@@ -69,3 +69,38 @@ jobs:
         run: uv pip install ".[${{ matrix.extras }}]"
       - name: Free-threaded smoke test
         run: .venv/bin/python scripts/ft_smoke.py
+
+  install-isolation:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+      - uses: astral-sh/setup-uv@v8.2.0
+        with:
+          enable-cache: true
+          cache-dependency-glob: "**/pyproject.toml"
+      - run: uv python install 3.10
+      - name: Each extra installs and imports in isolation
+        run: |
+          set -uo pipefail
+          # GitHub runs run-steps with `bash -eo pipefail`; disable errexit so a
+          # venv-create/cleanup hiccup can't abort the loop before every extra is
+          # checked — failures are collected explicitly in `failed` below.
+          set +e
+          extras="orjson sentry pyroscope otl otl-http logging free-all \
+            fastapi fastapi-sentry fastapi-otl fastapi-logging fastapi-metrics fastapi-all \
+            litestar litestar-sentry litestar-otl litestar-logging litestar-metrics litestar-all \
+            faststream faststream-sentry faststream-otl faststream-logging faststream-metrics faststream-all \
+            fastmcp fastmcp-metrics fastmcp-all"
+          failed=""
+          uv venv --python 3.10 .v-bare >/dev/null
+          if uv pip install --python .v-bare/bin/python . >/dev/null 2>&1 \
+               && .v-bare/bin/python -c "import lite_bootstrap"; then :; else failed="$failed __bare__"; fi
+          rm -rf .v-bare
+          for e in $extras; do
+            uv venv --python 3.10 ".v-$e" >/dev/null
+            if uv pip install --python ".v-$e/bin/python" ".[$e]" >/dev/null 2>&1 \
+                 && ".v-$e/bin/python" -c "import lite_bootstrap"; then :; else failed="$failed $e"; fi
+            rm -rf ".v-$e"
+          done
+          if [ -n "$failed" ]; then echo "::error::extras failed isolated install+import:$failed"; exit 1; fi
+          echo "all extras install and import in isolation"
@@ -33,10 +33,16 @@
     from litestar.logging.config import StructLoggingConfig
     from litestar.openapi import OpenAPIConfig
     from litestar.openapi.plugins import SwaggerRenderPlugin
-    from litestar.plugins.prometheus import PrometheusConfig, PrometheusController
     from litestar.plugins.structlog import StructlogConfig, StructlogPlugin
     from litestar.static_files import create_static_files_router
 
+if import_checker.is_litestar_installed and import_checker.is_prometheus_client_installed:
+    # litestar.plugins.prometheus imports prometheus_client, which the `litestar`
+    # extra does not install (only `litestar-metrics` does). Used only inside
+    # LitestarPrometheusInstrument.bootstrap(), gated by check_dependencies() ->
+    # is_prometheus_client_installed, so this guard matches the usage.
+    from litestar.plugins.prometheus import PrometheusConfig, PrometheusController
+
 if import_checker.is_litestar_opentelemetry_installed:
     from litestar.middleware import ASGIMiddleware
     from litestar.types.asgi_types import ASGIApp, Receive, Scope, Send
 
@@ -0,0 +1,110 @@
+---
+summary: Add a CI job that installs each optional extra in isolation and imports lite_bootstrap (catching undeclared transitive dependencies the `--all-extras`-only suite masks), and fix the litestar bug it found — the `litestar.plugins.prometheus` import is guarded by litestar presence but needs prometheus_client, so `lite-bootstrap[litestar]` crashed on import.
+---
+
+# Design: Per-extra isolation install-check + fix the litestar/prometheus import
+
+## Summary
+
+Existing CI only ever installs `--all-extras`, so any extra that imports a
+package it does not declare passes CI while breaking a real single-extra install.
+This shipped twice (the bare-core `typing_extensions` crash in 1.3.1, and the
+litestar bug below). Add a CI job that installs **each** extra in its own clean
+venv and imports `lite_bootstrap`, and fix the one live bug a local sweep found.
+
+## Motivation
+
+An isolation sweep (clean venv per extra → `import lite_bootstrap`) across all 28
+extras on Python 3.10 and 3.12 found:
+
+- **`litestar`, `litestar-sentry`, `litestar-otl`, `litestar-logging` crash on
+  import** (both versions): `litestar_bootstrapper.py:36` does
+  `from litestar.plugins.prometheus import PrometheusConfig, PrometheusController`
+  under the `is_litestar_installed` guard, but that litestar plugin imports
+  `prometheus_client`, which the `litestar` extra does not install (only
+  `litestar-metrics` does). `litestar-metrics`/`litestar-all` pass because they
+  pull `prometheus-client` in. So `pip install lite-bootstrap[litestar]` +
+  `import lite_bootstrap` raises `MissingDependencyException: prometheus_client`.
+- Everything else (bare core + 24 extras) imports clean.
+- (`fastmcp` on local macOS-arm 3.10 hit a `cryptography` Rust source-build
+  failure — a local toolchain artifact, not a bug: `cryptography` supports ≥3.9
+  via abi3 wheels, so it installs on Linux CI. The check runs on Linux.)
+
+## Design
+
+### 1. Fix the litestar/prometheus import
+
+Move line 36 into its own guard (the usage sites at `litestar_bootstrapper.py:209,219`
+already run only when `check_dependencies() → is_prometheus_client_installed`,
+so this only tightens the import to match — same shape as the otl-exporter guard):
+
+```python
+if import_checker.is_litestar_installed and import_checker.is_prometheus_client_installed:
+    from litestar.plugins.prometheus import PrometheusConfig, PrometheusController
+```
+
+TDD: `emulate_package_missing_with_module_reload("prometheus_client", ["...litestar_bootstrapper"])`
+must not crash the reload; assert `import_checker.is_prometheus_client_installed`
+is False and the bootstrapper module reimports. Fails on current code, green after.
+
+### 2. Isolation install-check CI job
+
+A single `install-isolation` job in `.github/workflows/_checks.yml`, Python
+**3.10** (the floor — the undeclared-dep class is version-independent, and the
+floor surfaces the most gated behavior; the `--all-extras` pytest matrix already
+covers all versions, and the ft legs cover per-extra installs on 3.13t/3.14t):
+
+```yaml
+  install-isolation:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+      - uses: astral-sh/setup-uv@v8.2.0
+        with:
+          enable-cache: true
+          cache-dependency-glob: "**/pyproject.toml"
+      - run: uv python install 3.10
+      - name: Each extra installs and imports in isolation
+        run: |
+          set -uo pipefail
+          extras="orjson sentry pyroscope otl otl-http logging free-all \
+            fastapi fastapi-sentry fastapi-otl fastapi-logging fastapi-metrics fastapi-all \
+            litestar litestar-sentry litestar-otl litestar-logging litestar-metrics litestar-all \
+            faststream faststream-sentry faststream-otl faststream-logging faststream-metrics faststream-all \
+            fastmcp fastmcp-metrics fastmcp-all"
+          failed=""
+          # bare core first
+          uv venv --python 3.10 .v-bare >/dev/null
+          uv pip install --python .v-bare/bin/python . >/dev/null 2>&1 \
+            && .v-bare/bin/python -c "import lite_bootstrap" \
+            || failed="$failed __bare__"
+          rm -rf .v-bare
+          for e in $extras; do
+            uv venv --python 3.10 ".v-$e" >/dev/null
+            if uv pip install --python ".v-$e/bin/python" ".[$e]" >/dev/null 2>&1 \
+                 && ".v-$e/bin/python" -c "import lite_bootstrap"; then :; else failed="$failed $e"; fi
+            rm -rf ".v-$e"
+          done
+          if [ -n "$failed" ]; then echo "::error::extras failed isolated install+import:$failed"; exit 1; fi
+          echo "all extras install and import in isolation"
+```
+
+Collects **all** failures (does not stop at first) and fails listing them.
+
+## Non-goals
+
+- Multi-version isolation matrix (floor-only per the reasoning above).
+- Running a bootstrap per extra (import is the cheap, sufficient signal for the
+  undeclared-dependency class).
+
+## Testing
+
+- The litestar fix's unit test (above); `just test` 100% coverage; `just lint-ci` clean.
+- The new CI job is the systemic proof: green means every extra imports in isolation.
+
+## Risk
+
+- **The isolation job surfaces a genuine install gap on 3.10 (e.g. an extra whose
+  dep truly lacks a 3.10 Linux wheel).** That is the job doing its work; handle
+  case-by-case (a `python_version` marker on the extra, or documentation). Not
+  expected for the current matrix.
@@ -0,0 +1,20 @@
+# lite-bootstrap 1.3.2 — fix `lite-bootstrap[litestar]` import
+
+**1.3.2 is a patch release. Fully backward compatible with 1.3.1.**
+
+## Bug fixes
+
+- **`import lite_bootstrap` no longer crashes under `lite-bootstrap[litestar]`
+  without prometheus-client.** `litestar_bootstrapper` imported
+  `litestar.plugins.prometheus` (which requires `prometheus_client`) under the
+  `is_litestar_installed` guard, but the `litestar` extra does not install
+  prometheus-client — only `litestar-metrics` does. So `pip install
+  lite-bootstrap[litestar]` followed by `import lite_bootstrap` raised litestar's
+  `MissingDependencyException: prometheus_client`. The import is now guarded by
+  prometheus-client presence too (its only uses are inside the metrics
+  instrument, already gated on that package). Found by a new per-extra isolation
+  install-check in CI.
+
+## References
+
+- `planning/changes/2026-07-19.04-extra-isolation-install-check.md`
@@ -1,5 +1,6 @@
 import dataclasses
 import gc
+import sys
 import warnings
 import weakref
 
@@ -16,13 +17,18 @@
 from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanExporter
 from opentelemetry.trace import get_tracer_provider
 
-from lite_bootstrap import LitestarBootstrapper, LitestarConfig
+from lite_bootstrap import LitestarBootstrapper, LitestarConfig, import_checker
 from lite_bootstrap.bootstrappers.litestar_bootstrapper import (
     LitestarOpenTelemetryInstrumentationMiddleware,
     build_litestar_route_details_from_scope,
     build_span_name,
 )
-from tests.conftest import CustomInstrumentor, SentryTestTransport, emulate_package_missing
+from tests.conftest import (
+    CustomInstrumentor,
+    SentryTestTransport,
+    emulate_package_missing,
+    emulate_package_missing_with_module_reload,
+)
 
 
 logger = structlog.getLogger(__name__)
@@ -254,3 +260,22 @@ async def transient_app(scope: dict, receive: object, send: object) -> None:  #
 
     assert weak_app() is None
     assert len(middleware._otel_apps) == 0  # noqa: SLF001
+
+
+def test_litestar_bootstrap_without_prometheus_client() -> None:
+    # Regression: `import lite_bootstrap` with the `litestar` extra but not
+    # prometheus_client crashed because litestar_bootstrapper imported
+    # `litestar.plugins.prometheus` (which imports prometheus_client) under the
+    # is_litestar_installed guard alone. Evict the cached litestar.plugins.prometheus
+    # submodules so the module reload re-runs the real import path (otherwise the
+    # cached submodule short-circuits it and the bug is masked).
+    prom_submodules = [name for name in list(sys.modules) if name.startswith("litestar.plugins.prometheus")]
+    saved = {name: sys.modules.pop(name) for name in prom_submodules}
+    try:
+        with emulate_package_missing_with_module_reload(
+            "prometheus_client",
+            ["lite_bootstrap.bootstrappers.litestar_bootstrapper"],
+        ):
+            assert import_checker.is_prometheus_client_installed is False
+    finally:
+        sys.modules.update(saved)