myxce/src/controller/testsuite/test_ha_evaluate_committing.c

/*
 * test_ha_evaluate_committing.c — Unity tests for Task 4.1:
 * ha_elect_evaluate_and_signal COMMITTING path.
 *
 * Tests verify:
 *   Req 4.1: quorum reached → ha->role transitions to CTRL_PRIMARY_COMMITTING
 *            (not CTRL_PRIMARY) after ha_elect_evaluate_and_signal
 *   Req 5.2: COMMITTING path: ha->repl_ack_count reset to 0 when entering COMMITTING
 *   Req 9.2: cluster_init_phase2 called exactly once on first election;
 *            second election (RDHUP) skips it (phase2_done=1)
 *
 * Design ref: design.md "ha_elect_evaluate_and_signal (extended)"
 * Boundary: ha.c (election evaluation)
 * Requirements: 4.1, 5.2, 9.2
 */
#define _GNU_SOURCE
#include <errno.h>
#include <semaphore.h>
#include <stdatomic.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>

#include <unity/unity.h>

#include "ha.h"
#include "xce/cluster_def.h"  /* full cluster_t layout for committing_timeout_fn tests */

/* ── Test-only seam: cluster_init_phase2 call counter ───────────────────────
 *
 * In production, ha_elect_evaluate_and_signal calls cluster_init_phase2(c)
 * when !ha->phase2_done. For unit tests we cannot provide a real cluster_t,
 * so we hook via an XCE_TESTING seam in ha.c: the evaluate function checks
 * ha_phase2_hook; if non-NULL it calls the hook instead of cluster_init_phase2.
 *
 * This avoids pulling in the full cluster_t dependency in the test binary.
 */
extern int (*ha_phase2_hook)(void *c);

/* Call counter for the hook */
static int g_phase2_call_count = 0;
static int g_phase2_hook_rc    = 0; /* return value for hook (0 = success) */

static int stub_cluster_init_phase2(void *c)
{
    (void)c;
    g_phase2_call_count++;
    return g_phase2_hook_rc;
}

/* ── Minimal ha_config_t for tests ─────────────────────────────────────── */

static ha_config_t g_cfg = {
    .heartbeat_interval_ms     = 3000,
    .heartbeat_timeout_ms      = 10000,
    .election_timeout_ms       = 2000,
    .probe_connect_timeout_ms  = 500,
    .max_promotion_retries     = 5,
    .election_jitter_max_ms    = 0,
    .election_priority_step_ms = 500,
    .committing_timeout_ms     = HA_DEFAULT_COMMITTING_TIMEOUT_MS,
};

/* ── Helper: build a minimal ha_elect_ctx_t for n_other peers ───────────── */

static ha_elect_ctx_t *make_ctx(int n_other, int votes_granted)
{
    ha_elect_ctx_t *ctx = calloc(1, sizeof(*ctx) +
                                    (size_t)n_other * sizeof(ctx->votes[0]));
    if (!ctx) return NULL;
    ctx->n_peers       = n_other;
    ctx->votes_granted = votes_granted;  /* includes self-vote */
    ctx->n_replied     = n_other;
    ctx->max_resp_tag  = 0;
    ctx->max_resp_lsn  = 0;
    ctx->result        = -1;
    ctx->done_posted   = 0;
    ctx->c             = NULL;           /* no real cluster in unit tests */
    pthread_mutex_init(&ctx->lock, NULL);
    sem_init(&ctx->done, 0, 0);
    /* Store my_tag/my_lsn in votes[0] for yield gate (only if n_other > 0) */
    if (n_other > 0) {
        ctx->votes[0].my_tag = 100;
        ctx->votes[0].my_lsn = 50;
    }
    return ctx;
}

static void free_ctx(ha_elect_ctx_t *ctx)
{
    if (!ctx) return;
    pthread_mutex_destroy(&ctx->lock);
    sem_destroy(&ctx->done);
    free(ctx);
}

/* ── Test setup/teardown ─────────────────────────────────────────────────── */

static void reset_counters(void)
{
    g_phase2_call_count = 0;
    g_phase2_hook_rc    = 0;
    /* Wire up the test seam */
    ha_phase2_hook = stub_cluster_init_phase2;
}

static void clear_hook(void)
{
    ha_phase2_hook = NULL;
}

/* ── Test 1: winning quorum → CTRL_PRIMARY_COMMITTING (not PRIMARY) ─────── */

static void test_winning_quorum_enters_committing(void)
{
    /* 3-node cluster: n_other=2, quorum=2. Self-vote + 2 peer grants = 3.
     * ha_elect_evaluate_and_signal should detect quorum → COMMITTING. */
    reset_counters();

    ha_state_t ha;
    ha_init(&ha, &g_cfg, 0);
    ha.phase2_done = 0; /* first boot */
    atomic_store_explicit(&ha.role, (int32_t)CTRL_ELECTING, memory_order_release);

    ha_elect_ctx_t *ctx = make_ctx(2, 3); /* votes_granted=3 (self + 2 peers) */
    TEST_ASSERT_NOT_NULL_MESSAGE(ctx, "make_ctx failed");
    /* Set votes[0] my_tag/my_lsn for yield gate */
    ctx->votes[0].my_tag = 100;
    ctx->votes[0].my_lsn = 50;

    ctrl_role_t result = ha_elect_evaluate_and_signal(&ha, ctx);

    /* Function must return CTRL_PRIMARY (the election result) */
    TEST_ASSERT_EQUAL_INT_MESSAGE((int)CTRL_PRIMARY, (int)result,
        "ha_elect_evaluate_and_signal must return CTRL_PRIMARY when quorum won");

    /* But ha->role must be CTRL_PRIMARY_COMMITTING (Req 4.1) */
    ctrl_role_t actual_role =
        (ctrl_role_t)atomic_load_explicit(&ha.role, memory_order_acquire);
    TEST_ASSERT_EQUAL_INT_MESSAGE((int)CTRL_PRIMARY_COMMITTING, (int)actual_role,
        "ha->role must be CTRL_PRIMARY_COMMITTING after winning election (not CTRL_PRIMARY)");

    free_ctx(ctx);
    ha_fini(&ha);
    clear_hook();
    printf("test_winning_quorum_enters_committing: PASS (role=%d==CTRL_PRIMARY_COMMITTING)\n",
           (int)actual_role);
}

/* ── Test 2: first boot — phase2 called exactly once ────────────────────── */

static void test_first_boot_phase2_called_once(void)
{
    /* phase2_done=0: cluster_init_phase2 must be called exactly once. */
    reset_counters();

    ha_state_t ha;
    ha_init(&ha, &g_cfg, 0);
    ha.phase2_done = 0;
    atomic_store_explicit(&ha.role, (int32_t)CTRL_ELECTING, memory_order_release);

    /* Single-node-like: n_other=0, quorum=1, votes_granted=1 → wins */
    ha_elect_ctx_t *ctx = make_ctx(0, 1);
    TEST_ASSERT_NOT_NULL_MESSAGE(ctx, "make_ctx failed");

    ha_elect_evaluate_and_signal(&ha, ctx);

    TEST_ASSERT_EQUAL_INT_MESSAGE(1, g_phase2_call_count,
        "cluster_init_phase2 must be called exactly once on first boot");
    TEST_ASSERT_EQUAL_INT_MESSAGE(1, ha.phase2_done,
        "ha->phase2_done must be set to 1 after cluster_init_phase2");

    free_ctx(ctx);
    ha_fini(&ha);
    clear_hook();
    printf("test_first_boot_phase2_called_once: PASS (calls=%d)\n", g_phase2_call_count);
}

/* ── Test 3: second election (RDHUP) skips phase2 ───────────────────────── */

static void test_rdhup_second_election_skips_phase2(void)
{
    /* phase2_done=1: cluster_init_phase2 must NOT be called. */
    reset_counters();

    ha_state_t ha;
    ha_init(&ha, &g_cfg, 0);
    ha.phase2_done = 1; /* already initialized (post-RDHUP failover) */
    atomic_store_explicit(&ha.role, (int32_t)CTRL_ELECTING, memory_order_release);

    ha_elect_ctx_t *ctx = make_ctx(0, 1); /* single-node wins again */
    TEST_ASSERT_NOT_NULL_MESSAGE(ctx, "make_ctx failed");

    ha_elect_evaluate_and_signal(&ha, ctx);

    TEST_ASSERT_EQUAL_INT_MESSAGE(0, g_phase2_call_count,
        "cluster_init_phase2 must NOT be called when phase2_done=1 (RDHUP failover)");

    free_ctx(ctx);
    ha_fini(&ha);
    clear_hook();
    printf("test_rdhup_second_election_skips_phase2: PASS (calls=%d)\n", g_phase2_call_count);
}

/* ── Test 4: COMMITTING path resets repl_ack_count ──────────────────────── */

static void test_committing_resets_repl_ack_count(void)
{
    /* Req 5.2: repl_ack_count must be 0 when entering COMMITTING.
     * Start with a non-zero value to verify it gets reset. */
    reset_counters();

    ha_state_t ha;
    ha_init(&ha, &g_cfg, 0);
    ha.phase2_done = 1; /* skip phase2 call */
    atomic_store_explicit(&ha.repl_ack_count, 3, memory_order_release); /* stale count */
    atomic_store_explicit(&ha.role, (int32_t)CTRL_ELECTING, memory_order_release);

    ha_elect_ctx_t *ctx = make_ctx(0, 1); /* wins */
    TEST_ASSERT_NOT_NULL_MESSAGE(ctx, "make_ctx failed");

    ha_elect_evaluate_and_signal(&ha, ctx);

    int ack_count = atomic_load_explicit(&ha.repl_ack_count, memory_order_acquire);
    TEST_ASSERT_EQUAL_INT_MESSAGE(0, ack_count,
        "ha->repl_ack_count must be reset to 0 when entering CTRL_PRIMARY_COMMITTING");

    free_ctx(ctx);
    ha_fini(&ha);
    clear_hook();
    printf("test_committing_resets_repl_ack_count: PASS (repl_ack_count=%d)\n", ack_count);
}

/* ── Test 5: losing election → CTRL_STANDBY, phase2 called on first boot ── */

static void test_losing_election_enters_standby(void)
{
    /* n_other=2, quorum=2, votes_granted=1 (self only) → loses.
     * On first boot, phase2 must still be called; role → CTRL_STANDBY. */
    reset_counters();

    ha_state_t ha;
    ha_init(&ha, &g_cfg, 0);
    ha.phase2_done = 0; /* first boot */
    atomic_store_explicit(&ha.role, (int32_t)CTRL_ELECTING, memory_order_release);

    ha_elect_ctx_t *ctx = make_ctx(2, 1); /* votes_granted=1, quorum=2 → loses */
    TEST_ASSERT_NOT_NULL_MESSAGE(ctx, "make_ctx failed");

    ctrl_role_t result = ha_elect_evaluate_and_signal(&ha, ctx);

    TEST_ASSERT_EQUAL_INT_MESSAGE((int)CTRL_STANDBY, (int)result,
        "ha_elect_evaluate_and_signal must return CTRL_STANDBY when quorum not won");

    ctrl_role_t actual_role =
        (ctrl_role_t)atomic_load_explicit(&ha.role, memory_order_acquire);
    TEST_ASSERT_EQUAL_INT_MESSAGE((int)CTRL_STANDBY, (int)actual_role,
        "ha->role must be CTRL_STANDBY after losing election");

    TEST_ASSERT_EQUAL_INT_MESSAGE(1, g_phase2_call_count,
        "cluster_init_phase2 must be called once even for losing standby (first boot)");
    TEST_ASSERT_EQUAL_INT_MESSAGE(1, ha.phase2_done,
        "ha->phase2_done must be set to 1 after losing first-boot election");

    free_ctx(ctx);
    ha_fini(&ha);
    clear_hook();
    printf("test_losing_election_enters_standby: PASS (role=%d==CTRL_STANDBY, phase2=%d)\n",
           (int)actual_role, g_phase2_call_count);
}

/* ── Test 6: election timeout fires evaluate → COMMITTING if wins ────────── */

static void test_election_timeout_fn_fires_evaluate(void)
{
    /* election_timeout_fn calls ha_elect_evaluate_and_signal.
     * Use election_timeout_fn_for_test (XCE_TESTING shim in ha.c):
     *   election_timeout_fn_for_test(ha, ctx, cancelled=0) → fires evaluate.
     *   election_timeout_fn_for_test(ha, ctx, cancelled=1) → no-op.
     */
    reset_counters();

    ha_state_t ha;
    ha_init(&ha, &g_cfg, 0);
    ha.phase2_done = 1; /* skip phase2 */
    atomic_store_explicit(&ha.role, (int32_t)CTRL_ELECTING, memory_order_release);

    ha_elect_ctx_t *ctx = make_ctx(0, 1); /* single-node wins */
    TEST_ASSERT_NOT_NULL_MESSAGE(ctx, "make_ctx failed");

    /* Use the test-shim to simulate the timeout firing with cancelled=0 */
    extern int election_timeout_fn_for_test(ha_state_t *ha, ha_elect_ctx_t *ctx,
                                            int cancelled_val);
    election_timeout_fn_for_test(&ha, ctx, 0 /* not cancelled */);

    ctrl_role_t role =
        (ctrl_role_t)atomic_load_explicit(&ha.role, memory_order_acquire);
    TEST_ASSERT_EQUAL_INT_MESSAGE((int)CTRL_PRIMARY_COMMITTING, (int)role,
        "election_timeout_fn (not cancelled) must drive ha->role to CTRL_PRIMARY_COMMITTING");

    free_ctx(ctx);
    ha_fini(&ha);
    clear_hook();
    printf("test_election_timeout_fn_fires_evaluate: PASS (role=%d)\n", (int)role);
}

/* ── Test 7: cancelled election timeout → no role change ────────────────── */

static void test_cancelled_timeout_is_noop(void)
{
    reset_counters();

    ha_state_t ha;
    ha_init(&ha, &g_cfg, 0);
    ha.phase2_done = 1;
    atomic_store_explicit(&ha.role, (int32_t)CTRL_ELECTING, memory_order_release);

    ha_elect_ctx_t *ctx = make_ctx(0, 1);
    TEST_ASSERT_NOT_NULL_MESSAGE(ctx, "make_ctx failed");

    extern int election_timeout_fn_for_test(ha_state_t *ha, ha_elect_ctx_t *ctx,
                                            int cancelled_val);
    election_timeout_fn_for_test(&ha, ctx, 1 /* cancelled */);

    ctrl_role_t role =
        (ctrl_role_t)atomic_load_explicit(&ha.role, memory_order_acquire);
    /* Role must still be CTRL_ELECTING — cancelled, nothing happened */
    TEST_ASSERT_EQUAL_INT_MESSAGE((int)CTRL_ELECTING, (int)role,
        "cancelled election_timeout_fn must not change ha->role");

    free_ctx(ctx);
    ha_fini(&ha);
    clear_hook();
    printf("test_cancelled_timeout_is_noop: PASS (role still CTRL_ELECTING)\n");
}

/* ── Test 8: done_posted guard prevents double-execute ───────────────────── */

static void test_done_posted_prevents_double_execute(void)
{
    /* Calling ha_elect_evaluate_and_signal twice on the same ctx must be a no-op
     * on the second call (done_posted guard). */
    reset_counters();

    ha_state_t ha;
    ha_init(&ha, &g_cfg, 0);
    ha.phase2_done = 0;
    atomic_store_explicit(&ha.role, (int32_t)CTRL_ELECTING, memory_order_release);

    ha_elect_ctx_t *ctx = make_ctx(0, 1); /* wins */
    TEST_ASSERT_NOT_NULL_MESSAGE(ctx, "make_ctx failed");

    ha_elect_evaluate_and_signal(&ha, ctx); /* first call: phase2_done→1, role→COMMITTING */
    /* Reset phase2_done to detect a second call attempt */
    ha.phase2_done = 0;
    ha_elect_evaluate_and_signal(&ha, ctx); /* second call: done_posted=1, should no-op */

    /* phase2_call_count must still be 1 (second call was no-op) */
    TEST_ASSERT_EQUAL_INT_MESSAGE(1, g_phase2_call_count,
        "done_posted guard must prevent cluster_init_phase2 from being called twice");

    free_ctx(ctx);
    ha_fini(&ha);
    clear_hook();
    printf("test_done_posted_prevents_double_execute: PASS (calls=%d)\n", g_phase2_call_count);
}

/* ── Test 9: committing_timeout_fn fires ha_promote_to_primary ───────────── */

static void test_committing_timeout_fn_promotes_to_primary(void)
{
    /* Req 4.3, 8.4: when not cancelled and role == CTRL_PRIMARY_COMMITTING,
     * committing_timeout_fn must call ha_promote_to_primary, which drives
     * c->ha.role to CTRL_PRIMARY (degraded promotion). */
    reset_counters();

    /* Zero-init cluster: xce_add_hook returns -EINVAL harmlessly on zeroed
     * hooksys, so ha_promote_to_primary is safe to call (comment at ha.c:603). */
    cluster_t c;
    memset(&c, 0, sizeof(c));
    ha_init(&c.ha, &g_cfg, 0);
    atomic_store_explicit(&c.ha.role, (int32_t)CTRL_PRIMARY_COMMITTING,
                          memory_order_release);

    extern int committing_timeout_fn_for_test(ha_state_t *ha, cluster_t *c,
                                              int cancelled_val);
    committing_timeout_fn_for_test(&c.ha, &c, 0 /* not cancelled */);

    ctrl_role_t role =
        (ctrl_role_t)atomic_load_explicit(&c.ha.role, memory_order_acquire);
    TEST_ASSERT_EQUAL_INT_MESSAGE((int)CTRL_PRIMARY, (int)role,
        "committing_timeout_fn (not cancelled, COMMITTING role) must promote to CTRL_PRIMARY");

    ha_fini(&c.ha);
    clear_hook();
    printf("test_committing_timeout_fn_promotes_to_primary: PASS (role=%d==CTRL_PRIMARY)\n",
           (int)role);
}

/* ── Test 10: cancelled committing_timeout_fn → no role change ───────────── */

static void test_committing_timeout_fn_cancelled_is_noop(void)
{
    /* Req 4.3: when cancelled=1, committing_timeout_fn must be a no-op;
     * ha->role must remain CTRL_PRIMARY_COMMITTING. */
    reset_counters();

    cluster_t c;
    memset(&c, 0, sizeof(c));
    ha_init(&c.ha, &g_cfg, 0);
    atomic_store_explicit(&c.ha.role, (int32_t)CTRL_PRIMARY_COMMITTING,
                          memory_order_release);

    extern int committing_timeout_fn_for_test(ha_state_t *ha, cluster_t *c,
                                              int cancelled_val);
    committing_timeout_fn_for_test(&c.ha, &c, 1 /* cancelled */);

    ctrl_role_t role =
        (ctrl_role_t)atomic_load_explicit(&c.ha.role, memory_order_acquire);
    TEST_ASSERT_EQUAL_INT_MESSAGE((int)CTRL_PRIMARY_COMMITTING, (int)role,
        "cancelled committing_timeout_fn must not change ha->role");

    ha_fini(&c.ha);
    clear_hook();
    printf("test_committing_timeout_fn_cancelled_is_noop: PASS (role still CTRL_PRIMARY_COMMITTING)\n");
}

/* ── Task 4.1 (ha-repl-hardening): ha_compute_safe_committed_lsn ────────────
 *
 * Computes safe_committed_lsn and safe_config_tag from the vote replies stored
 * in ha_elect_ctx_t.votes[] after winning an election.
 *
 * Algorithm: collect LSNs from all granted voters (including self at votes[0].my_lsn),
 * sort descending, take the value at index floor(n_granted/2) (i.e. the majority
 * threshold element) — this is the highest LSN held by a majority.
 *
 * Same logic applies for config tags (peer_tag).
 *
 * Requirements: 2.3 (ha-repl-hardening spec)
 * Design ref: design.md §Flow 0: Post-Election — Determine Safe Commit Point
 */
#ifdef XCE_TESTING
extern void ha_compute_safe_committed_lsn(ha_elect_ctx_t *ctx,
                                           uint64_t       *safe_lsn_out,
                                           uint64_t       *safe_tag_out);
#endif

/*
 * Test case A (from task description):
 * 3-node cluster — self at lsn=100, peer0 granted at lsn=99, peer1 granted at lsn=100
 * Sorted granted LSNs desc: [100 (self), 100 (peer1), 99 (peer0)]
 * Majority threshold for 3 granted = ceil(3/2) = 2; element at index 1 (0-based) = 100
 * → safe_committed_lsn = 100
 */
static void test_safe_committed_lsn_two_peers_at_99_and_100(void)
{
#ifdef XCE_TESTING
    /* n_other=2: ctx->votes[] has 2 entries */
    ha_elect_ctx_t *ctx = calloc(1, sizeof(*ctx) + 2 * sizeof(ctx->votes[0]));
    TEST_ASSERT_NOT_NULL(ctx);
    ctx->n_peers       = 2;       /* 2 other peers */
    ctx->votes_granted = 3;       /* self + 2 peers granted */
    ctx->n_replied     = 2;
    pthread_mutex_init(&ctx->lock, NULL);
    sem_init(&ctx->done, 0, 0);

    /* Self data: self_lsn/self_tag (task 6.3) and votes[0].my_lsn/my_tag */
    ctx->self_lsn              = 100;
    ctx->self_tag              = 5;
    ctx->votes[0].my_lsn      = 100;
    ctx->votes[0].my_tag      = 5;
    ctx->votes[0].vote_granted = 1;  /* peer0: granted, lsn=99 */
    ctx->votes[0].peer_lsn    = 99;
    ctx->votes[0].peer_tag    = 5;

    ctx->votes[1].vote_granted = 1;  /* peer1: granted, lsn=100 */
    ctx->votes[1].peer_lsn    = 100;
    ctx->votes[1].peer_tag    = 5;

    uint64_t safe_lsn = 0, safe_tag = 0;
    ha_compute_safe_committed_lsn(ctx, &safe_lsn, &safe_tag);

    TEST_ASSERT_EQUAL_UINT64_MESSAGE(100, safe_lsn,
        "voters [99,100] + self=100 → safe_committed_lsn must be 100");
    TEST_ASSERT_EQUAL_UINT64_MESSAGE(5, safe_tag,
        "voters all at tag=5 → safe_config_tag must be 5");

    free_ctx(ctx);
    printf("test_safe_committed_lsn_two_peers_at_99_and_100: PASS (safe_lsn=%" PRIu64
           ", safe_tag=%" PRIu64 ")\n", safe_lsn, safe_tag);
#else
    printf("test_safe_committed_lsn_two_peers_at_99_and_100: SKIP (non-test build)\n");
#endif
}

/*
 * Test case B (from task description):
 * 3-node cluster — self at lsn=100, peer0 granted at lsn=50, peer1 granted at lsn=51
 * Sorted granted LSNs desc: [100 (self), 51 (peer1), 50 (peer0)]
 * Majority threshold for 3 granted = 2; element at index 1 = 51
 * → safe_committed_lsn = 51
 */
static void test_safe_committed_lsn_two_peers_at_50_and_51(void)
{
#ifdef XCE_TESTING
    ha_elect_ctx_t *ctx = calloc(1, sizeof(*ctx) + 2 * sizeof(ctx->votes[0]));
    TEST_ASSERT_NOT_NULL(ctx);
    ctx->n_peers       = 2;
    ctx->votes_granted = 3;
    ctx->n_replied     = 2;
    pthread_mutex_init(&ctx->lock, NULL);
    sem_init(&ctx->done, 0, 0);

    ctx->self_lsn              = 100;
    ctx->self_tag              = 5;
    ctx->votes[0].my_lsn      = 100;
    ctx->votes[0].my_tag      = 5;
    ctx->votes[0].vote_granted = 1;  /* peer0: granted, lsn=50 */
    ctx->votes[0].peer_lsn    = 50;
    ctx->votes[0].peer_tag    = 5;

    ctx->votes[1].vote_granted = 1;  /* peer1: granted, lsn=51 */
    ctx->votes[1].peer_lsn    = 51;
    ctx->votes[1].peer_tag    = 5;

    uint64_t safe_lsn = 0, safe_tag = 0;
    ha_compute_safe_committed_lsn(ctx, &safe_lsn, &safe_tag);

    TEST_ASSERT_EQUAL_UINT64_MESSAGE(51, safe_lsn,
        "voters [50,51] + self=100 → safe_committed_lsn must be 51");

    free_ctx(ctx);
    printf("test_safe_committed_lsn_two_peers_at_50_and_51: PASS (safe_lsn=%" PRIu64 ")\n",
           safe_lsn);
#else
    printf("test_safe_committed_lsn_two_peers_at_50_and_51: SKIP (non-test build)\n");
#endif
}

/*
 * Test case C: single-node cluster (n_peers=0, no votes[] entries).
 * safe_committed_lsn must equal self's own applied_lsn (self is the only majority).
 * Req 2.3 / task 6.3: returning 0 would truncate all WAL on re-election — wrong.
 * The fix (task 6.3): ha_elect_ctx_t gains self_lsn/self_tag fields populated
 * unconditionally by ha_start_election_async; ha_compute_safe_committed_lsn
 * returns ctx->self_lsn for the n_peers=0 case.
 */
static void test_safe_committed_lsn_single_node(void)
{
#ifdef XCE_TESTING
    ha_elect_ctx_t *ctx = calloc(1, sizeof(*ctx));
    TEST_ASSERT_NOT_NULL(ctx);
    ctx->n_peers       = 0;
    ctx->votes_granted = 1;   /* self-vote only */
    ctx->n_replied     = 0;
    /* Task 6.3: self_lsn/self_tag populated unconditionally */
    ctx->self_lsn      = 77;
    ctx->self_tag      = 3;
    pthread_mutex_init(&ctx->lock, NULL);
    sem_init(&ctx->done, 0, 0);

    uint64_t safe_lsn = 0xDEAD, safe_tag = 0xDEAD;
    ha_compute_safe_committed_lsn(ctx, &safe_lsn, &safe_tag);

    /* Single-node: safe_committed_lsn must equal self_lsn (not 0) */
    TEST_ASSERT_EQUAL_UINT64_MESSAGE(77, safe_lsn,
        "single-node (n_peers=0): safe_committed_lsn must equal self_lsn (77), not 0");
    TEST_ASSERT_EQUAL_UINT64_MESSAGE(3, safe_tag,
        "single-node (n_peers=0): safe_config_tag must equal self_tag (3), not 0");

    free_ctx(ctx);
    printf("test_safe_committed_lsn_single_node: PASS (safe_lsn=%" PRIu64 ")\n", safe_lsn);
#else
    printf("test_safe_committed_lsn_single_node: SKIP (non-test build)\n");
#endif
}

/*
 * Test case D: only one peer but it didn't grant vote.
 * Only self vote is in the granted set; n_granted=1, majority threshold index=0.
 * safe_lsn should be from the only granted voter (self), but since self's lsn
 * is in votes[0].my_lsn, result should reflect that.
 * This tests the partial-grant scenario.
 */
static void test_safe_committed_lsn_one_peer_denied(void)
{
#ifdef XCE_TESTING
    ha_elect_ctx_t *ctx = calloc(1, sizeof(*ctx) + 1 * sizeof(ctx->votes[0]));
    TEST_ASSERT_NOT_NULL(ctx);
    ctx->n_peers       = 1;       /* 1 other peer */
    ctx->votes_granted = 1;       /* only self-vote granted */
    ctx->n_replied     = 1;
    pthread_mutex_init(&ctx->lock, NULL);
    sem_init(&ctx->done, 0, 0);

    ctx->self_lsn              = 200;
    ctx->self_tag              = 7;
    ctx->votes[0].my_lsn      = 200;
    ctx->votes[0].my_tag      = 7;
    ctx->votes[0].vote_granted = 0;  /* peer denied vote */
    ctx->votes[0].peer_lsn    = 150;
    ctx->votes[0].peer_tag    = 7;

    uint64_t safe_lsn = 0, safe_tag = 0;
    ha_compute_safe_committed_lsn(ctx, &safe_lsn, &safe_tag);

    /* Only self granted (my_lsn=200). n_granted=1, majority index=0 → lsn=200 */
    TEST_ASSERT_EQUAL_UINT64_MESSAGE(200, safe_lsn,
        "only self granted (my_lsn=200): safe_committed_lsn must be 200");

    free_ctx(ctx);
    printf("test_safe_committed_lsn_one_peer_denied: PASS (safe_lsn=%" PRIu64 ")\n",
           safe_lsn);
#else
    printf("test_safe_committed_lsn_one_peer_denied: SKIP (non-test build)\n");
#endif
}

/* ── Task 4.2 (ha-repl-hardening): committed_lsn set to safe_committed_lsn ──
 *
 * raft_cb_become_leader must set ha->last_known_committed_lsn to the value
 * returned by ha_compute_safe_committed_lsn after WAL truncation.
 *
 * This ensures that in test mode (c == NULL) the decision loop reads the
 * correct committed_lsn from ha->last_known_committed_lsn (see decision-loop
 * XCE_TESTING path in ha.c).
 *
 * Requirement 2.3 (ha-repl-hardening): safe_committed_lsn is derived from
 * voter replies; entries at or below it survive truncation; entries above are
 * removed.
 *
 * The test uses raft_cb_become_leader_for_test (XCE_TESTING shim) which calls
 * raft_cb_become_leader with ha->raft_c = NULL (no real cluster, no WAL I/O).
 * The WAL-level truncation behaviour (file entries above safe_lsn deleted) is
 * covered by test_persist_truncate.c; this test focuses on the committed_lsn
 * field assignment that task 4.2 adds.
 *
 * Design ref: design.md §Flow 0 step 5: committed_lsn = safe_committed_lsn
 */

#ifdef XCE_TESTING
extern void raft_cb_become_leader_for_test(ha_state_t *ha, uint64_t term);
#endif

/*
 * Test E: raft_cb_become_leader sets ha->last_known_committed_lsn = safe_lsn.
 *
 * 3-node cluster (n_other=2, votes_granted=3):
 *   votes[0]: my_lsn=200, peer_lsn=100, vote_granted=1
 *   votes[1]: peer_lsn=150, vote_granted=1
 *
 * Sorted granted LSNs desc: [200 (self), 150 (peer1), 100 (peer0)]
 * Majority threshold for 3 granted = ceil(3/2) = 2; element at index 1 = 150
 * → safe_committed_lsn = 150
 *
 * After raft_cb_become_leader_for_test, ha->last_known_committed_lsn must == 150.
 *
 * Additionally verify via ha_compute_safe_committed_lsn that entry AT safe_lsn
 * (lsn=150) is the boundary: safe_lsn=150 means truncate ABOVE 150 (entries
 * 151+ removed); entry at 150 is preserved.
 */
static void test_become_leader_sets_committed_lsn_to_safe_lsn(void)
{
#ifdef XCE_TESTING
    reset_counters();

    ha_state_t ha;
    ha_init(&ha, &g_cfg, 0);
    ha.phase2_done = 1;  /* skip phase2 in this test */

    /* Build elect_ctx with 2 peers; safe_lsn will be 150 */
    ha_elect_ctx_t *ctx = calloc(1, sizeof(*ctx) + 2 * sizeof(ctx->votes[0]));
    TEST_ASSERT_NOT_NULL(ctx);
    ctx->n_peers       = 2;
    ctx->votes_granted = 3;   /* self + 2 peers */
    ctx->n_replied     = 2;
    pthread_mutex_init(&ctx->lock, NULL);
    sem_init(&ctx->done, 0, 0);

    /* Self data in self_lsn/self_tag (task 6.3) and votes[0].my_lsn/my_tag */
    ctx->self_lsn              = 200;
    ctx->self_tag              = 5;
    /* votes[0]: self data (my_lsn=200) + peer0 granted at lsn=100 */
    ctx->votes[0].my_lsn      = 200;
    ctx->votes[0].my_tag      = 5;
    ctx->votes[0].vote_granted = 1;
    ctx->votes[0].peer_lsn    = 100;
    ctx->votes[0].peer_tag    = 5;

    /* votes[1]: peer1 granted at lsn=150 */
    ctx->votes[1].vote_granted = 1;
    ctx->votes[1].peer_lsn    = 150;
    ctx->votes[1].peer_tag    = 5;

    /* Verify the safe_lsn computation independently */
    uint64_t safe_lsn = 0, safe_tag = 0;
    ha_compute_safe_committed_lsn(ctx, &safe_lsn, &safe_tag);
    TEST_ASSERT_EQUAL_UINT64_MESSAGE(150, safe_lsn,
        "ha_compute_safe_committed_lsn: voters [100,150]+self=200 → safe_lsn must be 150");

    /* Wire elect_ctx into ha_state so raft_cb_become_leader can read it */
    atomic_store_explicit(&ha.elect_ctx, (void *)ctx, memory_order_release);

    /* Drive the leader promotion path (c=NULL → no WAL I/O, no phase2) */
    raft_cb_become_leader_for_test(&ha, /*term=*/1);

    /* Task 4.2: ha->last_known_committed_lsn must equal safe_lsn (150) */
    uint64_t committed_lsn =
        atomic_load_explicit(&ha.last_known_committed_lsn, memory_order_acquire);
    TEST_ASSERT_EQUAL_UINT64_MESSAGE(150, committed_lsn,
        "raft_cb_become_leader must set ha->last_known_committed_lsn = safe_lsn (150); "
        "WAL entry AT safe_lsn=150 is preserved; entries above 150 are truncated");

    sem_destroy(&ctx->done);
    pthread_mutex_destroy(&ctx->lock);
    free(ctx);
    ha_fini(&ha);
    clear_hook();
    printf("test_become_leader_sets_committed_lsn_to_safe_lsn: PASS "
           "(committed_lsn=%" PRIu64 ")\n", committed_lsn);
#else
    printf("test_become_leader_sets_committed_lsn_to_safe_lsn: SKIP (non-test build)\n");
#endif
}

/* ── Suite entry point ───────────────────────────────────────────────────── */

void test_ha_evaluate_committing(void)
{
    RUN_TEST(test_winning_quorum_enters_committing);
    RUN_TEST(test_first_boot_phase2_called_once);
    RUN_TEST(test_rdhup_second_election_skips_phase2);
    RUN_TEST(test_committing_resets_repl_ack_count);
    RUN_TEST(test_losing_election_enters_standby);
    RUN_TEST(test_election_timeout_fn_fires_evaluate);
    RUN_TEST(test_cancelled_timeout_is_noop);
    RUN_TEST(test_done_posted_prevents_double_execute);
    RUN_TEST(test_committing_timeout_fn_promotes_to_primary);
    RUN_TEST(test_committing_timeout_fn_cancelled_is_noop);
    /* Task 4.1 (ha-repl-hardening): safe committed LSN computation */
    RUN_TEST(test_safe_committed_lsn_two_peers_at_99_and_100);
    RUN_TEST(test_safe_committed_lsn_two_peers_at_50_and_51);
    RUN_TEST(test_safe_committed_lsn_single_node);
    RUN_TEST(test_safe_committed_lsn_one_peer_denied);
    /* Task 4.2 (ha-repl-hardening): committed_lsn set to safe_committed_lsn */
    RUN_TEST(test_become_leader_sets_committed_lsn_to_safe_lsn);
}