Skip to content

Graph-Native Infrastructure for Context and Accountable AI Systems

ci: keep the known failures running under a strict xfail (#1870)

Kevineba0abce3ff5
diff --git a/.github/full-suite-known-failures.txt b/.github/full-suite-known-failures.txt
index 30caa14d..84c680ce 100644
--- a/.github/full-suite-known-failures.txt
+++ b/.github/full-suite-known-failures.txt
@@ -1,10 +1,24 @@
# Tests that already fail on an unmodified tree.
#
-# The `Run the full test suite` step in .github/workflows/ci.yml deselects
-# every node id in this file, so that step gates on new breakage instead of on
-# these pre-existing defects. Nothing here is caused by wiring the suite into
-# CI, and none of it is fixed here on purpose: the step reports the gap, it
-# does not paper over it.
+# `tests/conftest.py` reads this file and marks every id below `xfail`, so the
+# tests keep running instead of being deselected. The marker is strict in CI and
+# non-strict outside it, and never strict for a `# non-strict` entry: an entry
+# that starts passing reports XPASS, which fails the run in CI and is only a note
+# locally. In CI that is what forces its line out of the file, so the list cannot
+# quietly rot. Nothing here is caused by wiring the suite into CI, and none of it
+# is fixed here on purpose: the list reports the gap, it does not paper over it.
+#
+# Two markers change how an entry is treated, and both the step and the hook
+# read them so the two agree:
+#
+# # windows-only the id fails only in the Windows measurement. The step
+# deselects it on Windows alone, and the hook leaves it out
+# on Linux, so there it runs and gates.
+# # non-strict the hook marks the id xfail(strict=False), in CI as well as
+# locally: it keeps running, but a pass is reported as XPASS
+# without failing the run. For an entry that genuinely varies
+# with run order or timing (a thread race, for instance);
+# every other entry below is strict in CI.
#
# Provenance. Generated on a clean checkout of
#
@@ -24,46 +38,19 @@
# That measurement is not a superset of a Linux run: the entries appended below
# from the suite's first Linux run are failures it could not see, so this list
# is the union of the two runs rather than an upper bound from either. The
-# entries marked `# windows-only` are expected to pass on Linux and are
-# deselected on Windows only. The rest are expected to reproduce.
+# entries marked `# windows-only` are expected to pass on Linux. The rest are
+# expected to reproduce.
#
-# Format: one pytest node id per line. The step ignores a line only when it is
-# empty or its first character is `#`, so keep comments flush left — an indented
-# comment would be read as a node id and deselected as the empty string. A
-# trailing `# windows-only` marker means the step deselects that id when it runs
-# on Windows, and runs it everywhere else.
+# Format: one pytest node id per line. A line is an id only when it is
+# non-empty and its first character is not `#`, so keep comments flush left —
+# an indented comment would be read as a node id. A trailing `# windows-only` or
+# `# non-strict` marker is stripped before the id is used. The hook matches
+# the id the way pytest writes it, relative to the rootdir (the repository root
+# unless --rootdir or -c overrides it).
#
# Delete a line to re-enable a test. Fixing the defect behind it is what should
# drive that, not convenience.
-# --- The test double patches a call the ingest path does not make -------------
-# Each of these stubs `requests` at a layer the ingestors do not use: they fetch
-# through `request_with_ssrf_guard()`, which issues `session.request(...)` —
-# neither `requests.get()` nor `Session.get()`. The stub therefore intercepts
-# nothing, the request is really sent, and the guard
-# pins the connection to the address it resolved. `tests/ingest/conftest.py`
-# installs an autouse fixture that stubs `ssrf.socket.getaddrinfo` to map *every*
-# hostname to the single literal 93.184.216.34, so all four calls aim at that
-# one address regardless of the URL the test passes. Windows refuses to connect
-# to it (`[WinError 10049] 在其上下文中,该请求的地址无效`); on the Linux runner
-# the connection times out instead. They fail on both platforms, so they are
-# deselected unconditionally rather than on Windows only.
-# What each one stubs, and why it misses:
-# test_ingest_feed — `requests.get`; the feed fetch goes through
-# `request_with_ssrf_guard()`, so the stub misses and GET /feed.xml is sent.
-tests/ingest/test_ingestors.py::TestFeedIngestor::test_ingest_feed
-# test_ingest_url_happy — `requests.Session.get`; the page fetch calls
-# `request_with_ssrf_guard(..., session=...)`, which uses `session.request`,
-# so the stub misses and GET / is sent.
-tests/ingest/test_web_ingestor.py::test_ingest_url_happy
-# test_sitemap_fallback_parsing — `requests.get`; `SitemapCrawler.parse_sitemap`
-# goes through `request_with_ssrf_guard()`, so the stub misses and GET / is sent.
-tests/ingest/test_web_ingestor.py::test_sitemap_fallback_parsing
-# test_sitemap_index_recursion — `requests.get`; `SitemapCrawler.crawl_sitemap_index`
-# goes through `request_with_ssrf_guard()`, so the stub misses and GET /index.xml
-# is sent.
-tests/ingest/test_web_ingestor.py::test_sitemap_index_recursion
-
# --- Windows-only: symlink creation needs a privilege -------------------------
# `OSError: [WinError 1314] 客户端没有所需的特权` — creating the symlink the
# test needs requires Developer Mode or an elevated shell on Windows. On Linux
@@ -78,26 +65,30 @@ tests/ingest/test_ingestors.py::TestUnifiedIngest::test_ingest_web_dispatch
tests/ingest/test_ingestors.py::TestWebIngestor::test_ingest_url
# --- Local embedding backend unavailable offline ------------------------------
-# `128 != 384` and `'fallback' != 'sentence_transformers'`: the real model could
-# not be loaded in this environment, so the fallback backend answers instead.
-tests/test_embedding_providers.py::TestEmbeddingProviders::test_embedding_generator_config
-tests/test_embedding_providers.py::TestEmbeddingProviders::test_sentence_transformers_default
-tests/test_model_selection.py::TestModelSelection::test_dynamic_switching
-tests/test_model_selection.py::TestModelSelection::test_generator_switching
+# The generator-config case is the exception: on the Linux runner the model does
+# load and the test passes, so it is marked `# windows-only` rather than left to
+# a strict xfail that would fail on that pass. The rest of this group is gone:
+# #1931 restored the semantic_extract config isolation and they now pass.
+tests/test_embedding_providers.py::TestEmbeddingProviders::test_embedding_generator_config # windows-only
-# --- Order-dependent: these pass in isolation, fail in a full run -------------
-# The progress tracker is process-wide state; whichever test enables it first
-# decides what the next one observes.
+# --- Progress tracking is forced off for the whole process --------------------
+# `semantica_mcp/mcp/__init__.py` sets `SEMANTICA_DISABLE_PROGRESS=1` at import
+# and `tests/test_mcp_package_export_graphml_parquet.py` sets it at module scope
+# as well, so the variable is already set while pytest collects the suite.
+# `ProgressTracker.enabled` then latches disabled for the process
+# (`progress_tracker.py:1140`) and the re-enable in `arrow_exporter.py:205` is a
+# no-op. Both pass alone and fail in every full-suite run — collection of the
+# MCP modules decides it, not the order — so they stay strict: fixing the
+# isolation makes them pass and the XPASS forces these lines out.
tests/test_arrow_exporter.py::TestArrowExporter::test_progress_tracking
tests/vector_store/test_backward_compatibility.py::TestVectorStoreBackwardCompatibility::test_progress_tracking_unchanged
# --- Assertion drift in the test or its expectation ---------------------------
tests/export/test_distance_exporter.py::test_hop_distance_no_warning_when_kg_unavailable
-tests/ingest/test_repo_ingestor_security.py::TestIsReservedNAT64Regression::test_nat64_local_prefix_not_blocked
+tests/ingest/test_repo_ingestor_security.py::TestIsReservedNAT64Regression::test_nat64_local_prefix_not_blocked # windows-only
tests/integrations/agno/test_context_store.py::TestAgnoContextStoreUpsertNERAttributes::test_upsert_indexes_entity_label_as_type
tests/integrations/agno/test_context_store.py::TestAgnoContextStoreUpsertNERAttributes::test_upsert_indexes_entity_text_not_repr
-tests/semantic_extract/test_cache_backends.py::test_zero_ttl_expires_immediately_on_both_backends
-tests/vector_store/test_hybrid_similarity.py::TestHybridSimilarityCalculator::test_pearson_similarity_calculation
+tests/semantic_extract/test_cache_backends.py::test_zero_ttl_expires_immediately_on_both_backends # windows-only
tests/vector_store/test_vector_store.py::test_backend_mirroring_and_save
# --- Integration tests outside the two dedicated integration directories ------
@@ -109,10 +100,13 @@ tests/vector_store/test_vector_store.py::test_backend_mirroring_and_save
# `sqlalchemy` extra this job does not install, a fallback backend answering
# because the real embedding model is offline, and two expectation drifts in
# the deepdive suite.
+#
+# `test_06_hybrid_search` used to sit here: it failed because `HybridSearch`
+# dropped the `filter=` argument. #1827 fixed that, the test now passes on the
+# runner, and its line is gone. `test_03_model_switching` was here too; #1931
+# turned it green.
tests/ingest/test_notebook_02.py::TestNotebook02DataIngestion::test_03_web_ingestion
tests/ingest/test_notebook_02.py::TestNotebook02DataIngestion::test_08_database_ingestion
-tests/test_all_features.py::TestSemanticaFeatures::test_03_model_switching
-tests/test_all_features.py::TestSemanticaFeatures::test_06_hybrid_search
tests/test_semantic_extract_deepdive.py::TestSemanticExtractDeepDive::test_ner_extractor_pattern
tests/test_semantic_extract_deepdive_part2.py::TestSemanticExtractDeepDivePart2::test_coreference_resolver_pronouns
tests/test_semantic_extract_deepdive_part2.py::TestSemanticExtractDeepDivePart2::test_event_detector_basic
@@ -144,6 +138,7 @@ tests/vector_store/test_faiss_index.py::test_builder_trains_pq_index
# `expected call not found`: the call the Weaviate test records no longer
# matches what the store issues. `assert 2 == 5`: the Jena empty-graph test
# counts operations that all complete only once every concurrent writer has
-# landed.
+# landed. That one is a thread race and can pass when the writers happen to
+# serialize, so it is `# non-strict`.
tests/vector_store/test_backend_metadata_filtering.py::TestBackendMetadataFiltering::test_weaviate_store_filter_by_metadata_native_filter
-tests/triplet_store/test_jena_store_empty_graph.py::TestJenaStoreEmptyGraph::test_empty_graph_with_concurrent_operations
+tests/triplet_store/test_jena_store_empty_graph.py::TestJenaStoreEmptyGraph::test_empty_graph_with_concurrent_operations # non-strict
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 941b6c81..187eb61c 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -159,38 +159,58 @@ jobs:
# two consistent.
#
# .github/full-suite-known-failures.txt lists the tests that already fail
- # on an unmodified checkout. They are deselected here, so this step gates
- # on new breakage instead of on those pre-existing defects. The file is
- # the record of the gap: fixing a defect means deleting its line. It is
- # LF-only — the loop below feeds each line to --deselect verbatim, so a
- # stray CR would make every node id miss.
+ # on an unmodified checkout. tests/conftest.py marks those ids `xfail`, so
+ # they keep running and an entry that starts passing reports XPASS and
+ # fails the job — that is what forces its line out of the file. (The
+ # marker is strict here because `CI` is set; outside CI the hook makes it
+ # non-strict, since the list is measured against this pinned tree and not
+ # against a developer's.) The loop below deselects only the entries the
+ # hook must not touch: the `# windows-only` ones, and only on Windows. The
+ # file is the record of the gap: fixing a defect means deleting its line.
+ # It is kept LF-only (.gitattributes); the loop below trims whitespace
+ # around each id, including a stray CR.
- name: Run the full test suite
+ timeout-minutes: 20
run: |
# A node id that no longer collects is a no-op for --deselect rather
- # than an error, so a stale line cannot break the job; it just stops
- # deselecting, and the test it named runs again.
+ # than an error, so a stale line cannot break the job. It is inert for
+ # the hook too, which only marks ids pytest actually collects: it
+ # neither runs nor reports XPASS, and the file's own review is what
+ # catches it.
#
- # A line may carry a trailing `# windows-only` marker. That means the
- # id fails only on Windows and is deselected there alone — a symlink
- # that needs a privilege, for instance. On Linux it runs, which is the
- # only place the symlink rejection in
+ # A line is deselected here only when it carries the `# windows-only`
+ # marker and this is a Windows runner. Every other line reaches the
+ # hook, which marks it xfail strictly here in CI.
+ #
+ # `# windows-only` is deselected on Windows alone — a symlink that
+ # needs a privilege, for instance. On Linux the line is left out, so
+ # the test runs, which is the only place the symlink rejection in
# tests/semantic_extract/test_cache_backends.py gets exercised at all;
# deselecting it unconditionally would drop a security check on the
- # platform where it works.
+ # platform where it works. This job runs on ubuntu-latest, so the
+ # Windows branch never fires in CI today; it is kept for a Windows
+ # runner, where that id does fail, rather than dropped as dead weight.
deselect=()
+ known=0
+ deselected=0
while IFS= read -r line; do
case "$line" in
''|'#'*) continue ;;
- *windows-only*)
+ esac
+ known=$((known + 1))
+ case "$line" in
+ *'# windows-only'*)
if [ "${RUNNER_OS:-}" != "Windows" ]; then continue; fi
;;
+ *) continue ;;
esac
node="${line%%#*}"
node="${node#"${node%%[![:space:]]*}"}"
node="${node%"${node##*[![:space:]]}"}"
deselect+=(--deselect "$node")
+ deselected=$((deselected + 1))
done < .github/full-suite-known-failures.txt
- echo "deselecting known failures: ${#deselect[@]}"
+ echo "known failures on the list: ${known}; deselected in this step: ${deselected}"
# The google_adk and open_ontologies directories have their own steps
# at the end of this job, each with its own dependency installation.
diff --git a/.github/workflows/codeql.yml b/.github/workflows/codeql.yml
index 69f9d17b..02c54916 100644
--- a/.github/workflows/codeql.yml
+++ b/.github/workflows/codeql.yml
@@ -34,7 +34,7 @@ jobs:
# meaningful state carried over from a failed attempt.
- name: Initialize CodeQL (attempt 1)
id: codeql-init-1
- uses: github/codeql-action/init@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/init@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
continue-on-error: true
with:
languages: python
@@ -44,7 +44,7 @@ jobs:
- name: Initialize CodeQL (attempt 2)
id: codeql-init-2
if: steps.codeql-init-1.outcome == 'failure'
- uses: github/codeql-action/init@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/init@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
continue-on-error: true
with:
languages: python
@@ -54,17 +54,17 @@ jobs:
- name: Initialize CodeQL (attempt 3)
id: codeql-init-3
if: steps.codeql-init-2.outcome == 'failure'
- uses: github/codeql-action/init@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/init@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
with:
languages: python
queries: security-and-quality
config-file: .github/codeql/codeql-config.yml
- name: Autobuild
- uses: github/codeql-action/autobuild@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/autobuild@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
- name: Perform CodeQL Analysis
- uses: github/codeql-action/analyze@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/analyze@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
with:
category: "/language:python"
upload: false
@@ -74,7 +74,7 @@ jobs:
# Uploads results only when Default Setup is not active.
# If Default Setup is still enabled, this step skips gracefully
# instead of failing the workflow with HTTP 409.
- uses: github/codeql-action/upload-sarif@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
with:
sarif_file: ${{ steps.codeql.outputs.sarif-output }}
category: "/language:python"
diff --git a/.github/workflows/container-scan.yml b/.github/workflows/container-scan.yml
index b74fafb6..3e9be255 100644
--- a/.github/workflows/container-scan.yml
+++ b/.github/workflows/container-scan.yml
@@ -61,7 +61,7 @@ jobs:
- name: Upload Trivy SARIF
if: always()
- uses: github/codeql-action/upload-sarif@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
with:
sarif_file: trivy-results.sarif
category: trivy-container
diff --git a/.github/workflows/defender-for-devops.yml b/.github/workflows/defender-for-devops.yml
index 1a9a556f..8e5da485 100644
--- a/.github/workflows/defender-for-devops.yml
+++ b/.github/workflows/defender-for-devops.yml
@@ -59,7 +59,7 @@ jobs:
# avoiding the guardian.cmd/checkov exit-code bug in the MSDO wrapper.
tools: eslint,templateanalyzer,terrascan
- name: Upload results to Security tab
- uses: github/codeql-action/upload-sarif@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
with:
sarif_file: ${{ steps.msdo.outputs.sarifFile }}
@@ -100,7 +100,7 @@ jobs:
run: python .github/scripts/filter_checkov_skipped.py reports/results_json.json reports/results_sarif.sarif reports/checkov.sarif
- name: Upload Checkov results to Security tab
- uses: github/codeql-action/upload-sarif@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
if: always()
with:
sarif_file: reports/checkov.sarif
diff --git a/.github/workflows/scorecard.yml b/.github/workflows/scorecard.yml
index 7530ab43..f19789c1 100644
--- a/.github/workflows/scorecard.yml
+++ b/.github/workflows/scorecard.yml
@@ -40,6 +40,6 @@ jobs:
retention-days: 5
- name: Upload to code-scanning
- uses: github/codeql-action/upload-sarif@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2 # v4
+ uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4
with:
sarif_file: results.sarif
diff --git a/tests/conftest.py b/tests/conftest.py
index 2d432015..c16d45da 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -1,8 +1,41 @@
-"""Shared pytest configuration for the whole test suite."""
+"""
+Suite-wide pytest configuration.
+
+``.github/full-suite-known-failures.txt`` records the tests that already fail on
+an unmodified checkout. Rather than deselecting them, the hook below marks the
+listed ids ``xfail``: they keep running, and one that starts passing reports
+XPASS — which, under a strict marker, fails the run and so forces its line out
+of the file.
+
+The list only holds against the pinned ``requirements-ci.txt`` tree it was
+measured on. A developer machine has a different environment, so entries here
+can pass there, and a strict marker would turn each of those passes into a
+failure of an ordinary local run. The marker is therefore strict only when
+``CI`` is set to a true value (``1``/``true``/``yes``; GitHub Actions sets
+``CI=true`` for every job) and non-strict everywhere else: locally a listed entry still runs and is still xfailed, but a
+pass is reported as XPASS without failing the run.
+
+The ``Run the full test suite`` step in ``.github/workflows/ci.yml`` deselects
+the entries it must — the ones marked ``# windows-only``, on Windows alone — so
+those never reach this hook. The hook leaves a ``# windows-only`` entry out on
+Linux, where it runs and gates. (For the symlink-rejection test that is the only
+platform where the rejection is exercised at all.) The ``# non-strict`` marker keeps an
+entry non-strict even in CI, for an entry that genuinely varies with run order
+or timing; every other listed entry is strict in CI.
+
+The autouse fixture below isolates the process-wide ``semantic_extract`` config
+between tests: a double left there by one test otherwise makes every later
+provider test see an API key that is not set, which is why the 24 ``test_llm_*``
+ids used to fail in a full-suite run (#1913).
+"""
+from __future__ import annotations
import copy
import importlib
+import os
+import re
import sys
+from pathlib import Path
import pytest
@@ -26,3 +59,50 @@ def _isolate_semantic_extract_config():
configs.clear()
configs.update(saved)
sys.modules[_CONFIG_MODULE_NAME] = _config_module
+
+
+_KNOWN_FAILURES = (
+ Path(__file__).resolve().parent.parent
+ / ".github"
+ / "full-suite-known-failures.txt"
+)
+
+_WINDOWS_ONLY = "# windows-only"
+_NON_STRICT = "# non-strict"
+_HEADING = re.compile(r"^#\s*-{3,}\s+(?P<title>\S.*?)\s*-*\s*$")
+_DEFAULT_REASON = "listed in .github/full-suite-known-failures.txt"
+
+
+def _listed_ids() -> dict[str, tuple[str, bool]]:
+ """Return the ids to xfail, each mapped to its heading and strictness."""
+ if not _KNOWN_FAILURES.is_file():
+ return {}
+ listed: dict[str, tuple[str, bool]] = {}
+ reason = _DEFAULT_REASON
+ for raw in _KNOWN_FAILURES.read_text(encoding="utf-8").splitlines():
+ line = raw.strip()
+ if not line:
+ continue
+ if line.startswith("#"):
+ heading = _HEADING.match(line)
+ if heading:
+ reason = heading.group("title")
+ continue
+ if _WINDOWS_ONLY in line and sys.platform != "win32":
+ continue
+ node = line.split("#", 1)[0].strip()
+ listed[node] = (reason, _NON_STRICT not in line)
+ return listed
+
+
+def pytest_collection_modifyitems(config, items):
+ listed = _listed_ids()
+ if not listed:
+ return
+ in_ci = os.environ.get("CI", "").strip().lower() in {"1", "true", "yes"}
+ for item in items:
+ entry = listed.get(item.nodeid)
+ if entry is None:
+ continue
+ reason, strict_ok = entry
+ item.add_marker(pytest.mark.xfail(reason=reason, strict=in_ci and strict_ok))
diff --git a/tests/ingest/test_ingestors.py b/tests/ingest/test_ingestors.py
index da1392ee..44da923d 100644
--- a/tests/ingest/test_ingestors.py
+++ b/tests/ingest/test_ingestors.py
@@ -78,8 +78,8 @@ class TestWebIngestor:
assert "Test content" in result.text
class TestFeedIngestor:
- @patch("requests.get")
- def test_ingest_feed(self, mock_get):
+ @patch("semantica.ingest.feed_ingestor.request_with_ssrf_guard")
+ def test_ingest_feed(self, mock_request):
ingestor = FeedIngestor()
rss_content = """
@@ -101,7 +101,7 @@ class TestFeedIngestor:
mock_response.status_code = 200
mock_response.text = rss_content
mock_response.content = rss_content.encode('utf-8')
- mock_get.return_value = mock_response
+ mock_request.return_value = mock_response
result = ingestor.ingest_feed("http://example.com/feed.xml")
diff --git a/tests/ingest/test_web_ingestor.py b/tests/ingest/test_web_ingestor.py
index 4ce6d908..f63b0af9 100644
--- a/tests/ingest/test_web_ingestor.py
+++ b/tests/ingest/test_web_ingestor.py
@@ -43,7 +43,9 @@ def test_sitemap_index_recursion() -> None:
</urlset>
"""
- with patch("requests.get") as mock_get:
+ with patch(
+ "semantica.ingest.web_ingestor.request_with_ssrf_guard"
+ ) as mock_get:
mock_get.side_effect = [
MagicMock(status_code=200, content=index_xml.encode()),
MagicMock(status_code=200, content=child_xml.encode()),
@@ -60,7 +62,7 @@ def test_sitemap_fallback_parsing() -> None:
xml = "<urlset><url><loc>http://a.com</loc></url></urlset>"
with patch(
- "requests.get",
+ "semantica.ingest.web_ingestor.request_with_ssrf_guard",
return_value=MagicMock(
status_code=200,
content=xml.encode(),
@@ -113,7 +115,7 @@ def test_extract_metadata_empty() -> None:
# --- WebIngestor Tests ---
-@patch("requests.Session.get")
+@patch("semantica.ingest.web_ingestor.request_with_ssrf_guard")
def test_ingest_url_happy(mock_get: MagicMock, sample_html: str) -> None:
"""Test successful URL ingestion."""