fix(ci): stop the e2e teardown from failing a green suite

.github/workflows/test.yml

@@ -80,8 +80,13 @@ jobs:
             coverage/coverage.out
             coverage/coverage.html
           if-no-files-found: ignore
+      # tmate keeps the runner busy until the 6 hour job limit, so a single
+      # failure costs a whole runner slot. Only open a session when someone
+      # asked for one by labelling the pull request `ci-debug`, and cap the
+      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
+        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
+        timeout-minutes: 30
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true
@@ -125,8 +130,13 @@ jobs:
           export PATH="/opt/homebrew/opt/make/libexec/gnubin:$PATH"
           PATH="$PATH:$HOME/go/bin" make protogen-go
           PATH="$PATH:$HOME/go/bin" BUILD_TYPE="GITHUB_CI_HAS_BROKEN_METAL" CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF" make --jobs 4 --output-sync=target test
+      # tmate keeps the runner busy until the 6 hour job limit, so a single
+      # failure costs a whole runner slot. Only open a session when someone
+      # asked for one by labelling the pull request `ci-debug`, and cap the
+      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
+        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
+        timeout-minutes: 30
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

.github/workflows/tests-aio.yml

@@ -77,8 +77,13 @@ jobs:
       - name: Test
         run: |
             PATH="$PATH:$HOME/go/bin" make backends/local-store backends/silero-vad backends/llama-cpp backends/whisper backends/piper backends/stablediffusion-ggml docker-build-e2e e2e-aio
+      # tmate keeps the runner busy until the 6 hour job limit, so a single
+      # failure costs a whole runner slot. Only open a session when someone
+      # asked for one by labelling the pull request `ci-debug`, and cap the
+      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
+        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
+        timeout-minutes: 30
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

.github/workflows/tests-e2e.yml

@@ -63,8 +63,13 @@ jobs:
       - name: Test Backend E2E
         run: |
           PATH="$PATH:$HOME/go/bin" make build-mock-backend test-e2e
+      # tmate keeps the runner busy until the 6 hour job limit, so a single
+      # failure costs a whole runner slot. Only open a session when someone
+      # asked for one by labelling the pull request `ci-debug`, and cap the
+      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
+        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
+        timeout-minutes: 30
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

.github/workflows/tests-pii-ner-e2e.yml

@@ -88,8 +88,13 @@ jobs:
       # CPU and runs the token_classify capability spec (byte-offset contract).
       - name: Run live PII NER backend E2E
         run: PATH="$PATH:$HOME/go/bin" make test-extra-backend-privacy-filter
+      # tmate keeps the runner busy until the 6 hour job limit, so a single
+      # failure costs a whole runner slot. Only open a session when someone
+      # asked for one by labelling the pull request `ci-debug`, and cap the
+      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
+        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
+        timeout-minutes: 30
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

.github/workflows/tests-ui-e2e.yml

@@ -75,8 +75,13 @@ jobs:
           path: core/http/react-ui/coverage/
           if-no-files-found: ignore
           retention-days: 7
+      # tmate keeps the runner busy until the 6 hour job limit, so a single
+      # failure costs a whole runner slot. Only open a session when someone
+      # asked for one by labelling the pull request `ci-debug`, and cap the
+      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
+        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
+        timeout-minutes: 30
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

Makefile

@@ -393,9 +393,17 @@ test-e2e: build-mock-backend build-cloud-proxy-backend prepare-e2e run-e2e-image
 	$(MAKE) teardown-e2e
 	docker rmi localai-tests
 
+# `docker stop` returns as soon as the container exits, but Docker reaps a
+# `--rm` container asynchronously after that. The `docker rmi localai-tests` in
+# test-e2e then loses the race against the reaper and fails on a still
+# referenced image, turning a green suite red. Removing the container ourselves
+# is synchronous, so the image reference is gone before we return. It also
+# covers the case where nothing is running, which `docker stop` could not
+# because it rejects an empty argument list.
 teardown-e2e:
 	rm -rf $(TEST_DIR) || true
-	docker stop $$(docker ps -q --filter ancestor=localai-tests)
+	@CONTAINERS=$$(docker ps -aq --filter ancestor=localai-tests 2>/dev/null); \
+	if [ -n "$$CONTAINERS" ]; then docker rm -f $$CONTAINERS || true; fi
 
 ########################################################
 ## Integration and unit tests