diff --git a/.claude/agent-memory/validator/MEMORY.md b/.claude/agent-memory/validator/MEMORY.md
index 4a49f4e..31c8d19 100644
--- a/.claude/agent-memory/validator/MEMORY.md
+++ b/.claude/agent-memory/validator/MEMORY.md
@@ -1 +1,2 @@
 - [Self-hosting loop_round probe](project_self_hosting_loop_round_probe.md) — task 14fd9ab6 was a deliberate no-bug probe; verified PASS, no code change is the correct outcome
+- [Zero-diff terminal state gap (2nd instance)](project_zero_diff_terminal_state_gap.md) — scheduler.py _BUSY_TIMEOUT_MS comment already present, PASS/no-change; same recurring pipeline gap as org_loop_route.py
diff --git a/.claude/agent-memory/validator/project_zero_diff_terminal_state_gap.md b/.claude/agent-memory/validator/project_zero_diff_terminal_state_gap.md
new file mode 100644
index 0000000..cc63e5f
--- /dev/null
+++ b/.claude/agent-memory/validator/project_zero_diff_terminal_state_gap.md
@@ -0,0 +1,38 @@
+---
+name: project-zero-diff-terminal-state-gap
+description: pipeline has no "already satisfied, zero-diff" terminal task state; this recurs across multiple comment-rationale tasks (org_loop_route.py _LOOP_LIMIT, scheduler.py _BUSY_TIMEOUT_MS)
+metadata:
+  type: project
+---
+
+Confirmed a second instance of the same process gap already noted for `src/org_loop_route.py`'s
+`_LOOP_LIMIT` comment (see the global auto-memory note "Loop-round comment already present",
+6x recurrence as of 2026-08-03): a Benchmark asked to add a one-line rationale comment above
+`src/scheduler.py`'s `_BUSY_TIMEOUT_MS = 30000` cross-referencing the module docstring's
+"Threading model" section (lines 21-28). Verified 2026-08-03 that commit `5bb25db` had already
+added exactly this line:
+
+```
+# Rationale: see module docstring's "Threading model" section (lines 21-28) above.
+_BUSY_TIMEOUT_MS = 30000
+```
+
+— correct line-range citation (21-28 is exactly the "Threading model" paragraph ending in
+"database is locked"), `_FIX_LOOP_TIMEOUT` untouched, `py_compile` clean, only `src/scheduler.py`
+touched in that commit, +1 line net. `git status` showed zero uncommitted diff for the file at
+verification time. Verdict: PASS, no changes made.
+
+**Why:** Same root cause as [[project-self-hosting-loop-round-probe]] and the org_loop_route.py
+recurrence — the Org Graph task lifecycle (`p_org_task_lifecycle`, 04-P) has no terminal state for
+"investigated and confirmed already satisfied, zero-diff," distinct from `done` (implies a fresh
+Coder diff was validated) or `blocked_pending_human` (implies an unresolved failure). Tasks of this
+shape (idempotent rationale-comment additions) keep getting re-dispatched to Coder/Validator instead
+of closing once satisfied.
+
+**How to apply:** When a task benchmark explicitly includes a "Scenario 2 (boundary): already
+present → zero-diff" case, treat that as a strong signal this is a repeat/probe task, not a fresh
+defect. Verify by reading the file and `git log -p` for the relevant commit rather than assuming
+work is still needed — a correct PASS-with-no-changes is the right outcome, not a sign of an
+incomplete job. If asked to design or fix the lifecycle gap itself, cite this and the
+org_loop_route.py recurrence together as evidence (now 2+ distinct comment-rationale sites) that a
+"verified, zero-diff" terminal state is needed generally, not just for one constant.