/* test_http_sigpipe.c — a client that hangs up mid-response must not kill the
 * server. Integration probe: point it at a running engram.
 *
 * WHAT THIS REPRODUCES. `send()` to a socket whose peer has closed raises
 * SIGPIPE, whose default disposition is terminate. Nothing in the runtime
 * suppressed it, so any abandoned request could kill the process. In production
 * the abandoning client was the heartbeat: ai.neuron.engram-tick.plist runs on
 * StartInterval 600 and calls `curl -s -m10 -X POST /api/tick`; when the endpoint
 * exceeded ten seconds curl hung up, and the eventual response write killed the
 * server. 254 restarts between 2026-08-13T19:37 and 2026-08-16T18:16, with
 * `launchctl list ai.neuron.engram` reporting LastExitStatus = 13 — raw wait
 * status 13, killed by signal 13, SIGPIPE.
 *
 * TWO THINGS THIS PROBE GETS RIGHT, both of which a naive version gets wrong and
 * both of which cost me a false PASS on the unpatched build before I caught them:
 *
 *   1. CLOSE MODE. Closing with SO_LINGER=0 emits RST, and the server's FIRST
 *      write then returns ECONNRESET rather than raising SIGPIPE: http_send_all
 *      sees w <= 0, returns -1, and stops. No signal, no crash — the test passes
 *      on the UNPATCHED build and proves nothing. A NORMAL close (FIN) is what
 *      kills: the first write succeeds, the peer answers RST because it is fully
 *      closed, and the SECOND write raises SIGPIPE. A response is emitted as four
 *      http_send_all calls (status line, headers, tail, body), so the sequence is
 *      always reached.
 *
 *   2. TIMING. The kill does not land when the client closes. It lands when the
 *      server reaches its write, which on a heavy endpoint is many seconds later
 *      (~16s measured on /api/activate over a 13,632-node store). Checking
 *      liveness a second after the hang-up finds the process healthy and reports
 *      a false pass.
 *
 * Usage: test_http_sigpipe <port> <pid> [rounds] [settle_seconds]
 * Exit 0 = server survived every round (PASS), 1 = server died (FAIL),
 *      2 = bad precondition.
 */
#define _POSIX_C_SOURCE 200809L
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <errno.h>
#include <signal.h>
#include <time.h>
#include <netdb.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>

/* The request is deliberately expensive: the body must be large enough and slow
 * enough that the server is still working when the client walks away. */
static const char* REQ_PATH =
    "/api/activate?q=will%20anderson&depth=3&_auth=ntn-user-2026";

static int alive(pid_t pid) { return kill(pid, 0) == 0 || errno == EPERM; }

static void sleep_ms(long ms) {
    struct timespec ts = { ms / 1000, (ms % 1000) * 1000000L };
    nanosleep(&ts, NULL);
}

/* Connect, ask for the expensive body, then hang up NORMALLY without reading. */
static int abort_request(int port) {
    int fd = socket(AF_INET, SOCK_STREAM, 0);
    if (fd < 0) return -1;
    struct sockaddr_in a;
    memset(&a, 0, sizeof a);
    a.sin_family = AF_INET;
    a.sin_port   = htons((uint16_t)port);
    a.sin_addr.s_addr = inet_addr("127.0.0.1");
    if (connect(fd, (struct sockaddr*)&a, sizeof a) != 0) { close(fd); return -1; }

    char req[512];
    int n = snprintf(req, sizeof req,
        "GET %s HTTP/1.1\r\nHost: probe\r\nConnection: close\r\nAccept: */*\r\n\r\n",
        REQ_PATH);
    if (write(fd, req, (size_t)n) != n) { close(fd); return -1; }

    sleep_ms(200);        /* ensure the request landed and work has begun */
    close(fd);            /* NORMAL close -> FIN. Never SO_LINGER=0 / RST. */
    return 0;
}

int main(int argc, char** argv) {
    if (argc < 3) {
        fprintf(stderr,
            "usage: %s <port> <pid> [rounds=1] [settle_seconds=45]\n", argv[0]);
        return 2;
    }
    int   port   = atoi(argv[1]);
    pid_t pid    = (pid_t)atoi(argv[2]);
    int   rounds = argc > 3 ? atoi(argv[3]) : 1;
    int   settle = argc > 4 ? atoi(argv[4]) : 45;

    if (!alive(pid)) {
        printf("  PRECONDITION FAILED: pid %d is not running before the probe\n", pid);
        return 2;
    }
    printf("  precondition: pid %d alive, target port %d\n", pid, port);

    for (int i = 1; i <= rounds; i++) {
        if (abort_request(port) != 0) {
            printf("  round %d: could not reach the server on port %d\n", i, port);
            return 2;
        }
        printf("  round %d: client hung up; waiting up to %ds for the server to "
               "reach its write...\n", i, settle);
        for (int s = 0; s < settle * 2; s++) {
            if (!alive(pid)) {
                printf("  round %d: SERVER DIED %.1fs after the hang-up  *** FAIL ***\n",
                       i, s / 2.0);
                return 1;
            }
            sleep_ms(500);
        }
        printf("  round %d: server survived\n", i);
    }
    printf("  PASS: the server survived %d abandoned request(s)\n", rounds);
    return 0;
}