Files
vdm/daemon/tests/sched_scheduler_test.cpp
T
samiandClaude Sonnet 5 824fa481bb daemon: event.* fan-out (D5) + category.list/queue.list (D3) — GUI-ready
The two items aimed at pointing GUI at a real veloxd instead of mockd.

rpc/event_hub — per-subscription fan-out shared by both transports.
subscribe() registers a connection with no interest; set_filter()
(session.subscribe, replaces not adds) turns on event kinds and an
optional per-task id filter; publish() delivers a pre-built
notification to every matching subscriber. session.subscribe on both
UdsServer and WsServer now does the real thing — registers/updates a
subscription, tears it down in close_conn.

sched/scheduler — the on_engine_state hook now actually publishes:
- transition() is the one place a task's row changes state; it reads
  the store's own prior row for previousState (authoritative
  regardless of engine/scheduler timing), writes the error columns,
  and — when a hub is supplied — publishes event.task.state with
  {taskId, state, previousState, summary, error}. Wired into every
  transition: scheduler-driven (admission -> probing, resume ->
  connecting, pause) and engine-reported (on_engine_state).
- progress_snapshot(): one row per task the engine is tracking
  (EnginePort::progress(), a new interface method backed by
  DownloadHandle::progress()), plus a store side-effect
  (Tasks::update_progress) so download.list/get stay current between
  state transitions. Returns rows; does NOT publish itself — batching
  into one array message is the caller's job, per the schema's
  x-maxRateHz: 4 and AGENT-DAEMON.md item 5 ("one message per task per
  tick burns a core"). main.cpp's 250 ms timerfd is that caller: one
  event.task.progress per tick, only when there's something to say.

dispatcher::on_download_add now publishes event.task.added (schema:
"summary is always present so a client can insert the row without a
follow-up download.get").

store/categories, store/queues — the two D3 handlers GUI's panels
call. category.list projects the six seeded built-ins; queue.list
derives taskIds from tasks.queue_id/queue_position (Queue's own schema
note: a queue's stored row never carries membership, download.update
/ queue.reorder do).

Verified live end to end against tools/testserver: a subscribed client
sees event.task.added on add, then the full event.task.state sequence
(queued -> probing -> connecting -> downloading -> assembling ->
verifying -> complete) with correct previousState at every step, and
real category.list / queue.list results.

Tests: event_hub (filter-by-kind, filter-by-task-id, replace-not-add,
unsubscribe), store_categories_queues, plus new sched_scheduler cases
for event.task.state publishing and progress_snapshot's store
side-effect. 38 daemon/cli tests green; sched_scheduler / event_hub /
ws_server / uds_roundtrip TSan-clean.

deferrals.md: D5 mostly closed (event.task.removed and the
still-unpublished events wait on their owning D3 handlers); D3 down to
the remaining download.* verbs, rules/settings/limiter/schedule,
queue mutation, category mutation, grabber, media.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Upd9WhG9oppieig5nRDLig
2026-09-11 07:19:11 +04:00

265 lines
11 KiB
C++

// Scheduler against a FakeEnginePort and an in-memory store: admission, priority order,
// queue stop, restart reconciliation, and the engine-state -> store projection.
#include <string>
#include <nlohmann/json.hpp>
#include "check.hpp"
#include "rpc/event_hub.hpp"
#include "sched/fake_engine_port.hpp"
#include "sched/governor.hpp"
#include "sched/scheduler.hpp"
#include "store/migrations.hpp"
#include "store/settings.hpp"
#include "store/sqlite.hpp"
#include "store/tasks.hpp"
using namespace velox::daemon;
using sched::FakeEnginePort;
using sched::Governor;
using sched::GovernorConfig;
using sched::Scheduler;
namespace {
store::TaskRow task(std::string id, std::string state, std::string created,
std::optional<std::string> queue = std::nullopt, std::int64_t pos = 0) {
store::TaskRow r;
r.task_id = std::move(id);
r.url = "https://cdn.example/" + r.task_id;
r.save_dir = "/tmp";
r.filename = r.task_id + ".bin";
r.state = std::move(state);
r.created_at = std::move(created);
r.queue_id = std::move(queue);
if (r.queue_id) r.queue_position = pos;
return r;
}
std::string task_state(store::Db& db, const std::string& id) {
store::Tasks t(db);
auto g = t.get(id);
return (g && *g) ? (*g)->state : std::string("<none>");
}
} // namespace
void run() {
auto db = store::Db::open(":memory:");
CHECK(db.has_value());
if (!db) return;
CHECK(store::migrate_to_head(*db).has_value());
store::Tasks tasks(*db);
// --- admission: 4 queued, cap 2 -> start the 2 oldest, in order -----------------
{
FakeEnginePort engine;
Scheduler sched(*db, engine,
Governor(GovernorConfig{.max_concurrent_downloads = 2,
.max_active_segments = 32}));
for (int i = 0; i < 4; ++i)
CHECK(tasks.insert(task("a" + std::to_string(i), "queued",
"2026-09-10T10:0" + std::to_string(i) + ":00Z"))
.has_value());
CHECK(sched.tick().has_value());
CHECK_EQ(engine.starts.size(), 2u);
CHECK_EQ(engine.starts[0].url, std::string("https://cdn.example/a0"));
CHECK_EQ(engine.starts[1].url, std::string("https://cdn.example/a1"));
CHECK_EQ(engine.starts[0].save_path, std::string("/tmp/a0.bin"));
CHECK_EQ(task_state(*db, "a0"), std::string("probing"));
CHECK_EQ(task_state(*db, "a2"), std::string("queued")); // not admitted
// set_task_order carries exactly the started tasks, oldest first.
CHECK_EQ(engine.last_order().size(), 2u);
CHECK(engine.last_order()[0] == engine.starts[0].id);
// A second tick with no free slots starts nothing new.
CHECK(sched.tick().has_value());
CHECK_EQ(engine.starts.size(), 2u);
}
// --- engine reports downloading, then one completes -> a slot frees ------------
{
for (const char* id : {"a0", "a1", "a2", "a3"}) tasks.remove(id);
FakeEnginePort engine;
Scheduler sched(*db, engine,
Governor(GovernorConfig{.max_concurrent_downloads = 1,
.max_active_segments = 32}));
CHECK(tasks.insert(task("b0", "queued", "2026-09-10T10:00:00Z")).has_value());
CHECK(tasks.insert(task("b1", "queued", "2026-09-10T10:01:00Z")).has_value());
CHECK(sched.tick().has_value());
CHECK_EQ(engine.starts.size(), 1u); // b0 only
CHECK_EQ(task_state(*db, "b0"), std::string("probing"));
sched.on_engine_state("b0", "probing", "downloading", std::nullopt);
CHECK_EQ(task_state(*db, "b0"), std::string("downloading"));
sched.on_engine_state("b0", "downloading", "complete", std::nullopt);
CHECK_EQ(task_state(*db, "b0"), std::string("complete"));
CHECK(sched.tick().has_value()); // b0 terminal -> b1 admitted
CHECK_EQ(engine.starts.size(), 2u);
CHECK_EQ(engine.starts[1].url, std::string("https://cdn.example/b1"));
}
// --- a stopped queue: running tasks get paused with reason queue_stopped -------
{
for (const char* id : {"b0", "b1"}) tasks.remove(id);
CHECK(db->exec("UPDATE queues SET state='running' WHERE queue_id='main'").has_value());
FakeEnginePort engine;
Scheduler sched(*db, engine,
Governor(GovernorConfig{.max_concurrent_downloads = 10,
.max_active_segments = 32}));
CHECK(tasks.insert(task("q0", "queued", "2026-09-10T10:00:00Z", "main", 0)).has_value());
CHECK(sched.tick().has_value());
CHECK_EQ(engine.starts.size(), 1u);
sched.on_engine_state("q0", "connecting", "downloading", std::nullopt);
CHECK(db->exec("UPDATE queues SET state='stopped' WHERE queue_id='main'").has_value());
CHECK(sched.tick().has_value());
CHECK_EQ(engine.paused.size(), 1u);
CHECK_EQ(task_state(*db, "q0"), std::string("paused"));
store::Tasks t(*db);
CHECK_EQ(t.get("q0").value().value().pause_reason.value_or(""), std::string("queue_stopped"));
// Restart the queue -> the task resumes (not a fresh start).
CHECK(db->exec("UPDATE queues SET state='running' WHERE queue_id='main'").has_value());
CHECK(sched.tick().has_value());
CHECK_EQ(engine.resumed.size(), 1u);
CHECK_EQ(engine.starts.size(), 1u); // no new start
}
// --- an engine auto-pause (error present) -> pause_reason 'auto', not touched --
{
for (const char* id : {"q0"}) tasks.remove(id);
FakeEnginePort engine;
Scheduler sched(*db, engine,
Governor(GovernorConfig{.max_concurrent_downloads = 10,
.max_active_segments = 32}));
CHECK(tasks.insert(task("auth", "queued", "2026-09-10T10:00:00Z")).has_value());
CHECK(sched.tick().has_value());
sched::TaskErrorFields ef;
ef.code = "auth_required";
ef.message = "401";
ef.http_status = 401;
sched.on_engine_state("auth", "connecting", "paused", ef);
store::Tasks t(*db);
auto row = t.get("auth").value().value();
CHECK_EQ(row.state, std::string("paused"));
CHECK_EQ(row.pause_reason.value_or(""), std::string("auto"));
CHECK_EQ(row.error_code.value_or(""), std::string("auth_required"));
// A tick must NOT resume an auto-paused task.
engine.resumed.clear();
CHECK(sched.tick().has_value());
CHECK_EQ(engine.resumed.size(), 0u);
}
// --- reconcile_after_restart: CORE-owned states -> queued --------------------
{
for (const char* id : {"auth"}) tasks.remove(id);
CHECK(tasks.insert(task("r0", "downloading", "2026-09-10T10:00:00Z")).has_value());
CHECK(tasks.insert(task("r1", "verifying", "2026-09-10T10:01:00Z")).has_value());
CHECK(tasks.insert(task("r2", "paused", "2026-09-10T10:02:00Z")).has_value());
CHECK(db->exec("UPDATE tasks SET pause_reason='user' WHERE task_id='r2'").has_value());
FakeEnginePort engine;
Scheduler sched(*db, engine, Governor(GovernorConfig{}));
CHECK(sched.reconcile_after_restart().has_value());
CHECK_EQ(task_state(*db, "r0"), std::string("queued"));
CHECK_EQ(task_state(*db, "r1"), std::string("queued"));
CHECK_EQ(task_state(*db, "r2"), std::string("paused")); // paused survives
store::Tasks t(*db);
CHECK_EQ(t.get("r2").value().value().pause_reason.value_or(""), std::string("user"));
}
// --- reload_config pushes the caps to the engine ---------------------------
{
store::Settings settings(*db);
CHECK(settings.set_raw("connection.maxActiveSegments", "12").has_value());
FakeEnginePort engine;
Scheduler sched(*db, engine, Governor(GovernorConfig{}));
CHECK(sched.reload_config().has_value());
CHECK_EQ(engine.max_active_segments.size(), 1u);
CHECK_EQ(engine.max_active_segments.back(), 12u);
CHECK_EQ(sched.reload_config().has_value() ? 0 : 1, 0);
}
// --- event.task.state: published on admission, on a paused transition, and on an
// engine-reported transition; previousState reflects the store's prior row ----------
{
for (const char* id : {"r0", "r1", "r2"}) tasks.remove(id); // leftover from above
FakeEnginePort engine;
rpc::EventHub hub;
Scheduler sched(*db, engine, Governor(GovernorConfig{.max_concurrent_downloads = 10,
.max_active_segments = 32}),
&hub);
std::vector<nlohmann::json> received;
const auto sub = hub.subscribe([&](const nlohmann::json& n) { received.push_back(n); });
hub.set_filter(sub, {velox::proto::Event::TaskState}, std::nullopt);
CHECK(tasks.insert(task("ev0", "queued", "2026-09-10T10:00:00Z")).has_value());
CHECK(sched.tick().has_value()); // admits ev0: queued -> probing
CHECK_EQ(received.size(), 1u);
CHECK_EQ(received[0]["params"]["taskId"].get<std::string>(), std::string("ev0"));
CHECK_EQ(received[0]["params"]["state"].get<std::string>(), std::string("probing"));
CHECK_EQ(received[0]["params"]["previousState"].get<std::string>(), std::string("queued"));
CHECK(received[0]["params"]["error"].is_null());
CHECK_EQ(received[0]["params"]["summary"]["taskId"].get<std::string>(), std::string("ev0"));
sched.on_engine_state("ev0", "probing", "downloading", std::nullopt);
CHECK_EQ(received.size(), 2u);
CHECK_EQ(received[1]["params"]["previousState"].get<std::string>(), std::string("probing"));
CHECK_EQ(received[1]["params"]["state"].get<std::string>(), std::string("downloading"));
sched::TaskErrorFields ef;
ef.code = "connection_reset";
ef.message = "reset";
sched.on_engine_state("ev0", "downloading", "paused", ef);
CHECK_EQ(received.size(), 3u);
CHECK(!received[2]["params"]["error"].is_null());
CHECK_EQ(received[2]["params"]["error"]["code"].get<std::string>(),
std::string("connection_reset"));
tasks.remove("ev0");
}
// --- progress_snapshot: only started tasks, plus a store side-effect --------------
{
FakeEnginePort engine;
Scheduler sched(*db, engine,
Governor(GovernorConfig{.max_concurrent_downloads = 10,
.max_active_segments = 32}));
CHECK(tasks.insert(task("pr0", "queued", "2026-09-10T10:00:00Z")).has_value());
CHECK(sched.tick().has_value());
CHECK_EQ(engine.starts.size(), 1u);
vdm::task::Progress p;
p.downloaded = 12345;
p.speed_bps = 999;
p.effective_segments = 4;
p.effective_buffer_bytes = 65536;
engine.fake_progress[engine.starts[0].id.value] = p;
const auto snap = sched.progress_snapshot();
CHECK_EQ(snap.size(), 1u);
CHECK_EQ(snap[0].task_id, std::string("pr0"));
CHECK_EQ(snap[0].downloaded_bytes, 12345u);
CHECK_EQ(snap[0].speed_bps, 999u);
auto row = tasks.get("pr0").value().value();
CHECK_EQ(row.downloaded_bytes, 12345);
CHECK_EQ(row.eff_segments, 4);
CHECK((row.eff_buffer_bytes.has_value() && *row.eff_buffer_bytes == 65536));
tasks.remove("pr0");
}
}
TEST_MAIN()