Merge branch 'main' into LCORE-1472_e2e_retries

Author: radofuchs

.github/workflows/e2e_tests.yaml

@@ -11,8 +11,9 @@ jobs:
       matrix:
         mode: ["server", "library"]
         environment: ["ci"]
-    
-    name: "E2E: ${{ matrix.mode }} mode / ${{ matrix.environment }}"
+        e2e_group: [1, 2, 3]
+
+    name: "E2E: ${{ matrix.mode }} mode / ${{ matrix.environment }} / group ${{ matrix.e2e_group }}"
 
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -103,6 +104,7 @@ jobs:
           echo "=== Configuration Summary ==="
           echo "Deployment mode: ${{ matrix.mode }}"
           echo "Environment: ${{ matrix.environment }}"
+          echo "E2E shard (Makefile test-e2e-tagged): @e2e_group_${{ matrix.e2e_group }} (with not @skip)"
           echo "Source config: tests/e2e/configs/run-${{ matrix.environment }}.yaml"
           echo ""
           echo "=== Configuration Preview ==="
@@ -187,13 +189,15 @@ jobs:
           TERM: xterm-256color
           FORCE_COLOR: 1
           E2E_DEPLOYMENT_MODE: ${{ matrix.mode }}
+          # Matches Makefile test-e2e-tagged / E2E_BEHAVE_TAG_EXPR (one @e2e_group_* per job).
+          E2E_BEHAVE_TAG_EXPR: "not @skip and @e2e_group_${{ matrix.e2e_group }}"
         run: |
           echo "Installing test dependencies..."
           pip install uv
           uv sync
 
-          echo "Running comprehensive e2e test suite..."
-          make test-e2e
+          echo "Running e2e tests (E2E_BEHAVE_TAG_EXPR=${E2E_BEHAVE_TAG_EXPR})..."
+          make test-e2e-tagged
 
       - name: Show logs on failure
         if: failure()

Makefile

@@ -32,9 +32,19 @@ test-integration: ## Run integration tests tests
 test-e2e: ## Run end to end tests for the service
 	script -q -e -c "uv run behave --color --format pretty --tags=-skip -D dump_errors=true @tests/e2e/test_list.txt"
 
-test-e2e-local: ## Run end to end tests for the service
+test-e2e-local: ## Run end to end tests for the service (no script wrapper)
 	uv run behave --color --format pretty --tags=-skip -D dump_errors=true @tests/e2e/test_list.txt
 
+# Tag-based subsets (@e2e_group_* on feature files). Default runs all groups; override for one shard, e.g.
+#   E2E_BEHAVE_TAG_EXPR='not @skip and @e2e_group_2' make test-e2e-tagged-local
+E2E_BEHAVE_TAG_EXPR ?= not @skip and (e2e_group_1 or e2e_group_2 or e2e_group_3)
+
+test-e2e-tagged: ## Run e2e tests with E2E_BEHAVE_TAG_EXPR (default: all @e2e_group_*)
+	script -q -e -c "uv run behave --color --format pretty --tags=\"$(E2E_BEHAVE_TAG_EXPR)\" -D dump_errors=true @tests/e2e/test_list.txt"
+
+test-e2e-tagged-local: ## Same as test-e2e-tagged without script wrapper
+	uv run behave --color --format pretty --tags="$(E2E_BEHAVE_TAG_EXPR)" -D dump_errors=true @tests/e2e/test_list.txt
+
 benchmarks: ## Run benchmarks
 	uv run python -m pytest -vv tests/benchmarks/
 

tests/e2e/features/authorized_noop.feature

@@ -1,3 +1,4 @@
+@e2e_group_1
 Feature: Authorized endpoint API tests for the noop authentication module
 
   Background:

tests/e2e/features/authorized_noop_token.feature

@@ -1,4 +1,4 @@
-@Authorized
+@e2e_group_2 @Authorized
 Feature: Authorized endpoint API tests for the noop-with-token authentication module
 
   Background:

tests/e2e/features/authorized_rh_identity.feature

@@ -1,4 +1,4 @@
-@RHIdentity
+@e2e_group_3 @RHIdentity
 Feature: Authorized endpoint API tests for the rh-identity authentication module
 
   Background:

tests/e2e/features/conversation_cache_v2.feature

@@ -1,4 +1,4 @@
-@Authorized
+@e2e_group_2 @Authorized
 Feature: Conversation Cache V2 API tests
 
   Background:

tests/e2e/features/conversations.feature

@@ -1,4 +1,4 @@
-@Authorized
+@e2e_group_2 @Authorized
 Feature: conversations endpoint API tests
 
   Background:

tests/e2e/features/environment.py

@@ -366,6 +366,7 @@ def before_feature(context: Context, feature: Feature) -> None:
     ``_E2E_FLAKY_MAX_ATTEMPTS`` and can be overridden with the
     ``E2E_FLAKY_MAX_ATTEMPTS`` environment variable.
     """
+    setattr(feature, _E2E_FEATURE_PERF_START_ATTR, time.perf_counter())
     reset_active_lightspeed_stack_config_basename()
     context.active_lightspeed_stack_config_basename = None
     # One real Llama disruption per feature (module-level flag; survives context resets)
@@ -423,3 +424,19 @@ def after_feature(context: Context, feature: Feature) -> None:
 
         _stop_proxy(context, "tunnel_proxy", "proxy_loop")
         _stop_proxy(context, "interception_proxy", "interception_proxy_loop")
+
+    start = getattr(feature, _E2E_FEATURE_PERF_START_ATTR, None)
+    if start is not None:
+        elapsed_s = time.perf_counter() - start
+        try:
+            delattr(feature, _E2E_FEATURE_PERF_START_ATTR)
+        except AttributeError:
+            pass
+        feat_path = getattr(feature, "filename", "") or ""
+        label = os.path.basename(feat_path) if feat_path else feature.name
+        print(f"[e2e feature timing] {elapsed_s:.2f}s  {label}", flush=True)
+
+
+# Behave captures hook stdout by default; output is only shown in some failure paths.
+# Disable capture so feature timing lines always appear on the real console/CI log.
+after_feature.capture = False  # type: ignore[attr-defined]

tests/e2e/features/faiss.feature

@@ -1,4 +1,4 @@
-@Authorized
+@e2e_group_1 @Authorized
 Feature: FAISS support tests
 
   Background:

tests/e2e/features/feedback.feature

@@ -1,4 +1,4 @@
-@Feedback
+@e2e_group_3 @Feedback
 Feature: feedback endpoint API tests