fix(worker): record real raw token usage per run, not the uncached remainder

task_runs.tokens_in only ever held the API's uncached "input_tokens" field
(off by a factor of ~400,000 on a resumed session), and tokens_out summed
only the last result event instead of the whole session. TaskRunner now
reads each run's cache-read/cache-write/input/output totals from the
session transcript via a new ITranscriptUsageReader.ReadSessionTotalsAsync,
storing the delta against prior runs on the same session so a --resume
doesn't double-count. New task_runs.cache_read_tokens/cache_write_tokens
columns; the Session tab now shows the raw total (what actually counts
against the 5h/7d usage limit) with a breakdown tooltip.

tests/ClaudeDo.Worker.Tests/External/AddSubtaskToolTests.cs

@@ -71,7 +71,7 @@ public sealed class AddSubtaskToolTests : IDisposable
         var argsBuilder = new ClaudeArgsBuilder();
         var state = TaskStateServiceBuilder.Build(dbFactory).State;
         var runner = new TaskRunner(fake, dbFactory, broadcaster, wtManager, argsBuilder, cfg,
-            NullLogger<TaskRunner>.Instance, state, new TaskRunTokenRegistry(), new AttachmentStore(), new FakeSessionSkillSeeder());
+            NullLogger<TaskRunner>.Instance, state, new TaskRunTokenRegistry(), new AttachmentStore(), new FakeSessionSkillSeeder(), new FakeTranscriptUsageReader());
         var waker = new ClaudeDo.Worker.Queue.QueueWaker();
         var picker = new ClaudeDo.Worker.Queue.QueuePicker(dbFactory);
         var runCancels = new RunCancellationRegistry();