
||||
global _active_layers_version
|
||||
_active_layers_version += 1
|
||||
with _data_lock:
|
||||
_active_layers_version += 1
|
||||
|
||||
|
||||
def get_active_layers_version() -> int:
|
||||
"""Return the current active-layer version (for ETag generation)."""
|
||||
return _active_layers_version
|
||||
with _data_lock:
|
||||
return _active_layers_version
|
||||
|
||||
|
||||
def get_latest_data_subset(*keys: str) -> DashboardData:
|
||||
"""Return a deep snapshot of only the requested top-level keys.
|
||||
|
||||
This avoids cloning the entire dashboard store for endpoints that only need
|
||||
a small tier-specific subset. Deep copy ensures callers cannot mutate
|
||||
nested structures (e.g. individual flight dicts) and affect the live store.
|
||||
Grabs references under the lock, then deep-copies outside it so fetcher
|
||||
writers are not blocked for the duration of a large clone (#375).
|
||||
"""
|
||||
with _data_lock:
|
||||
snap: DashboardData = {}
|
||||
for key in keys:
|
||||
value = latest_data.get(key)
|
||||
snap[key] = copy.deepcopy(value)
|
||||
return snap
|
||||
items = [(key, latest_data.get(key)) for key in keys]
|
||||
snap: DashboardData = {}
|
||||
for key, value in items:
|
||||
snap[key] = copy.deepcopy(value)
|
||||
return snap
|
||||
|
||||
|
||||
def get_latest_data_deepcopy_snapshot() -> DashboardData:
|
||||
"""Deep-copy the full dashboard for legacy /api/live-data consumers."""
|
||||
with _data_lock:
|
||||
items = list(latest_data.items())
|
||||
return {key: copy.deepcopy(value) for key, value in items}
|
||||
|
||||
|
||||
def get_latest_data_subset_refs(*keys: str) -> DashboardData:
|
||||
@@ -320,6 +338,12 @@ active_layers: dict[str, bool] = {
|
||||
"ai_intel": True,
|
||||
"crowdthreat": False,
|
||||
"sar": True,
|
||||
"road_corridor_trends": False,
|
||||
"malware_c2": False,
|
||||
"submarine_cables": False,
|
||||
"scm_suppliers": False,
|
||||
"cyber_threats": False,
|
||||
"telegram_osint": True,
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -38,8 +38,6 @@ _S3_NS = "{http://s3.amazonaws.com/doc/2006-03-01/}"
|
||||
_REFRESH_INTERVAL_S = 5 * 24 * 3600
|
||||
_LIST_TIMEOUT_S = 30
|
||||
_DOWNLOAD_TIMEOUT_S = 600
|
||||
from services.network_utils import DEFAULT_USER_AGENT as _USER_AGENT
|
||||
|
||||
_lock = threading.RLock()
|
||||
_aircraft_by_hex: dict[str, dict[str, str]] = {}
|
||||
_last_refresh = 0.0
|
||||
|
||||
@@ -0,0 +1,62 @@
|
||||
"""CISA KEV + cyber threat stats (Osiris port)."""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
|
||||
from services.fetchers._store import _data_lock, _mark_fresh, is_any_active, latest_data
|
||||
from services.network_utils import fetch_with_curl
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def fetch_cyber_threats() -> dict[str, Any]:
|
||||
if not is_any_active("cyber_threats"):
|
||||
return latest_data.get("cyber_threats") or {"threats": [], "stats": {}}
|
||||
|
||||
results: dict[str, Any] = {"threats": [], "stats": {}, "timestamp": datetime.now(timezone.utc).isoformat()}
|
||||
try:
|
||||
resp = fetch_with_curl(
|
||||
"https://www.cisa.gov/sites/default/files/feeds/known_exploited_vulnerabilities.json",
|
||||
timeout=15,
|
||||
)
|
||||
if resp.status_code == 200:
|
||||
data = resp.json()
|
||||
vulns = data.get("vulnerabilities") or []
|
||||
results["stats"]["cisa_total"] = len(vulns)
|
||||
now = datetime.now(timezone.utc)
|
||||
recent = []
|
||||
for v in vulns:
|
||||
try:
|
||||
added = datetime.fromisoformat(v.get("dateAdded", "").replace("Z", "+00:00"))
|
||||
days = (now - added).total_seconds() / 86400
|
||||
except Exception:
|
||||
continue
|
||||
if days <= 30:
|
||||
recent.append(v)
|
||||
recent = recent[:10]
|
||||
results["threats"] = [
|
||||
{
|
||||
"id": v.get("cveID"),
|
||||
"name": v.get("vulnerabilityName"),
|
||||
"vendor": v.get("vendorProject"),
|
||||
"product": v.get("product"),
|
||||
"severity": "CRITICAL",
|
||||
"date": v.get("dateAdded"),
|
||||
"due": v.get("dueDate"),
|
||||
"source": "CISA KEV",
|
||||
}
|
||||
for v in recent
|
||||
]
|
||||
except Exception as exc:
|
||||
logger.warning("CISA KEV fetch failed: %s", exc)
|
||||
|
||||
count = len(results["threats"])
|
||||
results["stats"]["active_cves"] = count
|
||||
results["stats"]["threat_level"] = "CRITICAL" if count >= 8 else "HIGH" if count >= 4 else "ELEVATED"
|
||||
|
||||
with _data_lock:
|
||||
latest_data["cyber_threats"] = results
|
||||
_mark_fresh("cyber_threats")
|
||||
return results
|
||||
@@ -692,7 +692,8 @@ _NUFORC_TILESET = "nuforc.cmm18aqea06bu1mmselhpnano-0ce5v"
|
||||
_NUFORC_TOKEN = os.environ.get("NUFORC_MAPBOX_TOKEN", "").strip()
|
||||
_NUFORC_RADIUS_M = 200_000 # 200 km query radius
|
||||
_NUFORC_LIMIT = 50 # max features per tilequery call
|
||||
_NUFORC_RECENT_DAYS = int(os.environ.get("NUFORC_RECENT_DAYS", "60"))
|
||||
# Rolling window shown on the map (~2 calendar months). Override via NUFORC_RECENT_DAYS.
|
||||
_NUFORC_RECENT_DAYS = max(1, int(os.environ.get("NUFORC_RECENT_DAYS", "60")))
|
||||
_NUFORC_HF_FALLBACK_LIMIT = max(25, int(os.environ.get("NUFORC_HF_FALLBACK_LIMIT", "250")))
|
||||
_NUFORC_HF_GEOCODE_LIMIT = max(25, int(os.environ.get("NUFORC_HF_GEOCODE_LIMIT", "150")))
|
||||
_NUFORC_GEOCODE_WORKERS = max(1, int(os.environ.get("NUFORC_GEOCODE_WORKERS", "1")))
|
||||
@@ -700,6 +701,12 @@ _NUFORC_GEOCODE_WORKERS = max(1, int(os.environ.get("NUFORC_GEOCODE_WORKERS", "1
|
||||
# practice, so a 0.3s spacing keeps us well under any soft throttle while
|
||||
# still rebuilding a full 12-month window in ~10 minutes.
|
||||
_NUFORC_GEOCODE_SPACING_S = float(os.environ.get("NUFORC_GEOCODE_SPACING_S", "0.3"))
|
||||
# Disk cache TTL — match the weekly scheduler so restarts between fetches still
|
||||
# serve the same rolling 60-day snapshot without hammering nuforc.org daily.
|
||||
_NUFORC_CACHE_TTL_S = max(
|
||||
3600,
|
||||
int(os.environ.get("NUFORC_CACHE_TTL_HOURS", "168")) * 3600,
|
||||
)
|
||||
_NUFORC_DATA_DIR = Path(__file__).resolve().parent.parent.parent / "data"
|
||||
_NUFORC_SIGHTINGS_CACHE_FILE = _NUFORC_DATA_DIR / "nuforc_recent_sightings.json"
|
||||
_NUFORC_LOCATION_CACHE_FILE = _NUFORC_DATA_DIR / "nuforc_location_cache.json"
|
||||
@@ -766,6 +773,35 @@ def _fetch_nuforc_tilequery(lng: float, lat: float) -> list[dict]:
|
||||
return []
|
||||
|
||||
|
||||
def _uap_cutoff_date_str() -> str:
|
||||
return (datetime.utcnow() - timedelta(days=_NUFORC_RECENT_DAYS)).strftime("%Y-%m-%d")
|
||||
|
||||
|
||||
def _uap_sighting_date_str(sighting: dict) -> str | None:
|
||||
"""Normalize a sighting row to YYYY-MM-DD for window filtering."""
|
||||
from services.fetchers.nuforc_enrichment import _parse_date
|
||||
|
||||
raw = str(sighting.get("date_time") or sighting.get("occurred") or "").strip()
|
||||
if not raw:
|
||||
return None
|
||||
parsed = _parse_date(raw)
|
||||
if parsed:
|
||||
return parsed
|
||||
if len(raw) >= 10 and raw[4] == "-" and raw[7] == "-":
|
||||
return raw[:10]
|
||||
return None
|
||||
|
||||
|
||||
def _filter_uap_sightings_recent(sightings: list[dict]) -> list[dict]:
|
||||
"""Drop anything outside the rolling NUFORC_RECENT_DAYS window."""
|
||||
cutoff = _uap_cutoff_date_str()
|
||||
return [
|
||||
sighting
|
||||
for sighting in sightings
|
||||
if (_uap_sighting_date_str(sighting) or "") >= cutoff
|
||||
]
|
||||
|
||||
|
||||
def _parse_nuforc_tile_date(value: str) -> datetime | None:
|
||||
raw = str(value or "").strip()
|
||||
if not raw:
|
||||
@@ -802,19 +838,41 @@ def _load_nuforc_sightings_cache(*, force_refresh: bool = False) -> list[dict] |
|
||||
built_dt = datetime.fromisoformat(built) if built else None
|
||||
if built_dt is None:
|
||||
return None
|
||||
if (datetime.utcnow() - built_dt).total_seconds() > 86400:
|
||||
if (datetime.utcnow() - built_dt).total_seconds() > _NUFORC_CACHE_TTL_S:
|
||||
return None
|
||||
if raw.get("cutoff_days") != _NUFORC_RECENT_DAYS:
|
||||
logger.info(
|
||||
"UAP sightings: cache cutoff_days mismatch (%s != %s); rebuilding",
|
||||
raw.get("cutoff_days"),
|
||||
_NUFORC_RECENT_DAYS,
|
||||
)
|
||||
return None
|
||||
sightings = raw.get("sightings")
|
||||
if isinstance(sightings, list):
|
||||
if len(sightings) <= 0:
|
||||
logger.info("UAP sightings: cache is fresh but empty; rebuilding")
|
||||
return None
|
||||
filtered = _filter_uap_sightings_recent(sightings)
|
||||
if not filtered:
|
||||
logger.warning(
|
||||
"UAP sightings: cache had %d rows but none within last %d days; rebuilding",
|
||||
len(sightings),
|
||||
_NUFORC_RECENT_DAYS,
|
||||
)
|
||||
return None
|
||||
if len(filtered) < len(sightings):
|
||||
logger.info(
|
||||
"UAP sightings: dropped %d stale cached rows outside %d-day window",
|
||||
len(sightings) - len(filtered),
|
||||
_NUFORC_RECENT_DAYS,
|
||||
)
|
||||
logger.info(
|
||||
"UAP sightings: loaded %d cached reports from %s",
|
||||
len(sightings),
|
||||
"UAP sightings: loaded %d cached reports from %s (within %d-day window)",
|
||||
len(filtered),
|
||||
built,
|
||||
_NUFORC_RECENT_DAYS,
|
||||
)
|
||||
return sightings
|
||||
return filtered
|
||||
except Exception as e:
|
||||
logger.warning("UAP sightings: cache load error: %s", e)
|
||||
return None
|
||||
@@ -828,6 +886,7 @@ def _save_nuforc_sightings_cache(sightings: list[dict]) -> None:
|
||||
_NUFORC_DATA_DIR.mkdir(parents=True, exist_ok=True)
|
||||
payload = {
|
||||
"built": datetime.utcnow().isoformat(),
|
||||
"cutoff_days": _NUFORC_RECENT_DAYS,
|
||||
"count": len(sightings),
|
||||
"sightings": sightings,
|
||||
}
|
||||
@@ -1035,27 +1094,128 @@ def _nuforc_months_for_window(days: int) -> list[str]:
|
||||
return months
|
||||
|
||||
|
||||
def _nuforc_fetch_month_live(yyyymm: str, cookie_jar: Path) -> list[dict]:
|
||||
"""Pull one month of NUFORC sightings via the live wpDataTables AJAX.
|
||||
|
||||
Returns a list of raw row dicts with the fields we care about:
|
||||
id, occurred (YYYY-MM-DD), posted (YYYY-MM-DD), city, state, country,
|
||||
shape_raw, summary, explanation. Empty list on any failure — caller
|
||||
decides whether a failure is fatal.
|
||||
"""
|
||||
def _parse_nuforc_live_datatables_rows(raw_rows: list) -> list[dict]:
|
||||
"""Parse wpDataTables ``data`` array into normalized row dicts."""
|
||||
from services.fetchers.nuforc_enrichment import _parse_date
|
||||
|
||||
curl_bin = shutil.which("curl") or "curl"
|
||||
out: list[dict] = []
|
||||
for raw in raw_rows:
|
||||
if not isinstance(raw, list) or len(raw) < 8:
|
||||
continue
|
||||
link_html = str(raw[0] or "")
|
||||
occurred_raw = str(raw[1] or "")
|
||||
city = str(raw[2] or "").strip()
|
||||
state = str(raw[3] or "").strip()
|
||||
country = str(raw[4] or "").strip()
|
||||
shape_raw = (str(raw[5] or "").strip() or "Unknown")
|
||||
summary = str(raw[6] or "").strip()
|
||||
reported_raw = str(raw[7] or "")
|
||||
explanation = str(raw[9] or "").strip() if len(raw) > 9 and raw[9] else ""
|
||||
|
||||
occurred_ymd = _parse_date(occurred_raw)
|
||||
if not occurred_ymd:
|
||||
continue
|
||||
if not city and not state and not country:
|
||||
continue
|
||||
|
||||
id_match = _NUFORC_LIVE_SIGHTING_ID_RE.search(link_html)
|
||||
if id_match:
|
||||
sighting_id = f"NUFORC-{id_match.group(1)}"
|
||||
else:
|
||||
digest = hashlib.sha1(
|
||||
f"{occurred_ymd}|{city}|{state}|{summary}".encode("utf-8", "ignore")
|
||||
).hexdigest()[:12]
|
||||
sighting_id = f"NUFORC-{digest}"
|
||||
|
||||
if summary and len(summary) > 280:
|
||||
summary = summary[:277] + "..."
|
||||
if not summary:
|
||||
summary = "Sighting reported"
|
||||
|
||||
out.append({
|
||||
"id": sighting_id,
|
||||
"occurred": occurred_ymd,
|
||||
"posted": _parse_date(reported_raw) or occurred_ymd,
|
||||
"city": city,
|
||||
"state": state,
|
||||
"country": country,
|
||||
"shape_raw": shape_raw,
|
||||
"summary": summary,
|
||||
"explanation": explanation,
|
||||
})
|
||||
return out
|
||||
|
||||
|
||||
def _nuforc_fetch_month_live_requests(yyyymm: str) -> list[dict]:
|
||||
"""Live NUFORC month fetch via requests (Windows-safe when curl is disabled)."""
|
||||
import requests
|
||||
|
||||
index_url = _NUFORC_LIVE_INDEX_URL.format(yyyymm=yyyymm)
|
||||
ajax_url = _NUFORC_LIVE_AJAX_URL.format(yyyymm=yyyymm)
|
||||
|
||||
if not external_curl_fallback_enabled():
|
||||
headers = {"User-Agent": _nuforc_live_user_agent()}
|
||||
session = requests.Session()
|
||||
session.headers.update(headers)
|
||||
try:
|
||||
index_res = session.get(index_url, timeout=60)
|
||||
except requests.RequestException as e:
|
||||
logger.warning("NUFORC live (requests): index fetch failed for %s: %s", yyyymm, e)
|
||||
return []
|
||||
if index_res.status_code != 200 or not index_res.text:
|
||||
logger.warning(
|
||||
"NUFORC live: external curl disabled on Windows for %s; "
|
||||
"set SHADOWBROKER_ENABLE_WINDOWS_CURL_FALLBACK=1 to opt in.",
|
||||
"NUFORC live (requests): index HTTP %s for %s",
|
||||
index_res.status_code,
|
||||
yyyymm,
|
||||
)
|
||||
return []
|
||||
nonce_match = _NUFORC_LIVE_NONCE_RE.search(index_res.text)
|
||||
if not nonce_match:
|
||||
logger.warning("NUFORC live (requests): wdtNonce not found for %s", yyyymm)
|
||||
return []
|
||||
nonce = nonce_match.group(1)
|
||||
post_data = (
|
||||
"draw=1"
|
||||
"&columns%5B0%5D%5Bdata%5D=0&columns%5B0%5D%5Bsearchable%5D=true&columns%5B0%5D%5Borderable%5D=false"
|
||||
"&columns%5B1%5D%5Bdata%5D=1&columns%5B1%5D%5Bsearchable%5D=true&columns%5B1%5D%5Borderable%5D=true"
|
||||
"&order%5B0%5D%5Bcolumn%5D=1&order%5B0%5D%5Bdir%5D=desc"
|
||||
"&start=0&length=-1"
|
||||
"&search%5Bvalue%5D=&search%5Bregex%5D=false"
|
||||
f"&wdtNonce={nonce}"
|
||||
)
|
||||
try:
|
||||
ajax_res = session.post(
|
||||
ajax_url,
|
||||
data=post_data,
|
||||
headers={
|
||||
**headers,
|
||||
"Referer": index_url,
|
||||
"X-Requested-With": "XMLHttpRequest",
|
||||
"Content-Type": "application/x-www-form-urlencoded",
|
||||
},
|
||||
timeout=120,
|
||||
)
|
||||
except requests.RequestException as e:
|
||||
logger.warning("NUFORC live (requests): ajax failed for %s: %s", yyyymm, e)
|
||||
return []
|
||||
if ajax_res.status_code != 200 or not ajax_res.text:
|
||||
logger.warning(
|
||||
"NUFORC live (requests): ajax HTTP %s for %s",
|
||||
ajax_res.status_code,
|
||||
yyyymm,
|
||||
)
|
||||
return []
|
||||
try:
|
||||
payload = ajax_res.json()
|
||||
except json.JSONDecodeError as e:
|
||||
logger.warning("NUFORC live (requests): ajax JSON decode failed for %s: %s", yyyymm, e)
|
||||
return []
|
||||
return _parse_nuforc_live_datatables_rows(payload.get("data") or [])
|
||||
|
||||
|
||||
def _nuforc_fetch_month_live_curl(yyyymm: str, cookie_jar: Path) -> list[dict]:
|
||||
"""Pull one month of NUFORC sightings via curl + wpDataTables AJAX."""
|
||||
curl_bin = shutil.which("curl") or "curl"
|
||||
index_url = _NUFORC_LIVE_INDEX_URL.format(yyyymm=yyyymm)
|
||||
ajax_url = _NUFORC_LIVE_AJAX_URL.format(yyyymm=yyyymm)
|
||||
|
||||
# Step 1: GET the month index to capture session cookies + fresh nonce.
|
||||
try:
|
||||
@@ -1125,65 +1285,27 @@ def _nuforc_fetch_month_live(yyyymm: str, cookie_jar: Path) -> list[dict]:
|
||||
logger.warning("NUFORC live: ajax JSON decode failed for %s: %s", yyyymm, e)
|
||||
return []
|
||||
|
||||
raw_rows = payload.get("data") or []
|
||||
out: list[dict] = []
|
||||
for raw in raw_rows:
|
||||
if not isinstance(raw, list) or len(raw) < 8:
|
||||
continue
|
||||
link_html = str(raw[0] or "")
|
||||
occurred_raw = str(raw[1] or "")
|
||||
city = str(raw[2] or "").strip()
|
||||
state = str(raw[3] or "").strip()
|
||||
country = str(raw[4] or "").strip()
|
||||
shape_raw = (str(raw[5] or "").strip() or "Unknown")
|
||||
summary = str(raw[6] or "").strip()
|
||||
reported_raw = str(raw[7] or "")
|
||||
explanation = str(raw[9] or "").strip() if len(raw) > 9 and raw[9] else ""
|
||||
return _parse_nuforc_live_datatables_rows(payload.get("data") or [])
|
||||
|
||||
occurred_ymd = _parse_date(occurred_raw)
|
||||
if not occurred_ymd:
|
||||
continue
|
||||
if not city and not state and not country:
|
||||
continue
|
||||
|
||||
id_match = _NUFORC_LIVE_SIGHTING_ID_RE.search(link_html)
|
||||
if id_match:
|
||||
sighting_id = f"NUFORC-{id_match.group(1)}"
|
||||
else:
|
||||
digest = hashlib.sha1(
|
||||
f"{occurred_ymd}|{city}|{state}|{summary}".encode("utf-8", "ignore")
|
||||
).hexdigest()[:12]
|
||||
sighting_id = f"NUFORC-{digest}"
|
||||
|
||||
if summary and len(summary) > 280:
|
||||
summary = summary[:277] + "..."
|
||||
if not summary:
|
||||
summary = "Sighting reported"
|
||||
|
||||
out.append({
|
||||
"id": sighting_id,
|
||||
"occurred": occurred_ymd,
|
||||
"posted": _parse_date(reported_raw) or occurred_ymd,
|
||||
"city": city,
|
||||
"state": state,
|
||||
"country": country,
|
||||
"shape_raw": shape_raw,
|
||||
"summary": summary,
|
||||
"explanation": explanation,
|
||||
})
|
||||
return out
|
||||
def _nuforc_fetch_month_live(yyyymm: str, cookie_jar: Path) -> list[dict]:
|
||||
"""Pull one month of NUFORC sightings via live wpDataTables AJAX."""
|
||||
if external_curl_fallback_enabled():
|
||||
rows = _nuforc_fetch_month_live_curl(yyyymm, cookie_jar)
|
||||
if rows:
|
||||
return rows
|
||||
return _nuforc_fetch_month_live_requests(yyyymm)
|
||||
|
||||
|
||||
def _build_recent_uap_sightings() -> list[dict]:
|
||||
"""Build the rolling 1-year UAP sightings layer from live NUFORC data.
|
||||
"""Build the rolling UAP sightings layer from live NUFORC data.
|
||||
|
||||
Hits nuforc.org's public sub-index once per month in the window, drops
|
||||
anything outside the exact day-precision cutoff, dedupes by sighting id,
|
||||
geocodes city+state via the existing location cache, and returns rows
|
||||
keyed to the same schema the frontend already renders.
|
||||
"""
|
||||
cutoff_dt = datetime.utcnow() - timedelta(days=_NUFORC_RECENT_DAYS)
|
||||
cutoff_str = cutoff_dt.strftime("%Y-%m-%d")
|
||||
cutoff_str = _uap_cutoff_date_str()
|
||||
months = _nuforc_months_for_window(_NUFORC_RECENT_DAYS)
|
||||
|
||||
try:
|
||||
@@ -1530,11 +1652,12 @@ def _build_uap_sightings_from_hf_mirror() -> list[dict]:
|
||||
|
||||
@with_retry(max_retries=1, base_delay=5)
|
||||
def fetch_uap_sightings(*, force_refresh: bool = False):
|
||||
"""Fetch last-year UAP sightings from NUFORC.
|
||||
"""Fetch rolling-window UAP sightings from live NUFORC.
|
||||
|
||||
Startup reads the cached daily snapshot when it is still fresh. The daily
|
||||
scheduler forces a rebuild so this layer updates once per day instead of
|
||||
churning continuously.
|
||||
Startup reads the cached snapshot when still within NUFORC_CACHE_TTL_HOURS
|
||||
(default 168h / one week). The weekly scheduler forces a rebuild so every
|
||||
install refreshes the same ~60-day layer without daily load on nuforc.org.
|
||||
Operators can also POST /api/refresh (admin) to pull immediately.
|
||||
"""
|
||||
from services.fetchers._store import is_any_active
|
||||
|
||||
@@ -1567,12 +1690,16 @@ def fetch_uap_sightings(*, force_refresh: bool = False):
|
||||
live_error,
|
||||
)
|
||||
|
||||
if sightings:
|
||||
sightings = _filter_uap_sightings_recent(sightings)
|
||||
|
||||
with _data_lock:
|
||||
latest_data["uap_sightings"] = sightings or []
|
||||
if sightings:
|
||||
_mark_fresh("uap_sightings")
|
||||
return
|
||||
|
||||
# Unreachable legacy Mapbox tilequery path (kept for reference).
|
||||
cutoff = datetime.utcnow() - timedelta(days=_NUFORC_RECENT_DAYS)
|
||||
|
||||
# Query the grid concurrently (up to 8 threads)
|
||||
|
||||
@@ -20,17 +20,9 @@ def _env_flag(name: str) -> str:
|
||||
|
||||
|
||||
def liveuamap_scraper_enabled() -> bool:
|
||||
"""Return whether the Playwright-based LiveUAMap scraper should run.
|
||||
from services.liveuamap_settings import liveuamap_scraper_enabled as _enabled
|
||||
|
||||
It is useful enrichment, but it starts a browser/Node driver and must not be
|
||||
allowed to destabilize Windows local startup.
|
||||
"""
|
||||
setting = _env_flag("SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER")
|
||||
if setting in {"1", "true", "yes", "on"}:
|
||||
return True
|
||||
if setting in {"0", "false", "no", "off"}:
|
||||
return False
|
||||
return os.name != "nt"
|
||||
return _enabled()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -210,10 +202,17 @@ def update_liveuamap():
|
||||
if not is_any_active("global_incidents"):
|
||||
return
|
||||
if not liveuamap_scraper_enabled():
|
||||
logger.info(
|
||||
"Liveuamap scraper disabled for this runtime; set "
|
||||
"SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER=1 to opt in."
|
||||
)
|
||||
from services.liveuamap_settings import liveuamap_requires_ui_opt_in
|
||||
|
||||
if liveuamap_requires_ui_opt_in():
|
||||
logger.info(
|
||||
"Liveuamap scraper disabled: enable Global Incidents in the UI to "
|
||||
"consent, or set SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER=1."
|
||||
)
|
||||
else:
|
||||
logger.info(
|
||||
"Liveuamap scraper disabled; set SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER=1 to opt in."
|
||||
)
|
||||
return
|
||||
logger.info("Running scheduled Liveuamap scraper...")
|
||||
try:
|
||||
@@ -279,6 +278,16 @@ _FISHING_FETCH_INTERVAL_S = 3600 # once per hour — GFW data has ~5 day lag
|
||||
_last_fishing_fetch_ts: float = 0.0
|
||||
|
||||
|
||||
def _gfw_int_env(name: str, default: int, *, minimum: int = 1, maximum: int | None = None) -> int:
|
||||
try:
|
||||
value = int(os.environ.get(name, str(default)) or default)
|
||||
except (TypeError, ValueError):
|
||||
value = default
|
||||
if maximum is not None:
|
||||
value = min(maximum, value)
|
||||
return max(minimum, value)
|
||||
|
||||
|
||||
@with_retry(max_retries=1, base_delay=5)
|
||||
def fetch_fishing_activity():
|
||||
"""Fetch recent fishing events from Global Fishing Watch (~5 day lag)."""
|
||||
@@ -301,10 +310,16 @@ def fetch_fishing_activity():
|
||||
try:
|
||||
import datetime as _dt
|
||||
|
||||
# GFW publishes with ~5 day lag; windows shorter than ~7 days often return 0 events.
|
||||
lookback_days = _gfw_int_env("GFW_EVENTS_LOOKBACK_DAYS", 7, minimum=1, maximum=14)
|
||||
max_pages = _gfw_int_env("GFW_EVENTS_MAX_PAGES", 10, minimum=1, maximum=100)
|
||||
timeout_s = _gfw_int_env("GFW_EVENTS_TIMEOUT_S", 90, minimum=30, maximum=180)
|
||||
_end = _dt.date.today().isoformat()
|
||||
_start = (_dt.date.today() - _dt.timedelta(days=7)).isoformat()
|
||||
page_size = max(1, int(os.environ.get("GFW_EVENTS_PAGE_SIZE", "500") or "500"))
|
||||
_start = (_dt.date.today() - _dt.timedelta(days=lookback_days)).isoformat()
|
||||
page_size = _gfw_int_env("GFW_EVENTS_PAGE_SIZE", 500, minimum=1, maximum=1000)
|
||||
offset = 0
|
||||
pages_fetched = 0
|
||||
total_available: int | None = None
|
||||
seen_offsets: set[int] = set()
|
||||
seen_ids: set[str] = set()
|
||||
headers = {"Authorization": f"Bearer {token}"}
|
||||
@@ -325,7 +340,7 @@ def fetch_fishing_activity():
|
||||
}
|
||||
)
|
||||
url = f"https://gateway.api.globalfishingwatch.org/v3/events?{query}"
|
||||
response = fetch_with_curl(url, timeout=30, headers=headers)
|
||||
response = fetch_with_curl(url, timeout=timeout_s, headers=headers)
|
||||
if response.status_code != 200:
|
||||
logger.warning(
|
||||
"Fishing activity fetch failed at offset=%s: HTTP %s",
|
||||
@@ -335,10 +350,16 @@ def fetch_fishing_activity():
|
||||
break
|
||||
|
||||
payload = response.json() or {}
|
||||
if total_available is None:
|
||||
try:
|
||||
total_available = int(payload.get("total")) if payload.get("total") is not None else None
|
||||
except (TypeError, ValueError):
|
||||
total_available = None
|
||||
entries = payload.get("entries", [])
|
||||
if not entries:
|
||||
break
|
||||
|
||||
pages_fetched += 1
|
||||
added_this_page = 0
|
||||
for e in entries:
|
||||
pos = e.get("position", {})
|
||||
@@ -373,6 +394,15 @@ def fetch_fishing_activity():
|
||||
if len(entries) < page_size:
|
||||
break
|
||||
|
||||
if pages_fetched >= max_pages:
|
||||
logger.info(
|
||||
"Fishing activity: capped at %s pages (%s events fetched; GFW total=%s)",
|
||||
max_pages,
|
||||
len(events),
|
||||
total_available if total_available is not None else "unknown",
|
||||
)
|
||||
break
|
||||
|
||||
next_offset = payload.get("nextOffset")
|
||||
if next_offset is None:
|
||||
next_offset = (payload.get("pagination") or {}).get("nextOffset")
|
||||
|
||||
@@ -235,11 +235,11 @@ _DC_GEOCODED_PATH = Path(__file__).parent.parent.parent / "data" / "datacenters_
|
||||
|
||||
|
||||
def fetch_datacenters():
|
||||
"""Load geocoded data centers (5K+ street-level precise locations)."""
|
||||
from services.fetchers._store import is_any_active
|
||||
"""Load geocoded data centers (5K+ street-level precise locations).
|
||||
|
||||
if not is_any_active("datacenters"):
|
||||
return
|
||||
Always loads from disk; /api/live-data/slow gates the payload on the
|
||||
datacenters layer toggle so enabling the layer can render immediately.
|
||||
"""
|
||||
dcs = []
|
||||
try:
|
||||
if not _DC_GEOCODED_PATH.exists():
|
||||
|
||||
@@ -0,0 +1,107 @@
|
||||
"""Malware C2 / URLhaus feed (abuse.ch, Osiris port)."""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
|
||||
from services.fetchers._store import _data_lock, _mark_fresh, is_any_active, latest_data
|
||||
from services.network_utils import fetch_with_curl
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
COUNTRY_CENTROIDS: dict[str, tuple[float, float]] = {
|
||||
"AF": (65, 33), "AL": (20, 41), "DZ": (3, 28), "AR": (-64, -34), "AU": (134, -25),
|
||||
"AT": (14, 47.5), "BE": (4, 50.8), "BR": (-51, -10), "CA": (-96, 62), "CN": (105, 35),
|
||||
"DE": (10, 51), "FR": (2, 46), "GB": (-2, 54), "IN": (79, 22), "IR": (53, 32),
|
||||
"IT": (12.5, 42.8), "JP": (138, 36), "KR": (128, 36), "MX": (-102, 23.5), "NL": (5.5, 52.5),
|
||||
"PL": (19.5, 52), "RU": (100, 60), "SG": (103.8, 1.35), "TW": (121, 23.7), "UA": (32, 49),
|
||||
"US": (-97, 38), "VN": (106, 16),
|
||||
}
|
||||
|
||||
|
||||
def fetch_malware_threats() -> list[dict[str, Any]]:
|
||||
if not is_any_active("malware_c2"):
|
||||
return latest_data.get("malware_threats") or []
|
||||
|
||||
threats: list[dict[str, Any]] = []
|
||||
threat_id = 0
|
||||
|
||||
try:
|
||||
resp = fetch_with_curl(
|
||||
"https://feodotracker.abuse.ch/downloads/ipblocklist.json",
|
||||
timeout=10,
|
||||
headers={"User-Agent": "Shadowbroker/1.0", "Accept": "application/json"},
|
||||
)
|
||||
if resp.status_code == 200:
|
||||
entries = resp.json()
|
||||
if not isinstance(entries, list):
|
||||
entries = []
|
||||
for entry in entries[:200]:
|
||||
cc = entry.get("country")
|
||||
if not cc or cc not in COUNTRY_CENTROIDS:
|
||||
continue
|
||||
lng, lat = COUNTRY_CENTROIDS[cc]
|
||||
j_lng = ((threat_id * 173.7) % 200 - 100) / 100 * 4
|
||||
j_lat = ((threat_id * 293.1) % 200 - 100) / 100 * 4
|
||||
threats.append(
|
||||
{
|
||||
"id": f"feodo-{threat_id}",
|
||||
"lat": lat + j_lat,
|
||||
"lng": lng + j_lng,
|
||||
"ip": entry.get("ip_address") or "unknown",
|
||||
"port": entry.get("dst_port") or 0,
|
||||
"malware": entry.get("malware") or "unknown",
|
||||
"status": entry.get("status") or "active",
|
||||
"first_seen": entry.get("first_seen"),
|
||||
"last_online": entry.get("last_online"),
|
||||
"country": cc,
|
||||
"threat_type": "botnet_c2",
|
||||
}
|
||||
)
|
||||
threat_id += 1
|
||||
except Exception as exc:
|
||||
logger.warning("Feodo fetch failed: %s", exc)
|
||||
|
||||
try:
|
||||
resp = fetch_with_curl(
|
||||
"https://urlhaus-api.abuse.ch/v1/urls/recent/limit/100/",
|
||||
timeout=8,
|
||||
)
|
||||
if resp.status_code == 200:
|
||||
urls = (resp.json() or {}).get("urls") or []
|
||||
for u in urls:
|
||||
cc = u.get("country")
|
||||
if not cc or cc not in COUNTRY_CENTROIDS:
|
||||
cc = next(iter(COUNTRY_CENTROIDS))
|
||||
lng, lat = COUNTRY_CENTROIDS[cc]
|
||||
j_lng = ((threat_id * 137.3) % 200 - 100) / 100 * 5
|
||||
j_lat = ((threat_id * 211.7) % 200 - 100) / 100 * 5
|
||||
threats.append(
|
||||
{
|
||||
"id": f"urlhaus-{threat_id}",
|
||||
"lat": lat + j_lat,
|
||||
"lng": lng + j_lng,
|
||||
"ip": u.get("host") or "unknown",
|
||||
"port": 0,
|
||||
"malware": ", ".join(u.get("tags") or []) or u.get("threat") or "malware",
|
||||
"status": u.get("url_status") or "online",
|
||||
"first_seen": u.get("dateadded"),
|
||||
"country": cc,
|
||||
"threat_type": "malware_url",
|
||||
}
|
||||
)
|
||||
threat_id += 1
|
||||
except Exception as exc:
|
||||
logger.debug("URLhaus supplement failed: %s", exc)
|
||||
|
||||
payload = {
|
||||
"threats": threats,
|
||||
"total": len(threats),
|
||||
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||
"source": "abuse.ch Feodo Tracker + URLhaus",
|
||||
}
|
||||
with _data_lock:
|
||||
latest_data["malware_threats"] = payload
|
||||
_mark_fresh("malware_threats")
|
||||
return threats
|
||||
@@ -188,8 +188,8 @@ def fetch_meshtastic_nodes():
|
||||
callsign = ""
|
||||
|
||||
send_callsign_header = str(
|
||||
_os.environ.get("MESHTASTIC_SEND_CALLSIGN_HEADER", "true")
|
||||
).strip().lower() not in {"0", "false", "no", "off", ""}
|
||||
_os.environ.get("MESHTASTIC_SEND_CALLSIGN_HEADER", "false")
|
||||
).strip().lower() in {"1", "true", "yes", "on"}
|
||||
|
||||
# Round 7a: outbound_user_agent already includes the per-install handle.
|
||||
# The optional Meshtastic callsign is appended as additional context so
|
||||
|
||||
@@ -158,21 +158,26 @@ _KEYWORD_COORDS = {
|
||||
_SORTED_KEYWORDS = sorted(_KEYWORD_COORDS.items(), key=lambda x: len(x[0]), reverse=True)
|
||||
|
||||
|
||||
def resolve_coords_match(text: str) -> tuple[tuple[float, float], str] | None:
|
||||
"""Return ((lat, lng), matched_keyword) for the most specific keyword hit."""
|
||||
padded_text = f" {text} "
|
||||
for kw, coords in _SORTED_KEYWORDS:
|
||||
if kw.startswith(" ") or kw.endswith(" "):
|
||||
if kw in padded_text:
|
||||
return coords, kw
|
||||
elif re.search(r"\b" + re.escape(kw) + r"\b", text):
|
||||
return coords, kw
|
||||
return None
|
||||
|
||||
|
||||
def _resolve_coords(text: str) -> tuple[float, float] | None:
|
||||
"""Return (lat, lng) for the most specific keyword match, or None.
|
||||
|
||||
Longer keywords are tried first. Space-padded keywords (" us ", " uk ")
|
||||
use substring matching on padded text; all others use word-boundary regex.
|
||||
"""
|
||||
padded_text = f" {text} "
|
||||
for kw, coords in _SORTED_KEYWORDS:
|
||||
if kw.startswith(" ") or kw.endswith(" "):
|
||||
if kw in padded_text:
|
||||
return coords
|
||||
else:
|
||||
if re.search(r'\b' + re.escape(kw) + r'\b', text):
|
||||
return coords
|
||||
return None
|
||||
match = resolve_coords_match(text)
|
||||
return match[0] if match else None
|
||||
|
||||
|
||||
@with_retry(max_retries=1, base_delay=2)
|
||||
|
||||
@@ -9,6 +9,7 @@ import json
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
import threading
|
||||
import time
|
||||
from urllib.parse import urlencode
|
||||
@@ -21,23 +22,34 @@ _prev_probabilities: dict[str, float] = {}
|
||||
_market_cache = TTLCache(maxsize=1, ttl=300)
|
||||
_POLYMARKET_PAGE_DELAY_S = float(os.environ.get("MESH_POLYMARKET_PAGE_DELAY_S", "0.02"))
|
||||
_KALSHI_PAGE_DELAY_S = float(os.environ.get("MESH_KALSHI_PAGE_DELAY_S", "0.08"))
|
||||
_POLYMARKET_PAGE_DELAY_JITTER_S = float(os.environ.get("MESH_POLYMARKET_PAGE_DELAY_JITTER_S", "0.08"))
|
||||
_KALSHI_PAGE_DELAY_JITTER_S = float(os.environ.get("MESH_KALSHI_PAGE_DELAY_JITTER_S", "0.2"))
|
||||
# Random delay before each full Polymarket+Kalshi cycle (decorrelates from other slow-tier jobs).
|
||||
_PRE_FETCH_JITTER_S = float(os.environ.get("PREDICTION_MARKETS_PRE_FETCH_JITTER_S", "90"))
|
||||
# Random pause between finishing Polymarket pagination and starting Kalshi.
|
||||
_PROVIDER_GAP_JITTER_S = float(os.environ.get("PREDICTION_MARKETS_PROVIDER_GAP_JITTER_S", "45"))
|
||||
_provider_pace_lock = threading.Lock()
|
||||
_provider_last_request_at: dict[str, float] = {}
|
||||
|
||||
|
||||
def prediction_markets_fetch_enabled() -> bool:
|
||||
"""Return True only when the operator explicitly opts into Polymarket/Kalshi pulls."""
|
||||
return str(os.environ.get("PREDICTION_MARKETS_ENABLED", "")).strip().lower() in {
|
||||
"1",
|
||||
"true",
|
||||
"yes",
|
||||
"on",
|
||||
}
|
||||
"""Return True when UI opt-in or PREDICTION_MARKETS_ENABLED enables pulls."""
|
||||
from services.prediction_markets_settings import prediction_markets_fetch_enabled as _enabled
|
||||
|
||||
return _enabled()
|
||||
|
||||
|
||||
def _pace_provider(provider: str, min_interval_s: float) -> None:
|
||||
if min_interval_s <= 0:
|
||||
return
|
||||
jitter_s = (
|
||||
_POLYMARKET_PAGE_DELAY_JITTER_S
|
||||
if provider == "polymarket"
|
||||
else _KALSHI_PAGE_DELAY_JITTER_S
|
||||
if provider == "kalshi"
|
||||
else 0.0
|
||||
)
|
||||
min_interval_s += random.uniform(0.0, jitter_s) if jitter_s > 0 else 0.0
|
||||
with _provider_pace_lock:
|
||||
now = time.monotonic()
|
||||
wait_s = min_interval_s - (now - _provider_last_request_at.get(provider, 0.0))
|
||||
@@ -47,6 +59,24 @@ def _pace_provider(provider: str, min_interval_s: float) -> None:
|
||||
_provider_last_request_at[provider] = now
|
||||
|
||||
|
||||
def _apply_pre_fetch_jitter() -> None:
|
||||
if _PRE_FETCH_JITTER_S <= 0:
|
||||
return
|
||||
delay = random.uniform(0.0, _PRE_FETCH_JITTER_S)
|
||||
if delay >= 1.0:
|
||||
logger.debug("Prediction markets: pre-fetch jitter %.1fs", delay)
|
||||
time.sleep(delay)
|
||||
|
||||
|
||||
def _apply_provider_gap_jitter() -> None:
|
||||
if _PROVIDER_GAP_JITTER_S <= 0:
|
||||
return
|
||||
delay = random.uniform(0.0, _PROVIDER_GAP_JITTER_S)
|
||||
if delay >= 1.0:
|
||||
logger.debug("Prediction markets: provider gap jitter %.1fs", delay)
|
||||
time.sleep(delay)
|
||||
|
||||
|
||||
def _finite_or_none(value):
|
||||
try:
|
||||
n = float(value)
|
||||
@@ -750,7 +780,9 @@ def _merge_markets(poly_events: list[dict], kalshi_events: list[dict]) -> list[d
|
||||
@cached(_market_cache)
|
||||
def fetch_prediction_markets_raw() -> list[dict]:
|
||||
"""Fetch and merge prediction markets from both sources. Cached 5 min."""
|
||||
_apply_pre_fetch_jitter()
|
||||
poly = _fetch_polymarket_events()
|
||||
_apply_provider_gap_jitter()
|
||||
kalshi = _fetch_kalshi_events()
|
||||
merged = _merge_markets(poly, kalshi)
|
||||
logger.info(
|
||||
|
||||
@@ -11,15 +11,20 @@ import random
|
||||
import logging
|
||||
import functools
|
||||
import requests
|
||||
from requests.exceptions import ChunkedEncodingError, ConnectionError as RequestsConnectionError
|
||||
from requests.exceptions import Timeout as RequestsTimeout
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Only retry on transient network/OS errors — not on parse errors, key errors, etc.
|
||||
# Only retry on transient network/OS errors — not parse/key errors or HTTP 4xx/5xx.
|
||||
# requests.HTTPError (from raise_for_status) is intentionally excluded.
|
||||
TRANSIENT_ERRORS = (
|
||||
TimeoutError,
|
||||
ConnectionError,
|
||||
OSError,
|
||||
requests.RequestException,
|
||||
RequestsConnectionError,
|
||||
RequestsTimeout,
|
||||
ChunkedEncodingError,
|
||||
)
|
||||
|
||||
|
||||
@@ -43,6 +48,8 @@ def with_retry(max_retries: int = 3, base_delay: float = 2.0, max_delay: float =
|
||||
for attempt in range(1 + max_retries):
|
||||
try:
|
||||
return func(*args, **kwargs)
|
||||
except requests.HTTPError:
|
||||
raise
|
||||
except TRANSIENT_ERRORS as exc:
|
||||
last_exc = exc
|
||||
if attempt < max_retries:
|
||||
|
||||
@@ -0,0 +1,84 @@
|
||||
"""Scheduled Sentinel-2 road corridor freight trend fetcher (opt-in, slow tier)."""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
from datetime import datetime, timezone
|
||||
|
||||
from services.fetchers._store import _data_lock, _mark_fresh, is_any_active, latest_data
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_REFRESH_HOURS = float(os.environ.get("ROAD_CORRIDOR_REFRESH_HOURS", "24"))
|
||||
|
||||
|
||||
def _hours_since(iso_ts: str) -> float | None:
|
||||
try:
|
||||
dt = datetime.fromisoformat(iso_ts.replace("Z", "+00:00"))
|
||||
if dt.tzinfo is None:
|
||||
dt = dt.replace(tzinfo=timezone.utc)
|
||||
return (datetime.now(timezone.utc) - dt).total_seconds() / 3600.0
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
|
||||
def _feature_ready() -> bool:
|
||||
from services.road_corridor_sat.config import optional_deps_available, road_corridor_sat_enabled
|
||||
from services.road_corridor_sat.credentials import sentinel_credentials_configured
|
||||
|
||||
if not road_corridor_sat_enabled():
|
||||
return False
|
||||
if not optional_deps_available():
|
||||
logger.debug("road_corridor_trends skipped — optional deps not installed")
|
||||
return False
|
||||
if not sentinel_credentials_configured():
|
||||
logger.debug("road_corridor_trends skipped — Sentinel credentials missing")
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def refresh_road_corridor_store() -> None:
|
||||
from services.road_corridor_sat.storage import build_trends_payload
|
||||
|
||||
payload = build_trends_payload()
|
||||
with _data_lock:
|
||||
latest_data["road_corridor_trends"] = payload
|
||||
_mark_fresh("road_corridor_trends")
|
||||
|
||||
|
||||
def fetch_road_corridor_trends(force: bool = False) -> None:
|
||||
"""Refresh scheduled corridor presets (default: laredo_i35 every 24h)."""
|
||||
if not is_any_active("road_corridor_trends"):
|
||||
return
|
||||
if not _feature_ready():
|
||||
return
|
||||
|
||||
from services.road_corridor_sat.config import SCHEDULED_PRESET_IDS
|
||||
from services.road_corridor_sat.pipeline import analyze_preset
|
||||
from services.road_corridor_sat.presets import get_preset
|
||||
from services.road_corridor_sat.storage import load_refresh_state
|
||||
|
||||
state = load_refresh_state()
|
||||
for preset_id in SCHEDULED_PRESET_IDS:
|
||||
preset = get_preset(preset_id)
|
||||
if preset is None:
|
||||
logger.warning("Unknown scheduled road corridor preset: %s", preset_id)
|
||||
continue
|
||||
last = state.get(preset_id)
|
||||
if last and not force:
|
||||
age_h = _hours_since(last)
|
||||
if age_h is not None and age_h < _REFRESH_HOURS:
|
||||
logger.info(
|
||||
"road_corridor %s fresh (%.1fh < %.1fh) — skipping",
|
||||
preset_id,
|
||||
age_h,
|
||||
_REFRESH_HOURS,
|
||||
)
|
||||
continue
|
||||
try:
|
||||
logger.info("road_corridor analysis starting for %s", preset_id)
|
||||
analyze_preset(preset_id)
|
||||
except Exception as exc:
|
||||
logger.exception("road_corridor analysis failed for %s: %s", preset_id, exc)
|
||||
|
||||
refresh_road_corridor_store()
|
||||
@@ -30,8 +30,6 @@ _AIRPORTS_URL = "https://vrs-standing-data.adsb.lol/airports.csv.gz"
|
||||
_REFRESH_INTERVAL_S = 5 * 24 * 3600
|
||||
_HTTP_TIMEOUT_S = 60
|
||||
|
||||
from services.network_utils import DEFAULT_USER_AGENT as _USER_AGENT
|
||||
|
||||
_lock = threading.RLock()
|
||||
_routes_by_callsign: dict[str, dict[str, Any]] = {}
|
||||
_airports_by_icao: dict[str, dict[str, Any]] = {}
|
||||
|
||||
@@ -0,0 +1,381 @@
|
||||
"""Telegram OSINT — public channel web previews (t.me/s) with keyword geoparsing."""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
|
||||
from services.fetchers._store import _data_lock, _mark_fresh, is_any_active, latest_data
|
||||
from services.fetchers.news import resolve_coords_match
|
||||
from services.network_utils import fetch_with_curl, outbound_user_agent
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_DEFAULT_CHANNELS = (
|
||||
"osintdefender",
|
||||
"insiderpaper",
|
||||
"aljazeeraenglish",
|
||||
"nexta_live",
|
||||
"war_monitor",
|
||||
"OSINTtechnical",
|
||||
"Liveuamap",
|
||||
)
|
||||
|
||||
_MESSAGE_BLOCK_RE = re.compile(
|
||||
r'<div class="tgme_widget_message_wrap js-widget_message_wrap"[\s\S]*?</div>\s*</div>\s*</div>',
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_TEXT_RE = re.compile(
|
||||
r'<div class="tgme_widget_message_text[^>]*>([\s\S]*?)</div>',
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_DATE_RE = re.compile(
|
||||
r'<a class="tgme_widget_message_date" href="(https://t\.me/[^"]+)".*?<time datetime="([^"]+)"',
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_HAS_VIDEO_RE = re.compile(
|
||||
r'tgme_widget_message_video|js-message_video|<video\s',
|
||||
re.IGNORECASE,
|
||||
)
|
||||
_HAS_PHOTO_RE = re.compile(r'tgme_widget_message_photo_wrap', re.IGNORECASE)
|
||||
_VIDEO_SRC_RE = re.compile(r'<video[^>]+src="([^"]+)"', re.IGNORECASE)
|
||||
_BG_IMAGE_RE = re.compile(r"background-image:url\('([^']+)'\)", re.IGNORECASE)
|
||||
|
||||
_TELEGRAM_MEDIA_HOST_SUFFIXES = (".telesco.pe", ".telegram-cdn.org")
|
||||
|
||||
# Cyrillic / Arabic aliases for war-reporting channels (merged after English resolver).
|
||||
_EXTRA_PLACE_KEYWORDS: dict[str, tuple[float, float]] = {
|
||||
"киев": (50.450, 30.523),
|
||||
"київ": (50.450, 30.523),
|
||||
"харьков": (49.993, 36.231),
|
||||
"харків": (49.993, 36.231),
|
||||
"одесса": (46.482, 30.724),
|
||||
"одеса": (46.482, 30.724),
|
||||
"донецк": (48.015, 37.803),
|
||||
"донецьк": (48.015, 37.803),
|
||||
"луганск": (48.574, 39.307),
|
||||
"луганськ": (48.574, 39.307),
|
||||
"москва": (55.755, 37.617),
|
||||
"крым": (45.000, 34.000),
|
||||
"крим": (45.000, 34.000),
|
||||
"бахмут": (48.595, 38.000),
|
||||
"запорожье": (47.838, 35.139),
|
||||
"запоріжжя": (47.838, 35.139),
|
||||
"غزة": (31.416, 34.333),
|
||||
"دمشق": (33.513, 36.276),
|
||||
"بيروت": (33.893, 35.501),
|
||||
"tel aviv": (32.085, 34.781),
|
||||
"תל אביב": (32.085, 34.781),
|
||||
}
|
||||
|
||||
# Country-level news geocodes sit on national centroids that stack with threat alerts.
|
||||
# Telegram uses major metro anchors so pins land on a different map cell than news.
|
||||
_TELEGRAM_ANCHOR_OVERRIDES: dict[str, tuple[float, float]] = {
|
||||
"israel": (32.085, 34.781), # Tel Aviv (news uses central Israel ~Jerusalem corridor)
|
||||
"middle east": (32.085, 34.781),
|
||||
"china": (39.904, 116.407), # Beijing (news uses country centroid)
|
||||
"united states": (40.712, -74.006), # New York (news uses Washington DC)
|
||||
"usa": (40.712, -74.006),
|
||||
"us": (40.712, -74.006),
|
||||
"america": (40.712, -74.006),
|
||||
"uk": (51.507, -0.127), # London
|
||||
"iran": (35.689, 51.389), # Tehran
|
||||
"russia": (55.755, 37.617), # Moscow
|
||||
"ukraine": (50.450, 30.523), # Kyiv
|
||||
"france": (48.856, 2.352), # Paris
|
||||
"germany": (52.520, 13.405), # Berlin
|
||||
"lebanon": (34.433, 35.844), # Tripoli (news uses Beirut corridor)
|
||||
}
|
||||
|
||||
_RISK_KEYWORDS = (
|
||||
"war",
|
||||
"missile",
|
||||
"strike",
|
||||
"attack",
|
||||
"crisis",
|
||||
"tension",
|
||||
"military",
|
||||
"conflict",
|
||||
"defense",
|
||||
"clash",
|
||||
"nuclear",
|
||||
"invasion",
|
||||
"bomb",
|
||||
"drone",
|
||||
"weapon",
|
||||
"sanctions",
|
||||
"ceasefire",
|
||||
"escalation",
|
||||
"killed",
|
||||
"destroyed",
|
||||
"operation",
|
||||
"casualty",
|
||||
"frontline",
|
||||
"threat",
|
||||
"explosion",
|
||||
"shelling",
|
||||
)
|
||||
|
||||
|
||||
def telegram_osint_enabled() -> bool:
|
||||
return str(os.environ.get("TELEGRAM_OSINT_ENABLED", "true")).strip().lower() not in {
|
||||
"0",
|
||||
"false",
|
||||
"no",
|
||||
"off",
|
||||
"",
|
||||
}
|
||||
|
||||
|
||||
def _configured_channels() -> list[str]:
|
||||
raw = str(os.environ.get("TELEGRAM_OSINT_CHANNELS", "")).strip()
|
||||
if raw:
|
||||
return [part.strip().lstrip("@") for part in raw.split(",") if part.strip()]
|
||||
return list(_DEFAULT_CHANNELS)
|
||||
|
||||
|
||||
def telegram_media_host_allowed(hostname: str | None) -> bool:
|
||||
host = str(hostname or "").strip().lower()
|
||||
if not host:
|
||||
return False
|
||||
return any(host.endswith(suffix) for suffix in _TELEGRAM_MEDIA_HOST_SUFFIXES)
|
||||
|
||||
|
||||
def _extract_media(block: str, link: str) -> dict[str, Any]:
|
||||
has_video = bool(_HAS_VIDEO_RE.search(block))
|
||||
has_photo = bool(_HAS_PHOTO_RE.search(block))
|
||||
media_type: str | None = None
|
||||
media_url: str | None = None
|
||||
if has_video:
|
||||
media_type = "video"
|
||||
video_match = _VIDEO_SRC_RE.search(block)
|
||||
if video_match:
|
||||
media_url = video_match.group(1).strip()
|
||||
elif has_photo:
|
||||
media_type = "photo"
|
||||
photo_match = _BG_IMAGE_RE.search(block)
|
||||
if photo_match:
|
||||
media_url = photo_match.group(1).strip()
|
||||
|
||||
embed_url: str | None = None
|
||||
if media_type and link:
|
||||
embed_url = f"{link}?embed=1"
|
||||
|
||||
return {
|
||||
"media_type": media_type,
|
||||
"media_url": media_url,
|
||||
"embed_url": embed_url,
|
||||
}
|
||||
|
||||
|
||||
def _strip_html(text: str) -> str:
|
||||
cleaned = re.sub(r"<br\s*/?>", "\n", text, flags=re.IGNORECASE)
|
||||
cleaned = re.sub(r"<[^>]+>", "", cleaned)
|
||||
return (
|
||||
cleaned.replace(""", '"')
|
||||
.replace("&", "&")
|
||||
.replace("<", "<")
|
||||
.replace(">", ">")
|
||||
.strip()
|
||||
)
|
||||
|
||||
|
||||
def _score_risk(text: str) -> int:
|
||||
lower = text.lower()
|
||||
score = 1
|
||||
for kw in _RISK_KEYWORDS:
|
||||
if kw in lower:
|
||||
score += 2
|
||||
return min(10, score)
|
||||
|
||||
|
||||
def _refresh_post_coords(post: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Re-apply geoparsing so stored posts pick up anchor updates."""
|
||||
text = "\n".join(
|
||||
str(part).strip()
|
||||
for part in (post.get("title"), post.get("description"))
|
||||
if part and str(part).strip()
|
||||
)
|
||||
if not text:
|
||||
return post
|
||||
coords = _resolve_telegram_coords(text)
|
||||
if not coords:
|
||||
return post
|
||||
updated = dict(post)
|
||||
updated["coords"] = [coords[0], coords[1]]
|
||||
return updated
|
||||
|
||||
|
||||
def _resolve_telegram_coords(text: str) -> tuple[float, float] | None:
|
||||
lower = text.lower()
|
||||
match = resolve_coords_match(lower)
|
||||
if match:
|
||||
_coords, keyword = match
|
||||
anchor = _TELEGRAM_ANCHOR_OVERRIDES.get(keyword.strip().lower())
|
||||
if anchor:
|
||||
return anchor
|
||||
return _coords
|
||||
for keyword, coords in sorted(_EXTRA_PLACE_KEYWORDS.items(), key=lambda x: len(x[0]), reverse=True):
|
||||
if keyword in lower:
|
||||
return coords
|
||||
return None
|
||||
|
||||
|
||||
def _post_link(post: dict[str, Any]) -> str:
|
||||
return str(post.get("link") or "").strip()
|
||||
|
||||
|
||||
def _extract_new_channel_posts(
|
||||
html: str,
|
||||
channel: str,
|
||||
known_links: set[str],
|
||||
*,
|
||||
bootstrap_limit: int = 12,
|
||||
) -> list[dict[str, Any]]:
|
||||
"""Return unseen posts from a channel page; stop once we hit a stored link."""
|
||||
parsed = parse_telegram_channel_html(html, channel)
|
||||
if not parsed:
|
||||
return []
|
||||
if not known_links:
|
||||
return parsed[-bootstrap_limit:]
|
||||
|
||||
fresh: list[dict[str, Any]] = []
|
||||
for post in reversed(parsed):
|
||||
link = _post_link(post)
|
||||
if not link:
|
||||
continue
|
||||
if link in known_links:
|
||||
break
|
||||
fresh.append(post)
|
||||
fresh.reverse()
|
||||
return fresh
|
||||
|
||||
|
||||
def _merge_telegram_posts(
|
||||
existing: list[dict[str, Any]],
|
||||
incoming: list[dict[str, Any]],
|
||||
*,
|
||||
max_posts: int = 120,
|
||||
) -> tuple[list[dict[str, Any]], int]:
|
||||
known_links = {_post_link(post) for post in existing if _post_link(post)}
|
||||
added = 0
|
||||
for post in incoming:
|
||||
link = _post_link(post)
|
||||
if not link or link in known_links:
|
||||
continue
|
||||
known_links.add(link)
|
||||
existing.append(post)
|
||||
added += 1
|
||||
existing.sort(key=lambda p: str(p.get("published") or ""), reverse=True)
|
||||
return existing[:max_posts], added
|
||||
|
||||
|
||||
def parse_telegram_channel_html(html: str, channel: str) -> list[dict[str, Any]]:
|
||||
"""Parse public t.me/s channel preview HTML into post dicts."""
|
||||
posts: list[dict[str, Any]] = []
|
||||
for block in _MESSAGE_BLOCK_RE.findall(html or ""):
|
||||
text_match = _TEXT_RE.search(block)
|
||||
if not text_match:
|
||||
continue
|
||||
text = _strip_html(text_match.group(1))
|
||||
if len(text) < 10:
|
||||
continue
|
||||
|
||||
date_match = _DATE_RE.search(block)
|
||||
link = date_match.group(1) if date_match else f"https://t.me/{channel}"
|
||||
published = date_match.group(2) if date_match else datetime.now(timezone.utc).isoformat()
|
||||
title = text.split("\n", 1)[0][:160]
|
||||
risk_score = _score_risk(text)
|
||||
coords = _resolve_telegram_coords(text)
|
||||
post_id = hashlib.sha1(f"{link}|{published}".encode("utf-8")).hexdigest()[:16]
|
||||
|
||||
media = _extract_media(block, link)
|
||||
posts.append(
|
||||
{
|
||||
"id": post_id,
|
||||
"title": title,
|
||||
"description": text[:1200],
|
||||
"link": link,
|
||||
"published": published,
|
||||
"source": f"t.me/{channel}",
|
||||
"channel": channel,
|
||||
"risk_score": risk_score,
|
||||
"coords": [coords[0], coords[1]] if coords else None,
|
||||
**media,
|
||||
}
|
||||
)
|
||||
return posts
|
||||
|
||||
|
||||
def fetch_telegram_osint() -> dict[str, Any]:
|
||||
if not is_any_active("telegram_osint"):
|
||||
return latest_data.get("telegram_osint") or {"posts": [], "total": 0, "timestamp": None}
|
||||
|
||||
if not telegram_osint_enabled():
|
||||
with _data_lock:
|
||||
latest_data["telegram_osint"] = {"posts": [], "total": 0, "timestamp": None, "disabled": True}
|
||||
_mark_fresh("telegram_osint")
|
||||
return latest_data["telegram_osint"]
|
||||
|
||||
headers = {
|
||||
"User-Agent": (
|
||||
f"Mozilla/5.0 (compatible; {outbound_user_agent('telegram-osint')}) "
|
||||
"AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
),
|
||||
"Accept": "text/html,application/xhtml+xml",
|
||||
}
|
||||
|
||||
with _data_lock:
|
||||
prior = latest_data.get("telegram_osint") or {}
|
||||
existing_posts = list(prior.get("posts") or [])
|
||||
|
||||
known_links = {_post_link(post) for post in existing_posts if _post_link(post)}
|
||||
incoming: list[dict[str, Any]] = []
|
||||
|
||||
for channel in _configured_channels():
|
||||
url = f"https://t.me/s/{channel}"
|
||||
try:
|
||||
resp = fetch_with_curl(url, timeout=15, headers=headers)
|
||||
if not resp or resp.status_code != 200:
|
||||
logger.warning(
|
||||
"Telegram channel %s fetch failed: HTTP %s",
|
||||
channel,
|
||||
resp.status_code if resp else "no response",
|
||||
)
|
||||
continue
|
||||
channel_new = _extract_new_channel_posts(resp.text, channel, known_links)
|
||||
for post in channel_new:
|
||||
link = _post_link(post)
|
||||
if not link or link in known_links:
|
||||
continue
|
||||
known_links.add(link)
|
||||
incoming.append(post)
|
||||
except Exception as exc:
|
||||
logger.warning("Telegram channel %s parse failed: %s", channel, exc)
|
||||
|
||||
merged_posts, added = _merge_telegram_posts(existing_posts, incoming)
|
||||
merged_posts = [_refresh_post_coords(post) for post in merged_posts]
|
||||
geolocated = sum(1 for p in merged_posts if p.get("coords"))
|
||||
|
||||
payload = {
|
||||
"posts": merged_posts,
|
||||
"total": len(merged_posts),
|
||||
"geolocated": geolocated,
|
||||
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||
"channels": _configured_channels(),
|
||||
"last_fetch_new": added,
|
||||
}
|
||||
|
||||
with _data_lock:
|
||||
latest_data["telegram_osint"] = payload
|
||||
_mark_fresh("telegram_osint")
|
||||
logger.info(
|
||||
"Telegram OSINT: +%s new, %s retained (%s geolocated)",
|
||||
added,
|
||||
len(merged_posts),
|
||||
geolocated,
|
||||
)
|
||||
return payload
|
||||
@@ -1,3 +1,4 @@
|
||||
import os
|
||||
import requests
|
||||
import logging
|
||||
import zipfile
|
||||
@@ -20,6 +21,50 @@ logger = logging.getLogger(__name__)
|
||||
# Cache Frontline data for 30 minutes, it doesn't move that fast
|
||||
frontline_cache = TTLCache(maxsize=1, ttl=1800)
|
||||
|
||||
_DEFAULT_DEEPSTATE_MIRROR_REPO = "cyterat/deepstate-map-data"
|
||||
|
||||
|
||||
def _deepstate_mirror_ref() -> tuple[str, str]:
|
||||
"""Return (github_repo_slug, git_ref) for the DeepState mirror.
|
||||
|
||||
When ``DEEPSTATE_MIRROR_COMMIT`` is set, ingest is pinned to that immutable
|
||||
SHA instead of following the mutable ``main`` branch (#362).
|
||||
"""
|
||||
repo = (os.environ.get("DEEPSTATE_MIRROR_REPO") or _DEFAULT_DEEPSTATE_MIRROR_REPO).strip()
|
||||
if repo.count("/") != 1:
|
||||
repo = _DEFAULT_DEEPSTATE_MIRROR_REPO
|
||||
commit = (os.environ.get("DEEPSTATE_MIRROR_COMMIT") or "").strip()
|
||||
ref = commit if commit else "main"
|
||||
return repo, ref
|
||||
|
||||
|
||||
def _latest_deepstate_geo_path(tree_items: list) -> str | None:
|
||||
geo_files = [
|
||||
item["path"]
|
||||
for item in tree_items
|
||||
if isinstance(item, dict)
|
||||
and str(item.get("path", "")).startswith("data/deepstatemap_data_")
|
||||
and str(item.get("path", "")).endswith(".geojson")
|
||||
]
|
||||
return sorted(geo_files)[-1] if geo_files else None
|
||||
|
||||
|
||||
def _annotate_deepstate_geojson(data: dict) -> dict:
|
||||
name_map = {
|
||||
0: "Russian-occupied areas",
|
||||
1: "Russian advance",
|
||||
2: "Liberated area",
|
||||
3: "Russian-occupied areas", # Crimea / LPR / DPR
|
||||
4: "Directions of UA attacks",
|
||||
}
|
||||
if "features" in data:
|
||||
for idx, feature in enumerate(data["features"]):
|
||||
if "properties" not in feature or feature["properties"] is None:
|
||||
feature["properties"] = {}
|
||||
feature["properties"]["name"] = name_map.get(idx, "Russian-occupied areas")
|
||||
feature["properties"]["zone_id"] = idx
|
||||
return data
|
||||
|
||||
|
||||
@cached(frontline_cache)
|
||||
def fetch_ukraine_frontlines():
|
||||
@@ -27,67 +72,34 @@ def fetch_ukraine_frontlines():
|
||||
Fetches the latest GeoJSON data representing the Ukraine frontline.
|
||||
We use the cyterat/deepstate-map-data github mirror since the public API is locked.
|
||||
"""
|
||||
repo, ref = _deepstate_mirror_ref()
|
||||
try:
|
||||
logger.info("Fetching DeepStateMap from GitHub mirror...")
|
||||
logger.info("Fetching DeepStateMap from GitHub mirror (%s @ %s)...", repo, ref)
|
||||
|
||||
# First, query the repo tree to find the latest file name
|
||||
tree_url = (
|
||||
"https://api.github.com/repos/cyterat/deepstate-map-data/git/trees/main?recursive=1"
|
||||
)
|
||||
tree_url = f"https://api.github.com/repos/{repo}/git/trees/{ref}?recursive=1"
|
||||
res_tree = requests.get(tree_url, timeout=10)
|
||||
|
||||
if res_tree.status_code == 200:
|
||||
tree_data = res_tree.json().get("tree", [])
|
||||
# Filter for geojson files in data folder
|
||||
geo_files = [
|
||||
item["path"]
|
||||
for item in tree_data
|
||||
if item["path"].startswith("data/deepstatemap_data_")
|
||||
and item["path"].endswith(".geojson")
|
||||
]
|
||||
|
||||
if geo_files:
|
||||
# Get the alphabetically latest file (since it's named with YYYYMMDD)
|
||||
latest_file = sorted(geo_files)[-1]
|
||||
|
||||
raw_url = f"https://raw.githubusercontent.com/cyterat/deepstate-map-data/main/{latest_file}"
|
||||
logger.info(f"Downloading latest DeepStateMap: {raw_url}")
|
||||
latest_file = _latest_deepstate_geo_path(res_tree.json().get("tree", []))
|
||||
if latest_file:
|
||||
raw_url = f"https://raw.githubusercontent.com/{repo}/{ref}/{latest_file}"
|
||||
logger.info("Downloading DeepStateMap: %s", raw_url)
|
||||
|
||||
res_geo = requests.get(raw_url, timeout=20)
|
||||
if res_geo.status_code == 200:
|
||||
data = res_geo.json()
|
||||
|
||||
# The Cyterat GitHub mirror strips all properties and just provides a raw array of Feature polygons.
|
||||
# Based on DeepStateMap's frontend mapping, the array index corresponds to the zone type:
|
||||
# 0: Russian-occupied areas
|
||||
# 1: Russian advance
|
||||
# 2: Liberated area
|
||||
# 3: Uncontested/Crimea (often folded into occupied)
|
||||
name_map = {
|
||||
0: "Russian-occupied areas",
|
||||
1: "Russian advance",
|
||||
2: "Liberated area",
|
||||
3: "Russian-occupied areas", # Crimea / LPR / DPR
|
||||
4: "Directions of UA attacks",
|
||||
}
|
||||
|
||||
if "features" in data:
|
||||
for idx, feature in enumerate(data["features"]):
|
||||
if "properties" not in feature or feature["properties"] is None:
|
||||
feature["properties"] = {}
|
||||
|
||||
feature["properties"]["name"] = name_map.get(
|
||||
idx, "Russian-occupied areas"
|
||||
)
|
||||
feature["properties"]["zone_id"] = idx
|
||||
|
||||
return data
|
||||
else:
|
||||
logger.error(
|
||||
f"Failed to fetch parsed Github Raw GeoJSON: {res_geo.status_code}"
|
||||
)
|
||||
return _annotate_deepstate_geojson(res_geo.json())
|
||||
logger.error(
|
||||
"Failed to fetch parsed Github Raw GeoJSON: %s", res_geo.status_code
|
||||
)
|
||||
else:
|
||||
logger.error("No deepstatemap_data_*.geojson files in mirror tree at %s", ref)
|
||||
else:
|
||||
logger.error(f"Failed to fetch Github Tree for Deepstatemap: {res_tree.status_code}")
|
||||
logger.error(
|
||||
"Failed to fetch Github tree for Deepstatemap (%s @ %s): %s",
|
||||
repo,
|
||||
ref,
|
||||
res_tree.status_code,
|
||||
)
|
||||
except (requests.RequestException, ConnectionError, TimeoutError, ValueError, KeyError) as e:
|
||||
logger.error(f"Error fetching DeepStateMap: {e}")
|
||||
return None
|
||||
|
||||
@@ -1,14 +1,20 @@
|
||||
"""Function Keys — anonymous citizenship proof.
|
||||
"""Function Keys — anonymous credential scaffolding.
|
||||
|
||||
Source of truth: ``infonet-economy/IMPLEMENTATION_PLAN.md`` §4.4,
|
||||
``infonet-economy/BRAINDUMP.md`` §11 item 9.
|
||||
|
||||
A citizen should be able to prove "I am a UBI-eligible Infonet
|
||||
citizen" to a real-world operator (food bank, community service)
|
||||
**without revealing their Infonet identity**. The naive approach
|
||||
(scramble a public key, record each redemption on chain) leaks
|
||||
identity through metadata correlation (time, location, operator,
|
||||
frequency).
|
||||
A citizen should eventually be able to prove "I am a UBI-eligible
|
||||
Infonet citizen" to a real-world operator (food bank, community
|
||||
service) **without revealing their Infonet identity**. The current
|
||||
Python implementation wires the accounting, nullifier, receipt, and
|
||||
operator flows, but its HMAC challenge-response is a placeholder for
|
||||
integration tests. It is not a production anonymous or zero-knowledge
|
||||
citizenship proof until blind signatures or anonymous credentials are
|
||||
selected and wired.
|
||||
|
||||
The naive approach (scramble a public key, record each redemption on
|
||||
chain) leaks identity through metadata correlation (time, location,
|
||||
operator, frequency).
|
||||
|
||||
The full design has six pieces; five are implemented in pure Python
|
||||
here. The remaining piece — issuance via blind signatures or
|
||||
@@ -27,7 +33,8 @@ Pieces:
|
||||
operator: tracked via ``NullifierTracker``.
|
||||
3. **Challenge-response** (`challenge_response.py`) — operator
|
||||
issues a fresh nonce, key-holder signs with the Function Key's
|
||||
secret. Prevents screenshot attacks, key sharing, replay.
|
||||
secret. This is HMAC placeholder plumbing for screenshot/replay
|
||||
resistance, not the final anonymous credential proof.
|
||||
4. **Two-phase commit receipts** (`receipt.py`) — Phase 1
|
||||
verification receipt (operator-signed, day-level date NOT
|
||||
timestamp, no node_id). Phase 2 fulfillment receipt (citizen
|
||||
|
||||
@@ -0,0 +1,94 @@
|
||||
"""Country risk index (static scores + USGS quake enrichment)."""
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
from zoneinfo import ZoneInfo
|
||||
|
||||
from services.network_utils import fetch_with_curl
|
||||
|
||||
RISK_FACTORS: dict[str, dict[str, Any]] = {
|
||||
"UA": {"base": 85, "tags": ["active_conflict", "infrastructure_damage"]},
|
||||
"RU": {"base": 72, "tags": ["sanctions", "military_mobilization"]},
|
||||
"IL": {"base": 78, "tags": ["active_conflict", "regional_instability"]},
|
||||
"PS": {"base": 90, "tags": ["active_conflict", "humanitarian_crisis"]},
|
||||
"SY": {"base": 82, "tags": ["post_conflict", "infrastructure_damage"]},
|
||||
"YE": {"base": 88, "tags": ["active_conflict", "humanitarian_crisis"]},
|
||||
"MM": {"base": 76, "tags": ["civil_unrest", "military_junta"]},
|
||||
"SD": {"base": 84, "tags": ["active_conflict", "humanitarian_crisis"]},
|
||||
"AF": {"base": 80, "tags": ["post_conflict", "governance_collapse"]},
|
||||
"KP": {"base": 70, "tags": ["nuclear_risk", "isolation"]},
|
||||
"IR": {"base": 68, "tags": ["sanctions", "nuclear_program", "regional_proxy"]},
|
||||
"CN": {"base": 35, "tags": ["strategic_competition", "taiwan_tensions"]},
|
||||
"TW": {"base": 45, "tags": ["invasion_risk", "semiconductor_dependency"]},
|
||||
"VE": {"base": 60, "tags": ["economic_collapse", "political_instability"]},
|
||||
"HT": {"base": 85, "tags": ["gang_violence", "governance_collapse"]},
|
||||
"LB": {"base": 65, "tags": ["economic_crisis", "political_deadlock"]},
|
||||
"PK": {"base": 55, "tags": ["terrorism", "political_instability"]},
|
||||
"SO": {"base": 82, "tags": ["terrorism", "state_fragility"]},
|
||||
"LY": {"base": 72, "tags": ["divided_government", "militia_control"]},
|
||||
"ET": {"base": 62, "tags": ["ethnic_tensions", "regional_conflicts"]},
|
||||
}
|
||||
|
||||
EXCHANGES = [
|
||||
{"name": "NYSE", "tz": "America/New_York", "open": 9.5, "close": 16, "country": "US"},
|
||||
{"name": "NASDAQ", "tz": "America/New_York", "open": 9.5, "close": 16, "country": "US"},
|
||||
{"name": "LSE", "tz": "Europe/London", "open": 8, "close": 16.5, "country": "GB"},
|
||||
{"name": "TSE", "tz": "Asia/Tokyo", "open": 9, "close": 15, "country": "JP"},
|
||||
{"name": "SSE", "tz": "Asia/Shanghai", "open": 9.5, "close": 15, "country": "CN"},
|
||||
{"name": "HKEX", "tz": "Asia/Hong_Kong", "open": 9.5, "close": 16, "country": "HK"},
|
||||
{"name": "FRA", "tz": "Europe/Berlin", "open": 8, "close": 20, "country": "DE"},
|
||||
{"name": "TSX", "tz": "America/Toronto", "open": 9.5, "close": 16, "country": "CA"},
|
||||
{"name": "MOEX", "tz": "Europe/Moscow", "open": 10, "close": 18.5, "country": "RU"},
|
||||
]
|
||||
|
||||
|
||||
def _exchange_open(ex: dict[str, Any]) -> bool:
|
||||
try:
|
||||
now = datetime.now(ZoneInfo(ex["tz"]))
|
||||
if now.weekday() >= 5:
|
||||
return False
|
||||
decimal = now.hour + now.minute / 60
|
||||
return ex["open"] <= decimal < ex["close"]
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def build_country_risk_payload() -> dict[str, Any]:
|
||||
quake_risks: dict[str, float] = {}
|
||||
try:
|
||||
resp = fetch_with_curl(
|
||||
"https://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/4.5_day.geojson",
|
||||
timeout=5,
|
||||
)
|
||||
if resp.status_code == 200:
|
||||
for f in resp.json().get("features") or []:
|
||||
place = (f.get("properties") or {}).get("place") or ""
|
||||
mag = (f.get("properties") or {}).get("mag") or 0
|
||||
for code in RISK_FACTORS:
|
||||
if code.lower() in place.lower():
|
||||
quake_risks[code] = quake_risks.get(code, 0) + mag
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
countries = []
|
||||
for code, data in RISK_FACTORS.items():
|
||||
base = data["base"]
|
||||
score = min(100, base + quake_risks.get(code, 0))
|
||||
countries.append(
|
||||
{
|
||||
"code": code,
|
||||
"risk_score": score,
|
||||
"risk_level": "CRITICAL" if base >= 80 else "HIGH" if base >= 60 else "ELEVATED" if base >= 40 else "LOW",
|
||||
"tags": data["tags"],
|
||||
}
|
||||
)
|
||||
countries.sort(key=lambda c: c["risk_score"], reverse=True)
|
||||
exchanges = [{"name": e["name"], "country": e["country"], "open": _exchange_open(e)} for e in EXCHANGES]
|
||||
return {
|
||||
"countries": countries,
|
||||
"exchanges": exchanges,
|
||||
"open_exchanges": sum(1 for e in exchanges if e["open"]),
|
||||
"total_exchanges": len(exchanges),
|
||||
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||
}
|
||||
@@ -32,14 +32,14 @@ logger = logging.getLogger(__name__)
|
||||
_REFRESH_SECONDS = 24 * 3600
|
||||
kiwisdr_cache: TTLCache = TTLCache(maxsize=1, ttl=_REFRESH_SECONDS)
|
||||
|
||||
_SOURCE_URL = "http://rx.linkfanel.net/kiwisdr_com.js"
|
||||
_SOURCE_URL_HTTP = "http://rx.linkfanel.net/kiwisdr_com.js"
|
||||
_SOURCE_URL_HTTPS = "https://rx.linkfanel.net/kiwisdr_com.js"
|
||||
_CACHE_FILE = Path(__file__).resolve().parent.parent / "data" / "kiwisdr_cache.json"
|
||||
# Bundled fallback — shipped with the codebase so the KiwiSDR layer always
|
||||
# has something to render even when the upstream is unreachable, returns
|
||||
# garbage, or appears to have been tampered with. Issue #206: the upstream
|
||||
# only speaks HTTP, so we can't rely on TLS for integrity — instead we
|
||||
# validate the response's shape and fall back to this bundle if it doesn't
|
||||
# look right.
|
||||
# garbage, or appears to have been tampered with. Issue #206 / #364: try HTTPS
|
||||
# first, then HTTP; we still validate shape and fall back to this bundle if the
|
||||
# payload does not look right.
|
||||
_BUNDLED_FALLBACK = Path(__file__).resolve().parent.parent / "data" / "kiwisdr_directory.json"
|
||||
|
||||
# Minimum number of receivers we expect from a healthy upstream response.
|
||||
@@ -184,6 +184,29 @@ def _validate_fetched_nodes(nodes: list[dict]) -> bool:
|
||||
return True
|
||||
|
||||
|
||||
def _fetch_mirror_payload_text() -> str | None:
|
||||
"""Try HTTPS first, then HTTP. Shape validation still applies (#364)."""
|
||||
from services.network_utils import fetch_with_curl
|
||||
|
||||
last_error: Exception | None = None
|
||||
for url in (_SOURCE_URL_HTTPS, _SOURCE_URL_HTTP):
|
||||
try:
|
||||
res = fetch_with_curl(url, timeout=20)
|
||||
if res and res.status_code == 200:
|
||||
if url == _SOURCE_URL_HTTP:
|
||||
logger.info(
|
||||
"KiwiSDR: HTTPS mirror unavailable; using HTTP with shape validation"
|
||||
)
|
||||
return res.text
|
||||
last_error = RuntimeError(f"HTTP {getattr(res, 'status_code', 'unknown')}")
|
||||
except Exception as e:
|
||||
last_error = e
|
||||
logger.debug("KiwiSDR mirror fetch failed for %s: %s", url, e)
|
||||
if last_error is not None:
|
||||
logger.warning("KiwiSDR mirror fetch failed: %s", last_error)
|
||||
return None
|
||||
|
||||
|
||||
def _load_bundled_fallback() -> list[dict]:
|
||||
"""Last-resort directory shipped with the codebase. Always returns a
|
||||
list (may be empty if the bundle is missing in older deployments)."""
|
||||
@@ -202,9 +225,8 @@ def _load_bundled_fallback() -> list[dict]:
|
||||
def fetch_kiwisdr_nodes() -> list[dict]:
|
||||
"""Return the KiwiSDR receiver list, refreshed at most once per day.
|
||||
|
||||
Layered fallback (issue #206 — upstream is HTTP-only, so we defend with
|
||||
content validation + bundled static directory rather than trying to
|
||||
upgrade the transport):
|
||||
Layered fallback (issue #206 / #364 — HTTPS first, HTTP fallback, plus
|
||||
content validation + bundled static directory):
|
||||
|
||||
1. In-memory cache (handled by @cached on this function)
|
||||
2. On-disk cache if <24h old
|
||||
@@ -216,8 +238,6 @@ def fetch_kiwisdr_nodes() -> list[dict]:
|
||||
tampered upstream returning garbage is caught by _validate_fetched_nodes()
|
||||
and falls through to whatever previously-trusted snapshot we have.
|
||||
"""
|
||||
from services.network_utils import fetch_with_curl
|
||||
|
||||
# 1. Trust on-disk cache if fresh.
|
||||
cached_nodes = _load_disk_cache()
|
||||
if cached_nodes is not None:
|
||||
@@ -230,14 +250,12 @@ def fetch_kiwisdr_nodes() -> list[dict]:
|
||||
fresh_nodes: list[dict] = []
|
||||
fetch_succeeded = False
|
||||
try:
|
||||
res = fetch_with_curl(_SOURCE_URL, timeout=20)
|
||||
if res and res.status_code == 200:
|
||||
fresh_nodes = _parse_mirror_payload(res.text)
|
||||
body = _fetch_mirror_payload_text()
|
||||
if body:
|
||||
fresh_nodes = _parse_mirror_payload(body)
|
||||
fetch_succeeded = True
|
||||
else:
|
||||
logger.warning(
|
||||
f"KiwiSDR fetch returned HTTP {res.status_code if res else 'no response'}"
|
||||
)
|
||||
logger.warning("KiwiSDR fetch returned no usable mirror payload")
|
||||
except (requests.RequestException, ConnectionError, TimeoutError, ValueError, KeyError) as e:
|
||||
logger.warning(f"KiwiSDR fetch exception: {e}")
|
||||
|
||||
|
||||
@@ -27,11 +27,21 @@ def fetch_liveuamap():
|
||||
browser = p.chromium.launch(
|
||||
headless=True, args=["--disable-blink-features=AutomationControlled"]
|
||||
)
|
||||
from services.network_utils import outbound_user_agent
|
||||
|
||||
# Per-install handle (no shared Shadowbroker product token). Stealth remains
|
||||
# for Turnstile; see docs/OUTBOUND_DATA.md #348.
|
||||
playwright_ua = (
|
||||
f"Mozilla/5.0 (compatible; {outbound_user_agent('liveuamap')})"
|
||||
)
|
||||
context = browser.new_context(
|
||||
user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||||
user_agent=playwright_ua,
|
||||
viewport={"width": 1920, "height": 1080},
|
||||
color_scheme="dark",
|
||||
)
|
||||
# Bound navigation and script evaluation so a stuck region cannot hang the slow pool.
|
||||
context.set_default_navigation_timeout(60_000)
|
||||
context.set_default_timeout(30_000)
|
||||
page = context.new_page()
|
||||
stealth_sync(page)
|
||||
|
||||
|
||||
@@ -0,0 +1,73 @@
|
||||
"""LiveUAMap Playwright scraper opt-in (#348) — UI consent on Windows."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import threading
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_OPT_IN_FILE = Path(__file__).resolve().parent.parent / "data" / "liveuamap_scraper_opt_in.json"
|
||||
_OPT_IN_LOCK = threading.Lock()
|
||||
|
||||
|
||||
def _env_flag(name: str) -> str:
|
||||
return str(os.getenv(name, "")).strip().lower()
|
||||
|
||||
|
||||
def liveuamap_requires_ui_opt_in() -> bool:
|
||||
"""Windows local installs need explicit consent before Playwright contacts LiveUAMap."""
|
||||
return os.name == "nt"
|
||||
|
||||
|
||||
def get_liveuamap_ui_opt_in() -> bool:
|
||||
if not _OPT_IN_FILE.exists():
|
||||
return False
|
||||
try:
|
||||
payload = json.loads(_OPT_IN_FILE.read_text(encoding="utf-8"))
|
||||
return bool(payload.get("opted_in"))
|
||||
except (OSError, json.JSONDecodeError, TypeError) as e:
|
||||
logger.warning("LiveUAMap opt-in file unreadable: %s", e)
|
||||
return False
|
||||
|
||||
|
||||
def set_liveuamap_ui_opt_in(opted_in: bool) -> None:
|
||||
_OPT_IN_FILE.parent.mkdir(parents=True, exist_ok=True)
|
||||
with _OPT_IN_LOCK:
|
||||
_OPT_IN_FILE.write_text(
|
||||
json.dumps({"opted_in": bool(opted_in)}, indent=2),
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
|
||||
def liveuamap_scraper_enabled() -> bool:
|
||||
"""Whether the Playwright LiveUAMap scraper may run on this backend."""
|
||||
setting = _env_flag("SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER")
|
||||
if setting in {"1", "true", "yes", "on"}:
|
||||
return True
|
||||
if setting in {"0", "false", "no", "off"}:
|
||||
return False
|
||||
if not liveuamap_requires_ui_opt_in():
|
||||
return True
|
||||
return get_liveuamap_ui_opt_in()
|
||||
|
||||
|
||||
def liveuamap_scraper_status() -> dict[str, Any]:
|
||||
setting = _env_flag("SHADOWBROKER_ENABLE_LIVEUAMAP_SCRAPER")
|
||||
env_override = None
|
||||
if setting in {"1", "true", "yes", "on"}:
|
||||
env_override = "on"
|
||||
elif setting in {"0", "false", "no", "off"}:
|
||||
env_override = "off"
|
||||
ui_opted_in = get_liveuamap_ui_opt_in()
|
||||
requires = liveuamap_requires_ui_opt_in()
|
||||
return {
|
||||
"platform_requires_opt_in": requires,
|
||||
"ui_opted_in": ui_opted_in,
|
||||
"scraper_enabled": liveuamap_scraper_enabled(),
|
||||
"env_override": env_override,
|
||||
}
|
||||
@@ -287,28 +287,18 @@ def write_signed_bootstrap_manifest(
|
||||
return manifest
|
||||
|
||||
|
||||
def load_bootstrap_manifest(
|
||||
path: str | Path,
|
||||
def parse_bootstrap_manifest_dict(
|
||||
raw: dict[str, Any],
|
||||
*,
|
||||
signer_public_key_b64: str,
|
||||
now: float | None = None,
|
||||
) -> BootstrapManifest:
|
||||
manifest_path = _resolve_manifest_path(str(path))
|
||||
try:
|
||||
raw = json.loads(manifest_path.read_text(encoding="utf-8"))
|
||||
except FileNotFoundError as exc:
|
||||
raise BootstrapManifestError(f"bootstrap manifest not found: {manifest_path}") from exc
|
||||
except json.JSONDecodeError as exc:
|
||||
raise BootstrapManifestError("bootstrap manifest is not valid JSON") from exc
|
||||
|
||||
if not isinstance(raw, dict):
|
||||
raise BootstrapManifestError("bootstrap manifest root must be an object")
|
||||
|
||||
signature = str(raw.get("signature", "") or "").strip()
|
||||
payload = {key: value for key, value in raw.items() if key != "signature"}
|
||||
if not signature:
|
||||
raise BootstrapManifestError("bootstrap manifest signature is required")
|
||||
|
||||
_verify_manifest_signature(
|
||||
payload,
|
||||
signature_b64=signature,
|
||||
@@ -325,11 +315,36 @@ def load_bootstrap_manifest(
|
||||
)
|
||||
|
||||
|
||||
def load_bootstrap_manifest(
|
||||
path: str | Path,
|
||||
*,
|
||||
signer_public_key_b64: str,
|
||||
now: float | None = None,
|
||||
) -> BootstrapManifest:
|
||||
manifest_path = _resolve_manifest_path(str(path))
|
||||
try:
|
||||
raw = json.loads(manifest_path.read_text(encoding="utf-8"))
|
||||
except FileNotFoundError as exc:
|
||||
raise BootstrapManifestError(f"bootstrap manifest not found: {manifest_path}") from exc
|
||||
except json.JSONDecodeError as exc:
|
||||
raise BootstrapManifestError("bootstrap manifest is not valid JSON") from exc
|
||||
|
||||
if not isinstance(raw, dict):
|
||||
raise BootstrapManifestError("bootstrap manifest root must be an object")
|
||||
return parse_bootstrap_manifest_dict(
|
||||
raw,
|
||||
signer_public_key_b64=signer_public_key_b64,
|
||||
now=now,
|
||||
)
|
||||
|
||||
|
||||
def load_bootstrap_manifest_from_settings(*, now: float | None = None) -> BootstrapManifest | None:
|
||||
settings = get_settings()
|
||||
if bool(getattr(settings, "MESH_BOOTSTRAP_DISABLED", False)):
|
||||
return None
|
||||
signer_public_key_b64 = str(getattr(settings, "MESH_BOOTSTRAP_SIGNER_PUBLIC_KEY", "") or "").strip()
|
||||
from services.mesh.mesh_fleet_defaults import effective_bootstrap_signer_public_key_b64
|
||||
|
||||
signer_public_key_b64 = effective_bootstrap_signer_public_key_b64()
|
||||
if not signer_public_key_b64:
|
||||
return None
|
||||
manifest_path = _resolve_manifest_path(str(getattr(settings, "MESH_BOOTSTRAP_MANIFEST_PATH", "") or ""))
|
||||
|
||||
@@ -168,9 +168,9 @@ def resolve_peer_key_for_url(peer_url: str) -> bytes:
|
||||
try:
|
||||
from services.config import get_settings
|
||||
|
||||
global_secret = str(
|
||||
getattr(get_settings(), "MESH_PEER_PUSH_SECRET", "") or ""
|
||||
).strip()
|
||||
from services.mesh.mesh_fleet_defaults import effective_peer_push_secret
|
||||
|
||||
global_secret = effective_peer_push_secret()
|
||||
except Exception:
|
||||
return b""
|
||||
if not global_secret:
|
||||
|
||||
@@ -0,0 +1,179 @@
|
||||
"""Invite-scoped DM connect delivery: auto relay release and contact severance."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
CONNECT_AUTO_RELEASE_INTENTS = frozenset(
|
||||
{
|
||||
"invite_short_address",
|
||||
"invite_import",
|
||||
"contact_request",
|
||||
"contact_accept",
|
||||
"contact_offer",
|
||||
}
|
||||
)
|
||||
|
||||
INVITE_CONNECT_TRUST_LEVELS = frozenset({"invite_pinned", "sas_verified"})
|
||||
|
||||
|
||||
def _release_profile() -> str:
|
||||
try:
|
||||
from services.release_profiles import current_release_profile
|
||||
|
||||
return str(current_release_profile() or "dev")
|
||||
except Exception:
|
||||
return "dev"
|
||||
|
||||
|
||||
def grant_connect_relay_policy(
|
||||
recipient_id: str,
|
||||
*,
|
||||
reason: str = "connect_scoped_auto_release",
|
||||
) -> dict[str, Any]:
|
||||
"""Pre-authorize hidden relay delivery for an explicit connect target."""
|
||||
peer_key = str(recipient_id or "").strip()
|
||||
if not peer_key:
|
||||
return {"ok": False, "detail": "recipient_id required"}
|
||||
try:
|
||||
from services.mesh.mesh_relay_policy import grant_relay_policy
|
||||
|
||||
return grant_relay_policy(
|
||||
scope_type="dm_contact",
|
||||
scope_id=peer_key,
|
||||
profile=_release_profile(),
|
||||
hidden_transport_required=True,
|
||||
reason=str(reason or "connect_scoped_auto_release"),
|
||||
)
|
||||
except Exception as exc:
|
||||
return {"ok": False, "detail": str(exc) or type(exc).__name__}
|
||||
|
||||
|
||||
def revoke_connect_relay_policy(recipient_id: str) -> dict[str, Any]:
|
||||
peer_key = str(recipient_id or "").strip()
|
||||
if not peer_key:
|
||||
return {"ok": False, "detail": "recipient_id required"}
|
||||
try:
|
||||
from services.mesh.mesh_relay_policy import revoke_relay_policy
|
||||
|
||||
revoked = int(
|
||||
revoke_relay_policy(
|
||||
scope_type="dm_contact",
|
||||
scope_id=peer_key,
|
||||
profile=_release_profile(),
|
||||
)
|
||||
or 0
|
||||
)
|
||||
return {"ok": True, "revoked": revoked}
|
||||
except Exception as exc:
|
||||
return {"ok": False, "detail": str(exc) or type(exc).__name__}
|
||||
|
||||
|
||||
def recipient_has_invite_connect_scope(recipient_id: str) -> bool:
|
||||
peer_key = str(recipient_id or "").strip()
|
||||
if not peer_key:
|
||||
return False
|
||||
try:
|
||||
from services.mesh.mesh_wormhole_contacts import get_wormhole_dm_contact
|
||||
|
||||
contact = get_wormhole_dm_contact(peer_key) or {}
|
||||
except Exception:
|
||||
return False
|
||||
if str(contact.get("invitePinnedPrekeyLookupHandle", "") or "").strip():
|
||||
return True
|
||||
if str(contact.get("invitePinnedLookupPeerUrl", "") or "").strip():
|
||||
return True
|
||||
trust = str(contact.get("trust_level", "") or "").strip().lower()
|
||||
return trust in INVITE_CONNECT_TRUST_LEVELS
|
||||
|
||||
|
||||
def relay_push_peer_urls_for_payload(payload: dict[str, Any]) -> list[str]:
|
||||
urls: list[str] = []
|
||||
for raw in list(payload.get("relay_push_peer_urls") or []):
|
||||
normalized = str(raw or "").strip().rstrip("/")
|
||||
if normalized and normalized not in urls:
|
||||
urls.append(normalized)
|
||||
lookup_peer_url = str(payload.get("lookup_peer_url", "") or "").strip().rstrip("/")
|
||||
if lookup_peer_url:
|
||||
urls = [url for url in urls if url != lookup_peer_url]
|
||||
urls.insert(0, lookup_peer_url)
|
||||
recipient_id = str(payload.get("recipient_id", "") or "").strip()
|
||||
if recipient_id and not urls:
|
||||
try:
|
||||
from services.mesh.mesh_wormhole_contacts import get_wormhole_dm_contact
|
||||
|
||||
contact = get_wormhole_dm_contact(recipient_id) or {}
|
||||
pinned = str(contact.get("invitePinnedLookupPeerUrl", "") or "").strip().rstrip("/")
|
||||
if pinned:
|
||||
urls.append(pinned)
|
||||
except Exception:
|
||||
pass
|
||||
return urls
|
||||
|
||||
|
||||
def should_auto_release_dm_payload(payload: dict[str, Any]) -> bool:
|
||||
if str(payload.get("delivery_class", "") or "").strip().lower() != "request":
|
||||
return False
|
||||
intent = str(payload.get("connect_intent", "") or "").strip().lower()
|
||||
if intent in CONNECT_AUTO_RELEASE_INTENTS:
|
||||
return True
|
||||
if str(payload.get("lookup_peer_url", "") or "").strip():
|
||||
return True
|
||||
recipient_id = str(payload.get("recipient_id", "") or "").strip()
|
||||
return bool(recipient_id and recipient_has_invite_connect_scope(recipient_id))
|
||||
|
||||
|
||||
def enrich_connect_release_payload(payload: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Attach invite-owner relay hints used during private release."""
|
||||
enriched = dict(payload or {})
|
||||
recipient_id = str(enriched.get("recipient_id", "") or "").strip()
|
||||
lookup_peer_url = str(enriched.get("lookup_peer_url", "") or "").strip().rstrip("/")
|
||||
if not lookup_peer_url and recipient_id:
|
||||
try:
|
||||
from services.mesh.mesh_wormhole_contacts import get_wormhole_dm_contact
|
||||
|
||||
contact = get_wormhole_dm_contact(recipient_id) or {}
|
||||
lookup_peer_url = str(contact.get("invitePinnedLookupPeerUrl", "") or "").strip().rstrip("/")
|
||||
except Exception:
|
||||
lookup_peer_url = ""
|
||||
if lookup_peer_url:
|
||||
enriched["lookup_peer_url"] = lookup_peer_url
|
||||
push_urls = relay_push_peer_urls_for_payload(enriched)
|
||||
if push_urls:
|
||||
enriched["relay_push_peer_urls"] = push_urls
|
||||
return enriched
|
||||
|
||||
|
||||
def auto_release_connect_dm_outbox(*, outbox_id: str, payload: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Grant scoped relay policy and approve release for invite-scoped connect traffic."""
|
||||
normalized_outbox = str(outbox_id or "").strip()
|
||||
enriched = enrich_connect_release_payload(payload)
|
||||
if not normalized_outbox:
|
||||
return {"ok": False, "detail": "missing outbox_id"}
|
||||
if not should_auto_release_dm_payload(enriched):
|
||||
return {"ok": True, "skipped": True, "reason": "not_connect_scoped"}
|
||||
recipient_id = str(enriched.get("recipient_id", "") or "").strip()
|
||||
if not recipient_id:
|
||||
return {"ok": False, "detail": "missing recipient_id"}
|
||||
grant = grant_connect_relay_policy(recipient_id)
|
||||
try:
|
||||
from services.mesh.mesh_private_outbox import private_delivery_outbox
|
||||
from services.mesh.mesh_private_release_worker import private_release_worker
|
||||
|
||||
private_delivery_outbox.approve_relay_release(normalized_outbox)
|
||||
private_release_worker.ensure_started()
|
||||
private_release_worker.wake()
|
||||
except Exception as exc:
|
||||
return {
|
||||
"ok": False,
|
||||
"detail": str(exc) or type(exc).__name__,
|
||||
"grant": grant,
|
||||
}
|
||||
return {
|
||||
"ok": True,
|
||||
"auto_released": True,
|
||||
"outbox_id": normalized_outbox,
|
||||
"recipient_id": recipient_id,
|
||||
"grant": grant,
|
||||
"relay_push_peer_urls": relay_push_peer_urls_for_payload(enriched),
|
||||
}
|
||||
@@ -1506,6 +1506,7 @@ class DMRelay:
|
||||
sender_token_hash: str = "",
|
||||
payload_format: str = "dm1",
|
||||
session_welcome: str = "",
|
||||
replication_peer_urls: list[str] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
with self._lock:
|
||||
self._refresh_from_shared_relay()
|
||||
@@ -1573,46 +1574,214 @@ class DMRelay:
|
||||
}
|
||||
if not msg_id:
|
||||
msg_id = f"dm_{int(time.time() * 1000)}_{secrets.token_hex(6)}"
|
||||
elif any(m.msg_id == msg_id for m in self._mailboxes[mailbox_key]):
|
||||
return {"ok": True, "msg_id": msg_id}
|
||||
relay_sender_id = (
|
||||
f"sender_token:{sender_token_hash}"
|
||||
if sender_token_hash
|
||||
else sender_id
|
||||
)
|
||||
self._mailboxes[mailbox_key].append(
|
||||
DMMessage(
|
||||
sender_id=relay_sender_id,
|
||||
ciphertext=ciphertext,
|
||||
timestamp=time.time(),
|
||||
msg_id=msg_id,
|
||||
delivery_class=delivery_class,
|
||||
sender_seal=sender_seal,
|
||||
sender_block_ref=sender_block_ref,
|
||||
payload_format=str(payload_format or "dm1"),
|
||||
session_welcome=str(session_welcome or ""),
|
||||
duplicate_hit = any(m.msg_id == msg_id for m in self._mailboxes[mailbox_key])
|
||||
if not duplicate_hit:
|
||||
relay_sender_id = (
|
||||
f"sender_token:{sender_token_hash}"
|
||||
if sender_token_hash
|
||||
else sender_id
|
||||
)
|
||||
)
|
||||
self._stats["messages_in_memory"] = sum(len(v) for v in self._mailboxes.values())
|
||||
self._save()
|
||||
# Cross-node mailbox replication: push the freshly-stored
|
||||
# envelope to every authenticated relay peer so the recipient
|
||||
# can log into ANY node and find their messages. The push is
|
||||
# async (fire-and-forget thread) so deposit() returns
|
||||
# immediately — slow Tor peers can't block the sender's UX.
|
||||
# Each receiving peer re-enforces the per-sender cap on
|
||||
# acceptance, so hostile relays can't widen the cap.
|
||||
self._mailboxes[mailbox_key].append(
|
||||
DMMessage(
|
||||
sender_id=relay_sender_id,
|
||||
ciphertext=ciphertext,
|
||||
timestamp=time.time(),
|
||||
msg_id=msg_id,
|
||||
delivery_class=delivery_class,
|
||||
sender_seal=sender_seal,
|
||||
sender_block_ref=sender_block_ref,
|
||||
payload_format=str(payload_format or "dm1"),
|
||||
session_welcome=str(session_welcome or ""),
|
||||
)
|
||||
)
|
||||
self._stats["messages_in_memory"] = sum(len(v) for v in self._mailboxes.values())
|
||||
self._save()
|
||||
preferred_urls = list(replication_peer_urls or [])
|
||||
envelope_for_push: dict[str, Any] | None = None
|
||||
try:
|
||||
envelope_for_push = self.envelope_for_replication(
|
||||
mailbox_key=mailbox_key, msg_id=msg_id,
|
||||
mailbox_key=mailbox_key,
|
||||
msg_id=msg_id,
|
||||
recipient_id=recipient_id,
|
||||
recipient_token=recipient_token,
|
||||
)
|
||||
if envelope_for_push:
|
||||
self._replicate_envelope_to_peers_async(
|
||||
envelope=envelope_for_push,
|
||||
)
|
||||
except Exception:
|
||||
metrics_inc("dm_replication_push_error")
|
||||
return {"ok": True, "msg_id": msg_id}
|
||||
deposit_result = {"ok": True, "msg_id": msg_id}
|
||||
if duplicate_hit:
|
||||
deposit_result["duplicate"] = True
|
||||
|
||||
if envelope_for_push:
|
||||
# Invite-scoped connect traffic names an explicit recipient relay
|
||||
# (lookup_peer_url). Block until that push completes so the
|
||||
# recipient can poll their own node; fleet-wide fan-out stays
|
||||
# async so dead manifest peers cannot wedge deposit().
|
||||
if preferred_urls:
|
||||
logger.info(
|
||||
"DM deposit awaiting scoped replicate to %d peer(s)",
|
||||
len(preferred_urls),
|
||||
)
|
||||
deposit_result["replicate"] = self._replicate_envelope_to_peers(
|
||||
envelope=envelope_for_push,
|
||||
preferred_peer_urls=preferred_urls,
|
||||
)
|
||||
else:
|
||||
self._replicate_envelope_to_peers_async(
|
||||
envelope=envelope_for_push,
|
||||
preferred_peer_urls=[],
|
||||
)
|
||||
elif preferred_urls:
|
||||
logger.warning(
|
||||
"DM deposit skipped scoped replicate: envelope missing for msg_id=%s",
|
||||
msg_id,
|
||||
)
|
||||
return deposit_result
|
||||
|
||||
def _replicate_envelope_to_peers(
|
||||
self,
|
||||
*,
|
||||
envelope: dict[str, Any],
|
||||
preferred_peer_urls: list[str] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Push an envelope to relay peers. Returns per-peer results."""
|
||||
import hashlib
|
||||
import hmac
|
||||
import requests as _requests
|
||||
|
||||
from services.mesh.mesh_crypto import (
|
||||
normalize_peer_url,
|
||||
resolve_peer_key_for_url,
|
||||
)
|
||||
from services.mesh.mesh_router import authenticated_push_peer_urls
|
||||
|
||||
peers: list[str] = []
|
||||
for raw_url in list(preferred_peer_urls or []):
|
||||
normalized_preferred = normalize_peer_url(str(raw_url or "").strip())
|
||||
if normalized_preferred and normalized_preferred not in peers:
|
||||
peers.append(normalized_preferred)
|
||||
if not peers:
|
||||
for peer_url in authenticated_push_peer_urls():
|
||||
normalized_peer = normalize_peer_url(str(peer_url or "").strip())
|
||||
if normalized_peer and normalized_peer not in peers:
|
||||
peers.append(normalized_peer)
|
||||
if not peers:
|
||||
return {"ok": False, "detail": "no_relay_peers", "pushed": [], "failed": []}
|
||||
|
||||
logger.info(
|
||||
"DM replicate push starting for %d peer(s): %s",
|
||||
len(peers),
|
||||
", ".join(peers[:3]) + ("..." if len(peers) > 3 else ""),
|
||||
)
|
||||
|
||||
payload = json.dumps(
|
||||
{"envelope": envelope},
|
||||
separators=(",", ":"),
|
||||
ensure_ascii=False,
|
||||
).encode("utf-8")
|
||||
|
||||
base_timeout = max(
|
||||
1,
|
||||
int(getattr(self._settings(), "MESH_RELAY_PUSH_TIMEOUT_S", 10) or 10),
|
||||
)
|
||||
|
||||
from main import _infonet_peer_requests_proxies
|
||||
|
||||
preferred_set = {
|
||||
normalize_peer_url(str(raw_url or "").strip())
|
||||
for raw_url in list(preferred_peer_urls or [])
|
||||
}
|
||||
preferred_set.discard("")
|
||||
|
||||
pushed: list[str] = []
|
||||
failed: list[dict[str, str]] = []
|
||||
for peer_url in peers:
|
||||
try:
|
||||
normalized = normalize_peer_url(peer_url)
|
||||
timeout = max(180 if ".onion" in normalized else 1, base_timeout)
|
||||
headers = {"Content-Type": "application/json"}
|
||||
peer_key = resolve_peer_key_for_url(normalized)
|
||||
if peer_key:
|
||||
headers["X-Peer-Url"] = normalized
|
||||
headers["X-Peer-HMAC"] = hmac.new(
|
||||
peer_key, payload, hashlib.sha256
|
||||
).hexdigest()
|
||||
url = f"{peer_url}/api/mesh/dm/replicate-envelope"
|
||||
request_kwargs: dict[str, Any] = {
|
||||
"data": payload,
|
||||
"timeout": timeout,
|
||||
"headers": headers,
|
||||
}
|
||||
proxies = _infonet_peer_requests_proxies(normalized)
|
||||
if proxies:
|
||||
request_kwargs["proxies"] = proxies
|
||||
resp = None
|
||||
max_attempts = 3 if normalized in preferred_set else 2
|
||||
last_exc = ""
|
||||
for attempt in range(max_attempts):
|
||||
try:
|
||||
resp = _requests.post(url, **request_kwargs)
|
||||
break
|
||||
except Exception as exc:
|
||||
last_exc = str(exc) or type(exc).__name__
|
||||
if attempt + 1 < max_attempts:
|
||||
time.sleep(5.0 * (attempt + 1))
|
||||
continue
|
||||
logger.warning(
|
||||
"DM replicate push to %s failed: %s",
|
||||
peer_url,
|
||||
last_exc,
|
||||
)
|
||||
metrics_inc("dm_replication_push_error")
|
||||
resp = None
|
||||
break
|
||||
if resp is None:
|
||||
failed.append({"url": peer_url, "detail": last_exc or "request_failed"})
|
||||
continue
|
||||
if resp.status_code == 200:
|
||||
body_ok = True
|
||||
detail = ""
|
||||
try:
|
||||
body = resp.json()
|
||||
if isinstance(body, dict) and body.get("ok") is False:
|
||||
body_ok = False
|
||||
detail = str(body.get("detail", "") or "replicate rejected")[:200]
|
||||
except Exception:
|
||||
body_ok = True
|
||||
if body_ok:
|
||||
logger.info("DM replicate push to %s succeeded", peer_url)
|
||||
metrics_inc("dm_replication_push_ok")
|
||||
pushed.append(peer_url)
|
||||
else:
|
||||
logger.warning(
|
||||
"DM replicate push to %s rejected: %s",
|
||||
peer_url,
|
||||
detail,
|
||||
)
|
||||
metrics_inc("dm_replication_push_rejected")
|
||||
failed.append({"url": peer_url, "detail": detail or "replicate_rejected"})
|
||||
else:
|
||||
detail = (resp.text or "")[:200]
|
||||
logger.warning(
|
||||
"DM replicate push to %s -> %s: %s",
|
||||
peer_url,
|
||||
resp.status_code,
|
||||
detail,
|
||||
)
|
||||
metrics_inc("dm_replication_push_rejected")
|
||||
failed.append({"url": peer_url, "detail": f"http_{resp.status_code}: {detail}"})
|
||||
except Exception as exc:
|
||||
logger.warning("DM replicate push outer failure for %s: %s", peer_url, exc)
|
||||
metrics_inc("dm_replication_push_error")
|
||||
failed.append({"url": peer_url, "detail": str(exc) or type(exc).__name__})
|
||||
|
||||
scoped = bool(preferred_set)
|
||||
ok = bool(pushed) if scoped else bool(pushed) or not failed
|
||||
return {
|
||||
"ok": ok,
|
||||
"scoped": scoped,
|
||||
"pushed": pushed,
|
||||
"failed": failed,
|
||||
}
|
||||
|
||||
def accept_replica(
|
||||
self,
|
||||
@@ -1645,6 +1814,33 @@ class DMRelay:
|
||||
mailbox_key = str(envelope.get("mailbox_key", "") or "").strip()
|
||||
sender_block_ref = str(envelope.get("sender_block_ref", "") or "").strip()
|
||||
ciphertext = str(envelope.get("ciphertext", "") or "")
|
||||
delivery_class = str(envelope.get("delivery_class", "") or "").strip().lower()
|
||||
recipient_id = str(envelope.get("recipient_id", "") or "").strip()
|
||||
recipient_token = str(envelope.get("recipient_token", "") or "").strip()
|
||||
if delivery_class not in ("request", "shared", "self"):
|
||||
if recipient_id and not recipient_token:
|
||||
delivery_class = "request"
|
||||
elif recipient_token:
|
||||
delivery_class = "shared"
|
||||
if delivery_class == "request":
|
||||
if not recipient_id:
|
||||
try:
|
||||
from services.mesh.mesh_wormhole_persona import get_dm_identity
|
||||
|
||||
recipient_id = str((get_dm_identity() or {}).get("node_id") or "").strip()
|
||||
except Exception:
|
||||
recipient_id = ""
|
||||
if recipient_id:
|
||||
mailbox_key = self.mailbox_key_for_delivery(
|
||||
recipient_id=recipient_id,
|
||||
delivery_class="request",
|
||||
)
|
||||
elif delivery_class == "shared" and recipient_token:
|
||||
mailbox_key = self.mailbox_key_for_delivery(
|
||||
recipient_id=recipient_id,
|
||||
delivery_class="shared",
|
||||
recipient_token=recipient_token,
|
||||
)
|
||||
if not msg_id or not mailbox_key or not sender_block_ref or not ciphertext:
|
||||
return {"ok": False, "detail": "envelope missing required fields"}
|
||||
|
||||
@@ -1662,7 +1858,6 @@ class DMRelay:
|
||||
# Same per-class cap as the deposit path — defense in depth
|
||||
# against a peer that wraps a "deposit" as a "replica" to
|
||||
# bypass the class limit.
|
||||
delivery_class = str(envelope.get("delivery_class", "") or "")
|
||||
if delivery_class in ("request", "shared", "self"):
|
||||
class_limit = self._mailbox_limit_for_class(delivery_class)
|
||||
else:
|
||||
@@ -1716,82 +1911,18 @@ class DMRelay:
|
||||
self,
|
||||
*,
|
||||
envelope: dict[str, Any],
|
||||
preferred_peer_urls: list[str] | None = None,
|
||||
) -> None:
|
||||
"""Push an outbound DM envelope to every authenticated relay peer.
|
||||
|
||||
Fire-and-forget: spawned in a background thread so ``deposit``
|
||||
returns to the caller immediately. Per-peer errors are logged
|
||||
and swallowed — the sender's UX must not block on slow Tor
|
||||
peers, and a peer that's down today gets the next message
|
||||
whenever it comes back. Inbound recipient polling from a healthy
|
||||
peer keeps the system functional during peer failures.
|
||||
|
||||
Each peer is authed with the existing per-peer HMAC pattern
|
||||
(#256) — same headers and key resolver gate-message replication
|
||||
uses, so a hostile node that doesn't know any peer's HMAC key
|
||||
can't impersonate a legitimate relay.
|
||||
"""
|
||||
"""Fire-and-forget fleet-wide replicate push (non-scoped traffic)."""
|
||||
import threading
|
||||
|
||||
def _do_push():
|
||||
def _do_push() -> None:
|
||||
try:
|
||||
import hashlib
|
||||
import hmac
|
||||
import requests as _requests
|
||||
|
||||
from services.mesh.mesh_crypto import (
|
||||
normalize_peer_url,
|
||||
resolve_peer_key_for_url,
|
||||
self._replicate_envelope_to_peers(
|
||||
envelope=envelope,
|
||||
preferred_peer_urls=preferred_peer_urls,
|
||||
)
|
||||
from services.mesh.mesh_router import (
|
||||
authenticated_push_peer_urls,
|
||||
)
|
||||
|
||||
peers = authenticated_push_peer_urls()
|
||||
if not peers:
|
||||
return
|
||||
|
||||
payload = json.dumps(
|
||||
{"envelope": envelope},
|
||||
separators=(",", ":"),
|
||||
ensure_ascii=False,
|
||||
).encode("utf-8")
|
||||
|
||||
timeout = max(
|
||||
1,
|
||||
int(getattr(self._settings(), "MESH_RELAY_PUSH_TIMEOUT_S", 10) or 10),
|
||||
)
|
||||
|
||||
for peer_url in peers:
|
||||
try:
|
||||
normalized = normalize_peer_url(peer_url)
|
||||
headers = {"Content-Type": "application/json"}
|
||||
peer_key = resolve_peer_key_for_url(normalized)
|
||||
if peer_key:
|
||||
headers["X-Peer-Url"] = normalized
|
||||
headers["X-Peer-HMAC"] = hmac.new(
|
||||
peer_key, payload, hashlib.sha256
|
||||
).hexdigest()
|
||||
url = f"{peer_url}/api/mesh/dm/replicate-envelope"
|
||||
resp = _requests.post(
|
||||
url, data=payload, timeout=timeout, headers=headers,
|
||||
)
|
||||
if resp.status_code == 200:
|
||||
metrics_inc("dm_replication_push_ok")
|
||||
else:
|
||||
# 4xx including the structured cap_violation
|
||||
# rejection from accept_replica — sender's
|
||||
# relay learns and stops retrying this msg_id.
|
||||
metrics_inc("dm_replication_push_rejected")
|
||||
except Exception:
|
||||
# Per-peer failure is non-fatal — log to metrics
|
||||
# but don't break the loop. Other peers and a
|
||||
# future retry can still propagate the envelope.
|
||||
metrics_inc("dm_replication_push_error")
|
||||
continue
|
||||
except Exception:
|
||||
# Outer guard — never let replication errors propagate
|
||||
# back to the sender's deposit() caller.
|
||||
metrics_inc("dm_replication_push_error")
|
||||
|
||||
thread = threading.Thread(
|
||||
@@ -1806,6 +1937,8 @@ class DMRelay:
|
||||
*,
|
||||
mailbox_key: str,
|
||||
msg_id: str,
|
||||
recipient_id: str = "",
|
||||
recipient_token: str | None = None,
|
||||
) -> dict[str, Any] | None:
|
||||
"""Return the wire-form envelope for a stored message, suitable
|
||||
for POSTing to a peer relay's replicate-envelope endpoint.
|
||||
@@ -1822,6 +1955,8 @@ class DMRelay:
|
||||
return {
|
||||
"msg_id": m.msg_id,
|
||||
"mailbox_key": mailbox_key,
|
||||
"recipient_id": str(recipient_id or "").strip(),
|
||||
"recipient_token": str(recipient_token or "").strip(),
|
||||
"sender_id": m.sender_id,
|
||||
"sender_block_ref": m.sender_block_ref,
|
||||
"sender_seal": m.sender_seal,
|
||||
|
||||
@@ -0,0 +1,64 @@
|
||||
"""Public Infonet fleet defaults for sb-testnet-0 participants.
|
||||
|
||||
Operators who run private single-node installs can set ``MESH_INFONET_FLEET_JOIN=false``
|
||||
and provide their own signer keys / peer secrets.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
FLEET_NETWORK_ID = "sb-testnet-0"
|
||||
FLEET_SEED_ONION_URL = (
|
||||
"http://gqpbunqbgtkcqilvclm3xrkt3zowjyl3s62kkktvojgvxzizamvbrqid.onion:8000"
|
||||
)
|
||||
FLEET_BOOTSTRAP_SIGNER_PUBLIC_KEY_B64 = (
|
||||
"ul1d0kj/ODPIp0OhHzX8eLAVXzJ3CVvzW1vn2IC6q3I="
|
||||
)
|
||||
# Shared fleet HMAC for sb-testnet peer announce/push/sync. Public testnet join model.
|
||||
FLEET_PEER_PUSH_SECRET = "b7GoqsvoUD9MV7tyt0ZOzMptLA84QG6KCfaV9nDqz5Y"
|
||||
|
||||
|
||||
def infonet_fleet_join_enabled() -> bool:
|
||||
try:
|
||||
from services.config import get_settings
|
||||
|
||||
if bool(getattr(get_settings(), "MESH_INFONET_FLEET_JOIN_DISABLED", False)):
|
||||
return False
|
||||
return bool(getattr(get_settings(), "MESH_INFONET_FLEET_JOIN", True))
|
||||
except Exception:
|
||||
return True
|
||||
|
||||
|
||||
def effective_bootstrap_signer_public_key_b64() -> str:
|
||||
try:
|
||||
from services.config import get_settings
|
||||
|
||||
configured = str(getattr(get_settings(), "MESH_BOOTSTRAP_SIGNER_PUBLIC_KEY", "") or "").strip()
|
||||
if configured:
|
||||
return configured
|
||||
except Exception:
|
||||
pass
|
||||
if infonet_fleet_join_enabled():
|
||||
return FLEET_BOOTSTRAP_SIGNER_PUBLIC_KEY_B64
|
||||
return ""
|
||||
|
||||
|
||||
def effective_peer_push_secret() -> str:
|
||||
try:
|
||||
from services.config import get_settings
|
||||
|
||||
configured = str(getattr(get_settings(), "MESH_PEER_PUSH_SECRET", "") or "").strip()
|
||||
if configured:
|
||||
return configured
|
||||
except Exception:
|
||||
pass
|
||||
if infonet_fleet_join_enabled():
|
||||
return FLEET_PEER_PUSH_SECRET
|
||||
return ""
|
||||
|
||||
|
||||
def configured_bootstrap_seed_peers_with_fleet_default(peers: list[str]) -> list[str]:
|
||||
if peers:
|
||||
return peers
|
||||
if infonet_fleet_join_enabled():
|
||||
return [FLEET_SEED_ONION_URL]
|
||||
return []
|
||||
@@ -0,0 +1,86 @@
|
||||
"""Auto-enable Tor wormhole transport on Infonet relay/seed nodes."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
from services.config import get_settings
|
||||
from services.wormhole_settings import read_wormhole_settings, write_wormhole_settings
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def infonet_relay_auto_wormhole_requested() -> bool:
|
||||
settings = get_settings()
|
||||
if bool(settings.MESH_INFONET_RELAY_AUTO_WORMHOLE_DISABLED):
|
||||
return False
|
||||
if bool(settings.MESH_INFONET_RELAY_AUTO_WORMHOLE):
|
||||
return True
|
||||
if str(settings.MESH_BOOTSTRAP_SIGNER_PRIVATE_KEY or "").strip():
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _relay_tor_wormhole_target_settings() -> dict[str, Any]:
|
||||
settings = get_settings()
|
||||
socks_port = int(settings.MESH_ARTI_SOCKS_PORT or 9050)
|
||||
return {
|
||||
"enabled": True,
|
||||
"transport": "tor_arti",
|
||||
"socks_proxy": f"socks5h://127.0.0.1:{socks_port}",
|
||||
"socks_dns": True,
|
||||
"anonymous_mode": True,
|
||||
}
|
||||
|
||||
|
||||
def _wormhole_settings_match(existing: dict[str, Any], target: dict[str, Any]) -> bool:
|
||||
return (
|
||||
bool(existing.get("enabled")) is bool(target["enabled"])
|
||||
and str(existing.get("transport", "")) == str(target["transport"])
|
||||
and str(existing.get("socks_proxy", "")) == str(target["socks_proxy"])
|
||||
and bool(existing.get("socks_dns", True)) is bool(target["socks_dns"])
|
||||
and bool(existing.get("anonymous_mode", False)) is bool(target["anonymous_mode"])
|
||||
)
|
||||
|
||||
|
||||
def ensure_infonet_relay_wormhole_ready(*, reason: str = "relay_auto") -> dict[str, Any]:
|
||||
"""Persist Tor wormhole settings and connect on relay/seed startup."""
|
||||
if not infonet_relay_auto_wormhole_requested():
|
||||
return {"ok": True, "skipped": True, "reason": "not_requested"}
|
||||
|
||||
from routers.ai_intel import _write_env_value
|
||||
from services.tor_hidden_service import tor_service
|
||||
from services.wormhole_supervisor import connect_wormhole, restart_wormhole
|
||||
|
||||
existing = read_wormhole_settings()
|
||||
target = _relay_tor_wormhole_target_settings()
|
||||
settings_updated = not _wormhole_settings_match(existing, target)
|
||||
updated = write_wormhole_settings(**target) if settings_updated else existing
|
||||
|
||||
tor_result: dict[str, Any] = {"ok": False, "detail": "not started"}
|
||||
try:
|
||||
tor_result = tor_service.start(target_port=8000)
|
||||
if tor_result.get("ok"):
|
||||
_write_env_value("MESH_ARTI_ENABLED", "true")
|
||||
get_settings.cache_clear()
|
||||
except Exception as exc:
|
||||
tor_result = {"ok": False, "detail": str(exc or type(exc).__name__)}
|
||||
|
||||
runtime = (
|
||||
restart_wormhole(reason=reason)
|
||||
if settings_updated
|
||||
else connect_wormhole(reason=reason)
|
||||
)
|
||||
|
||||
if settings_updated:
|
||||
logger.info("Infonet relay auto-wormhole enabled (%s)", reason)
|
||||
|
||||
return {
|
||||
"ok": True,
|
||||
"skipped": False,
|
||||
"settings_updated": settings_updated,
|
||||
"tor": tor_result,
|
||||
"runtime": runtime,
|
||||
"settings": updated,
|
||||
}
|
||||
@@ -125,8 +125,8 @@ def dm_lookup_response_view(
|
||||
view.pop("lookup_mode", None)
|
||||
view.pop("removal_target", None)
|
||||
return view
|
||||
if invite_lookup:
|
||||
view.pop("agent_id", None)
|
||||
# Successful invite lookups keep agent_id: the handle is the capability and
|
||||
# first-contact messaging needs a delivery target. Failures stay generic.
|
||||
return view
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,152 @@
|
||||
"""Operator-signed peer registry for private Infonet swarm discovery."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import time
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from services.mesh.mesh_crypto import normalize_peer_url
|
||||
from services.mesh.mesh_router import peer_transport_kind
|
||||
|
||||
BACKEND_DIR = Path(__file__).resolve().parents[2]
|
||||
DATA_DIR = BACKEND_DIR / "data"
|
||||
DEFAULT_PEER_REGISTRY_PATH = DATA_DIR / "peer_registry.json"
|
||||
REGISTRY_VERSION = 1
|
||||
ALLOWED_REGISTRY_ROLES = {"participant", "relay", "seed"}
|
||||
|
||||
|
||||
@dataclass
|
||||
class RegistryPeer:
|
||||
peer_url: str
|
||||
transport: str
|
||||
role: str
|
||||
node_id: str = ""
|
||||
label: str = ""
|
||||
announced_at: int = 0
|
||||
last_seen_at: int = 0
|
||||
failure_count: int = 0
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
def manifest_peer(self) -> dict[str, str]:
|
||||
return {
|
||||
"peer_url": self.peer_url,
|
||||
"transport": self.transport,
|
||||
"role": self.role,
|
||||
"label": self.label or self.node_id[:16],
|
||||
}
|
||||
|
||||
|
||||
class PeerRegistry:
|
||||
def __init__(self, path: str | Path = DEFAULT_PEER_REGISTRY_PATH):
|
||||
self.path = Path(path)
|
||||
self._peers: dict[str, RegistryPeer] = {}
|
||||
|
||||
def load(self) -> list[RegistryPeer]:
|
||||
if not self.path.exists():
|
||||
self._peers = {}
|
||||
return []
|
||||
raw = json.loads(self.path.read_text(encoding="utf-8"))
|
||||
if not isinstance(raw, dict):
|
||||
raise ValueError("peer registry root must be an object")
|
||||
version = int(raw.get("version", 0) or 0)
|
||||
if version != REGISTRY_VERSION:
|
||||
raise ValueError(f"unsupported peer registry version: {version}")
|
||||
entries = raw.get("peers", [])
|
||||
if not isinstance(entries, list):
|
||||
raise ValueError("peer registry peers must be a list")
|
||||
peers: dict[str, RegistryPeer] = {}
|
||||
for entry in entries:
|
||||
if not isinstance(entry, dict):
|
||||
continue
|
||||
peer = self._normalize_entry(entry)
|
||||
peers[peer.peer_url] = peer
|
||||
self._peers = peers
|
||||
return self.records()
|
||||
|
||||
def save(self) -> None:
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
payload = {
|
||||
"version": REGISTRY_VERSION,
|
||||
"updated_at": int(time.time()),
|
||||
"peers": [peer.to_dict() for peer in self.records()],
|
||||
}
|
||||
self.path.write_text(
|
||||
json.dumps(payload, sort_keys=True, indent=2) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
def records(self) -> list[RegistryPeer]:
|
||||
return sorted(self._peers.values(), key=lambda item: (item.role, item.peer_url))
|
||||
|
||||
def upsert_announcement(
|
||||
self,
|
||||
*,
|
||||
peer_url: str,
|
||||
transport: str,
|
||||
role: str,
|
||||
node_id: str = "",
|
||||
label: str = "",
|
||||
now: float | None = None,
|
||||
) -> RegistryPeer:
|
||||
normalized = normalize_peer_url(peer_url)
|
||||
if not normalized:
|
||||
raise ValueError("peer_url is required")
|
||||
resolved_transport = str(transport or "").strip().lower() or str(peer_transport_kind(normalized) or "")
|
||||
if resolved_transport not in {"onion", "clearnet"}:
|
||||
raise ValueError("unsupported peer transport")
|
||||
resolved_role = str(role or "participant").strip().lower()
|
||||
if resolved_role not in ALLOWED_REGISTRY_ROLES:
|
||||
raise ValueError("unsupported peer role")
|
||||
timestamp = int(now if now is not None else time.time())
|
||||
existing = self._peers.get(normalized)
|
||||
peer = RegistryPeer(
|
||||
peer_url=normalized,
|
||||
transport=resolved_transport,
|
||||
role=resolved_role,
|
||||
node_id=str(node_id or (existing.node_id if existing else "") or "").strip(),
|
||||
label=str(label or (existing.label if existing else "") or "").strip(),
|
||||
announced_at=int(existing.announced_at if existing and existing.announced_at else timestamp),
|
||||
last_seen_at=timestamp,
|
||||
failure_count=int(existing.failure_count if existing else 0),
|
||||
)
|
||||
self._peers[normalized] = peer
|
||||
return peer
|
||||
|
||||
def prune_stale(self, *, max_age_s: int, now: float | None = None) -> int:
|
||||
timestamp = int(now if now is not None else time.time())
|
||||
removed = 0
|
||||
for peer_url, peer in list(self._peers.items()):
|
||||
if peer.role == "seed":
|
||||
continue
|
||||
last_seen = int(peer.last_seen_at or peer.announced_at or 0)
|
||||
if last_seen > 0 and timestamp - last_seen > max(60, int(max_age_s or 0)):
|
||||
del self._peers[peer_url]
|
||||
removed += 1
|
||||
return removed
|
||||
|
||||
def manifest_peers(self) -> list[dict[str, str]]:
|
||||
return [peer.manifest_peer() for peer in self.records()]
|
||||
|
||||
def _normalize_entry(self, entry: dict[str, Any]) -> RegistryPeer:
|
||||
peer_url = normalize_peer_url(str(entry.get("peer_url", "") or ""))
|
||||
if not peer_url:
|
||||
raise ValueError("registry peer_url is required")
|
||||
transport = str(entry.get("transport", "") or peer_transport_kind(peer_url) or "").strip().lower()
|
||||
role = str(entry.get("role", "participant") or "participant").strip().lower()
|
||||
if role not in ALLOWED_REGISTRY_ROLES:
|
||||
raise ValueError("registry role unsupported")
|
||||
return RegistryPeer(
|
||||
peer_url=peer_url,
|
||||
transport=transport,
|
||||
role=role,
|
||||
node_id=str(entry.get("node_id", "") or "").strip(),
|
||||
label=str(entry.get("label", "") or "").strip(),
|
||||
announced_at=int(entry.get("announced_at", 0) or 0),
|
||||
last_seen_at=int(entry.get("last_seen_at", 0) or entry.get("announced_at", 0) or 0),
|
||||
failure_count=int(entry.get("failure_count", 0) or 0),
|
||||
)
|
||||
@@ -16,7 +16,7 @@ DATA_DIR = BACKEND_DIR / "data"
|
||||
DEFAULT_PEER_STORE_PATH = DATA_DIR / "peer_store.json"
|
||||
PEER_STORE_VERSION = 1
|
||||
ALLOWED_PEER_BUCKETS = {"bootstrap", "sync", "push"}
|
||||
ALLOWED_PEER_SOURCES = {"bundle", "operator", "bootstrap_promoted", "runtime"}
|
||||
ALLOWED_PEER_SOURCES = {"bundle", "operator", "bootstrap_promoted", "runtime", "swarm"}
|
||||
ALLOWED_PEER_TRANSPORTS = {"clearnet", "onion"}
|
||||
ALLOWED_PEER_ROLES = {"participant", "relay", "seed"}
|
||||
|
||||
|
||||
@@ -140,10 +140,24 @@ def transport_tier_from_state(state: dict[str, Any] | None) -> str:
|
||||
snapshot = state or {}
|
||||
if not bool(snapshot.get("configured")):
|
||||
return "public_degraded"
|
||||
if not bool(snapshot.get("ready")):
|
||||
return "public_degraded"
|
||||
arti_ready = bool(snapshot.get("arti_ready"))
|
||||
rns_ready = bool(snapshot.get("rns_ready"))
|
||||
running = bool(snapshot.get("running"))
|
||||
transport_usable = bool(snapshot.get("ready"))
|
||||
if not transport_usable:
|
||||
try:
|
||||
from services.config import get_settings
|
||||
|
||||
if (
|
||||
bool(getattr(get_settings(), "MESH_WORMHOLE_TRUST_FILE_READY", False))
|
||||
and running
|
||||
and arti_ready
|
||||
):
|
||||
transport_usable = True
|
||||
except Exception:
|
||||
pass
|
||||
if not transport_usable:
|
||||
return "public_degraded"
|
||||
if arti_ready and rns_ready:
|
||||
return "private_strong"
|
||||
if arti_ready or rns_ready:
|
||||
@@ -157,8 +171,45 @@ def transport_tier_is_sufficient(current_tier: str | None, required_tier: str |
|
||||
return TRANSPORT_TIER_ORDER[current] >= TRANSPORT_TIER_ORDER[required]
|
||||
|
||||
|
||||
def release_lane_required_tier(lane: str) -> str:
|
||||
return network_release_required_tier(lane)
|
||||
_DM_RUNTIME_ENFORCEMENT_ROUTES = {
|
||||
("POST", "/api/mesh/dm/send"),
|
||||
("POST", "/api/mesh/dm/poll"),
|
||||
("GET", "/api/mesh/dm/poll"),
|
||||
("GET", "/api/mesh/dm/count"),
|
||||
("POST", "/api/mesh/dm/count"),
|
||||
}
|
||||
|
||||
|
||||
def runtime_route_enforcement_tier(path: str, method: str, *, static_tier: str) -> str:
|
||||
"""Adjust static route tiers for Tor-only nodes that never reach private_strong."""
|
||||
normalized_path = str(path or "").strip()
|
||||
normalized_method = str(method or "").strip().upper()
|
||||
static = normalize_transport_tier(static_tier)
|
||||
if (normalized_method, normalized_path) not in _DM_RUNTIME_ENFORCEMENT_ROUTES:
|
||||
return static
|
||||
if static != "private_strong":
|
||||
return static
|
||||
return release_lane_required_tier("dm")
|
||||
|
||||
|
||||
def release_lane_required_tier(lane: str, *, wormhole_state: dict[str, Any] | None = None) -> str:
|
||||
normalized_lane = str(lane or "").strip().lower()
|
||||
required = network_release_required_tier(normalized_lane)
|
||||
if normalized_lane != "dm":
|
||||
return required
|
||||
state = wormhole_state
|
||||
if state is None:
|
||||
try:
|
||||
from services.wormhole_supervisor import get_wormhole_state
|
||||
|
||||
state = get_wormhole_state()
|
||||
except Exception:
|
||||
state = {}
|
||||
# Tor-only nodes never reach private_strong (needs Arti + RNS). Encrypted
|
||||
# relay over Arti still preserves ciphertext privacy for offline delivery.
|
||||
if not bool((state or {}).get("rns_enabled")):
|
||||
return "private_transitional"
|
||||
return required
|
||||
|
||||
|
||||
def private_delivery_status(status_code: str, *, reason_code: str = "", plain_reason: str = "") -> dict[str, str]:
|
||||
|
||||
@@ -386,6 +386,20 @@ def _dispatch_dm(
|
||||
sampled=sampled,
|
||||
)
|
||||
|
||||
replication_peer_urls: list[str] = []
|
||||
try:
|
||||
from services.mesh.mesh_dm_connect_delivery import relay_push_peer_urls_for_payload
|
||||
|
||||
replication_peer_urls = [
|
||||
str(raw or "").strip().rstrip("/")
|
||||
for raw in list(payload.get("relay_push_peer_urls") or [])
|
||||
if str(raw or "").strip()
|
||||
]
|
||||
if not replication_peer_urls:
|
||||
replication_peer_urls = relay_push_peer_urls_for_payload(payload)
|
||||
except Exception:
|
||||
replication_peer_urls = []
|
||||
|
||||
apply_dm_relay_jitter()
|
||||
relay_result = dm_relay.deposit(
|
||||
sender_id=relay_sender_id,
|
||||
@@ -399,7 +413,25 @@ def _dispatch_dm(
|
||||
sender_token_hash=sender_token_hash,
|
||||
payload_format=payload_format,
|
||||
session_welcome=session_welcome,
|
||||
replication_peer_urls=replication_peer_urls,
|
||||
)
|
||||
replicate_info = dict(relay_result.get("replicate") or {})
|
||||
if replication_peer_urls and not replicate_info.get("ok"):
|
||||
return _dispatch_result(
|
||||
ok=False,
|
||||
lane="dm",
|
||||
selected_transport="relay",
|
||||
selected_carrier="relay",
|
||||
dispatch_reason="scoped_relay_replicate_failed",
|
||||
hidden_transport_effective=bool(hidden_relay),
|
||||
no_acceptable_path=False,
|
||||
detail=(
|
||||
"Scoped relay replicate did not reach the recipient node: "
|
||||
+ str(replicate_info.get("failed") or replicate_info.get("detail") or "unknown")
|
||||
),
|
||||
msg_id=msg_id,
|
||||
replicate=replicate_info,
|
||||
)
|
||||
if not relay_result.get("ok"):
|
||||
return _dispatch_result(
|
||||
ok=False,
|
||||
@@ -436,6 +468,7 @@ def _dispatch_dm(
|
||||
else str(relay_result.get("detail", "") or "Delivered privately")
|
||||
),
|
||||
msg_id=str(relay_result.get("msg_id", "") or msg_id),
|
||||
replicate=replicate_info,
|
||||
)
|
||||
|
||||
|
||||
@@ -600,8 +633,15 @@ def attempt_private_release(
|
||||
policy_reason_code=str(decision.reason_code or ""),
|
||||
)
|
||||
if normalized_lane == "dm":
|
||||
dm_payload = dict(payload or {})
|
||||
try:
|
||||
from services.mesh.mesh_dm_connect_delivery import enrich_connect_release_payload
|
||||
|
||||
dm_payload = enrich_connect_release_payload(dm_payload)
|
||||
except Exception:
|
||||
pass
|
||||
return _dispatch_dm(
|
||||
dict(payload or {}),
|
||||
dm_payload,
|
||||
secure_dm_enabled=secure_dm_enabled or _secure_dm_enabled,
|
||||
rns_private_dm_ready=rns_private_dm_ready or _rns_private_dm_ready,
|
||||
anonymous_dm_hidden_transport_enforced=(
|
||||
|
||||
@@ -36,6 +36,22 @@ def _require_fields(payload: dict[str, Any], fields: tuple[str, ...]) -> tuple[b
|
||||
return True, "ok"
|
||||
|
||||
|
||||
_SEALED_CIPHERTEXT_PREFIXES = ("x3dh1:", "dm1:", "mls1:", "sealed:")
|
||||
|
||||
|
||||
def _strip_sealed_ciphertext_prefix(value: str) -> str:
|
||||
lowered = value.lower()
|
||||
for prefix in _SEALED_CIPHERTEXT_PREFIXES:
|
||||
if lowered.startswith(prefix):
|
||||
return value[len(prefix) :]
|
||||
return value
|
||||
|
||||
|
||||
def _sealed_ciphertext_has_known_prefix(value: str) -> bool:
|
||||
lowered = str(value or "").strip().lower()
|
||||
return any(lowered.startswith(prefix) for prefix in _SEALED_CIPHERTEXT_PREFIXES)
|
||||
|
||||
|
||||
def _decode_base64ish(value: Any) -> bytes | None:
|
||||
raw = str(value or "").strip()
|
||||
if not raw or any(ch.isspace() for ch in raw):
|
||||
@@ -49,6 +65,13 @@ def _decode_base64ish(value: Any) -> bytes | None:
|
||||
return None
|
||||
|
||||
|
||||
def _decode_sealed_ciphertext_value(value: Any) -> bytes | None:
|
||||
raw = str(value or "").strip()
|
||||
if not raw:
|
||||
return None
|
||||
return _decode_base64ish(_strip_sealed_ciphertext_prefix(raw))
|
||||
|
||||
|
||||
def _byte_entropy(data: bytes) -> float:
|
||||
if not data:
|
||||
return 0.0
|
||||
@@ -66,12 +89,19 @@ def _validate_sealed_bytes_field(
|
||||
min_bytes: int = 8,
|
||||
entropy_floor: float = 2.5,
|
||||
) -> tuple[bool, str]:
|
||||
data = _decode_base64ish(payload.get(field, ""))
|
||||
raw = str(payload.get(field, "") or "").strip()
|
||||
prefixed = _sealed_ciphertext_has_known_prefix(raw)
|
||||
data = _decode_sealed_ciphertext_value(raw)
|
||||
if data is None:
|
||||
return False, f"{field} must be base64-encoded sealed bytes"
|
||||
if len(data) < min_bytes:
|
||||
return False, f"{field} is too short"
|
||||
|
||||
# X3DH / MLS envelopes are structured JSON or ratchet frames — skip
|
||||
# plaintext heuristics once a known wire prefix is present.
|
||||
if prefixed:
|
||||
return True, "ok"
|
||||
|
||||
# Short test vectors and compact envelopes can be low entropy; only apply
|
||||
# heuristics once there is enough material to distinguish a sealed blob
|
||||
# from accidental base64-encoded plaintext.
|
||||
|
||||
@@ -38,6 +38,11 @@ _REVOCATION_TTL_CACHE: dict[str, dict[str, Any]] = {}
|
||||
_REVOCATION_TTL_LOCK = threading.Lock()
|
||||
_REVOCATION_REFRESH_LOCK = threading.Lock()
|
||||
_REVOCATION_REFRESH_FAIL_FAST_WINDOW_S = 5.0
|
||||
|
||||
|
||||
def _request_scope_path(request: Request) -> str:
|
||||
scope = getattr(request, "scope", {}) or {}
|
||||
return str(scope.get("path") or "")
|
||||
_REVOCATION_REFRESH_RETRY_AFTER_S = 5
|
||||
_REVOCATION_PRECHECK_UNAVAILABLE_DETAIL = "Signed event integrity preflight unavailable"
|
||||
|
||||
@@ -166,7 +171,7 @@ def _canonical_signed_write_retry_payload(
|
||||
signed_context = build_signed_context(
|
||||
event_type=prepared.event_type,
|
||||
kind=prepared.kind.value,
|
||||
endpoint=str(request.url.path or ""),
|
||||
endpoint=_request_scope_path(request),
|
||||
lane_floor=_content_private_required_transport_tier(prepared.kind),
|
||||
sequence_domain=_signed_context_sequence_domain(prepared),
|
||||
node_id=prepared.node_id,
|
||||
@@ -458,8 +463,26 @@ def _apply_content_private_transport_lock_policy(prepared: "PreparedSignedWrite"
|
||||
except Exception:
|
||||
current_tier = "public_degraded"
|
||||
|
||||
lock_to_satisfy = normalized
|
||||
if prepared.kind in {
|
||||
SignedWriteKind.DM_POLL,
|
||||
SignedWriteKind.DM_COUNT,
|
||||
SignedWriteKind.DM_SEND,
|
||||
SignedWriteKind.DM_REGISTER,
|
||||
SignedWriteKind.DM_BLOCK,
|
||||
SignedWriteKind.DM_WITNESS,
|
||||
}:
|
||||
from services.mesh.mesh_privacy_policy import release_lane_required_tier
|
||||
|
||||
lane_cap = release_lane_required_tier("dm")
|
||||
# Clients sign private_strong; Tor-only nodes cap DM at
|
||||
# private_transitional. Accept when live transport meets the
|
||||
# strongest tier this node can offer on the DM lane.
|
||||
if not transport_tier_is_sufficient(lane_cap, normalized):
|
||||
lock_to_satisfy = lane_cap
|
||||
|
||||
if (
|
||||
not transport_tier_is_sufficient(current_tier, normalized)
|
||||
not transport_tier_is_sufficient(current_tier, lock_to_satisfy)
|
||||
and prepared.kind not in _QUEUEABLE_CONTENT_PRIVATE_KINDS
|
||||
):
|
||||
metrics_inc("signed_write_transport_lock_tier_mismatch")
|
||||
@@ -540,7 +563,7 @@ def _apply_signed_context_policy(prepared: "PreparedSignedWrite", request: Reque
|
||||
ok, reason = validate_signed_context(
|
||||
event_type=prepared.event_type,
|
||||
kind=prepared.kind.value,
|
||||
endpoint=str(request.url.path or ""),
|
||||
endpoint=_request_scope_path(request),
|
||||
lane_floor=_content_private_required_transport_tier(prepared.kind),
|
||||
sequence_domain=_signed_context_sequence_domain(prepared),
|
||||
node_id=prepared.node_id,
|
||||
|
||||
@@ -0,0 +1,507 @@
|
||||
"""Private Infonet swarm discovery and immediate ledger propagation."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import threading
|
||||
import time
|
||||
from typing import Any
|
||||
|
||||
from services.config import get_settings
|
||||
from services.mesh.mesh_bootstrap_manifest import (
|
||||
BootstrapManifest,
|
||||
BootstrapManifestError,
|
||||
BootstrapPeer,
|
||||
build_bootstrap_manifest_payload,
|
||||
load_bootstrap_manifest,
|
||||
parse_bootstrap_manifest_dict,
|
||||
sign_bootstrap_manifest_payload,
|
||||
write_signed_bootstrap_manifest,
|
||||
)
|
||||
from services.mesh.mesh_crypto import normalize_peer_url, resolve_peer_key_for_url
|
||||
from services.mesh.mesh_peer_registry import DEFAULT_PEER_REGISTRY_PATH, PeerRegistry, RegistryPeer
|
||||
from services.mesh.mesh_peer_store import (
|
||||
DEFAULT_PEER_STORE_PATH,
|
||||
PeerStore,
|
||||
make_push_peer_record,
|
||||
make_sync_peer_record,
|
||||
)
|
||||
from services.mesh.mesh_router import parse_configured_relay_peers, peer_transport_kind
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_SWARM_LOCK = threading.Lock()
|
||||
_LAST_MANIFEST_PULL_AT = 0.0
|
||||
_LAST_ANNOUNCE_AT = 0.0
|
||||
|
||||
|
||||
def peer_registry_enabled() -> bool:
|
||||
settings = get_settings()
|
||||
if bool(getattr(settings, "MESH_PEER_REGISTRY_DISABLED", False)):
|
||||
return False
|
||||
if str(getattr(settings, "MESH_BOOTSTRAP_SIGNER_PRIVATE_KEY", "") or "").strip():
|
||||
return True
|
||||
return bool(getattr(settings, "MESH_PEER_REGISTRY_ENABLED", False))
|
||||
|
||||
|
||||
def _manifest_path() -> str:
|
||||
return str(getattr(get_settings(), "MESH_BOOTSTRAP_MANIFEST_PATH", "") or "data/bootstrap_peers.json")
|
||||
|
||||
|
||||
def _signer_public_key_b64() -> str:
|
||||
from services.mesh.mesh_fleet_defaults import effective_bootstrap_signer_public_key_b64
|
||||
|
||||
return effective_bootstrap_signer_public_key_b64()
|
||||
|
||||
|
||||
def _signer_private_key_b64() -> str:
|
||||
return str(getattr(settings, "MESH_BOOTSTRAP_SIGNER_PRIVATE_KEY", "") or "").strip() if (settings := get_settings()) else ""
|
||||
|
||||
|
||||
def _signer_id() -> str:
|
||||
configured = str(getattr(get_settings(), "MESH_BOOTSTRAP_SIGNER_ID", "") or "").strip()
|
||||
return configured or "shadowbroker-seed"
|
||||
|
||||
|
||||
def _private_transport_required() -> bool:
|
||||
return not bool(getattr(get_settings(), "MESH_INFONET_ALLOW_CLEARNET_SYNC", False))
|
||||
|
||||
|
||||
def _configured_seed_peer_urls() -> list[str]:
|
||||
from services.mesh.mesh_fleet_defaults import configured_bootstrap_seed_peers_with_fleet_default
|
||||
|
||||
settings = get_settings()
|
||||
primary = str(getattr(settings, "MESH_BOOTSTRAP_SEED_PEERS", "") or "").strip()
|
||||
legacy = str(getattr(settings, "MESH_DEFAULT_SYNC_PEERS", "") or "").strip()
|
||||
return configured_bootstrap_seed_peers_with_fleet_default(
|
||||
parse_configured_relay_peers(primary or legacy)
|
||||
)
|
||||
|
||||
|
||||
def _seed_manifest_peers() -> list[dict[str, str]]:
|
||||
peers: list[dict[str, str]] = []
|
||||
for peer_url in _configured_seed_peer_urls():
|
||||
transport = str(peer_transport_kind(peer_url) or "")
|
||||
if _private_transport_required() and transport != "onion":
|
||||
continue
|
||||
peers.append(
|
||||
{
|
||||
"peer_url": peer_url,
|
||||
"transport": transport,
|
||||
"role": "seed",
|
||||
"label": "ShadowBroker bootstrap seed",
|
||||
}
|
||||
)
|
||||
return peers
|
||||
|
||||
|
||||
def publish_registry_manifest(*, now: float | None = None, persist: bool = True) -> BootstrapManifest:
|
||||
private_key = _signer_private_key_b64()
|
||||
public_key = _signer_public_key_b64()
|
||||
if not private_key or not public_key:
|
||||
raise BootstrapManifestError("bootstrap signer keys are required to publish swarm manifest")
|
||||
|
||||
timestamp = int(now if now is not None else time.time())
|
||||
registry = PeerRegistry(DEFAULT_PEER_REGISTRY_PATH)
|
||||
try:
|
||||
registry.load()
|
||||
except Exception:
|
||||
registry = PeerRegistry(DEFAULT_PEER_REGISTRY_PATH)
|
||||
stale_s = int(getattr(get_settings(), "MESH_PEER_REGISTRY_STALE_S", 0) or 7 * 86400)
|
||||
if stale_s > 0:
|
||||
registry.prune_stale(max_age_s=stale_s, now=timestamp)
|
||||
|
||||
peers = _seed_manifest_peers() + registry.manifest_peers()
|
||||
ttl_s = int(getattr(get_settings(), "MESH_SWARM_MANIFEST_TTL_S", 0) or 4 * 3600)
|
||||
payload = build_bootstrap_manifest_payload(
|
||||
signer_id=_signer_id(),
|
||||
peers=peers,
|
||||
issued_at=timestamp,
|
||||
valid_until=timestamp + max(300, ttl_s),
|
||||
)
|
||||
signature = sign_bootstrap_manifest_payload(payload, signer_private_key_b64=private_key)
|
||||
manifest = BootstrapManifest(
|
||||
version=int(payload["version"]),
|
||||
issued_at=int(payload["issued_at"]),
|
||||
valid_until=int(payload["valid_until"]),
|
||||
signer_id=str(payload["signer_id"]),
|
||||
peers=tuple(BootstrapPeer(**dict(peer)) for peer in peers),
|
||||
signature=signature,
|
||||
)
|
||||
if persist:
|
||||
registry.save()
|
||||
write_signed_bootstrap_manifest(
|
||||
_manifest_path(),
|
||||
signer_id=manifest.signer_id,
|
||||
signer_private_key_b64=private_key,
|
||||
peers=[peer.to_dict() for peer in manifest.peers],
|
||||
issued_at=manifest.issued_at,
|
||||
valid_until=manifest.valid_until,
|
||||
)
|
||||
return manifest
|
||||
|
||||
|
||||
def load_live_bootstrap_manifest(*, now: float | None = None) -> BootstrapManifest | None:
|
||||
public_key = _signer_public_key_b64()
|
||||
if not public_key:
|
||||
return None
|
||||
if peer_registry_enabled():
|
||||
try:
|
||||
return publish_registry_manifest(now=now, persist=False)
|
||||
except BootstrapManifestError:
|
||||
logger.warning("live registry manifest unavailable", exc_info=True)
|
||||
try:
|
||||
return load_bootstrap_manifest(_manifest_path(), signer_public_key_b64=public_key, now=now)
|
||||
except BootstrapManifestError:
|
||||
return None
|
||||
|
||||
|
||||
def _upsert_swarm_peer_into_store(
|
||||
*,
|
||||
peer_url: str,
|
||||
transport: str,
|
||||
role: str,
|
||||
label: str = "",
|
||||
signer_id: str = "",
|
||||
now: float | None = None,
|
||||
) -> None:
|
||||
timestamp = int(now if now is not None else time.time())
|
||||
if _private_transport_required() and transport != "onion":
|
||||
return
|
||||
store = PeerStore(DEFAULT_PEER_STORE_PATH)
|
||||
try:
|
||||
store.load()
|
||||
except Exception:
|
||||
store = PeerStore(DEFAULT_PEER_STORE_PATH)
|
||||
store.upsert(
|
||||
make_sync_peer_record(
|
||||
peer_url=peer_url,
|
||||
transport=transport,
|
||||
role=role,
|
||||
source="swarm",
|
||||
label=label,
|
||||
signer_id=signer_id,
|
||||
now=timestamp,
|
||||
)
|
||||
)
|
||||
store.upsert(
|
||||
make_push_peer_record(
|
||||
peer_url=peer_url,
|
||||
transport=transport,
|
||||
role=role if role != "seed" else "relay",
|
||||
source="swarm",
|
||||
label=label,
|
||||
now=timestamp,
|
||||
)
|
||||
)
|
||||
store.save()
|
||||
|
||||
|
||||
def record_peer_announcement(body: dict[str, Any], *, now: float | None = None) -> RegistryPeer:
|
||||
if not peer_registry_enabled():
|
||||
raise ValueError("peer registry is not enabled on this node")
|
||||
registry = PeerRegistry(DEFAULT_PEER_REGISTRY_PATH)
|
||||
try:
|
||||
registry.load()
|
||||
except Exception:
|
||||
registry = PeerRegistry(DEFAULT_PEER_REGISTRY_PATH)
|
||||
peer = registry.upsert_announcement(
|
||||
peer_url=str(body.get("peer_url", "") or ""),
|
||||
transport=str(body.get("transport", "") or ""),
|
||||
role=str(body.get("role", "participant") or "participant"),
|
||||
node_id=str(body.get("node_id", "") or ""),
|
||||
label=str(body.get("label", "") or ""),
|
||||
now=now,
|
||||
)
|
||||
registry.save()
|
||||
_upsert_swarm_peer_into_store(
|
||||
peer_url=peer.peer_url,
|
||||
transport=peer.transport,
|
||||
role=peer.role,
|
||||
label=peer.label,
|
||||
signer_id=_signer_id(),
|
||||
now=now,
|
||||
)
|
||||
try:
|
||||
publish_registry_manifest(now=now, persist=True)
|
||||
except Exception:
|
||||
logger.warning("failed to republish swarm manifest after announce", exc_info=True)
|
||||
return peer
|
||||
|
||||
|
||||
def merge_manifest_into_peer_store(manifest: BootstrapManifest, *, now: float | None = None) -> int:
|
||||
timestamp = int(now if now is not None else time.time())
|
||||
merged = 0
|
||||
for peer in manifest.peers:
|
||||
if _private_transport_required() and peer.transport != "onion":
|
||||
continue
|
||||
_upsert_swarm_peer_into_store(
|
||||
peer_url=peer.peer_url,
|
||||
transport=peer.transport,
|
||||
role=peer.role,
|
||||
label=peer.label,
|
||||
signer_id=manifest.signer_id,
|
||||
now=timestamp,
|
||||
)
|
||||
merged += 1
|
||||
return merged
|
||||
|
||||
|
||||
def fetch_remote_bootstrap_manifest(seed_peer_url: str, *, now: float | None = None) -> BootstrapManifest | None:
|
||||
import requests
|
||||
|
||||
public_key = _signer_public_key_b64()
|
||||
if not public_key:
|
||||
return None
|
||||
normalized = normalize_peer_url(seed_peer_url)
|
||||
if not normalized:
|
||||
return None
|
||||
|
||||
from main import _infonet_peer_requests_proxies
|
||||
|
||||
proxies = _infonet_peer_requests_proxies(normalized)
|
||||
timeout = int(getattr(get_settings(), "MESH_SYNC_TIMEOUT_S", 0) or 45)
|
||||
request_kwargs: dict[str, Any] = {"timeout": timeout}
|
||||
if proxies:
|
||||
request_kwargs["proxies"] = proxies
|
||||
try:
|
||||
response = requests.get(f"{normalized}/api/mesh/infonet/bootstrap-manifest", **request_kwargs)
|
||||
except Exception as exc:
|
||||
logger.debug("swarm manifest fetch failed for %s: %s", normalized, exc)
|
||||
return None
|
||||
if response.status_code != 200:
|
||||
return None
|
||||
try:
|
||||
raw = response.json()
|
||||
except Exception:
|
||||
return None
|
||||
if not isinstance(raw, dict) or raw.get("ok") is False:
|
||||
return None
|
||||
manifest_body = dict(raw.get("manifest") or raw)
|
||||
try:
|
||||
return parse_bootstrap_manifest_dict(
|
||||
manifest_body,
|
||||
signer_public_key_b64=public_key,
|
||||
now=now,
|
||||
)
|
||||
except BootstrapManifestError:
|
||||
return None
|
||||
|
||||
|
||||
def refresh_swarm_manifest_from_seeds(*, now: float | None = None, force: bool = False) -> dict[str, Any]:
|
||||
global _LAST_MANIFEST_PULL_AT
|
||||
interval_s = int(getattr(get_settings(), "MESH_SWARM_MANIFEST_PULL_INTERVAL_S", 0) or 300)
|
||||
timestamp = float(now if now is not None else time.time())
|
||||
with _SWARM_LOCK:
|
||||
if not force and _LAST_MANIFEST_PULL_AT and timestamp - _LAST_MANIFEST_PULL_AT < max(30, interval_s):
|
||||
return {"ok": True, "skipped": True, "reason": "manifest_pull_interval"}
|
||||
_LAST_MANIFEST_PULL_AT = timestamp
|
||||
|
||||
if not _signer_public_key_b64():
|
||||
return {"ok": False, "detail": "MESH_BOOTSTRAP_SIGNER_PUBLIC_KEY is not configured"}
|
||||
|
||||
last_error = "manifest fetch failed"
|
||||
for seed_url in _configured_seed_peer_urls():
|
||||
manifest = fetch_remote_bootstrap_manifest(seed_url, now=timestamp)
|
||||
if manifest is None:
|
||||
continue
|
||||
try:
|
||||
merged = merge_manifest_into_peer_store(manifest, now=timestamp)
|
||||
return {
|
||||
"ok": True,
|
||||
"seed_peer_url": seed_url,
|
||||
"peer_count": len(manifest.peers),
|
||||
"merged_peer_count": merged,
|
||||
}
|
||||
except Exception as exc:
|
||||
last_error = str(exc or type(exc).__name__)
|
||||
return {"ok": False, "detail": last_error}
|
||||
|
||||
|
||||
def announce_local_peer_to_seeds(*, now: float | None = None, force: bool = False) -> dict[str, Any]:
|
||||
global _LAST_ANNOUNCE_AT
|
||||
import hashlib as _hashlib_mod
|
||||
import hmac as _hmac_mod
|
||||
import requests
|
||||
|
||||
from main import _infonet_peer_requests_proxies, _local_infonet_peer_url, _participant_node_enabled
|
||||
|
||||
if not _participant_node_enabled():
|
||||
return {"ok": False, "detail": "participant node disabled"}
|
||||
peer_url = _local_infonet_peer_url()
|
||||
if not peer_url:
|
||||
return {"ok": False, "detail": "local peer URL is not ready"}
|
||||
peer_key = resolve_peer_key_for_url(peer_url)
|
||||
if not peer_key:
|
||||
return {"ok": False, "detail": "peer HMAC secret is not configured"}
|
||||
|
||||
timestamp = float(now if now is not None else time.time())
|
||||
with _SWARM_LOCK:
|
||||
if not force and _LAST_ANNOUNCE_AT and timestamp - _LAST_ANNOUNCE_AT < 300:
|
||||
return {"ok": True, "skipped": True, "reason": "announce_interval"}
|
||||
_LAST_ANNOUNCE_AT = timestamp
|
||||
|
||||
transport = str(peer_transport_kind(peer_url) or "onion")
|
||||
body = {
|
||||
"peer_url": peer_url,
|
||||
"transport": transport,
|
||||
"role": "participant",
|
||||
"node_id": "",
|
||||
"label": "",
|
||||
"ts": int(timestamp),
|
||||
}
|
||||
body_bytes = json.dumps(body, sort_keys=True, separators=(",", ":"), ensure_ascii=False).encode("utf-8")
|
||||
hmac_hex = _hmac_mod.new(peer_key, body_bytes, _hashlib_mod.sha256).hexdigest()
|
||||
timeout = int(getattr(get_settings(), "MESH_RELAY_PUSH_TIMEOUT_S", 0) or 45)
|
||||
results: list[dict[str, Any]] = []
|
||||
for seed_url in _configured_seed_peer_urls():
|
||||
normalized = normalize_peer_url(seed_url)
|
||||
if not normalized:
|
||||
continue
|
||||
proxies = _infonet_peer_requests_proxies(normalized)
|
||||
request_kwargs: dict[str, Any] = {
|
||||
"data": body_bytes,
|
||||
"headers": {
|
||||
"Content-Type": "application/json",
|
||||
"X-Peer-Url": peer_url,
|
||||
"X-Peer-HMAC": hmac_hex,
|
||||
},
|
||||
"timeout": timeout,
|
||||
}
|
||||
if proxies:
|
||||
request_kwargs["proxies"] = proxies
|
||||
try:
|
||||
response = requests.post(
|
||||
f"{normalized}/api/mesh/infonet/peer-announce",
|
||||
**request_kwargs,
|
||||
)
|
||||
results.append(
|
||||
{
|
||||
"seed_peer_url": normalized,
|
||||
"status_code": int(response.status_code),
|
||||
"ok": response.status_code == 200,
|
||||
}
|
||||
)
|
||||
except Exception as exc:
|
||||
results.append({"seed_peer_url": normalized, "ok": False, "detail": str(exc)})
|
||||
ok = any(bool(item.get("ok")) for item in results)
|
||||
return {"ok": ok, "peer_url": peer_url, "results": results}
|
||||
|
||||
|
||||
def _announce_succeeded(announce: dict[str, Any]) -> bool:
|
||||
if not bool(announce.get("ok")):
|
||||
return False
|
||||
results = announce.get("results") or []
|
||||
return any(bool(item.get("ok")) and int(item.get("status_code") or 0) == 200 for item in results)
|
||||
|
||||
|
||||
def _manifest_succeeded(manifest: dict[str, Any]) -> bool:
|
||||
if not bool(manifest.get("ok")):
|
||||
return False
|
||||
peer_count = int(manifest.get("merged_peer_count") or manifest.get("peer_count") or 0)
|
||||
return peer_count >= 1
|
||||
|
||||
|
||||
def join_swarm_with_retries(
|
||||
*,
|
||||
attempts: int = 6,
|
||||
delay_s: float = 15.0,
|
||||
force: bool = True,
|
||||
) -> dict[str, Any]:
|
||||
"""Announce to seed and pull manifest, retrying while Tor circuits warm up."""
|
||||
last_announce: dict[str, Any] = {"ok": False, "detail": "not attempted"}
|
||||
last_manifest: dict[str, Any] = {"ok": False, "detail": "not attempted"}
|
||||
tries = max(1, int(attempts))
|
||||
pause_s = max(1.0, float(delay_s))
|
||||
for attempt in range(tries):
|
||||
last_announce = announce_local_peer_to_seeds(force=force)
|
||||
last_manifest = refresh_swarm_manifest_from_seeds(force=force)
|
||||
if _announce_succeeded(last_announce) and _manifest_succeeded(last_manifest):
|
||||
return {
|
||||
"ok": True,
|
||||
"attempts": attempt + 1,
|
||||
"announce": last_announce,
|
||||
"manifest_pull": last_manifest,
|
||||
}
|
||||
if attempt + 1 < tries:
|
||||
time.sleep(pause_s)
|
||||
return {
|
||||
"ok": False,
|
||||
"attempts": tries,
|
||||
"announce": last_announce,
|
||||
"manifest_pull": last_manifest,
|
||||
"detail": "swarm join incomplete after retries",
|
||||
}
|
||||
|
||||
|
||||
def push_infonet_events_to_http_peers(events: list[dict[str, Any]]) -> dict[str, Any]:
|
||||
import hashlib as _hashlib_mod
|
||||
import hmac as _hmac_mod
|
||||
import requests
|
||||
|
||||
from main import (
|
||||
_filter_infonet_peer_urls,
|
||||
_infonet_peer_requests_proxies,
|
||||
_local_infonet_peer_url,
|
||||
_participant_node_enabled,
|
||||
_record_public_push_result,
|
||||
)
|
||||
from services.mesh.mesh_router import authenticated_push_peer_urls
|
||||
|
||||
if not _participant_node_enabled() or not events:
|
||||
return {"ok": False, "detail": "nothing to push"}
|
||||
peers = _filter_infonet_peer_urls(authenticated_push_peer_urls())
|
||||
if not peers:
|
||||
return {"ok": False, "detail": "no push peers configured"}
|
||||
|
||||
sender_url = _local_infonet_peer_url()
|
||||
peer_key = resolve_peer_key_for_url(sender_url)
|
||||
if not peer_key:
|
||||
return {"ok": False, "detail": "peer HMAC secret is not configured"}
|
||||
|
||||
body_bytes = json.dumps(
|
||||
{"events": events},
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
ensure_ascii=False,
|
||||
).encode("utf-8")
|
||||
hmac_hex = _hmac_mod.new(peer_key, body_bytes, _hashlib_mod.sha256).hexdigest()
|
||||
timeout = int(getattr(get_settings(), "MESH_RELAY_PUSH_TIMEOUT_S", 0) or 45)
|
||||
results: list[dict[str, Any]] = []
|
||||
for peer_url in peers:
|
||||
normalized = normalize_peer_url(peer_url)
|
||||
if not normalized:
|
||||
continue
|
||||
proxies = _infonet_peer_requests_proxies(normalized)
|
||||
request_kwargs: dict[str, Any] = {
|
||||
"data": body_bytes,
|
||||
"headers": {
|
||||
"Content-Type": "application/json",
|
||||
"X-Peer-Url": sender_url,
|
||||
"X-Peer-HMAC": hmac_hex,
|
||||
},
|
||||
"timeout": timeout,
|
||||
}
|
||||
if proxies:
|
||||
request_kwargs["proxies"] = proxies
|
||||
try:
|
||||
response = requests.post(f"{normalized}/api/mesh/infonet/peer-push", **request_kwargs)
|
||||
results.append(
|
||||
{
|
||||
"peer_url": normalized,
|
||||
"ok": response.status_code == 200,
|
||||
"status_code": int(response.status_code),
|
||||
}
|
||||
)
|
||||
except Exception as exc:
|
||||
results.append({"peer_url": normalized, "ok": False, "detail": str(exc)})
|
||||
ok = any(bool(item.get("ok")) for item in results)
|
||||
event_id = str((events[-1] or {}).get("event_id", "") or "")
|
||||
_record_public_push_result(
|
||||
event_id,
|
||||
ok=ok,
|
||||
error="" if ok else "immediate peer push failed",
|
||||
results=results,
|
||||
)
|
||||
return {"ok": ok, "results": results}
|
||||
@@ -929,6 +929,85 @@ def list_wormhole_dm_contacts() -> dict[str, dict[str, Any]]:
|
||||
return _read_contacts()
|
||||
|
||||
|
||||
def get_wormhole_dm_contact(peer_id: str) -> dict[str, Any] | None:
|
||||
peer_key = str(peer_id or "").strip()
|
||||
if not peer_key:
|
||||
return None
|
||||
contacts = _read_contacts()
|
||||
if peer_key not in contacts:
|
||||
return None
|
||||
return dict(_normalize_contact(contacts[peer_key]))
|
||||
|
||||
|
||||
def sever_wormhole_dm_contact(peer_id: str, *, block: bool = False) -> dict[str, Any]:
|
||||
"""Close the shared DM lane; a fresh contact request + accept is required to reopen."""
|
||||
peer_key = str(peer_id or "").strip()
|
||||
if not peer_key:
|
||||
return {"ok": False, "detail": "peer_id required"}
|
||||
|
||||
contacts = _read_contacts()
|
||||
current = _normalize_contact(contacts.get(peer_key))
|
||||
now = int(time.time())
|
||||
current["sharedAlias"] = ""
|
||||
current["sharedAliasCounter"] = 0
|
||||
current["sharedAliasPublicKey"] = ""
|
||||
current["sharedAliasPublicKeyAlgo"] = "Ed25519"
|
||||
current["previousSharedAliases"] = []
|
||||
current["pendingSharedAlias"] = ""
|
||||
current["pendingSharedAliasCounter"] = 0
|
||||
current["pendingSharedAliasPublicKey"] = ""
|
||||
current["pendingSharedAliasPublicKeyAlgo"] = "Ed25519"
|
||||
current["pendingSharedAliasGraceMs"] = 0
|
||||
current["sharedAliasGraceUntil"] = 0
|
||||
current["sharedAliasRotatedAt"] = 0
|
||||
current["acceptedPreviousAlias"] = ""
|
||||
current["acceptedPreviousAliasCounter"] = 0
|
||||
current["acceptedPreviousAliasPublicKey"] = ""
|
||||
current["acceptedPreviousAliasPublicKeyAlgo"] = "Ed25519"
|
||||
current["acceptedPreviousGraceUntil"] = 0
|
||||
current["acceptedPreviousHardGraceUntil"] = 0
|
||||
current["acceptedPreviousAwaitingReply"] = False
|
||||
current["aliasBindingSeq"] = 0
|
||||
current["aliasBindingPendingReason"] = ""
|
||||
current["aliasBindingPreparedAt"] = 0
|
||||
current["aliasGateJoinAppliedSeq"] = 0
|
||||
if block:
|
||||
current["blocked"] = True
|
||||
current["updated_at"] = now
|
||||
contacts[peer_key] = _normalize_contact(current)
|
||||
_write_contacts(contacts)
|
||||
|
||||
relay_policy = {}
|
||||
try:
|
||||
from services.mesh.mesh_dm_connect_delivery import revoke_connect_relay_policy
|
||||
|
||||
relay_policy = revoke_connect_relay_policy(peer_key)
|
||||
except Exception:
|
||||
relay_policy = {"ok": False}
|
||||
|
||||
relay_block = {"ok": False}
|
||||
if block:
|
||||
try:
|
||||
from services.mesh.mesh_dm_relay import dm_relay
|
||||
from services.mesh.mesh_wormhole_persona import get_dm_identity
|
||||
|
||||
local_id = str(get_dm_identity().get("node_id", "") or "").strip()
|
||||
if local_id:
|
||||
dm_relay.block(local_id, peer_key)
|
||||
relay_block = {"ok": True, "local_id": local_id}
|
||||
except Exception as exc:
|
||||
relay_block = {"ok": False, "detail": str(exc) or type(exc).__name__}
|
||||
|
||||
return {
|
||||
"ok": True,
|
||||
"peer_id": peer_key,
|
||||
"severed": True,
|
||||
"blocked": bool(block),
|
||||
"relay_policy": relay_policy,
|
||||
"relay_block": relay_block,
|
||||
}
|
||||
|
||||
|
||||
def _promote_invite_lookup_mode(contact: dict[str, Any], *, now: int | None = None) -> bool:
|
||||
current = dict(contact or {})
|
||||
lookup_handle = str(current.get("invitePinnedPrekeyLookupHandle", "") or "").strip()
|
||||
@@ -1070,11 +1149,14 @@ def pin_wormhole_dm_invite(
|
||||
identity_dh_pub_key = str(payload.get("identity_dh_pub_key", "") or "")
|
||||
dh_algo = str(payload.get("dh_algo", "X25519") or "X25519")
|
||||
prekey_lookup_handle = str(payload.get("prekey_lookup_handle", "") or "")
|
||||
lookup_peer_url = str(payload.get("lookup_peer_url", "") or "").strip().rstrip("/")
|
||||
if str(alias or "").strip():
|
||||
current["alias"] = str(alias or "").strip()
|
||||
current["dhPubKey"] = identity_dh_pub_key
|
||||
current["dhAlgo"] = dh_algo
|
||||
current["invitePinnedPrekeyLookupHandle"] = prekey_lookup_handle
|
||||
if lookup_peer_url:
|
||||
current["invitePinnedLookupPeerUrl"] = lookup_peer_url
|
||||
current["invitePinnedRootFingerprint"] = str(payload.get("root_fingerprint", "") or "").strip().lower()
|
||||
current["invitePinnedRootManifestFingerprint"] = str(
|
||||
payload.get("root_manifest_fingerprint", "") or ""
|
||||
@@ -1170,6 +1252,12 @@ def pin_wormhole_dm_invite(
|
||||
current["updated_at"] = now
|
||||
contacts[peer_key] = _normalize_contact(current)
|
||||
_write_contacts(contacts)
|
||||
try:
|
||||
from services.mesh.mesh_dm_connect_delivery import grant_connect_relay_policy
|
||||
|
||||
grant_connect_relay_policy(peer_key, reason="invite_import")
|
||||
except Exception:
|
||||
pass
|
||||
return contacts[peer_key]
|
||||
|
||||
|
||||
|
||||
@@ -549,6 +549,27 @@ def invite_identity_commitment_for_identity_material(
|
||||
return hashlib.sha256(_stable_json(material).encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def _local_dm_lookup_peer_url() -> str:
|
||||
"""Return this node's fleet-reachable URL for invite-scoped prekey lookup."""
|
||||
try:
|
||||
from services.config import get_settings
|
||||
from services.mesh.mesh_crypto import normalize_peer_url
|
||||
|
||||
configured = normalize_peer_url(str(getattr(get_settings(), "MESH_PUBLIC_PEER_URL", "") or ""))
|
||||
if configured:
|
||||
return configured
|
||||
from services.tor_hidden_service import tor_service
|
||||
|
||||
onion = str(getattr(tor_service, "onion_address", "") or "").strip()
|
||||
if onion:
|
||||
if "://" not in onion:
|
||||
onion = f"http://{onion}:8000"
|
||||
return normalize_peer_url(onion)
|
||||
except Exception:
|
||||
pass
|
||||
return ""
|
||||
|
||||
|
||||
def _dm_invite_payload(
|
||||
data: dict[str, Any],
|
||||
*,
|
||||
@@ -930,6 +951,9 @@ def export_wormhole_dm_invite(*, label: str = "", expires_in_s: int = 0) -> dict
|
||||
# fetch our prekey bundle without using our stable agent_id.
|
||||
lookup_handle = secrets.token_hex(24)
|
||||
payload["prekey_lookup_handle"] = lookup_handle
|
||||
lookup_peer_url = _local_dm_lookup_peer_url()
|
||||
if lookup_peer_url:
|
||||
payload["lookup_peer_url"] = lookup_peer_url
|
||||
|
||||
# Persist the handle so it is included in future prekey registrations.
|
||||
existing_handles, _ = _normalize_prekey_lookup_handles(
|
||||
|
||||
@@ -79,6 +79,164 @@ def _warn_legacy_prekey_lookup(agent_id: str) -> None:
|
||||
)
|
||||
|
||||
|
||||
def _fleet_peer_lookup_user_agent() -> str:
|
||||
custom = str(os.environ.get("SHADOWBROKER_MESH_PEER_USER_AGENT") or "").strip()
|
||||
if custom:
|
||||
return custom
|
||||
return "Mozilla/5.0 (compatible; ShadowbrokerMesh/1.0)"
|
||||
|
||||
|
||||
_INVITE_LOOKUP_MAX_ELAPSED_S = 120
|
||||
_INVITE_LOOKUP_MAX_BOOTSTRAP_PEERS = 3
|
||||
_INVITE_LOOKUP_MAX_PUSH_PEERS = 16
|
||||
_INVITE_LOOKUP_PARALLEL_WORKERS = 8
|
||||
|
||||
|
||||
def _invite_lookup_request_timeout(peer_url: str) -> tuple[int, int]:
|
||||
from services.mesh.mesh_router import peer_transport_kind
|
||||
|
||||
if peer_transport_kind(peer_url) == "onion":
|
||||
return (10, 35)
|
||||
return (5, 15)
|
||||
|
||||
|
||||
def _bootstrap_seed_peer_urls() -> set[str]:
|
||||
try:
|
||||
from services.config import get_settings
|
||||
from services.mesh.mesh_router import parse_configured_relay_peers
|
||||
|
||||
seeds: set[str] = set()
|
||||
raw = str(getattr(get_settings(), "MESH_BOOTSTRAP_SEED_PEERS", "") or "")
|
||||
for peer in parse_configured_relay_peers(raw):
|
||||
normalized = str(peer or "").strip().rstrip("/")
|
||||
if normalized:
|
||||
seeds.add(normalized)
|
||||
return seeds
|
||||
except Exception:
|
||||
return set()
|
||||
|
||||
|
||||
def _discovered_push_peer_urls(*, limit: int = _INVITE_LOOKUP_MAX_PUSH_PEERS) -> list[str]:
|
||||
try:
|
||||
from services.mesh.mesh_router import authenticated_push_peer_urls
|
||||
|
||||
seeds = _bootstrap_seed_peer_urls()
|
||||
peers: list[str] = []
|
||||
for peer in authenticated_push_peer_urls():
|
||||
normalized = str(peer or "").strip().rstrip("/")
|
||||
if not normalized or normalized in seeds:
|
||||
continue
|
||||
peers.append(normalized)
|
||||
if len(peers) >= max(1, int(limit or 1)):
|
||||
break
|
||||
return peers
|
||||
except Exception:
|
||||
return []
|
||||
|
||||
|
||||
def _prioritized_invite_lookup_peer_urls(*, preferred: list[str] | None = None) -> list[str]:
|
||||
preferred_urls = [
|
||||
str(peer or "").strip().rstrip("/")
|
||||
for peer in list(preferred or [])
|
||||
if str(peer or "").strip()
|
||||
]
|
||||
configured = _configured_public_lookup_peer_urls()
|
||||
seeds = _bootstrap_seed_peer_urls()
|
||||
active: list[str] = []
|
||||
bootstrap: list[str] = []
|
||||
push_discovery: list[str] = []
|
||||
seen = set(preferred_urls)
|
||||
for peer in configured:
|
||||
if peer in seen:
|
||||
continue
|
||||
seen.add(peer)
|
||||
if peer in seeds:
|
||||
bootstrap.append(peer)
|
||||
else:
|
||||
active.append(peer)
|
||||
for peer in _discovered_push_peer_urls():
|
||||
if peer in seen:
|
||||
continue
|
||||
seen.add(peer)
|
||||
push_discovery.append(peer)
|
||||
ordered = list(preferred_urls)
|
||||
ordered.extend(active)
|
||||
ordered.extend(push_discovery)
|
||||
ordered.extend(bootstrap[:_INVITE_LOOKUP_MAX_BOOTSTRAP_PEERS])
|
||||
return ordered
|
||||
|
||||
|
||||
def _preferred_invite_lookup_peer_urls(lookup_token: str) -> list[str]:
|
||||
token = str(lookup_token or "").strip()
|
||||
if not token:
|
||||
return []
|
||||
try:
|
||||
from services.mesh.mesh_wormhole_contacts import list_wormhole_dm_contacts
|
||||
except Exception:
|
||||
return []
|
||||
peers: list[str] = []
|
||||
for contact in list_wormhole_dm_contacts() or []:
|
||||
if not isinstance(contact, dict):
|
||||
continue
|
||||
if str(contact.get("invitePinnedPrekeyLookupHandle", "") or "").strip() != token:
|
||||
continue
|
||||
peer_url = str(contact.get("invitePinnedLookupPeerUrl", "") or "").strip().rstrip("/")
|
||||
if peer_url and peer_url not in peers:
|
||||
peers.append(peer_url)
|
||||
return peers
|
||||
|
||||
|
||||
def _peer_http_request(
|
||||
method: str,
|
||||
peer_url: str,
|
||||
*,
|
||||
body_bytes: bytes | None = None,
|
||||
headers: dict[str, str] | None = None,
|
||||
timeout: int | tuple[int, int] = 45,
|
||||
):
|
||||
"""HTTP to a fleet peer, using Tor SOCKS when the URL is an onion address."""
|
||||
import requests
|
||||
|
||||
from services.mesh.mesh_crypto import normalize_peer_url
|
||||
from urllib.parse import urlparse
|
||||
|
||||
raw_peer_url = str(peer_url or "").strip()
|
||||
parsed = urlparse(raw_peer_url)
|
||||
if parsed.path and parsed.path not in {"", "/"}:
|
||||
# Full request URLs include invite lookup query params; do not
|
||||
# normalize them away when deriving the peer base URL.
|
||||
normalized = raw_peer_url
|
||||
else:
|
||||
normalized = normalize_peer_url(raw_peer_url)
|
||||
if not normalized:
|
||||
raise OSError("invalid peer url")
|
||||
if isinstance(timeout, tuple):
|
||||
connect_timeout, read_timeout = timeout
|
||||
resolved_timeout: int | tuple[int, int] = (
|
||||
max(1, int(connect_timeout or 5)),
|
||||
max(1, int(read_timeout or 15)),
|
||||
)
|
||||
else:
|
||||
resolved_timeout = max(1, int(timeout or 45))
|
||||
request_kwargs: dict[str, Any] = {
|
||||
"headers": dict(headers or {}),
|
||||
"timeout": resolved_timeout,
|
||||
}
|
||||
try:
|
||||
from main import _infonet_peer_requests_proxies
|
||||
|
||||
proxy_peer_url = normalize_peer_url(f"{parsed.scheme}://{parsed.netloc}")
|
||||
proxies = _infonet_peer_requests_proxies(proxy_peer_url)
|
||||
if proxies:
|
||||
request_kwargs["proxies"] = proxies
|
||||
except Exception:
|
||||
pass
|
||||
if method.upper() == "GET":
|
||||
return requests.get(normalized, **request_kwargs)
|
||||
request_kwargs["data"] = body_bytes or b""
|
||||
return requests.post(normalized, **request_kwargs)
|
||||
|
||||
|
||||
def _fetch_dm_prekey_bundle_from_peer_lookup(lookup_token: str) -> dict[str, Any]:
|
||||
"""Fetch an invite-scoped prekey bundle from configured authenticated peers.
|
||||
|
||||
@@ -95,12 +253,12 @@ def _fetch_dm_prekey_bundle_from_peer_lookup(lookup_token: str) -> dict[str, Any
|
||||
normalize_peer_url,
|
||||
resolve_peer_key_for_url,
|
||||
)
|
||||
from services.mesh.mesh_router import configured_relay_peer_urls
|
||||
from services.mesh.mesh_router import authenticated_push_peer_urls
|
||||
|
||||
settings = get_settings()
|
||||
# Issue #256: secret check moved per-peer below. We still bail out
|
||||
# cleanly when there are no peers configured at all.
|
||||
peers = configured_relay_peer_urls()
|
||||
peers = authenticated_push_peer_urls()
|
||||
if not peers:
|
||||
return {"ok": False, "detail": "peer prekey lookup unavailable"}
|
||||
timeout = max(1, _safe_int(getattr(settings, "MESH_RELAY_PUSH_TIMEOUT_S", 10) or 10, 10))
|
||||
@@ -132,17 +290,17 @@ def _fetch_dm_prekey_bundle_from_peer_lookup(lookup_token: str) -> dict[str, Any
|
||||
"X-Peer-Url": sender_peer_url,
|
||||
"X-Peer-HMAC": hmac.new(peer_key, body, hashlib.sha256).hexdigest(),
|
||||
}
|
||||
request = urllib.request.Request(
|
||||
f"{normalized_peer_url}/api/mesh/dm/prekey-peer-lookup",
|
||||
data=body,
|
||||
headers=headers,
|
||||
method="POST",
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=timeout) as response:
|
||||
raw = response.read(256 * 1024)
|
||||
response = _peer_http_request(
|
||||
"POST",
|
||||
f"{normalized_peer_url}/api/mesh/dm/prekey-peer-lookup",
|
||||
body_bytes=body,
|
||||
headers=headers,
|
||||
timeout=timeout,
|
||||
)
|
||||
raw = response.content[: 256 * 1024]
|
||||
payload = json.loads(raw.decode("utf-8"))
|
||||
except (urllib.error.URLError, TimeoutError, json.JSONDecodeError, OSError) as exc:
|
||||
except (json.JSONDecodeError, OSError, Exception) as exc:
|
||||
last_detail = str(exc) or type(exc).__name__
|
||||
continue
|
||||
if isinstance(payload, dict) and payload.get("ok"):
|
||||
@@ -161,12 +319,18 @@ def _configured_public_lookup_peer_urls() -> list[str]:
|
||||
|
||||
settings = get_settings()
|
||||
candidates: list[str] = []
|
||||
# Operator-configured peers first, then recently active fleet nodes.
|
||||
# Invite handles are minted on a specific node; cold bootstrap seeds
|
||||
# rarely have them cached and should not be tried before contacts.
|
||||
for raw in (
|
||||
getattr(settings, "MESH_BOOTSTRAP_SEED_PEERS", ""),
|
||||
getattr(settings, "MESH_DEFAULT_SYNC_PEERS", ""),
|
||||
):
|
||||
candidates.extend(parse_configured_relay_peers(str(raw or "")))
|
||||
candidates.extend(active_sync_peer_urls())
|
||||
for raw in (
|
||||
getattr(settings, "MESH_BOOTSTRAP_SEED_PEERS", ""),
|
||||
):
|
||||
candidates.extend(parse_configured_relay_peers(str(raw or "")))
|
||||
except Exception:
|
||||
return []
|
||||
|
||||
@@ -204,7 +368,50 @@ def _normalize_remote_lookup_bundle(payload: dict[str, Any]) -> dict[str, Any]:
|
||||
return data
|
||||
|
||||
|
||||
def _fetch_dm_prekey_bundle_from_public_lookup(lookup_token: str) -> dict[str, Any]:
|
||||
def _try_public_prekey_lookup_peer(
|
||||
peer_url: str,
|
||||
encoded: str,
|
||||
*,
|
||||
timeout: int | tuple[int, int] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
normalized_peer_url = str(peer_url or "").strip().rstrip("/")
|
||||
if not normalized_peer_url:
|
||||
return {"ok": False, "detail": "invalid peer url"}
|
||||
resolved_timeout = timeout or _invite_lookup_request_timeout(normalized_peer_url)
|
||||
try:
|
||||
response = _peer_http_request(
|
||||
"GET",
|
||||
f"{normalized_peer_url}/api/mesh/dm/prekey-bundle?{encoded}",
|
||||
headers={
|
||||
"Accept": "application/json",
|
||||
"User-Agent": _fleet_peer_lookup_user_agent(),
|
||||
},
|
||||
timeout=resolved_timeout,
|
||||
)
|
||||
raw = response.content[: 256 * 1024]
|
||||
payload = json.loads(raw.decode("utf-8"))
|
||||
except (json.JSONDecodeError, OSError, Exception) as exc:
|
||||
logger.debug("public prekey lookup failed for %s: %s", normalized_peer_url, type(exc).__name__)
|
||||
return {"ok": False, "detail": "peer prekey lookup unavailable"}
|
||||
if not isinstance(payload, dict):
|
||||
return {"ok": False, "detail": "invalid peer response"}
|
||||
if payload.get("pending") or str(payload.get("status", "") or "") == "preparing_private_lane":
|
||||
return {"ok": False, "detail": "peer prekey lookup still preparing"}
|
||||
if not payload.get("ok"):
|
||||
return {
|
||||
"ok": False,
|
||||
"detail": str(payload.get("detail", "") or "Prekey bundle not found"),
|
||||
}
|
||||
if not isinstance(payload.get("bundle"), dict):
|
||||
return {"ok": False, "detail": "Prekey bundle not found"}
|
||||
return _normalize_remote_lookup_bundle(payload)
|
||||
|
||||
|
||||
def _fetch_dm_prekey_bundle_from_public_lookup(
|
||||
lookup_token: str,
|
||||
*,
|
||||
extra_preferred_peer_urls: list[str] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Fetch an invite-scoped prekey bundle from bootstrap/sync peers.
|
||||
|
||||
The token is high-entropy and invite-scoped. This path does not expose a
|
||||
@@ -212,61 +419,69 @@ def _fetch_dm_prekey_bundle_from_public_lookup(lookup_token: str) -> dict[str, A
|
||||
derive it from the signed identity public key and validate the bundle before
|
||||
accepting it.
|
||||
"""
|
||||
from concurrent.futures import FIRST_COMPLETED, ThreadPoolExecutor, wait
|
||||
|
||||
token = str(lookup_token or "").strip()
|
||||
if not token:
|
||||
return {"ok": False, "detail": "lookup token required"}
|
||||
peers = _configured_public_lookup_peer_urls()
|
||||
preferred = list(_preferred_invite_lookup_peer_urls(token))
|
||||
for peer in list(extra_preferred_peer_urls or []):
|
||||
normalized = str(peer or "").strip().rstrip("/")
|
||||
if normalized and normalized not in preferred:
|
||||
preferred.insert(0, normalized)
|
||||
peers = _prioritized_invite_lookup_peer_urls(preferred=preferred)
|
||||
if not peers:
|
||||
return {"ok": False, "detail": "peer prekey lookup unavailable"}
|
||||
try:
|
||||
from services.config import get_settings
|
||||
|
||||
timeout = max(1, _safe_int(getattr(get_settings(), "MESH_SYNC_TIMEOUT_S", 5) or 5, 5))
|
||||
except Exception:
|
||||
timeout = 5
|
||||
|
||||
encoded = urllib.parse.urlencode({"lookup_token": token})
|
||||
last_detail = ""
|
||||
for peer_url in peers:
|
||||
normalized_peer_url = str(peer_url or "").strip().rstrip("/")
|
||||
if not normalized_peer_url:
|
||||
continue
|
||||
# Generic UA: any peer-facing crypto request should not carry a
|
||||
# fork-specific identifier — that turns prekey lookups into a
|
||||
# software-fingerprinting beacon.
|
||||
from services.network_utils import DEFAULT_USER_AGENT
|
||||
request = urllib.request.Request(
|
||||
f"{normalized_peer_url}/api/mesh/dm/prekey-bundle?{encoded}",
|
||||
headers={
|
||||
"Accept": "application/json",
|
||||
"User-Agent": DEFAULT_USER_AGENT,
|
||||
},
|
||||
method="GET",
|
||||
hinted_only = bool(list(extra_preferred_peer_urls or []))
|
||||
hint_timeout = (5, 20)
|
||||
for peer_url in preferred:
|
||||
hinted = _try_public_prekey_lookup_peer(
|
||||
peer_url,
|
||||
encoded,
|
||||
timeout=hint_timeout if hinted_only else None,
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=timeout) as response:
|
||||
raw = response.read(256 * 1024)
|
||||
payload = json.loads(raw.decode("utf-8"))
|
||||
except (urllib.error.URLError, TimeoutError, json.JSONDecodeError, OSError) as exc:
|
||||
logger.debug("public prekey lookup failed for %s: %s", normalized_peer_url, type(exc).__name__)
|
||||
last_detail = "peer prekey lookup unavailable"
|
||||
continue
|
||||
if not isinstance(payload, dict):
|
||||
last_detail = "invalid peer response"
|
||||
continue
|
||||
if payload.get("pending") or str(payload.get("status", "") or "") == "preparing_private_lane":
|
||||
last_detail = "peer prekey lookup still preparing"
|
||||
continue
|
||||
if not payload.get("ok"):
|
||||
last_detail = str(payload.get("detail", "") or last_detail or "Prekey bundle not found")
|
||||
continue
|
||||
if not isinstance(payload.get("bundle"), dict):
|
||||
last_detail = "Prekey bundle not found"
|
||||
continue
|
||||
normalized = _normalize_remote_lookup_bundle(payload)
|
||||
if normalized.get("ok"):
|
||||
return normalized
|
||||
last_detail = str(normalized.get("detail", "") or last_detail)
|
||||
if hinted.get("ok"):
|
||||
return hinted
|
||||
if isinstance(hinted, dict):
|
||||
last_detail = str(hinted.get("detail", "") or last_detail)
|
||||
remaining_peers = [peer for peer in peers if peer not in set(preferred)]
|
||||
if not remaining_peers:
|
||||
return {"ok": False, "detail": last_detail or "Prekey bundle not found"}
|
||||
if hinted_only:
|
||||
return {"ok": False, "detail": last_detail or "Prekey bundle not found"}
|
||||
deadline = time.time() + _INVITE_LOOKUP_MAX_ELAPSED_S
|
||||
workers = min(_INVITE_LOOKUP_PARALLEL_WORKERS, max(1, len(remaining_peers)))
|
||||
with ThreadPoolExecutor(max_workers=workers) as executor:
|
||||
futures = {
|
||||
executor.submit(_try_public_prekey_lookup_peer, peer_url, encoded): peer_url
|
||||
for peer_url in remaining_peers
|
||||
}
|
||||
while futures and time.time() < deadline:
|
||||
done, _ = wait(
|
||||
futures,
|
||||
timeout=max(0.1, deadline - time.time()),
|
||||
return_when=FIRST_COMPLETED,
|
||||
)
|
||||
if not done:
|
||||
break
|
||||
for future in done:
|
||||
futures.pop(future, None)
|
||||
try:
|
||||
result = future.result()
|
||||
except Exception as exc:
|
||||
last_detail = str(exc) or type(exc).__name__
|
||||
continue
|
||||
if isinstance(result, dict) and result.get("ok"):
|
||||
for pending in futures:
|
||||
pending.cancel()
|
||||
return result
|
||||
if isinstance(result, dict):
|
||||
last_detail = str(result.get("detail", "") or last_detail)
|
||||
for pending in futures:
|
||||
pending.cancel()
|
||||
return {"ok": False, "detail": last_detail or "Prekey bundle not found"}
|
||||
|
||||
|
||||
@@ -1019,6 +1234,7 @@ def fetch_dm_prekey_bundle(
|
||||
lookup_token: str = "",
|
||||
*,
|
||||
allow_peer_lookup: bool = True,
|
||||
lookup_peer_urls: list[str] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
from services.mesh.mesh_dm_relay import dm_relay
|
||||
|
||||
@@ -1043,12 +1259,18 @@ def fetch_dm_prekey_bundle(
|
||||
resolved_id = found_id
|
||||
lookup_mode = "invite_lookup_handle"
|
||||
elif allow_peer_lookup:
|
||||
peer_found = _fetch_dm_prekey_bundle_from_peer_lookup(resolved_lookup)
|
||||
if peer_found.get("ok"):
|
||||
return peer_found
|
||||
public_found = _fetch_dm_prekey_bundle_from_public_lookup(resolved_lookup)
|
||||
preferred_peer_urls = list(lookup_peer_urls or [])
|
||||
public_found = _fetch_dm_prekey_bundle_from_public_lookup(
|
||||
resolved_lookup,
|
||||
extra_preferred_peer_urls=preferred_peer_urls,
|
||||
)
|
||||
if public_found.get("ok"):
|
||||
return public_found
|
||||
peer_found: dict[str, Any] = {"ok": False, "detail": ""}
|
||||
if not preferred_peer_urls:
|
||||
peer_found = _fetch_dm_prekey_bundle_from_peer_lookup(resolved_lookup)
|
||||
if peer_found.get("ok"):
|
||||
return peer_found
|
||||
if str(public_found.get("detail", "") or "").strip():
|
||||
return {"ok": False, "detail": str(public_found.get("detail", "") or "Prekey bundle not found")}
|
||||
return {"ok": False, "detail": str(peer_found.get("detail", "") or "Prekey bundle not found")}
|
||||
@@ -1134,12 +1356,24 @@ def _classify_root_attestation_failure(peer_id: str) -> tuple[str, bool]:
|
||||
return "", False
|
||||
|
||||
|
||||
def bootstrap_encrypt_for_peer(peer_id: str, plaintext: str) -> dict[str, Any]:
|
||||
fetched_bundle = fetch_dm_prekey_bundle(str(peer_id or "").strip())
|
||||
def bootstrap_encrypt_for_peer(
|
||||
peer_id: str,
|
||||
plaintext: str,
|
||||
*,
|
||||
lookup_token: str = "",
|
||||
fetched_bundle: dict[str, Any] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
token = str(lookup_token or "").strip()
|
||||
peer = str(peer_id or "").strip()
|
||||
if fetched_bundle is None:
|
||||
fetched_bundle = fetch_dm_prekey_bundle(
|
||||
agent_id=peer if not token else "",
|
||||
lookup_token=token,
|
||||
)
|
||||
if not fetched_bundle.get("ok"):
|
||||
detail = str(fetched_bundle.get("detail", "") or "")
|
||||
if "root attestation" in detail.lower():
|
||||
trust_level, trust_changed = _classify_root_attestation_failure(str(peer_id or "").strip())
|
||||
trust_level, trust_changed = _classify_root_attestation_failure(peer or token)
|
||||
if trust_level:
|
||||
return {
|
||||
"ok": False,
|
||||
@@ -1152,32 +1386,68 @@ def bootstrap_encrypt_for_peer(peer_id: str, plaintext: str) -> dict[str, Any]:
|
||||
|
||||
from services.mesh.mesh_dm_relay import dm_relay
|
||||
|
||||
resolved_peer_id = str(fetched_bundle.get("agent_id", peer_id) or peer_id).strip()
|
||||
resolved_peer_id = str(fetched_bundle.get("agent_id", peer) or peer).strip()
|
||||
stored = dm_relay.get_prekey_bundle(resolved_peer_id)
|
||||
if not stored:
|
||||
return {"ok": False, "detail": "Peer prekey bundle not found"}
|
||||
remote_bundle = dict(fetched_bundle.get("bundle") or {})
|
||||
if not remote_bundle and fetched_bundle.get("identity_dh_pub_key"):
|
||||
remote_bundle = fetched_bundle
|
||||
if remote_bundle:
|
||||
stored = {
|
||||
"bundle": remote_bundle,
|
||||
"signature": str(fetched_bundle.get("signature", "") or ""),
|
||||
"public_key": str(fetched_bundle.get("public_key", "") or ""),
|
||||
"public_key_algo": str(fetched_bundle.get("public_key_algo", "") or ""),
|
||||
"sequence": _safe_int(fetched_bundle.get("sequence", 0) or 0),
|
||||
}
|
||||
else:
|
||||
return {"ok": False, "detail": "Peer prekey bundle not found"}
|
||||
validated_record = {**dict(stored), "agent_id": resolved_peer_id}
|
||||
ok, reason = _validate_bundle_record(validated_record)
|
||||
if not ok:
|
||||
return {"ok": False, "detail": reason}
|
||||
trust_state = observe_remote_prekey_bundle(resolved_peer_id, validated_record)
|
||||
trust_level = str(trust_state.get("trust_level", "") or "")
|
||||
from services.mesh.mesh_wormhole_contacts import verified_first_contact_requirement
|
||||
consent_handshake = False
|
||||
try:
|
||||
from services.mesh.mesh_wormhole_dead_drop import parse_contact_consent
|
||||
|
||||
verified_first_contact = verified_first_contact_requirement(
|
||||
resolved_peer_id,
|
||||
trust_level=trust_level,
|
||||
)
|
||||
if not verified_first_contact.get("ok"):
|
||||
return {
|
||||
"ok": False,
|
||||
"peer_id": resolved_peer_id,
|
||||
"detail": str(verified_first_contact.get("detail", "") or "verified first contact required"),
|
||||
"trust_changed": trust_level in ("mismatch", "continuity_broken"),
|
||||
"trust_level": str(verified_first_contact.get("trust_level", "") or trust_level or "unpinned"),
|
||||
consent = parse_contact_consent(str(plaintext or "")) or {}
|
||||
consent_handshake = str(consent.get("kind", "") or "") in {
|
||||
"contact_offer",
|
||||
"contact_accept",
|
||||
"contact_deny",
|
||||
}
|
||||
except Exception:
|
||||
consent_handshake = False
|
||||
if not consent_handshake:
|
||||
from services.mesh.mesh_wormhole_contacts import verified_first_contact_requirement
|
||||
|
||||
verified_first_contact = verified_first_contact_requirement(
|
||||
resolved_peer_id,
|
||||
trust_level=trust_level,
|
||||
)
|
||||
if not verified_first_contact.get("ok"):
|
||||
return {
|
||||
"ok": False,
|
||||
"peer_id": resolved_peer_id,
|
||||
"detail": str(
|
||||
verified_first_contact.get("detail", "") or "verified first contact required"
|
||||
),
|
||||
"trust_changed": trust_level in ("mismatch", "continuity_broken"),
|
||||
"trust_level": str(
|
||||
verified_first_contact.get("trust_level", "") or trust_level or "unpinned"
|
||||
),
|
||||
}
|
||||
peer_bundle_stored = dm_relay.consume_one_time_prekey(resolved_peer_id)
|
||||
if not peer_bundle_stored:
|
||||
remote_bundle = dict(stored.get("bundle") or {})
|
||||
otks = list(remote_bundle.get("one_time_prekeys") or [])
|
||||
peer_bundle_stored = {
|
||||
"bundle": remote_bundle,
|
||||
"claimed_one_time_prekey": dict(otks[0] or {}) if otks else {},
|
||||
}
|
||||
if not peer_bundle_stored.get("bundle"):
|
||||
return {"ok": False, "detail": "Peer prekey bundle not found"}
|
||||
peer_bundle = dict(peer_bundle_stored.get("bundle") or {})
|
||||
peer_static = str(peer_bundle.get("identity_dh_pub_key", "") or "")
|
||||
|
||||
@@ -34,9 +34,9 @@ _session.mount("http://", HTTPAdapter(max_retries=_retry, pool_maxsize=10))
|
||||
# upstream's only recourse was to block "Shadowbroker" as a whole — which
|
||||
# would take out every other install too.
|
||||
#
|
||||
# Fix: give each install a stable pseudonymous handle and include it in
|
||||
# the User-Agent. Now an upstream can rate-limit or block the offending
|
||||
# operator without affecting anyone else.
|
||||
# Fix: give each install a stable pseudonymous handle used as the entire
|
||||
# User-Agent product token (no shared "Shadowbroker" label). Upstreams see
|
||||
# ``operator-7f3a92`` (or ``OPERATOR_HANDLE``), not one monolithic app name.
|
||||
#
|
||||
# The handle:
|
||||
#
|
||||
@@ -51,7 +51,6 @@ _session.mount("http://", HTTPAdapter(max_retries=_retry, pool_maxsize=10))
|
||||
# - Is NEVER mixed into mesh / Wormhole / Infonet identity. This layer is
|
||||
# strictly for public third-party API attribution.
|
||||
|
||||
_SHADOWBROKER_VERSION = "0.9"
|
||||
_OPERATOR_HANDLE_FILE = (
|
||||
Path(__file__).parent.parent / "data" / "operator_handle.json"
|
||||
)
|
||||
@@ -146,7 +145,12 @@ def get_operator_handle() -> str:
|
||||
# 3. On-disk handle from a previous run.
|
||||
persisted = _load_persisted_operator_handle()
|
||||
if persisted:
|
||||
_OPERATOR_HANDLE_CACHE = _normalize_handle(persisted)
|
||||
normalized = _normalize_handle(persisted)
|
||||
# Migrate legacy auto-generated handles (pre-Round-7a ``shadow-`` prefix).
|
||||
if normalized.startswith("shadow-"):
|
||||
normalized = f"operator-{normalized[len('shadow-'):]}"
|
||||
_persist_operator_handle(normalized)
|
||||
_OPERATOR_HANDLE_CACHE = normalized
|
||||
return _OPERATOR_HANDLE_CACHE
|
||||
|
||||
# 4. Generate, persist, return.
|
||||
@@ -170,41 +174,21 @@ def _normalize_handle(raw: str) -> str:
|
||||
return safe[:48] if safe else "anonymous"
|
||||
|
||||
|
||||
_CONTACT_URL = "https://github.com/BigBodyCobain/Shadowbroker/issues"
|
||||
|
||||
|
||||
def outbound_user_agent(purpose: str = "") -> str:
|
||||
"""Build a User-Agent for an outbound third-party HTTP request.
|
||||
|
||||
Returns something like::
|
||||
Returns the per-install handle only, e.g. ``operator-7f3a92`` or
|
||||
``operator-7f3a92 (purpose: wikipedia)``. No shared project name — so
|
||||
upstream abuse teams cannot block every install with one ``Shadowbroker``
|
||||
rule.
|
||||
|
||||
Shadowbroker/0.9 (operator: shadow-7f3a92; purpose: wikipedia;
|
||||
+https://github.com/BigBodyCobain/Shadowbroker/issues)
|
||||
|
||||
The ``purpose`` is optional but recommended — it tells the upstream
|
||||
what feature of ours is making the call (``wikipedia``, ``openmhz``,
|
||||
``nominatim``, etc.), which makes their logs and our complaints
|
||||
actionable.
|
||||
|
||||
Every outbound call in the backend that previously sent a custom
|
||||
User-Agent should call this helper instead. Centralizing here means:
|
||||
- one place to change the contact URL,
|
||||
- one place to bump the version on release,
|
||||
- one place a Wikimedia / OpenMHz operator can reach to ask for
|
||||
the project to back off, with a per-install handle so they can
|
||||
target the specific install instead of the project as a whole.
|
||||
Set ``SHADOWBROKER_USER_AGENT`` to override the entire string if needed.
|
||||
"""
|
||||
handle = get_operator_handle()
|
||||
if purpose:
|
||||
purpose_clean = _normalize_handle(purpose)
|
||||
return (
|
||||
f"Shadowbroker/{_SHADOWBROKER_VERSION} "
|
||||
f"(operator: {handle}; purpose: {purpose_clean}; +{_CONTACT_URL})"
|
||||
)
|
||||
return (
|
||||
f"Shadowbroker/{_SHADOWBROKER_VERSION} "
|
||||
f"(operator: {handle}; +{_CONTACT_URL})"
|
||||
)
|
||||
return f"{handle} (purpose: {purpose_clean})"
|
||||
return handle
|
||||
|
||||
|
||||
def _reset_operator_handle_cache_for_tests() -> None:
|
||||
@@ -215,19 +199,13 @@ def _reset_operator_handle_cache_for_tests() -> None:
|
||||
_OPERATOR_HANDLE_CACHE = ""
|
||||
|
||||
|
||||
# Default outbound User-Agent. Retained for backwards compatibility with
|
||||
# call sites that haven't been migrated to ``outbound_user_agent()`` yet.
|
||||
# Operators who want full per-install attribution should set the
|
||||
# ``OPERATOR_HANDLE`` setting and migrate call sites incrementally.
|
||||
#
|
||||
# Operators who run a public-facing relay can also override the whole UA
|
||||
# string via the ``SHADOWBROKER_USER_AGENT`` env var. That override
|
||||
# completely bypasses the per-operator helper; only use it if you know
|
||||
# what you're doing.
|
||||
DEFAULT_USER_AGENT = os.environ.get(
|
||||
"SHADOWBROKER_USER_AGENT",
|
||||
f"Shadowbroker/{_SHADOWBROKER_VERSION}",
|
||||
)
|
||||
def default_user_agent() -> str:
|
||||
"""Default User-Agent for ``fetch_with_curl`` and legacy call sites."""
|
||||
custom = (os.environ.get("SHADOWBROKER_USER_AGENT") or "").strip()
|
||||
if custom:
|
||||
return custom
|
||||
return outbound_user_agent()
|
||||
|
||||
|
||||
# Find bash for curl fallback — Git bash's curl has the TLS features
|
||||
# needed to pass CDN fingerprint checks (brotli, zstd, libpsl)
|
||||
@@ -283,7 +261,7 @@ def fetch_with_curl(url, method="GET", json_data=None, timeout=15, headers=None,
|
||||
both Python requests and the barebones Windows system curl.
|
||||
"""
|
||||
default_headers = {
|
||||
"User-Agent": DEFAULT_USER_AGENT,
|
||||
"User-Agent": default_user_agent(),
|
||||
}
|
||||
if headers:
|
||||
default_headers.update(headers)
|
||||
|
||||
@@ -12,6 +12,8 @@ logger = logging.getLogger(__name__)
|
||||
CONFIG_PATH = Path(__file__).parent.parent / "config" / "news_feeds.json"
|
||||
MAX_FEEDS = 50
|
||||
_FEED_URL_REPLACEMENTS = {
|
||||
"http://feeds.bbci.co.uk/news/world/rss.xml": "https://feeds.bbci.co.uk/news/world/rss.xml",
|
||||
"http://www.news.cn/english/rss/worldrss.xml": "https://www.news.cn/english/rss/worldrss.xml",
|
||||
"https://www.channelnewsasia.com/rssfeed/8395986": "https://www.channelnewsasia.com/api/v1/rss-outbound-feed?_format=xml",
|
||||
}
|
||||
_DEAD_FEED_URLS = {
|
||||
@@ -27,7 +29,7 @@ _DEAD_FEED_URLS = {
|
||||
|
||||
DEFAULT_FEEDS = [
|
||||
{"name": "NPR", "url": "https://feeds.npr.org/1004/rss.xml", "weight": 4},
|
||||
{"name": "BBC", "url": "http://feeds.bbci.co.uk/news/world/rss.xml", "weight": 3},
|
||||
{"name": "BBC", "url": "https://feeds.bbci.co.uk/news/world/rss.xml", "weight": 3},
|
||||
{"name": "AlJazeera", "url": "https://www.aljazeera.com/xml/rss/all.xml", "weight": 2},
|
||||
{"name": "NYT", "url": "https://rss.nytimes.com/services/xml/rss/nyt/World.xml", "weight": 1},
|
||||
{"name": "GDACS", "url": "https://www.gdacs.org/xml/rss.xml", "weight": 5},
|
||||
@@ -35,7 +37,7 @@ DEFAULT_FEEDS = [
|
||||
{"name": "Bellingcat", "url": "https://www.bellingcat.com/feed/", "weight": 4},
|
||||
{"name": "Guardian", "url": "https://www.theguardian.com/world/rss", "weight": 3},
|
||||
{"name": "TASS", "url": "https://tass.com/rss/v2.xml", "weight": 2},
|
||||
{"name": "Xinhua", "url": "http://www.news.cn/english/rss/worldrss.xml", "weight": 2},
|
||||
{"name": "Xinhua", "url": "https://www.news.cn/english/rss/worldrss.xml", "weight": 2},
|
||||
{"name": "CNA", "url": "https://www.channelnewsasia.com/api/v1/rss-outbound-feed?_format=xml", "weight": 3},
|
||||
{"name": "Mercopress", "url": "https://en.mercopress.com/rss/", "weight": 3},
|
||||
{"name": "SCMP", "url": "https://www.scmp.com/rss/91/feed", "weight": 4},
|
||||
|
||||
@@ -83,6 +83,18 @@ READ_COMMANDS = frozenset({
|
||||
"sar_pin_click",
|
||||
# Analysis zones (OpenClaw map overlays)
|
||||
"list_analysis_zones",
|
||||
# Recon / OSINT toolkit (server-side proxies, SSRF guarded)
|
||||
"osint_lookup",
|
||||
"osint_tools",
|
||||
"entity_expand",
|
||||
# Agent routing helpers
|
||||
"route_query",
|
||||
"run_playbook",
|
||||
# Private Infonet reads (operator-delegated)
|
||||
"infonet_status",
|
||||
"list_gates",
|
||||
"read_gate_messages",
|
||||
"poll_dms",
|
||||
})
|
||||
|
||||
WRITE_COMMANDS = frozenset({
|
||||
@@ -112,6 +124,14 @@ WRITE_COMMANDS = frozenset({
|
||||
"place_analysis_zone",
|
||||
"delete_analysis_zone",
|
||||
"clear_analysis_zones",
|
||||
# Active recon (subnet device discovery)
|
||||
"osint_sweep",
|
||||
# Private Infonet writes (operator wormhole identity)
|
||||
"ensure_infonet_ready",
|
||||
"join_infonet_swarm",
|
||||
"post_gate_message",
|
||||
"cast_vote",
|
||||
"send_dm",
|
||||
})
|
||||
|
||||
|
||||
@@ -637,6 +657,19 @@ def _compact_query_result(result: Any) -> Any:
|
||||
# Command dispatcher
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _expensive_gate(cmd: str, args: dict[str, Any]) -> dict[str, Any] | None:
|
||||
from services.openclaw_routing import EXPENSIVE_GATE_MESSAGE, requires_expensive_confirm
|
||||
|
||||
if requires_expensive_confirm(cmd, args):
|
||||
return {
|
||||
"ok": False,
|
||||
"detail": EXPENSIVE_GATE_MESSAGE,
|
||||
"code": "expensive_command_blocked",
|
||||
"hint": "route_query",
|
||||
}
|
||||
return None
|
||||
|
||||
|
||||
def _dispatch_command(cmd: str, args: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Route a command to the appropriate AI Intel function.
|
||||
|
||||
@@ -644,6 +677,43 @@ def _dispatch_command(cmd: str, args: dict[str, Any]) -> dict[str, Any]:
|
||||
Commands run in an isolated thread (via _execute_command) so they
|
||||
do not need or touch the caller's event loop.
|
||||
"""
|
||||
blocked = _expensive_gate(cmd, args)
|
||||
if blocked is not None:
|
||||
return blocked
|
||||
|
||||
if cmd == "route_query":
|
||||
from services.openclaw_routing import route_query
|
||||
|
||||
result = route_query(
|
||||
text=str(args.get("text", "") or args.get("query", "") or ""),
|
||||
lat=args.get("lat"),
|
||||
lng=args.get("lng"),
|
||||
radius_km=float(args.get("radius_km", 50) or 50),
|
||||
compact=bool(args.get("compact", True)),
|
||||
)
|
||||
return {"ok": True, "data": result}
|
||||
|
||||
if cmd == "run_playbook":
|
||||
from services.openclaw_routing import plan_playbook
|
||||
|
||||
plan = plan_playbook(str(args.get("name", "") or args.get("playbook", "")), args)
|
||||
if not plan.get("ok"):
|
||||
return plan
|
||||
batch_results: list[dict[str, Any]] = []
|
||||
for item in plan.get("batch", []):
|
||||
inner_cmd = str(item.get("cmd", "")).strip().lower()
|
||||
inner_args = item.get("args") or {}
|
||||
inner_result = _dispatch_command(inner_cmd, inner_args)
|
||||
batch_results.append({"cmd": inner_cmd, **inner_result})
|
||||
return {
|
||||
"ok": True,
|
||||
"data": {
|
||||
"playbook": plan.get("playbook"),
|
||||
"description": plan.get("description", ""),
|
||||
"results": batch_results,
|
||||
},
|
||||
}
|
||||
|
||||
if cmd == "get_telemetry":
|
||||
from services.telemetry import get_cached_telemetry_refs
|
||||
data = get_cached_telemetry_refs()
|
||||
@@ -725,6 +795,7 @@ def _dispatch_command(cmd: str, args: dict[str, Any]) -> dict[str, Any]:
|
||||
owner=str(args.get("owner", "") or args.get("operator", "") or ""),
|
||||
layers=args.get("layers") if isinstance(args.get("layers"), (list, tuple)) else None,
|
||||
limit=args.get("limit", 10),
|
||||
fallback_search=bool(args.get("fallback_search") or args.get("confirm_fuzzy")),
|
||||
)
|
||||
if _wants_compact(args):
|
||||
compact = dict(result)
|
||||
@@ -780,6 +851,7 @@ def _dispatch_command(cmd: str, args: dict[str, Any]) -> dict[str, Any]:
|
||||
query=str(args.get("query", "") or ""),
|
||||
limit=args.get("limit", 10),
|
||||
include_gdelt=bool(args.get("include_gdelt", True)),
|
||||
include_telegram=bool(args.get("include_telegram", True)),
|
||||
)
|
||||
if _wants_compact(args):
|
||||
return {"ok": True, "data": _compact_query_result(result), "format": "compressed_v1"}
|
||||
@@ -846,6 +918,26 @@ def _dispatch_command(cmd: str, args: dict[str, Any]) -> dict[str, Any]:
|
||||
return {"ok": True, "data": _compact_query_result(result), "format": "compressed_v1"}
|
||||
return {"ok": True, "data": result}
|
||||
|
||||
if cmd == "osint_lookup":
|
||||
from services.osint.openclaw_recon import run_osint_lookup
|
||||
tool = str(args.get("tool", "") or args.get("lookup", "") or args.get("type", "") or "")
|
||||
result = run_osint_lookup(tool, args)
|
||||
return {"ok": True, "data": result, "tool": tool.strip().lower()}
|
||||
|
||||
if cmd == "osint_tools":
|
||||
from services.osint.openclaw_recon import osint_tool_help
|
||||
return {"ok": True, "data": osint_tool_help()}
|
||||
|
||||
if cmd == "osint_sweep":
|
||||
from services.osint.openclaw_recon import run_osint_sweep
|
||||
result = run_osint_sweep(args)
|
||||
return {"ok": True, "data": result}
|
||||
|
||||
if cmd == "entity_expand":
|
||||
from services.osint.openclaw_recon import run_entity_expand
|
||||
result = run_entity_expand(args)
|
||||
return {"ok": True, "data": result}
|
||||
|
||||
if cmd == "get_report":
|
||||
from services.telemetry import get_cached_telemetry_refs, get_cached_slow_telemetry_refs
|
||||
fast = get_cached_telemetry_refs()
|
||||
@@ -1065,6 +1157,7 @@ def _dispatch_command(cmd: str, args: dict[str, Any]) -> dict[str, Any]:
|
||||
owner=str(args.get("owner", "") or args.get("operator", "") or ""),
|
||||
layers=args.get("layers") if isinstance(args.get("layers"), (list, tuple)) else None,
|
||||
limit=5,
|
||||
fallback_search=True,
|
||||
)
|
||||
best = lookup.get("best_match") if isinstance(lookup.get("best_match"), dict) else {}
|
||||
group = str(best.get("group", "") or entity_type).lower()
|
||||
@@ -1516,6 +1609,85 @@ def _dispatch_command(cmd: str, args: dict[str, Any]) -> dict[str, Any]:
|
||||
count = clear_zones(source="openclaw")
|
||||
return {"ok": True, "data": {"removed_count": count}}
|
||||
|
||||
# -- Infonet / gate / DM (operator-delegated, full tier for writes) ------
|
||||
|
||||
if cmd == "infonet_status":
|
||||
from services.openclaw_infonet import get_infonet_status
|
||||
|
||||
return get_infonet_status()
|
||||
|
||||
if cmd == "ensure_infonet_ready":
|
||||
from services.openclaw_infonet import ensure_infonet_ready
|
||||
|
||||
return ensure_infonet_ready(join_swarm=bool(args.get("join_swarm", True)))
|
||||
|
||||
if cmd == "join_infonet_swarm":
|
||||
from services.openclaw_infonet import join_infonet_swarm
|
||||
|
||||
return join_infonet_swarm()
|
||||
|
||||
if cmd == "list_gates":
|
||||
from services.openclaw_infonet import list_gates
|
||||
|
||||
return list_gates()
|
||||
|
||||
if cmd == "read_gate_messages":
|
||||
from services.openclaw_infonet import read_gate_messages
|
||||
|
||||
gate_id = str(args.get("gate_id", "") or args.get("gate", "")).strip()
|
||||
return read_gate_messages(
|
||||
gate_id,
|
||||
limit=int(args.get("limit", 20) or 20),
|
||||
decrypt=bool(args.get("decrypt", False)),
|
||||
)
|
||||
|
||||
if cmd == "post_gate_message":
|
||||
from services.openclaw_infonet import post_gate_message
|
||||
|
||||
gate_id = str(args.get("gate_id", "") or args.get("gate", "")).strip()
|
||||
plaintext = str(args.get("plaintext", "") or args.get("message", "")).strip()
|
||||
return post_gate_message(
|
||||
gate_id,
|
||||
plaintext,
|
||||
reply_to=str(args.get("reply_to", "") or ""),
|
||||
)
|
||||
|
||||
if cmd == "cast_vote":
|
||||
from services.openclaw_infonet import cast_vote
|
||||
|
||||
target_id = str(args.get("target_id", "") or args.get("target", "")).strip()
|
||||
vote_raw = args.get("vote", args.get("direction"))
|
||||
try:
|
||||
vote_val = int(vote_raw)
|
||||
except (TypeError, ValueError):
|
||||
return {"ok": False, "detail": "vote must be 1 or -1"}
|
||||
return cast_vote(
|
||||
target_id,
|
||||
vote_val,
|
||||
gate=str(args.get("gate", "") or args.get("gate_id", "")).strip(),
|
||||
)
|
||||
|
||||
if cmd == "send_dm":
|
||||
from services.openclaw_infonet import send_dm
|
||||
|
||||
peer_id = str(
|
||||
args.get("peer_id", "")
|
||||
or args.get("recipient_id", "")
|
||||
or args.get("recipient", "")
|
||||
).strip()
|
||||
plaintext = str(args.get("plaintext", "") or args.get("message", "")).strip()
|
||||
return send_dm(
|
||||
peer_id,
|
||||
plaintext,
|
||||
delivery_class=str(args.get("delivery_class", "shared") or "shared"),
|
||||
recipient_token=str(args.get("recipient_token", "") or ""),
|
||||
)
|
||||
|
||||
if cmd == "poll_dms":
|
||||
from services.openclaw_infonet import poll_dms
|
||||
|
||||
return poll_dms(limit=int(args.get("limit", 20) or 20))
|
||||
|
||||
return {"ok": False, "detail": f"unhandled command: {cmd}"}
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,796 @@
|
||||
"""OpenClaw agent delegation for private Infonet / gate / DM actions.
|
||||
|
||||
Agents authenticate with OpenClaw HMAC on the command channel. Write
|
||||
commands require ``OPENCLAW_ACCESS_TIER=full``. Actions use the operator's
|
||||
local wormhole persona and node runtime — the agent posts on behalf of the
|
||||
user who configured the skill, not as a separate fleet identity.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import secrets
|
||||
import time
|
||||
from typing import Any
|
||||
|
||||
from starlette.requests import Request
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _run_async(coro):
|
||||
try:
|
||||
asyncio.get_running_loop()
|
||||
except RuntimeError:
|
||||
return asyncio.run(coro)
|
||||
return asyncio.run(coro)
|
||||
|
||||
|
||||
def _local_agent_request(path: str, *, method: str = "POST") -> Request:
|
||||
scope = {
|
||||
"type": "http",
|
||||
"method": method.upper(),
|
||||
"path": path,
|
||||
"headers": [],
|
||||
"client": ("127.0.0.1", 52421),
|
||||
}
|
||||
request = Request(scope)
|
||||
request.state._private_lane_current_tier = "private_strong"
|
||||
request.state._transport_tier = "private_strong"
|
||||
return request
|
||||
|
||||
|
||||
def ensure_infonet_ready(*, join_swarm: bool = True) -> dict[str, Any]:
|
||||
"""Warm Tor, enable the participant node, and optionally join the swarm."""
|
||||
from routers.ai_intel import _write_env_value
|
||||
from services.config import get_settings
|
||||
from services.mesh.mesh_swarm_runtime import join_swarm_with_retries
|
||||
from services.node_settings import read_node_settings, write_node_settings
|
||||
from services.tor_hidden_service import tor_service
|
||||
from services.wormhole_supervisor import _check_arti_ready
|
||||
|
||||
steps: dict[str, Any] = {}
|
||||
|
||||
tor_result = tor_service.start(target_port=8000)
|
||||
steps["tor"] = tor_result
|
||||
if tor_result.get("ok"):
|
||||
try:
|
||||
_write_env_value("MESH_ARTI_ENABLED", "true")
|
||||
get_settings.cache_clear()
|
||||
except Exception as exc:
|
||||
logger.debug("failed to persist MESH_ARTI_ENABLED: %s", exc)
|
||||
|
||||
if not _check_arti_ready():
|
||||
return {
|
||||
"ok": False,
|
||||
"detail": "Tor/Arti transport is not ready yet",
|
||||
"steps": steps,
|
||||
}
|
||||
|
||||
if not bool(read_node_settings().get("enabled")):
|
||||
write_node_settings(enabled=True)
|
||||
steps["node_enabled"] = True
|
||||
try:
|
||||
import main as main_mod
|
||||
|
||||
main_mod._refresh_node_peer_store()
|
||||
main_mod._start_infonet_node_runtime("openclaw_agent")
|
||||
except Exception as exc:
|
||||
logger.warning("node runtime start after agent enable failed: %s", exc)
|
||||
else:
|
||||
steps["node_enabled"] = True
|
||||
|
||||
if join_swarm:
|
||||
joined = join_swarm_with_retries()
|
||||
steps["announce"] = joined.get("announce") or {}
|
||||
steps["manifest_pull"] = joined.get("manifest_pull") or {}
|
||||
steps["swarm_attempts"] = joined.get("attempts")
|
||||
ok = bool(joined.get("ok"))
|
||||
else:
|
||||
ok = True
|
||||
|
||||
return {
|
||||
"ok": ok,
|
||||
"detail": "Infonet participant runtime ready" if ok else "swarm join incomplete",
|
||||
"steps": steps,
|
||||
"onion_address": str(tor_result.get("onion_address") or ""),
|
||||
}
|
||||
|
||||
|
||||
def join_infonet_swarm() -> dict[str, Any]:
|
||||
from services.mesh.mesh_swarm_runtime import join_swarm_with_retries
|
||||
|
||||
joined = join_swarm_with_retries()
|
||||
return {
|
||||
"ok": bool(joined.get("ok")),
|
||||
"announce": joined.get("announce") or {},
|
||||
"manifest_pull": joined.get("manifest_pull") or {},
|
||||
"attempts": joined.get("attempts"),
|
||||
"detail": joined.get("detail"),
|
||||
}
|
||||
|
||||
|
||||
def get_infonet_status() -> dict[str, Any]:
|
||||
from services.mesh.mesh_hashchain import infonet
|
||||
from services.wormhole_supervisor import get_wormhole_state
|
||||
|
||||
info = infonet.get_info()
|
||||
valid, reason = infonet.validate_chain(verify_signatures=False)
|
||||
try:
|
||||
wormhole = get_wormhole_state()
|
||||
except Exception:
|
||||
wormhole = {"configured": False, "ready": False, "arti_ready": False, "rns_ready": False}
|
||||
try:
|
||||
import main as main_mod
|
||||
|
||||
runtime = main_mod._node_runtime_snapshot()
|
||||
private_tier = main_mod._current_private_lane_tier(wormhole)
|
||||
except Exception:
|
||||
runtime = {}
|
||||
private_tier = "public_degraded"
|
||||
|
||||
return {
|
||||
"ok": True,
|
||||
"chain": info,
|
||||
"valid": valid,
|
||||
"validation": reason,
|
||||
"private_lane_tier": private_tier,
|
||||
"wormhole": wormhole,
|
||||
"runtime": runtime,
|
||||
}
|
||||
|
||||
|
||||
def list_gates() -> dict[str, Any]:
|
||||
from services.mesh.mesh_reputation import gate_manager
|
||||
|
||||
return {"ok": True, "gates": gate_manager.list_gates()}
|
||||
|
||||
|
||||
def read_gate_messages(
|
||||
gate_id: str,
|
||||
*,
|
||||
limit: int = 20,
|
||||
decrypt: bool = False,
|
||||
) -> dict[str, Any]:
|
||||
from services.mesh.mesh_hashchain import gate_store
|
||||
|
||||
gate_key = str(gate_id or "").strip().lower()
|
||||
if not gate_key:
|
||||
return {"ok": False, "detail": "gate_id required"}
|
||||
|
||||
messages, cursor = gate_store.get_messages_with_cursor(gate_key, limit=max(1, min(int(limit), 100)))
|
||||
out = []
|
||||
if decrypt:
|
||||
from services.mesh.mesh_gate_repair import decrypt_gate_message_with_repair
|
||||
|
||||
for msg in messages:
|
||||
item = dict(msg)
|
||||
try:
|
||||
decrypted = decrypt_gate_message_with_repair(
|
||||
gate_id=gate_key,
|
||||
epoch=int(item.get("epoch") or 0),
|
||||
ciphertext=str(item.get("ciphertext") or ""),
|
||||
nonce=str(item.get("nonce") or item.get("iv") or ""),
|
||||
sender_ref=str(item.get("sender_ref") or ""),
|
||||
gate_envelope=str(item.get("gate_envelope") or ""),
|
||||
envelope_hash=str(item.get("envelope_hash") or ""),
|
||||
event_id=str(item.get("event_id") or ""),
|
||||
)
|
||||
if decrypted.get("ok"):
|
||||
item["plaintext"] = decrypted.get("plaintext", "")
|
||||
except Exception as exc:
|
||||
item["decrypt_error"] = str(exc)
|
||||
out.append(item)
|
||||
else:
|
||||
out = [dict(m) for m in messages]
|
||||
|
||||
return {
|
||||
"ok": True,
|
||||
"gate": gate_key,
|
||||
"count": len(out),
|
||||
"cursor": cursor,
|
||||
"messages": out,
|
||||
}
|
||||
|
||||
|
||||
def post_gate_message(
|
||||
gate_id: str,
|
||||
plaintext: str,
|
||||
*,
|
||||
reply_to: str = "",
|
||||
) -> dict[str, Any]:
|
||||
"""Compose, sign, and post an MLS gate message using the operator persona."""
|
||||
from services.mesh.mesh_gate_repair import (
|
||||
compose_gate_message_with_repair,
|
||||
sign_gate_message_with_repair,
|
||||
)
|
||||
from services.mesh.mesh_wormhole_persona import bootstrap_wormhole_persona_state, create_gate_persona
|
||||
|
||||
gate_key = str(gate_id or "").strip().lower()
|
||||
if not gate_key:
|
||||
return {"ok": False, "detail": "gate_id required"}
|
||||
if not str(plaintext or "").strip():
|
||||
return {"ok": False, "detail": "plaintext required"}
|
||||
|
||||
bootstrap_wormhole_persona_state(force=False)
|
||||
try:
|
||||
create_gate_persona(gate_key, label="openclaw-agent")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
composed = compose_gate_message_with_repair(
|
||||
gate_id=gate_key,
|
||||
plaintext=str(plaintext),
|
||||
reply_to=str(reply_to or ""),
|
||||
)
|
||||
if not composed.get("ok"):
|
||||
return composed
|
||||
|
||||
signed = sign_gate_message_with_repair(
|
||||
gate_id=gate_key,
|
||||
epoch=int(composed.get("epoch") or 0),
|
||||
ciphertext=str(composed.get("ciphertext") or ""),
|
||||
nonce=str(composed.get("nonce") or ""),
|
||||
payload_format=str(composed.get("format") or "mls1"),
|
||||
reply_to=str(reply_to or ""),
|
||||
envelope_hash=str(composed.get("envelope_hash") or ""),
|
||||
transport_lock="private_strong",
|
||||
)
|
||||
if not signed.get("ok"):
|
||||
return signed
|
||||
|
||||
body = {
|
||||
"sender_id": str(signed.get("sender_id") or composed.get("sender_id") or ""),
|
||||
"public_key": str(signed.get("public_key") or composed.get("public_key") or ""),
|
||||
"public_key_algo": str(signed.get("public_key_algo") or composed.get("public_key_algo") or ""),
|
||||
"signature": str(signed.get("signature") or ""),
|
||||
"sequence": int(signed.get("sequence") or composed.get("sequence") or 0),
|
||||
"protocol_version": str(signed.get("protocol_version") or composed.get("protocol_version") or ""),
|
||||
"epoch": int(signed.get("epoch") or composed.get("epoch") or 0),
|
||||
"ciphertext": str(signed.get("ciphertext") or composed.get("ciphertext") or ""),
|
||||
"nonce": str(signed.get("nonce") or composed.get("nonce") or ""),
|
||||
"sender_ref": str(signed.get("sender_ref") or composed.get("sender_ref") or ""),
|
||||
"format": str(signed.get("format") or composed.get("format") or "mls1"),
|
||||
"gate_envelope": str(signed.get("gate_envelope") or composed.get("gate_envelope") or ""),
|
||||
"envelope_hash": str(signed.get("envelope_hash") or composed.get("envelope_hash") or ""),
|
||||
"transport_lock": "private_strong",
|
||||
"reply_to": str(signed.get("reply_to") or reply_to or ""),
|
||||
}
|
||||
|
||||
import main as main_mod
|
||||
|
||||
path = f"/api/mesh/gate/{gate_key}/message"
|
||||
request = _local_agent_request(path)
|
||||
return main_mod._submit_gate_message_envelope(request, gate_key, body)
|
||||
|
||||
|
||||
def cast_vote(
|
||||
target_id: str,
|
||||
vote: int,
|
||||
*,
|
||||
gate: str = "",
|
||||
) -> dict[str, Any]:
|
||||
"""Cast a signed reputation vote using the operator gate/transport persona."""
|
||||
from services.mesh.mesh_hashchain import infonet
|
||||
from services.mesh.mesh_protocol import PROTOCOL_VERSION, normalize_payload
|
||||
from services.mesh.mesh_reputation import gate_manager, reputation_ledger
|
||||
from services.mesh.mesh_wormhole_persona import (
|
||||
bootstrap_wormhole_persona_state,
|
||||
sign_gate_wormhole_event,
|
||||
sign_public_wormhole_event,
|
||||
)
|
||||
|
||||
voter_gate = str(gate or "").strip().lower()
|
||||
target = str(target_id or "").strip()
|
||||
vote_val = int(vote)
|
||||
if not target:
|
||||
return {"ok": False, "detail": "target_id required"}
|
||||
if vote_val not in (1, -1):
|
||||
return {"ok": False, "detail": "vote must be 1 or -1"}
|
||||
|
||||
bootstrap_wormhole_persona_state(force=False)
|
||||
vote_payload = {"target_id": target, "vote": vote_val, "gate": voter_gate}
|
||||
normalized = normalize_payload("vote", vote_payload)
|
||||
ok_payload, reason = True, "ok"
|
||||
from services.mesh.mesh_schema import validate_event_payload
|
||||
|
||||
ok_payload, reason = validate_event_payload("vote", normalized)
|
||||
if not ok_payload:
|
||||
return {"ok": False, "detail": reason}
|
||||
|
||||
if voter_gate:
|
||||
signed = sign_gate_wormhole_event(
|
||||
gate_id=voter_gate,
|
||||
event_type="vote",
|
||||
payload=normalized,
|
||||
)
|
||||
else:
|
||||
signed = sign_public_wormhole_event(event_type="vote", payload=normalized)
|
||||
|
||||
if not signed.get("ok", True):
|
||||
return signed
|
||||
|
||||
voter_id = str(signed.get("node_id") or "")
|
||||
public_key = str(signed.get("public_key") or "")
|
||||
public_key_algo = str(signed.get("public_key_algo") or "")
|
||||
signature = str(signed.get("signature") or "")
|
||||
sequence = int(signed.get("sequence") or 0)
|
||||
|
||||
if voter_gate:
|
||||
can_enter, enter_reason = gate_manager.can_enter(voter_id, voter_gate)
|
||||
if not can_enter:
|
||||
return {"ok": False, "detail": f"Gate vote denied: {enter_reason}"}
|
||||
|
||||
reputation_ledger.register_node(voter_id, public_key, public_key_algo)
|
||||
stable_voter_id = voter_id
|
||||
try:
|
||||
import main as main_mod
|
||||
|
||||
root_nid = main_mod._cached_root_node_id()
|
||||
if root_nid:
|
||||
stable_voter_id = root_nid
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
ok, cast_reason, weight = reputation_ledger.cast_vote(
|
||||
stable_voter_id,
|
||||
target,
|
||||
vote_val,
|
||||
voter_gate,
|
||||
)
|
||||
if ok:
|
||||
try:
|
||||
infonet.append(
|
||||
event_type="vote",
|
||||
node_id=voter_id,
|
||||
payload=normalized,
|
||||
signature=signature,
|
||||
sequence=sequence,
|
||||
public_key=public_key,
|
||||
public_key_algo=public_key_algo,
|
||||
protocol_version=str(signed.get("protocol_version") or PROTOCOL_VERSION),
|
||||
)
|
||||
except Exception as exc:
|
||||
logger.warning("vote recorded in ledger but infonet append failed: %s", exc)
|
||||
|
||||
return {"ok": ok, "detail": cast_reason, "weight": round(float(weight or 0), 2)}
|
||||
|
||||
|
||||
def _http_post_json(
|
||||
url: str,
|
||||
body: dict[str, Any],
|
||||
*,
|
||||
extra_headers: dict[str, str] | None = None,
|
||||
timeout: int = 120,
|
||||
) -> dict[str, Any]:
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
payload_bytes = json.dumps(body, separators=(",", ":"), sort_keys=True).encode("utf-8")
|
||||
headers = {"Content-Type": "application/json"}
|
||||
if extra_headers:
|
||||
headers.update(extra_headers)
|
||||
req = urllib.request.Request(url, data=payload_bytes, headers=headers, method="POST")
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=timeout) as resp:
|
||||
raw = resp.read().decode("utf-8")
|
||||
except urllib.error.HTTPError as exc:
|
||||
detail = exc.read().decode("utf-8", errors="replace")
|
||||
try:
|
||||
parsed = json.loads(detail)
|
||||
if isinstance(parsed, dict):
|
||||
return parsed
|
||||
except Exception:
|
||||
pass
|
||||
return {"ok": False, "detail": detail or f"http {exc.code}"}
|
||||
if not raw:
|
||||
return {}
|
||||
parsed = json.loads(raw)
|
||||
return parsed if isinstance(parsed, dict) else {"ok": False, "detail": "invalid json response"}
|
||||
|
||||
|
||||
def _issue_sender_token_for_http_send(
|
||||
api_base: str,
|
||||
*,
|
||||
recipient: str,
|
||||
delivery: str,
|
||||
recipient_token: str,
|
||||
) -> dict[str, Any]:
|
||||
extra_headers: dict[str, str] = {}
|
||||
admin_key = str(os.environ.get("ADMIN_KEY") or "").strip()
|
||||
if admin_key:
|
||||
extra_headers["X-Admin-Key"] = admin_key
|
||||
return _http_post_json(
|
||||
f"{api_base}/api/wormhole/dm/sender-token",
|
||||
{
|
||||
"recipient_id": recipient,
|
||||
"delivery_class": delivery,
|
||||
"recipient_token": recipient_token,
|
||||
},
|
||||
extra_headers=extra_headers or None,
|
||||
)
|
||||
|
||||
|
||||
def _submit_signed_dm_send(
|
||||
*,
|
||||
recipient: str,
|
||||
delivery_class: str,
|
||||
recipient_token: str,
|
||||
ciphertext: str,
|
||||
payload_format: str,
|
||||
session_welcome: str = "",
|
||||
connect_intent: str = "",
|
||||
lookup_peer_url: str = "",
|
||||
peer_dh_pub: str = "",
|
||||
) -> dict[str, Any]:
|
||||
import main as main_mod
|
||||
from services.mesh.mesh_protocol import (
|
||||
PROTOCOL_VERSION,
|
||||
SIGNED_CONTEXT_FIELD,
|
||||
build_signed_context,
|
||||
)
|
||||
from services.mesh.mesh_schema import validate_event_payload
|
||||
from services.mesh.mesh_wormhole_persona import get_dm_identity, sign_dm_wormhole_event
|
||||
from services.mesh.mesh_wormhole_sender_token import issue_wormhole_dm_sender_token
|
||||
|
||||
delivery = str(delivery_class or "shared").strip().lower()
|
||||
identity = get_dm_identity()
|
||||
sender_id = str(identity.get("node_id") or "")
|
||||
msg_id = secrets.token_hex(16)
|
||||
timestamp = int(time.time())
|
||||
sequence = int(identity.get("sequence", 0) or 0) + 1
|
||||
|
||||
dm_payload: dict[str, Any] = {
|
||||
"recipient_id": recipient,
|
||||
"delivery_class": delivery,
|
||||
"recipient_token": str(recipient_token or ""),
|
||||
"ciphertext": str(ciphertext or ""),
|
||||
"msg_id": msg_id,
|
||||
"timestamp": timestamp,
|
||||
"format": str(payload_format or "mls1"),
|
||||
"transport_lock": "private_strong",
|
||||
}
|
||||
if session_welcome:
|
||||
dm_payload["session_welcome"] = str(session_welcome)
|
||||
|
||||
try:
|
||||
from services.config import get_settings
|
||||
from services.mesh.mesh_wormhole_seal import build_sender_seal
|
||||
|
||||
if (
|
||||
delivery == "shared"
|
||||
and bool(get_settings().MESH_DM_REQUIRE_SENDER_SEAL_SHARED)
|
||||
and not str(dm_payload.get("sender_seal", "") or "").strip()
|
||||
):
|
||||
seal = build_sender_seal(
|
||||
recipient_id=recipient,
|
||||
recipient_dh_pub=str(peer_dh_pub or ""),
|
||||
msg_id=msg_id,
|
||||
timestamp=timestamp,
|
||||
)
|
||||
if seal.get("ok"):
|
||||
dm_payload["sender_seal"] = str(seal.get("sender_seal") or "")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
ok_payload, reason = validate_event_payload("dm_message", dm_payload)
|
||||
if not ok_payload:
|
||||
return {"ok": False, "detail": reason}
|
||||
|
||||
dm_payload[SIGNED_CONTEXT_FIELD] = build_signed_context(
|
||||
event_type="dm_message",
|
||||
kind="dm_send",
|
||||
endpoint="/api/mesh/dm/send",
|
||||
lane_floor="private_strong",
|
||||
sequence_domain="dm_send",
|
||||
node_id=sender_id,
|
||||
sequence=sequence,
|
||||
payload=dm_payload,
|
||||
recipient_id=recipient,
|
||||
)
|
||||
signed = sign_dm_wormhole_event(
|
||||
event_type="dm_message",
|
||||
payload=dm_payload,
|
||||
sequence=sequence,
|
||||
)
|
||||
if not signed.get("ok", True):
|
||||
return signed
|
||||
|
||||
body = {
|
||||
"sender_id": sender_id,
|
||||
"sender_token": "",
|
||||
"recipient_id": recipient,
|
||||
"delivery_class": delivery,
|
||||
"recipient_token": str(recipient_token or ""),
|
||||
"ciphertext": str(ciphertext or ""),
|
||||
"format": str(payload_format or "mls1"),
|
||||
"transport_lock": "private_strong",
|
||||
"session_welcome": str(session_welcome or ""),
|
||||
"msg_id": msg_id,
|
||||
"timestamp": timestamp,
|
||||
"sender_seal": str(dm_payload.get("sender_seal") or ""),
|
||||
"public_key": str(signed.get("public_key") or ""),
|
||||
"public_key_algo": str(signed.get("public_key_algo") or ""),
|
||||
"signature": str(signed.get("signature") or ""),
|
||||
"sequence": int(signed.get("sequence") or 0),
|
||||
"protocol_version": str(signed.get("protocol_version") or PROTOCOL_VERSION),
|
||||
"signed_context": dict(dm_payload.get(SIGNED_CONTEXT_FIELD) or {}),
|
||||
}
|
||||
normalized_intent = str(connect_intent or "").strip().lower()
|
||||
normalized_lookup_peer = str(lookup_peer_url or "").strip().rstrip("/")
|
||||
if normalized_intent:
|
||||
body["connect_intent"] = normalized_intent
|
||||
if normalized_lookup_peer:
|
||||
body["lookup_peer_url"] = normalized_lookup_peer
|
||||
|
||||
api_base = str(os.environ.get("SB_API_BASE", "http://127.0.0.1:8000") or "http://127.0.0.1:8000").rstrip("/")
|
||||
result: dict[str, Any] = {"ok": False, "detail": "dm send failed"}
|
||||
try:
|
||||
import urllib.error
|
||||
|
||||
if delivery in ("request", "shared"):
|
||||
issued = _issue_sender_token_for_http_send(
|
||||
api_base,
|
||||
recipient=recipient,
|
||||
delivery=delivery,
|
||||
recipient_token=str(recipient_token or ""),
|
||||
)
|
||||
if not issued.get("ok"):
|
||||
return issued
|
||||
body["sender_token"] = str(issued.get("sender_token") or "")
|
||||
|
||||
result = _http_post_json(f"{api_base}/api/mesh/dm/send", body)
|
||||
except (urllib.error.URLError, TimeoutError):
|
||||
if delivery in ("request", "shared"):
|
||||
issued = issue_wormhole_dm_sender_token(
|
||||
recipient_id=recipient,
|
||||
delivery_class=delivery,
|
||||
recipient_token=str(recipient_token or ""),
|
||||
)
|
||||
if not issued.get("ok"):
|
||||
return issued
|
||||
body["sender_token"] = str(issued.get("sender_token") or "")
|
||||
|
||||
async def _send():
|
||||
import json as _json
|
||||
|
||||
raw = _json.dumps(body).encode("utf-8")
|
||||
|
||||
async def receive():
|
||||
return {"type": "http.request", "body": raw, "more_body": False}
|
||||
|
||||
req = Request(
|
||||
{
|
||||
"type": "http",
|
||||
"method": "POST",
|
||||
"path": "/api/mesh/dm/send",
|
||||
"headers": [(b"content-type", b"application/json")],
|
||||
"client": ("127.0.0.1", 52421),
|
||||
},
|
||||
receive,
|
||||
)
|
||||
req.state._private_lane_current_tier = "private_strong"
|
||||
req.state._transport_tier = "private_strong"
|
||||
return await main_mod.dm_send(req)
|
||||
|
||||
result = _run_async(_send())
|
||||
except Exception as exc:
|
||||
result = {"ok": False, "detail": str(exc) or type(exc).__name__}
|
||||
if isinstance(result, dict):
|
||||
result.setdefault("msg_id", msg_id)
|
||||
result.setdefault("sender_id", sender_id)
|
||||
result.setdefault("recipient_id", recipient)
|
||||
return result
|
||||
|
||||
|
||||
def send_contact_request(
|
||||
*,
|
||||
lookup_token: str = "",
|
||||
peer_id: str = "",
|
||||
note: str = "",
|
||||
lookup_peer_url: str = "",
|
||||
cached_prekey_bundle: dict[str, Any] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Send a first-contact request using a short address or peer id."""
|
||||
from services.mesh.mesh_wormhole_dead_drop import build_contact_offer
|
||||
from services.mesh.mesh_wormhole_persona import get_dm_identity
|
||||
from services.mesh.mesh_wormhole_prekey import bootstrap_encrypt_for_peer, fetch_dm_prekey_bundle
|
||||
|
||||
token = str(lookup_token or "").strip()
|
||||
peer = str(peer_id or "").strip()
|
||||
if not token and not peer:
|
||||
return {"ok": False, "detail": "lookup_token or peer_id required"}
|
||||
|
||||
preferred_peer = str(lookup_peer_url or "").strip().rstrip("/")
|
||||
if cached_prekey_bundle and cached_prekey_bundle.get("ok"):
|
||||
bundle = dict(cached_prekey_bundle)
|
||||
else:
|
||||
bundle = fetch_dm_prekey_bundle(
|
||||
agent_id=peer if not token else "",
|
||||
lookup_token=token,
|
||||
lookup_peer_urls=[preferred_peer] if preferred_peer else None,
|
||||
)
|
||||
if not bundle.get("ok"):
|
||||
return bundle
|
||||
recipient = str(bundle.get("agent_id") or peer).strip()
|
||||
if not recipient:
|
||||
return {"ok": False, "detail": "recipient unresolved"}
|
||||
|
||||
identity = get_dm_identity()
|
||||
offer = build_contact_offer(
|
||||
dh_pub_key=str(identity.get("dh_pub_key") or ""),
|
||||
dh_algo=str(identity.get("dh_algo") or "X25519"),
|
||||
geo_hint=str(note or ""),
|
||||
)
|
||||
encrypted = bootstrap_encrypt_for_peer(
|
||||
recipient,
|
||||
offer,
|
||||
fetched_bundle=bundle,
|
||||
)
|
||||
if not encrypted.get("ok"):
|
||||
return encrypted
|
||||
|
||||
return _submit_signed_dm_send(
|
||||
recipient=recipient,
|
||||
delivery_class="request",
|
||||
recipient_token="",
|
||||
ciphertext=str(encrypted.get("result") or ""),
|
||||
payload_format="mls1",
|
||||
connect_intent="contact_request",
|
||||
lookup_peer_url=preferred_peer,
|
||||
)
|
||||
|
||||
|
||||
def send_contact_accept(
|
||||
*,
|
||||
peer_id: str,
|
||||
peer_dh_pub: str = "",
|
||||
lookup_token: str = "",
|
||||
lookup_peer_url: str = "",
|
||||
) -> dict[str, Any]:
|
||||
"""Accept a pending contact request and open the shared DM lane."""
|
||||
from services.mesh.mesh_wormhole_dead_drop import build_contact_accept, issue_pairwise_dm_alias
|
||||
from services.mesh.mesh_wormhole_prekey import bootstrap_encrypt_for_peer, fetch_dm_prekey_bundle
|
||||
|
||||
peer = str(peer_id or "").strip()
|
||||
if not peer:
|
||||
return {"ok": False, "detail": "peer_id required"}
|
||||
|
||||
token = str(lookup_token or "").strip()
|
||||
preferred_peer = str(lookup_peer_url or "").strip().rstrip("/")
|
||||
dh_pub = str(peer_dh_pub or "").strip()
|
||||
if not dh_pub:
|
||||
bundle = fetch_dm_prekey_bundle(
|
||||
agent_id=peer if not token else "",
|
||||
lookup_token=token,
|
||||
lookup_peer_urls=[preferred_peer] if preferred_peer else None,
|
||||
)
|
||||
if not bundle.get("ok"):
|
||||
return bundle
|
||||
dh_pub = str(bundle.get("dh_pub_key") or "").strip()
|
||||
if not dh_pub:
|
||||
return {"ok": False, "detail": "peer dh_pub_key unavailable"}
|
||||
|
||||
alias = issue_pairwise_dm_alias(peer_id=peer, peer_dh_pub=dh_pub)
|
||||
if not alias.get("ok"):
|
||||
return alias
|
||||
shared_alias = str(alias.get("shared_alias") or "").strip()
|
||||
if not shared_alias:
|
||||
return {"ok": False, "detail": "shared_alias unavailable"}
|
||||
|
||||
accept_plain = build_contact_accept(shared_alias=shared_alias)
|
||||
encrypted = bootstrap_encrypt_for_peer(peer, accept_plain, lookup_token=token)
|
||||
if not encrypted.get("ok"):
|
||||
return encrypted
|
||||
|
||||
sent = _submit_signed_dm_send(
|
||||
recipient=peer,
|
||||
delivery_class="request",
|
||||
recipient_token="",
|
||||
ciphertext=str(encrypted.get("result") or ""),
|
||||
payload_format="mls1",
|
||||
connect_intent="contact_accept",
|
||||
lookup_peer_url=preferred_peer,
|
||||
)
|
||||
if isinstance(sent, dict):
|
||||
sent.setdefault("shared_alias", shared_alias)
|
||||
return sent
|
||||
|
||||
|
||||
def send_dm(
|
||||
peer_id: str,
|
||||
plaintext: str,
|
||||
*,
|
||||
delivery_class: str = "shared",
|
||||
recipient_token: str = "",
|
||||
) -> dict[str, Any]:
|
||||
"""Compose and send an encrypted DM on behalf of the operator."""
|
||||
import main as main_mod
|
||||
|
||||
recipient = str(peer_id or "").strip()
|
||||
if not recipient:
|
||||
return {"ok": False, "detail": "peer_id required"}
|
||||
if not str(plaintext or "").strip():
|
||||
return {"ok": False, "detail": "plaintext required"}
|
||||
|
||||
delivery = str(delivery_class or "shared").strip().lower()
|
||||
if delivery not in ("shared", "request"):
|
||||
return {"ok": False, "detail": "delivery_class must be shared or request"}
|
||||
|
||||
composed = main_mod.compose_wormhole_dm(
|
||||
peer_id=recipient,
|
||||
peer_dh_pub="",
|
||||
plaintext=str(plaintext),
|
||||
)
|
||||
if not composed.get("ok"):
|
||||
return composed
|
||||
|
||||
return _submit_signed_dm_send(
|
||||
recipient=recipient,
|
||||
delivery_class=delivery,
|
||||
recipient_token=str(recipient_token or ""),
|
||||
ciphertext=str(composed.get("ciphertext") or ""),
|
||||
payload_format=str(composed.get("format") or "mls1"),
|
||||
session_welcome=str(composed.get("session_welcome") or ""),
|
||||
)
|
||||
|
||||
|
||||
def poll_dms(*, limit: int = 20) -> dict[str, Any]:
|
||||
"""Poll encrypted DMs for the operator DM identity."""
|
||||
import json
|
||||
|
||||
import main as main_mod
|
||||
from services.mesh.mesh_protocol import PROTOCOL_VERSION
|
||||
from services.mesh.mesh_wormhole_persona import get_dm_identity, sign_dm_wormhole_event
|
||||
|
||||
identity = get_dm_identity()
|
||||
agent_id = str(identity.get("node_id") or "")
|
||||
if not agent_id:
|
||||
return {"ok": False, "detail": "dm identity is not configured"}
|
||||
|
||||
poll_payload = {"mailbox_claims": [], "agent_id": agent_id}
|
||||
signed = sign_dm_wormhole_event(event_type="dm_poll", payload=poll_payload)
|
||||
if not signed.get("ok", True):
|
||||
return signed
|
||||
|
||||
body = {
|
||||
"agent_id": agent_id,
|
||||
"mailbox_claims": [],
|
||||
"timestamp": int(time.time()),
|
||||
"nonce": secrets.token_hex(8),
|
||||
"public_key": str(signed.get("public_key") or ""),
|
||||
"public_key_algo": str(signed.get("public_key_algo") or ""),
|
||||
"signature": str(signed.get("signature") or ""),
|
||||
"sequence": int(signed.get("sequence") or 0),
|
||||
"protocol_version": str(signed.get("protocol_version") or PROTOCOL_VERSION),
|
||||
}
|
||||
|
||||
raw = json.dumps(body).encode("utf-8")
|
||||
|
||||
async def _poll():
|
||||
async def receive():
|
||||
return {"type": "http.request", "body": raw, "more_body": False}
|
||||
|
||||
req = Request(
|
||||
{
|
||||
"type": "http",
|
||||
"method": "POST",
|
||||
"path": "/api/mesh/dm/poll",
|
||||
"headers": [(b"content-type", b"application/json")],
|
||||
"client": ("127.0.0.1", 52421),
|
||||
},
|
||||
receive,
|
||||
)
|
||||
return await main_mod.dm_poll_secure(req)
|
||||
|
||||
result = _run_async(_poll())
|
||||
if isinstance(result, dict):
|
||||
messages = list(result.get("messages") or [])
|
||||
if limit and len(messages) > int(limit):
|
||||
result = dict(result)
|
||||
result["messages"] = messages[: int(limit)]
|
||||
result["count"] = len(result["messages"])
|
||||
return result if isinstance(result, dict) else {"ok": False, "detail": "dm poll failed"}
|
||||
@@ -0,0 +1,531 @@
|
||||
"""Deterministic OpenClaw routing — intent → fastest command.
|
||||
|
||||
Keeps expensive fuzzy scans and full-layer dumps out of the default agent path.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
EXPENSIVE_COMMANDS = frozenset({
|
||||
"search_telemetry",
|
||||
"get_telemetry",
|
||||
"get_slow_telemetry",
|
||||
"get_report",
|
||||
})
|
||||
|
||||
EXPENSIVE_GATE_MESSAGE = (
|
||||
"expensive command blocked — use route_query, find_entity, run_playbook, or targeted reads. "
|
||||
"Pass confirm_expensive=true only when fuzzy search or full dumps are intentional."
|
||||
)
|
||||
|
||||
LATENCY_TIER_MS: dict[str, int] = {
|
||||
"channel_status": 5,
|
||||
"route_query": 5,
|
||||
"get_summary": 10,
|
||||
"what_changed": 15,
|
||||
"search_news": 15,
|
||||
"find_flights": 25,
|
||||
"find_ships": 25,
|
||||
"find_entity": 30,
|
||||
"entities_near": 30,
|
||||
"brief_area": 30,
|
||||
"get_layer_slice": 50,
|
||||
"correlate_entity": 15,
|
||||
"entity_expand": 40,
|
||||
"osint_lookup": 200,
|
||||
"run_playbook": 120,
|
||||
"infonet_status": 20,
|
||||
"list_gates": 15,
|
||||
"read_gate_messages": 40,
|
||||
"poll_dms": 80,
|
||||
"ensure_infonet_ready": 120000,
|
||||
"join_infonet_swarm": 90000,
|
||||
"post_gate_message": 15000,
|
||||
"cast_vote": 5000,
|
||||
"send_dm": 20000,
|
||||
"search_telemetry": 8000,
|
||||
"get_telemetry": 3500,
|
||||
"get_slow_telemetry": 1500,
|
||||
"get_report": 5000,
|
||||
}
|
||||
|
||||
RE_N_NUMBER = re.compile(r"\bN\d{1,5}[A-Z]{0,2}\b", re.I)
|
||||
RE_CALLSIGN = re.compile(r"\b[A-Z]{2,4}\d{1,4}[A-Z]?\b")
|
||||
RE_MMSI = re.compile(r"\b\d{9}\b")
|
||||
RE_CVE = re.compile(r"\bCVE-\d{4}-\d+\b", re.I)
|
||||
RE_IPV4 = re.compile(r"\b(?:\d{1,3}\.){3}\d{1,3}\b")
|
||||
RE_DOMAIN = re.compile(
|
||||
r"\b(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\.)+(?:[a-z]{2,})\b",
|
||||
re.I,
|
||||
)
|
||||
|
||||
KNOWN_CALLSIGNS = frozenset({
|
||||
"AF1", "AF2", "EXEC1", "EXEC2", "SAM", "STALK52", "SPAR19", "SPAR20",
|
||||
})
|
||||
|
||||
PLAYBOOKS: dict[str, dict[str, Any]] = {
|
||||
"hot_snapshot": {
|
||||
"description": "Summary + hot layers + what changed (one batch)",
|
||||
"batch": [
|
||||
{"cmd": "get_summary", "args": {"compact": True}},
|
||||
{
|
||||
"cmd": "get_layer_slice",
|
||||
"args": {
|
||||
"layers": [
|
||||
"news",
|
||||
"telegram_osint",
|
||||
"military_flights",
|
||||
"private_jets",
|
||||
"earthquakes",
|
||||
],
|
||||
"limit_per_layer": 10,
|
||||
"compact": True,
|
||||
},
|
||||
},
|
||||
{"cmd": "what_changed", "args": {"compact": True}},
|
||||
],
|
||||
},
|
||||
"status_check": {
|
||||
"description": "Channel health + layer counts",
|
||||
"batch": [
|
||||
{"cmd": "channel_status", "args": {}},
|
||||
{"cmd": "get_summary", "args": {"compact": True}},
|
||||
],
|
||||
},
|
||||
"morning_brief": {
|
||||
"description": "Operator morning digest layers",
|
||||
"batch": [
|
||||
{"cmd": "get_summary", "args": {"compact": True}},
|
||||
{"cmd": "what_changed", "args": {"compact": True}},
|
||||
{
|
||||
"cmd": "get_layer_slice",
|
||||
"args": {
|
||||
"layers": [
|
||||
"news",
|
||||
"telegram_osint",
|
||||
"gdelt",
|
||||
"earthquakes",
|
||||
"crowdthreat",
|
||||
"military_flights",
|
||||
],
|
||||
"limit_per_layer": 15,
|
||||
"compact": True,
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
"monitor_heartbeat": {
|
||||
"description": "Low-latency monitor poll (replaces full telemetry pull)",
|
||||
"batch": [
|
||||
{"cmd": "what_changed", "args": {"compact": True}},
|
||||
{
|
||||
"cmd": "get_layer_slice",
|
||||
"args": {
|
||||
"layers": [
|
||||
"military_flights",
|
||||
"ships",
|
||||
"earthquakes",
|
||||
"liveuamap",
|
||||
"crowdthreat",
|
||||
"uap_sightings",
|
||||
"firms_fires",
|
||||
"gps_jamming",
|
||||
"wastewater",
|
||||
],
|
||||
"limit_per_layer": 200,
|
||||
"compact": True,
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def routing_manifest() -> dict[str, Any]:
|
||||
"""Machine-readable routing hints for /api/ai/capabilities."""
|
||||
return {
|
||||
"default_read": "find_entity",
|
||||
"preferred_entry": "route_query",
|
||||
"client_wrapper": "ShadowBrokerClient.ask",
|
||||
"batch_playbook": "run_playbook",
|
||||
"last_resort": "search_telemetry",
|
||||
"expensive_commands": sorted(EXPENSIVE_COMMANDS),
|
||||
"latency_tier_ms": LATENCY_TIER_MS,
|
||||
"anti_patterns": [
|
||||
"search_telemetry for known tail numbers, callsigns, owners, or MMSI",
|
||||
"get_telemetry for routine reads — use get_layer_slice or run_playbook hot_snapshot",
|
||||
"sequential send_command loops — use send_batch or run_playbook",
|
||||
"/api/health for liveness — use channel_status",
|
||||
"empty layers: [] on get_layer_slice — pass explicit layer names",
|
||||
],
|
||||
"recipes": [
|
||||
{
|
||||
"intent": "natural language question",
|
||||
"use": "route_query → recommended cmd, or ShadowBrokerClient.ask()",
|
||||
},
|
||||
{
|
||||
"intent": "known person/aircraft",
|
||||
"use": "find_entity(query=...) or find_flights(owner=...)",
|
||||
},
|
||||
{
|
||||
"intent": "news / telegram topic",
|
||||
"use": "search_news(query=...)",
|
||||
},
|
||||
{
|
||||
"intent": "near a point",
|
||||
"use": "entities_near or brief_area",
|
||||
},
|
||||
{
|
||||
"intent": "hot snapshot",
|
||||
"use": "run_playbook(name=hot_snapshot)",
|
||||
},
|
||||
{
|
||||
"intent": "post to infonet gate / join swarm",
|
||||
"use": "ensure_infonet_ready then post_gate_message (full tier)",
|
||||
},
|
||||
{
|
||||
"intent": "read encrypted gate traffic",
|
||||
"use": "read_gate_messages(gate_id=infonet, decrypt=true)",
|
||||
},
|
||||
{
|
||||
"intent": "dm another node",
|
||||
"use": "send_dm(peer_id=..., plaintext=...) (full tier)",
|
||||
},
|
||||
],
|
||||
"playbooks": {
|
||||
name: {"description": spec.get("description", "")}
|
||||
for name, spec in PLAYBOOKS.items()
|
||||
},
|
||||
"agent_surface": {
|
||||
"primary": ["ask", "send_batch", "channel_status"],
|
||||
"writes": [
|
||||
"place_pin",
|
||||
"add_watch",
|
||||
"inject_data",
|
||||
"place_analysis_zone",
|
||||
"ensure_infonet_ready",
|
||||
"post_gate_message",
|
||||
"cast_vote",
|
||||
"send_dm",
|
||||
],
|
||||
"infonet_reads": [
|
||||
"infonet_status",
|
||||
"list_gates",
|
||||
"read_gate_messages",
|
||||
"poll_dms",
|
||||
],
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def requires_expensive_confirm(cmd: str, args: dict[str, Any] | None) -> bool:
|
||||
if cmd not in EXPENSIVE_COMMANDS:
|
||||
return False
|
||||
if isinstance(args, dict) and args.get("confirm_expensive") is True:
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def _compact_args(args: dict[str, Any], *, compact: bool) -> dict[str, Any]:
|
||||
out = dict(args)
|
||||
if compact and "compact" not in out:
|
||||
out["compact"] = True
|
||||
return out
|
||||
|
||||
|
||||
def _estimate_ms(cmd: str) -> int:
|
||||
return int(LATENCY_TIER_MS.get(cmd, 100))
|
||||
|
||||
|
||||
def _news_query(text: str) -> str:
|
||||
cleaned = text
|
||||
for prefix in (
|
||||
"news about",
|
||||
"news on",
|
||||
"telegram",
|
||||
"headlines about",
|
||||
"headlines on",
|
||||
"latest on",
|
||||
"search news for",
|
||||
):
|
||||
if cleaned.lower().startswith(prefix):
|
||||
cleaned = cleaned[len(prefix):].strip()
|
||||
return cleaned.strip(" ?.")
|
||||
|
||||
|
||||
def route_query(
|
||||
text: str = "",
|
||||
*,
|
||||
lat: float | None = None,
|
||||
lng: float | None = None,
|
||||
radius_km: float = 50,
|
||||
compact: bool = True,
|
||||
) -> dict[str, Any]:
|
||||
"""Map natural-language intent to the fastest command (no LLM)."""
|
||||
raw = str(text or "").strip()
|
||||
lowered = raw.lower()
|
||||
avoid = ["search_telemetry", "get_telemetry", "get_slow_telemetry"]
|
||||
alternates: list[dict[str, Any]] = []
|
||||
|
||||
if not raw and lat is not None and lng is not None:
|
||||
recommended = {
|
||||
"cmd": "brief_area",
|
||||
"args": _compact_args(
|
||||
{"lat": lat, "lng": lng, "radius_km": radius_km},
|
||||
compact=compact,
|
||||
),
|
||||
}
|
||||
return {
|
||||
"intent": "area_brief",
|
||||
"recommended": recommended,
|
||||
"alternates": [{"cmd": "entities_near", "args": recommended["args"]}],
|
||||
"avoid": avoid,
|
||||
"estimated_ms": _estimate_ms("brief_area"),
|
||||
}
|
||||
|
||||
if not raw:
|
||||
recommended = {"cmd": "get_summary", "args": _compact_args({}, compact=compact)}
|
||||
return {
|
||||
"intent": "discovery",
|
||||
"recommended": recommended,
|
||||
"alternates": [{"cmd": "channel_status", "args": {}}],
|
||||
"avoid": avoid,
|
||||
"estimated_ms": _estimate_ms("get_summary"),
|
||||
}
|
||||
|
||||
cve_match = RE_CVE.search(raw)
|
||||
if cve_match:
|
||||
recommended = {
|
||||
"cmd": "osint_lookup",
|
||||
"args": _compact_args({"tool": "cve", "cve": cve_match.group(0).upper()}, compact=compact),
|
||||
}
|
||||
return _route_result("cve_lookup", recommended, avoid, alternates)
|
||||
|
||||
ip_match = RE_IPV4.search(raw)
|
||||
if ip_match and ("ip" in lowered or "address" in lowered or lowered.count(".") >= 3):
|
||||
recommended = {
|
||||
"cmd": "osint_lookup",
|
||||
"args": _compact_args({"tool": "ip", "ip": ip_match.group(0)}, compact=compact),
|
||||
}
|
||||
alternates.append({"cmd": "entity_expand", "args": {"type": "ip", "id": ip_match.group(0)}})
|
||||
return _route_result("ip_lookup", recommended, avoid, alternates)
|
||||
|
||||
if "whois" in lowered or ("dns" in lowered and RE_DOMAIN.search(raw)):
|
||||
domain = (RE_DOMAIN.search(raw) or re.search(r"\b([a-z0-9-]+\.[a-z]{2,})\b", raw, re.I))
|
||||
tool = "whois" if "whois" in lowered else "dns"
|
||||
domain_value = domain.group(0) if domain else raw
|
||||
recommended = {
|
||||
"cmd": "osint_lookup",
|
||||
"args": _compact_args({"tool": tool, "domain": domain_value}, compact=compact),
|
||||
}
|
||||
return _route_result("domain_lookup", recommended, avoid, alternates)
|
||||
|
||||
if "sanction" in lowered or "ofac" in lowered:
|
||||
recommended = {
|
||||
"cmd": "osint_lookup",
|
||||
"args": _compact_args({"tool": "sanctions", "query": raw}, compact=compact),
|
||||
}
|
||||
return _route_result("sanctions_lookup", recommended, avoid, alternates)
|
||||
|
||||
mmsi_match = RE_MMSI.search(raw)
|
||||
if mmsi_match and any(k in lowered for k in ("mmsi", "ship", "vessel", "yacht", "boat", "maritime")):
|
||||
recommended = {
|
||||
"cmd": "find_ships",
|
||||
"args": _compact_args({"mmsi": mmsi_match.group(0)}, compact=compact),
|
||||
}
|
||||
alternates.append({"cmd": "find_entity", "args": {"mmsi": mmsi_match.group(0), "entity_type": "ship"}})
|
||||
return _route_result("maritime_identifier", recommended, avoid, alternates)
|
||||
|
||||
n_match = RE_N_NUMBER.search(raw)
|
||||
if n_match:
|
||||
reg = n_match.group(0).upper()
|
||||
recommended = {
|
||||
"cmd": "find_flights",
|
||||
"args": _compact_args({"registration": reg}, compact=compact),
|
||||
}
|
||||
alternates.append({"cmd": "find_entity", "args": {"registration": reg, "entity_type": "aircraft"}})
|
||||
return _route_result("tail_number", recommended, avoid, alternates)
|
||||
|
||||
# callsign tokens
|
||||
tokens = re.findall(r"\b[A-Z0-9]{2,8}\b", raw.upper())
|
||||
for token in tokens:
|
||||
if token in KNOWN_CALLSIGNS or RE_CALLSIGN.fullmatch(token):
|
||||
recommended = {
|
||||
"cmd": "find_flights",
|
||||
"args": _compact_args({"callsign": token}, compact=compact),
|
||||
}
|
||||
alternates.append({"cmd": "find_entity", "args": {"callsign": token, "entity_type": "aircraft"}})
|
||||
return _route_result("callsign", recommended, avoid, alternates)
|
||||
|
||||
if any(k in lowered for k in ("news", "telegram", "headline", "headlines", "gdelt")):
|
||||
recommended = {
|
||||
"cmd": "search_news",
|
||||
"args": _compact_args({"query": _news_query(raw), "limit": 10}, compact=compact),
|
||||
}
|
||||
alternates.append({
|
||||
"cmd": "get_layer_slice",
|
||||
"args": {"layers": ["telegram_osint", "news"], "limit_per_layer": 10, "compact": compact},
|
||||
})
|
||||
return _route_result("news_search", recommended, avoid, alternates)
|
||||
|
||||
if lat is not None and lng is not None and any(
|
||||
k in lowered for k in ("near", "around", "within", "radius", "brief", "aoi")
|
||||
):
|
||||
recommended = {
|
||||
"cmd": "brief_area",
|
||||
"args": _compact_args(
|
||||
{"lat": lat, "lng": lng, "radius_km": radius_km, "query": raw},
|
||||
compact=compact,
|
||||
),
|
||||
}
|
||||
alternates.append({
|
||||
"cmd": "entities_near",
|
||||
"args": {"lat": lat, "lng": lng, "radius_km": radius_km, "compact": compact},
|
||||
})
|
||||
return _route_result("area_brief", recommended, avoid, alternates)
|
||||
|
||||
if any(k in lowered for k in ("what changed", "updates", "delta", "since last")):
|
||||
recommended = {"cmd": "what_changed", "args": _compact_args({}, compact=compact)}
|
||||
return _route_result("incremental_poll", recommended, avoid, alternates)
|
||||
|
||||
if any(k in lowered for k in ("summary", "status", "layers populated", "what data")):
|
||||
recommended = {"cmd": "get_summary", "args": _compact_args({}, compact=compact)}
|
||||
alternates.append({"cmd": "channel_status", "args": {}})
|
||||
return _route_result("discovery", recommended, avoid, alternates)
|
||||
|
||||
if any(k in lowered for k in ("recon", "whois", "dns lookup", "cve", "mac address")):
|
||||
recommended = {
|
||||
"cmd": "osint_tools",
|
||||
"args": {},
|
||||
}
|
||||
return _route_result("recon_discovery", recommended, avoid, alternates)
|
||||
|
||||
entity_type = ""
|
||||
if any(k in lowered for k in ("ship", "vessel", "yacht", "boat", "maritime", "carrier")):
|
||||
entity_type = "ship"
|
||||
elif any(k in lowered for k in ("jet", "plane", "flight", "aircraft", "helicopter", "tail")):
|
||||
entity_type = "aircraft"
|
||||
|
||||
owner_hint = ""
|
||||
if any(k in lowered for k in ("owner", "operated by", "'s jet", "'s yacht", "belongs to")):
|
||||
owner_hint = raw
|
||||
for phrase in ("where is", "find", "track", "locate", "jet", "yacht", "plane", "flight", "ship"):
|
||||
owner_hint = re.sub(rf"\b{phrase}\b", "", owner_hint, flags=re.I).strip()
|
||||
|
||||
entity_args: dict[str, Any] = {"query": raw, "compact": compact}
|
||||
if entity_type:
|
||||
entity_args["entity_type"] = entity_type
|
||||
if owner_hint and len(owner_hint) >= 3:
|
||||
entity_args["owner"] = owner_hint
|
||||
|
||||
recommended = {
|
||||
"cmd": "find_entity",
|
||||
"args": _compact_args(entity_args, compact=compact),
|
||||
}
|
||||
alternates = [
|
||||
{"cmd": "search_news", "args": {"query": raw, "limit": 10, "compact": compact}},
|
||||
]
|
||||
if any(k in lowered for k in ("near", "around")):
|
||||
alternates.append({
|
||||
"cmd": "search_telemetry",
|
||||
"args": {"query": raw, "limit": 10, "confirm_expensive": True, "compact": compact},
|
||||
})
|
||||
|
||||
return _route_result("entity_lookup", recommended, avoid, alternates)
|
||||
|
||||
|
||||
def _route_result(
|
||||
intent: str,
|
||||
recommended: dict[str, Any],
|
||||
avoid: list[str],
|
||||
alternates: list[dict[str, Any]],
|
||||
) -> dict[str, Any]:
|
||||
cmd = str(recommended.get("cmd", ""))
|
||||
return {
|
||||
"intent": intent,
|
||||
"recommended": recommended,
|
||||
"alternates": alternates,
|
||||
"avoid": avoid,
|
||||
"estimated_ms": _estimate_ms(cmd),
|
||||
}
|
||||
|
||||
|
||||
def plan_playbook(name: str, args: dict[str, Any] | None = None) -> dict[str, Any]:
|
||||
"""Resolve a named playbook to a command batch."""
|
||||
playbook = str(name or "").strip().lower()
|
||||
params = dict(args or {})
|
||||
if not playbook:
|
||||
return {"ok": False, "detail": "playbook name required"}
|
||||
|
||||
if playbook == "track_snapshot":
|
||||
query = str(params.get("query", "") or params.get("name", "") or "").strip()
|
||||
if not query:
|
||||
return {"ok": False, "detail": "track_snapshot requires query"}
|
||||
return {
|
||||
"ok": True,
|
||||
"playbook": playbook,
|
||||
"description": "Resolve entity for tracking",
|
||||
"batch": [
|
||||
{
|
||||
"cmd": "find_entity",
|
||||
"args": {
|
||||
"query": query,
|
||||
"entity_type": params.get("entity_type", ""),
|
||||
"fallback_search": True,
|
||||
"compact": True,
|
||||
},
|
||||
}
|
||||
],
|
||||
}
|
||||
|
||||
if playbook == "area_brief":
|
||||
lat = params.get("lat")
|
||||
lng = params.get("lng")
|
||||
if lat is None or lng is None:
|
||||
return {"ok": False, "detail": "area_brief requires lat and lng"}
|
||||
return {
|
||||
"ok": True,
|
||||
"playbook": playbook,
|
||||
"description": "Brief an area of interest",
|
||||
"batch": [
|
||||
{
|
||||
"cmd": "brief_area",
|
||||
"args": {
|
||||
"lat": lat,
|
||||
"lng": lng,
|
||||
"radius_km": params.get("radius_km", 50),
|
||||
"query": params.get("query", ""),
|
||||
"compact": True,
|
||||
},
|
||||
}
|
||||
],
|
||||
}
|
||||
|
||||
if playbook == "entity_recon":
|
||||
query = str(params.get("query", "") or params.get("ip", "") or "").strip()
|
||||
ip_match = RE_IPV4.search(query)
|
||||
if not ip_match:
|
||||
return {"ok": False, "detail": "entity_recon requires an IP in query"}
|
||||
return {
|
||||
"ok": True,
|
||||
"playbook": playbook,
|
||||
"description": "IP recon + entity graph",
|
||||
"batch": [
|
||||
{"cmd": "osint_lookup", "args": {"tool": "ip", "ip": ip_match.group(0), "compact": True}},
|
||||
{"cmd": "entity_expand", "args": {"type": "ip", "id": ip_match.group(0)}},
|
||||
],
|
||||
}
|
||||
|
||||
spec = PLAYBOOKS.get(playbook)
|
||||
if not spec:
|
||||
known = sorted(PLAYBOOKS) + ["track_snapshot", "area_brief", "entity_recon"]
|
||||
return {"ok": False, "detail": f"unknown playbook: {playbook}", "known": known}
|
||||
|
||||
return {
|
||||
"ok": True,
|
||||
"playbook": playbook,
|
||||
"description": spec.get("description", ""),
|
||||
"batch": [dict(item) for item in spec.get("batch", [])],
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
"""Operator-initiated OSINT lookups (server-side proxies)."""
|
||||
@@ -0,0 +1,492 @@
|
||||
"""Server-side OSINT lookups (Osiris port, HTTPS outbound only)."""
|
||||
from __future__ import annotations
|
||||
|
||||
import ipaddress
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
import socket
|
||||
import time
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
from urllib.parse import quote
|
||||
|
||||
from services.network_utils import fetch_with_curl
|
||||
from services.sanctions.ofac import match_exact, search_sanctions
|
||||
from services.ssrf_guard import safe_get, validate_domain, validate_host
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_IPV4_RE = re.compile(r"^(\d{1,3}\.){3}\d{1,3}$")
|
||||
_IPV6_RE = re.compile(r"^[0-9a-fA-F:]+$")
|
||||
_CVE_RE = re.compile(r"^CVE-\d{4}-\d{4,}$", re.I)
|
||||
_ASN_RE = re.compile(r"^(AS)?\d+$", re.I)
|
||||
|
||||
|
||||
def _now_iso() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def _json_get(url: str, *, timeout: float = 8.0, headers: dict[str, str] | None = None) -> Any:
|
||||
resp = fetch_with_curl(url, timeout=timeout, headers=headers or {"Accept": "application/json"})
|
||||
if resp.status_code != 200:
|
||||
return None
|
||||
try:
|
||||
return resp.json()
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def _sanctions_hits(*values: str) -> list[dict[str, Any]] | None:
|
||||
hits: list[dict[str, Any]] = []
|
||||
seen: set[str] = set()
|
||||
for value in values:
|
||||
if not value or value in seen:
|
||||
continue
|
||||
seen.add(value)
|
||||
entries = match_exact(value)
|
||||
if entries:
|
||||
hits.append({"matched_value": value, "entries": entries})
|
||||
return hits or None
|
||||
|
||||
|
||||
def lookup_ip(ip: str) -> dict[str, Any]:
|
||||
if not _IPV4_RE.match(ip) and not _IPV6_RE.match(ip):
|
||||
raise ValueError("Invalid IP format")
|
||||
check = validate_host(ip.strip("[]"))
|
||||
if not check.get("ok"):
|
||||
raise ValueError(check.get("reason", "blocked IP"))
|
||||
|
||||
results: dict[str, Any] = {"ip": ip, "timestamp": _now_iso()}
|
||||
fields = (
|
||||
"status,message,continent,country,countryCode,region,regionName,city,zip,"
|
||||
"lat,lon,timezone,isp,org,as,asname,mobile,proxy,hosting,query"
|
||||
)
|
||||
geo = _json_get(f"https://ip-api.com/json/{quote(ip)}?fields={fields}", timeout=5)
|
||||
if isinstance(geo, dict) and geo.get("status") == "success":
|
||||
results["geo"] = {
|
||||
"country": geo.get("country"),
|
||||
"country_code": geo.get("countryCode"),
|
||||
"region": geo.get("regionName"),
|
||||
"city": geo.get("city"),
|
||||
"lat": geo.get("lat"),
|
||||
"lon": geo.get("lon"),
|
||||
"timezone": geo.get("timezone"),
|
||||
"isp": geo.get("isp"),
|
||||
"org": geo.get("org"),
|
||||
"as_number": geo.get("as"),
|
||||
"as_name": geo.get("asname"),
|
||||
"is_mobile": geo.get("mobile"),
|
||||
"is_proxy": geo.get("proxy"),
|
||||
"is_hosting": geo.get("hosting"),
|
||||
}
|
||||
results["reputation"] = {
|
||||
"is_proxy": bool(geo.get("proxy")),
|
||||
"is_hosting": bool(geo.get("hosting")),
|
||||
"is_mobile": bool(geo.get("mobile")),
|
||||
"risk_level": "HIGH" if geo.get("proxy") else "MEDIUM" if geo.get("hosting") else "LOW",
|
||||
}
|
||||
sm = _sanctions_hits(geo.get("org") or "", geo.get("isp") or "", geo.get("asname") or "")
|
||||
if sm:
|
||||
results["sanctions_match"] = {"source": "OFAC SDN", "hits": sm}
|
||||
return results
|
||||
|
||||
|
||||
def lookup_dns(domain: str) -> dict[str, Any]:
|
||||
if not validate_domain(domain):
|
||||
raise ValueError("Invalid domain format")
|
||||
results: dict[str, Any] = {"domain": domain, "records": {}, "timestamp": _now_iso()}
|
||||
for rtype in ("A", "AAAA", "MX", "NS", "TXT", "CNAME", "SOA"):
|
||||
data = _json_get(
|
||||
f"https://dns.google/resolve?name={quote(domain)}&type={rtype}",
|
||||
timeout=5,
|
||||
)
|
||||
answers = []
|
||||
if isinstance(data, dict):
|
||||
for ans in data.get("Answer") or []:
|
||||
answers.append(
|
||||
{
|
||||
"name": ans.get("name"),
|
||||
"type": ans.get("type"),
|
||||
"ttl": ans.get("TTL"),
|
||||
"data": ans.get("data"),
|
||||
}
|
||||
)
|
||||
results["records"][rtype] = answers
|
||||
a_records = results["records"].get("A") or []
|
||||
mx_records = results["records"].get("MX") or []
|
||||
ns_records = results["records"].get("NS") or []
|
||||
results["summary"] = {
|
||||
"ip_addresses": [r["data"] for r in a_records if r.get("data")],
|
||||
"mail_servers": [r["data"] for r in mx_records if r.get("data")],
|
||||
"nameservers": [r["data"] for r in ns_records if r.get("data")],
|
||||
"total_records": sum(len(v) for v in results["records"].values()),
|
||||
}
|
||||
return results
|
||||
|
||||
|
||||
def lookup_whois(domain: str) -> dict[str, Any]:
|
||||
if not validate_domain(domain):
|
||||
raise ValueError("Invalid domain format")
|
||||
results: dict[str, Any] = {"domain": domain, "timestamp": _now_iso()}
|
||||
rdap = _json_get(f"https://rdap.org/domain/{quote(domain)}", timeout=8)
|
||||
if isinstance(rdap, dict):
|
||||
entities = []
|
||||
for ent in rdap.get("entities") or []:
|
||||
vcard = ent.get("vcardArray")
|
||||
name = org = None
|
||||
if isinstance(vcard, list) and len(vcard) > 1:
|
||||
for row in vcard[1]:
|
||||
if row[0] == "fn":
|
||||
name = row[3]
|
||||
if row[0] == "org":
|
||||
org = row[3]
|
||||
if name or org:
|
||||
entities.append({"handle": ent.get("handle"), "roles": ent.get("roles"), "name": name, "org": org})
|
||||
events = [
|
||||
{"action": e.get("eventAction"), "date": e.get("eventDate")}
|
||||
for e in (rdap.get("events") or [])
|
||||
]
|
||||
results["rdap"] = {
|
||||
"handle": rdap.get("handle"),
|
||||
"name": rdap.get("ldhName"),
|
||||
"status": rdap.get("status"),
|
||||
"events": events,
|
||||
"nameservers": [ns.get("ldhName") for ns in (rdap.get("nameservers") or [])],
|
||||
"entities": entities,
|
||||
}
|
||||
results["registration"] = next((e["date"] for e in events if e["action"] == "registration"), None)
|
||||
results["expiration"] = next((e["date"] for e in events if e["action"] == "expiration"), None)
|
||||
results["last_changed"] = next((e["date"] for e in events if e["action"] == "last changed"), None)
|
||||
sm = _sanctions_hits(*(e.get("name") or "" for e in entities), *(e.get("org") or "" for e in entities))
|
||||
if sm:
|
||||
results["sanctions_match"] = {"source": "OFAC SDN", "hits": sm}
|
||||
|
||||
try:
|
||||
res = safe_get(f"https://{domain}", timeout=5, headers={"User-Agent": "Shadowbroker-OSINT/1.0"})
|
||||
headers = {}
|
||||
for h in (
|
||||
"server",
|
||||
"x-powered-by",
|
||||
"x-frame-options",
|
||||
"strict-transport-security",
|
||||
"content-security-policy",
|
||||
"x-content-type-options",
|
||||
"x-xss-protection",
|
||||
"referrer-policy",
|
||||
"permissions-policy",
|
||||
):
|
||||
val = res.headers.get(h)
|
||||
if val:
|
||||
headers[h] = val
|
||||
score = sum(
|
||||
1
|
||||
for k in (
|
||||
"strict-transport-security",
|
||||
"content-security-policy",
|
||||
"x-frame-options",
|
||||
"x-content-type-options",
|
||||
"referrer-policy",
|
||||
)
|
||||
if k in headers
|
||||
) + (2 if "strict-transport-security" in headers else 0) + (2 if "content-security-policy" in headers else 0)
|
||||
results["http"] = {"status": res.status_code, "headers": headers, "final_url": res.url}
|
||||
results["security_score"] = {
|
||||
"score": score,
|
||||
"max": 7,
|
||||
"grade": "A" if score >= 5 else "B" if score >= 3 else "C" if score >= 1 else "F",
|
||||
}
|
||||
except Exception as exc:
|
||||
logger.debug("WHOIS header probe failed for %s: %s", domain, exc)
|
||||
return results
|
||||
|
||||
|
||||
def lookup_certs(domain: str) -> dict[str, Any]:
|
||||
if not validate_domain(domain):
|
||||
raise ValueError("Invalid domain format")
|
||||
resp = fetch_with_curl(
|
||||
f"https://crt.sh/?q=%25.{quote(domain)}&output=json",
|
||||
timeout=10,
|
||||
headers={"User-Agent": "Shadowbroker-OSINT/1.0"},
|
||||
)
|
||||
if resp.status_code != 200:
|
||||
return {"domain": domain, "certificates": [], "error": "crt.sh unavailable"}
|
||||
try:
|
||||
certs = resp.json()
|
||||
except Exception:
|
||||
certs = []
|
||||
seen: set[str] = set()
|
||||
subdomains: set[str] = set()
|
||||
unique: list[dict[str, Any]] = []
|
||||
for cert in (certs or [])[:200]:
|
||||
key = f"{cert.get('common_name')}-{cert.get('serial_number')}"
|
||||
if key in seen:
|
||||
continue
|
||||
seen.add(key)
|
||||
for name in (cert.get("name_value") or "").split("\n"):
|
||||
clean = name.strip().replace("*.", "")
|
||||
if clean.endswith(domain):
|
||||
subdomains.add(clean)
|
||||
unique.append(
|
||||
{
|
||||
"id": cert.get("id"),
|
||||
"issuer": cert.get("issuer_name"),
|
||||
"common_name": cert.get("common_name"),
|
||||
"not_before": cert.get("not_before"),
|
||||
"not_after": cert.get("not_after"),
|
||||
}
|
||||
)
|
||||
return {
|
||||
"domain": domain,
|
||||
"certificates": unique[:50],
|
||||
"subdomains": sorted(subdomains)[:100],
|
||||
"total_found": len(certs or []),
|
||||
"timestamp": _now_iso(),
|
||||
}
|
||||
|
||||
|
||||
def lookup_threats(query: str | None = None) -> dict[str, Any]:
|
||||
results: dict[str, Any] = {"timestamp": _now_iso()}
|
||||
pulses = _json_get("https://otx.alienvault.com/api/v1/pulses/activity?limit=10", timeout=8)
|
||||
if isinstance(pulses, dict):
|
||||
results["pulses"] = [
|
||||
{
|
||||
"name": p.get("name"),
|
||||
"description": (p.get("description") or "")[:200],
|
||||
"created": p.get("created"),
|
||||
"tags": (p.get("tags") or [])[:5],
|
||||
"adversary": p.get("adversary"),
|
||||
"indicators_count": p.get("indicator_count"),
|
||||
}
|
||||
for p in (pulses.get("results") or [])[:10]
|
||||
]
|
||||
if query:
|
||||
if _IPV4_RE.match(query):
|
||||
try:
|
||||
tor_resp = fetch_with_curl("https://check.torproject.org/torbulkexitlist", timeout=5)
|
||||
results["tor_exit_node"] = query in (tor_resp.text or "").splitlines() if tor_resp.status_code == 200 else None
|
||||
except Exception:
|
||||
results["tor_exit_node"] = None
|
||||
otx = _json_get(f"https://otx.alienvault.com/api/v1/indicators/IPv4/{quote(query)}/general", timeout=5)
|
||||
if isinstance(otx, dict):
|
||||
results["otx"] = {
|
||||
"reputation": otx.get("reputation"),
|
||||
"pulse_count": (otx.get("pulse_info") or {}).get("count", 0),
|
||||
"country": otx.get("country_name"),
|
||||
"asn": otx.get("asn"),
|
||||
}
|
||||
elif validate_domain(query):
|
||||
otx = _json_get(f"https://otx.alienvault.com/api/v1/indicators/domain/{quote(query)}/general", timeout=5)
|
||||
if isinstance(otx, dict):
|
||||
results["otx"] = {"pulse_count": (otx.get("pulse_info") or {}).get("count", 0)}
|
||||
pulse_count = (results.get("otx") or {}).get("pulse_count", 0)
|
||||
results["threat_level"] = "HIGH" if pulse_count > 5 else "MEDIUM" if pulse_count > 0 else "LOW"
|
||||
return results
|
||||
|
||||
|
||||
def lookup_bgp(query: str) -> dict[str, Any]:
|
||||
results: dict[str, Any] = {"query": query, "timestamp": _now_iso()}
|
||||
if _IPV4_RE.match(query):
|
||||
data = _json_get(f"https://api.bgpview.io/ip/{quote(query)}", timeout=8)
|
||||
if isinstance(data, dict) and data.get("status") == "ok":
|
||||
results["ip"] = data.get("data")
|
||||
results["type"] = "ip"
|
||||
return results
|
||||
if _ASN_RE.match(query):
|
||||
asn_num = re.sub(r"^AS", "", query, flags=re.I)
|
||||
asn = _json_get(f"https://api.bgpview.io/asn/{asn_num}", timeout=8)
|
||||
prefixes = _json_get(f"https://api.bgpview.io/asn/{asn_num}/prefixes", timeout=8)
|
||||
peers = _json_get(f"https://api.bgpview.io/asn/{asn_num}/peers", timeout=8)
|
||||
if isinstance(asn, dict) and asn.get("status") == "ok":
|
||||
results["asn"] = asn.get("data")
|
||||
if isinstance(prefixes, dict) and prefixes.get("status") == "ok":
|
||||
pdata = prefixes.get("data") or {}
|
||||
results["prefixes"] = {
|
||||
"ipv4": (pdata.get("ipv4_prefixes") or [])[:20],
|
||||
"ipv6": (pdata.get("ipv6_prefixes") or [])[:10],
|
||||
"total_v4": len(pdata.get("ipv4_prefixes") or []),
|
||||
"total_v6": len(pdata.get("ipv6_prefixes") or []),
|
||||
}
|
||||
if isinstance(peers, dict) and peers.get("status") == "ok":
|
||||
pdata = peers.get("data") or {}
|
||||
results["peers"] = {
|
||||
"upstream": (pdata.get("ipv4_peers") or [])[:10],
|
||||
"total": len(pdata.get("ipv4_peers") or []),
|
||||
}
|
||||
results["type"] = "asn"
|
||||
return results
|
||||
raise ValueError("Unrecognized query format. Use IP address or AS number.")
|
||||
|
||||
|
||||
def lookup_sanctions(query: str, *, schema: str | None = None, limit: int = 25) -> dict[str, Any]:
|
||||
matches = search_sanctions(query, schema=schema, limit=limit)
|
||||
return {
|
||||
"query": query,
|
||||
"schema": schema,
|
||||
"total": len(matches),
|
||||
"matches": matches,
|
||||
"source": "OpenSanctions / US OFAC SDN",
|
||||
"timestamp": _now_iso(),
|
||||
}
|
||||
|
||||
|
||||
def lookup_cve(cve: str) -> dict[str, Any]:
|
||||
if not _CVE_RE.match(cve):
|
||||
raise ValueError("Invalid CVE format")
|
||||
cve_id = cve.upper()
|
||||
data = _json_get(f"https://cveawg.mitre.org/api/cve/{quote(cve_id)}", timeout=8)
|
||||
if isinstance(data, dict) and data.get("cveMetadata"):
|
||||
meta = data["cveMetadata"]
|
||||
desc = ""
|
||||
for block in (data.get("containers") or {}).get("cna", {}).get("descriptions") or []:
|
||||
if block.get("lang") == "en":
|
||||
desc = block.get("value") or desc
|
||||
return {"id": meta.get("cveId", cve_id), "description": desc or "No description.", "timestamp": _now_iso()}
|
||||
fallback = _json_get(f"https://cve.circl.lu/api/cve/{quote(cve_id)}", timeout=8)
|
||||
if isinstance(fallback, dict):
|
||||
return {
|
||||
"id": fallback.get("id", cve_id),
|
||||
"description": fallback.get("summary") or "No description.",
|
||||
"cvss": fallback.get("cvss"),
|
||||
"references": (fallback.get("references") or [])[:5],
|
||||
"timestamp": _now_iso(),
|
||||
}
|
||||
raise ValueError("CVE not found")
|
||||
|
||||
|
||||
def lookup_mac(mac: str) -> dict[str, Any]:
|
||||
clean = mac.strip().upper()
|
||||
clean = re.sub(r"[^A-F0-9:-]", "", clean)
|
||||
data = _json_get(f"https://api.macvendors.com/{quote(clean)}", timeout=8)
|
||||
if isinstance(data, dict):
|
||||
return {"mac": clean, "vendor": data.get("company") or data.get("organization") or "Not Found"}
|
||||
if isinstance(data, str) and data:
|
||||
return {"mac": clean, "vendor": data}
|
||||
return {"mac": clean, "vendor": "Not Found"}
|
||||
|
||||
|
||||
def lookup_github(username: str) -> dict[str, Any]:
|
||||
user = _json_get(f"https://api.github.com/users/{quote(username)}", timeout=8)
|
||||
if not isinstance(user, dict) or user.get("message") == "Not Found":
|
||||
raise ValueError("GitHub user not found")
|
||||
repos = _json_get(f"https://api.github.com/users/{quote(username)}/repos?per_page=10&sort=updated", timeout=8)
|
||||
return {
|
||||
"username": username,
|
||||
"profile": {
|
||||
"name": user.get("name"),
|
||||
"bio": user.get("bio"),
|
||||
"company": user.get("company"),
|
||||
"location": user.get("location"),
|
||||
"public_repos": user.get("public_repos"),
|
||||
"followers": user.get("followers"),
|
||||
"created_at": user.get("created_at"),
|
||||
"html_url": user.get("html_url"),
|
||||
},
|
||||
"repos": [
|
||||
{"name": r.get("name"), "language": r.get("language"), "stars": r.get("stargazers_count")}
|
||||
for r in (repos or [])[:10]
|
||||
if isinstance(r, dict)
|
||||
],
|
||||
"timestamp": _now_iso(),
|
||||
}
|
||||
|
||||
|
||||
def lookup_leaks(email: str) -> dict[str, Any]:
|
||||
if "@" not in email or len(email) < 5:
|
||||
raise ValueError("Invalid email")
|
||||
# HIBP requires API key for v3; use public breach directory style via leak-lookup (rate limited)
|
||||
data = _json_get(f"https://leakcheck.io/api/public?check={quote(email)}", timeout=8)
|
||||
if isinstance(data, dict):
|
||||
return {
|
||||
"email": email,
|
||||
"found": bool(data.get("found")),
|
||||
"sources": data.get("sources") or [],
|
||||
"timestamp": _now_iso(),
|
||||
}
|
||||
return {"email": email, "found": False, "sources": [], "timestamp": _now_iso()}
|
||||
|
||||
|
||||
def sweep_init(ip: str, cidr: int = 24) -> dict[str, Any]:
|
||||
try:
|
||||
addr = ipaddress.IPv4Address(ip)
|
||||
except ValueError as exc:
|
||||
raise ValueError("Invalid IPv4 address format") from exc
|
||||
if addr.is_private or addr.is_loopback or addr.is_link_local or addr.is_reserved:
|
||||
raise ValueError("Private and reserved IP ranges are not allowed")
|
||||
if cidr < 24 or cidr > 32:
|
||||
raise ValueError("CIDR must be between 24 and 32")
|
||||
|
||||
fields = "status,message,country,countryCode,region,regionName,city,lat,lon,isp,org,as,proxy,hosting"
|
||||
geo = _json_get(f"https://ip-api.com/json/{quote(ip)}?fields={fields}", timeout=5)
|
||||
if not isinstance(geo, dict) or geo.get("status") != "success":
|
||||
raise ValueError(f"Geolocation failed: {(geo or {}).get('message', 'unknown')}")
|
||||
return {
|
||||
"center": {
|
||||
"lat": geo.get("lat"),
|
||||
"lng": geo.get("lon"),
|
||||
"city": geo.get("city"),
|
||||
"region": geo.get("regionName"),
|
||||
"country": geo.get("country"),
|
||||
"countryCode": geo.get("countryCode"),
|
||||
"isp": geo.get("isp"),
|
||||
"asn": geo.get("as") or "",
|
||||
"org": geo.get("org") or "",
|
||||
},
|
||||
"target_ip": ip,
|
||||
"cidr": cidr,
|
||||
}
|
||||
|
||||
|
||||
def _internetdb_lookup(ip: str) -> dict[str, Any] | None:
|
||||
try:
|
||||
resp = fetch_with_curl(
|
||||
f"https://internetdb.shodan.io/{quote(ip)}",
|
||||
timeout=4,
|
||||
headers={"Accept": "application/json"},
|
||||
)
|
||||
if resp.status_code == 404:
|
||||
return None
|
||||
if resp.status_code != 200:
|
||||
return None
|
||||
return resp.json()
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def sweep_scan(subnet_start: str, cidr: int, *, max_workers: int = 12) -> dict[str, Any]:
|
||||
"""Scan a /24-/32 via Shodan InternetDB (server-side proxy)."""
|
||||
base = int(ipaddress.IPv4Address(subnet_start))
|
||||
host_count = 2 ** (32 - cidr)
|
||||
if host_count > 256:
|
||||
raise ValueError("Subnet too large")
|
||||
ips = [str(ipaddress.IPv4Address(base + i)) for i in range(host_count)]
|
||||
devices: list[dict[str, Any]] = []
|
||||
t0 = time.time()
|
||||
with ThreadPoolExecutor(max_workers=max_workers) as pool:
|
||||
futures = {pool.submit(_internetdb_lookup, ip): ip for ip in ips}
|
||||
for fut in as_completed(futures):
|
||||
ip = futures[fut]
|
||||
data = fut.result()
|
||||
if not data:
|
||||
continue
|
||||
devices.append(
|
||||
{
|
||||
"ip": data.get("ip") or ip,
|
||||
"ports": data.get("ports") or [],
|
||||
"hostnames": data.get("hostnames") or [],
|
||||
"cpes": data.get("cpes") or [],
|
||||
"vulns": data.get("vulns") or [],
|
||||
"tags": data.get("tags") or [],
|
||||
}
|
||||
)
|
||||
return {
|
||||
"devices": devices,
|
||||
"summary": {"total_hosts": host_count, "total_responsive": len(devices)},
|
||||
"sweep_time_ms": int((time.time() - t0) * 1000),
|
||||
}
|
||||
|
||||
|
||||
def subnet_start_for(ip: str, cidr: int) -> str:
|
||||
net = ipaddress.IPv4Network(f"{ip}/{cidr}", strict=False)
|
||||
return str(net.network_address)
|
||||
@@ -0,0 +1,135 @@
|
||||
"""OpenClaw dispatch for the operator recon / OSINT lookup toolkit."""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from services.osint import lookups
|
||||
from services.osint_intel.resolve import ALLOWED_TYPES, resolve_entity
|
||||
|
||||
_OSINT_TOOLS: dict[str, str] = {
|
||||
"ip": "ip",
|
||||
"dns": "domain",
|
||||
"whois": "domain",
|
||||
"certs": "domain",
|
||||
"threats": "query",
|
||||
"bgp": "query",
|
||||
"sanctions": "query",
|
||||
"cve": "cve",
|
||||
"mac": "mac",
|
||||
"github": "username",
|
||||
"leaks": "email",
|
||||
"sweep_init": "ip",
|
||||
}
|
||||
|
||||
_ENTITY_SCHEMAS = frozenset({
|
||||
"Person",
|
||||
"Organization",
|
||||
"Company",
|
||||
"Vessel",
|
||||
"Airplane",
|
||||
"LegalEntity",
|
||||
})
|
||||
|
||||
|
||||
def _require_str(args: dict[str, Any], *keys: str) -> str:
|
||||
for key in keys:
|
||||
value = str(args.get(key, "") or "").strip()
|
||||
if value:
|
||||
return value
|
||||
joined = "/".join(keys)
|
||||
raise ValueError(f"Missing required argument: {joined}")
|
||||
|
||||
|
||||
def run_osint_lookup(tool: str, args: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Run a passive OSINT lookup (same backends as /api/osint/*)."""
|
||||
name = str(tool or "").strip().lower().replace("-", "_")
|
||||
if name not in _OSINT_TOOLS:
|
||||
allowed = ", ".join(sorted(_OSINT_TOOLS))
|
||||
raise ValueError(f"Unknown OSINT tool '{tool}'. Allowed: {allowed}")
|
||||
|
||||
if name == "ip":
|
||||
return lookups.lookup_ip(_require_str(args, "ip", "query", "value"))
|
||||
if name == "dns":
|
||||
return lookups.lookup_dns(_require_str(args, "domain", "query", "value"))
|
||||
if name == "whois":
|
||||
return lookups.lookup_whois(_require_str(args, "domain", "query", "value"))
|
||||
if name == "certs":
|
||||
return lookups.lookup_certs(_require_str(args, "domain", "query", "value"))
|
||||
if name == "threats":
|
||||
query = str(args.get("query", "") or args.get("value", "") or "").strip() or None
|
||||
return lookups.lookup_threats(query)
|
||||
if name == "bgp":
|
||||
return lookups.lookup_bgp(_require_str(args, "query", "asn", "value"))
|
||||
if name == "sanctions":
|
||||
query = _require_str(args, "query", "name", "value")
|
||||
schema = str(args.get("schema", "") or "").strip() or None
|
||||
if schema and schema not in _ENTITY_SCHEMAS:
|
||||
allowed = ", ".join(sorted(_ENTITY_SCHEMAS))
|
||||
raise ValueError(f"Invalid schema. Allowed: {allowed}")
|
||||
limit = args.get("limit", 25)
|
||||
try:
|
||||
limit = int(limit)
|
||||
except (TypeError, ValueError):
|
||||
limit = 25
|
||||
limit = max(1, min(100, limit))
|
||||
return lookups.lookup_sanctions(query, schema=schema, limit=limit)
|
||||
if name == "cve":
|
||||
return lookups.lookup_cve(_require_str(args, "cve", "query", "value"))
|
||||
if name == "mac":
|
||||
return lookups.lookup_mac(_require_str(args, "mac", "query", "value"))
|
||||
if name == "github":
|
||||
return lookups.lookup_github(_require_str(args, "username", "user", "query", "value"))
|
||||
if name == "leaks":
|
||||
return lookups.lookup_leaks(_require_str(args, "email", "query", "value"))
|
||||
if name == "sweep_init":
|
||||
ip = _require_str(args, "ip", "query", "value")
|
||||
cidr = args.get("cidr", 24)
|
||||
try:
|
||||
cidr = int(cidr)
|
||||
except (TypeError, ValueError):
|
||||
cidr = 24
|
||||
return lookups.sweep_init(ip, cidr)
|
||||
|
||||
raise ValueError(f"Unhandled OSINT tool: {name}")
|
||||
|
||||
|
||||
def run_osint_sweep(args: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Run subnet device discovery (Shodan InternetDB proxy). Requires full access tier."""
|
||||
ip = _require_str(args, "ip", "query", "value")
|
||||
cidr = args.get("cidr", 24)
|
||||
try:
|
||||
cidr = int(cidr)
|
||||
except (TypeError, ValueError):
|
||||
cidr = 24
|
||||
subnet = lookups.subnet_start_for(ip, cidr)
|
||||
scan = lookups.sweep_scan(subnet, cidr)
|
||||
init = lookups.sweep_init(ip, cidr)
|
||||
return {**init, **scan, "subnet": f"{subnet}/{cidr}"}
|
||||
|
||||
|
||||
def run_entity_expand(args: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Expand an entity graph node (aircraft, vessel, IP, company, person, country)."""
|
||||
entity_type = _require_str(args, "type", "entity_type")
|
||||
entity_id = _require_str(args, "id", "entity_id", "query", "value")
|
||||
props = {
|
||||
"label": entity_id,
|
||||
"registration": str(args.get("registration", "") or "").strip() or None,
|
||||
"model": str(args.get("model", "") or "").strip() or None,
|
||||
"icao24": str(args.get("icao24", "") or "").strip() or None,
|
||||
}
|
||||
props = {key: value for key, value in props.items() if value is not None}
|
||||
return resolve_entity(entity_type, entity_id, props)
|
||||
|
||||
|
||||
def osint_tool_help() -> dict[str, Any]:
|
||||
"""Discovery metadata for agents."""
|
||||
return {
|
||||
"tools": sorted(_OSINT_TOOLS),
|
||||
"entity_types": sorted(ALLOWED_TYPES),
|
||||
"sanctions_schemas": sorted(_ENTITY_SCHEMAS),
|
||||
"notes": {
|
||||
"osint_lookup": "Passive lookups — same data as the Recon panel /api/osint/* routes.",
|
||||
"osint_sweep": "Active subnet scan via Shodan InternetDB — requires full OpenClaw access tier.",
|
||||
"entity_expand": "Build a relationship graph around aircraft, vessels, IPs, companies, people, or countries.",
|
||||
},
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
"""Entity graph resolution (Osiris intel layer port)."""
|
||||
@@ -0,0 +1,268 @@
|
||||
"""Entity graph resolver (Python port of Osiris intel/server.js)."""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import re
|
||||
import threading
|
||||
import time
|
||||
from typing import Any
|
||||
from urllib.parse import quote
|
||||
|
||||
from services.network_utils import fetch_with_curl
|
||||
from services.sanctions.ofac import match_exact, search_sanctions
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
ALLOWED_TYPES = frozenset({"aircraft", "vessel", "company", "person", "ip", "country"})
|
||||
_WD_CACHE: dict[str, tuple[float, dict[str, Any]]] = {}
|
||||
_WD_LOCK = threading.Lock()
|
||||
_WD_TTL = 24 * 60 * 60
|
||||
_WD_UA = "Shadowbroker-Intel/1.0 (ontology engine)"
|
||||
|
||||
|
||||
def _dedup(nodes: list[dict], links: list[dict]) -> dict[str, Any]:
|
||||
node_map: dict[str, dict] = {}
|
||||
for n in nodes:
|
||||
node_map[n["id"]] = n
|
||||
seen_links: set[str] = set()
|
||||
out_links: list[dict] = []
|
||||
for link in links:
|
||||
key = f"{link['source']}→{link['target']}→{link['label']}"
|
||||
if key in seen_links:
|
||||
continue
|
||||
seen_links.add(key)
|
||||
out_links.append(link)
|
||||
return {"nodes": list(node_map.values()), "links": out_links}
|
||||
|
||||
|
||||
def _wd_cache_get(key: str) -> dict[str, Any] | None:
|
||||
with _WD_LOCK:
|
||||
entry = _WD_CACHE.get(key)
|
||||
if not entry:
|
||||
return None
|
||||
ts, data = entry
|
||||
if time.time() - ts > _WD_TTL:
|
||||
_WD_CACHE.pop(key, None)
|
||||
return None
|
||||
return data
|
||||
|
||||
|
||||
def _wd_cache_set(key: str, data: dict[str, Any]) -> None:
|
||||
with _WD_LOCK:
|
||||
if len(_WD_CACHE) > 5000:
|
||||
oldest = next(iter(_WD_CACHE))
|
||||
_WD_CACHE.pop(oldest, None)
|
||||
_WD_CACHE[key] = (time.time(), data)
|
||||
|
||||
|
||||
def _add_sanctions(id_label: str, root_id: str, nodes: list, links: list) -> None:
|
||||
for hit in search_sanctions(id_label, limit=3):
|
||||
sid = f"sanction:{hit['id']}"
|
||||
nodes.append(
|
||||
{
|
||||
"id": sid,
|
||||
"label": hit["name"],
|
||||
"type": "sanction",
|
||||
"properties": {"programs": hit.get("programs"), "source": "OFAC SDN"},
|
||||
}
|
||||
)
|
||||
links.append({"source": root_id, "target": sid, "label": "SANCTIONS MATCH"})
|
||||
|
||||
|
||||
def _sparql(query: str) -> list[dict[str, Any]]:
|
||||
url = f"https://query.wikidata.org/sparql?query={quote(query)}&format=json"
|
||||
resp = fetch_with_curl(url, timeout=10, headers={"User-Agent": _WD_UA, "Accept": "application/sparql-results+json"})
|
||||
if resp.status_code != 200:
|
||||
return []
|
||||
try:
|
||||
data = resp.json()
|
||||
except Exception:
|
||||
return []
|
||||
return data.get("results", {}).get("bindings", [])
|
||||
|
||||
|
||||
def _wd_search(label: str) -> str | None:
|
||||
url = (
|
||||
"https://www.wikidata.org/w/api.php?action=wbsearchentities"
|
||||
f"&search={quote(label)}&language=en&limit=1&format=json"
|
||||
)
|
||||
resp = fetch_with_curl(url, timeout=5, headers={"User-Agent": _WD_UA})
|
||||
if resp.status_code != 200:
|
||||
return None
|
||||
try:
|
||||
hits = resp.json().get("search") or []
|
||||
except Exception:
|
||||
return None
|
||||
return hits[0]["id"] if hits else None
|
||||
|
||||
|
||||
def _resolve_ip(id_value: str) -> dict[str, Any]:
|
||||
cache_key = f"ip:{id_value}"
|
||||
cached = _wd_cache_get(cache_key)
|
||||
if cached:
|
||||
return cached
|
||||
|
||||
root_id = f"ip:{id_value}"
|
||||
nodes: list[dict] = [{"id": root_id, "label": id_value, "type": "ip", "properties": {}}]
|
||||
links: list[dict] = []
|
||||
|
||||
geo = fetch_with_curl(
|
||||
f"https://ip-api.com/json/{quote(id_value)}"
|
||||
"?fields=status,country,countryCode,city,lat,lon,isp,org,as,asname,proxy,hosting,mobile",
|
||||
timeout=8,
|
||||
)
|
||||
if geo.status_code == 200:
|
||||
try:
|
||||
data = geo.json()
|
||||
except Exception:
|
||||
data = {}
|
||||
if data.get("status") == "success":
|
||||
nodes[0]["properties"] = {
|
||||
"proxy": bool(data.get("proxy")),
|
||||
"hosting": bool(data.get("hosting")),
|
||||
"mobile": bool(data.get("mobile")),
|
||||
"source": "ip-api.com",
|
||||
}
|
||||
if data.get("isp"):
|
||||
iid = f"company:{data['isp']}"
|
||||
nodes.append({"id": iid, "label": data["isp"], "type": "company", "properties": {"role": "ISP"}})
|
||||
links.append({"source": root_id, "target": iid, "label": "HOSTED_BY"})
|
||||
if data.get("country"):
|
||||
cid = f"country:{data['country']}"
|
||||
nodes.append(
|
||||
{
|
||||
"id": cid,
|
||||
"label": data["country"],
|
||||
"type": "country",
|
||||
"properties": {"code": data.get("countryCode")},
|
||||
}
|
||||
)
|
||||
links.append({"source": root_id, "target": cid, "label": "LOCATED_IN"})
|
||||
for val in (data.get("isp"), data.get("org"), data.get("asname")):
|
||||
if val:
|
||||
for entry in match_exact(val):
|
||||
sid = f"sanction:{entry['id']}"
|
||||
nodes.append({"id": sid, "label": entry["name"], "type": "sanction", "properties": {}})
|
||||
links.append({"source": root_id, "target": sid, "label": "SANCTIONS MATCH"})
|
||||
|
||||
whois = fetch_with_curl(
|
||||
f"https://stat.ripe.net/data/whois/data.json?resource={quote(id_value)}",
|
||||
timeout=8,
|
||||
)
|
||||
if whois.status_code == 200:
|
||||
try:
|
||||
records = whois.json().get("data", {}).get("records") or []
|
||||
except Exception:
|
||||
records = []
|
||||
for record in records:
|
||||
for field in record:
|
||||
if field.get("key") in ("netname", "NetName"):
|
||||
nid = f"company:{field['value']}"
|
||||
nodes.append({"id": nid, "label": field["value"], "type": "company", "properties": {"role": "Network"}})
|
||||
links.append({"source": root_id, "target": nid, "label": "HOSTED_BY"})
|
||||
|
||||
result = _dedup(nodes, links)
|
||||
_wd_cache_set(cache_key, result)
|
||||
return result
|
||||
|
||||
|
||||
def _resolve_company(id_value: str) -> dict[str, Any]:
|
||||
cache_key = f"company:{id_value}"
|
||||
cached = _wd_cache_get(cache_key)
|
||||
if cached:
|
||||
return cached
|
||||
root_id = f"company:{id_value}"
|
||||
nodes = [{"id": root_id, "label": id_value, "type": "company", "properties": {}}]
|
||||
links: list[dict] = []
|
||||
safe = re.sub(r'[^a-zA-Z0-9 \-._]', '', id_value).strip()
|
||||
qid = _wd_search(safe)
|
||||
filt = f"VALUES ?item {{ wd:{qid} }}" if qid else f'?item rdfs:label "{safe}"@en . ?item wdt:P31/wdt:P279* wd:Q4830453 .'
|
||||
rows = _sparql(
|
||||
f"""
|
||||
SELECT ?countryLabel ?parentLabel ?ceoLabel WHERE {{
|
||||
{filt}
|
||||
OPTIONAL {{ ?item wdt:P17 ?country . }}
|
||||
OPTIONAL {{ ?item wdt:P749 ?parent . }}
|
||||
OPTIONAL {{ ?item wdt:P169 ?ceo . }}
|
||||
SERVICE wikibase:label {{ bd:serviceParam wikibase:language "en" . }}
|
||||
}} LIMIT 10
|
||||
"""
|
||||
)
|
||||
for row in rows:
|
||||
if row.get("countryLabel", {}).get("value"):
|
||||
cid = f"country:{row['countryLabel']['value']}"
|
||||
nodes.append({"id": cid, "label": row["countryLabel"]["value"], "type": "country", "properties": {}})
|
||||
links.append({"source": root_id, "target": cid, "label": "HEADQUARTERED"})
|
||||
if row.get("parentLabel", {}).get("value"):
|
||||
pid = f"company:{row['parentLabel']['value']}"
|
||||
nodes.append({"id": pid, "label": row["parentLabel"]["value"], "type": "company", "properties": {}})
|
||||
links.append({"source": root_id, "target": pid, "label": "PARENT ORG"})
|
||||
if row.get("ceoLabel", {}).get("value"):
|
||||
pid = f"person:{row['ceoLabel']['value']}"
|
||||
nodes.append({"id": pid, "label": row["ceoLabel"]["value"], "type": "person", "properties": {"role": "CEO"}})
|
||||
links.append({"source": root_id, "target": pid, "label": "CEO"})
|
||||
_add_sanctions(id_value, root_id, nodes, links)
|
||||
result = _dedup(nodes, links)
|
||||
_wd_cache_set(cache_key, result)
|
||||
return result
|
||||
|
||||
|
||||
def _resolve_from_store(entity_type: str, id_value: str, props: dict[str, Any]) -> dict[str, Any]:
|
||||
from services.fetchers._store import get_latest_data_subset_refs
|
||||
|
||||
root_id = f"{entity_type}:{id_value}"
|
||||
nodes = [{"id": root_id, "label": props.get("label") or id_value, "type": entity_type, "properties": props}]
|
||||
links: list[dict] = []
|
||||
data = get_latest_data_subset_refs("flights", "ships", "military_flights", "tracked_flights")
|
||||
|
||||
if entity_type == "aircraft":
|
||||
icao = (props.get("icao24") or id_value).lower()
|
||||
for bucket in ("military_flights", "tracked_flights", "flights"):
|
||||
for f in data.get(bucket) or []:
|
||||
if str(f.get("icao24", "")).lower() == icao:
|
||||
if f.get("country"):
|
||||
cid = f"country:{f['country']}"
|
||||
nodes.append({"id": cid, "label": f["country"], "type": "country", "properties": {}})
|
||||
links.append({"source": root_id, "target": cid, "label": "REGISTERED_IN"})
|
||||
if f.get("registration"):
|
||||
nodes[0]["properties"]["registration"] = f["registration"]
|
||||
break
|
||||
elif entity_type == "vessel":
|
||||
mmsi = str(props.get("mmsi") or id_value)
|
||||
for ship in data.get("ships") or []:
|
||||
if str(ship.get("mmsi")) == mmsi:
|
||||
if ship.get("country"):
|
||||
cid = f"country:{ship['country']}"
|
||||
nodes.append({"id": cid, "label": ship["country"], "type": "country", "properties": {}})
|
||||
links.append({"source": root_id, "target": cid, "label": "FLAG"})
|
||||
break
|
||||
_add_sanctions(id_value, root_id, nodes, links)
|
||||
return _dedup(nodes, links)
|
||||
|
||||
|
||||
def resolve_entity(entity_type: str, id_value: str, properties: dict[str, Any] | None = None) -> dict[str, Any]:
|
||||
etype = (entity_type or "").lower().strip()
|
||||
eid = (id_value or "").strip()
|
||||
if etype not in ALLOWED_TYPES:
|
||||
raise ValueError(f"Invalid type. Allowed: {', '.join(sorted(ALLOWED_TYPES))}")
|
||||
if len(eid) < 2 or len(eid) > 200:
|
||||
raise ValueError("Invalid id (2-200 chars)")
|
||||
props = properties or {}
|
||||
|
||||
if etype == "ip":
|
||||
return _resolve_ip(eid)
|
||||
if etype in ("company", "person", "country"):
|
||||
if etype == "company":
|
||||
return _resolve_company(eid)
|
||||
if etype == "person":
|
||||
root_id = f"person:{eid}"
|
||||
nodes = [{"id": root_id, "label": eid, "type": "person", "properties": {}}]
|
||||
links: list[dict] = []
|
||||
_add_sanctions(eid, root_id, nodes, links)
|
||||
return _dedup(nodes, links)
|
||||
root_id = f"country:{eid}"
|
||||
nodes = [{"id": root_id, "label": eid, "type": "country", "properties": {}}]
|
||||
links = []
|
||||
_add_sanctions(eid, root_id, nodes, links)
|
||||
return _dedup(nodes, links)
|
||||
return _resolve_from_store(etype, eid, props)
|
||||
@@ -0,0 +1,81 @@
|
||||
"""Operator opt-in for Polymarket/Kalshi outbound fetches (Global Threat Intercept)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import threading
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_OPT_IN_FILE = Path(__file__).resolve().parent.parent / "data" / "prediction_markets_opt_in.json"
|
||||
_OPT_IN_LOCK = threading.Lock()
|
||||
|
||||
|
||||
def _env_flag(name: str) -> str:
|
||||
return str(os.getenv(name, "")).strip().lower()
|
||||
|
||||
|
||||
def get_prediction_markets_ui_opt_in() -> bool:
|
||||
if not _OPT_IN_FILE.exists():
|
||||
return False
|
||||
try:
|
||||
payload = json.loads(_OPT_IN_FILE.read_text(encoding="utf-8"))
|
||||
return bool(payload.get("opted_in"))
|
||||
except (OSError, json.JSONDecodeError, TypeError) as exc:
|
||||
logger.warning("Prediction markets opt-in file unreadable: %s", exc)
|
||||
return False
|
||||
|
||||
|
||||
def set_prediction_markets_ui_opt_in(opted_in: bool) -> None:
|
||||
_OPT_IN_FILE.parent.mkdir(parents=True, exist_ok=True)
|
||||
with _OPT_IN_LOCK:
|
||||
_OPT_IN_FILE.write_text(
|
||||
json.dumps({"opted_in": bool(opted_in)}, indent=2),
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
|
||||
def prediction_markets_env_forced_on() -> bool:
|
||||
return _env_flag("PREDICTION_MARKETS_ENABLED") in {"1", "true", "yes", "on"}
|
||||
|
||||
|
||||
def prediction_markets_env_forced_off() -> bool:
|
||||
return _env_flag("PREDICTION_MARKETS_ENABLED") in {"0", "false", "no", "off"}
|
||||
|
||||
|
||||
def prediction_markets_fetch_enabled() -> bool:
|
||||
"""True when UI opt-in or env enables Polymarket/Kalshi pulls."""
|
||||
if get_prediction_markets_ui_opt_in():
|
||||
return True
|
||||
return prediction_markets_env_forced_on()
|
||||
|
||||
|
||||
def prediction_markets_status() -> dict[str, Any]:
|
||||
ui_opted_in = get_prediction_markets_ui_opt_in()
|
||||
env_on = prediction_markets_env_forced_on()
|
||||
env_off = prediction_markets_env_forced_off()
|
||||
env_override = None
|
||||
if env_on:
|
||||
env_override = "on"
|
||||
elif env_off:
|
||||
env_override = "off"
|
||||
return {
|
||||
"enabled": prediction_markets_fetch_enabled(),
|
||||
"ui_opted_in": ui_opted_in,
|
||||
"env_override": env_override,
|
||||
"jitter": {
|
||||
"scheduler_interval_minutes": int(
|
||||
os.environ.get("PREDICTION_MARKETS_INTERVAL_MINUTES", "7")
|
||||
),
|
||||
"scheduler_jitter_seconds": int(
|
||||
os.environ.get("PREDICTION_MARKETS_SCHEDULER_JITTER_S", "240")
|
||||
),
|
||||
"pre_fetch_jitter_seconds": float(
|
||||
os.environ.get("PREDICTION_MARKETS_PRE_FETCH_JITTER_S", "90")
|
||||
),
|
||||
},
|
||||
}
|
||||
@@ -213,7 +213,7 @@ def validate_privacy_core_startup(settings: Any | None = None) -> None:
|
||||
|
||||
attestation = privacy_core_attestation(snapshot)
|
||||
state = str(attestation.get("attestation_state", "") or "").strip()
|
||||
if state == "attested_current":
|
||||
if state in {"attested_current", "development_override"}:
|
||||
return
|
||||
|
||||
logger.critical(
|
||||
|
||||
@@ -301,3 +301,36 @@ def get_region_dossier(lat: float, lng: float) -> dict:
|
||||
|
||||
dossier_cache[cache_key] = result
|
||||
return result
|
||||
|
||||
|
||||
def fetch_wikipedia_page_summary(title: str) -> dict | None:
|
||||
"""Wikipedia REST summary for a page title (backend-proxied for #360)."""
|
||||
trimmed = (title or "").strip()
|
||||
if not trimmed:
|
||||
return None
|
||||
data = _fetch_local_wiki_summary(trimmed, "")
|
||||
if not data.get("extract") and not data.get("description"):
|
||||
return None
|
||||
return {
|
||||
"title": trimmed,
|
||||
"description": data.get("description", ""),
|
||||
"extract": data.get("extract", ""),
|
||||
"thumbnail": data.get("thumbnail", ""),
|
||||
"type": "standard",
|
||||
}
|
||||
|
||||
|
||||
def fetch_wikidata_sparql_bindings(sparql: str) -> list:
|
||||
"""Run a Wikidata SPARQL query; returns bindings list (empty on failure)."""
|
||||
trimmed = (sparql or "").strip()
|
||||
if not trimmed:
|
||||
return []
|
||||
url = f"https://query.wikidata.org/sparql?query={quote(trimmed)}&format=json"
|
||||
try:
|
||||
res = fetch_with_curl(url, timeout=8, headers=_wikimedia_request_headers())
|
||||
if res.status_code == 200:
|
||||
bindings = res.json().get("results", {}).get("bindings", [])
|
||||
return bindings if isinstance(bindings, list) else []
|
||||
except (ConnectionError, TimeoutError, ValueError, KeyError, OSError) as e:
|
||||
logger.warning("Wikidata SPARQL failed: %s", e)
|
||||
return []
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
"""Sentinel-2 road corridor freight trend analysis (DrishX engine port)."""
|
||||
|
||||
from .config import optional_deps_available, road_corridor_sat_enabled
|
||||
|
||||
__all__ = ["optional_deps_available", "road_corridor_sat_enabled"]
|
||||
@@ -0,0 +1,4 @@
|
||||
from .cli import main
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,53 @@
|
||||
"""CLI for manual road corridor analysis runs."""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import sys
|
||||
|
||||
from .config import optional_deps_available, road_corridor_sat_enabled
|
||||
from .credentials import sentinel_credentials_configured
|
||||
from .pipeline import analyze_preset
|
||||
from .presets import CORRIDOR_PRESETS
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
parser = argparse.ArgumentParser(description="Run Sentinel-2 road corridor truck trend analysis")
|
||||
parser.add_argument("--preset", required=True, help="Preset id (e.g. laredo_i35)")
|
||||
parser.add_argument("-v", "--verbose", action="store_true")
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO)
|
||||
|
||||
if not optional_deps_available():
|
||||
print(
|
||||
"Install optional deps: uv sync --extra road-corridor "
|
||||
"(geopandas, osmnx, rasterio, sentinelhub, scikit-learn, imageio)",
|
||||
file=sys.stderr,
|
||||
)
|
||||
return 2
|
||||
if not road_corridor_sat_enabled() and not args.verbose:
|
||||
print("Note: ROAD_CORRIDOR_SAT_ENABLED is off — CLI still runs for manual analysis.")
|
||||
if not sentinel_credentials_configured():
|
||||
print("Set SENTINEL_CLIENT_ID and SENTINEL_CLIENT_SECRET first.", file=sys.stderr)
|
||||
return 2
|
||||
|
||||
valid = {p["id"] for p in CORRIDOR_PRESETS}
|
||||
if args.preset not in valid:
|
||||
print(f"Unknown preset {args.preset!r}. Choose from: {', '.join(sorted(valid))}", file=sys.stderr)
|
||||
return 2
|
||||
|
||||
def progress(msg: str, pct: int | None = None) -> None:
|
||||
suffix = f" ({pct}%)" if pct is not None else ""
|
||||
print(f"{msg}{suffix}")
|
||||
|
||||
result = analyze_preset(args.preset, progress_cb=progress)
|
||||
print(
|
||||
f"Done: {result.get('total_detections', 0)} detections across "
|
||||
f"{len(result.get('daily_counts') or [])} days — status={result.get('status')}"
|
||||
)
|
||||
return 0 if result.get("status") == "ok" else 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,41 @@
|
||||
"""Configuration for Sentinel-2 road corridor trend analysis."""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
_BACKEND_ROOT = Path(__file__).resolve().parents[2]
|
||||
DATA_ROOT = Path(os.environ.get("ROAD_CORRIDOR_DATA_DIR", str(_BACKEND_ROOT / "data" / "road_corridors")))
|
||||
CACHE_DIR = DATA_ROOT / "cache"
|
||||
DETECTION_CROP_DIR = DATA_ROOT / "detection_crops"
|
||||
STATE_PATH = DATA_ROOT / "_refresh_state.json"
|
||||
|
||||
DEFAULT_MONTHS = int(os.environ.get("ROAD_CORRIDOR_MONTHS", "2"))
|
||||
DEFAULT_MAX_FRAMES = int(os.environ.get("ROAD_CORRIDOR_MAX_FRAMES", "6"))
|
||||
SCHEDULED_PRESET_IDS = [
|
||||
s.strip()
|
||||
for s in os.environ.get("ROAD_CORRIDOR_SCHEDULED_PRESETS", "laredo_i35").split(",")
|
||||
if s.strip()
|
||||
]
|
||||
|
||||
|
||||
def road_corridor_sat_enabled() -> bool:
|
||||
return os.environ.get("ROAD_CORRIDOR_SAT_ENABLED", "").strip().lower() in {
|
||||
"1",
|
||||
"true",
|
||||
"yes",
|
||||
"on",
|
||||
}
|
||||
|
||||
|
||||
def optional_deps_available() -> bool:
|
||||
try:
|
||||
import geopandas # noqa: F401
|
||||
import osmnx # noqa: F401
|
||||
import rasterio # noqa: F401
|
||||
import sentinelhub # noqa: F401
|
||||
import sklearn # noqa: F401
|
||||
|
||||
return True
|
||||
except ImportError:
|
||||
return False
|
||||
@@ -0,0 +1,37 @@
|
||||
"""Reuse Shadowbroker Sentinel Hub / Copernicus CDSE credentials."""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
|
||||
from .config import CACHE_DIR
|
||||
|
||||
|
||||
def resolve_sentinel_credentials() -> tuple[str, str]:
|
||||
client_id = (os.environ.get("SENTINEL_CLIENT_ID") or "").strip()
|
||||
client_secret = (os.environ.get("SENTINEL_CLIENT_SECRET") or "").strip()
|
||||
return client_id, client_secret
|
||||
|
||||
|
||||
def sentinel_credentials_configured() -> bool:
|
||||
client_id, client_secret = resolve_sentinel_credentials()
|
||||
return bool(client_id and client_secret)
|
||||
|
||||
|
||||
def build_sh_config():
|
||||
from sentinelhub import SHConfig
|
||||
|
||||
client_id, client_secret = resolve_sentinel_credentials()
|
||||
if not client_id or not client_secret:
|
||||
raise RuntimeError(
|
||||
"SENTINEL_CLIENT_ID and SENTINEL_CLIENT_SECRET are required for road corridor analysis"
|
||||
)
|
||||
config = SHConfig()
|
||||
config.sh_client_id = client_id
|
||||
config.sh_client_secret = client_secret
|
||||
config.sh_base_url = "https://sh.dataspace.copernicus.eu"
|
||||
config.sh_token_url = (
|
||||
"https://identity.dataspace.copernicus.eu/auth/realms/CDSE/protocol/openid-connect/token"
|
||||
)
|
||||
CACHE_DIR.mkdir(parents=True, exist_ok=True)
|
||||
config.cache_dir = str(CACHE_DIR / "sentinelhub")
|
||||
return config
|
||||
@@ -0,0 +1,149 @@
|
||||
"""In-memory job queue for on-demand Analyze Here runs."""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import threading
|
||||
import uuid
|
||||
from dataclasses import dataclass
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_lock = threading.Lock()
|
||||
_jobs: dict[str, AnalyzeJob] = {}
|
||||
|
||||
|
||||
@dataclass
|
||||
class AnalyzeJob:
|
||||
job_id: str
|
||||
lat: float
|
||||
lon: float
|
||||
status: str = "queued"
|
||||
message: str = "Queued"
|
||||
progress: int = 0
|
||||
result: dict[str, Any] | None = None
|
||||
error: str | None = None
|
||||
|
||||
|
||||
def get_job(job_id: str) -> AnalyzeJob | None:
|
||||
with _lock:
|
||||
return _jobs.get(job_id)
|
||||
|
||||
|
||||
def get_latest_job() -> AnalyzeJob | None:
|
||||
with _lock:
|
||||
if not _jobs:
|
||||
return None
|
||||
return max(_jobs.values(), key=lambda j: j.job_id)
|
||||
|
||||
|
||||
def _running_job() -> AnalyzeJob | None:
|
||||
with _lock:
|
||||
for job in _jobs.values():
|
||||
if job.status in {"queued", "running"}:
|
||||
return job
|
||||
return None
|
||||
|
||||
|
||||
def _prune_jobs(max_keep: int = 8) -> None:
|
||||
with _lock:
|
||||
if len(_jobs) <= max_keep:
|
||||
return
|
||||
ordered = sorted(_jobs.items(), key=lambda item: item[0], reverse=True)
|
||||
for job_id, _ in ordered[max_keep:]:
|
||||
_jobs.pop(job_id, None)
|
||||
|
||||
|
||||
def _worker(job_id: str, lat: float, lon: float, label: str | None) -> None:
|
||||
from services.fetchers.road_corridor_sat import refresh_road_corridor_store
|
||||
|
||||
from .pipeline import analyze_corridor
|
||||
from .viewport import adhoc_preset_id, bbox_around_point, default_label_for_point
|
||||
|
||||
job = get_job(job_id)
|
||||
if job is None:
|
||||
return
|
||||
|
||||
def progress(msg: str, pct: int | None = None) -> None:
|
||||
with _lock:
|
||||
current = _jobs.get(job_id)
|
||||
if current is None:
|
||||
return
|
||||
current.message = msg
|
||||
if pct is not None:
|
||||
current.progress = pct
|
||||
|
||||
with _lock:
|
||||
job.status = "running"
|
||||
job.message = "Starting road corridor analysis"
|
||||
job.progress = 0
|
||||
|
||||
try:
|
||||
bbox = bbox_around_point(lat, lon)
|
||||
preset_id = adhoc_preset_id(lat, lon)
|
||||
corridor_label = label or default_label_for_point(lat, lon)
|
||||
result = analyze_corridor(
|
||||
preset_id=preset_id,
|
||||
label=corridor_label,
|
||||
bbox=bbox,
|
||||
country="adhoc",
|
||||
category="viewport",
|
||||
progress_cb=progress,
|
||||
)
|
||||
refresh_road_corridor_store()
|
||||
with _lock:
|
||||
current = _jobs.get(job_id)
|
||||
if current is None:
|
||||
return
|
||||
current.status = "ok" if result.get("status") == "ok" else "error"
|
||||
current.result = result
|
||||
current.error = result.get("error")
|
||||
current.message = (
|
||||
f"{result.get('total_detections', 0)} signatures · "
|
||||
f"{len(result.get('daily_counts') or [])} days"
|
||||
)
|
||||
current.progress = 100
|
||||
except Exception as exc:
|
||||
logger.exception("road corridor analyze job %s failed", job_id)
|
||||
with _lock:
|
||||
current = _jobs.get(job_id)
|
||||
if current is None:
|
||||
return
|
||||
current.status = "error"
|
||||
current.error = str(exc)
|
||||
current.message = "Analysis failed"
|
||||
current.progress = 100
|
||||
|
||||
|
||||
def enqueue_analyze(lat: float, lon: float, label: str | None = None) -> AnalyzeJob:
|
||||
running = _running_job()
|
||||
if running is not None:
|
||||
raise RuntimeError("analysis_already_running")
|
||||
|
||||
job_id = uuid.uuid4().hex[:12]
|
||||
job = AnalyzeJob(job_id=job_id, lat=lat, lon=lon)
|
||||
with _lock:
|
||||
_jobs[job_id] = job
|
||||
_prune_jobs()
|
||||
|
||||
thread = threading.Thread(
|
||||
target=_worker,
|
||||
args=(job_id, lat, lon, label),
|
||||
name=f"road-corridor-analyze-{job_id}",
|
||||
daemon=True,
|
||||
)
|
||||
thread.start()
|
||||
return job
|
||||
|
||||
|
||||
def job_to_dict(job: AnalyzeJob) -> dict[str, Any]:
|
||||
return {
|
||||
"job_id": job.job_id,
|
||||
"lat": job.lat,
|
||||
"lon": job.lon,
|
||||
"status": job.status,
|
||||
"message": job.message,
|
||||
"progress": job.progress,
|
||||
"result": job.result,
|
||||
"error": job.error,
|
||||
}
|
||||
@@ -0,0 +1,216 @@
|
||||
"""Run Sentinel-2 road-corridor truck trend analysis for a bbox preset."""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from collections.abc import Callable
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
from datetime import datetime, timedelta
|
||||
from typing import Any
|
||||
|
||||
from .config import CACHE_DIR, DEFAULT_MAX_FRAMES, DEFAULT_MONTHS, DETECTION_CROP_DIR
|
||||
from .storage import store_analysis_result
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
ProgressCb = Callable[[str, int | None], None]
|
||||
|
||||
_EVALSCRIPT = """//VERSION=3
|
||||
function setup() {
|
||||
return {
|
||||
input: ["B02", "B03", "B04", "B08", "CLM"],
|
||||
output: { id: "default", bands: 5, sampleType: "FLOAT32" }
|
||||
};
|
||||
}
|
||||
function evaluatePixel(s) {
|
||||
return [s.B04, s.B03, s.B02, s.B08, s.CLM];
|
||||
}"""
|
||||
|
||||
|
||||
def _noop_progress(_msg: str, _pct: int | None = None) -> None:
|
||||
return None
|
||||
|
||||
|
||||
def analyze_corridor(
|
||||
*,
|
||||
preset_id: str,
|
||||
label: str,
|
||||
bbox: list[float],
|
||||
country: str = "",
|
||||
category: str = "",
|
||||
months: int = DEFAULT_MONTHS,
|
||||
max_frames: int = DEFAULT_MAX_FRAMES,
|
||||
progress_cb: ProgressCb | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Synchronously analyze one corridor bbox and persist daily truck-count trends."""
|
||||
from rasterio import features as rio_features
|
||||
from rasterio import transform as rio_transform
|
||||
from sentinelhub import BBox, CRS, DataCollection, MimeType, SentinelHubCatalog, SentinelHubRequest
|
||||
|
||||
from .credentials import build_sh_config
|
||||
from .s2_truck_detect import S2TruckEngine
|
||||
|
||||
progress = progress_cb or _noop_progress
|
||||
min_lat, min_lon, max_lat, max_lon = bbox
|
||||
if abs(max_lat - min_lat) > 0.5 or abs(max_lon - min_lon) > 0.5:
|
||||
raise ValueError("AOI too large. Max strategic sector is ~55 km x 55 km.")
|
||||
|
||||
CACHE_DIR.mkdir(parents=True, exist_ok=True)
|
||||
engine = S2TruckEngine(
|
||||
cache_dir=str(CACHE_DIR),
|
||||
detection_dir=str(DETECTION_CROP_DIR),
|
||||
)
|
||||
config = build_sh_config()
|
||||
|
||||
progress(f"Road discovery for {label}", 10)
|
||||
roads = engine.fetch_roads(bbox)
|
||||
if roads.empty:
|
||||
return store_analysis_result(
|
||||
preset_id,
|
||||
label=label,
|
||||
bbox=bbox,
|
||||
country=country,
|
||||
category=category,
|
||||
road_count=0,
|
||||
frame_count=0,
|
||||
detections=[],
|
||||
status="error",
|
||||
error="No major roads found in AOI.",
|
||||
)
|
||||
|
||||
progress(f"Found {len(roads)} road segments — querying Copernicus catalog", 25)
|
||||
sh_bbox = BBox(bbox=[min_lon, min_lat, max_lon, max_lat], crs=CRS.WGS84)
|
||||
catalog = SentinelHubCatalog(config=config)
|
||||
end_date = datetime.utcnow()
|
||||
start_date = end_date - timedelta(days=max(1, months) * 30)
|
||||
cdse_collection = DataCollection.SENTINEL2_L2A.define_from(
|
||||
"s2l2a",
|
||||
service_url=config.sh_base_url,
|
||||
)
|
||||
search_results = list(
|
||||
catalog.search(
|
||||
cdse_collection,
|
||||
bbox=sh_bbox,
|
||||
datetime=(
|
||||
f"{start_date.strftime('%Y-%m-%dT00:00:00Z')}/"
|
||||
f"{end_date.strftime('%Y-%m-%dT23:59:59Z')}"
|
||||
),
|
||||
filter="eo:cloud_cover < 60",
|
||||
fields={"include": ["properties.datetime", "id"], "exclude": []},
|
||||
)
|
||||
)
|
||||
unique_scenes: dict[str, Any] = {}
|
||||
for res in search_results:
|
||||
date_key = res["properties"]["datetime"][:10]
|
||||
if date_key not in unique_scenes:
|
||||
unique_scenes[date_key] = res
|
||||
final_obs = [unique_scenes[d] for d in sorted(unique_scenes.keys(), reverse=True)]
|
||||
final_obs = final_obs[: max(1, max_frames)]
|
||||
if not final_obs:
|
||||
return store_analysis_result(
|
||||
preset_id,
|
||||
label=label,
|
||||
bbox=bbox,
|
||||
country=country,
|
||||
category=category,
|
||||
road_count=len(roads),
|
||||
frame_count=0,
|
||||
detections=[],
|
||||
status="error",
|
||||
error=f"No clear imagery found in the last {months} months.",
|
||||
)
|
||||
|
||||
def _fetch_frame(idx: int, res_obs: dict[str, Any]):
|
||||
try:
|
||||
date_str = res_obs["properties"]["datetime"]
|
||||
req_sh = SentinelHubRequest(
|
||||
evalscript=_EVALSCRIPT,
|
||||
input_data=[
|
||||
SentinelHubRequest.input_data(
|
||||
data_collection=cdse_collection,
|
||||
time_interval=(date_str, date_str),
|
||||
)
|
||||
],
|
||||
responses=[SentinelHubRequest.output_response("default", MimeType.TIFF)],
|
||||
bbox=sh_bbox,
|
||||
config=config,
|
||||
)
|
||||
data_list = req_sh.get_data()
|
||||
if not data_list:
|
||||
return idx, date_str, None
|
||||
return idx, date_str, data_list[0]
|
||||
except Exception as exc:
|
||||
logger.error("Sentinel frame %s failed: %s", idx, exc)
|
||||
return idx, None, None
|
||||
|
||||
progress(f"Seed frame 1/{len(final_obs)}", 35)
|
||||
_, seed_ts, seed_data = _fetch_frame(0, final_obs[0])
|
||||
if seed_data is None:
|
||||
return store_analysis_result(
|
||||
preset_id,
|
||||
label=label,
|
||||
bbox=bbox,
|
||||
country=country,
|
||||
category=category,
|
||||
road_count=len(roads),
|
||||
frame_count=0,
|
||||
detections=[],
|
||||
status="error",
|
||||
error="Failed to acquire seed spectral data.",
|
||||
)
|
||||
|
||||
roads_buf = roads.to_crs(epsg=3857).buffer(20).to_crs(epsg=4326)
|
||||
h, w = seed_data.shape[:2]
|
||||
trans = rio_transform.from_bounds(min_lon, min_lat, max_lon, max_lat, w, h)
|
||||
road_mask = rio_features.rasterize(
|
||||
[(geom.__geo_interface__, 1) for geom in roads_buf.geometry],
|
||||
out_shape=(h, w),
|
||||
transform=trans,
|
||||
fill=0,
|
||||
all_touched=True,
|
||||
)
|
||||
|
||||
detections: list[dict[str, Any]] = []
|
||||
detections.extend(engine.detect_trucks(seed_data, bbox, final_obs[0]["properties"]["datetime"], road_mask))
|
||||
|
||||
if len(final_obs) > 1:
|
||||
progress(f"Parallel frames ({len(final_obs) - 1} remaining)", 45)
|
||||
with ThreadPoolExecutor(max_workers=3, thread_name_prefix="road-corridor") as executor:
|
||||
futures = {
|
||||
executor.submit(_fetch_frame, i, final_obs[i]): i for i in range(1, len(final_obs))
|
||||
}
|
||||
done = 1
|
||||
for future in as_completed(futures):
|
||||
idx, date_str, frame_data = future.result()
|
||||
done += 1
|
||||
if frame_data is not None and date_str:
|
||||
detections.extend(engine.detect_trucks(frame_data, bbox, date_str, road_mask))
|
||||
progress(f"Frame {done}/{len(final_obs)}", 45 + int((done / len(final_obs)) * 50))
|
||||
|
||||
progress(f"Complete — {len(detections)} truck signatures", 100)
|
||||
return store_analysis_result(
|
||||
preset_id,
|
||||
label=label,
|
||||
bbox=bbox,
|
||||
country=country,
|
||||
category=category,
|
||||
road_count=len(roads),
|
||||
frame_count=len(final_obs),
|
||||
detections=detections,
|
||||
status="ok",
|
||||
)
|
||||
|
||||
|
||||
def analyze_preset(preset_id: str, progress_cb: ProgressCb | None = None) -> dict[str, Any]:
|
||||
from .presets import get_preset
|
||||
|
||||
preset = get_preset(preset_id)
|
||||
if preset is None:
|
||||
raise KeyError(f"Unknown preset: {preset_id}")
|
||||
return analyze_corridor(
|
||||
preset_id=preset["id"],
|
||||
label=preset["label"],
|
||||
bbox=preset["bbox"],
|
||||
country=preset["country"],
|
||||
category=preset["category"],
|
||||
progress_cb=progress_cb,
|
||||
)
|
||||
@@ -0,0 +1,59 @@
|
||||
"""Preset freight / chokepoint corridors for scheduled trend analysis."""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TypedDict
|
||||
|
||||
|
||||
class CorridorPreset(TypedDict):
|
||||
id: str
|
||||
label: str
|
||||
bbox: list[float] # [min_lat, min_lon, max_lat, max_lon]
|
||||
country: str
|
||||
category: str
|
||||
|
||||
|
||||
# Bboxes are small (~5–10 km) highway segments suitable for 10 m Sentinel-2 analysis.
|
||||
CORRIDOR_PRESETS: list[CorridorPreset] = [
|
||||
{
|
||||
"id": "laredo_i35",
|
||||
"label": "Laredo I-35 (US–Mexico freight)",
|
||||
"bbox": [27.48, -99.58, 27.54, -99.48],
|
||||
"country": "USA / Mexico",
|
||||
"category": "border_crossing",
|
||||
},
|
||||
{
|
||||
"id": "bandar_abbas_feeder",
|
||||
"label": "Bandar Abbas port feeder (Highway 71)",
|
||||
"bbox": [27.12, 56.22, 27.22, 56.38],
|
||||
"country": "Iran",
|
||||
"category": "port_feeder",
|
||||
},
|
||||
{
|
||||
"id": "rotterdam_a15",
|
||||
"label": "Rotterdam A15 port feeder",
|
||||
"bbox": [51.88, 4.42, 51.96, 4.58],
|
||||
"country": "Netherlands",
|
||||
"category": "port_feeder",
|
||||
},
|
||||
{
|
||||
"id": "mombasa_nairobi_a109",
|
||||
"label": "Mombasa–Nairobi A109 corridor",
|
||||
"bbox": [-4.10, 39.55, -1.20, 37.00],
|
||||
"country": "Kenya",
|
||||
"category": "trade_corridor",
|
||||
},
|
||||
{
|
||||
"id": "braunschweig_a7",
|
||||
"label": "Braunschweig A7 (validation)",
|
||||
"bbox": [52.25, 10.45, 52.32, 10.55],
|
||||
"country": "Germany",
|
||||
"category": "validation",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
def get_preset(preset_id: str) -> CorridorPreset | None:
|
||||
for preset in CORRIDOR_PRESETS:
|
||||
if preset["id"] == preset_id:
|
||||
return preset
|
||||
return None
|
||||
@@ -0,0 +1,731 @@
|
||||
"""S2 truck motion detection core (DrishX / Fisser et al. 2022 — see third_party/drishx/NOTICE.md)."""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import pickle
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
import imageio.v3 as imageio
|
||||
import numpy as np
|
||||
import requests
|
||||
from requests.adapters import HTTPAdapter
|
||||
from shapely.geometry import LineString
|
||||
from urllib3.util.retry import Retry
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
SECONDS_OFFSET_B02_B04 = 1.01
|
||||
|
||||
OVERPASS_MIRRORS = [
|
||||
"https://lz4.overpass-api.de/api/interpreter",
|
||||
"https://z.overpass-api.de/api/interpreter",
|
||||
"https://overpass.osm.ch/api/interpreter",
|
||||
"https://overpass-api.de/api/interpreter",
|
||||
]
|
||||
|
||||
_session = requests.Session()
|
||||
_retry = Retry(
|
||||
total=2,
|
||||
backoff_factor=1.0,
|
||||
status_forcelist=[429, 500, 502, 503, 504],
|
||||
allowed_methods=["GET", "POST"],
|
||||
)
|
||||
_adapter = HTTPAdapter(max_retries=_retry)
|
||||
_session.mount("http://", _adapter)
|
||||
_session.mount("https://", _adapter)
|
||||
|
||||
|
||||
def _configure_osmnx(data_dir: str) -> None:
|
||||
import osmnx as ox
|
||||
|
||||
ox.settings.requests_session = _session
|
||||
ox.settings.requests_timeout = 30
|
||||
ox.settings.overpass_rate_limit = False
|
||||
ox.settings.max_query_area_size = 1_000_000_000_000
|
||||
ox.settings.log_console = False
|
||||
ox.settings.use_cache = True
|
||||
ox.settings.cache_folder = os.path.join(data_dir, "osm_cache")
|
||||
|
||||
|
||||
def _default_rf_model_path() -> str:
|
||||
return str(Path(__file__).resolve().parents[2] / "data" / "drishx" / "rf_model.pickle")
|
||||
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Helper math — mirrors S2TD.array_utils.math
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
def normalized_ratio(a, b):
|
||||
"""(a - b) / (a + b), safe division."""
|
||||
denom = a + b
|
||||
with np.errstate(divide="ignore", invalid="ignore"):
|
||||
result = np.where(denom != 0, (a - b) / denom, 0.0)
|
||||
return result.astype(np.float32)
|
||||
|
||||
|
||||
def rescale_s2(bands):
|
||||
"""Rescale Sentinel-2 L2A reflectance values (typically 0–10000 int) to 0–1 float."""
|
||||
bands = bands.astype(np.float32)
|
||||
if np.nanmax(bands) > 10: # likely DN scale
|
||||
bands /= 10000.0
|
||||
return bands
|
||||
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Array subset — exact replica of S2TD.pick_arr_subset
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
def pick_arr_subset(arr, y, x, size):
|
||||
"""Pick a size×size window centred on (y, x) from a 2D or 3D array."""
|
||||
size_low = size // 2
|
||||
size_up = size // 2
|
||||
if size_low + size_up < size:
|
||||
size_up += 1
|
||||
ymin = max(0, y - size_low)
|
||||
ymax = max(0, y + size_up)
|
||||
xmin = max(0, x - size_low)
|
||||
xmax = max(0, x + size_up)
|
||||
if arr.ndim == 2:
|
||||
return arr[ymin:ymax, xmin:xmax]
|
||||
elif arr.ndim == 3:
|
||||
return arr[:, ymin:ymax, xmin:xmax]
|
||||
return arr
|
||||
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Feature stack — exact 7 features as in S2TD._build_feature_stack (Table 1)
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
def build_feature_stack(data):
|
||||
"""
|
||||
Build the 7-feature stack from Sentinel-2 bands.
|
||||
|
||||
Input `data` shape: (H, W, 5) with channels [B04(R), B03(G), B02(B), B08(NIR), CLM].
|
||||
|
||||
Feature order (Table 1, Fisser et al. 2022):
|
||||
0: variance of (B04, B03, B02)
|
||||
1: normalized_ratio(B04, B02) — red / blue
|
||||
2: normalized_ratio(B03, B02) — green / blue
|
||||
3: B04 - mean(B04)
|
||||
4: B03 - mean(B03)
|
||||
5: B02 - mean(B02)
|
||||
6: B08 - mean(B08)
|
||||
"""
|
||||
R = data[:, :, 0].astype(np.float32) # B04
|
||||
G = data[:, :, 1].astype(np.float32) # B03
|
||||
B = data[:, :, 2].astype(np.float32) # B02
|
||||
NIR = data[:, :, 3].astype(np.float32) # B08
|
||||
CLM = data[:, :, 4]
|
||||
|
||||
# Rescale if needed
|
||||
bands = np.stack([R, G, B, NIR], axis=0)
|
||||
bands = rescale_s2(bands)
|
||||
R, G, B, NIR = bands[0], bands[1], bands[2], bands[3]
|
||||
|
||||
# Cloud mask → NaN
|
||||
cloud = CLM > 0
|
||||
R[cloud] = np.nan
|
||||
G[cloud] = np.nan
|
||||
B[cloud] = np.nan
|
||||
NIR[cloud] = np.nan
|
||||
|
||||
H, W = R.shape
|
||||
fs = np.zeros((7, H, W), dtype=np.float32)
|
||||
|
||||
# Check for any valid data to avoid "Mean of empty slice" warnings
|
||||
if np.any(~cloud):
|
||||
import warnings
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("ignore", category=RuntimeWarning)
|
||||
# Feature 0: variance of visible bands
|
||||
fs[0] = np.nanvar(np.stack([R, G, B], axis=0), axis=0, ddof=0)
|
||||
|
||||
# Features 1–2: normalized ratios
|
||||
fs[1] = normalized_ratio(R, B)
|
||||
fs[2] = normalized_ratio(G, B)
|
||||
|
||||
# Features 3–6: mean-centered bands
|
||||
fs[3] = R - np.nanmean(R)
|
||||
fs[4] = G - np.nanmean(G)
|
||||
fs[5] = B - np.nanmean(B)
|
||||
fs[6] = NIR - np.nanmean(NIR)
|
||||
else:
|
||||
# All pixels are cloud-masked
|
||||
fs.fill(np.nan)
|
||||
|
||||
# Ensure NaN consistency
|
||||
nan_mask = np.isnan(fs[3])
|
||||
fs[:, nan_mask] = np.nan
|
||||
|
||||
return {
|
||||
"feature_stack": fs,
|
||||
"bands": {"R": R, "G": G, "B": B, "NIR": NIR},
|
||||
"cloud_mask": cloud,
|
||||
}
|
||||
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# RF Model loading
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
# Path to the trained Random Forest model from S2TruckDetect
|
||||
RF_MODEL_PATH = _default_rf_model_path()
|
||||
_rf_model = None
|
||||
|
||||
|
||||
def load_rf_model(path=None):
|
||||
"""Load the trained RF model from pickle. Returns None if not found."""
|
||||
global _rf_model
|
||||
p = path or RF_MODEL_PATH
|
||||
if _rf_model is not None:
|
||||
return _rf_model
|
||||
if os.path.isfile(p):
|
||||
try:
|
||||
_rf_model = pickle.load(open(p, "rb"))
|
||||
logger.info(f"Loaded trained RF model from {p}")
|
||||
return _rf_model
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to load RF model from {p}: {e}")
|
||||
else:
|
||||
logger.warning(f"RF model not found at {p} — will use proxy classifier (lower accuracy)")
|
||||
return None
|
||||
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Classification — real RF (preferred) or proxy fallback
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
def rf_classify(feature_stack, road_mask, rf_model):
|
||||
"""
|
||||
Classify pixels using the trained Random Forest model.
|
||||
Exact replica of S2TD._predict + _postprocess_prediction.
|
||||
|
||||
:param feature_stack: (7, H, W) feature array
|
||||
:param road_mask: (H, W) binary road mask
|
||||
:param rf_model: trained sklearn RandomForestClassifier
|
||||
:return: (probabilities (4, H, W), prediction (H, W) int8)
|
||||
"""
|
||||
H, W = feature_stack.shape[1], feature_stack.shape[2]
|
||||
|
||||
# Reshape to (n_pixels, 7) for sklearn
|
||||
vars_reshaped = []
|
||||
for band_idx in range(feature_stack.shape[0]):
|
||||
vars_reshaped.append(feature_stack[band_idx].flatten())
|
||||
vars_reshaped = np.array(vars_reshaped).swapaxes(0, 1) # (n_pixels, 7)
|
||||
|
||||
# Build NaN mask — exclude NaN and Inf pixels
|
||||
nan_mask_flat = np.zeros_like(vars_reshaped)
|
||||
for var_idx in range(vars_reshaped.shape[1]):
|
||||
nan_mask_flat[:, var_idx] = ~np.isnan(vars_reshaped[:, var_idx])
|
||||
not_nan = (np.nanmin(nan_mask_flat, axis=1).astype(bool)
|
||||
& np.min(np.isfinite(vars_reshaped), axis=1).astype(bool))
|
||||
|
||||
# Run RF predict_proba on valid pixels only
|
||||
if not np.any(not_nan):
|
||||
# Graceful return if no valid pixels found (e.g., all cloud masked)
|
||||
probabilities_shaped = np.zeros((4, H, W), dtype=np.float32)
|
||||
classification = np.zeros((H, W), dtype=np.int8)
|
||||
return probabilities_shaped, classification
|
||||
|
||||
predictions_flat = rf_model.predict_proba(vars_reshaped[not_nan])
|
||||
|
||||
# Map probabilities back to spatial grid
|
||||
n_classes = predictions_flat.shape[1]
|
||||
probabilities_shaped = np.zeros((n_classes, H * W), dtype=np.float32)
|
||||
for idx in range(n_classes):
|
||||
probabilities_shaped[idx, not_nan] = predictions_flat[:, idx]
|
||||
|
||||
probabilities_shaped = probabilities_shaped.reshape((n_classes, H, W))
|
||||
|
||||
# Zero out NaN positions
|
||||
nan_2d = np.isnan(feature_stack[0])
|
||||
probabilities_shaped[:, nan_2d] = 0
|
||||
|
||||
# Post-process: suppress low-confidence background (exact S2TD logic)
|
||||
probabilities_shaped[1][probabilities_shaped[1] < 0.75] = 0
|
||||
|
||||
classification = np.nanargmax(probabilities_shaped, axis=0).astype(np.int8) + 1
|
||||
classification[np.max(probabilities_shaped, axis=0) == 0] = 0
|
||||
classification[nan_2d] = 0
|
||||
|
||||
# Apply road mask
|
||||
rm = road_mask.astype(bool)
|
||||
classification[~rm] = 0
|
||||
|
||||
return probabilities_shaped, classification
|
||||
|
||||
|
||||
def proxy_classify(feature_stack, road_mask):
|
||||
"""
|
||||
Heuristic proxy when RF model is unavailable. Lower accuracy.
|
||||
|
||||
Produces:
|
||||
probabilities: (4, H, W) — class probs for [background, blue, green, red]
|
||||
prediction: (H, W) — int8 labels {0=nan, 1=background, 2=blue, 3=green, 4=red}
|
||||
"""
|
||||
fs = feature_stack # (7, H, W)
|
||||
H, W = fs.shape[1], fs.shape[2]
|
||||
probs = np.zeros((4, H, W), dtype=np.float32)
|
||||
|
||||
centered_R = fs[3]
|
||||
centered_G = fs[4]
|
||||
centered_B = fs[5]
|
||||
var_feat = fs[0]
|
||||
nratio_rb = fs[1]
|
||||
nratio_gb = fs[2]
|
||||
|
||||
rm = road_mask.astype(bool)
|
||||
nan_mask = np.isnan(centered_R)
|
||||
|
||||
blue_score = np.clip(-nratio_rb * 2 + centered_B * 5 + var_feat * 10, 0, None)
|
||||
blue_score[~rm | nan_mask] = 0
|
||||
|
||||
green_score = np.clip(nratio_gb * 2 + centered_G * 5 + var_feat * 10, 0, None)
|
||||
green_score[~rm | nan_mask] = 0
|
||||
|
||||
red_score = np.clip(nratio_rb * 2 + centered_R * 5 + var_feat * 10, 0, None)
|
||||
red_score[~rm | nan_mask] = 0
|
||||
|
||||
total = blue_score + green_score + red_score + 1e-8
|
||||
probs[1] = blue_score / total
|
||||
probs[2] = green_score / total
|
||||
probs[3] = red_score / total
|
||||
probs[0] = 1.0 - np.max(probs[1:], axis=0)
|
||||
|
||||
probs[0][probs[0] < 0.75] = 0
|
||||
|
||||
classification = np.nanargmax(probs, axis=0).astype(np.int8) + 1
|
||||
classification[np.max(probs, axis=0) == 0] = 0
|
||||
classification[nan_mask] = 0
|
||||
classification[~rm] = 0
|
||||
|
||||
return probs, classification
|
||||
|
||||
|
||||
def classify(feature_stack, road_mask, rf_model=None):
|
||||
"""
|
||||
Unified classifier entry point.
|
||||
Uses trained RF if model is provided, otherwise falls back to proxy.
|
||||
"""
|
||||
if rf_model is not None:
|
||||
logger.debug("Using trained RF model for classification")
|
||||
return rf_classify(feature_stack, road_mask, rf_model)
|
||||
else:
|
||||
logger.debug("Using proxy classifier (no RF model loaded)")
|
||||
return proxy_classify(feature_stack, road_mask)
|
||||
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Object extraction — faithful port of S2TD ObjectExtractor
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
class ObjectExtractor:
|
||||
"""
|
||||
Extracts truck objects from the RF prediction raster using recursive
|
||||
neighbourhood clustering, matching the S2TD reference implementation.
|
||||
"""
|
||||
|
||||
def __init__(self, probabilities, lat_arr, lon_arr):
|
||||
"""
|
||||
:param probabilities: (4, H, W) class probabilities
|
||||
:param lat_arr: 1-D array of latitude per row
|
||||
:param lon_arr: 1-D array of longitude per column
|
||||
"""
|
||||
self.probabilities = probabilities
|
||||
self.lat = lat_arr
|
||||
self.lon = lon_arr
|
||||
|
||||
def extract(self, predictions_arr):
|
||||
"""Main extraction loop over all blue (class 2) seed pixels."""
|
||||
preds = predictions_arr.copy()
|
||||
probs = self.probabilities.copy()
|
||||
|
||||
preds[preds == 1] = 0 # zero out background
|
||||
blue_ys, blue_xs = np.where(preds == 2)
|
||||
detections = []
|
||||
sub_size = 9
|
||||
|
||||
for i in range(len(blue_ys)):
|
||||
y_blue, x_blue = int(blue_ys[i]), int(blue_xs[i])
|
||||
if preds[y_blue, x_blue] == 0:
|
||||
continue
|
||||
|
||||
subset_9 = pick_arr_subset(preds, y_blue, x_blue, sub_size).copy()
|
||||
subset_3 = pick_arr_subset(preds, y_blue, x_blue, 3).copy()
|
||||
subset_9_probs = pick_arr_subset(probs, y_blue, x_blue, sub_size).copy()
|
||||
|
||||
half_idx_y = y_blue if subset_9.shape[0] < sub_size else subset_9.shape[0] // 2
|
||||
half_idx_x = x_blue if subset_9.shape[1] < sub_size else subset_9.shape[1] // 2
|
||||
try:
|
||||
current_value = subset_9[half_idx_y, half_idx_x]
|
||||
except IndexError:
|
||||
half_idx_y, half_idx_x = sub_size // 2, sub_size // 2
|
||||
current_value = subset_9[half_idx_y, half_idx_x]
|
||||
|
||||
new_value = 100
|
||||
if not all(v in subset_9 for v in [2, 3, 4]):
|
||||
continue
|
||||
|
||||
cluster, seen_idx, seen_vals, _ = self._cluster_array(
|
||||
arr=subset_9, probs=subset_9_probs,
|
||||
point=[half_idx_y, half_idx_x],
|
||||
new_value=new_value, current_value=current_value,
|
||||
yet_seen_indices=[], yet_seen_values=[],
|
||||
skipped_one=False,
|
||||
)
|
||||
|
||||
if np.count_nonzero(cluster == new_value) < 3:
|
||||
continue
|
||||
|
||||
det = self._postprocess_cluster(
|
||||
cluster, preds, probs, subset_3,
|
||||
y_blue, x_blue,
|
||||
half_idx_y, half_idx_x,
|
||||
new_value,
|
||||
)
|
||||
if det is not None:
|
||||
preds = det["updated_preds"]
|
||||
detections.append(det["detection"])
|
||||
|
||||
return detections
|
||||
|
||||
def _cluster_array(self, arr, probs, point, new_value, current_value,
|
||||
yet_seen_indices, yet_seen_values, skipped_one):
|
||||
"""Recursive neighbourhood clustering — matches S2TD._cluster_array."""
|
||||
if len(yet_seen_indices) == 0:
|
||||
yet_seen_indices.append(point)
|
||||
yet_seen_values.append(current_value)
|
||||
|
||||
arr_mod = arr.copy()
|
||||
arr_mod[point[0], point[1]] = 0
|
||||
|
||||
window_3x3 = pick_arr_subset(arr_mod, point[0], point[1], 3).copy()
|
||||
if window_3x3.shape[0] >= 2 and window_3x3.shape[1] >= 2:
|
||||
cy = min(1, window_3x3.shape[0] - 1)
|
||||
cx = min(1, window_3x3.shape[1] - 1)
|
||||
if window_3x3[cy, cx] == 2:
|
||||
window_3x3[window_3x3 == 4] = 1 # eliminate reds near blue
|
||||
|
||||
y, x = point[0], point[1]
|
||||
window_3x3_probs = pick_arr_subset(probs, y, x, 3)
|
||||
|
||||
windows = [window_3x3]
|
||||
windows_probs = [window_3x3_probs]
|
||||
if current_value == 4 or skipped_one:
|
||||
windows = windows[0:1]
|
||||
|
||||
ys, xs = np.array([], dtype=int), np.array([], dtype=int)
|
||||
window_idx = 0
|
||||
offset_y, offset_x = 0, 0
|
||||
|
||||
while len(ys) == 0 and window_idx < len(windows):
|
||||
window = windows[window_idx]
|
||||
window_p = windows_probs[window_idx]
|
||||
offset_y = window.shape[0] // 2
|
||||
offset_x = window.shape[1] // 2
|
||||
|
||||
go_next = (current_value + 1) in window or current_value == 2
|
||||
target_value = current_value + 1 if go_next else current_value
|
||||
match = window == target_value
|
||||
if np.count_nonzero(match) == 0:
|
||||
target_value = current_value
|
||||
match = window == target_value
|
||||
|
||||
ys_found, xs_found = np.where(match)
|
||||
|
||||
# Probability-based tie-breaking
|
||||
if len(ys_found) > 1 and window_p.ndim == 3 and window_p.shape[0] > (target_value - 1):
|
||||
wp_target = window_p[target_value - 1] * match
|
||||
max_prob_mask = (wp_target == np.max(wp_target))
|
||||
ys_found, xs_found = np.where(max_prob_mask)
|
||||
|
||||
ys, xs = ys_found, xs_found
|
||||
window_idx += 1
|
||||
|
||||
ymin_w = max(0, point[0] - offset_y)
|
||||
xmin_w = max(0, point[1] - offset_x)
|
||||
|
||||
for y_local, x_local in zip(ys, xs):
|
||||
ny, nx = ymin_w + int(y_local), xmin_w + int(x_local)
|
||||
if [ny, nx] in yet_seen_indices:
|
||||
continue
|
||||
if ny < 0 or ny >= arr.shape[0] or nx < 0 or nx >= arr.shape[1]:
|
||||
continue
|
||||
try:
|
||||
cv = arr[ny, nx]
|
||||
except IndexError:
|
||||
continue
|
||||
|
||||
# Red already seen but this is green or blue → skip
|
||||
if 4 in yet_seen_values and cv <= 3:
|
||||
continue
|
||||
|
||||
arr_mod[ny, nx] = new_value
|
||||
yet_seen_indices.append([ny, nx])
|
||||
yet_seen_values.append(cv)
|
||||
|
||||
# Guard: avoid picking many more reds than blues and greens
|
||||
n_blue = sum(1 for v in yet_seen_values if v == 2)
|
||||
n_green = sum(1 for v in yet_seen_values if v == 3)
|
||||
n_red = sum(1 for v in yet_seen_values if v == 4)
|
||||
if n_red > n_blue and n_red > n_green:
|
||||
break
|
||||
|
||||
arr_mod, yet_seen_indices, yet_seen_values, skipped_one = self._cluster_array(
|
||||
arr_mod, probs, [ny, nx], new_value, cv,
|
||||
yet_seen_indices, yet_seen_values, skipped_one,
|
||||
)
|
||||
|
||||
arr_mod[point[0], point[1]] = new_value
|
||||
return arr_mod, yet_seen_indices, yet_seen_values, skipped_one
|
||||
|
||||
def _postprocess_cluster(self, cluster, preds_copy, probs, subset_3,
|
||||
y_blue, x_blue, half_idx_y, half_idx_x,
|
||||
new_value):
|
||||
"""Validate cluster and produce a detection dict — mirrors S2TD._postprocess_cluster."""
|
||||
# Add neighbouring blues from the 3×3 window
|
||||
ys_ba, xs_ba = np.where(subset_3 == 2)
|
||||
ys_ba = ys_ba + half_idx_y - 1
|
||||
xs_ba = xs_ba + half_idx_x - 1
|
||||
for yb, xb in zip(ys_ba, xs_ba):
|
||||
yb_c = int(np.clip(yb, 0, cluster.shape[0] - 1))
|
||||
xb_c = int(np.clip(xb, 0, cluster.shape[1] - 1))
|
||||
cluster[yb_c, xb_c] = new_value
|
||||
|
||||
cluster[cluster != new_value] = 0
|
||||
cys, cxs = np.where(cluster == new_value)
|
||||
if len(cys) == 0:
|
||||
return None
|
||||
|
||||
# Map subset coords back to full array
|
||||
ymin_sub = int(np.clip(y_blue - half_idx_y, 0, np.inf))
|
||||
xmin_sub = int(np.clip(x_blue - half_idx_x, 0, np.inf))
|
||||
cys_full = cys + ymin_sub
|
||||
cxs_full = cxs + xmin_sub
|
||||
|
||||
ymin = int(np.min(cys_full))
|
||||
xmin = int(np.min(cxs_full))
|
||||
ymax = int(np.max(cys_full)) + 1 # +1: box extends to upper bound of pixel
|
||||
xmax = int(np.max(cxs_full)) + 1
|
||||
|
||||
H, W = preds_copy.shape
|
||||
ymin, ymax = max(0, ymin), min(H, ymax)
|
||||
xmin, xmax = max(0, xmin), min(W, xmax)
|
||||
|
||||
box_preds = preds_copy[ymin:ymax, xmin:xmax].copy()
|
||||
box_probs = probs[1:, ymin:ymax, xmin:xmax].copy() # classes 2,3,4 → indices 0,1,2
|
||||
|
||||
# Spectral probability scores (exact S2TD logic)
|
||||
max_probs = []
|
||||
for cls_offset, cls_val in enumerate([2, 3, 4]):
|
||||
mask = (box_preds == cls_val)
|
||||
vals = box_probs[cls_offset] * mask
|
||||
mp = float(np.nanmax(vals)) if np.any(mask) else 0.0
|
||||
max_probs.append(mp)
|
||||
|
||||
mean_max_spectral_probability = float(np.nanmean(max_probs))
|
||||
mean_spectral_probability = float(np.nanmean(np.nanmax(box_probs, axis=0)))
|
||||
|
||||
# Validation checks
|
||||
all_given = all(v in box_preds for v in [2, 3, 4])
|
||||
large_enough = box_preds.shape[0] > 2 or box_preds.shape[1] > 2
|
||||
too_large = box_preds.shape[0] > 5 or box_preds.shape[1] > 5
|
||||
|
||||
if too_large or not all_given or not large_enough:
|
||||
return None
|
||||
|
||||
# Score: TWO terms — matches reference
|
||||
score = mean_max_spectral_probability + mean_spectral_probability
|
||||
if score <= 1.2:
|
||||
return None
|
||||
|
||||
# Direction (blue → red vector)
|
||||
by, bx = np.where(box_preds == 2)
|
||||
ry, rx = np.where(box_preds == 4)
|
||||
blue_idx = np.array([by[0], bx[0]], dtype=np.int8)
|
||||
red_idx = np.array([ry[0], rx[0]], dtype=np.int8)
|
||||
vector = (blue_idx - red_idx) * np.array([1, -1], dtype=np.int8)
|
||||
heading = float(np.degrees(np.arctan2(vector[1], vector[0])) % 360)
|
||||
|
||||
# Speed
|
||||
diameter = max(box_preds.shape) * 10 - 10
|
||||
speed_kmh = float(np.sqrt(diameter * 20) / SECONDS_OFFSET_B02_B04 * 3.6)
|
||||
|
||||
# Geo-coordinates (centre of detection box)
|
||||
lat_centre = float((self.lat[ymin] + self.lat[min(ymax, len(self.lat) - 1)]) / 2)
|
||||
lon_centre = float((self.lon[xmin] + self.lon[min(xmax, len(self.lon) - 1)]) / 2)
|
||||
|
||||
# Zero out detected pixels to prevent re-detection
|
||||
preds_copy[ymin:ymax, xmin:xmax] *= np.zeros_like(box_preds)
|
||||
# Also zero 3×3 around blue pixels
|
||||
blue_in_box = np.where(box_preds == 2)
|
||||
for yb, xb in zip(blue_in_box[0], blue_in_box[1]):
|
||||
y0, y1 = max(0, ymin + yb - 1), min(H, ymin + yb + 2)
|
||||
x0, x1 = max(0, xmin + xb - 1), min(W, xmin + xb + 2)
|
||||
preds_copy[y0:y1, x0:x1] *= (preds_copy[y0:y1, x0:x1] != 2).astype(np.int8)
|
||||
|
||||
crop_id = f"truck_{int(time.time() * 1000)}_{ymin}_{xmin}.png"
|
||||
|
||||
return {
|
||||
"updated_preds": preds_copy,
|
||||
"detection": {
|
||||
"lat": lat_centre,
|
||||
"lon": lon_centre,
|
||||
"confidence": float(min(score / 2.4, 1.0)),
|
||||
"s_score": round(score, 3),
|
||||
"speed_kmh": round(speed_kmh, 1),
|
||||
"heading": round(heading, 1),
|
||||
"heading_desc": self._direction_to_compass(heading),
|
||||
"id": crop_id,
|
||||
"image_url": f"/detections/{crop_id}",
|
||||
"box_shape": list(box_preds.shape),
|
||||
"max_probs": {"blue": max_probs[0], "green": max_probs[1], "red": max_probs[2]},
|
||||
},
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _direction_to_compass(deg):
|
||||
bins = np.arange(0, 359, 45, dtype=np.float32)
|
||||
labels = ["N", "NE", "E", "SE", "S", "SW", "W", "NW"]
|
||||
return labels[int(np.argmin(np.abs(bins - deg)))]
|
||||
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# ARGUS Engine
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
class S2TruckEngine:
|
||||
def __init__(self, *, cache_dir: str, detection_dir: str, rf_model_path: str | None = None):
|
||||
self.cache_dir = cache_dir
|
||||
self.detection_dir = detection_dir
|
||||
os.makedirs(self.detection_dir, exist_ok=True)
|
||||
_configure_osmnx(cache_dir)
|
||||
self.rf_model = load_rf_model(rf_model_path)
|
||||
|
||||
def fetch_roads(self, bbox_coords, progress_cb=None):
|
||||
"""Fetch major roads with automatic mirror rotation and fallbacks."""
|
||||
import geopandas as gpd
|
||||
import osmnx as ox
|
||||
|
||||
def log(msg, level="info", pct=None):
|
||||
if level == "info":
|
||||
logger.info(msg)
|
||||
elif level == "warn":
|
||||
logger.warning(msg)
|
||||
if progress_cb:
|
||||
progress_cb(msg, pct)
|
||||
|
||||
min_lat, min_lon, max_lat, max_lon = bbox_coords
|
||||
center_lat = (min_lat + max_lat) / 2
|
||||
center_lon = (min_lon + max_lon) / 2
|
||||
|
||||
lat_span = (max_lat - min_lat) * 111000
|
||||
lon_span = (max_lon - min_lon) * 111000 * np.cos(np.radians(center_lat))
|
||||
dist_m = int(max(lat_span, lon_span) * 0.6) + 1000
|
||||
|
||||
log(f"Starting road discovery (ROI: {center_lat:.4f}, {center_lon:.4f})", pct=5)
|
||||
|
||||
for i, mirror in enumerate(OVERPASS_MIRRORS):
|
||||
log(f"Trying mirror {i+1}/{len(OVERPASS_MIRRORS)}: {mirror}", pct=10 + i * 5)
|
||||
ox.settings.overpass_url = mirror
|
||||
try:
|
||||
graph = ox.graph_from_point(
|
||||
(center_lat, center_lon), dist=dist_m,
|
||||
network_type="drive", simplify=True,
|
||||
retain_all=False, truncate_by_edge=True,
|
||||
)
|
||||
roads = ox.graph_to_gdfs(graph, nodes=False)
|
||||
major_types = [
|
||||
"motorway", "trunk", "primary", "secondary",
|
||||
"motorway_link", "trunk_link", "primary_link",
|
||||
]
|
||||
roads = roads[roads["highway"].isin(major_types)].copy()
|
||||
if not roads.empty:
|
||||
logger.info(f"Fetched {len(roads)} major roads from {mirror}")
|
||||
return roads
|
||||
except Exception as e:
|
||||
logger.warning(f"Mirror {mirror} failed: {e}")
|
||||
time.sleep(1)
|
||||
|
||||
# Raw Overpass fallback
|
||||
logger.warning("All mirrors failed. Trying raw Overpass query.")
|
||||
try:
|
||||
query = f"""
|
||||
[out:json][timeout:60];
|
||||
(way["highway"~"motorway|trunk|primary"]({min_lat},{min_lon},{max_lat},{max_lon}););
|
||||
out body; >; out skel qt;
|
||||
"""
|
||||
resp = requests.post(OVERPASS_MIRRORS[0], data={"data": query}, timeout=60)
|
||||
if resp.status_code == 200:
|
||||
data = resp.json()
|
||||
nodes = {n["id"]: (n["lon"], n["lat"]) for n in data["elements"] if n["type"] == "node"}
|
||||
ways = []
|
||||
for w in data["elements"]:
|
||||
if w["type"] == "way" and "nodes" in w:
|
||||
coords = [nodes[nid] for nid in w["nodes"] if nid in nodes]
|
||||
if len(coords) > 1:
|
||||
ways.append({"geometry": LineString(coords), "highway": w["tags"].get("highway")})
|
||||
if ways:
|
||||
roads = gpd.GeoDataFrame(ways, crs="EPSG:4326")
|
||||
logger.info(f"Raw fallback: {len(roads)} roads")
|
||||
return roads
|
||||
except Exception as e:
|
||||
logger.error(f"Raw fallback failed: {e}")
|
||||
|
||||
return gpd.GeoDataFrame()
|
||||
|
||||
def detect_trucks(self, data, bbox_coords, timestamp, road_mask):
|
||||
"""
|
||||
Detect trucks using corrected Fisser et al. methodology.
|
||||
|
||||
:param data: (H, W, 5) array — [B04, B03, B02, B08, CLM]
|
||||
:param bbox_coords: [min_lat, min_lon, max_lat, max_lon]
|
||||
:param timestamp: str ISO timestamp
|
||||
:param road_mask: (H, W) binary mask of road pixels
|
||||
:return: list of detection dicts
|
||||
"""
|
||||
min_lat, min_lon, max_lat, max_lon = bbox_coords
|
||||
H, W = data.shape[:2]
|
||||
|
||||
# 1. Build feature stack (corrected order)
|
||||
feat = build_feature_stack(data)
|
||||
feature_stack = feat["feature_stack"]
|
||||
|
||||
# 2. Classify (real RF if loaded, proxy fallback otherwise)
|
||||
probs, prediction = classify(feature_stack, road_mask, self.rf_model)
|
||||
|
||||
# 3. Lat/lon arrays for geo-referencing
|
||||
lat_arr = np.linspace(max_lat, min_lat, H) # top to bottom
|
||||
lon_arr = np.linspace(min_lon, max_lon, W) # left to right
|
||||
|
||||
# 4. Object extraction (corrected)
|
||||
extractor = ObjectExtractor(probs, lat_arr, lon_arr)
|
||||
detections = extractor.extract(prediction)
|
||||
|
||||
# 5. Add timestamp and save crops
|
||||
for det in detections:
|
||||
det["timestamp"] = timestamp
|
||||
try:
|
||||
self._save_crop(data, det, H, W, min_lat, min_lon, max_lat, max_lon)
|
||||
except Exception as e:
|
||||
logger.warning(f"Could not save crop for {det['id']}: {e}")
|
||||
|
||||
return detections
|
||||
|
||||
def _save_crop(self, data, det, H, W, min_lat, min_lon, max_lat, max_lon):
|
||||
"""Save a 20×20 RGB crop centred on the detection."""
|
||||
cy = int((max_lat - det["lat"]) / (max_lat - min_lat + 1e-9) * H)
|
||||
cx = int((det["lon"] - min_lon) / (max_lon - min_lon + 1e-9) * W)
|
||||
cy, cx = int(np.clip(cy, 0, H - 1)), int(np.clip(cx, 0, W - 1))
|
||||
|
||||
y0, y1 = max(0, cy - 10), min(H, cy + 10)
|
||||
x0, x1 = max(0, cx - 10), min(W, cx + 10)
|
||||
|
||||
rgb = data[y0:y1, x0:x1, :3].astype(np.float32)
|
||||
rgb = rescale_s2(rgb)
|
||||
rgb = (np.clip(rgb, 0, 0.3) / 0.3 * 255).astype(np.uint8)
|
||||
|
||||
path = os.path.join(self.detection_dir, det["id"])
|
||||
imageio.imwrite(path, rgb)
|
||||
@@ -0,0 +1,145 @@
|
||||
"""Disk persistence for road corridor trend runs."""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from .config import DATA_ROOT, STATE_PATH
|
||||
from .presets import CORRIDOR_PRESETS, get_preset
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _utc_now_iso() -> str:
|
||||
return datetime.now(timezone.utc).replace(microsecond=0).isoformat()
|
||||
|
||||
|
||||
def preset_result_path(preset_id: str) -> Path:
|
||||
return DATA_ROOT / f"{preset_id}.json"
|
||||
|
||||
|
||||
def load_preset_result(preset_id: str) -> dict[str, Any] | None:
|
||||
path = preset_result_path(preset_id)
|
||||
if not path.is_file():
|
||||
return None
|
||||
try:
|
||||
return json.loads(path.read_text(encoding="utf-8"))
|
||||
except (OSError, json.JSONDecodeError) as exc:
|
||||
logger.warning("Could not read road corridor result %s: %s", path, exc)
|
||||
return None
|
||||
|
||||
|
||||
def save_preset_result(preset_id: str, payload: dict[str, Any]) -> None:
|
||||
DATA_ROOT.mkdir(parents=True, exist_ok=True)
|
||||
path = preset_result_path(preset_id)
|
||||
path.write_text(json.dumps(payload, indent=2), encoding="utf-8")
|
||||
|
||||
|
||||
def load_refresh_state() -> dict[str, str]:
|
||||
if not STATE_PATH.is_file():
|
||||
return {}
|
||||
try:
|
||||
raw = json.loads(STATE_PATH.read_text(encoding="utf-8"))
|
||||
return {str(k): str(v) for k, v in raw.items()}
|
||||
except (OSError, json.JSONDecodeError):
|
||||
return {}
|
||||
|
||||
|
||||
def save_refresh_state(state: dict[str, str]) -> None:
|
||||
DATA_ROOT.mkdir(parents=True, exist_ok=True)
|
||||
STATE_PATH.write_text(json.dumps(state, indent=2), encoding="utf-8")
|
||||
|
||||
|
||||
def mark_preset_refreshed(preset_id: str) -> None:
|
||||
state = load_refresh_state()
|
||||
state[preset_id] = _utc_now_iso()
|
||||
save_refresh_state(state)
|
||||
|
||||
|
||||
def list_corridor_summaries() -> list[dict[str, Any]]:
|
||||
summaries: list[dict[str, Any]] = []
|
||||
for preset in CORRIDOR_PRESETS:
|
||||
stored = load_preset_result(preset["id"])
|
||||
if stored:
|
||||
summaries.append(stored)
|
||||
continue
|
||||
summaries.append(
|
||||
{
|
||||
"preset_id": preset["id"],
|
||||
"label": preset["label"],
|
||||
"bbox": preset["bbox"],
|
||||
"country": preset["country"],
|
||||
"category": preset["category"],
|
||||
"status": "never_run",
|
||||
"daily_counts": [],
|
||||
"total_detections": 0,
|
||||
}
|
||||
)
|
||||
return summaries
|
||||
|
||||
|
||||
def build_trends_payload() -> dict[str, Any]:
|
||||
return {
|
||||
"updated_at": _utc_now_iso(),
|
||||
"corridors": list_corridor_summaries(),
|
||||
}
|
||||
|
||||
|
||||
def store_analysis_result(
|
||||
preset_id: str,
|
||||
*,
|
||||
label: str,
|
||||
bbox: list[float],
|
||||
country: str,
|
||||
category: str,
|
||||
road_count: int,
|
||||
frame_count: int,
|
||||
detections: list[dict[str, Any]],
|
||||
status: str = "ok",
|
||||
error: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
daily: dict[str, int] = {}
|
||||
for det in detections:
|
||||
ts = str(det.get("timestamp", ""))[:10]
|
||||
if ts:
|
||||
daily[ts] = daily.get(ts, 0) + 1
|
||||
daily_counts = [{"date": d, "count": daily[d]} for d in sorted(daily.keys())]
|
||||
payload = {
|
||||
"preset_id": preset_id,
|
||||
"label": label,
|
||||
"bbox": bbox,
|
||||
"country": country,
|
||||
"category": category,
|
||||
"updated_at": _utc_now_iso(),
|
||||
"road_count": road_count,
|
||||
"frame_count": frame_count,
|
||||
"total_detections": len(detections),
|
||||
"daily_counts": daily_counts,
|
||||
"status": status,
|
||||
"error": error,
|
||||
}
|
||||
save_preset_result(preset_id, payload)
|
||||
mark_preset_refreshed(preset_id)
|
||||
return payload
|
||||
|
||||
|
||||
def preset_metadata(preset_id: str) -> dict[str, Any] | None:
|
||||
preset = get_preset(preset_id)
|
||||
if preset is None:
|
||||
return None
|
||||
stored = load_preset_result(preset_id)
|
||||
if stored:
|
||||
return stored
|
||||
return {
|
||||
"preset_id": preset["id"],
|
||||
"label": preset["label"],
|
||||
"bbox": preset["bbox"],
|
||||
"country": preset["country"],
|
||||
"category": preset["category"],
|
||||
"status": "never_run",
|
||||
"daily_counts": [],
|
||||
"total_detections": 0,
|
||||
}
|
||||
@@ -0,0 +1,19 @@
|
||||
"""Map-viewport helpers for on-demand corridor analysis."""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
|
||||
|
||||
def bbox_around_point(lat: float, lon: float, *, half_span_deg: float = 0.04) -> list[float]:
|
||||
"""Square AOI around a map center (~4–5 km half-span, under the 0.5° engine cap)."""
|
||||
span = min(max(half_span_deg, 0.02), 0.24)
|
||||
return [lat - span, lon - span, lat + span, lon + span]
|
||||
|
||||
|
||||
def adhoc_preset_id(lat: float, lon: float) -> str:
|
||||
digest = hashlib.sha256(f"{lat:.4f},{lon:.4f}".encode()).hexdigest()[:12]
|
||||
return f"adhoc_{digest}"
|
||||
|
||||
|
||||
def default_label_for_point(lat: float, lon: float) -> str:
|
||||
return f"Map center ({lat:.4f}, {lon:.4f})"
|
||||
@@ -0,0 +1 @@
|
||||
"""Sanctions screening (OpenSanctions OFAC SDN)."""
|
||||
@@ -0,0 +1,154 @@
|
||||
"""OFAC SDN index via OpenSanctions (adapted from Osiris sanctions.ts)."""
|
||||
from __future__ import annotations
|
||||
|
||||
import csv
|
||||
import io
|
||||
import logging
|
||||
import re
|
||||
import threading
|
||||
import time
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any
|
||||
|
||||
from services.network_utils import fetch_with_curl
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
SDN_CSV_URL = "https://data.opensanctions.org/datasets/latest/us_ofac_sdn/targets.simple.csv"
|
||||
TTL_S = 24 * 60 * 60
|
||||
|
||||
_lock = threading.Lock()
|
||||
_cache: dict[str, Any] | None = None
|
||||
_cache_at: float = 0.0
|
||||
_inflight: threading.Event | None = None
|
||||
|
||||
|
||||
@dataclass
|
||||
class SanctionEntry:
|
||||
id: str
|
||||
schema: str
|
||||
name: str
|
||||
aliases: list[str] = field(default_factory=list)
|
||||
countries: list[str] = field(default_factory=list)
|
||||
programs: list[str] = field(default_factory=list)
|
||||
sanctions: str = ""
|
||||
first_seen: str | None = None
|
||||
last_seen: str | None = None
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"id": self.id,
|
||||
"schema": self.schema,
|
||||
"name": self.name,
|
||||
"aliases": self.aliases,
|
||||
"countries": self.countries,
|
||||
"programs": self.programs,
|
||||
"sanctions": self.sanctions,
|
||||
"first_seen": self.first_seen,
|
||||
"last_seen": self.last_seen,
|
||||
}
|
||||
|
||||
|
||||
def norm_name(s: str) -> str:
|
||||
s = re.sub(r"[^\w\s]+", " ", s.lower(), flags=re.UNICODE)
|
||||
return re.sub(r"\s+", " ", s).strip()
|
||||
|
||||
|
||||
def _split_semi(val: str) -> list[str]:
|
||||
return [x.strip() for x in (val or "").split(";") if x.strip()]
|
||||
|
||||
|
||||
def _load_list() -> dict[str, Any]:
|
||||
global _cache, _cache_at
|
||||
with _lock:
|
||||
if _cache and (time.time() - _cache_at) < TTL_S:
|
||||
return _cache
|
||||
|
||||
try:
|
||||
resp = fetch_with_curl(SDN_CSV_URL, timeout=45, headers={"Accept": "text/csv"})
|
||||
if resp.status_code != 200:
|
||||
raise RuntimeError(f"OpenSanctions HTTP {resp.status_code}")
|
||||
text = resp.text
|
||||
reader = csv.DictReader(io.StringIO(text))
|
||||
entries: list[SanctionEntry] = []
|
||||
by_norm: dict[str, list[SanctionEntry]] = {}
|
||||
for row in reader:
|
||||
name = (row.get("name") or "").strip()
|
||||
if not name:
|
||||
continue
|
||||
entry = SanctionEntry(
|
||||
id=row.get("id") or "",
|
||||
schema=row.get("schema") or "LegalEntity",
|
||||
name=name,
|
||||
aliases=_split_semi(row.get("aliases") or ""),
|
||||
countries=_split_semi(row.get("countries") or ""),
|
||||
programs=_split_semi(row.get("program_ids") or ""),
|
||||
sanctions=row.get("sanctions") or "",
|
||||
first_seen=row.get("first_seen") or None,
|
||||
last_seen=row.get("last_seen") or None,
|
||||
)
|
||||
entries.append(entry)
|
||||
for key in {norm_name(name), *(norm_name(a) for a in entry.aliases)}:
|
||||
if not key:
|
||||
continue
|
||||
by_norm.setdefault(key, []).append(entry)
|
||||
loaded = {"entries": entries, "by_norm": by_norm, "fetched_at": time.time()}
|
||||
with _lock:
|
||||
_cache = loaded
|
||||
_cache_at = time.time()
|
||||
logger.info("OFAC SDN index loaded: %s entries", len(entries))
|
||||
return loaded
|
||||
except Exception as exc:
|
||||
logger.error("OFAC SDN load failed: %s", exc)
|
||||
with _lock:
|
||||
if _cache:
|
||||
return _cache
|
||||
raise
|
||||
|
||||
|
||||
def match_exact(query: str) -> list[dict[str, Any]]:
|
||||
if not query or len(query) < 3:
|
||||
return []
|
||||
data = _load_list()
|
||||
hits = data["by_norm"].get(norm_name(query), [])
|
||||
return [e.to_dict() for e in hits]
|
||||
|
||||
|
||||
def search_sanctions(query: str, *, schema: str | None = None, limit: int = 50) -> list[dict[str, Any]]:
|
||||
if not query or len(query) < 4:
|
||||
return []
|
||||
data = _load_list()
|
||||
q = norm_name(query)
|
||||
exact_name: list[SanctionEntry] = []
|
||||
exact_alias: list[SanctionEntry] = []
|
||||
sub_name: list[SanctionEntry] = []
|
||||
sub_alias: list[SanctionEntry] = []
|
||||
seen: set[str] = set()
|
||||
|
||||
def push(bucket: list[SanctionEntry], entry: SanctionEntry) -> None:
|
||||
if entry.id in seen:
|
||||
return
|
||||
if schema and entry.schema != schema:
|
||||
return
|
||||
seen.add(entry.id)
|
||||
bucket.append(entry)
|
||||
|
||||
for entry in data["entries"]:
|
||||
name_norm = norm_name(entry.name)
|
||||
if name_norm == q:
|
||||
push(exact_name, entry)
|
||||
elif any(norm_name(a) == q for a in entry.aliases):
|
||||
push(exact_alias, entry)
|
||||
elif q in name_norm:
|
||||
push(sub_name, entry)
|
||||
elif any(q in norm_name(a) for a in entry.aliases):
|
||||
push(sub_alias, entry)
|
||||
if len(seen) >= limit * 4:
|
||||
break
|
||||
|
||||
ordered = exact_name + exact_alias + sub_name + sub_alias
|
||||
return [e.to_dict() for e in ordered[:limit]]
|
||||
|
||||
|
||||
def index_size() -> int:
|
||||
return len(_load_list()["entries"])
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user