diff --git a/architecture/dependency-injection.md b/architecture/dependency-injection.md
index cfd0f7e..72314fc 100644
--- a/architecture/dependency-injection.md
+++ b/architecture/dependency-injection.md
@@ -13,35 +13,50 @@ is `setup_di`, `fetch_di_container`, `FromDI`, `inject`, and `DITask`.
    (`"modern_di_container"`), a named constant — writer (`setup_di`) and
    reader (`fetch_di_container`) stay in provable agreement instead of
    relying on a bare string literal.
-2. Connects two named closures to Celery's worker-process signals:
-   `signals.worker_process_init.connect(_open_container, weak=False)` calls
-   `container.open()`, and
-   `signals.worker_process_shutdown.connect(_close_container, weak=False)`
-   calls `container.close_sync()`.
-
-`weak=False` is required on both connections. Celery's signal dispatcher
+2. Connects two named closures to **two pairs** of Celery worker signals:
+   `worker_process_init`/`worker_process_shutdown` and
+   `worker_init`/`worker_shutdown`. Both pairs call the same closures —
+   `_open_container` (`container.open()`) and `_close_container`
+   (`container.close_sync()`).
+
+The two pairs cover different pool families. `worker_process_init`/
+`worker_process_shutdown` fire only under the **prefork** and **solo** pools
+(once per forked child for prefork), giving each forked process its own
+open/close so cached resources and finalizers are fork-safe. `worker_init`/
+`worker_shutdown` fire once in the main worker process for **all** pools —
+this is the *only* pair the **gevent**, **eventlet**, and **threads** pools
+send, since those pools run tasks in the main process and never fork. Without
+`worker_init`/`worker_shutdown`, the root container would never open under
+those pools and every `@inject` task would raise `ContainerClosedError`. The
+overlap between the pairs under prefork/solo is harmless: `Container.open()`
+is a no-op when already open, and `close_sync()` is a no-op when nothing was
+cached.
+
+`weak=False` is required on all four connections. Celery's signal dispatcher
 holds receivers by weak reference by default; `_open_container` and
 `_close_container` are local closures with no other strong reference keeping
 them alive, so a weak-ref connection would let the garbage collector reclaim
-them before a forked worker process ever fires the signal — the handlers
-would silently never run. `weak=False` makes the dispatcher hold a strong
-reference for the life of the connection instead.
+them before a worker process ever fires the signal — the handlers would
+silently never run. `weak=False` makes the dispatcher hold a strong reference
+for the life of each connection instead.
 
 `fetch_di_container(app)` reads the same key back off `app.conf` and returns
 the root container.
 
 ## Lifecycle
 
-Reopening on `worker_process_init` is idempotent: a fresh `Container` is
-already open on construction, and `Container.open` is a no-op when already
-open, so firing `worker_process_init` again — a restart, a test re-entry —
-reopens a container that was closed on a previous `worker_process_shutdown`
+Reopening is idempotent: a fresh `Container` is already open on construction,
+and `Container.open` is a no-op when already open, so firing an open signal
+again — a restart, a test re-entry, or the second signal of an overlapping
+pair — reopens a container that was closed on a previous shutdown signal
 instead of raising an error. This matters because Celery's prefork pool forks
 one worker process per configured concurrency slot, and each forked process
 fires its own `worker_process_init`/`worker_process_shutdown` pair
 independently on the container object it inherited from the fork — the
 open/close cycle is scoped per forked worker process, not to the parent
-process as a whole.
+process as a whole. Under gevent/eventlet/threads there is no fork at all;
+`worker_init`/`worker_shutdown` scope the same open/close cycle to the single
+main worker process instead.
 
 ## Per-task scope
 
diff --git a/modern_di_celery/main.py b/modern_di_celery/main.py
index 5f245ad..bdea2a1 100644
--- a/modern_di_celery/main.py
+++ b/modern_di_celery/main.py
@@ -23,8 +23,21 @@ def _close_container(**_: typing.Any) -> None:  # noqa: ANN401
 
     # weak=False is required: Celery signals default to weak refs, which would
     # garbage-collect these handlers before a worker process ever fires them.
+    #
+    # worker_process_init/worker_process_shutdown fire only under the prefork and
+    # solo pools (once per forked child for prefork), giving each forked process
+    # its own open/close so cached resources and finalizers are fork-safe.
+    # worker_init/worker_shutdown fire once in the main worker process for ALL
+    # pools, which is the only signal the gevent/eventlet/threads pools send —
+    # those pools never fork and never emit worker_process_init, so without this
+    # the root container would stay closed and every @inject task would raise
+    # ContainerClosedError. The overlap between the two pairs is harmless:
+    # Container.open() is a no-op when already open, and close_sync() is a no-op
+    # when nothing was cached.
     signals.worker_process_init.connect(_open_container, weak=False)
     signals.worker_process_shutdown.connect(_close_container, weak=False)
+    signals.worker_init.connect(_open_container, weak=False)
+    signals.worker_shutdown.connect(_close_container, weak=False)
     return container
 
 
diff --git a/planning/changes/2026-07-21.01-open-root-all-pools.md b/planning/changes/2026-07-21.01-open-root-all-pools.md
new file mode 100644
index 0000000..92b92bc
--- /dev/null
+++ b/planning/changes/2026-07-21.01-open-root-all-pools.md
@@ -0,0 +1,49 @@
+---
+summary: `setup_di` now also opens/closes the root container on `worker_init`/`worker_shutdown`, so the gevent/eventlet/threads pools (which never fire `worker_process_init`) get a working root container instead of every `@inject` task raising `ContainerClosedError`.
+---
+
+# Change: Open the root container for non-forking worker pools
+
+**Lane:** lightweight — one file (~13 LOC net) + one new test, no new file,
+no public-API change, single straightforward test.
+
+## Goal
+
+`setup_di` opened the root container only via `worker_process_init` (closed
+via `worker_process_shutdown`). Celery sends `worker_process_init` only from
+the **prefork** and **solo** pools. The **gevent**, **eventlet**, and
+**threads** pools run tasks in the main worker process and never send it — so
+under those pools the root container was never opened, and modern-di 3.0's
+mandatory-open lifecycle made every `@inject` task raise `ContainerClosedError`.
+
+## Approach
+
+Connect the existing `_open_container`/`_close_container` closures to
+`worker_init`/`worker_shutdown` *in addition to* the existing
+`worker_process_init`/`worker_process_shutdown` — the per-process pair is
+unchanged. `worker_init`/`worker_shutdown` fire once in the main worker
+process for all pools, covering gevent/eventlet/threads.
+`worker_process_init`/`worker_process_shutdown` still fire per forked child
+(prefork) and in solo, giving each forked process its own open/close so
+cached resources and finalizers stay fork-safe. The overlap under
+prefork/solo is harmless: `Container.open()` is a no-op on an already-open
+container, and `close_sync()` is a no-op when nothing was cached.
+
+## Files
+
+- `modern_di_celery/main.py` — `setup_di` connects `_open_container`/
+  `_close_container` to `worker_init`/`worker_shutdown` as well.
+- `tests/test_lifespan.py` — new test fires `worker_init`/`worker_shutdown`
+  directly (without `worker_process_init`) against a fresh app/container to
+  prove the new signals — not the test fixture — open/close it.
+- `architecture/dependency-injection.md` — "Setup and worker-signal
+  lifecycle" and "Lifecycle" sections updated to describe both signal pairs.
+
+## Verification
+
+- [x] Failing test first: with the fix reverted, the new test fails at
+  `assert container.closed is False` after `signals.worker_init.send(...)`.
+- [x] Apply the change.
+- [x] Test passes with the fix restored.
+- [x] `just test-ci` — full suite green, 100% line coverage.
+- [x] `just lint-ci` — clean.
diff --git a/planning/releases/3.0.1.md b/planning/releases/3.0.1.md
new file mode 100644
index 0000000..21808eb
--- /dev/null
+++ b/planning/releases/3.0.1.md
@@ -0,0 +1,28 @@
+# modern-di-celery 3.0.1 — non-forking pool fix
+
+A patch release fixing the root container never opening under the
+gevent/eventlet/threads worker pools.
+
+## Fix
+
+- **The root container now opens for the non-forking gevent/eventlet/threads
+  pools too.** `setup_di` opened the root container only via
+  `worker_process_init` (closed via `worker_process_shutdown`), which Celery
+  sends only from the **prefork** and **solo** pools. The **gevent**,
+  **eventlet**, and **threads** pools run tasks in the main worker process
+  and never send it, so the root container was never opened under those
+  pools and every `@inject` task raised `ContainerClosedError`. `setup_di`
+  now also connects the same open/close handlers to `worker_init`/
+  `worker_shutdown`, which fire once in the main worker process for all
+  pools. `worker_process_init`/`worker_process_shutdown` are unchanged —
+  prefork and solo still get their own per-forked-process open/close cycle.
+
+## Downstream
+
+No action needed. If you run Celery workers on prefork or solo, nothing
+changes. If you run gevent, eventlet, or threads, `@inject`/`DITask` tasks
+that previously raised `ContainerClosedError` on every call now work.
+
+## Internals
+
+- 100% line coverage; `ruff`, `ty` clean.
diff --git a/tests/test_lifespan.py b/tests/test_lifespan.py
index a300008..e3003ca 100644
--- a/tests/test_lifespan.py
+++ b/tests/test_lifespan.py
@@ -1,9 +1,11 @@
+import typing
+
 from celery import Celery, signals
 from modern_di import Container
 
 import modern_di_celery
-from modern_di_celery import fetch_di_container
-from tests.dependencies import Dependencies
+from modern_di_celery import FromDI, fetch_di_container, inject
+from tests.dependencies import Dependencies, DependentCreator, SimpleCreator
 
 
 def test_fetch_returns_the_same_container(app: Celery) -> None:
@@ -32,3 +34,30 @@ def test_restart_reopens_without_error(app: Celery) -> None:
     assert container.closed is True
     signals.worker_process_init.send(sender=None)  # second cycle must not raise ContainerClosedError
     assert container.closed is False
+
+
+def test_worker_init_opens_container_for_non_forking_pools() -> None:
+    # gevent/eventlet/threads run in the main worker process and never fire
+    # worker_process_init — only worker_init. Use a fresh app/container (not the
+    # `app` fixture, which auto-opens) so this proves the signal opens it.
+    non_forking_app = Celery("non-forking", broker="memory://", backend="cache+memory://")
+    non_forking_app.conf.task_always_eager = True
+    non_forking_app.conf.task_store_eager_result = True
+    container = modern_di_celery.setup_di(non_forking_app, Container(groups=[Dependencies], validate=True))
+    assert container.closed is True
+
+    signals.worker_init.send(sender=None)  # no worker_process_init: simulates gevent/eventlet/threads
+    assert container.closed is False
+
+    @non_forking_app.task
+    @inject
+    def sample(
+        app_instance: typing.Annotated[SimpleCreator, FromDI(SimpleCreator)],
+        request_instance: typing.Annotated[DependentCreator, FromDI(Dependencies.request_factory)],
+    ) -> bool:
+        return isinstance(app_instance, SimpleCreator) and isinstance(request_instance, DependentCreator)
+
+    assert sample.delay().get() is True
+
+    signals.worker_shutdown.send(sender=None)
+    assert container.closed is True