diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 72d0638..0a9699a 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -45,7 +45,12 @@ jobs:
         # run as part of the main Test step below.
 
       - name: Test
-        run: python -m pytest --cov=agents_shipgate --cov-report=term-missing --cov-fail-under=75
+        # v0.21 (E7): bumped from 75 → 85. Actual aggregate coverage on
+        # current main is ~88%, so the gate is +10pp tighter with ~3pp
+        # headroom for day-to-day movement. The bump catches the next
+        # time a refactor lands materially less-covered code without
+        # a corresponding test pass.
+        run: python -m pytest --cov=agents_shipgate --cov-report=term-missing --cov-fail-under=85
 
       - name: Build package
         run: |
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index d8b3973..b5e15b1 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -31,10 +31,12 @@ jobs:
           python -m pip install "uv==0.11.7"
 
       - name: Lint and test
+        # v0.21 (E7): coverage threshold bumped from 75 → 85, matching
+        # CI gate so release cannot bypass the tighter floor.
         run: |
           python -m ruff check .
           python -m compileall -q src tests
-          python -m pytest --cov=agents_shipgate --cov-report=term-missing --cov-fail-under=75
+          python -m pytest --cov=agents_shipgate --cov-report=term-missing --cov-fail-under=85
 
       - name: Build package
         run: |
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8307066..95e309c 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,16 @@
 
 ## Unreleased
 
+- **v0.21 — CI coverage gate raised from 75% → 85% (E7 from round-4 review).**
+  Both `.github/workflows/ci.yml` and `.github/workflows/release.yml` now
+  pass `--cov-fail-under=85`. Aggregate coverage on `main` at the time of
+  the bump is ~88%, so the gate is +10pp tighter with ~3pp headroom for
+  day-to-day movement. The bump catches the next time a refactor lands
+  materially less-covered code without corresponding tests. No source
+  change required to land — the gate is simply closer to the actual
+  signal. Per-file coverage is not enforced; the aggregate floor only
+  rises in step with what's already proven on `main`.
+
 - **v0.20 — third-party adapter entry-point discovery (E4 from round-3 review).**
   Opens the same extension surface for adapters (input loaders) that M5
   already opened for check plugins. Discovery is gated by the existing