diff --git a/.wolf/buglog.json b/.wolf/buglog.json
index 4d95fa08..6ade41ea 100644
--- a/.wolf/buglog.json
+++ b/.wolf/buglog.json
@@ -18231,6 +18231,31 @@
       ],
       "occurrences": 1,
       "last_seen": "2026-08-22T12:40:00Z"
+    },
+    {
+      "id": "bug-1624",
+      "timestamp": "2026-08-22T19:53:00Z",
+      "error_message": "None yet observed at runtime -- found via code trace while answering an architectural question about job RUN-state boundaries and over/under-commit safety.",
+      "file": "src/scheduler/src/scheduler.c, src/scheduler/src/core_session.c, src/scheduler/src/resource.c",
+      "root_cause": "sched_account_jobs() (scheduler.c:1258-1292) re-derives core->sharedInUse/worker->resInUse every round from scratch, but gates on JOB_IS_RUN(job->state) before checking job->accounts. A job that has been DISPATCHED (job->accounts set synchronously at commit-decision time via sched_commit_job_alloc(), scheduler.c:1446) but not yet confirmed RUN by the worker is still job->state==PEND, so it is skipped by this resum. Since xce_core_begin_session() (core_session.c:66-108) unconditionally zeroes sharedInUse/resInUse every round (normal-mode cadence: 1s, main.c:453-460), that job's charge -- correct within the round it was dispatched -- is wiped at the very next round and not restored until the RUN confirmation is processed. The admission check other jobs go through (sched_check_host_satisfy_/sched_check_shared_satisfy_, resource.c:252-370, called from seqjob_allocator.c:130) reads exactly this same resInUse/sharedInUse, with no separate reserved/committed pool (xce_sched_job_t has only state/allocs/accounts, sched/types.h:96-116) -- so once wiped, the resource looks free again and can be granted to a second job, a genuine over-commit/double-booking risk under any dispatch-to-worker-confirmation latency exceeding ~1 round (ordinary for real worker RPC + fork/exec).",
+      "fix": "NOT YET FIXED -- found during investigation, not yet remediated. Candidate direction: sched_account_jobs() (or an equivalent pass) needs to also re-sum jobs with accounts != NULL regardless of RUN state (mirroring the same decouple-from-state-gate pattern already being applied to simulation-mode capture in the scheduler-sim-eager-reconciliation spec), OR resInUse/sharedInUse charges need to survive the per-round reset for dispatched-but-unconfirmed jobs some other way. Needs its own spec -- this is normal-mode live-accounting correctness, explicitly out of scope for scheduler-sim-eager-reconciliation (which only touches simulation-mode capture/observability).",
+      "tags": [
+        "scheduler",
+        "resource-accounting",
+        "over-commit",
+        "double-booking",
+        "normal-mode",
+        "sched_account_jobs",
+        "JOB_IS_RUN",
+        "race-condition",
+        "unfixed"
+      ],
+      "related_bugs": [
+        "bug-1611",
+        "bug-1613"
+      ],
+      "occurrences": 1,
+      "last_seen": "2026-08-22T19:53:00Z"
     }
   ]
 }
\ No newline at end of file