diff --git a/.github/workflows/qwen-autofix.yml b/.github/workflows/qwen-autofix.yml
index e1120b2ba7f..59dc85a5461 100644
--- a/.github/workflows/qwen-autofix.yml
+++ b/.github/workflows/qwen-autofix.yml
@@ -164,14 +164,27 @@ env:
   INFRA_FAILURE_SIGNATURES: 'lost communication with the server|No space left on device|ENOSPC|received a shutdown signal|The runner has received|Failed to initialize container|runner (was|has been) (lost|terminated)|invalid index-pack output|RPC failed'
   # Upper bound on review targets emitted per scan (fan-out defense-in-depth;
   # excess is logged and deferred to the next scan).
-  MAX_TARGETS_PER_SCAN: '10'
+  # TUNABLE WITHOUT A CODE CHANGE: set the repository variable to re-size the
+  # loop as the takeover pool grows — Settings → Variables, no PR, no deploy.
+  # The literal here is only the fallback when the variable is unset.
+  # Why 30: 37 PRs carried autofix/takeover on 2026-08-08, so the previous
+  # budget of 10 emitted at most 27% of the eligible set per tick and pushed
+  # the rest a scan further out every time. It must also stay strictly above
+  # the address matrix's max-parallel or the matrix can never fill, and the
+  # same-repo candidate pool was 51, so 30 still bounds a pathological
+  # backlog. RAISE BOTH TOGETHER: this must stay above QWEN_AUTOFIX_MAX_PARALLEL.
+  MAX_TARGETS_PER_SCAN: '${{ vars.QWEN_AUTOFIX_MAX_TARGETS_PER_SCAN || 30 }}'
   # Upper bound on candidates INSPECTED per scan: idle candidates consume
   # serial API calls even when they emit nothing, and takeover widens the
   # candidate pool. Candidates are inspected NEWEST-first; past the budget
   # the oldest tail defers — old quiet PRs are the least likely to hold new
   # feedback, and a deferred PR with a live conflict is still picked up by
   # the shepherd's conflict lever.
-  MAX_CANDIDATE_INSPECTIONS: '60'
+  # TUNABLE WITHOUT A CODE CHANGE, for the same reason as the two above: this
+  # one gates whether a PR is even LOOKED AT, so it has to grow ahead of the
+  # candidate pool or the oldest PRs starve. The pool was 51 same-repo open
+  # PRs on 2026-08-08, still under the 60 fallback.
+  MAX_CANDIDATE_INSPECTIONS: '${{ vars.QWEN_AUTOFIX_MAX_CANDIDATE_INSPECTIONS || 60 }}'
   # Maintainer-facing engagement labels (applying labels requires GitHub
   # triage+, so the permission gate is GitHub's own): TAKEOVER opts a PR —
   # including a human-authored one — into the loop; SKIP opts any PR out
@@ -3277,14 +3290,29 @@ jobs:
       # Measured at 3, on the scan that selected 7 PRs: the legs started
       # 3-at-a-time and each new one began 3-4s after a slot freed, so the
       # 7th PR waited 81 minutes for a slot it could have had immediately.
-      # 5 halves that tail while staying a real bound — the point of the cap
-      # is that a backlog cannot open an unbounded number of agent runs at
-      # once, not the specific number. The 300-minute job cap raises the
-      # worst-case hold to 5 runner-hours per slot (25 across the fleet) and
-      # holds the per-PR head-write concurrency group for the same window.
-      # The cap itself does not lengthen the queueing tail above; the raised
-      # 120-minute budget does, for the PRs that exhaust it.
-      max-parallel: 5
+      # 5 halved that tail — the point of the cap is that a backlog cannot
+      # open an unbounded number of agent runs at once, not the specific
+      # number.
+      # TUNABLE WITHOUT A CODE CHANGE: set QWEN_AUTOFIX_MAX_PARALLEL in
+      # Settings → Variables to re-size the fleet as the takeover pool grows;
+      # the literal below is only the fallback when the variable is unset.
+      # Verified on a live runner that `max-parallel` accepts this expression
+      # and schedules by it — a 6-leg matrix at 3 started 3, then began the
+      # 4th only once a slot freed.
+      # Why 20: 37 PRs carried the label on 2026-08-08, so 5 slots served
+      # ~14% of them at a time and the tail measured at 3 simply reappeared
+      # at a larger scale. The ecs-qwen fleet is 84 runners, so 20 concurrent
+      # legs occupy under a quarter of it, and the executed legs sampled that
+      # day finished in 3-28 minutes.
+      # The 300-minute job cap puts the worst case at 5 runner-hours per slot
+      # (100 across the fleet at 20) and holds the per-PR head-write
+      # concurrency group for the same window. Different PRs never share that
+      # group, so raising this does not add push contention.
+      # RAISE BOTH TOGETHER: this must stay strictly below
+      # MAX_TARGETS_PER_SCAN, or the scan cannot emit enough legs to fill the
+      # matrix and the extra slots sit idle. A test pins that for the
+      # fallbacks; for the variables it is an operator invariant.
+      max-parallel: '${{ fromJSON(vars.QWEN_AUTOFIX_MAX_PARALLEL || 20) }}'
       matrix:
         target: '${{ fromJSON(needs.review-scan.outputs.targets) }}'
     # Serialises every writer of THIS PR's head branch, across workflows.
diff --git a/scripts/tests/qwen-autofix-workflow.test.js b/scripts/tests/qwen-autofix-workflow.test.js
index 126eaac0edb..e940327b528 100644
--- a/scripts/tests/qwen-autofix-workflow.test.js
+++ b/scripts/tests/qwen-autofix-workflow.test.js
@@ -413,11 +413,19 @@ describe('qwen-autofix workflow', () => {
     // that it exists AND still binds below MAX_TARGETS_PER_SCAN is pinned by
     // 'bounds fleet-wide simultaneity below the per-scan target budget'.
     // Asserting the literal number here only detected edits, not breakage.
-    expect(workflow).toMatch(/max-parallel: \d+/);
+    expect(workflow).toMatch(
+      /max-parallel: '\$\{\{ fromJSON\(vars\.QWEN_AUTOFIX_MAX_PARALLEL \|\| \d+\) \}\}'/,
+    );
     // Pathological-backlog bound: the budget BREAKS the candidate loop (so it
     // bounds runtime and API usage, not just matrix size), the deferral is
     // LOGGED, and the next scan picks up the remainder.
-    expect(workflow).toContain("MAX_TARGETS_PER_SCAN: '10'");
+    // Operator-tunable via a repository variable so the loop can be re-sized
+    // as the takeover pool grows without a code change; the literal is the
+    // fallback. Both halves are asserted so the knob cannot silently lose
+    // either its variable or its default.
+    expect(workflow).toMatch(
+      /MAX_TARGETS_PER_SCAN: '\$\{\{ vars\.QWEN_AUTOFIX_MAX_TARGETS_PER_SCAN \|\| \d+ \}\}'/,
+    );
     expect(reviewScanJob).toContain(
       'deferring the remaining candidates to the next scan',
     );
@@ -1387,10 +1395,17 @@ describe('qwen-autofix workflow', () => {
     // raising it to the target budget, both let one backlog open every agent
     // run at once — which is the thing the cap exists to prevent, and neither
     // would fail any other test.
+    // Both are repository variables now, so what is checkable here is the
+    // FALLBACK pair — the values that apply until an operator sets them.
+    // Keeping the relation true for the fallbacks means an unconfigured repo
+    // is still correctly bounded; for configured ones it is an operator
+    // invariant, stated at both definitions.
     expect(reviewAddressJob).toContain('matrix:');
-    const parallel = Number(reviewAddressJob.match(/max-parallel: (\d+)/)?.[1]);
+    const parallel = Number(
+      reviewAddressJob.match(/max-parallel:.*?\|\|\s*(\d+)/)?.[1],
+    );
     const targetBudget = Number(
-      workflow.match(/MAX_TARGETS_PER_SCAN: '(\d+)'/)?.[1],
+      workflow.match(/MAX_TARGETS_PER_SCAN:.*?\|\|\s*(\d+)/)?.[1],
     );
     expect(Number.isInteger(parallel)).toBe(true);
     expect(parallel).toBeGreaterThan(0);