ForexBot2/static/news_summary.php

<?php
/**
 * On-demand gold-impact AI summary for one published headline.
 *
 * The ONLY dynamic piece of the otherwise-static dashboard. Serves
 * GET ?id=<sha1-of-headline> and returns {"summary": ..., "generated_at": ...}.
 *
 * Abuse model (the page is public):
 *   - WHITELIST: the id must match a headline in the local news.json —
 *     arbitrary text can never reach the LLM through this endpoint.
 *   - CACHE FOREVER: headlines are immutable, so each id costs at most
 *     one DeepSeek call, ever (ai/<id>.json). Cache is checked BEFORE
 *     the whitelist on purpose: summaries stay reachable after the
 *     headline ages out of the 24 h feed window.
 *   - DAILY CAP: file-based UTC-day counter, FAIL CLOSED on counter I/O
 *     errors (a perms mistake must not mean unmetered spend).
 *
 * DeepSeek doctrine (mirrors llm_client.py — deliberate local copy, the
 * dashboard never imports bot code and this file never reads the repo's
 * config.json):
 *   - STATIC byte-identical system prompt (prefix-cache pricing).
 *   - "thinking": disabled is MANDATORY for V4-Flash (else it burns the
 *     timeout reasoning), temperature 0, json response_format.
 *   - One attempt, no retries; every failure returns a JSON error the
 *     page renders as a graceful fallback.
 *
 * Key file lives OUTSIDE the docroot: /etc/gold-dashboard/deepseek.key
 * (root:apache 640). Override paths/caps via Apache SetEnv:
 * DEEPSEEK_KEY_FILE, AI_SUMMARY_DAILY_CAP.
 */

const NEWS_FILE = __DIR__ . '/news.json';
const CACHE_DIR = __DIR__ . '/ai';   // apache-owned; created at deploy time
const API_URL   = 'https://api.deepseek.com/chat/completions';
const MODEL     = 'deepseek-v4-flash';
const TIMEOUT   = 12;
const MAX_TOKENS = 200;
const SUMMARY_MAX_CHARS = 400;

// .ht_ prefix: Apache's default <Files ".ht*"> rule denies these even
// though they sit in the public docroot.
const CAP_FILE = CACHE_DIR . '/.ht_cap.json';

const SYSTEM_PROMPT = <<<'PROMPT'
You are a forex/gold news analyst. You receive one news item as JSON:
{"headline", "description", "score", "xau_score", "keywords", "currencies"}.
"xau_score" is the platform's automated gold-effect score for this item,
-1.0 (gold down) to 1.0 (gold up); "score" is overall market sentiment.
Both are automated and can be wrong — judge the news yourself.
In 1-2 plain-English sentences (max 45 words) explain what this news
means for the GOLD (XAU/USD) price and WHY it is bullish, bearish, or
neutral. If your reading clearly contradicts xau_score, add "(the
automated score disagrees)". Never write the words "xau_score" or
"score" — a general reader sees this text.
Gold doctrine: hawkish Fed / rate hikes / rising real yields / strong
dollar are gold-bearish; easing / rate cuts / safe-haven flows /
geopolitical stress / weak dollar are gold-bullish.
Reply with ONLY JSON: {"summary": "..."}
PROMPT;

function respond(int $status, array $obj, string $cache = 'no-store'): void
{
    http_response_code($status);
    header('Content-Type: application/json; charset=utf-8');
    header('Cache-Control: ' . $cache);
    echo json_encode($obj, JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE);
    exit;
}

function atomic_write(string $path, string $data): bool
{
    $tmp = $path . '.tmp.' . getmypid();
    if (@file_put_contents($tmp, $data) === false) {
        return false;
    }
    if (!@rename($tmp, $path)) {
        @unlink($tmp);
        return false;
    }
    return true;
}

// ── 1. id validation ────────────────────────────────────────────────
$id = $_GET['id'] ?? '';
if (!preg_match('/^[a-f0-9]{40}$/', $id)) {
    respond(400, ['error' => 'bad_id']);
}

// ── 2. cache first (immutable headlines → summaries never change) ───
$cachePath = CACHE_DIR . '/' . $id . '.json';
$cached = @file_get_contents($cachePath);
if ($cached !== false && $cached !== '') {
    http_response_code(200);
    header('Content-Type: application/json; charset=utf-8');
    header('Cache-Control: max-age=3600');
    echo $cached;
    exit;
}

// ── 3. whitelist against the published feed ─────────────────────────
$news = json_decode((string)@file_get_contents(NEWS_FILE), true);
if (!is_array($news)) {
    respond(503, ['error' => 'no_feed']);
}
$hit = null;
foreach ($news['headlines'] ?? [] as $h) {
    // Fallback sha1(): a publisher that predates the id field still
    // serves a valid whitelist during the restart window.
    $hid = $h['id'] ?? sha1($h['headline'] ?? '');
    if ($hid === $id) {
        $hit = $h;
        break;
    }
}
if ($hit === null) {
    respond(404, ['error'   => 'unknown_id',
                  'message' => 'Headline is no longer in the feed.']);
}

// ── 4. daily cap (fail closed) ──────────────────────────────────────
$dailyCap = (int)(getenv('AI_SUMMARY_DAILY_CAP') ?: 150);
$capFh = @fopen(CAP_FILE, 'c+');
if ($capFh === false || !flock($capFh, LOCK_EX)) {
    respond(503, ['error' => 'cap_io']);
}
$today = gmdate('Y-m-d');
$cap = json_decode((string)stream_get_contents($capFh), true);
if (!is_array($cap) || ($cap['day'] ?? '') !== $today) {
    $cap = ['day' => $today, 'count' => 0];
}
if ($cap['count'] >= $dailyCap) {
    flock($capFh, LOCK_UN);
    fclose($capFh);
    respond(429, ['error' => 'cap_exceeded']);
}
// Increment BEFORE the LLM call — attempts count against the cap
// (same semantics as llm_client._under_cap).
$cap['count']++;
rewind($capFh);
if (ftruncate($capFh, 0) === false
        || fwrite($capFh, json_encode($cap)) === false) {
    flock($capFh, LOCK_UN);
    fclose($capFh);
    respond(503, ['error' => 'cap_io']);
}
fflush($capFh);
flock($capFh, LOCK_UN);
fclose($capFh);

// ── 5. API key ──────────────────────────────────────────────────────
$keyFile = getenv('DEEPSEEK_KEY_FILE') ?: '/etc/gold-dashboard/deepseek.key';
$apiKey = trim((string)@file_get_contents($keyFile));
if ($apiKey === '') {
    respond(503, ['error' => 'no_key']);
}

// ── 6. per-id stampede lock, then re-check the cache ────────────────
$lockFh = @fopen(CACHE_DIR . '/.ht_lock_' . $id, 'c');
if ($lockFh !== false) {
    flock($lockFh, LOCK_EX);   // blocks while a concurrent winner generates
    $cached = @file_get_contents($cachePath);
    if ($cached !== false && $cached !== '') {
        flock($lockFh, LOCK_UN);
        fclose($lockFh);
        http_response_code(200);
        header('Content-Type: application/json; charset=utf-8');
        header('Cache-Control: max-age=3600');
        echo $cached;
        exit;
    }
}

// ── 7. DeepSeek call (exact chat_json body shape) ───────────────────
$userPayload = json_encode([
    'headline'    => $hit['headline'] ?? '',
    'description' => $hit['description'] ?? null,
    'score'       => $hit['score'] ?? null,
    'xau_score'   => $hit['score_by_currency']['XAU'] ?? null,
    'keywords'    => $hit['keywords'] ?? [],
    'currencies'  => $hit['currencies'] ?? [],
], JSON_UNESCAPED_UNICODE);

$body = json_encode([
    'model'    => MODEL,
    'messages' => [
        ['role' => 'system', 'content' => SYSTEM_PROMPT],
        ['role' => 'user',   'content' => $userPayload],
    ],
    'response_format' => ['type' => 'json_object'],
    'temperature'     => 0,
    'thinking'        => ['type' => 'disabled'],
    'max_tokens'      => MAX_TOKENS,
]);

$ch = curl_init(API_URL);
curl_setopt_array($ch, [
    CURLOPT_POST           => true,
    CURLOPT_POSTFIELDS     => $body,
    CURLOPT_HTTPHEADER     => ['Content-Type: application/json',
                               'Authorization: Bearer ' . $apiKey],
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_TIMEOUT        => TIMEOUT,
]);
$raw = curl_exec($ch);
$httpCode = curl_getinfo($ch, CURLINFO_RESPONSE_CODE);
curl_close($ch);

// ── 8. parse (any failure → 502, never cached) ──────────────────────
$summary = null;
if ($raw !== false && $httpCode === 200) {
    $resp = json_decode($raw, true);
    $content = $resp['choices'][0]['message']['content'] ?? '';
    $parsed = json_decode((string)$content, true);
    if (is_array($parsed) && is_string($parsed['summary'] ?? null)
            && trim($parsed['summary']) !== '') {
        $summary = trim($parsed['summary']);
        if (mb_strlen($summary) > SUMMARY_MAX_CHARS) {
            $summary = mb_substr($summary, 0, SUMMARY_MAX_CHARS) . '…';
        }
    }
}
if ($lockFh !== false && $summary === null) {
    flock($lockFh, LOCK_UN);
    fclose($lockFh);
}
if ($summary === null) {
    respond(502, ['error' => 'llm_failed']);
}

// ── 9. cache + respond ──────────────────────────────────────────────
$out = json_encode(['summary' => $summary, 'generated_at' => gmdate('c')],
                   JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE);
if (!atomic_write($cachePath, $out)) {
    // Degrade to per-click generation rather than a broken feature —
    // the daily cap still bounds spend.
    error_log('news_summary.php: cache write failed for ' . $cachePath);
}
if ($lockFh !== false) {
    flock($lockFh, LOCK_UN);
    fclose($lockFh);
}
http_response_code(200);
header('Content-Type: application/json; charset=utf-8');
header('Cache-Control: max-age=3600');
echo $out;