# News pipeline — scraper + Nous Portal summarizer

The OSINT dashboard ingests a large curated feed list (`news/scraper/urls.txt`)
continuously and produces an English LLM brief plus flagged ticker/map rows
every 15 minutes. Both services were vendored from the upstream
`~/Projects/newsPipeline` project and re-integrated here against the EXISTING
osint-db — **no second Postgres**. The LLM is **Nous Portal**
(`inference-api.nousresearch.com`) — not Gemini.

## Architecture

```
urls.txt (RSS + homepages)
        │
        ▼
news-scraper   (Scrapy, continuous) ──► articles table (osint-db)
        │                                      │
        │                                      ▼
news-summarizer (Nous Portal, every 15m) ──► article_summaries + news_items
                                                      │
                                                      ▼
     GET /api/news · /api/news/summaries · /api/news/ticker · /api/news/map
     GET /api/news/models · GET/PUT /api/settings
```

| Component | Image | Container | Scheduling |
|---|---|---|---|
| Scraper | `localhost/osint-news-scraper` | `osint-news-scraper` | loop, `NEWS_SCRAPE_INTERVAL_S` (default 10s after each crawl) |
| Summarizer | `localhost/osint-news-summarizer` | `osint-news-summarizer` | loop, `NEWS_SUMMARIZE_INTERVAL_S` (default 900s) |

Both services live under the `ingest` compose profile (same as the ingester
and camera-scraper): `docker compose --profile ingest up -d`.

The summarizer is a batch sidecar, **not** a live overlay. Do **not** reuse
`GET /api/alerts` (dashboard entity/keyword alerts). Do **not** stuff news
into `overlay_catalog()` — `/api/map/layers` `overlays` stays live upstream
feeds (`GET /api/news` exact key set is unchanged on purpose).

## Data flow

1. **Scraper** — `news/scraper/run_news_scraper.py` runs
   `scrapy crawl articles` back-to-back (default 10s pause). The spider reads
   URLs from `urls.txt` (homepages autodiscover RSS; feed URLs are parsed
   directly), follows each `<item>` link, extracts the main article body, and
   the `PostgresPipeline` writes to `articles` with URL-based dedup
   (`ON CONFLICT (url) DO NOTHING`).
2. **Summarizer** — `news/summerizer/run_news_summarizer.py` runs
   `summarizer.py` every `NEWS_SUMMARIZE_INTERVAL_S` (default 900). It reads
   articles from the last `SUMMARY_WINDOW_MINUTES` (default 15), map-reduces
   them through Nous Portal (`SUMMARY_MODEL` / Settings, default
   `Hermes-4.3-36B`), writes the English brief to `article_summaries` (column
   `model` is the LLM id), and flagged ticker/map rows to `news_items`.

Loops are serial (two crawls/summaries never overlap). Interval idempotency:
if `article_summaries` already has a row in the last interval, the summarizer
**skips** (prevents double-pins on `RUN_ON_START` recreate). Set
`NEWS_SUMMARIZE_FORCE=1` to ignore that skip.

The `articles` and `article_summaries` tables are created by the idempotent
alembic migration `003_news` (also created by the scraper's own
`CREATE TABLE IF NOT EXISTS`). `news_items` is alembic `005_news_items`.
Container startup order doesn't matter.

## Keys and Settings

- **`NOUS_API_KEY`** — paste in the dashboard **Keys** UI (`api_keys` /
  `keystore.KEY_REGISTRY`). Env / `.env` is an **override** (env wins, same
  as FIRMS). Never returned by any API; never emitted into `index.html`;
  never proxied from the browser.
- **Idle without a key** — if env is unset **and** the keystore row is empty,
  the summarizer logs and idles (never crashes). News intel APIs return `[]`.
- **Model** — non-secret. Settings UI model selector `PUT /api/settings`
  `{ "summary_model": "…" }` stores `SUMMARY_MODEL` in `app_settings` (1–128
  chars). `GET /api/settings` echoes `{summary_model, nous_base_url}`.
  `nous_base_url` is read-only. Default `Hermes-4.3-36B`. Live catalog is
  best-effort `GET /api/news/models`.

## Endpoints

### GET /api/news — recent articles

Key set **unchanged** (no `lat`/`lon` on articles; geo lives on `/api/news/map`).

| Query param | Meaning | Default |
|---|---|---|
| `domain` | filter by source domain (e.g. `www.reuters.com`) | none |
| `since` | only articles captured at/after this UTC instant (ISO-8601) | none |
| `limit` | max rows | `50` (max `500`) |
| `offset` | pagination offset | `0` |
| `include_content` | include full article body | `false` |

```json
[
  {
    "id": 1,
    "title": "…",
    "url": "https://…",
    "content": null,
    "domain": "www.reuters.com",
    "timestamp": "2026-08-24T18:10:00Z"
  }
]
```

### GET /api/news/summaries — master LLM briefs

| Query param | Meaning | Default |
|---|---|---|
| `since` | only summaries generated at/after this UTC instant | none |
| `limit` | max rows | `20` (max `100`) |
| `offset` | pagination offset | `0` |

```json
[
  {
    "id": 1,
    "summary_text": "English markdown brief…",
    "batch_timestamp": "2026-08-24T18:10:00Z",
    "model": "Hermes-4.3-36B"
  }
]
```

`model` is additive. Empty DB → `[]` (no crash).

### GET /api/news/ticker — flagged HUD headlines

Critical/high `news_items` with `kind=ticker` only. Do **not** reuse
`GET /api/alerts`. Bottom HUD `#nt-track` scrolls these rows, not a dump of
the whole brief.

| Query param | Meaning | Default |
|---|---|---|
| `since` | only items created at/after this UTC instant | none |
| `limit` | max rows | `20` (max `50`) |

```json
[
  {
    "id": 1,
    "headline": "…",
    "importance": "critical",
    "location_name": "Kyiv",
    "url": "https://…",
    "created_at": "2026-08-24T18:10:00Z"
  }
]
```

### GET /api/news/map — geolocated critical/high pins

Only rows with valid `lat`/`lon`. Optional bbox. **No zoom skip** — world
view is the point. Layer-panel toggle uses this dedicated path (same as
event blips), not `overlay_catalog`.

| Query param | Meaning | Default |
|---|---|---|
| `bbox` | `minlon,minlat,maxlon,maxlat` | all flagged pins |
| `since` | only items created at/after this UTC instant | last 24 hours |
| `limit` | max rows | `200` (max `500`) |

Malformed bbox → `422`.

```json
[
  {
    "id": 1,
    "headline": "…",
    "importance": "high",
    "location_name": "Kyiv",
    "lat": 50.45,
    "lon": 30.52,
    "location_confidence": "city",
    "category": "military/conflict",
    "url": "https://…",
    "created_at": "2026-08-24T18:10:00Z"
  }
]
```

Pins are LLM-estimated and clamped (`lat∈[-90,90]`, `lon∈[-180,180]`). No
Nominatim. No writes into `events`.

### GET /api/news/models — Settings dropdown catalog

Never 502s. `{ "source": "live"|"fallback", "models": [{"id": "…"}] }`.

### GET /api/settings · PUT /api/settings

```json
{ "summary_model": "Hermes-4.3-36B", "nous_base_url": "https://inference-api.nousresearch.com/v1" }
```

PUT body is `{ "summary_model": "<1–128 char id>" }`. `nous_base_url` is
ignored even if sent.

## Reduce JSON contract

Reduce phase (`response_format: json_object`, English only) must be a single
object. Parser (`intel.parse_reduce_json`) strips `<think>…</think>` and
markdown json fences, then brace-slices:

```json
{
  "summary_en": "English markdown brief or the no-qualifying-events sentence",
  "ticker": [
    {"headline": "", "importance": "critical", "url": "", "location_name": ""}
  ],
  "map_items": [
    {
      "headline": "",
      "importance": "critical",
      "location_name": "",
      "lat": 0,
      "lon": 0,
      "location_confidence": "city",
      "category": "military/conflict",
      "url": ""
    }
  ]
}
```

Persist ticker/map only for `importance` in `critical`/`high`. Map rows also
need valid coords; Unknown / invented places are dropped. Caps: 12 ticker
(≤140 chars, no markdown), 20 map. Empty ticker is allowed. `summary_en`
lands in `article_summaries.summary_text`.

## Configuration (all via env / `.env`)

| Var | Default | Notes |
|---|---|---|
| `NOUS_API_KEY` | *(blank)* | **Required for summaries.** Prefer Keys UI; env overrides. Unset in **both** env and `api_keys` = summarizer logs and idles (never crashes); APIs return `[]`. |
| `NOUS_BASE_URL` | `https://inference-api.nousresearch.com/v1` | Read-only in Settings. |
| `SUMMARY_MODEL` | `Hermes-4.3-36B` | Compose default. Operator-facing choice is Settings → `app_settings.SUMMARY_MODEL`. |
| `NEWS_BATCH_SIZE` | `50` | Articles per map-phase batch (compose maps to container `BATCH_SIZE`). |
| `SUMMARY_WINDOW_MINUTES` | `15` | How far back the summarizer looks for new articles. |
| `NEWS_SCRAPE_INTERVAL_S` | `10` | Pause after each crawl before the next (scraper is otherwise continuous). |
| `NEWS_SUMMARIZE_INTERVAL_S` | `900` | Seconds between analyst runs (default 15 min). |
| `NEWS_SCRAPE_RUN_ON_START` | `1` | Run one scrape immediately on container start. |
| `NEWS_SUMMARIZE_RUN_ON_START` | `1` | Run one summarize immediately on container start. |
| `NEWS_SUMMARIZE_FORCE` | `0` | `1` ignores the interval idempotency skip (double-pins on recreate). |
| `INCLUDE_FUTURES` | `0` | Legacy futures-prices coupling. OFF for OSINT; set `1` + install `yfinance` to enable. |
| `NEWS_LOG_LEVEL` | `INFO` | Scrapy log level. |
| `OSINT_USER_AGENT` | `osint-dashboard-news-summarizer` | Sent on every outbound Nous call. |
| `TELEGRAM_TOKEN` / `TELEGRAM_CHAT_ID` | *(blank)* | Reserved for the (out-of-scope) Telegram delivery bot. |

DB_* for both services is mapped to the shared osint-db credentials
(`DB_HOST=db`, same `DB_USER/DB_PASSWORD/DB_NAME` as the rest of the stack).

Nous chat: `POST {NOUS_BASE_URL}/chat/completions` via `news/summerizer/nous_client.py`
(`httpx`, no `openai` SDK). Auth is a Bearer token from `NOUS_API_KEY`.
No Hermes-4 reasoning system prompt. Reduce uses `json_mode=True`.

## Prompts

Both prompts are env-overridable — the default `MAP_PROMPT` is OSINT-neutral
(facts, locations, entities, category, OSINT signal per article; English) and
the default `SUMMARY_PROMPT` demands the reduce JSON above (with a
"no qualifying events" escape hatch). Upstream's futures/markets prompt
language is gated behind `INCLUDE_FUTURES=1`.

## Tests

```bash
PYTHONPATH=news/summerizer pytest news/summerizer/tests -v
# intel + nous_client tests PASS (no network)

PYTHONPATH=app pytest tests/test_api_news.py \
  tests/test_api_settings.py tests/test_api_live_layers.py -v
# DB-marked tests skip without Postgres; live_layers must still PASS
# /api/map/layers overlays key set UNCHANGED
```

## Live verification

After deploy / compose rebuild of `news-summarizer` on the Pi:

1. Keys UI: save `NOUS_API_KEY` → status `****last4`.
2. Settings: pick a model → Save → `GET /api/settings` echoes it.
3. `docker compose --profile ingest logs -f news-summarizer` — next run (or
   `NEWS_SUMMARIZE_RUN_ON_START=1` recreate) logs `Processing N articles with <model>`.
4. `curl -s localhost:8000/api/news/summaries?limit=1` — English `summary_text`, `model` set.
5. `curl -s localhost:8000/api/news/ticker` — flagged headlines only.
6. `curl -s localhost:8000/api/news/map` — only rows with lat/lon.
7. HUD: NEWS ticker scrolls flagged items; map overlay pins popup with location.
8. Unset key + empty keystore → summarizer logs idle, APIs return `[]`, no crash.

**Operator action after merge:** paste a Nous Portal API key in API Keys; pick
a model in Settings if the default `Hermes-4.3-36B` is not wanted; rebuild
`osint-news-summarizer` on the Pi (`pi-app-deploy` / compose).