From bde02c22275adf0c22d6ba6ff8a82acb01adfef4 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Wed, 11 Mar 2026 20:48:26 +0100
Subject: [PATCH 01/34] WIP: Local Works somewhat

---
 docs.bzl                                      |  17 +-
 scripts_bazel/generate_sourcelinks_cli.py     |  51 ++++-
 scripts_bazel/merge_sourcelinks.py            |  70 ++++++-
 .../score_source_code_linker/__init__.py      | 184 +++++++++---------
 .../score_source_code_linker/metadata.py      |  23 +++
 .../module_source_links.py                    | 137 +++++++++++++
 .../need_source_links.py                      |  51 +++++
 .../score_source_code_linker/needlinks.py     | 114 +++++++++--
 src/helper_lib/additional_functions.py        |  25 +++
 9 files changed, 555 insertions(+), 117 deletions(-)
 create mode 100644 src/extensions/score_source_code_linker/metadata.py
 create mode 100644 src/extensions/score_source_code_linker/module_source_links.py

diff --git a/docs.bzl b/docs.bzl
index cd41a4c83..fe26590e8 100644
--- a/docs.bzl
+++ b/docs.bzl
@@ -69,7 +69,7 @@ def _rewrite_needs_json_to_sourcelinks(labels):
             out.append(s)
     return out
 
-def _merge_sourcelinks(name, sourcelinks):
+def _merge_sourcelinks(name, sourcelinks, known_good = None):
     """Merge multiple sourcelinks JSON files into a single file.
 
     Args:
@@ -77,15 +77,22 @@ def _merge_sourcelinks(name, sourcelinks):
         sourcelinks: List of sourcelinks JSON file targets
     """
 
+    extra_srcs = []
+    known_good_arg = ""
+    if known_good != None:
+        extra_srcs = [known_good]
+        known_good_arg = "--known_good $(location %s)" % known_good
+
     native.genrule(
         name = name,
-        srcs = sourcelinks,
+        srcs = sourcelinks + extra_srcs,
         outs = [name + ".json"],
         cmd = """
         $(location @score_docs_as_code//scripts_bazel:merge_sourcelinks) \
             --output $@ \
+            {known_good_arg} \
             $(SRCS)
-        """,
+        """.format(known_good_arg = known_good_arg),
         tools = ["@score_docs_as_code//scripts_bazel:merge_sourcelinks"],
     )
 
@@ -120,7 +127,7 @@ def _missing_requirements(deps):
         fail(msg)
     fail("This case should be unreachable?!")
 
-def docs(source_dir = "docs", data = [], deps = [], scan_code = []):
+def docs(source_dir = "docs", data = [], deps = [], scan_code = [], known_good = None):
     """Creates all targets related to documentation.
 
     By using this function, you'll get any and all updates for documentation targets in one place.
@@ -175,7 +182,7 @@ def docs(source_dir = "docs", data = [], deps = [], scan_code = []):
 
     data_with_docs_sources = _rewrite_needs_json_to_docs_sources(data)
     additional_combo_sourcelinks = _rewrite_needs_json_to_sourcelinks(data)
-    _merge_sourcelinks(name = "merged_sourcelinks", sourcelinks = [":sourcelinks_json"] + additional_combo_sourcelinks)
+    _merge_sourcelinks(name = "merged_sourcelinks", sourcelinks = [":sourcelinks_json"] + additional_combo_sourcelinks, known_good = known_good)
 
     py_binary(
         name = "docs",
diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 4291b97c5..27a0e4508 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -26,24 +26,51 @@
     _extract_references_from_file,  # pyright: ignore[reportPrivateUsage] TODO: move it out of the extension and into this script
 )
 from src.extensions.score_source_code_linker.needlinks import (
-    store_source_code_links_json,
+    store_source_code_links_with_metadata_json,
 )
+from src.extensions.score_source_code_linker.metadata import MetaData
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
 
+def parse_module_name_from_path(path: Path) -> str:
+    """
+    Parse out the Module-Name from the filename gotten
+    /home/user/.cache/bazel/aksj37981712/external/score_docs_as_code+/src/tests/testfile.py
+    => score_docs_as_code
+    """
+
+    # COMBO BUILD
+    # If external is in the filepath that gets parsed =>
+    # file is in an external module => combo build
+    # e.g. .../external/score_docs_as_code+/src/helper_lib/__init__.py
+
+    # PATH if we are in local repository
+    # PosixPath('src/helper_lib/test_helper_lib.py')
+    # Path if we are in combo build and externally
+    # PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
+    print("======== THIs IS PATH we PARSIGN FOr MODULE NAME")
+    print(path)
+    if str(path).startswith("external/"):
+        module_raw = str(path).removeprefix("external/")
+        filepath_split = str(module_raw).split("/", maxsplit=1)
+        module_name = str(filepath_split[0].removesuffix("+"))
+        return module_name
+    return "local_module"
+
+
 def main():
     parser = argparse.ArgumentParser(
         description="Generate source code links JSON from source files"
     )
-    parser.add_argument(
+    _ = parser.add_argument(
         "--output",
         required=True,
         type=Path,
         help="Output JSON file path",
     )
-    parser.add_argument(
+    _ = parser.add_argument(
         "files",
         nargs="*",
         type=Path,
@@ -53,15 +80,29 @@ def main():
     args = parser.parse_args()
 
     all_need_references = []
+    metadata: MetaData = {
+        "module_name": "",
+        "hash": "",
+        "url": "",
+    }
+    metadata_set = False
     for file_path in args.files:
+        if "known_good.json" not in str(file_path) and not metadata_set:
+            metadata["module_name"] = parse_module_name_from_path(file_path)
+            print("================")
+            print(metadata)
+            print("===============")
+            print("METADATA SET")
+            metadata_set = True
         abs_file_path = file_path.resolve()
         assert abs_file_path.exists(), abs_file_path
         references = _extract_references_from_file(
             abs_file_path.parent, Path(abs_file_path.name)
         )
         all_need_references.extend(references)
-
-    store_source_code_links_json(args.output, all_need_references)
+    store_source_code_links_with_metadata_json(
+        file=args.output, metadata=metadata, needlist=all_need_references
+    )
     logger.info(
         f"Found {len(all_need_references)} need references in {len(args.files)} files"
     )
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index f194e19ca..034d45db5 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -20,22 +20,71 @@
 import logging
 import sys
 from pathlib import Path
+from typing import Any
+
+# from src.extensions.score_source_code_linker.need_source_links import (
+#     store_source_code_links_combined_json,
+# )
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
+# [
+# PosixPath('bazel-out/k8-fastbuild/bin/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_persistency+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_orchestrator+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_kyron+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_baselibs+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_baselibs_rust+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_logging+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_platform+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_process+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_docs_as_code+/sourcelinks_json.json')
+# ]
+
+
+"""
+if bazel-out/k8-fastbuild/bin/external/ in file_path => module is external 
+otherwise it's local 
+if local => module_name & hash == empty
+if external => parse thing for module_name => look up known_good json for hash & url
+"""
+
+
+def parse_info_from_known_good(
+    known_good_json: Path, module_name: str
+) -> tuple[str, str]:
+    print("===THIS IS MODULE NAME WE LOOK FOR===========")
+    print(module_name)
+    with open(known_good_json, "r") as f:
+        kg_json = json.load(f)
+    for category in kg_json["modules"].values():
+        print("===THIS IS CATEGORY=========")
+        print(category)
+        if module_name in category:
+            print("===THIS IS MODULE NAME INSIDe CATEGORY===========")
+            print(module_name)
+            m = category[module_name]
+            return (m["hash"], m["repo"].removesuffix(".git"))
+    raise KeyError(f"Module {module_name!r} not found in known_good_json.")
+
 
 def main():
     parser = argparse.ArgumentParser(
         description="Merge multiple sourcelinks JSON files into one"
     )
-    parser.add_argument(
+    _ = parser.add_argument(
         "--output",
         required=True,
         type=Path,
         help="Output merged JSON file path",
     )
-    parser.add_argument(
+    _ = parser.add_argument(
+        "--known_good",
+        default=None,
+        help="Optional path to a 'known good' JSON file (provided by Bazel).",
+    )
+    _ = parser.add_argument(
         "files",
         nargs="*",
         type=Path,
@@ -43,13 +92,26 @@ def main():
     )
 
     args = parser.parse_args()
+    all_files = [x for x in args.files if "known_good.json" not in str(x)]
 
     merged = []
-    for json_file in args.files:
+    for json_file in all_files:
         with open(json_file) as f:
             data = json.load(f)
+            metadata = data[0]
+            if metadata["module_name"] and metadata["module_name"] != "local_module":
+                hash, repo = parse_info_from_known_good(
+                    known_good_json=args.known_good, module_name=metadata["module_name"]
+                )
+                metadata["hash"] = hash
+                metadata["url"] = repo
+            # In the case that 'metadata[module_name]' is empty
+            # hash & url are already existing and empty inside of 'metadata'
+            # Therefore all 3 keys will be written to needlinks in each branch
+            for d in data[1:]:
+                d.update(metadata)
             assert isinstance(data, list), repr(data)
-            merged.extend(data)
+            merged.extend(data[1:])
 
     with open(args.output, "w") as f:
         json.dump(merged, f, indent=2, ensure_ascii=False)
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index cf9843dc5..7e0ff0252 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -21,7 +21,6 @@
 # This whole directory implements the above mentioned tool requirements
 
 import os
-from collections import defaultdict
 from copy import deepcopy
 from pathlib import Path
 from typing import cast
@@ -40,10 +39,19 @@
     SourceCodeLinks,
     load_source_code_links_combined_json,
     store_source_code_links_combined_json,
+    group_by_need,
 )
+
+from src.extensions.score_source_code_linker.module_source_links import (
+    group_needs_by_module,
+    store_module_source_links_json,
+    load_module_source_links_json,
+)
+
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
     load_source_code_links_json,
+    load_source_code_links_with_metadata_json,
 )
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
@@ -71,53 +79,6 @@
 #          ╰──────────────────────────────────────╯
 
 
-def group_by_need(
-    source_code_links: list[NeedLink],
-    test_case_links: list[DataForTestLink] | None = None,
-) -> list[SourceCodeLinks]:
-    """
-    Groups the given need links and test case links by their need ID.
-    Returns a nested dictionary structure with 'CodeLink' and 'TestLink' categories.
-    Example output:
-
-
-      {
-        "need": "<need_id>",
-        "links": {
-          "CodeLinks": [NeedLink, NeedLink, ...],
-          "TestLinks": [testlink, testlink, ...]
-        }
-      }
-    """
-    # TODO: I wonder if there is a more efficent way to do this
-    grouped_by_need: dict[str, NeedSourceLinks] = defaultdict(
-        lambda: NeedSourceLinks(TestLinks=[], CodeLinks=[])
-    )
-
-    # Group source code links
-    for needlink in source_code_links:
-        grouped_by_need[needlink.need].CodeLinks.append(needlink)
-
-    # Group test case links
-    if test_case_links is not None:
-        for testlink in test_case_links:
-            grouped_by_need[testlink.need].TestLinks.append(testlink)
-
-    # Build final list of SourceCodeLinks
-    result: list[SourceCodeLinks] = [
-        SourceCodeLinks(
-            need=need,
-            links=NeedSourceLinks(
-                CodeLinks=need_links.CodeLinks,
-                TestLinks=need_links.TestLinks,
-            ),
-        )
-        for need, need_links in grouped_by_need.items()
-    ]
-
-    return result
-
-
 def get_cache_filename(build_dir: Path, filename: str) -> Path:
     """
     Returns the path to the cache file for the source code linker.
@@ -142,14 +103,19 @@ def build_and_save_combined_file(outdir: Path):
     else:
         source_code_links_json = Path(source_code_links_json)
 
-    source_code_links = load_source_code_links_json(source_code_links_json)
+    # This isn't pretty will think of a better solution later, for now this should work
+    try:
+        source_code_links = load_source_code_links_json(source_code_links_json)
+    except AssertionError:
+        source_code_links = load_source_code_links_with_metadata_json(
+            source_code_links_json
+        )
     test_code_links = load_test_xml_parsed_json(
         get_cache_filename(outdir, "score_xml_parser_cache.json")
     )
-
+    scl_list = group_by_need(source_code_links, test_code_links)
     store_source_code_links_combined_json(
-        outdir / "score_scl_grouped_cache.json",
-        group_by_need(source_code_links, test_code_links),
+        outdir / "score_scl_grouped_cache.json", scl_list
     )
 
 
@@ -254,10 +220,10 @@ def setup_test_code_linker(app: Sphinx, env: BuildEnvironment):
 
 
 def register_combined_linker(app: Sphinx):
-    # Registering the combined linker to Sphinx
+    # Registering the final combine linker to Sphinx
     # priority is set to make sure it is called in the right order.
-    # Needs to be called after xml parsing & codelink
-    app.connect("env-updated", setup_combined_linker, priority=507)
+    # Needs to be called after xml parsing & codelink & combined_linker
+    app.connect("env-updated", setup_combined_linker, priority=510)
 
 
 def setup_combined_linker(app: Sphinx, _: BuildEnvironment):
@@ -272,6 +238,37 @@ def setup_combined_linker(app: Sphinx, _: BuildEnvironment):
         build_and_save_combined_file(app.outdir)
 
 
+def register_module_linker(app: Sphinx):
+    # Registering the combined linker to Sphinx
+    # priority is set to make sure it is called in the right order.
+    # Needs to be called after xml parsing & codelink
+    app.connect("env-updated", setup_module_linker, priority=520)
+
+
+def build_and_save_module_scl_file(outdir: Path):
+    scl_links = load_source_code_links_combined_json(
+        get_cache_filename(outdir, "score_scl_grouped_cache.json")
+    )
+    mcl_links = group_needs_by_module(scl_links)
+    store_module_source_links_json(
+        outdir / "score_module_grouped_scl_cache.json", mcl_links
+    )
+
+
+def setup_module_linker(app: Sphinx, _: BuildEnvironment):
+    grouped_cache = get_cache_filename(
+        app.outdir, "score_module_grouped_scl_cache.json"
+    )
+    gruped_cache_exists = grouped_cache.exists()
+    # TODO this cache should be done via Bazel
+    if not gruped_cache_exists or not app.config.skip_rescanning_via_source_code_linker:
+        LOGGER.debug(
+            "Did not find combined json 'score_module_grouped_scl_cache.json' "
+            "in _build. Generating new one"
+        )
+        build_and_save_module_scl_file(app.outdir)
+
+
 def setup_once(app: Sphinx):
     # might be the only way to solve this?
     if "skip_rescanning_via_source_code_linker" in app.config:
@@ -295,9 +292,10 @@ def setup_once(app: Sphinx):
     setup_source_code_linker(app, ws_root)
     register_test_code_linker(app)
     register_combined_linker(app)
+    register_module_linker(app)
 
-    # Priorty=510 to ensure it's called after the test code linker & combined connection
-    app.connect("env-updated", inject_links_into_needs, priority=510)
+    # Priorty=515 to ensure it's called after the test code linker & combined connection
+    app.connect("env-updated", inject_links_into_needs, priority=525)
 
 
 def setup(app: Sphinx) -> dict[str, str | bool]:
@@ -352,42 +350,46 @@ def inject_links_into_needs(app: Sphinx, env: BuildEnvironment) -> None:
                     f"?? Need {id} already has testlink: {need.get('testlink')}"
                 )
 
-    source_code_links_by_need = load_source_code_links_combined_json(
-        get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
+    scl_by_module = load_module_source_links_json(
+        get_cache_filename(app.outdir, "score_module_grouped_scl_cache.json")
     )
+    # source_code_links_by_need = load_source_code_links_combined_json(
+    #     get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
+    # )
+    for module_grouped_needs in scl_by_module:
+        for source_code_links in module_grouped_needs.needs:
+            need = find_need(needs_copy, source_code_links.need)
+            if need is None:
+                # TODO: print github annotations as in https://github.com/eclipse-score/bazel_registry/blob/7423b9996a45dd0a9ec868e06a970330ee71cf4f/tools/verify_semver_compatibility_level.py#L126-L129
+                for n in source_code_links.links.CodeLinks:
+                    LOGGER.warning(
+                        f"{n.file}:{n.line}: Could not find {source_code_links.need} "
+                        "in documentation [CODE LINK]",
+                        type="score_source_code_linker",
+                    )
+                for n in source_code_links.links.TestLinks:
+                    LOGGER.warning(
+                        f"{n.file}:{n.line}: Could not find {source_code_links.need} "
+                        "in documentation [TEST LINK]",
+                        type="score_source_code_linker",
+                    )
+                continue
+
+            need_as_dict = cast(dict[str, object], need)
+            metadata = module_grouped_needs.module_name
+            need_as_dict["source_code_link"] = ", ".join(
+                f"{get_github_link(metadata, n)}<>{n.file}:{n.line}"
+                for n in source_code_links.links.CodeLinks
+            )
+            need_as_dict["testlink"] = ", ".join(
+                f"{get_github_link(metadata, n)}<>{n.name}"
+                for n in source_code_links.links.TestLinks
+            )
 
-    for source_code_links in source_code_links_by_need:
-        need = find_need(needs_copy, source_code_links.need)
-        if need is None:
-            # TODO: print github annotations as in https://github.com/eclipse-score/bazel_registry/blob/7423b9996a45dd0a9ec868e06a970330ee71cf4f/tools/verify_semver_compatibility_level.py#L126-L129
-            for n in source_code_links.links.CodeLinks:
-                LOGGER.warning(
-                    f"{n.file}:{n.line}: Could not find {source_code_links.need} "
-                    "in documentation [CODE LINK]",
-                    type="score_source_code_linker",
-                )
-            for n in source_code_links.links.TestLinks:
-                LOGGER.warning(
-                    f"{n.file}:{n.line}: Could not find {source_code_links.need} "
-                    "in documentation [TEST LINK]",
-                    type="score_source_code_linker",
-                )
-            continue
-
-        need_as_dict = cast(dict[str, object], need)
-
-        need_as_dict["source_code_link"] = ", ".join(
-            f"{get_github_link(n)}<>{n.file}:{n.line}"
-            for n in source_code_links.links.CodeLinks
-        )
-        need_as_dict["testlink"] = ", ".join(
-            f"{get_github_link(n)}<>{n.name}" for n in source_code_links.links.TestLinks
-        )
-
-        # NOTE: Removing & adding the need is important to make sure
-        # the needs gets 're-evaluated'.
-        Needs_Data.remove_need(need["id"])
-        Needs_Data.add_need(need)
+            # NOTE: Removing & adding the need is important to make sure
+            # the needs gets 're-evaluated'.
+            Needs_Data.remove_need(need["id"])
+            Needs_Data.add_need(need)
 
 
 #          ╭──────────────────────────────────────╮
diff --git a/src/extensions/score_source_code_linker/metadata.py b/src/extensions/score_source_code_linker/metadata.py
new file mode 100644
index 000000000..03acc537a
--- /dev/null
+++ b/src/extensions/score_source_code_linker/metadata.py
@@ -0,0 +1,23 @@
+# *******************************************************************************
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+
+from typing import TypedDict, TypeGuard
+
+class MetaData(TypedDict):
+    module_name: str
+    hash: str
+    url: str
+
+def is_metadata(x: object) -> TypeGuard[MetaData]:
+    # Make this as strict/loose as you want; at minimum, it must be a dict.
+    return isinstance(x, dict) and {"module_name", "hash", "url"} <= x.keys()
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
new file mode 100644
index 000000000..3957733f0
--- /dev/null
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -0,0 +1,137 @@
+# *******************************************************************************
+# Copyright (c) 2025 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+
+
+from dataclasses import dataclass, asdict, field
+import json
+from typing import Any
+from pathlib import Path
+
+
+from src.extensions.score_source_code_linker.need_source_links import (
+    NeedSourceLinks,
+    SourceCodeLinks,
+    SourceCodeLinks_JSON_Decoder,
+)
+from src.extensions.score_source_code_linker.needlinks import NeedLink
+from src.extensions.score_source_code_linker.testlink import DataForTestLink
+
+
+@dataclass
+class moduleInfo:
+    name: str
+    hash: str
+    url: str
+
+
+@dataclass
+class ModuleSourceLinks:
+    module_name: moduleInfo
+    needs: list[SourceCodeLinks] = field(default_factory=list)
+
+
+class ModuleSourceLinks_JSON_Encoder(json.JSONEncoder):
+    def default(self, o: object):
+        if isinstance(o, Path):
+            return str(o)
+        # We do not want to save the metadata inside the codelink
+        # (hash, module_name, url)
+        if isinstance(o, NeedLink):
+            return o.to_dict_without_metadata()
+        if isinstance(
+            o, ModuleSourceLinks | SourceCodeLinks | DataForTestLink | NeedSourceLinks
+        ):
+            return asdict(o)
+        return super().default(o)
+
+
+def ModuleSourceLinks_JSON_Decoder(
+    d: dict[str, Any],
+) -> ModuleSourceLinks | dict[str, Any]:
+    if "module_name" in d and "needs" in d:
+        module_name = d["module_name"]
+        needs = d["needs"]
+        return ModuleSourceLinks(
+            module_name=moduleInfo(
+                name=module_name.get("module_name"),
+                hash=module_name.get("hash"),
+                url=module_name.get("url"),
+            ),
+            # We know this can only be list[SourceCodeLinks] and nothing else
+            # Therefore => we ignore the type error here
+            needs=[SourceCodeLinks_JSON_Decoder(need) for need in needs] # type: ignore
+        )
+    return d
+
+
+def store_module_source_links_json(
+    file: Path, source_code_links: list[ModuleSourceLinks]
+):
+    # After `rm -rf _build` or on clean builds the directory does not exist, so we need
+    # to create it
+    file.parent.mkdir(exist_ok=True)
+    with open(file, "w") as f:
+        json.dump(
+            source_code_links,
+            f,
+            cls=ModuleSourceLinks_JSON_Encoder,
+            indent=2,
+            ensure_ascii=False,
+        )
+
+
+def load_module_source_links_json(file: Path) -> list[ModuleSourceLinks]:
+    links: list[ModuleSourceLinks] = json.loads(
+        file.read_text(encoding="utf-8"),
+        object_hook=ModuleSourceLinks_JSON_Decoder,
+    )
+    assert isinstance(links, list), (
+        "The combined source code linker links should be "
+        "a list of SourceCodeLinks objects."
+    )
+    assert all(isinstance(link, ModuleSourceLinks) for link in links), (
+        "All items in combined_source_code_linker_cache should be "
+        "SourceCodeLinks objects."
+    )
+    return links
+
+
+def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLinks]:
+    module_groups: dict[str, ModuleSourceLinks] = {}
+
+    for source_link in links:
+        if not source_link.links.CodeLinks:
+            continue
+
+        first_link = source_link.links.CodeLinks[0]
+        module_key = first_link.module_name
+
+        if module_key not in module_groups:
+            module_groups[module_key] = ModuleSourceLinks(
+                module_name=moduleInfo(name=module_key, hash=first_link.hash, url=first_link.url)
+            )
+
+        module_groups[module_key].needs.append(source_link)  # Much clearer!
+
+    return [
+        ModuleSourceLinks(module_name=group.module_name, needs=group.needs)
+        for group in module_groups.values()
+    ]
+
+
+# # Pouplate Metadata
+# # Since all metadata inside the Codelinks is the same
+# # we can just arbitrarily grab the first one
+# module_name=need_links.CodeLinks[0].module_name,
+# hash=need_links.CodeLinks[0].hash,
+# url=need_links.CodeLinks[0].url,
diff --git a/src/extensions/score_source_code_linker/need_source_links.py b/src/extensions/score_source_code_linker/need_source_links.py
index 6c738da8e..2deb4c5e8 100644
--- a/src/extensions/score_source_code_linker/need_source_links.py
+++ b/src/extensions/score_source_code_linker/need_source_links.py
@@ -21,6 +21,7 @@
 
 import json
 from dataclasses import asdict, dataclass, field
+from collections import defaultdict
 from pathlib import Path
 from typing import Any
 
@@ -108,3 +109,53 @@ def load_source_code_links_combined_json(file: Path) -> list[SourceCodeLinks]:
         "SourceCodeLinks objects."
     )
     return links
+
+
+def group_by_need(
+    source_code_links: list[NeedLink],
+    test_case_links: list[DataForTestLink] | None = None,
+) -> list[SourceCodeLinks]:
+    """
+    Groups the given need links and test case links by their need ID.
+    Returns a nested dictionary structure with 'CodeLink' and 'TestLink' categories.
+    Example output:
+
+
+      {
+        "need": "<need_id>",
+        "module_name": <module_name>,
+        "hash": <git hash>,
+        "url": <github base url>,
+        "links": {
+          "CodeLinks": [NeedLink, NeedLink, ...],
+          "TestLinks": [testlink, testlink, ...]
+        }
+      }
+    """
+    # TODO: I wonder if there is a more efficent way to do this
+    grouped_by_need: dict[str, NeedSourceLinks] = defaultdict(
+        lambda: NeedSourceLinks(TestLinks=[], CodeLinks=[])
+    )
+
+    # Group source code links
+    for needlink in source_code_links:
+        grouped_by_need[needlink.need].CodeLinks.append(needlink)
+
+    # Group test case links
+    if test_case_links is not None:
+        for testlink in test_case_links:
+            grouped_by_need[testlink.need].TestLinks.append(testlink)
+
+    # Build final list of SourceCodeLinks
+    result: list[SourceCodeLinks] = [
+        SourceCodeLinks(
+            need=need,
+            links=NeedSourceLinks(
+                CodeLinks=need_links.CodeLinks,
+                TestLinks=need_links.TestLinks,
+            ),
+        )
+        for need, need_links in grouped_by_need.items()
+    ]
+
+    return result
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index 348147292..a727025bd 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -16,10 +16,11 @@
 import os
 from dataclasses import asdict, dataclass
 from pathlib import Path
-from typing import Any
+from typing import Any, TypeGuard
+from src.extensions.score_source_code_linker.metadata import MetaData, is_metadata
 
 
-@dataclass(frozen=True, order=True)
+@dataclass(order=True)
 class NeedLink:
     """Represents a single template string finding in a file."""
 
@@ -28,6 +29,19 @@ class NeedLink:
     tag: str
     need: str
     full_line: str
+    module_name: str = ""
+    hash: str = ""
+    url: str = ""
+
+    def to_dict_full(self) -> dict[str, str | Path]:
+        return asdict(self)
+
+    def to_dict_without_metadata(self) -> dict[str, str | Path]:
+        d = asdict(self)
+        d.pop("module_name", None)
+        d.pop("hash", None)
+        d.pop("url", None)
+        return d
 
 
 def DefaultNeedLink() -> NeedLink:
@@ -41,6 +55,8 @@ def DefaultNeedLink() -> NeedLink:
         tag="",
         need="",
         full_line="",
+        # Module_name, hash, url are defaulted to ""
+        # therefore not needed to be listed
     )
 
 
@@ -61,26 +77,99 @@ def needlink_decoder(d: dict[str, Any]) -> NeedLink | dict[str, Any]:
             tag=d["tag"],
             need=d["need"],
             full_line=d["full_line"],
+            module_name=d.get("module_name", ""),
+            hash=d.get("hash", ""),
+            url=d.get("url", ""),
         )
     # It's something else, pass it on to other decoders
     return d
 
 
-def store_source_code_links_json(file: Path, needlist: list[NeedLink]):
-    # After `rm -rf _build` or on clean builds the directory does not exist,
-    # so we need to create it
+def store_source_code_links_with_metadata_json(
+    file: Path, metadata: MetaData, needlist: list[NeedLink]
+) -> None:
+    """
+    Writes a JSON array:
+      [ meta_dict, needlink1, needlink2, ... ]
+
+    meta_dict must include:
+      module_name, hash, url
+    """
+    payload: list[object] = [metadata, *needlist]
+
     file.parent.mkdir(exist_ok=True)
-    with open(file, "w") as f:
-        json.dump(
-            needlist,
-            f,
-            cls=NeedLinkEncoder,  # use your custom encoder
-            indent=2,
-            ensure_ascii=False,
+    with open(file, "w", encoding="utf-8") as f:
+        json.dump(payload, f, cls=NeedLinkEncoder, indent=2, ensure_ascii=False)
+
+
+def store_source_code_links_json(file: Path, needlist: list[NeedLink]) -> None:
+    """
+    Writes a JSON array:
+      [ meta_dict, needlink1, needlink2, ... ]
+
+    meta_dict must include:
+      module_name, hash, url
+    """
+
+    file.parent.mkdir(exist_ok=True)
+    with open(file, "w", encoding="utf-8") as f:
+        json.dump(needlist, f, cls=NeedLinkEncoder, indent=2, ensure_ascii=False)
+
+
+def _is_needlink_list(xs: list[object]) -> TypeGuard[list[NeedLink]]:
+    return all(isinstance(link, NeedLink) for link in xs)
+
+
+def load_source_code_links_with_metadata_json(file: Path) -> list[NeedLink]:
+    """
+    Expects the JSON array where first is a meta_dict:
+      [ meta_dict, needlink1, needlink2, ... ]
+    Returns:
+      [NeedLink, NeedLink, ...]
+
+    This normally should be the one called 'locally' => :docs target
+    """
+    if not file.is_absolute():
+        ws_root = os.environ.get("BUILD_WORKSPACE_DIRECTORY")
+        if ws_root:
+            file = Path(ws_root) / file
+
+    data: list[object] = json.loads(
+        file.read_text(encoding="utf-8"),
+        object_hook=needlink_decoder,
+    )
+    links: list[object] = []
+    if not is_metadata(data[0]):
+        raise TypeError(
+            "If you do not have a 'metadata' dict as the first one in the json "
+            "you might wanted to call the load without metadata named: "
+            "'load_source_code_links_json'"
         )
+    metadata: MetaData = data[0]
+    links = data[1:]
+    if not _is_needlink_list(links):
+        raise TypeError(
+            "In local build context all items after"
+            f"metadata must decode to NeedLink objects. File: {file}"
+        )
+    for d in links:
+        d.module_name = metadata["module_name"]
+        d.hash = metadata["hash"]
+        d.url = metadata["url"]
+    return links
 
 
 def load_source_code_links_json(file: Path) -> list[NeedLink]:
+    """
+    Expects the JSON array with needlinks
+    *that already have extra info in them* (module_name, hash, url):
+      [ needlink1, needlink2, ... ]
+    Returns:
+      [NeedLink, NeedLink, ...]
+
+    This normally should be the one called in combo builds
+    => :docs_combo_experimental target
+    """
     if not file.is_absolute():
         # use env variable set by Bazel
         ws_root = os.environ.get("BUILD_WORKSPACE_DIRECTORY")
@@ -98,3 +187,4 @@ def load_source_code_links_json(file: Path) -> list[NeedLink]:
         "All items in source_code_links should be NeedLink objects."
     )
     return links
+
diff --git a/src/helper_lib/additional_functions.py b/src/helper_lib/additional_functions.py
index 5b1ce6d98..872d66af2 100644
--- a/src/helper_lib/additional_functions.py
+++ b/src/helper_lib/additional_functions.py
@@ -14,6 +14,7 @@
 
 # Import types that depend on score_source_code_linker
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink, NeedLink
+from src.extensions.score_source_code_linker.module_source_links import moduleInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
     DataOfTestCase,
@@ -26,6 +27,19 @@
 
 
 def get_github_link(
+    metadata: moduleInfo,
+    link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
+) -> str:
+    if link is None:
+        link = DefaultNeedLink()
+    if not metadata.hash:
+        # Local path (//:docs)
+        return get_github_link_from_git(link)
+    # Ref-Integration path (//:docs_combo..)
+    return get_github_link_from_json(metadata, link)
+
+
+def get_github_link_from_git(
     link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
 ) -> str:
     if link is None:
@@ -36,3 +50,14 @@ def get_github_link(
     base_url = get_github_base_url()
     current_hash = get_current_git_hash(passed_git_root)
     return f"{base_url}/blob/{current_hash}/{link.file}#L{link.line}"
+
+
+def get_github_link_from_json(
+    metadata: moduleInfo,
+    link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
+):
+    if link is None:
+        link = DefaultNeedLink()
+    base_url = metadata.url
+    current_hash = metadata.hash
+    return f"{base_url}/blob/{current_hash}/{link.file}#L{link.line}"

From a898eee3194806d5030e24775ba7b4069fae23c8 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Wed, 11 Mar 2026 21:55:42 +0100
Subject: [PATCH 02/34] WIP: seems to work in ref & local

---
 scripts_bazel/generate_sourcelinks_cli.py     | 13 ++++++++-----
 .../generate_source_code_links_json.py        | 19 +++++++++++--------
 2 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 27a0e4508..2f26784ff 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -89,15 +89,18 @@ def main():
     for file_path in args.files:
         if "known_good.json" not in str(file_path) and not metadata_set:
             metadata["module_name"] = parse_module_name_from_path(file_path)
-            print("================")
-            print(metadata)
-            print("===============")
-            print("METADATA SET")
+            # print("================")
+            # print(metadata)
+            # print("===============")
+            # print("METADATA SET")
             metadata_set = True
         abs_file_path = file_path.resolve()
         assert abs_file_path.exists(), abs_file_path
+        # print("THIS Is ABS FILEPATH: ", file_path)
+        # print("THIS IS ABS FILEPATH NAME: ", abs_file_path.name)
+        # print("THIS Is ABS FILEPATH PARENT: ", abs_file_path.parent)
         references = _extract_references_from_file(
-            abs_file_path.parent, Path(abs_file_path.name)
+            abs_file_path.parent, Path(abs_file_path.name), file_path
         )
         all_need_references.extend(references)
     store_source_code_links_with_metadata_json(
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index abedc2db4..1c240e0ef 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -19,6 +19,8 @@
 
 import os
 from pathlib import Path
+from sphinx_needs.logging import get_logger
+LOGGER = get_logger(__name__)
 
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
@@ -43,21 +45,21 @@ def _extract_references_from_line(line: str):
                 yield tag, req.strip()
 
 
-def _extract_references_from_file(root: Path, file_path: Path) -> list[NeedLink]:
+def _extract_references_from_file(root: Path, file_path_name: Path, file_path: Path) -> list[NeedLink]:
     """Scan a single file for template strings and return findings."""
     assert root.is_absolute(), "Root path must be absolute"
-    assert not file_path.is_absolute(), "File path must be relative to the root"
+    assert not file_path_name.is_absolute(), "File path must be relative to the root"
     # assert file_path.is_relative_to(root), (
     #     f"File path ({file_path}) must be relative to the root ({root})"
     # )
-    assert (root / file_path).exists(), (
-        f"File {file_path} does not exist in root {root}."
+    assert (root / file_path_name).exists(), (
+        f"File {file_path_name} does not exist in root {root}."
     )
 
     findings: list[NeedLink] = []
 
     try:
-        with open(root / file_path, encoding="utf-8", errors="ignore") as f:
+        with open(root / file_path_name, encoding="utf-8", errors="ignore") as f:
             for line_num, line in enumerate(f, 1):
                 for tag, req in _extract_references_from_line(line):
                     findings.append(
@@ -69,8 +71,9 @@ def _extract_references_from_file(root: Path, file_path: Path) -> list[NeedLink]
                             full_line=line.strip(),
                         )
                     )
-    except (UnicodeDecodeError, PermissionError, OSError):
+    except (UnicodeDecodeError, PermissionError, OSError) as e:
         # Skip files that can't be read as text
+        LOGGER.debug(f"Error reading file to parse for linked needs: \n{e}")
         pass
 
     return findings
@@ -121,8 +124,8 @@ def find_all_need_references(search_path: Path) -> list[NeedLink]:
         all_need_references.extend(references)
 
     elapsed_time = os.times().elapsed - start_time
-    print(
-        f"DEBUG: Found {len(all_need_references)} need references "
+    LOGGER.debug(
+        f"Found {len(all_need_references)} need references "
         f"in {elapsed_time:.2f} seconds"
     )
 

From c2861cd1c6f70558f1f2d795d9dc91a5b971cb08 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:23:22 +0100
Subject: [PATCH 03/34] Remove metadata file

---
 scripts_bazel/generate_sourcelinks_cli.py     |  2 +-
 .../score_source_code_linker/metadata.py      | 23 -------------------
 .../score_source_code_linker/needlinks.py     | 14 ++++++++---
 3 files changed, 12 insertions(+), 27 deletions(-)
 delete mode 100644 src/extensions/score_source_code_linker/metadata.py

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 2f26784ff..6d9336e23 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -27,8 +27,8 @@
 )
 from src.extensions.score_source_code_linker.needlinks import (
     store_source_code_links_with_metadata_json,
+    MetaData,
 )
-from src.extensions.score_source_code_linker.metadata import MetaData
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
diff --git a/src/extensions/score_source_code_linker/metadata.py b/src/extensions/score_source_code_linker/metadata.py
deleted file mode 100644
index 03acc537a..000000000
--- a/src/extensions/score_source_code_linker/metadata.py
+++ /dev/null
@@ -1,23 +0,0 @@
-# *******************************************************************************
-# Copyright (c) 2026 Contributors to the Eclipse Foundation
-#
-# See the NOTICE file(s) distributed with this work for additional
-# information regarding copyright ownership.
-#
-# This program and the accompanying materials are made available under the
-# terms of the Apache License Version 2.0 which is available at
-# https://www.apache.org/licenses/LICENSE-2.0
-#
-# SPDX-License-Identifier: Apache-2.0
-# *******************************************************************************
-
-from typing import TypedDict, TypeGuard
-
-class MetaData(TypedDict):
-    module_name: str
-    hash: str
-    url: str
-
-def is_metadata(x: object) -> TypeGuard[MetaData]:
-    # Make this as strict/loose as you want; at minimum, it must be a dict.
-    return isinstance(x, dict) and {"module_name", "hash", "url"} <= x.keys()
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index a727025bd..abcdd0dbb 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -16,8 +16,17 @@
 import os
 from dataclasses import asdict, dataclass
 from pathlib import Path
-from typing import Any, TypeGuard
-from src.extensions.score_source_code_linker.metadata import MetaData, is_metadata
+from typing import Any, TypeGuard, TypedDict
+
+
+class MetaData(TypedDict):
+    module_name: str
+    hash: str
+    url: str
+
+def is_metadata(x: object) -> TypeGuard[MetaData]:
+    # Make this as strict/loose as you want; at minimum, it must be a dict.
+    return isinstance(x, dict) and {"module_name", "hash", "url"} <= x.keys()
 
 
 @dataclass(order=True)
@@ -187,4 +196,3 @@ def load_source_code_links_json(file: Path) -> list[NeedLink]:
         "All items in source_code_links should be NeedLink objects."
     )
     return links
-

From fb5bdc57e88d96627a64254c6081379aed84a60b Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:24:21 +0100
Subject: [PATCH 04/34] Formatting & Linting

---
 scripts_bazel/merge_sourcelinks.py               |  7 +++----
 .../score_source_code_linker/__init__.py         | 16 +++++++---------
 .../generate_source_code_links_json.py           |  2 ++
 .../module_source_links.py                       | 13 ++++++-------
 .../need_source_links.py                         |  2 +-
 src/helper_lib/additional_functions.py           |  3 ++-
 6 files changed, 21 insertions(+), 22 deletions(-)

diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index 034d45db5..aa5ece761 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -20,7 +20,6 @@
 import logging
 import sys
 from pathlib import Path
-from typing import Any
 
 # from src.extensions.score_source_code_linker.need_source_links import (
 #     store_source_code_links_combined_json,
@@ -44,8 +43,8 @@
 
 
 """
-if bazel-out/k8-fastbuild/bin/external/ in file_path => module is external 
-otherwise it's local 
+if bazel-out/k8-fastbuild/bin/external/ in file_path => module is external
+otherwise it's local
 if local => module_name & hash == empty
 if external => parse thing for module_name => look up known_good json for hash & url
 """
@@ -56,7 +55,7 @@ def parse_info_from_known_good(
 ) -> tuple[str, str]:
     print("===THIS IS MODULE NAME WE LOOK FOR===========")
     print(module_name)
-    with open(known_good_json, "r") as f:
+    with open(known_good_json) as f:
         kg_json = json.load(f)
     for category in kg_json["modules"].values():
         print("===THIS IS CATEGORY=========")
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index 7e0ff0252..d82994dd0 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -34,20 +34,18 @@
 from src.extensions.score_source_code_linker.generate_source_code_links_json import (
     generate_source_code_links_json,
 )
+from src.extensions.score_source_code_linker.module_source_links import (
+    group_needs_by_module,
+    load_module_source_links_json,
+    store_module_source_links_json,
+)
 from src.extensions.score_source_code_linker.need_source_links import (
     NeedSourceLinks,
     SourceCodeLinks,
+    group_by_need,
     load_source_code_links_combined_json,
     store_source_code_links_combined_json,
-    group_by_need,
 )
-
-from src.extensions.score_source_code_linker.module_source_links import (
-    group_needs_by_module,
-    store_module_source_links_json,
-    load_module_source_links_json,
-)
-
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
     load_source_code_links_json,
@@ -376,7 +374,7 @@ def inject_links_into_needs(app: Sphinx, env: BuildEnvironment) -> None:
                 continue
 
             need_as_dict = cast(dict[str, object], need)
-            metadata = module_grouped_needs.module_name
+            metadata = module_grouped_needs.module
             need_as_dict["source_code_link"] = ", ".join(
                 f"{get_github_link(metadata, n)}<>{n.file}:{n.line}"
                 for n in source_code_links.links.CodeLinks
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index 1c240e0ef..ce6839b80 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -19,7 +19,9 @@
 
 import os
 from pathlib import Path
+
 from sphinx_needs.logging import get_logger
+
 LOGGER = get_logger(__name__)
 
 from src.extensions.score_source_code_linker.needlinks import (
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index 3957733f0..fe757b947 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -12,11 +12,10 @@
 # *******************************************************************************
 
 
-from dataclasses import dataclass, asdict, field
 import json
-from typing import Any
+from dataclasses import asdict, dataclass, field
 from pathlib import Path
-
+from typing import Any
 
 from src.extensions.score_source_code_linker.need_source_links import (
     NeedSourceLinks,
@@ -36,7 +35,7 @@ class moduleInfo:
 
 @dataclass
 class ModuleSourceLinks:
-    module_name: moduleInfo
+    module: moduleInfo
     needs: list[SourceCodeLinks] = field(default_factory=list)
 
 
@@ -62,7 +61,7 @@ def ModuleSourceLinks_JSON_Decoder(
         module_name = d["module_name"]
         needs = d["needs"]
         return ModuleSourceLinks(
-            module_name=moduleInfo(
+            module=moduleInfo(
                 name=module_name.get("module_name"),
                 hash=module_name.get("hash"),
                 url=module_name.get("url"),
@@ -118,13 +117,13 @@ def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLink
 
         if module_key not in module_groups:
             module_groups[module_key] = ModuleSourceLinks(
-                module_name=moduleInfo(name=module_key, hash=first_link.hash, url=first_link.url)
+                module=moduleInfo(name=module_key, hash=first_link.hash, url=first_link.url)
             )
 
         module_groups[module_key].needs.append(source_link)  # Much clearer!
 
     return [
-        ModuleSourceLinks(module_name=group.module_name, needs=group.needs)
+        ModuleSourceLinks(module=group.module, needs=group.needs)
         for group in module_groups.values()
     ]
 
diff --git a/src/extensions/score_source_code_linker/need_source_links.py b/src/extensions/score_source_code_linker/need_source_links.py
index 2deb4c5e8..1823ba4b4 100644
--- a/src/extensions/score_source_code_linker/need_source_links.py
+++ b/src/extensions/score_source_code_linker/need_source_links.py
@@ -20,8 +20,8 @@
 # req-Id: tool_req__docs_dd_link_source_code_link
 
 import json
-from dataclasses import asdict, dataclass, field
 from collections import defaultdict
+from dataclasses import asdict, dataclass, field
 from pathlib import Path
 from typing import Any
 
diff --git a/src/helper_lib/additional_functions.py b/src/helper_lib/additional_functions.py
index 872d66af2..049a14548 100644
--- a/src/helper_lib/additional_functions.py
+++ b/src/helper_lib/additional_functions.py
@@ -12,9 +12,10 @@
 # *******************************************************************************
 from pathlib import Path
 
+from src.extensions.score_source_code_linker.module_source_links import moduleInfo
+
 # Import types that depend on score_source_code_linker
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink, NeedLink
-from src.extensions.score_source_code_linker.module_source_links import moduleInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
     DataOfTestCase,

From 8ea74178ce76d900d0ee72978737ade17fb8b5b1 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:26:11 +0100
Subject: [PATCH 05/34] Known_good required in merge script

---
 scripts_bazel/merge_sourcelinks.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index aa5ece761..43785ea91 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -80,7 +80,7 @@ def main():
     )
     _ = parser.add_argument(
         "--known_good",
-        default=None,
+        required=True,
         help="Optional path to a 'known good' JSON file (provided by Bazel).",
     )
     _ = parser.add_argument(

From f818cf26d03a359d1330db68c48c12fc5a22c5b4 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:30:37 +0100
Subject: [PATCH 06/34] Remove debug print statements

---
 scripts_bazel/generate_sourcelinks_cli.py | 17 +++--------------
 scripts_bazel/merge_sourcelinks.py        |  8 +-------
 2 files changed, 4 insertions(+), 21 deletions(-)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 6d9336e23..8b1c4bfd5 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -44,15 +44,11 @@ def parse_module_name_from_path(path: Path) -> str:
     # COMBO BUILD
     # If external is in the filepath that gets parsed =>
     # file is in an external module => combo build
-    # e.g. .../external/score_docs_as_code+/src/helper_lib/__init__.py
+    # Example Path:
+    #   PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
 
-    # PATH if we are in local repository
-    # PosixPath('src/helper_lib/test_helper_lib.py')
-    # Path if we are in combo build and externally
-    # PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
-    print("======== THIs IS PATH we PARSIGN FOr MODULE NAME")
-    print(path)
     if str(path).startswith("external/"):
+        # This allows for files / folders etc. to have `external` in their name too.
         module_raw = str(path).removeprefix("external/")
         filepath_split = str(module_raw).split("/", maxsplit=1)
         module_name = str(filepath_split[0].removesuffix("+"))
@@ -89,16 +85,9 @@ def main():
     for file_path in args.files:
         if "known_good.json" not in str(file_path) and not metadata_set:
             metadata["module_name"] = parse_module_name_from_path(file_path)
-            # print("================")
-            # print(metadata)
-            # print("===============")
-            # print("METADATA SET")
             metadata_set = True
         abs_file_path = file_path.resolve()
         assert abs_file_path.exists(), abs_file_path
-        # print("THIS Is ABS FILEPATH: ", file_path)
-        # print("THIS IS ABS FILEPATH NAME: ", abs_file_path.name)
-        # print("THIS Is ABS FILEPATH PARENT: ", abs_file_path.parent)
         references = _extract_references_from_file(
             abs_file_path.parent, Path(abs_file_path.name), file_path
         )
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index 43785ea91..b956b0bda 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -53,16 +53,10 @@
 def parse_info_from_known_good(
     known_good_json: Path, module_name: str
 ) -> tuple[str, str]:
-    print("===THIS IS MODULE NAME WE LOOK FOR===========")
-    print(module_name)
     with open(known_good_json) as f:
         kg_json = json.load(f)
     for category in kg_json["modules"].values():
-        print("===THIS IS CATEGORY=========")
-        print(category)
         if module_name in category:
-            print("===THIS IS MODULE NAME INSIDe CATEGORY===========")
-            print(module_name)
             m = category[module_name]
             return (m["hash"], m["repo"].removesuffix(".git"))
     raise KeyError(f"Module {module_name!r} not found in known_good_json.")
@@ -104,7 +98,7 @@ def main():
                 )
                 metadata["hash"] = hash
                 metadata["url"] = repo
-            # In the case that 'metadata[module_name]' is empty
+            # In the case that 'metadata[module_name]' is 'local_module' or empty (somehow)
             # hash & url are already existing and empty inside of 'metadata'
             # Therefore all 3 keys will be written to needlinks in each branch
             for d in data[1:]:

From adeae4f8501a3c31369528fba7e3d8d4019c24d4 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:40:57 +0100
Subject: [PATCH 07/34] Copilot Findings

---
 .../score_source_code_linker/__init__.py           |  4 ++--
 .../module_source_links.py                         | 14 ++++++++------
 .../score_source_code_linker/needlinks.py          |  9 +++------
 src/helper_lib/additional_functions.py             |  6 +++---
 4 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index d82994dd0..6a409b917 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -226,9 +226,9 @@ def register_combined_linker(app: Sphinx):
 
 def setup_combined_linker(app: Sphinx, _: BuildEnvironment):
     grouped_cache = get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
-    gruped_cache_exists = grouped_cache.exists()
+    grouped_cache_exists = grouped_cache.exists()
     # TODO this cache should be done via Bazel
-    if not gruped_cache_exists or not app.config.skip_rescanning_via_source_code_linker:
+    if not grouped_cache_exists or not app.config.skip_rescanning_via_source_code_linker:
         LOGGER.debug(
             "Did not find combined json 'score_scl_grouped_cache.json' in _build."
             "Generating new one"
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index fe757b947..9197b75ff 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -27,7 +27,7 @@
 
 
 @dataclass
-class moduleInfo:
+class ModuleInfo:
     name: str
     hash: str
     url: str
@@ -35,7 +35,7 @@ class moduleInfo:
 
 @dataclass
 class ModuleSourceLinks:
-    module: moduleInfo
+    module: ModuleInfo
     needs: list[SourceCodeLinks] = field(default_factory=list)
 
 
@@ -48,7 +48,7 @@ def default(self, o: object):
         if isinstance(o, NeedLink):
             return o.to_dict_without_metadata()
         if isinstance(
-            o, ModuleSourceLinks | SourceCodeLinks | DataForTestLink | NeedSourceLinks
+            o, (ModuleSourceLinks, SourceCodeLinks, DataForTestLink, NeedSourceLinks)
         ):
             return asdict(o)
         return super().default(o)
@@ -61,14 +61,14 @@ def ModuleSourceLinks_JSON_Decoder(
         module_name = d["module_name"]
         needs = d["needs"]
         return ModuleSourceLinks(
-            module=moduleInfo(
+            module=ModuleInfo(
                 name=module_name.get("module_name"),
                 hash=module_name.get("hash"),
                 url=module_name.get("url"),
             ),
             # We know this can only be list[SourceCodeLinks] and nothing else
             # Therefore => we ignore the type error here
-            needs=[SourceCodeLinks_JSON_Decoder(need) for need in needs] # type: ignore
+            needs=[SourceCodeLinks_JSON_Decoder(need) for need in needs],  # type: ignore
         )
     return d
 
@@ -117,7 +117,9 @@ def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLink
 
         if module_key not in module_groups:
             module_groups[module_key] = ModuleSourceLinks(
-                module=moduleInfo(name=module_key, hash=first_link.hash, url=first_link.url)
+                module=ModuleInfo(
+                    name=module_key, hash=first_link.hash, url=first_link.url
+                )
             )
 
         module_groups[module_key].needs.append(source_link)  # Much clearer!
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index abcdd0dbb..324e54114 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -42,10 +42,10 @@ class NeedLink:
     hash: str = ""
     url: str = ""
 
-    def to_dict_full(self) -> dict[str, str | Path]:
+    def to_dict_full(self) -> dict[str, str | Path | int]:
         return asdict(self)
 
-    def to_dict_without_metadata(self) -> dict[str, str | Path]:
+    def to_dict_without_metadata(self) -> dict[str, str | Path | int]:
         d = asdict(self)
         d.pop("module_name", None)
         d.pop("hash", None)
@@ -114,10 +114,7 @@ def store_source_code_links_with_metadata_json(
 def store_source_code_links_json(file: Path, needlist: list[NeedLink]) -> None:
     """
     Writes a JSON array:
-      [ meta_dict, needlink1, needlink2, ... ]
-
-    meta_dict must include:
-      module_name, hash, url
+      [ needlink1, needlink2, ... ]
     """
 
     file.parent.mkdir(exist_ok=True)
diff --git a/src/helper_lib/additional_functions.py b/src/helper_lib/additional_functions.py
index 049a14548..21b4d6fd2 100644
--- a/src/helper_lib/additional_functions.py
+++ b/src/helper_lib/additional_functions.py
@@ -12,7 +12,7 @@
 # *******************************************************************************
 from pathlib import Path
 
-from src.extensions.score_source_code_linker.module_source_links import moduleInfo
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
 
 # Import types that depend on score_source_code_linker
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink, NeedLink
@@ -28,7 +28,7 @@
 
 
 def get_github_link(
-    metadata: moduleInfo,
+    metadata: ModuleInfo,
     link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
 ) -> str:
     if link is None:
@@ -54,7 +54,7 @@ def get_github_link_from_git(
 
 
 def get_github_link_from_json(
-    metadata: moduleInfo,
+    metadata: ModuleInfo,
     link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
 ):
     if link is None:

From b92bf6e912a24081946b2427c786d01e2ecbfb95 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 14:06:22 +0100
Subject: [PATCH 08/34] Formatting & Linting

---
 scripts_bazel/generate_sourcelinks_cli.py          |  5 ++---
 scripts_bazel/merge_sourcelinks.py                 | 14 +-------------
 .../score_source_code_linker/__init__.py           | 12 ++++--------
 .../generate_source_code_links_json.py             |  8 +++++---
 .../module_source_links.py                         |  2 +-
 .../score_source_code_linker/needlinks.py          |  2 +-
 6 files changed, 14 insertions(+), 29 deletions(-)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 8b1c4bfd5..ba54b5d23 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -26,8 +26,8 @@
     _extract_references_from_file,  # pyright: ignore[reportPrivateUsage] TODO: move it out of the extension and into this script
 )
 from src.extensions.score_source_code_linker.needlinks import (
-    store_source_code_links_with_metadata_json,
     MetaData,
+    store_source_code_links_with_metadata_json,
 )
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
@@ -51,8 +51,7 @@ def parse_module_name_from_path(path: Path) -> str:
         # This allows for files / folders etc. to have `external` in their name too.
         module_raw = str(path).removeprefix("external/")
         filepath_split = str(module_raw).split("/", maxsplit=1)
-        module_name = str(filepath_split[0].removesuffix("+"))
-        return module_name
+        return str(filepath_split[0].removesuffix("+"))
     return "local_module"
 
 
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index b956b0bda..626b48c56 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -28,18 +28,6 @@
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
-# [
-# PosixPath('bazel-out/k8-fastbuild/bin/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_persistency+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_orchestrator+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_kyron+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_baselibs+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_baselibs_rust+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_logging+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_platform+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_process+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_docs_as_code+/sourcelinks_json.json')
-# ]
 
 
 """
@@ -98,7 +86,7 @@ def main():
                 )
                 metadata["hash"] = hash
                 metadata["url"] = repo
-            # In the case that 'metadata[module_name]' is 'local_module' or empty (somehow)
+            # In the case that 'metadata[module_name]' is 'local_module'
             # hash & url are already existing and empty inside of 'metadata'
             # Therefore all 3 keys will be written to needlinks in each branch
             for d in data[1:]:
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index 6a409b917..a84ddfb42 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -40,19 +40,15 @@
     store_module_source_links_json,
 )
 from src.extensions.score_source_code_linker.need_source_links import (
-    NeedSourceLinks,
-    SourceCodeLinks,
     group_by_need,
     load_source_code_links_combined_json,
     store_source_code_links_combined_json,
 )
 from src.extensions.score_source_code_linker.needlinks import (
-    NeedLink,
     load_source_code_links_json,
     load_source_code_links_with_metadata_json,
 )
 from src.extensions.score_source_code_linker.testlink import (
-    DataForTestLink,
     load_data_of_test_case_json,
     load_test_xml_parsed_json,
 )
@@ -228,7 +224,10 @@ def setup_combined_linker(app: Sphinx, _: BuildEnvironment):
     grouped_cache = get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
     grouped_cache_exists = grouped_cache.exists()
     # TODO this cache should be done via Bazel
-    if not grouped_cache_exists or not app.config.skip_rescanning_via_source_code_linker:
+    if (
+        not grouped_cache_exists
+        or not app.config.skip_rescanning_via_source_code_linker
+    ):
         LOGGER.debug(
             "Did not find combined json 'score_scl_grouped_cache.json' in _build."
             "Generating new one"
@@ -351,9 +350,6 @@ def inject_links_into_needs(app: Sphinx, env: BuildEnvironment) -> None:
     scl_by_module = load_module_source_links_json(
         get_cache_filename(app.outdir, "score_module_grouped_scl_cache.json")
     )
-    # source_code_links_by_need = load_source_code_links_combined_json(
-    #     get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
-    # )
     for module_grouped_needs in scl_by_module:
         for source_code_links in module_grouped_needs.needs:
             need = find_need(needs_copy, source_code_links.need)
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index ce6839b80..33ef6af37 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -22,13 +22,13 @@
 
 from sphinx_needs.logging import get_logger
 
-LOGGER = get_logger(__name__)
-
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
     store_source_code_links_json,
 )
 
+LOGGER = get_logger(__name__)
+
 TAGS = [
     "# " + "req-traceability:",
     "# " + "req-Id:",
@@ -47,7 +47,9 @@ def _extract_references_from_line(line: str):
                 yield tag, req.strip()
 
 
-def _extract_references_from_file(root: Path, file_path_name: Path, file_path: Path) -> list[NeedLink]:
+def _extract_references_from_file(
+    root: Path, file_path_name: Path, file_path: Path
+) -> list[NeedLink]:
     """Scan a single file for template strings and return findings."""
     assert root.is_absolute(), "Root path must be absolute"
     assert not file_path_name.is_absolute(), "File path must be relative to the root"
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index 9197b75ff..887d4b667 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -48,7 +48,7 @@ def default(self, o: object):
         if isinstance(o, NeedLink):
             return o.to_dict_without_metadata()
         if isinstance(
-            o, (ModuleSourceLinks, SourceCodeLinks, DataForTestLink, NeedSourceLinks)
+            o, ModuleSourceLinks | SourceCodeLinks | DataForTestLink | NeedSourceLinks
         ):
             return asdict(o)
         return super().default(o)
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index 324e54114..8bc8f9439 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -16,7 +16,7 @@
 import os
 from dataclasses import asdict, dataclass
 from pathlib import Path
-from typing import Any, TypeGuard, TypedDict
+from typing import Any, TypedDict, TypeGuard
 
 
 class MetaData(TypedDict):

From 5a08e5da679545e32c31386010708498da6b3633 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 14:11:28 +0100
Subject: [PATCH 09/34] Basepyright linting

---
 .../score_source_code_linker/generate_source_code_links_json.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index 33ef6af37..7b39b7228 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -124,7 +124,7 @@ def find_all_need_references(search_path: Path) -> list[NeedLink]:
 
     # Use os.walk to have better control over directory traversal
     for file in iterate_files_recursively(search_path):
-        references = _extract_references_from_file(search_path, file)
+        references = _extract_references_from_file(search_path,Path(file.name), file)
         all_need_references.extend(references)
 
     elapsed_time = os.times().elapsed - start_time

From ce313871ed1e07d268fe88546ee01a37f07fb448 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Fri, 13 Mar 2026 16:51:28 +0100
Subject: [PATCH 10/34] WIP: Testlinks endlink still wrong

---
 scripts_bazel/BUILD                           |  1 +
 scripts_bazel/generate_sourcelinks_cli.py     | 23 +-------
 scripts_bazel/merge_sourcelinks.py            | 22 +++-----
 src/extensions/score_source_code_linker/BUILD |  1 +
 .../score_source_code_linker/__init__.py      |  2 +-
 .../score_source_code_linker/helpers.py}      | 36 ++++++++++++
 .../module_source_links.py                    | 42 ++++++++------
 .../score_source_code_linker/testlink.py      | 34 +++++++++++
 .../tests/test_codelink.py                    |  2 +-
 .../test_source_code_link_integration.py      |  3 +-
 .../score_source_code_linker/xml_parser.py    | 56 ++++++++++++++++---
 src/helper_lib/BUILD                          |  3 +-
 src/helper_lib/__init__.py                    |  2 +-
 13 files changed, 160 insertions(+), 67 deletions(-)
 rename src/{helper_lib/additional_functions.py => extensions/score_source_code_linker/helpers.py} (60%)

diff --git a/scripts_bazel/BUILD b/scripts_bazel/BUILD
index 81c9212f1..befe51730 100644
--- a/scripts_bazel/BUILD
+++ b/scripts_bazel/BUILD
@@ -33,6 +33,7 @@ py_binary(
 py_binary(
     name = "merge_sourcelinks",
     srcs = ["merge_sourcelinks.py"],
+    deps= [ "//src/extensions/score_source_code_linker"],
     main = "merge_sourcelinks.py",
     visibility = ["//visibility:public"],
 )
diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index ba54b5d23..e1feb8e0b 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -25,36 +25,17 @@
 from src.extensions.score_source_code_linker.generate_source_code_links_json import (
     _extract_references_from_file,  # pyright: ignore[reportPrivateUsage] TODO: move it out of the extension and into this script
 )
+from src.extensions.score_source_code_linker.helpers import parse_module_name_from_path
 from src.extensions.score_source_code_linker.needlinks import (
     MetaData,
     store_source_code_links_with_metadata_json,
 )
 
+
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
 
-def parse_module_name_from_path(path: Path) -> str:
-    """
-    Parse out the Module-Name from the filename gotten
-    /home/user/.cache/bazel/aksj37981712/external/score_docs_as_code+/src/tests/testfile.py
-    => score_docs_as_code
-    """
-
-    # COMBO BUILD
-    # If external is in the filepath that gets parsed =>
-    # file is in an external module => combo build
-    # Example Path:
-    #   PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
-
-    if str(path).startswith("external/"):
-        # This allows for files / folders etc. to have `external` in their name too.
-        module_raw = str(path).removeprefix("external/")
-        filepath_split = str(module_raw).split("/", maxsplit=1)
-        return str(filepath_split[0].removesuffix("+"))
-    return "local_module"
-
-
 def main():
     parser = argparse.ArgumentParser(
         description="Generate source code links JSON from source files"
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index 626b48c56..afb2cc198 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -21,9 +21,7 @@
 import sys
 from pathlib import Path
 
-# from src.extensions.score_source_code_linker.need_source_links import (
-#     store_source_code_links_combined_json,
-# )
+from src.extensions.score_source_code_linker.helpers import parse_info_from_known_good
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
@@ -38,17 +36,10 @@
 """
 
 
-def parse_info_from_known_good(
-    known_good_json: Path, module_name: str
-) -> tuple[str, str]:
-    with open(known_good_json) as f:
-        kg_json = json.load(f)
-    for category in kg_json["modules"].values():
-        if module_name in category:
-            m = category[module_name]
-            return (m["hash"], m["repo"].removesuffix(".git"))
-    raise KeyError(f"Module {module_name!r} not found in known_good_json.")
 
+def add_needid_to_metaneed_mapping(mapping: dict[str, dict[str, str]], metadata: dict[str, str], needid: str):
+    mapping
+    pass
 
 def main():
     parser = argparse.ArgumentParser(
@@ -76,6 +67,7 @@ def main():
     all_files = [x for x in args.files if "known_good.json" not in str(x)]
 
     merged = []
+    needs_metadata_mapping = {}
     for json_file in all_files:
         with open(json_file) as f:
             data = json.load(f)
@@ -89,11 +81,11 @@ def main():
             # In the case that 'metadata[module_name]' is 'local_module'
             # hash & url are already existing and empty inside of 'metadata'
             # Therefore all 3 keys will be written to needlinks in each branch
+
             for d in data[1:]:
                 d.update(metadata)
             assert isinstance(data, list), repr(data)
-            merged.extend(data[1:])
-
+            merged.extend(data[1:]) 
     with open(args.output, "w") as f:
         json.dump(merged, f, indent=2, ensure_ascii=False)
 
diff --git a/src/extensions/score_source_code_linker/BUILD b/src/extensions/score_source_code_linker/BUILD
index e3c289c66..55d471374 100644
--- a/src/extensions/score_source_code_linker/BUILD
+++ b/src/extensions/score_source_code_linker/BUILD
@@ -54,6 +54,7 @@ py_library(
         "needlinks.py",
         "testlink.py",
         "xml_parser.py",
+        "helpers.py",
     ],
     imports = ["."],
     visibility = ["//visibility:public"],
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index a84ddfb42..c687e2e3e 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -60,7 +60,7 @@
     find_git_root,
     find_ws_root,
 )
-from src.helper_lib.additional_functions import get_github_link
+from src.extensions.score_source_code_linker.helpers import get_github_link
 
 LOGGER = get_logger(__name__)
 # Uncomment this to enable more verbose logging
diff --git a/src/helper_lib/additional_functions.py b/src/extensions/score_source_code_linker/helpers.py
similarity index 60%
rename from src/helper_lib/additional_functions.py
rename to src/extensions/score_source_code_linker/helpers.py
index 21b4d6fd2..5544e2696 100644
--- a/src/helper_lib/additional_functions.py
+++ b/src/extensions/score_source_code_linker/helpers.py
@@ -10,6 +10,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 # *******************************************************************************
+import json
 from pathlib import Path
 
 from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
@@ -62,3 +63,38 @@ def get_github_link_from_json(
     base_url = metadata.url
     current_hash = metadata.hash
     return f"{base_url}/blob/{current_hash}/{link.file}#L{link.line}"
+
+
+def parse_module_name_from_path(path: Path) -> str:
+    """
+    Parse out the Module-Name from the filename gotten
+    /home/user/.cache/bazel/aksj37981712/external/score_docs_as_code+/src/tests/testfile.py
+    => score_docs_as_code
+    """
+
+    # COMBO BUILD
+    # If external is in the filepath that gets parsed =>
+    # file is in an external module => combo build
+    # Example Path:
+    #   PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
+
+    if str(path).startswith("external/"):
+        # This allows for files / folders etc. to have `external` in their name too.
+        module_raw = str(path).removeprefix("external/")
+        filepath_split = str(module_raw).split("/", maxsplit=1)
+        return str(filepath_split[0].removesuffix("+"))
+    # We return this when we are in a local build `//:docs` the rest of DaC knows
+    # What to do then if it encounters this module_name
+    return "local_module"
+
+
+def parse_info_from_known_good(
+    known_good_json: Path, module_name: str
+) -> tuple[str, str]:
+    with open(known_good_json) as f:
+        kg_json = json.load(f)
+    for category in kg_json["modules"].values():
+        if module_name in category:
+            m = category[module_name]
+            return (m["hash"], m["repo"].removesuffix(".git"))
+    raise KeyError(f"Module {module_name!r} not found in known_good_json.")
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index 887d4b667..97dc27a68 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -15,6 +15,7 @@
 import json
 from dataclasses import asdict, dataclass, field
 from pathlib import Path
+from re import M
 from typing import Any
 
 from src.extensions.score_source_code_linker.need_source_links import (
@@ -43,13 +44,12 @@ class ModuleSourceLinks_JSON_Encoder(json.JSONEncoder):
     def default(self, o: object):
         if isinstance(o, Path):
             return str(o)
-        # We do not want to save the metadata inside the codelink
+        # We do not want to save the metadata inside the codelink or testlink
+        # As we save this already in a structure above it
         # (hash, module_name, url)
-        if isinstance(o, NeedLink):
+        if isinstance(o, NeedLink | DataForTestLink):
             return o.to_dict_without_metadata()
-        if isinstance(
-            o, ModuleSourceLinks | SourceCodeLinks | DataForTestLink | NeedSourceLinks
-        ):
+        if isinstance(o, ModuleSourceLinks | SourceCodeLinks | NeedSourceLinks):
             return asdict(o)
         return super().default(o)
 
@@ -57,14 +57,14 @@ def default(self, o: object):
 def ModuleSourceLinks_JSON_Decoder(
     d: dict[str, Any],
 ) -> ModuleSourceLinks | dict[str, Any]:
-    if "module_name" in d and "needs" in d:
-        module_name = d["module_name"]
+    if "module" in d and "needs" in d:
+        module = d["module"]
         needs = d["needs"]
         return ModuleSourceLinks(
             module=ModuleInfo(
-                name=module_name.get("module_name"),
-                hash=module_name.get("hash"),
-                url=module_name.get("url"),
+                name=module.get("module_name"),
+                hash=module.get("hash"),
+                url=module.get("url"),
             ),
             # We know this can only be list[SourceCodeLinks] and nothing else
             # Therefore => we ignore the type error here
@@ -95,12 +95,16 @@ def load_module_source_links_json(file: Path) -> list[ModuleSourceLinks]:
         object_hook=ModuleSourceLinks_JSON_Decoder,
     )
     assert isinstance(links, list), (
-        "The combined source code linker links should be "
-        "a list of SourceCodeLinks objects."
+        "The ModuleSourceLink json should be aa list of ModuleSourceLink objects."
     )
+    print("=====================")
+    print("=== TESTING LINKS IN ModuleSourceLink === ")
+    for link in links:
+        if not isinstance(link, ModuleSourceLinks):
+            print(f"Link not module_sourcelink: {link}")
+    print("=====================")
     assert all(isinstance(link, ModuleSourceLinks) for link in links), (
-        "All items in combined_source_code_linker_cache should be "
-        "SourceCodeLinks objects."
+        "All items in module source link cache should be ModuleSourceLink objects."
     )
     return links
 
@@ -109,10 +113,14 @@ def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLink
     module_groups: dict[str, ModuleSourceLinks] = {}
 
     for source_link in links:
-        if not source_link.links.CodeLinks:
+        # Check if we can take moduleInfo from code or testlinks
+        if source_link.links.CodeLinks:
+            first_link = source_link.links.CodeLinks[0]
+        elif source_link.links.TestLinks:
+            first_link = source_link.links.TestLinks[0]
+        else:
+            # This should not happen?
             continue
-
-        first_link = source_link.links.CodeLinks[0]
         module_key = first_link.module_name
 
         if module_key not in module_groups:
diff --git a/src/extensions/score_source_code_linker/testlink.py b/src/extensions/score_source_code_linker/testlink.py
index ee83c7f95..f001cc203 100644
--- a/src/extensions/score_source_code_linker/testlink.py
+++ b/src/extensions/score_source_code_linker/testlink.py
@@ -30,6 +30,7 @@
 
 from sphinx_needs import logging
 
+
 LOGGER = logging.get_logger(__name__)
 
 
@@ -42,6 +43,19 @@ class DataForTestLink:
     verify_type: str
     result: str
     result_text: str = ""
+    module_name: str = ""
+    hash: str = ""
+    url: str = ""
+
+    def to_dict_full(self) -> dict[str, str | Path | int]:
+        return asdict(self)
+
+    def to_dict_without_metadata(self) -> dict[str, str | Path | int]:
+        d = asdict(self)
+        d.pop("module_name", None)
+        d.pop("hash", None)
+        d.pop("url", None)
+        return d
 
 
 class DataForTestLink_JSON_Encoder(json.JSONEncoder):
@@ -60,6 +74,9 @@ def DataForTestLink_JSON_Decoder(d: dict[str, Any]) -> DataForTestLink | dict[st
         "line",
         "need",
         "verify_type",
+        "module_name",
+        "hash",
+        "url",
         "result",
         "result_text",
     } <= d.keys():
@@ -68,6 +85,9 @@ def DataForTestLink_JSON_Decoder(d: dict[str, Any]) -> DataForTestLink | dict[st
             file=Path(d["file"]),
             line=d["line"],
             need=d["need"],
+            module_name=d.get("module_name", ""),
+            hash=d.get("hash", ""),
+            url=d.get("url", ""),
             verify_type=d["verify_type"],
             result=d["result"],
             result_text=d["result_text"],
@@ -83,6 +103,9 @@ class DataOfTestCase:
     file: str | None = None
     line: str | None = None
     result: str | None = None  # passed | falied | skipped | disabled
+    module_name: str | None = None
+    hash: str | None = None
+    url: str | None = None
     # Intentionally not snakecase to make dict parsing simple
     TestType: str | None = None
     DerivationTechnique: str | None = None
@@ -98,6 +121,9 @@ def from_dict(cls, data: dict[str, Any]):  # type-ignore
             file=data.get("file"),
             line=data.get("line"),
             result=data.get("result"),
+            module_name=data.get("module_name"),
+            hash=data.get("hash"),
+            url=data.get("url"),
             TestType=data.get("TestType"),
             DerivationTechnique=data.get("DerivationTechnique"),
             result_text=data.get("result_text"),
@@ -158,6 +184,8 @@ def is_valid(self) -> bool:
         #         and self.TestType is not None
         #         and self.DerivationTechnique is not None
         # ):
+        # Hash & URL are explictily allowed to be empty but not none.
+        # module_name has to be always filled or something went wrong
         fields = [
             x
             for x in self.__dataclass_fields__
@@ -199,6 +227,9 @@ def parse_attributes(verify_field: str | None, verify_type: str):
             assert self.file is not None
             assert self.line is not None
             assert self.result is not None
+            assert self.module_name is not None
+            assert self.hash is not None
+            assert self.url is not None
             assert self.result_text is not None
             assert self.TestType is not None
             assert self.DerivationTechnique is not None
@@ -212,6 +243,9 @@ def parse_attributes(verify_field: str | None, verify_type: str):
                     verify_type=verify_type,
                     result=self.result,
                     result_text=self.result_text,
+                    module_name=self.module_name,
+                    hash=self.hash,
+                    url=self.url,
                 )
 
         return list(
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 29ddc7235..9615c0058 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -43,7 +43,7 @@
 from src.helper_lib import (
     get_current_git_hash,
 )
-from src.helper_lib.additional_functions import get_github_link
+from src.extensions.score_source_code_linker.helpers import get_github_link
 
 """
 #          ────────────────ATTENTION───────────────
diff --git a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
index 60bb98f80..01bb7ff58 100644
--- a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
@@ -37,7 +37,8 @@
     SourceCodeLinks_TEST_JSON_Decoder,
 )
 from src.helper_lib import find_ws_root, get_github_base_url
-from src.helper_lib.additional_functions import get_github_link
+
+from src.extensions.score_source_code_linker.helpers import  get_github_link
 
 
 @pytest.fixture()
diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index 8432e1fc3..6facb983b 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -33,18 +33,41 @@
 from sphinx_needs import logging
 from sphinx_needs.api import add_external_need
 
+from src.extensions.score_source_code_linker.needlinks import (
+    MetaData,
+)
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataOfTestCase,
     store_data_of_test_case_json,
     store_test_xml_parsed_json,
 )
 from src.helper_lib import find_ws_root
-from src.helper_lib.additional_functions import get_github_link
+from src.extensions.score_source_code_linker.helpers import (
+    get_github_link,
+    parse_info_from_known_good,
+    parse_module_name_from_path,
+)
 
 logger = logging.get_logger(__name__)
 logger.setLevel("DEBUG")
 
 
+def get_metadata_from_test_path(filepath: Path) -> MetaData:
+    known_good_json = os.environ.get("KNOWN_GOOD_JSON")
+    module_name = parse_module_name_from_path(filepath)
+    md: MetaData = {
+        "module_name": module_name,
+        "hash": "",
+        "url": "",
+    }
+    if module_name != "local_module" and known_good_json:
+        md["hash"], md["url"] = parse_info_from_known_good(
+            Path(known_good_json), module_name
+        )
+    return md
+
+
 def parse_testcase_result(testcase: ET.Element) -> tuple[str, str]:
     """
     Returns 'result' and 'result_text' found in the 'message'
@@ -101,7 +124,7 @@ def read_test_xml_file(file: Path) -> tuple[list[DataOfTestCase], list[str], lis
     missing_prop_tests: list[str] = []
     tree = ET.parse(file)
     root = tree.getroot()
-
+    md = get_metadata_from_test_path(file)
     for testsuite in root.findall("testsuite"):
         for testcase in testsuite.findall("testcase"):
             case_properties = {}
@@ -161,6 +184,7 @@ def read_test_xml_file(file: Path) -> tuple[list[DataOfTestCase], list[str], lis
             # If the is_valid method would return 'False' anyway.
             # I just can't think of it right now, leaving this for future me
             case_properties = parse_properties(case_properties, properties_element)
+            case_properties.update(md)
             test_case = DataOfTestCase.from_dict(case_properties)
             if not test_case.is_valid():
                 missing_prop_tests.append(testname)
@@ -169,6 +193,7 @@ def read_test_xml_file(file: Path) -> tuple[list[DataOfTestCase], list[str], lis
     return test_case_needs, non_prop_tests, missing_prop_tests
 
 
+# /home/maximilianp/score_personal/reference_integration/bazel-testlogs/external/score_docs_as_code+/src/helper_lib/helper_lib_tests/test.xml
 def find_xml_files(dir: Path) -> list[Path]:
     """
     Recursively search all test.xml files inside 'bazel-testlogs'
@@ -183,18 +208,21 @@ def find_xml_files(dir: Path) -> list[Path]:
     for root, _, files in os.walk(dir):
         if test_file_name in files:
             xml_paths.append(Path(os.path.join(root, test_file_name)))
+    print("=========================================")
+    print(xml_paths[0])
+    print("=========================================")
     return xml_paths
 
 
-def find_test_folder(base_path: Path | None = None) -> Path | None:
+def find_test_folder(base_path: Path | None = None) -> tuple[Path | None, Path | None]:
     ws_root = base_path if base_path is not None else find_ws_root()
     assert ws_root is not None
     if os.path.isdir(ws_root / "tests-report"):
-        return ws_root / "tests-report"
+        return ws_root, ws_root / "tests-report"
     if os.path.isdir(ws_root / "bazel-testlogs"):
-        return ws_root / "bazel-testlogs"
+        return ws_root, ws_root / "bazel-testlogs"
     logger.info("could not find tests-report or bazel-testlogs to parse testcases")
-    return None
+    return ws_root, None
 
 
 def run_xml_parser(app: Sphinx, env: BuildEnvironment):
@@ -203,11 +231,19 @@ def run_xml_parser(app: Sphinx, env: BuildEnvironment):
     building testcase needs.
     It gets called from the source_code_linker __init__
     """
-    testlogs_dir = find_test_folder()
+    root_path, testlogs_dir = find_test_folder()
     # early return
     if testlogs_dir is None:
         return
     xml_file_paths = find_xml_files(testlogs_dir)
+    # scl_with_metadata = load_source_code_links_with_metadata_json(
+    #     app.outdir / "score_source_links_metadata.json"
+    # )[0]
+    # metadata: MetaData = {
+    #     "module_name": scl_with_metadata.module_name,
+    #     "hash": scl_with_metadata.hash,
+    #     "url": scl_with_metadata.url,
+    # }
     test_case_needs = build_test_needs_from_files(app, env, xml_file_paths)
     # Saving the test case needs for cache
     store_data_of_test_case_json(
@@ -262,6 +298,10 @@ def construct_and_add_need(app: Sphinx, tn: DataOfTestCase):
     # and either 'Fully' or 'PartiallyVerifies' should not be None here
     assert tn.file is not None
     assert tn.name is not None
+    assert tn.module_name is not None
+    assert tn.hash is not None
+    assert tn.url is not None
+    metadata = ModuleInfo(name=tn.module_name, hash=tn.hash, url=tn.url)
     # IDK if this is ideal or not
     with contextlib.suppress(BaseException):
         _ = add_external_need(
@@ -271,7 +311,7 @@ def construct_and_add_need(app: Sphinx, tn: DataOfTestCase):
             tags="TEST",
             id=f"testcase__{tn.name}_{short_hash(tn.file + tn.name).upper()}",
             name=tn.name,
-            external_url=get_github_link(tn),
+            external_url=get_github_link(metadata, tn),
             fully_verifies=tn.FullyVerifies if tn.FullyVerifies is not None else "",
             partially_verifies=tn.PartiallyVerifies
             if tn.PartiallyVerifies is not None
diff --git a/src/helper_lib/BUILD b/src/helper_lib/BUILD
index 748a2a730..ad6316363 100644
--- a/src/helper_lib/BUILD
+++ b/src/helper_lib/BUILD
@@ -27,8 +27,7 @@ py_library(
     visibility = ["//visibility:public"],
     deps = [
         "@rules_python//python/runfiles",
-        "@score_docs_as_code//src/extensions/score_source_code_linker:source_code_linker_helpers",
-    ],
+    ] + all_requirements,
 )
 
 score_py_pytest(
diff --git a/src/helper_lib/__init__.py b/src/helper_lib/__init__.py
index 5699e478d..a72fffb0b 100644
--- a/src/helper_lib/__init__.py
+++ b/src/helper_lib/__init__.py
@@ -17,7 +17,7 @@
 from pathlib import Path
 from typing import Any
 
-from runfiles import Runfiles
+from python.runfiles import Runfiles
 from sphinx.config import Config
 from sphinx_needs.logging import get_logger
 

From c573b2f9f2d5130807b23da1a8ab65f63ec4b045 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Fri, 13 Mar 2026 16:52:42 +0100
Subject: [PATCH 11/34] Formatting

---
 scripts_bazel/generate_sourcelinks_cli.py            |  1 -
 scripts_bazel/merge_sourcelinks.py                   |  2 +-
 src/extensions/score_source_code_linker/__init__.py  |  2 +-
 .../score_source_code_linker/module_source_links.py  |  1 -
 src/extensions/score_source_code_linker/testlink.py  |  1 -
 .../score_source_code_linker/tests/test_codelink.py  |  2 +-
 .../tests/test_source_code_link_integration.py       |  3 +--
 .../score_source_code_linker/xml_parser.py           | 12 ++++++------
 8 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index e1feb8e0b..6f09ef075 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -31,7 +31,6 @@
     store_source_code_links_with_metadata_json,
 )
 
-
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index afb2cc198..932d91380 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -85,7 +85,7 @@ def main():
             for d in data[1:]:
                 d.update(metadata)
             assert isinstance(data, list), repr(data)
-            merged.extend(data[1:]) 
+            merged.extend(data[1:])
     with open(args.output, "w") as f:
         json.dump(merged, f, indent=2, ensure_ascii=False)
 
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index c687e2e3e..d80754036 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -34,6 +34,7 @@
 from src.extensions.score_source_code_linker.generate_source_code_links_json import (
     generate_source_code_links_json,
 )
+from src.extensions.score_source_code_linker.helpers import get_github_link
 from src.extensions.score_source_code_linker.module_source_links import (
     group_needs_by_module,
     load_module_source_links_json,
@@ -60,7 +61,6 @@
     find_git_root,
     find_ws_root,
 )
-from src.extensions.score_source_code_linker.helpers import get_github_link
 
 LOGGER = get_logger(__name__)
 # Uncomment this to enable more verbose logging
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index 97dc27a68..b77450eb8 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -15,7 +15,6 @@
 import json
 from dataclasses import asdict, dataclass, field
 from pathlib import Path
-from re import M
 from typing import Any
 
 from src.extensions.score_source_code_linker.need_source_links import (
diff --git a/src/extensions/score_source_code_linker/testlink.py b/src/extensions/score_source_code_linker/testlink.py
index f001cc203..bd7139271 100644
--- a/src/extensions/score_source_code_linker/testlink.py
+++ b/src/extensions/score_source_code_linker/testlink.py
@@ -30,7 +30,6 @@
 
 from sphinx_needs import logging
 
-
 LOGGER = logging.get_logger(__name__)
 
 
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 9615c0058..9d3fa78f5 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -35,6 +35,7 @@
     get_cache_filename,
     group_by_need,
 )
+from src.extensions.score_source_code_linker.helpers import get_github_link
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
     load_source_code_links_json,
@@ -43,7 +44,6 @@
 from src.helper_lib import (
     get_current_git_hash,
 )
-from src.extensions.score_source_code_linker.helpers import get_github_link
 
 """
 #          ────────────────ATTENTION───────────────
diff --git a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
index 01bb7ff58..b4e65279d 100644
--- a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
@@ -25,6 +25,7 @@
 from sphinx.testing.util import SphinxTestApp
 from sphinx_needs.data import SphinxNeedsData
 
+from src.extensions.score_source_code_linker.helpers import get_github_link
 from src.extensions.score_source_code_linker.needlinks import NeedLink
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
@@ -38,8 +39,6 @@
 )
 from src.helper_lib import find_ws_root, get_github_base_url
 
-from src.extensions.score_source_code_linker.helpers import  get_github_link
-
 
 @pytest.fixture()
 def sphinx_base_dir(tmp_path_factory: TempPathFactory) -> Path:
diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index 6facb983b..123ebd5d8 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -33,21 +33,21 @@
 from sphinx_needs import logging
 from sphinx_needs.api import add_external_need
 
+from src.extensions.score_source_code_linker.helpers import (
+    get_github_link,
+    parse_info_from_known_good,
+    parse_module_name_from_path,
+)
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
 from src.extensions.score_source_code_linker.needlinks import (
     MetaData,
 )
-from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataOfTestCase,
     store_data_of_test_case_json,
     store_test_xml_parsed_json,
 )
 from src.helper_lib import find_ws_root
-from src.extensions.score_source_code_linker.helpers import (
-    get_github_link,
-    parse_info_from_known_good,
-    parse_module_name_from_path,
-)
 
 logger = logging.get_logger(__name__)
 logger.setLevel("DEBUG")

From 9d87c2ccaffeb36433c4829702c5c3c04dc2a0c7 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Mon, 16 Mar 2026 11:00:31 +0100
Subject: [PATCH 12/34] Formating & Linting & Comments

---
 scripts_bazel/generate_sourcelinks_cli.py     | 19 +++++++-
 scripts_bazel/merge_sourcelinks.py            |  8 ----
 .../generate_source_code_links_json.py        |  8 +++-
 .../score_source_code_linker/xml_parser.py    | 47 ++++++++++++-------
 4 files changed, 54 insertions(+), 28 deletions(-)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 6f09ef075..89898d0ee 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -35,6 +35,22 @@
 logger = logging.getLogger(__name__)
 
 
+def clean_external_prefix(path: Path) -> Path:
+    """
+    As it can be in combo builds that the path is:
+    `external/score_docs_as_code+/....` or similar
+    We have to remove this prefix from the file
+    before we pass it to the extract function. Otherwise we have
+    this prefix inside the `file` attribute leading to wrong links
+    """
+    if not str(path).startswith("external/"):
+        return path
+    # This allows for files / folders etc. to have `external` in their name too.
+    path_raw = str(path).removeprefix("external/")
+    filepath_split = str(path_raw).split("/", maxsplit=1)
+    return Path("".join(filepath_split[1:]))
+
+
 def main():
     parser = argparse.ArgumentParser(
         description="Generate source code links JSON from source files"
@@ -67,8 +83,9 @@ def main():
             metadata_set = True
         abs_file_path = file_path.resolve()
         assert abs_file_path.exists(), abs_file_path
+        clean_path = clean_external_prefix(file_path)
         references = _extract_references_from_file(
-            abs_file_path.parent, Path(abs_file_path.name), file_path
+            abs_file_path.parent, Path(abs_file_path.name), clean_path
         )
         all_need_references.extend(references)
     store_source_code_links_with_metadata_json(
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index 932d91380..9325afc24 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -27,7 +27,6 @@
 logger = logging.getLogger(__name__)
 
 
-
 """
 if bazel-out/k8-fastbuild/bin/external/ in file_path => module is external
 otherwise it's local
@@ -35,12 +34,6 @@
 if external => parse thing for module_name => look up known_good json for hash & url
 """
 
-
-
-def add_needid_to_metaneed_mapping(mapping: dict[str, dict[str, str]], metadata: dict[str, str], needid: str):
-    mapping
-    pass
-
 def main():
     parser = argparse.ArgumentParser(
         description="Merge multiple sourcelinks JSON files into one"
@@ -67,7 +60,6 @@ def main():
     all_files = [x for x in args.files if "known_good.json" not in str(x)]
 
     merged = []
-    needs_metadata_mapping = {}
     for json_file in all_files:
         with open(json_file) as f:
             data = json.load(f)
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index 7b39b7228..8e9e2d807 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -50,7 +50,13 @@ def _extract_references_from_line(line: str):
 def _extract_references_from_file(
     root: Path, file_path_name: Path, file_path: Path
 ) -> list[NeedLink]:
-    """Scan a single file for template strings and return findings."""
+    """Scan a single file for template strings and return findings.
+    Examples:
+    # ROOT: <local_root>/docs-as-code/src/extensions/score_source_code_linker
+    #FILE PATH:
+        external/score_docs_as_code+/src/extensions/score_source_code_linker/testlink.py
+    #FILE PATH NAME:  testlink.py
+    """
     assert root.is_absolute(), "Root path must be absolute"
     assert not file_path_name.is_absolute(), "File path must be relative to the root"
     # assert file_path.is_relative_to(root), (
diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index 123ebd5d8..7347429ce 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -54,6 +54,23 @@
 
 
 def get_metadata_from_test_path(filepath: Path) -> MetaData:
+    """
+    Will parse out the metadata from the testpath.
+    If test is local then the metadata will be:
+
+        "module_name": "local_module",
+        "hash": "",
+        "url": "",
+
+    Else it will parse the module_name e.g. `score_docs_as_code`
+    match this in the known_good_json and grab the accompanying
+    hash, url as well and return metadata like so for example:
+
+          "module_name": "score_docs_as_code",
+          "hash": "c1207676afe6cafd25c35d420e73279a799515d8",
+          "url": "https://github.com/eclipse-score/docs-as-code"
+
+    """
     known_good_json = os.environ.get("KNOWN_GOOD_JSON")
     module_name = parse_module_name_from_path(filepath)
     md: MetaData = {
@@ -193,13 +210,17 @@ def read_test_xml_file(file: Path) -> tuple[list[DataOfTestCase], list[str], lis
     return test_case_needs, non_prop_tests, missing_prop_tests
 
 
-# /home/maximilianp/score_personal/reference_integration/bazel-testlogs/external/score_docs_as_code+/src/helper_lib/helper_lib_tests/test.xml
 def find_xml_files(dir: Path) -> list[Path]:
     """
     Recursively search all test.xml files inside 'bazel-testlogs'
 
     Returns:
         - list[Path] => Paths to all found 'test.xml' files.
+
+    Example combo TestPath for future reference:
+
+    '<local path to folder>/reference_integration/bazel-testlogs
+    /feature_integration_tests/test_cases/fit/test.xml'
     """
 
     test_file_name = "test.xml"
@@ -208,21 +229,19 @@ def find_xml_files(dir: Path) -> list[Path]:
     for root, _, files in os.walk(dir):
         if test_file_name in files:
             xml_paths.append(Path(os.path.join(root, test_file_name)))
-    print("=========================================")
-    print(xml_paths[0])
-    print("=========================================")
+
     return xml_paths
 
 
-def find_test_folder(base_path: Path | None = None) -> tuple[Path | None, Path | None]:
+def find_test_folder(base_path: Path | None = None) -> Path | None:
     ws_root = base_path if base_path is not None else find_ws_root()
     assert ws_root is not None
     if os.path.isdir(ws_root / "tests-report"):
-        return ws_root, ws_root / "tests-report"
+        return ws_root / "tests-report"
     if os.path.isdir(ws_root / "bazel-testlogs"):
-        return ws_root, ws_root / "bazel-testlogs"
+        return ws_root / "bazel-testlogs"
     logger.info("could not find tests-report or bazel-testlogs to parse testcases")
-    return ws_root, None
+    return None
 
 
 def run_xml_parser(app: Sphinx, env: BuildEnvironment):
@@ -231,19 +250,10 @@ def run_xml_parser(app: Sphinx, env: BuildEnvironment):
     building testcase needs.
     It gets called from the source_code_linker __init__
     """
-    root_path, testlogs_dir = find_test_folder()
-    # early return
+    testlogs_dir = find_test_folder()
     if testlogs_dir is None:
         return
     xml_file_paths = find_xml_files(testlogs_dir)
-    # scl_with_metadata = load_source_code_links_with_metadata_json(
-    #     app.outdir / "score_source_links_metadata.json"
-    # )[0]
-    # metadata: MetaData = {
-    #     "module_name": scl_with_metadata.module_name,
-    #     "hash": scl_with_metadata.hash,
-    #     "url": scl_with_metadata.url,
-    # }
     test_case_needs = build_test_needs_from_files(app, env, xml_file_paths)
     # Saving the test case needs for cache
     store_data_of_test_case_json(
@@ -301,6 +311,7 @@ def construct_and_add_need(app: Sphinx, tn: DataOfTestCase):
     assert tn.module_name is not None
     assert tn.hash is not None
     assert tn.url is not None
+    # Have to build metadata here for the gh link func
     metadata = ModuleInfo(name=tn.module_name, hash=tn.hash, url=tn.url)
     # IDK if this is ideal or not
     with contextlib.suppress(BaseException):

From f50ef0c0f57d2ea51fb790e3d543509351c380d6 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Mon, 16 Mar 2026 13:43:04 +0100
Subject: [PATCH 13/34] Fixing copilot & other findings

---
 docs.bzl                                      | 73 ++++++++-----------
 scripts_bazel/merge_sourcelinks.py            | 12 +++
 src/extensions/score_source_code_linker/BUILD |  1 +
 .../score_source_code_linker/helpers.py       | 18 ++---
 .../module_source_links.py                    |  2 +-
 .../need_source_links.py                      |  3 -
 src/incremental.py                            |  2 +
 7 files changed, 57 insertions(+), 54 deletions(-)

diff --git a/docs.bzl b/docs.bzl
index fe26590e8..9eca87261 100644
--- a/docs.bzl
+++ b/docs.bzl
@@ -183,33 +183,43 @@ def docs(source_dir = "docs", data = [], deps = [], scan_code = [], known_good =
     data_with_docs_sources = _rewrite_needs_json_to_docs_sources(data)
     additional_combo_sourcelinks = _rewrite_needs_json_to_sourcelinks(data)
     _merge_sourcelinks(name = "merged_sourcelinks", sourcelinks = [":sourcelinks_json"] + additional_combo_sourcelinks, known_good = known_good)
+    docs_data = data + [":sourcelinks_json"]
+    combo_data = data_with_docs_sources + [":merged_sourcelinks"]
+
+    docs_env = {
+        "SOURCE_DIRECTORY": source_dir,
+        "DATA": str(data),
+        "ACTION": "incremental",
+        "SCORE_SOURCELINKS": "$(location :sourcelinks_json)",
+    }
+    docs_sources_env = {
+        "SOURCE_DIRECTORY": source_dir,
+        "DATA": str(data_with_docs_sources),
+        "ACTION": "incremental",
+        "SCORE_SOURCELINKS": "$(location :merged_sourcelinks)",
+    }
+    if known_good:
+        docs_env["KNOWN_GOOD_JSON"] = "$(location "+ known_good + ")"
+        docs_sources_env["KNOWN_GOOD_JSON"] = "$(location "+ known_good + ")"
+        docs_data.append(known_good)
+        combo_data.append(known_good)
 
     py_binary(
         name = "docs",
         tags = ["cli_help=Build documentation:\nbazel run //:docs"],
         srcs = ["@score_docs_as_code//src:incremental.py"],
-        data = data + [":sourcelinks_json"],
+        data = docs_data,
         deps = deps,
-        env = {
-            "SOURCE_DIRECTORY": source_dir,
-            "DATA": str(data),
-            "ACTION": "incremental",
-            "SCORE_SOURCELINKS": "$(location :sourcelinks_json)",
-        },
+        env = docs_env,
     )
 
     py_binary(
         name = "docs_combo",
         tags = ["cli_help=Build full documentation with all dependencies:\nbazel run //:docs_combo"],
         srcs = ["@score_docs_as_code//src:incremental.py"],
-        data = data_with_docs_sources + [":merged_sourcelinks"],
+        data = combo_data,
         deps = deps,
-        env = {
-            "SOURCE_DIRECTORY": source_dir,
-            "DATA": str(data_with_docs_sources),
-            "ACTION": "incremental",
-            "SCORE_SOURCELINKS": "$(location :merged_sourcelinks)",
-        },
+        env = docs_sources_env
     )
 
     native.alias(
@@ -222,55 +232,36 @@ def docs(source_dir = "docs", data = [], deps = [], scan_code = [], known_good =
         name = "docs_link_check",
         tags = ["cli_help=Verify Links inside Documentation:\nbazel run //:link_check\n (Note: this could take a long time)"],
         srcs = ["@score_docs_as_code//src:incremental.py"],
-        data = data,
+        data = docs_data,
         deps = deps,
-        env = {
-            "SOURCE_DIRECTORY": source_dir,
-            "DATA": str(data),
-            "ACTION": "linkcheck",
-        },
+        env = docs_env
     )
 
     py_binary(
         name = "docs_check",
         tags = ["cli_help=Verify documentation:\nbazel run //:docs_check"],
         srcs = ["@score_docs_as_code//src:incremental.py"],
-        data = data + [":sourcelinks_json"],
+        data = docs_data,
         deps = deps,
-        env = {
-            "SOURCE_DIRECTORY": source_dir,
-            "DATA": str(data),
-            "ACTION": "check",
-            "SCORE_SOURCELINKS": "$(location :sourcelinks_json)",
-        },
+        env = docs_env,
     )
 
     py_binary(
         name = "live_preview",
         tags = ["cli_help=Live preview documentation in the browser:\nbazel run //:live_preview"],
         srcs = ["@score_docs_as_code//src:incremental.py"],
-        data = data + [":sourcelinks_json"],
+        data = docs_data,
         deps = deps,
-        env = {
-            "SOURCE_DIRECTORY": source_dir,
-            "DATA": str(data),
-            "ACTION": "live_preview",
-            "SCORE_SOURCELINKS": "$(location :sourcelinks_json)",
-        },
+        env = docs_env,
     )
 
     py_binary(
         name = "live_preview_combo_experimental",
         tags = ["cli_help=Live preview full documentation with all dependencies in the browser:\nbazel run //:live_preview_combo_experimental"],
         srcs = ["@score_docs_as_code//src:incremental.py"],
-        data = data_with_docs_sources + [":merged_sourcelinks"],
+        data = combo_data,
         deps = deps,
-        env = {
-            "SOURCE_DIRECTORY": source_dir,
-            "DATA": str(data_with_docs_sources),
-            "ACTION": "live_preview",
-            "SCORE_SOURCELINKS": "$(location :merged_sourcelinks)",
-        },
+        env = docs_sources_env
     )
 
     score_virtualenv(
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index 9325afc24..a6cc03e29 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -34,6 +34,7 @@
 if external => parse thing for module_name => look up known_good json for hash & url
 """
 
+
 def main():
     parser = argparse.ArgumentParser(
         description="Merge multiple sourcelinks JSON files into one"
@@ -63,7 +64,18 @@ def main():
     for json_file in all_files:
         with open(json_file) as f:
             data = json.load(f)
+            # If the file is empty e.g. '[]' there is nothing to parse, we continue
+            if not data:
+                continue
             metadata = data[0]
+            if not isinstance(metadata, dict) or "module_name" not in metadata:
+                logger.warning(
+                    f"Unexpected schema in sourcelinks file '{json_file}': "
+                    "expected first element to be a metadata dict "
+                    "with a 'module_name' key. "
+                )
+                # As we can't deal with bad JSON structure we just skip it
+                continue
             if metadata["module_name"] and metadata["module_name"] != "local_module":
                 hash, repo = parse_info_from_known_good(
                     known_good_json=args.known_good, module_name=metadata["module_name"]
diff --git a/src/extensions/score_source_code_linker/BUILD b/src/extensions/score_source_code_linker/BUILD
index 55d471374..85b8f222b 100644
--- a/src/extensions/score_source_code_linker/BUILD
+++ b/src/extensions/score_source_code_linker/BUILD
@@ -55,6 +55,7 @@ py_library(
         "testlink.py",
         "xml_parser.py",
         "helpers.py",
+        "module_source_links.py",
     ],
     imports = ["."],
     visibility = ["//visibility:public"],
diff --git a/src/extensions/score_source_code_linker/helpers.py b/src/extensions/score_source_code_linker/helpers.py
index 5544e2696..ad471f757 100644
--- a/src/extensions/score_source_code_linker/helpers.py
+++ b/src/extensions/score_source_code_linker/helpers.py
@@ -57,7 +57,7 @@ def get_github_link_from_git(
 def get_github_link_from_json(
     metadata: ModuleInfo,
     link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
-):
+) -> str:
     if link is None:
         link = DefaultNeedLink()
     base_url = metadata.url
@@ -67,16 +67,17 @@ def get_github_link_from_json(
 
 def parse_module_name_from_path(path: Path) -> str:
     """
-    Parse out the Module-Name from the filename gotten
-    /home/user/.cache/bazel/aksj37981712/external/score_docs_as_code+/src/tests/testfile.py
-    => score_docs_as_code
+    Parse out the Module-Name from the filename:
+    Combo Example:
+        Path: external/score_docs_as_code+/src/helper_lib/test_helper_lib.py
+        => score_docs_as_code
+    Local:
+        Path: src/helper_lib/test_helper_lib.py
+        => local_module
+
     """
 
     # COMBO BUILD
-    # If external is in the filepath that gets parsed =>
-    # file is in an external module => combo build
-    # Example Path:
-    #   PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
 
     if str(path).startswith("external/"):
         # This allows for files / folders etc. to have `external` in their name too.
@@ -84,7 +85,6 @@ def parse_module_name_from_path(path: Path) -> str:
         filepath_split = str(module_raw).split("/", maxsplit=1)
         return str(filepath_split[0].removesuffix("+"))
     # We return this when we are in a local build `//:docs` the rest of DaC knows
-    # What to do then if it encounters this module_name
     return "local_module"
 
 
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index b77450eb8..bf299a49f 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -78,7 +78,7 @@ def store_module_source_links_json(
     # After `rm -rf _build` or on clean builds the directory does not exist, so we need
     # to create it
     file.parent.mkdir(exist_ok=True)
-    with open(file, "w") as f:
+    with open(file, "w", encoding="utf-8") as f:
         json.dump(
             source_code_links,
             f,
diff --git a/src/extensions/score_source_code_linker/need_source_links.py b/src/extensions/score_source_code_linker/need_source_links.py
index 1823ba4b4..1582c2fe8 100644
--- a/src/extensions/score_source_code_linker/need_source_links.py
+++ b/src/extensions/score_source_code_linker/need_source_links.py
@@ -123,9 +123,6 @@ def group_by_need(
 
       {
         "need": "<need_id>",
-        "module_name": <module_name>,
-        "hash": <git hash>,
-        "url": <github base url>,
         "links": {
           "CodeLinks": [NeedLink, NeedLink, ...],
           "TestLinks": [testlink, testlink, ...]
diff --git a/src/incremental.py b/src/incremental.py
index 1c3816229..fa1c5abc2 100644
--- a/src/incremental.py
+++ b/src/incremental.py
@@ -90,6 +90,8 @@ def get_env(name: str) -> str:
         base_arguments.append(f"-A=github_repo={args.github_repo}")
         base_arguments.append("-A=github_version=main")
         base_arguments.append(f"-A=doc_path={get_env('SOURCE_DIRECTORY')}")
+    if os.getenv("KNOWN_GOOD_JSON"):
+        base_arguments.append(f"--define=KNOWN_GOOD_JSON={get_env('KNOWN_GOOD_JSON')}")
 
     action = get_env("ACTION")
     if action == "live_preview":

From 976c2eccf60e1cdd6732babdb36c1347eb24b93e Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Mon, 16 Mar 2026 20:03:01 +0100
Subject: [PATCH 14/34] WIP: Tests debuging

---
 pyproject.toml                                |  2 +
 .../generate_source_code_links_json.py        |  6 +++
 .../tests/expected_codelink.json              | 20 +++++++--
 .../tests/expected_grouped.json               | 45 +++++++++++++++----
 .../tests/expected_testlink.json              | 25 ++++++++---
 .../tests/test_codelink.py                    | 20 ++++++---
 .../test_source_code_link_integration.py      |  2 +-
 .../tests/test_testlink.py                    | 22 ++++++++-
 .../tests/test_xml_parser.py                  | 18 +++++++-
 9 files changed, 133 insertions(+), 27 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 6aa48c6f3..b9efbffb8 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -23,6 +23,7 @@ extend-exclude = [
     ".venv*/**",
 ]
 [tool.pytest.ini_options]
+addopts = ["-v", "-s"]
 log_cli = true
 log_cli_level = "Debug"
 log_cli_format = "[%(asctime)s.%(msecs)03d] [%(levelname)-3s] [%(name)s] %(message)s"
@@ -66,3 +67,4 @@ filterwarnings = [
 pythonpath = [
     "src/extensions/",
 ]
+basetemp = "./debug_tmp"
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index 8e9e2d807..44c1c8bed 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -57,6 +57,9 @@ def _extract_references_from_file(
         external/score_docs_as_code+/src/extensions/score_source_code_linker/testlink.py
     #FILE PATH NAME:  testlink.py
     """
+    print("ROOT: ", root)
+    print("FILE_PATH: ", file_path)
+    print("FILE_PATH_NAME: ", file_path_name)
     assert root.is_absolute(), "Root path must be absolute"
     assert not file_path_name.is_absolute(), "File path must be relative to the root"
     # assert file_path.is_relative_to(root), (
@@ -130,6 +133,9 @@ def find_all_need_references(search_path: Path) -> list[NeedLink]:
 
     # Use os.walk to have better control over directory traversal
     for file in iterate_files_recursively(search_path):
+        print("Search_path: ", search_path)
+        print("File.name: ", file.name)
+        print("File: ", file)
         references = _extract_references_from_file(search_path,Path(file.name), file)
         all_need_references.extend(references)
 
diff --git a/src/extensions/score_source_code_linker/tests/expected_codelink.json b/src/extensions/score_source_code_linker/tests/expected_codelink.json
index 447ef8a69..4ff1f14bb 100644
--- a/src/extensions/score_source_code_linker/tests/expected_codelink.json
+++ b/src/extensions/score_source_code_linker/tests/expected_codelink.json
@@ -4,27 +4,39 @@
         "line": 3,
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_1",
-        "full_line": "#-----req-Id: TREQ_ID_1"
+        "full_line": "#-----req-Id: TREQ_ID_1",
+        "module_name": "local_module",
+        "hash": "",
+        "url": ""
     },
     {
         "file": "src/implementation2.py",
         "line": 5,
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_1",
-        "full_line": "#-----req-Id: TREQ_ID_1"
+        "full_line": "#-----req-Id: TREQ_ID_1",
+        "module_name": "local_module",
+        "hash": "",
+        "url": ""
     },
     {
         "file": "src/implementation1.py",
         "line": 9,
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_2",
-        "full_line":"#-----req-Id: TREQ_ID_2"
+        "full_line":"#-----req-Id: TREQ_ID_2",
+        "module_name": "local_module",
+        "hash": "",
+        "url": ""
     },
     {
         "file": "src/bad_implementation.py",
         "line":2,
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_200",
-        "full_line":"#-----req-Id: TREQ_ID_200"
+        "full_line":"#-----req-Id: TREQ_ID_200",
+        "module_name": "local_module",
+        "hash": "",
+        "url": ""
     }
 ]
diff --git a/src/extensions/score_source_code_linker/tests/expected_grouped.json b/src/extensions/score_source_code_linker/tests/expected_grouped.json
index 256232661..bd6df7e40 100644
--- a/src/extensions/score_source_code_linker/tests/expected_grouped.json
+++ b/src/extensions/score_source_code_linker/tests/expected_grouped.json
@@ -8,14 +8,20 @@
         "line": 3,
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_1",
-        "full_line": "#-----req-Id: TREQ_ID_1"
+        "full_line": "#-----req-Id: TREQ_ID_1",
+        "module_name": "local_module",
+        "hash": "",
+        "url": ""
     },
     {
         "file": "src/implementation2.py",
         "line": 5,
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_1",
-        "full_line": "#-----req-Id: TREQ_ID_1"
+        "full_line": "#-----req-Id: TREQ_ID_1",
+        "module_name": "local_module",
+        "hash": "",
+        "url": ""
     }
 
             ],
@@ -27,7 +33,10 @@
     "need": "TREQ_ID_1",
     "verify_type": "fully",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   }
             ]
     }
@@ -41,7 +50,10 @@
         "line": 9,
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_2",
-        "full_line":"#-----req-Id: TREQ_ID_2"
+        "full_line":"#-----req-Id: TREQ_ID_2",
+        "module_name": "local_module",
+        "hash": "",
+        "url": ""
     }
             ],
       "TestLinks": [
@@ -53,7 +65,10 @@
     "need": "TREQ_ID_2",
     "verify_type": "partially",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   },
   {
     "name": "test_error_handling",
@@ -62,7 +77,10 @@
     "need": "TREQ_ID_2",
     "verify_type": "partially",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   }
 
             ]
@@ -80,7 +98,10 @@
     "need": "TREQ_ID_3",
     "verify_type": "partially",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   },
   {
     "name": "test_error_handling",
@@ -89,7 +110,10 @@
     "need": "TREQ_ID_3",
     "verify_type": "partially",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   }
             ]
     }
@@ -103,7 +127,10 @@
             "line":2,
             "tag":"#-----req-Id:",
             "need": "TREQ_ID_200",
-            "full_line":"#-----req-Id: TREQ_ID_200"
+            "full_line":"#-----req-Id: TREQ_ID_200",
+            "module_name": "local_module",
+            "hash": "",
+            "url": ""
         }
 
             ],
diff --git a/src/extensions/score_source_code_linker/tests/expected_testlink.json b/src/extensions/score_source_code_linker/tests/expected_testlink.json
index 19068a4d5..145c31c31 100644
--- a/src/extensions/score_source_code_linker/tests/expected_testlink.json
+++ b/src/extensions/score_source_code_linker/tests/expected_testlink.json
@@ -6,7 +6,10 @@
     "need": "TREQ_ID_2",
     "verify_type": "partially",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   },
   {
     "name": "test_api_response_format",
@@ -15,7 +18,10 @@
     "need": "TREQ_ID_3",
     "verify_type": "partially",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   },
   {
     "name": "test_error_handling",
@@ -24,7 +30,10 @@
     "need": "TREQ_ID_2",
     "verify_type": "partially",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   },
   {
     "name": "test_error_handling",
@@ -33,7 +42,10 @@
     "need": "TREQ_ID_3",
     "verify_type": "partially",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   },
   {
     "name": "TestRequirementsCoverage__test_system_startup_time",
@@ -42,6 +54,9 @@
     "need": "TREQ_ID_1",
     "verify_type": "fully",
     "result": "passed",
-    "result_text": ""
+    "result_text": "",
+    "module_name": "local_module",
+    "hash": "",
+    "url": ""
   }
 ]
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 9d3fa78f5..ff23ad184 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -1,5 +1,5 @@
 # *******************************************************************************
-# Copyright (c) 2025 Contributors to the Eclipse Foundation
+# Copyright (c) 2025-2026 Contributors to the Eclipse Foundation
 #
 # See the NOTICE file(s) distributed with this work for additional
 # information regarding copyright ownership.
@@ -35,7 +35,6 @@
     get_cache_filename,
     group_by_need,
 )
-from src.extensions.score_source_code_linker.helpers import get_github_link
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
     load_source_code_links_json,
@@ -44,6 +43,10 @@
 from src.helper_lib import (
     get_current_git_hash,
 )
+# ADAPTED: Importing from the new generator location
+from src.extensions.score_source_code_linker.helpers import (
+    get_github_link_from_git,
+)
 
 """
 #          ────────────────ATTENTION───────────────
@@ -127,6 +130,7 @@ def default(self, o: object):
 
 
 def needlink_test_decoder(d: dict[str, Any]) -> NeedLink | dict[str, Any]:
+    # ADAPTED: Updated to include new optional fields (module_name, hash, url)
     if {"file", "line", "tag", "need", "full_line"} <= d.keys():
         return NeedLink(
             file=Path(d["file"]),
@@ -134,6 +138,9 @@ def needlink_test_decoder(d: dict[str, Any]) -> NeedLink | dict[str, Any]:
             tag=decode_comment(d["tag"]),
             need=d["need"],
             full_line=decode_comment(d["full_line"]),
+            module_name=d.get("module_name", ""),
+            hash=d.get("hash", ""),
+            url=d.get("url", ""),
         )
     # It's something else, pass it on to other decoders
     return d
@@ -347,7 +354,8 @@ def test_get_github_link_with_real_repo(git_repo: Path) -> None:
 
     # Have to change directories in order to ensure that we get the right/any .git file
     os.chdir(Path(git_repo).absolute())
-    result = get_github_link(needlink)
+    # ADAPTED: Using get_github_link_from_git for direct local repo testing
+    result = get_github_link_from_git(needlink)
 
     # Should contain the base URL, hash, file path, and line number
     assert "https://github.com/test-user/test-repo/blob/" in result
@@ -549,7 +557,8 @@ def another_function():
     # Have to change directories in order to ensure that we get the right/any .git file
     os.chdir(Path(git_repo).absolute())
     for needlink in loaded_links:
-        github_link = get_github_link(needlink)
+        # ADAPTED: Using get_github_link_from_git
+        github_link = get_github_link_from_git(needlink)
         assert "https://github.com/test-user/test-repo/blob/" in github_link
         assert f"src/{needlink.file.name}#L{needlink.line}" in github_link
 
@@ -587,5 +596,6 @@ def test_multiple_commits_hash_consistency(git_repo: Path) -> None:
     )
 
     os.chdir(Path(git_repo).absolute())
-    github_link = get_github_link(needlink)
+    # ADAPTED: Using get_github_link_from_git
+    github_link = get_github_link_from_git(needlink)
     assert new_hash in github_link
diff --git a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
index b4e65279d..fb4780dc1 100644
--- a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
@@ -25,7 +25,6 @@
 from sphinx.testing.util import SphinxTestApp
 from sphinx_needs.data import SphinxNeedsData
 
-from src.extensions.score_source_code_linker.helpers import get_github_link
 from src.extensions.score_source_code_linker.needlinks import NeedLink
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
@@ -38,6 +37,7 @@
     SourceCodeLinks_TEST_JSON_Decoder,
 )
 from src.helper_lib import find_ws_root, get_github_base_url
+from src.extensions.score_source_code_linker.helpers import get_github_link
 
 
 @pytest.fixture()
diff --git a/src/extensions/score_source_code_linker/tests/test_testlink.py b/src/extensions/score_source_code_linker/tests/test_testlink.py
index 74becef6b..de6811183 100644
--- a/src/extensions/score_source_code_linker/tests/test_testlink.py
+++ b/src/extensions/score_source_code_linker/tests/test_testlink.py
@@ -1,5 +1,5 @@
 # *******************************************************************************
-# Copyright (c) 2025 Contributors to the Eclipse Foundation
+# Copyright (c) 2025-2026 Contributors to the Eclipse Foundation
 #
 # See the NOTICE file(s) distributed with this work for additional
 # information regarding copyright ownership.
@@ -41,6 +41,10 @@ def test_testlink_serialization_roundtrip():
         verify_type="fully",
         result="passed",
         result_text="All good",
+        # ADAPTED: Added new fields
+        module_name="test_module",
+        hash="abc12345",
+        url="https://github.com/org/repo",
     )
     dumped = json.dumps(link, cls=DataForTestLink_JSON_Encoder)
     loaded = json.loads(dumped, object_hook=DataForTestLink_JSON_Decoder)
@@ -101,6 +105,10 @@ def test_testcaseneed_to_dict_multiple_links():
         result_text="Something went wrong",
         PartiallyVerifies="REQ-1, REQ-2",
         FullyVerifies="REQ-3",
+        # ADAPTED: Added new fields which are now required for valid TestLinks
+        module_name="test_module",
+        hash="hash123",
+        url="http://github.com",
     )
 
     links = case.get_test_links()
@@ -114,6 +122,10 @@ def test_testcaseneed_to_dict_multiple_links():
         assert link.line == 10
         assert link.name == "TC_01"
         assert link.result == "failed"
+        # ADAPTED: Verify new fields are propagated
+        assert link.module_name == "test_module"
+        assert link.hash == "hash123"
+        assert link.url == "http://github.com"
 
 
 @add_test_properties(
@@ -134,6 +146,10 @@ def test_store_and_load_testlinks_roundtrip(tmp_path: Path):
             verify_type="partially",
             result="passed",
             result_text="Looks good",
+            # ADAPTED: Added new fields
+            module_name="mod1",
+            hash="h1",
+            url="u1",
         ),
         DataForTestLink(
             name="L2",
@@ -143,6 +159,10 @@ def test_store_and_load_testlinks_roundtrip(tmp_path: Path):
             verify_type="fully",
             result="failed",
             result_text="Needs work",
+            # ADAPTED: Added new fields
+            module_name="mod2",
+            hash="h2",
+            url="u2",
         ),
     ]
 
diff --git a/src/extensions/score_source_code_linker/tests/test_xml_parser.py b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
index 95b445dde..c283aada5 100644
--- a/src/extensions/score_source_code_linker/tests/test_xml_parser.py
+++ b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
@@ -1,5 +1,5 @@
 # *******************************************************************************
-# Copyright (c) 2025 Contributors to the Eclipse Foundation
+# Copyright (c) 2025-2026 Contributors to the Eclipse Foundation
 #
 # See the NOTICE file(s) distributed with this work for additional
 # information regarding copyright ownership.
@@ -20,6 +20,7 @@
 from collections.abc import Callable
 from pathlib import Path
 from typing import Any
+from unittest.mock import patch
 
 import pytest
 
@@ -262,10 +263,18 @@ def test_parse_properties():
     test_type="requirements-based",
     derivation_technique="requirements-analysis",
 )
+# ADAPTED: Added patching for metadata functions
+@patch("src.extensions.score_source_code_linker.xml_parser.parse_module_name_from_path")
 def test_read_test_xml_file(
+    mock_parse_module: Any,
     tmp_xml_dirs: Callable[..., tuple[Path, Path, Path, Path, Path]],
 ):
     """Ensure a whole pre-defined xml file is parsed correctly"""
+    # ADAPTED: Mock return value to ensure metadata is populated.
+    # 'local_module' triggers the path where hash/url are empty strings,
+    # which is valid but avoids the need to mock parse_info_from_known_good.
+    mock_parse_module.return_value = "local_module"
+
     _: Path
     dir1: Path
     dir2: Path
@@ -276,6 +285,11 @@ def test_read_test_xml_file(
     tcneed = needs1[0]
     assert isinstance(tcneed, DataOfTestCase)
     assert tcneed.result == "failed"
+    # ADAPTED: Verify metadata fields were populated
+    assert tcneed.module_name == "local_module"
+    assert tcneed.hash == ""
+    assert tcneed.url == ""
+
     assert no_props1 == []
     assert missing_props1 == []
 
@@ -287,7 +301,7 @@ def test_read_test_xml_file(
 
     # Extra Properties => Should not cause an error
     needs3, no_props3, missing_props3 = xml_parser.read_test_xml_file(dir3 / "test.xml")
-    assert isinstance(needs1, list) and len(needs1) == 1
+    assert isinstance(needs3, list) and len(needs3) == 1
     tcneed3 = needs3[0]
     assert isinstance(tcneed3, DataOfTestCase)
     assert no_props3 == []

From d094914cec1a1c9a8c76ee693ce2dba67dec5950 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 05:32:23 +0100
Subject: [PATCH 15/34] Tests Passing & Tests adapted

---
 pyproject.toml                                |   1 -
 .../generate_source_code_links_json.py        |   5 +-
 .../score_source_code_linker/helpers.py       |  12 +
 .../score_source_code_linker/needlinks.py     |  36 +-
 .../score_source_code_linker/testlink.py      |  41 ++-
 .../tests/test_codelink.py                    |  32 +-
 .../tests/test_helpers.py                     | 347 ++++++++++++++++++
 .../test_source_code_link_integration.py      |  45 ++-
 8 files changed, 478 insertions(+), 41 deletions(-)
 create mode 100644 src/extensions/score_source_code_linker/tests/test_helpers.py

diff --git a/pyproject.toml b/pyproject.toml
index b9efbffb8..8dd24d16b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -67,4 +67,3 @@ filterwarnings = [
 pythonpath = [
     "src/extensions/",
 ]
-basetemp = "./debug_tmp"
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index 44c1c8bed..87e4aa554 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -19,6 +19,7 @@
 
 import os
 from pathlib import Path
+import subprocess
 
 from sphinx_needs.logging import get_logger
 
@@ -60,6 +61,8 @@ def _extract_references_from_file(
     print("ROOT: ", root)
     print("FILE_PATH: ", file_path)
     print("FILE_PATH_NAME: ", file_path_name)
+    output = subprocess.run(["ls", "-la", f"{root}"], capture_output=True)
+    print(output)
     assert root.is_absolute(), "Root path must be absolute"
     assert not file_path_name.is_absolute(), "File path must be relative to the root"
     # assert file_path.is_relative_to(root), (
@@ -136,7 +139,7 @@ def find_all_need_references(search_path: Path) -> list[NeedLink]:
         print("Search_path: ", search_path)
         print("File.name: ", file.name)
         print("File: ", file)
-        references = _extract_references_from_file(search_path,Path(file.name), file)
+        references = _extract_references_from_file(search_path,Path(file), file)
         all_need_references.extend(references)
 
     elapsed_time = os.times().elapsed - start_time
diff --git a/src/extensions/score_source_code_linker/helpers.py b/src/extensions/score_source_code_linker/helpers.py
index ad471f757..a186754ac 100644
--- a/src/extensions/score_source_code_linker/helpers.py
+++ b/src/extensions/score_source_code_linker/helpers.py
@@ -93,6 +93,18 @@ def parse_info_from_known_good(
 ) -> tuple[str, str]:
     with open(known_good_json) as f:
         kg_json = json.load(f)
+
+    #   ───────[ Assert our worldview that has to exist here ]─────
+    assert kg_json, (
+        f"Known good json at: {known_good_json} is empty. This is not allowed"
+    )
+    assert "modules" in kg_json, (
+        f"Known good json at: {known_good_json} is missing the 'modules' key"
+    )
+    assert kg_json["modules"], (
+        f"Known good json at: {known_good_json} has an empty 'modules' dictionary"
+    )
+
     for category in kg_json["modules"].values():
         if module_name in category:
             m = category[module_name]
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index 8bc8f9439..0f55d6dd3 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -24,6 +24,7 @@ class MetaData(TypedDict):
     hash: str
     url: str
 
+
 def is_metadata(x: object) -> TypeGuard[MetaData]:
     # Make this as strict/loose as you want; at minimum, it must be a dict.
     return isinstance(x, dict) and {"module_name", "hash", "url"} <= x.keys()
@@ -38,13 +39,46 @@ class NeedLink:
     tag: str
     need: str
     full_line: str
-    module_name: str = ""
+    module_name: str = "local_module"
     hash: str = ""
     url: str = ""
 
+    # Adding hashing & equality as this is needed to make comparisions.
+    # Since the Dataclass is not 'frozen = true' it isn't automatically hashable
+    def __hash__(self):
+        return hash(
+            (
+                self.file,
+                self.line,
+                self.tag,
+                self.need,
+                self.full_line,
+                self.module_name,
+                self.hash,
+                self.url,
+            )
+        )
+
+    def __eq__(self, other):
+        if not isinstance(other, NeedLink):
+            return NotImplemented
+        return (
+            self.file == other.file
+            and self.line == other.line
+            and self.tag == other.tag
+            and self.need == other.need
+            and self.full_line == other.full_line
+            and self.module_name == other.module_name
+            and self.hash == other.hash
+            and self.url == other.url
+        )
+
+    # Normal 'dictionary conversion'. Converts all fields
     def to_dict_full(self) -> dict[str, str | Path | int]:
         return asdict(self)
 
+    # Drops MetaData fields for saving the Dataclass (saving space in json)
+    # The information is in the 'Module_Source_Link' in the end
     def to_dict_without_metadata(self) -> dict[str, str | Path | int]:
         d = asdict(self)
         d.pop("module_name", None)
diff --git a/src/extensions/score_source_code_linker/testlink.py b/src/extensions/score_source_code_linker/testlink.py
index bd7139271..170bd0ad4 100644
--- a/src/extensions/score_source_code_linker/testlink.py
+++ b/src/extensions/score_source_code_linker/testlink.py
@@ -33,7 +33,7 @@
 LOGGER = logging.get_logger(__name__)
 
 
-@dataclass(frozen=True, order=True)
+@dataclass(order=True)
 class DataForTestLink:
     name: str
     file: Path
@@ -42,13 +42,50 @@ class DataForTestLink:
     verify_type: str
     result: str
     result_text: str = ""
-    module_name: str = ""
+    module_name: str = "local_module"
     hash: str = ""
     url: str = ""
 
+    # Adding hashing & equality as this is needed to make comparisions.
+    # Since the Dataclass is not 'frozen = true' it isn't automatically hashable
+    def __hash__(self):
+        return hash(
+            (
+                self.name,
+                str(self.file),
+                self.line,
+                self.need,
+                self.verify_type,
+                self.result,
+                self.result_text,
+                self.module_name,
+                self.hash,
+                self.url,
+            )
+        )
+
+    def __eq__(self, other):
+        if not isinstance(other, DataForTestLink):
+            return NotImplemented
+        return (
+            self.name == other.name
+            and self.file == other.file
+            and self.line == other.line
+            and self.need == other.need
+            and self.verify_type == other.verify_type
+            and self.result == other.result
+            and self.result_text == other.result_text
+            and self.module_name == other.module_name
+            and self.hash == other.hash
+            and self.url == other.url
+        )
+
+    # Normal 'dictionary conversion'. Converts all fields
     def to_dict_full(self) -> dict[str, str | Path | int]:
         return asdict(self)
 
+    # Drops MetaData fields for saving the Dataclass (saving space in json)
+    # The information is in the 'Module_Source_Link' in the end
     def to_dict_without_metadata(self) -> dict[str, str | Path | int]:
         d = asdict(self)
         d.pop("module_name", None)
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index ff23ad184..46d45a59c 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -131,7 +131,7 @@ def default(self, o: object):
 
 def needlink_test_decoder(d: dict[str, Any]) -> NeedLink | dict[str, Any]:
     # ADAPTED: Updated to include new optional fields (module_name, hash, url)
-    if {"file", "line", "tag", "need", "full_line"} <= d.keys():
+    if {"file", "line", "tag", "need", "full_line", "module_name", "hash" ,"url" } <= d.keys():
         return NeedLink(
             file=Path(d["file"]),
             line=d["line"],
@@ -336,36 +336,6 @@ def test_group_by_need_empty_list():
     assert len(result) == 0
 
 
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
-def test_get_github_link_with_real_repo(git_repo: Path) -> None:
-    """Test generating GitHub link with real repository."""
-    # Create a needlink
-    needlink = NeedLink(
-        file=Path("src/test.py"),
-        line=42,
-        tag="#" + " req-Id:",
-        need="REQ_001",
-        full_line="#" + " req-Id: REQ_001",
-    )
-
-    # Have to change directories in order to ensure that we get the right/any .git file
-    os.chdir(Path(git_repo).absolute())
-    # ADAPTED: Using get_github_link_from_git for direct local repo testing
-    result = get_github_link_from_git(needlink)
-
-    # Should contain the base URL, hash, file path, and line number
-    assert "https://github.com/test-user/test-repo/blob/" in result
-    assert "src/test.py#L42" in result
-    assert len(result.split("/")) >= 7  # Should have proper URL structure
-
-    # Verify the hash is actually from the repo
-    hash_from_link = result.split("/blob/")[1].split("/")[0]
-    actual_hash = get_current_git_hash(git_repo)
-    assert hash_from_link == actual_hash
 
 
 # Test cache file operations
diff --git a/src/extensions/score_source_code_linker/tests/test_helpers.py b/src/extensions/score_source_code_linker/tests/test_helpers.py
new file mode 100644
index 000000000..593253583
--- /dev/null
+++ b/src/extensions/score_source_code_linker/tests/test_helpers.py
@@ -0,0 +1,347 @@
+# *******************************************************************************
+# Copyright (c) 2025 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+import json
+import os
+from pathlib import Path
+import tempfile
+from collections.abc import Generator
+
+import pytest
+import subprocess
+
+from src.helper_lib import get_current_git_hash 
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
+from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink
+
+from src.extensions.score_source_code_linker.helpers import (
+    get_github_link,
+    get_github_link_from_json,
+    parse_info_from_known_good,
+    parse_module_name_from_path,
+)
+
+
+#              ╭──────────────────────────────────────────────────────────╮
+#              │          Tests for parse_module_name_from_path           │
+#              ╰──────────────────────────────────────────────────────────╯
+
+
+def test_parse_module_name_from_external_path():
+    """Test parsing module name from external/combo build path."""
+    path = Path("external/score_docs_as_code+/src/helper_lib/test_helper_lib.py")
+
+    result = parse_module_name_from_path(path)
+
+    assert result == "score_docs_as_code"
+
+
+def test_parse_module_name_from_external_path_2():
+    """Test that an extra 'external' in the path does not change the output"""
+    path = Path(
+        "external/score_docs_as_code+/src/external/helper_lib/test_helper_lib.py"
+    )
+
+    result = parse_module_name_from_path(path)
+
+    assert result == "score_docs_as_code"
+
+
+def test_parse_module_name_from_local_path():
+    """Test parsing module name from local build path."""
+    path = Path("src/helper_lib/test_helper_lib.py")
+
+    result = parse_module_name_from_path(path)
+
+    assert result == "local_module"
+
+
+def test_parse_module_name_from_empty_path():
+    """Test parsing module name from an empty path."""
+    path = Path("")
+
+    result = parse_module_name_from_path(path)
+
+    assert result == "local_module"
+
+
+def test_parse_module_name_without_plus_suffix():
+    """
+    Test parsing external module without plus suffix.
+    This should never happen (due to bazel adding the '+')
+    But testing this edge case anyway
+    """
+    path = Path("external/module_without_plus/file.py")
+
+    result = parse_module_name_from_path(path)
+
+    assert result == "module_without_plus"
+
+
+#              ╭──────────────────────────────────────────────────────────╮
+#              │                PARSE INFO FROM KNOWN GOOD                │
+#              ╰──────────────────────────────────────────────────────────╯
+
+
+# Example of a minimal valid known_good.json structure
+VALID_KNOWN_GOOD = {
+    "modules": {
+        "target_sw": {
+            "score_baselibs": {
+                "repo": "https://github.com/eclipse-score/baselibs.git",
+                "hash": "158fe6a7b791c58f6eac5f7e4662b8db0cf9ac6e",
+            },
+            "score_communication": {
+                "repo": "https://github.com/eclipse-score/communication.git",
+                "hash": "56448a5589a5f7d3921b873e8127b824a8c1ca95",
+            },
+        },
+        "tooling": {
+            "score_docs_as_code": {
+                "repo": "https://github.com/eclipse-score/docs-as-code.git",
+                "hash": "c1207676afe6cafd25c35d420e73279a799515d8",
+            }
+        },
+    }
+}
+
+#             ────────────────────────────────────────────────────────────
+#            ──────────────────────[ Test Functions ]──────────────────────
+
+
+@pytest.fixture
+def known_good_json(tmp_path: Path):
+    """Fixture providing a valid known_good.json file."""
+    json_file = tmp_path / "known_good.json"
+    _ = json_file.write_text(json.dumps(VALID_KNOWN_GOOD))
+    return json_file
+
+
+# Tests for parse_info_from_known_good
+def test_parse_info_from_known_good_happy_path(known_good_json: Path):
+    """Test parsing module info from valid known_good.json."""
+    hash_result, repo_result = parse_info_from_known_good(
+        known_good_json, "score_baselibs"
+    )
+
+    assert hash_result == "158fe6a7b791c58f6eac5f7e4662b8db0cf9ac6e"
+    assert repo_result == "https://github.com/eclipse-score/baselibs"
+
+
+def test_parse_info_from_known_good_different_category(known_good_json: Path):
+    """Test finding module in different category."""
+    hash_result, repo_result = parse_info_from_known_good(
+        known_good_json, "score_docs_as_code"
+    )
+
+    assert hash_result == "c1207676afe6cafd25c35d420e73279a799515d8"
+    assert repo_result == "https://github.com/eclipse-score/docs-as-code"
+
+
+def test_parse_info_from_known_good_module_not_found(known_good_json: Path):
+    """Test that KeyError is raised when module doesn't exist."""
+    with pytest.raises(KeyError, match="Module 'nonexistent' not found"):
+        parse_info_from_known_good(known_good_json, "nonexistent")
+
+
+def test_parse_info_from_known_good_empty_json(tmp_path: Path):
+    """Test with empty JSON file."""
+    json_file = tmp_path / "example.json"
+    _ = json_file.write_text("{}")
+
+    with pytest.raises(
+        AssertionError,
+        match=f"Known good json at: {json_file} is empty. This is not allowed",
+    ):
+        parse_info_from_known_good(json_file, "any_module")
+
+
+def test_parse_info_from_known_good_no_module_in_json(tmp_path: Path):
+    """Test that assertion works when module not in top level keys"""
+    json_file = tmp_path / "example.json"
+    _ = json_file.write_text(
+        '{"another_key": {"a": "b"}, "second_key": ["a" , "b", "c"]}'
+    )
+
+    with pytest.raises(
+        AssertionError,
+        match=f"Known good json at: {json_file} is missing the 'modules' key",
+    ):
+        parse_info_from_known_good(json_file, "any_module")
+
+
+def test_parse_info_from_known_good_empty_module_dict_in_json(tmp_path: Path):
+    """Test that assertion works if module dictionary is empty"""
+    json_file = tmp_path / "emample.json"
+    _ = json_file.write_text('{"another_key": {"a": "b"}, "modules": {}}')
+
+    with pytest.raises(
+        AssertionError,
+        match=f"Known good json at: {json_file} has an empty 'modules' dictionary",
+    ):
+        parse_info_from_known_good(json_file, "any_module")
+
+
+# Tests for get_github_link_from_json
+def test_get_github_link_from_json_happy_path():
+    """Test generating GitHub link from metadata."""
+    metadata = ModuleInfo(
+        name="project_name",
+        url="https://github.com/eclipse/project",
+        hash="commit123abc",
+    )
+
+    link = DefaultNeedLink()
+    link.file = Path("docs/index.rst")
+    link.line = 100
+
+    result = get_github_link_from_json(metadata, link)
+
+    assert (
+        result
+        == "https://github.com/eclipse/project/blob/commit123abc/docs/index.rst#L100"
+    )
+
+
+def test_get_github_link_from_json_with_none_link():
+    """Test that None link creates DefaultNeedLink."""
+    metadata = ModuleInfo(
+        name="test_repo", url="https://github.com/test/repo", hash="def456"
+    )
+
+    result = get_github_link_from_json(metadata, None)
+
+    assert result.startswith("https://github.com/test/repo/blob/def456/")
+    assert "#L" in result
+
+
+def test_get_github_link_from_json_with_line_zero():
+    """Test generating link with line number 0."""
+    metadata = ModuleInfo(
+        name="test_repo", url="https://github.com/test/repo", hash="hash123"
+    )
+
+    link = DefaultNeedLink()
+    link.file = Path("file.py")
+    link.line = 0
+
+    result = get_github_link_from_json(metadata, link)
+
+    assert result == "https://github.com/test/repo/blob/hash123/file.py#L0"
+
+
+# Tests for get_github_link
+def test_get_github_link_with_hash():
+    """Test get_github_link uses json method when hash is present."""
+    metadata = ModuleInfo(
+        name="some_module", url="https://github.com/org/repo", hash="commit_hash_123"
+    )
+
+    link = DefaultNeedLink()
+    link.file = Path("src/example.py")
+    link.line = 42
+
+    result = get_github_link(metadata, link)
+
+    assert (
+        result == "https://github.com/org/repo/blob/commit_hash_123/src/example.py#L42"
+    )
+
+@pytest.fixture
+def temp_dir() -> Generator[Path, None, None]:
+    """Create a temporary directory for tests."""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        yield Path(temp_dir)
+
+@pytest.fixture
+def git_repo(temp_dir: Path) -> Path:
+    """Create a real git repository for testing."""
+    git_dir: Path = temp_dir / "test_repo"
+    git_dir.mkdir()
+
+    # Initialize git repo
+    _ = subprocess.run(["git", "init"], cwd=git_dir, check=True, capture_output=True)
+    _ = subprocess.run(
+        ["git", "config", "user.email", "test@example.com"], cwd=git_dir, check=True
+    )
+    _ = subprocess.run(
+        ["git", "config", "user.name", "Test User"], cwd=git_dir, check=True
+    )
+
+    # Create a test file and commit
+    test_file: Path = git_dir / "test_file.py"
+    _ = test_file.write_text("# Test file\nprint('hello')\n")
+    _ = subprocess.run(["git", "add", "."], cwd=git_dir, check=True)
+    _ = subprocess.run(
+        ["git", "commit", "-m", "Initial commit"], cwd=git_dir, check=True
+    )
+
+    # Add a remote
+    _ = subprocess.run(
+        ["git", "remote", "add", "origin", "git@github.com:test-user/test-repo.git"],
+        cwd=git_dir,
+        check=True,
+    )
+    return git_dir
+
+
+def test_get_github_link_with_real_repo(git_repo: Path) -> None:
+    """
+    Test generating GitHub link without url/hash.
+    This expects to be in a git module
+    """
+    metadata = ModuleInfo(name="some_module", url="", hash="")
+
+    link = DefaultNeedLink()
+    link.file = Path("src/example.py")
+    link.line = 42
+
+    # Have to change directories in order to ensure that we get the right/any .git file
+    os.chdir(Path(git_repo).absolute())
+    # ADAPTED: Using get_github_link_from_git for direct local repo testing
+    result = get_github_link(metadata, link)
+
+    # Should contain the base URL, hash, file path, and line number
+    assert "https://github.com/test-user/test-repo/blob/" in result
+    assert "src/example.py#L42" in result
+
+    # Verify the hash is actually from the repo
+    hash_from_link = result.split("/blob/")[1].split("/")[0]
+    actual_hash = get_current_git_hash(git_repo)
+    assert hash_from_link == actual_hash
+
+
+def test_complete_workflow(known_good_json: Path):
+    """Test complete workflow from path to GitHub link."""
+
+    # Parse path
+    path = Path("external/score_docs_as_code+/src/helper_lib/test_helper_lib.py")
+    module_name = parse_module_name_from_path(path)
+    assert module_name == "score_docs_as_code"
+
+    # Get metadata
+    hash_val, repo_url = parse_info_from_known_good(known_good_json, module_name)
+    assert hash_val == "c1207676afe6cafd25c35d420e73279a799515d8"
+    assert repo_url == "https://github.com/eclipse-score/docs-as-code"
+
+    # Generate link
+    metadata = ModuleInfo(name=module_name, url=repo_url, hash=hash_val)
+    link = DefaultNeedLink()
+    link.file = Path("src/helper_lib/test_helper_lib.py")
+    link.line = 75
+
+    result = get_github_link(metadata, link)
+
+    assert (
+        result
+        == "https://github.com/eclipse-score/docs-as-code/blob/c1207676afe6cafd25c35d420e73279a799515d8/src/helper_lib/test_helper_lib.py#L75"
+    )
diff --git a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
index fb4780dc1..e49d856da 100644
--- a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
@@ -26,6 +26,7 @@
 from sphinx_needs.data import SphinxNeedsData
 
 from src.extensions.score_source_code_linker.needlinks import NeedLink
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
     DataForTestLink_JSON_Decoder,
@@ -40,12 +41,12 @@
 from src.extensions.score_source_code_linker.helpers import get_github_link
 
 
-@pytest.fixture()
+@pytest.fixture(scope="session")
 def sphinx_base_dir(tmp_path_factory: TempPathFactory) -> Path:
     return tmp_path_factory.mktemp("test_git_repo")
 
 
-@pytest.fixture()
+@pytest.fixture(scope="session")
 def git_repo_setup(sphinx_base_dir: Path) -> Path:
     """Creating git repo, to make testing possible"""
 
@@ -67,7 +68,7 @@ def git_repo_setup(sphinx_base_dir: Path) -> Path:
     return repo_path
 
 
-@pytest.fixture()
+@pytest.fixture(scope="session")
 def create_demo_files(sphinx_base_dir: Path, git_repo_setup: Path):
     repo_path = sphinx_base_dir
 
@@ -312,6 +313,9 @@ def example_source_link_text_all_ok(sphinx_base_dir: Path) -> dict[str, list[Nee
                 tag="#" + " req-Id:",
                 need="TREQ_ID_1",
                 full_line="#" + " req-Id: TREQ_ID_1",
+                module_name="local_module",
+                url="",
+                hash="",
             ),
             NeedLink(
                 file=Path("src/implementation1.py"),
@@ -319,6 +323,9 @@ def example_source_link_text_all_ok(sphinx_base_dir: Path) -> dict[str, list[Nee
                 tag="#" + " req-Id:",
                 need="TREQ_ID_1",
                 full_line="#" + " req-Id: TREQ_ID_1",
+                module_name="local_module",
+                url="",
+                hash="",
             ),
         ],
         "TREQ_ID_2": [
@@ -328,6 +335,9 @@ def example_source_link_text_all_ok(sphinx_base_dir: Path) -> dict[str, list[Nee
                 tag="#" + " req-Id:",
                 need="TREQ_ID_2",
                 full_line="#" + " req-Id: TREQ_ID_2",
+                module_name="local_module",
+                url="",
+                hash="",
             )
         ],
         "TREQ_ID_3": [],
@@ -346,6 +356,9 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="fully",
                 result="passed",
                 result_text="",
+                module_name="local_module",
+                url="",
+                hash="",
             ),
         ],
         "TREQ_ID_2": [
@@ -357,6 +370,9 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="partially",
                 result="passed",
                 result_text="",
+                module_name="local_module",
+                url="",
+                hash="",
             ),
             DataForTestLink(
                 name="test_error_handling",
@@ -366,6 +382,9 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="partially",
                 result="passed",
                 result_text="",
+                module_name="local_module",
+                url="",
+                hash="",
             ),
         ],
         "TREQ_ID_3": [
@@ -377,6 +396,9 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="partially",
                 result="passed",
                 result_text="",
+                module_name="local_module",
+                url="",
+                hash="",
             ),
             DataForTestLink(
                 name="test_error_handling",
@@ -386,6 +408,9 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="partially",
                 result="passed",
                 result_text="",
+                module_name="local_module",
+                url="",
+                hash="",
             ),
         ],
     }
@@ -409,11 +434,21 @@ def example_source_link_text_non_existent(sphinx_base_dir: Path):
 
 
 def make_source_link(needlinks: list[NeedLink]):
-    return ", ".join(f"{get_github_link(n)}<>{n.file}:{n.line}" for n in needlinks)
+    metadata= ModuleInfo(
+                name="local_module",
+                url="",
+                hash="",
+    )
+    return ", ".join(f"{get_github_link(metadata,n)}<>{n.file}:{n.line}" for n in needlinks)
 
 
 def make_test_link(testlinks: list[DataForTestLink]):
-    return ", ".join(f"{get_github_link(n)}<>{n.name}" for n in testlinks)
+    metadata= ModuleInfo(
+                name="local_module",
+                url="",
+                hash="",
+    )
+    return ", ".join(f"{get_github_link(metadata,n)}<>{n.name}" for n in testlinks)
 
 
 def compare_json_files(

From 0d1e490f205db22fac4d849fab2ff11055538af2 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 10:22:12 +0100
Subject: [PATCH 16/34] Fixing tests

---
 .../module_source_links.py                    |  40 +-
 .../need_source_links.py                      |   6 +-
 .../score_source_code_linker/needlinks.py     |   8 +-
 .../tests/expected_module_grouped.json        |  83 +++
 .../tests/test_codelink.py                    | 614 +++++++++++++++---
 .../tests/test_module_source_links.py         | 467 +++++++++++++
 .../test_module_source_links_integration.py   | 456 +++++++++++++
 .../tests/test_testlink.py                    | 228 +++++++
 8 files changed, 1799 insertions(+), 103 deletions(-)
 create mode 100644 src/extensions/score_source_code_linker/tests/expected_module_grouped.json
 create mode 100644 src/extensions/score_source_code_linker/tests/test_module_source_links.py
 create mode 100644 src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py

diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index bf299a49f..cc4e39165 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -48,8 +48,25 @@ def default(self, o: object):
         # (hash, module_name, url)
         if isinstance(o, NeedLink | DataForTestLink):
             return o.to_dict_without_metadata()
-        if isinstance(o, ModuleSourceLinks | SourceCodeLinks | NeedSourceLinks):
-            return asdict(o)
+        # We need to split this up, otherwise the nested 
+        # dictionaries won't get split up and we will not 
+        # run into the 'to_dict_without_metadata' as 
+        # everything will be converted to a normal dictionary
+        if isinstance(o, ModuleSourceLinks):
+            return {
+                "module": asdict(o.module),
+                "needs": o.needs,  # Let the encoder handle the list
+            }
+        if isinstance(o, SourceCodeLinks):
+            return {
+                "need": o.need,
+                "links": o.links,
+            }
+        if isinstance(o, NeedSourceLinks):
+            return {
+                "CodeLinks": o.CodeLinks,
+                "TestLinks": o.TestLinks,
+            }
         return super().default(o)
 
 
@@ -61,7 +78,7 @@ def ModuleSourceLinks_JSON_Decoder(
         needs = d["needs"]
         return ModuleSourceLinks(
             module=ModuleInfo(
-                name=module.get("module_name"),
+                name=module.get("name"),
                 hash=module.get("hash"),
                 url=module.get("url"),
             ),
@@ -75,10 +92,10 @@ def ModuleSourceLinks_JSON_Decoder(
 def store_module_source_links_json(
     file: Path, source_code_links: list[ModuleSourceLinks]
 ):
-    # After `rm -rf _build` or on clean builds the directory does not exist, so we need
-    # to create it
-    file.parent.mkdir(exist_ok=True)
-    with open(file, "w", encoding="utf-8") as f:
+    # After `rm -rf _build` or on clean builds the directory does not exist, 
+    # so we need to create it. We create any folder that might be missing
+    file.parent.mkdir(exist_ok=True, parents=True)
+    with open(file, "w") as f:
         json.dump(
             source_code_links,
             f,
@@ -94,14 +111,11 @@ def load_module_source_links_json(file: Path) -> list[ModuleSourceLinks]:
         object_hook=ModuleSourceLinks_JSON_Decoder,
     )
     assert isinstance(links, list), (
-        "The ModuleSourceLink json should be aa list of ModuleSourceLink objects."
+        "The ModuleSourceLink json should be a list of ModuleSourceLink objects."
     )
-    print("=====================")
-    print("=== TESTING LINKS IN ModuleSourceLink === ")
     for link in links:
         if not isinstance(link, ModuleSourceLinks):
             print(f"Link not module_sourcelink: {link}")
-    print("=====================")
     assert all(isinstance(link, ModuleSourceLinks) for link in links), (
         "All items in module source link cache should be ModuleSourceLink objects."
     )
@@ -129,7 +143,9 @@ def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLink
                 )
             )
 
-        module_groups[module_key].needs.append(source_link)  # Much clearer!
+        # TODO: Add an assert that checks if needs only are
+        # in a singular module (not allowed to be in multiple)
+        module_groups[module_key].needs.append(source_link)
 
     return [
         ModuleSourceLinks(module=group.module, needs=group.needs)
diff --git a/src/extensions/score_source_code_linker/need_source_links.py b/src/extensions/score_source_code_linker/need_source_links.py
index 1582c2fe8..a0b79d796 100644
--- a/src/extensions/score_source_code_linker/need_source_links.py
+++ b/src/extensions/score_source_code_linker/need_source_links.py
@@ -82,9 +82,9 @@ def SourceCodeLinks_JSON_Decoder(d: dict[str, Any]) -> SourceCodeLinks | dict[st
 def store_source_code_links_combined_json(
     file: Path, source_code_links: list[SourceCodeLinks]
 ):
-    # After `rm -rf _build` or on clean builds the directory does not exist, so we need
-    # to create it
-    file.parent.mkdir(exist_ok=True)
+    # After `rm -rf _build` or on clean builds the directory does not exist, 
+    # so we need to create it. We create any folder that might be missing
+    file.parent.mkdir(exist_ok=True, parents=True)
     with open(file, "w") as f:
         json.dump(
             source_code_links,
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index 0f55d6dd3..588c95fef 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -140,7 +140,9 @@ def store_source_code_links_with_metadata_json(
     """
     payload: list[object] = [metadata, *needlist]
 
-    file.parent.mkdir(exist_ok=True)
+    # After `rm -rf _build` or on clean builds the directory does not exist, 
+    # so we need to create it. We create any folder that might be missing
+    file.parent.mkdir(exist_ok=True,parents=True)
     with open(file, "w", encoding="utf-8") as f:
         json.dump(payload, f, cls=NeedLinkEncoder, indent=2, ensure_ascii=False)
 
@@ -151,7 +153,9 @@ def store_source_code_links_json(file: Path, needlist: list[NeedLink]) -> None:
       [ needlink1, needlink2, ... ]
     """
 
-    file.parent.mkdir(exist_ok=True)
+    # After `rm -rf _build` or on clean builds the directory does not exist, 
+    # so we need to create it. We create any folder that might be missing
+    file.parent.mkdir(exist_ok=True, parents=True)
     with open(file, "w", encoding="utf-8") as f:
         json.dump(needlist, f, cls=NeedLinkEncoder, indent=2, ensure_ascii=False)
 
diff --git a/src/extensions/score_source_code_linker/tests/expected_module_grouped.json b/src/extensions/score_source_code_linker/tests/expected_module_grouped.json
new file mode 100644
index 000000000..fd1ebfd79
--- /dev/null
+++ b/src/extensions/score_source_code_linker/tests/expected_module_grouped.json
@@ -0,0 +1,83 @@
+[
+  {
+    "module": {
+      "name": "local_module",
+      "hash": "",
+      "url": ""
+    },
+    "needs": [
+      {
+        "need": "MOD_REQ_1",
+        "links": {
+          "CodeLinks": [
+            {
+              "file": "src/module_a_impl.py",
+              "line": 3,
+              "tag": "# req-Id:",
+              "need": "MOD_REQ_1",
+              "full_line": "# req-Id: MOD_REQ_1"
+            },
+            {
+              "file": "src/module_b_impl.py",
+              "line": 3,
+              "tag": "# req-Id:",
+              "need": "MOD_REQ_1",
+              "full_line": "# req-Id: MOD_REQ_1"
+            }
+          ],
+          "TestLinks": [
+            {
+              "name": "test_module_a",
+              "file": "src/test_module_a.py",
+              "line": 10,
+              "need": "MOD_REQ_1",
+              "verify_type": "fully",
+              "result": "passed",
+              "result_text": ""
+            }
+          ]
+        }
+      },
+      {
+        "need": "MOD_REQ_2",
+        "links": {
+          "CodeLinks": [
+            {
+              "file": "src/module_a_impl.py",
+              "line": 7,
+              "tag": "# req-Id:",
+              "need": "MOD_REQ_2",
+              "full_line": "# req-Id: MOD_REQ_2"
+            }
+          ],
+          "TestLinks": []
+        }
+      },
+      {
+        "need": "MOD_REQ_3",
+        "links": {
+          "CodeLinks": [
+            {
+              "file": "src/module_b_impl.py",
+              "line": 7,
+              "tag": "# req-Id:",
+              "need": "MOD_REQ_3",
+              "full_line": "# req-Id: MOD_REQ_3"
+            }
+          ],
+          "TestLinks": [
+            {
+              "name": "test_module_b",
+              "file": "src/test_module_b.py",
+              "line": 20,
+              "need": "MOD_REQ_3",
+              "verify_type": "partially",
+              "result": "passed",
+              "result_text": ""
+            }
+          ]
+        }
+      }
+    ]
+  }
+]
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 46d45a59c..e65adcb08 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -10,8 +10,14 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 # *******************************************************************************
+
+# ╓                                                          ╖
+# ║ Some portions created by Co-Pilot                        ║
+# ╙                                                          ╜
+
 import json
 import os
+from pkgutil import ModuleInfo
 import subprocess
 import tempfile
 from collections.abc import Generator
@@ -20,7 +26,11 @@
 from typing import Any
 
 import pytest
+
+# S-CORE plugin to allow for properties/attributes in xml
+# Enables Testlinking
 from attribute_plugin import add_test_properties  # type: ignore[import-untyped]
+
 from sphinx_needs.data import NeedsInfoType, NeedsMutable
 from sphinx_needs.need_item import (
     NeedItem,
@@ -28,39 +38,35 @@
     NeedsContent,
 )
 
-# Import the module under test
-# Note: You'll need to adjust these imports based on your actual module structure
 from src.extensions.score_source_code_linker import (
     find_need,
     get_cache_filename,
     group_by_need,
 )
+
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
+
 from src.extensions.score_source_code_linker.needlinks import (
+    DefaultNeedLink,
+    MetaData,
     NeedLink,
+    NeedLinkEncoder,
+    is_metadata,
     load_source_code_links_json,
+    load_source_code_links_with_metadata_json,
+    needlink_decoder,
     store_source_code_links_json,
+    store_source_code_links_with_metadata_json,
 )
 from src.helper_lib import (
     get_current_git_hash,
 )
-# ADAPTED: Importing from the new generator location
+
 from src.extensions.score_source_code_linker.helpers import (
     get_github_link_from_git,
+    get_github_link,
 )
 
-"""
-#          ────────────────ATTENTION───────────────
-
-#          ╭──────────────────────────────────────╮
-#          │                !!!!!                 │
-#          │      BOILERPLATE TEST MADE VIA       │
-#          │   GENERATION. NOT YET FULLY LOOKED   │
-#          │               THROUGH                │
-#          │                 !!!!                 │
-#          ╰──────────────────────────────────────╯
-
-"""
-
 
 def test_need(**kwargs: Any) -> NeedItem:
     """Convenience function to create a NeedItem object with some defaults."""
@@ -130,8 +136,19 @@ def default(self, o: object):
 
 
 def needlink_test_decoder(d: dict[str, Any]) -> NeedLink | dict[str, Any]:
-    # ADAPTED: Updated to include new optional fields (module_name, hash, url)
-    if {"file", "line", "tag", "need", "full_line", "module_name", "hash" ,"url" } <= d.keys():
+    """
+    Since we have our own decoder, we have to ensure it works as expected
+    """
+    if {
+        "file",
+        "line",
+        "tag",
+        "need",
+        "full_line",
+        "module_name",
+        "hash",
+        "url",
+    } <= d.keys():
         return NeedLink(
             file=Path(d["file"]),
             line=d["line"],
@@ -191,6 +208,9 @@ def sample_needlinks() -> list[NeedLink]:
             tag="#" + " req-Id:",
             need="TREQ_ID_1",
             full_line="#" + " req-Id: TREQ_ID_1",
+            module_name="local_module",
+            hash="",
+            url="",
         ),
         NeedLink(
             file=Path("src/implementation2.py"),
@@ -198,6 +218,9 @@ def sample_needlinks() -> list[NeedLink]:
             tag="#" + " req-Id:",
             need="TREQ_ID_1",
             full_line="#" + " req-Id: TREQ_ID_1",
+            module_name="local_module",
+            hash="",
+            url="",
         ),
         NeedLink(
             file=Path("src/implementation1.py"),
@@ -205,6 +228,9 @@ def sample_needlinks() -> list[NeedLink]:
             tag="#" + " req-Id:",
             need="TREQ_ID_2",
             full_line="#" + " req-Id: TREQ_ID_2",
+            module_name="local_module",
+            hash="",
+            url="",
         ),
         NeedLink(
             file=Path("src/bad_implementation.py"),
@@ -212,6 +238,9 @@ def sample_needlinks() -> list[NeedLink]:
             tag="#" + " req-Id:",
             need="TREQ_ID_200",
             full_line="#" + " req-Id: TREQ_ID_200",
+            module_name="local_module",
+            hash="",
+            url="",
         ),
     ]
 
@@ -246,12 +275,6 @@ def sample_needs() -> dict[str, dict[str, str]]:
     }
 
 
-# Test utility functions
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_get_cache_filename():
     """Test cache filename generation."""
     build_dir = Path("/tmp/build")
@@ -260,17 +283,13 @@ def test_get_cache_filename():
     assert result == expected
 
 
+# Done to appease the LSP Gods
 def make_needs(needs_dict: dict[str, dict[str, Any]]) -> NeedsMutable:
     return NeedsMutable(
         {need_id: test_need(**params) for need_id, params in needs_dict.items()}
     )
 
 
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_find_need_direct_match():
     """Test finding a need with direct ID match."""
     all_needs = make_needs(
@@ -284,11 +303,6 @@ def test_find_need_direct_match():
     assert result["id"] == "REQ_001"
 
 
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_find_need_not_found():
     """Test finding a need that doesn't exist."""
     all_needs = make_needs(
@@ -301,11 +315,6 @@ def test_find_need_not_found():
     assert result is None
 
 
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_group_by_need(sample_needlinks: list[NeedLink]) -> None:
     """Test grouping source code links by need ID."""
     result = group_by_need(sample_needlinks)
@@ -325,25 +334,12 @@ def test_group_by_need(sample_needlinks: list[NeedLink]) -> None:
             assert len(found_link.links.CodeLinks) == 1
 
 
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_group_by_need_empty_list():
     """Test grouping empty list of needlinks."""
     result = group_by_need([], [])
     assert len(result) == 0
 
 
-
-
-# Test cache file operations
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_cache_file_operations(
     temp_dir: Path, sample_needlinks: list[NeedLink]
 ) -> None:
@@ -370,11 +366,6 @@ def test_cache_file_operations(
     assert loaded_links[3].line == 2
 
 
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_cache_file_with_encoded_comments(temp_dir: Path) -> None:
     """Test that cache file properly handles encoded comments."""
     # Create needlinks with spaces in tags and full_line
@@ -385,6 +376,9 @@ def test_cache_file_with_encoded_comments(temp_dir: Path) -> None:
             tag="#" + " req-Id:",
             need="TEST_001",
             full_line="#" + " req-Id: TEST_001",
+            module_name="local_module",
+            hash="",
+            url="",
         )
     ]
 
@@ -404,14 +398,6 @@ def test_cache_file_with_encoded_comments(temp_dir: Path) -> None:
     assert loaded_links[0].full_line == "#" + " req-Id: TEST_001"
 
 
-# Integration tests
-
-
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_group_by_need_and_find_need_integration(
     sample_needlinks: list[NeedLink],
 ) -> None:
@@ -435,11 +421,6 @@ def test_group_by_need_and_find_need_integration(
             assert found_need["id"] == found_link.need
 
 
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_source_linker_end_to_end_with_real_files(
     temp_dir: Path, git_repo: Path
 ) -> None:
@@ -448,7 +429,7 @@ def test_source_linker_end_to_end_with_real_files(
     src_dir: Path = git_repo / "src"
     src_dir.mkdir()
 
-    (src_dir / "implementation1.py").write_text(
+    _ = (src_dir / "implementation1.py").write_text(
         """
 # Some implementation
 #"""
@@ -464,7 +445,7 @@ def function2():
 """
     )
 
-    (src_dir / "implementation2.py").write_text(
+    _ = (src_dir / "implementation2.py").write_text(
         """
 # Another implementation
 #"""
@@ -475,8 +456,8 @@ def another_function():
     )
 
     # Commit the changes
-    subprocess.run(["git", "add", "."], cwd=git_repo, check=True)
-    subprocess.run(
+    _ = subprocess.run(["git", "add", "."], cwd=git_repo, check=True)
+    _ = subprocess.run(
         ["git", "commit", "-m", "Add implementation files"], cwd=git_repo, check=True
     )
 
@@ -489,6 +470,9 @@ def another_function():
             tag="#" + " req-Id:",
             need="TREQ_ID_1",
             full_line="#" + " req-Id: TREQ_ID_1",
+            module_name="local_module",
+            hash="",
+            url="",
         ),
         NeedLink(
             file=Path("src/implementation1.py"),
@@ -496,6 +480,9 @@ def another_function():
             tag="#" + " req-Id:",
             need="TREQ_ID_2",
             full_line="#" + " req-Id: TREQ_ID_2",
+            module_name="local_module",
+            hash="",
+            url="",
         ),
         NeedLink(
             file=Path("src/implementation2.py"),
@@ -503,6 +490,9 @@ def another_function():
             tag="#" + " req-Id:",
             need="TREQ_ID_1",
             full_line="#" + " req-Id: TREQ_ID_1",
+            module_name="local_module",
+            hash="",
+            url="",
         ),
     ]
 
@@ -526,18 +516,13 @@ def another_function():
     # Test GitHub link generation
     # Have to change directories in order to ensure that we get the right/any .git file
     os.chdir(Path(git_repo).absolute())
+    metadata = ModuleInfo(name="local_module", hash="", url="")
     for needlink in loaded_links:
-        # ADAPTED: Using get_github_link_from_git
-        github_link = get_github_link_from_git(needlink)
+        github_link = get_github_link(metadata, needlink)
         assert "https://github.com/test-user/test-repo/blob/" in github_link
         assert f"src/{needlink.file.name}#L{needlink.line}" in github_link
 
 
-@add_test_properties(
-    partially_verifies=["tool_req__docs_dd_link_source_code_link"],
-    test_type="requirements-based",
-    derivation_technique="requirements-analysis",
-)
 def test_multiple_commits_hash_consistency(git_repo: Path) -> None:
     """Test that git hash remains consistent and links update properly."""
     # Get initial hash
@@ -545,9 +530,11 @@ def test_multiple_commits_hash_consistency(git_repo: Path) -> None:
 
     # Create and commit a new file
     new_file: Path = git_repo / "new_file.py"
-    new_file.write_text("# New file\nprint('new')")
-    subprocess.run(["git", "add", "."], cwd=git_repo, check=True)
-    subprocess.run(["git", "commit", "-m", "Add new file"], cwd=git_repo, check=True)
+    _ = new_file.write_text("# New file\nprint('new')")
+    _ = subprocess.run(["git", "add", "."], cwd=git_repo, check=True)
+    _ = subprocess.run(
+        ["git", "commit", "-m", "Add new file"], cwd=git_repo, check=True
+    )
 
     # Get new hash
     new_hash = get_current_git_hash(git_repo)
@@ -565,7 +552,462 @@ def test_multiple_commits_hash_consistency(git_repo: Path) -> None:
         full_line="#" + " req-Id: TREQ_ID_1",
     )
 
+    metadata = ModuleInfo(name="local_module", hash="", url="")
     os.chdir(Path(git_repo).absolute())
-    # ADAPTED: Using get_github_link_from_git
-    github_link = get_github_link_from_git(needlink)
+    github_link = get_github_link(metadata, needlink)
     assert new_hash in github_link
+
+
+def test_is_metadata_missing_keys():
+    """Bad path: Dict missing required keys returns False"""
+    incomplete = {"module_name": "test", "hash": "abc"}
+    assert is_metadata(incomplete) is False
+
+
+#            ─────────────────[ NeedLink Dataclass Tests ]─────────────────
+
+
+def test_needlink_to_dict_without_metadata():
+    """to_dict_without_metadata should return NeedLink without metadata"""
+    needlink = NeedLink(
+        file=Path("src/test.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="test_module",
+        url="https://github.com/test/repo",
+        hash="abc123",
+    )
+    result = needlink.to_dict_without_metadata()
+
+    assert "module_name" not in result
+    assert "hash" not in result
+    assert "url" not in result
+    assert result["need"] == "REQ_1"
+    assert result["line"] == 10
+
+
+def test_needlink_to_dict_full():
+    """to_dict_full includes all fields"""
+    needlink = NeedLink(
+        file=Path("src/test.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="test_module",
+        url="https://github.com/test/repo",
+        hash="abc123",
+    )
+    result = needlink.to_dict_full()
+
+    assert result["module_name"] == "test_module"
+    assert result["hash"] == "abc123"
+    assert result["url"] == "https://github.com/test/repo"
+    assert result["need"] == "REQ_1"
+
+
+#            ────────────────────[ JSON Encoder Tests ]────────────────────
+
+
+def test_needlink_encoder_includes_metadata():
+    """Encoder includes all fields"""
+    encoder = NeedLinkEncoder()
+    needlink = NeedLink(
+        file=Path("src/test.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="test_module",
+        url="https://github.com/test/repo",
+        hash="abc123",
+    )
+    result = encoder.default(needlink)
+
+    assert result["module_name"] == "test_module"
+    assert result["hash"] == "abc123"
+    assert result["url"] == "https://github.com/test/repo"
+
+
+# ============================================================================
+# JSON Decoder Tests
+# ============================================================================
+
+
+def test_needlink_decoder_with_all_fields():
+    """Decoder reconstructs NeedLink with all fields"""
+    json_data = {
+        "file": "src/test.py",
+        "line": 10,
+        "tag": "# req-Id:",
+        "need": "REQ_1",
+        "full_line": "# req-Id: REQ_1",
+        "module_name": "test_module",
+        "hash": "abc123",
+        "url": "https://github.com/test/repo",
+    }
+    result = needlink_decoder(json_data)
+
+    assert isinstance(result, NeedLink)
+    assert result.file == Path("src/test.py")
+    assert result.line == 10
+    assert result.module_name == "test_module"
+
+
+def test_needlink_decoder_non_needlink_dict():
+    """Edge case: Non-NeedLink dict is returned unchanged"""
+    json_data = {"some": "other", "data": "structure"}
+    result = needlink_decoder(json_data)
+    assert result == json_data
+
+
+#            ───────────────[ Testing Encoding / Decoding ]─────────────
+
+
+def test_store_and_load_source_code_links(tmp_path: Path):
+    """Happy path: Store and load without metadata"""
+    needlinks = [
+        NeedLink(
+            file=Path("src/impl.py"),
+            line=42,
+            tag="# req-Id:",
+            need="REQ_1",
+            full_line="# req-Id: REQ_1",
+            module_name="mod",
+            url="url",
+            hash="hash",
+        )
+    ]
+
+    test_file = tmp_path / "standard.json"
+    store_source_code_links_json(test_file, needlinks)
+    loaded = load_source_code_links_json(test_file)
+
+    assert len(loaded) == 1
+    assert loaded[0].need == "REQ_1"
+    assert loaded[0].module_name == "mod"
+
+
+def test_load_validates_list_type(tmp_path: Path):
+    """Bad path: Non-list JSON fails validation"""
+    test_file = tmp_path / "not_list.json"
+    _ = test_file.write_text('{"file": "src/test.py", "line": 1}')
+
+    with pytest.raises(AssertionError, match="should be a list"):
+        load_source_code_links_json(test_file)
+
+
+def test_load_validates_all_items_are_needlinks(tmp_path: Path):
+    """Bad path: List with invalid items fails validation"""
+    test_file = tmp_path / "invalid_items.json"
+    _ = test_file.write_text('[{"invalid": "item"}]')
+
+    with pytest.raises(AssertionError, match="should be NeedLink objects"):
+        load_source_code_links_json(test_file)
+
+
+# Adding additional tests to test the metadata stuff (excluding it if wanted)
+
+
+def test_store_and_load_with_metadata(tmp_path: Path):
+    """Happy path: Store with metadata dict and load correctly"""
+    metadata: MetaData = {
+        "module_name": "external_module",
+        "hash": "commit_xyz",
+        "url": "https://github.com/external/repo",
+    }
+    needlinks = [
+        NeedLink(
+            file=Path("src/impl.py"),
+            line=10,
+            tag="# req-Id:",
+            need="REQ_1",
+            full_line="# req-Id: REQ_1",
+            module_name="",  # Will be filled from metadata
+            url="",
+            hash="",
+        ),
+        NeedLink(
+            file=Path("src/impl2.py"),
+            line=20,
+            tag="# req-Id:",
+            need="REQ_2",
+            full_line="# req-Id: REQ_2",
+            module_name="",
+            url="",
+            hash="",
+        ),
+    ]
+
+    test_file = tmp_path / "with_metadata.json"
+    store_source_code_links_with_metadata_json(test_file, metadata, needlinks)
+    loaded = load_source_code_links_with_metadata_json(test_file)
+
+    assert len(loaded) == 2
+    # Verify metadata was applied to all links
+    assert loaded[0].module_name == "external_module"
+    assert loaded[0].hash == "commit_xyz"
+    assert loaded[0].url == "https://github.com/external/repo"
+    assert loaded[1].module_name == "external_module"
+
+
+def test_load_with_metadata_missing_metadata_dict(tmp_path: Path):
+    """Bad path: Loading file without metadata dict raises TypeError"""
+    # Store without metadata (just needlinks)
+    needlinks = [
+        NeedLink(
+            file=Path("src/test.py"),
+            line=1,
+            tag="# req-Id:",
+            need="REQ_1",
+            full_line="# req-Id: REQ_1",
+        )
+    ]
+
+    test_file = tmp_path / "no_metadata.json"
+    store_source_code_links_json(test_file, needlinks)
+
+    # Try to load as if it has metadata
+    with pytest.raises(TypeError, match="you might wanted to call"):
+        load_source_code_links_with_metadata_json(test_file)
+
+
+def test_load_with_metadata_invalid_items_after_metadata(tmp_path: Path):
+    """Bad path: Items after metadata dict are not NeedLinks"""
+    test_file = tmp_path / "bad_items.json"
+    # Manually create invalid JSON
+    _ = test_file.write_text(
+        json.dumps(
+            [{"module_name": "mod", "hash": "h", "url": "u"}, {"invalid": "structure"}]
+        )
+    )
+
+    with pytest.raises(TypeError, match="must decode to NeedLink objects"):
+        load_source_code_links_with_metadata_json(test_file)
+
+
+#            ────────────────[ File Path Resolution Tests ]────────────────
+
+
+def test_load_resolves_relative_path_with_env_var(tmp_path: Path, monkeypatch):
+    """Edge case: Relative path is resolved using BUILD_WORKSPACE_DIRECTORY"""
+    workspace = tmp_path / "workspace"
+    workspace.mkdir()
+
+    needlinks = [
+        NeedLink(
+            file=Path("src/test.py"),
+            line=1,
+            tag="# req-Id:",
+            need="REQ_1",
+            full_line="# req-Id: REQ_1",
+        )
+    ]
+
+    # Store in workspace
+    cache_file = workspace / "cache.json"
+    store_source_code_links_json(cache_file, needlinks)
+
+    # Set env var and load with relative path
+    monkeypatch.setenv("BUILD_WORKSPACE_DIRECTORY", str(workspace))
+    loaded = load_source_code_links_json(Path("cache.json"))
+
+    assert len(loaded) == 1
+    assert loaded[0].need == "REQ_1"
+
+
+def test_load_with_metadata_resolves_relative_path(tmp_path: Path, monkeypatch):
+    """Edge case: load_with_metadata resolves relative paths using env var"""
+    workspace = tmp_path / "workspace"
+    workspace.mkdir()
+
+    metadata: MetaData = {
+        "module_name": "mod",
+        "hash": "h",
+        "url": "u",
+    }
+    needlinks = [
+        NeedLink(
+            file=Path("src/test.py"),
+            line=1,
+            tag="# req-Id:",
+            need="REQ_1",
+            full_line="# req-Id: REQ_1",
+        )
+    ]
+
+    cache_file = workspace / "metadata_cache.json"
+    store_source_code_links_with_metadata_json(cache_file, metadata, needlinks)
+
+    monkeypatch.setenv("BUILD_WORKSPACE_DIRECTORY", str(workspace))
+    loaded = load_source_code_links_with_metadata_json(Path("metadata_cache.json"))
+
+    assert len(loaded) == 1
+    assert loaded[0].module_name == "mod"
+
+
+#            ─────────────────────[ Roundtrip Tests ]───────────────────
+
+
+def test_roundtrip_standard_format(tmp_path: Path):
+    """Happy path: Standard format preserves all data"""
+    needlinks = [
+        NeedLink(
+            file=Path("src/file1.py"),
+            line=10,
+            tag="# req-Id:",
+            need="REQ_A",
+            full_line="# req-Id: REQ_A",
+            module_name="mod_a",
+            url="url_a",
+            hash="hash_a",
+        ),
+        NeedLink(
+            file=Path("src/file2.py"),
+            line=20,
+            tag="# req-Id:",
+            need="REQ_B",
+            full_line="# req-Id: REQ_B",
+            module_name="mod_b",
+            url="url_b",
+            hash="hash_b",
+        ),
+    ]
+
+    test_file = tmp_path / "standard.json"
+    store_source_code_links_json(test_file, needlinks)
+    loaded = load_source_code_links_json(test_file)
+
+    assert len(loaded) == 2
+    assert loaded[0].module_name == "mod_a"
+    assert loaded[1].module_name == "mod_b"
+
+
+def test_roundtrip_metadata_format_applies_metadata(tmp_path: Path):
+    """Happy path: Metadata format applies metadata to all links"""
+    metadata: MetaData = {
+        "module_name": "shared_module",
+        "hash": "shared_hash",
+        "url": "https://github.com/shared/repo",
+    }
+    needlinks = [
+        NeedLink(
+            file=Path("src/f1.py"),
+            line=5,
+            tag="# req-Id:",
+            need="R1",
+            full_line="# req-Id: R1",
+        ),
+        NeedLink(
+            file=Path("src/f2.py"),
+            line=15,
+            tag="# req-Id:",
+            need="R2",
+            full_line="# req-Id: R2",
+        ),
+    ]
+
+    test_file = tmp_path / "with_metadata.json"
+    store_source_code_links_with_metadata_json(test_file, metadata, needlinks)
+    loaded = load_source_code_links_with_metadata_json(test_file)
+
+    assert len(loaded) == 2
+    # Both should have the same metadata applied
+    for link in loaded:
+        assert link.module_name == "shared_module"
+        assert link.hash == "shared_hash"
+        assert link.url == "https://github.com/shared/repo"
+
+
+def test_roundtrip_empty_lists(tmp_path: Path):
+    """Edge case: Empty list can be stored and loaded"""
+    test_file = tmp_path / "empty.json"
+    store_source_code_links_json(test_file, [])
+    loaded = load_source_code_links_json(test_file)
+
+    assert loaded == []
+
+
+#            ──────────────[ JSON Format Verification Tests ]──────────────
+
+
+def test_json_format_with_metadata_has_separate_dict(tmp_path: Path):
+    """Edge case: Verify metadata format has metadata as first element"""
+    metadata: MetaData = {
+        "module_name": "test_mod",
+        "hash": "test_hash",
+        "url": "test_url",
+    }
+    needlink = NeedLink(
+        file=Path("src/test.py"),
+        line=1,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+    )
+
+    test_file = tmp_path / "metadata_format.json"
+    store_source_code_links_with_metadata_json(test_file, metadata, [needlink])
+
+    with open(test_file) as f:
+        raw_json = json.load(f)
+
+    assert isinstance(raw_json, list)
+    assert len(raw_json) == 2  # metadata + 1 needlink
+    # First element should be metadata dict
+    assert raw_json[0]["module_name"] == "test_mod"
+    assert raw_json[0]["hash"] == "test_hash"
+    assert raw_json[0]["url"] == "test_url"
+
+
+#            ───────────[ NeedLink Equality and Hashing Tests ]─────────
+
+
+def test_needlink_equality_same_values():
+    """Happy path: Two NeedLinks with same values are equal"""
+    link1 = NeedLink(
+        file=Path("src/test.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="mod",
+        url="url",
+        hash="hash",
+    )
+    link2 = NeedLink(
+        file=Path("src/test.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="mod",
+        url="url",
+        hash="hash",
+    )
+
+    assert link1 == link2
+    assert hash(link1) == hash(link2)
+
+
+def test_needlink_inequality_different_values():
+    """Edge case: NeedLinks with different values are not equal"""
+    link1 = NeedLink(
+        file=Path("src/test.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+    )
+    link2 = NeedLink(
+        file=Path("src/test.py"),
+        line=20,  # Different line
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+    )
+
+    assert link1 != link2
+    assert hash(link1) != hash(link2)
diff --git a/src/extensions/score_source_code_linker/tests/test_module_source_links.py b/src/extensions/score_source_code_linker/tests/test_module_source_links.py
new file mode 100644
index 000000000..5119c3f0e
--- /dev/null
+++ b/src/extensions/score_source_code_linker/tests/test_module_source_links.py
@@ -0,0 +1,467 @@
+# *******************************************************************************
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+import json
+from pathlib import Path
+
+import pytest
+
+from src.extensions.score_source_code_linker.module_source_links import (
+    ModuleInfo,
+    ModuleSourceLinks,
+    ModuleSourceLinks_JSON_Decoder,
+    ModuleSourceLinks_JSON_Encoder,
+    group_needs_by_module,
+    load_module_source_links_json,
+    store_module_source_links_json,
+)
+from src.extensions.score_source_code_linker.need_source_links import (
+    NeedSourceLinks,
+    SourceCodeLinks,
+)
+from src.extensions.score_source_code_linker.needlinks import NeedLink
+from src.extensions.score_source_code_linker.testlink import DataForTestLink
+
+
+"""
+                        ────────────────INFORMATION───────────────
+
+#              ╭──────────────────────────────────────────────────────────╮
+#              │                  partially generated                     │
+#              │                Human screened and adapted                │
+#              │            though still be aware of mistakes             │
+#              ╰──────────────────────────────────────────────────────────╯
+
+"""
+
+
+#              ╭──────────────────────────────────────────────────────────╮
+#              │                    JSON ENCODER TEST                     │
+#              ╰──────────────────────────────────────────────────────────╯
+
+
+def test_json_encoder_removes_metadata_from_needlink():
+    """Happy path: NeedLink metadata fields are excluded from JSON output"""
+    encoder = ModuleSourceLinks_JSON_Encoder()
+    needlink = NeedLink(
+        file=Path("src/test.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="test_module",
+        url="https://github.com/test/repo",
+        hash="abc123",
+    )
+    result = encoder.default(needlink)
+
+    assert "module_name" not in result
+    assert "url" not in result
+    assert "hash" not in result
+    assert result["need"] == "REQ_1"
+    assert result["line"] == 10
+
+
+def test_json_encoder_removes_metadata_from_testlink():
+    """Happy path: DataForTestLink metadata fields are excluded from JSON output"""
+    encoder = ModuleSourceLinks_JSON_Encoder()
+    testlink = DataForTestLink(
+        name="test_something",
+        file=Path("src/test_file.py"),
+        need="REQ_1",
+        line=20,
+        verify_type="fully",
+        result="passed",
+        result_text="",
+        module_name="test_module",
+        url="https://github.com/test/repo",
+        hash="abc123",
+    )
+    result = encoder.default(testlink)
+
+    assert "module_name" not in result
+    assert "url" not in result
+    assert "hash" not in result
+    assert result["name"] == "test_something"
+    assert result["need"] == "REQ_1"
+
+
+def test_json_encoder_converts_path_to_string():
+    """Happy path: Path objects are converted to strings"""
+    encoder = ModuleSourceLinks_JSON_Encoder()
+    result = encoder.default(Path("/test/path/file.py"))
+    assert result == "/test/path/file.py"
+    assert isinstance(result, str)
+
+
+# ============================================================================
+# JSON Decoder Tests
+# ============================================================================
+
+
+def test_json_decoder_reconstructs_module_source_links():
+    """Happy path: Valid JSON dict is decoded into ModuleSourceLinks"""
+    json_data = {
+        "module": {"name": "test_module", "hash": "hash1", "url": "url1"},
+        "needs": [
+            {
+                "need": "REQ_1",
+                "links": {"CodeLinks": [], "TestLinks": []},
+            }
+        ],
+    }
+    result = ModuleSourceLinks_JSON_Decoder(json_data)
+
+    assert isinstance(result, ModuleSourceLinks)
+    assert result.module.name == "test_module"
+    assert result.module.hash == "hash1"
+    assert result.module.url == "url1"
+    assert len(result.needs) == 1
+
+
+def test_json_decoder_returns_unchanged_for_non_module_dict():
+    """Edge case: Non-ModuleSourceLinks dicts are returned unchanged"""
+    json_data = {"some": "data", "other": "values"}
+    result = ModuleSourceLinks_JSON_Decoder(json_data)
+    assert result == json_data
+
+
+# ============================================================================
+# Store/Load Tests
+# ============================================================================
+
+
+def test_store_and_load_roundtrip(tmp_path: Path):
+    """Happy path: Store and load preserves data correctly"""
+    module = ModuleInfo(name="test_module", hash="hash1", url="url1")
+    needlink = NeedLink(
+        file=Path("src/test.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="test_module",
+        url="url1",
+        hash="hash1",
+    )
+    scl = SourceCodeLinks(
+        need="REQ_1",
+        links=NeedSourceLinks(CodeLinks=[needlink], TestLinks=[]),
+    )
+    module_links = ModuleSourceLinks(module=module, needs=[scl])
+
+    test_file = tmp_path / "test.json"
+    store_module_source_links_json(test_file, [module_links])
+    loaded = load_module_source_links_json(test_file)
+
+    assert len(loaded) == 1
+    assert loaded[0].module.name == "test_module"
+    assert loaded[0].needs[0].need == "REQ_1"
+
+
+def test_store_creates_parent_directories(tmp_path: Path):
+    """Edge case: Parent directories are created if they don't exist"""
+    nested_path = tmp_path / "nested" / "deeply" / "test.json"
+    module = ModuleInfo(name="test", hash="h", url="u")
+    module_links = ModuleSourceLinks(module=module, needs=[])
+
+    store_module_source_links_json(nested_path, [module_links])
+
+    assert nested_path.exists()
+    assert nested_path.parent.exists()
+
+
+def test_load_empty_list(tmp_path: Path):
+    """Edge case: Loading empty list returns empty list"""
+    test_file = tmp_path / "empty.json"
+    store_module_source_links_json(test_file, [])
+
+    loaded = load_module_source_links_json(test_file)
+    assert loaded == []
+
+
+def test_load_validates_is_list(tmp_path: Path):
+    """Bad path: Loading non-list JSON fails validation"""
+    test_file = tmp_path / "not_list.json"
+    test_file.write_text('{"module": {}, "needs": []}')
+
+    with pytest.raises(AssertionError, match="should be a list"):
+        load_module_source_links_json(test_file)
+
+
+def test_load_validates_items_are_correct_type(tmp_path: Path):
+    """Bad path: Loading list with invalid items fails validation"""
+    test_file = tmp_path / "invalid_items.json"
+    test_file.write_text('[{"invalid": "structure"}]')
+
+    with pytest.raises(AssertionError, match="should be ModuleSourceLink objects"):
+        load_module_source_links_json(test_file)
+
+
+# ============================================================================
+# group_needs_by_module Tests
+# ============================================================================
+
+
+def test_group_needs_single_module_with_codelinks():
+    """Happy path: Multiple needs from same module are grouped together"""
+    needlink1 = NeedLink(
+        file=Path("src/file1.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="shared_module",
+        url="https://github.com/test/repo",
+        hash="hash1",
+    )
+    needlink2 = NeedLink(
+        file=Path("src/file2.py"),
+        line=20,
+        tag="# req-Id:",
+        need="REQ_2",
+        full_line="# req-Id: REQ_2",
+        module_name="shared_module",
+        url="https://github.com/test/repo",
+        hash="hash1",
+    )
+
+    scl1 = SourceCodeLinks(
+        need="REQ_1", links=NeedSourceLinks(CodeLinks=[needlink1], TestLinks=[])
+    )
+    scl2 = SourceCodeLinks(
+        need="REQ_2", links=NeedSourceLinks(CodeLinks=[needlink2], TestLinks=[])
+    )
+
+    result = group_needs_by_module([scl1, scl2])
+
+    assert len(result) == 1
+    assert result[0].module.name == "shared_module"
+    assert result[0].module.hash == "hash1"
+    assert len(result[0].needs) == 2
+    assert len(result[0].needs[0].links.CodeLinks) == 1
+    assert len(result[0].needs[1].links.CodeLinks) == 1
+
+
+def test_group_needs_multiple_modules():
+    """Happy path: Needs from different modules create separate groups"""
+    needlink_a = NeedLink(
+        file=Path("src/a.py"),
+        line=10,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="module_a",
+        url="https://github.com/a/repo",
+        hash="hash_a",
+    )
+    needlink_b = NeedLink(
+        file=Path("src/b.py"),
+        line=20,
+        tag="# req-Id:",
+        need="REQ_2",
+        full_line="# req-Id: REQ_2",
+        module_name="module_b",
+        url="https://github.com/b/repo",
+        hash="hash_b",
+    )
+
+    scl1 = SourceCodeLinks(
+        need="REQ_1", links=NeedSourceLinks(CodeLinks=[needlink_a], TestLinks=[])
+    )
+    scl2 = SourceCodeLinks(
+        need="REQ_2", links=NeedSourceLinks(CodeLinks=[needlink_b], TestLinks=[])
+    )
+
+    result = group_needs_by_module([scl1, scl2])
+
+    assert len(result) == 2
+    assert result[0].module.name == "module_a"
+    assert result[0].module.hash == "hash_a"
+    assert result[0].module.url == "https://github.com/a/repo"
+    assert result[1].module.name == "module_b"
+    assert result[1].module.hash == "hash_b"
+    assert result[1].module.url == "https://github.com/b/repo"
+
+
+def test_group_needs_with_testlinks_only():
+    """Happy path: Needs with only test links (no code links) are grouped correctly"""
+    testlink = DataForTestLink(
+        name="test_feature",
+        file=Path("tests/test.py"),
+        need="REQ_1",
+        line=15,
+        verify_type="fully",
+        result="passed",
+        result_text="",
+        module_name="test_module",
+        url="https://github.com/test/repo",
+        hash="hash1",
+    )
+    testlink2 = DataForTestLink(
+        name="test_feature",
+        file=Path("tests/test2.py"),
+        need="REQ_10",
+        line=153,
+        verify_type="partially",
+        result="passed",
+        result_text="",
+        module_name="test_module",
+        url="https://github.com/test/repo",
+        hash="hash1",
+    )
+
+    scl = SourceCodeLinks(
+        need="REQ_1",
+        links=NeedSourceLinks(CodeLinks=[], TestLinks=[testlink]),
+    )
+    scl2 = SourceCodeLinks(
+        need="REQ_10",
+        links=NeedSourceLinks(CodeLinks=[], TestLinks=[testlink2]),
+    )
+
+    result = group_needs_by_module([scl, scl2])
+
+    assert len(result) == 1
+    assert result[0].module.name == "test_module"
+    assert len(result[0].needs) == 2
+    needs = [x.need for x in result[0].needs]
+    assert "REQ_1" in needs
+    assert "REQ_10" in needs
+    assert len(result[0].needs[0].links.TestLinks) == 1
+    assert len(result[0].needs[1].links.TestLinks) == 1
+
+
+def test_group_needs_with_testlinks_different_modules():
+    """Testing Testlinks grouping for different modules"""
+    testlink = DataForTestLink(
+        name="test_feature",
+        file=Path("tests/test.py"),
+        need="REQ_1",
+        line=15,
+        verify_type="fully",
+        result="passed",
+        result_text="",
+        module_name="module_a",
+        url="https://github.com/test_a/repo_a",
+        hash="hash_a",
+    )
+    testlink2 = DataForTestLink(
+        name="test_feature",
+        file=Path("tests/test3.py"),
+        need="REQ_10",
+        line=153,
+        verify_type="partially",
+        result="passed",
+        result_text="",
+        module_name="module_b",
+        url="https://github.com/test_b/repo_b",
+        hash="hash_b",
+    )
+
+    scl = SourceCodeLinks(
+        need="REQ_1",
+        links=NeedSourceLinks(CodeLinks=[], TestLinks=[testlink]),
+    )
+    scl2 = SourceCodeLinks(
+        need="REQ_10",
+        links=NeedSourceLinks(CodeLinks=[], TestLinks=[testlink2]),
+    )
+
+    result = group_needs_by_module([scl, scl2])
+
+    assert len(result) == 2
+    assert result[0].module.name == "module_a"
+    assert result[0].module.hash == "hash_a"
+    assert result[0].module.url == "https://github.com/test_a/repo_a"
+    assert result[1].module.name == "module_b"
+    assert result[1].module.hash == "hash_b"
+    assert result[1].module.url == "https://github.com/test_b/repo_b"
+
+
+def test_group_needs_empty_list():
+    """Edge case: Empty list returns empty result"""
+    result = group_needs_by_module([])
+    assert result == []
+
+
+def test_group_needs_skips_needs_without_links():
+    """
+    Edge case: Needs with no code or test links are skipped
+    This should normally never even be possible to get
+    to this function. Though we should test what happens
+    """
+    scl_with_links = SourceCodeLinks(
+        need="REQ_1",
+        links=NeedSourceLinks(
+            CodeLinks=[
+                NeedLink(
+                    file=Path("src/test.py"),
+                    line=10,
+                    tag="# req-Id:",
+                    need="REQ_1",
+                    full_line="# req-Id: REQ_1",
+                    module_name="module_a",
+                    url="url1",
+                    hash="hash1",
+                )
+            ],
+            TestLinks=[],
+        ),
+    )
+    scl_without_links = SourceCodeLinks(
+        need="REQ_2",
+        links=NeedSourceLinks(CodeLinks=[], TestLinks=[]),
+    )
+
+    result = group_needs_by_module([scl_with_links, scl_without_links])
+
+    assert len(result) == 1
+    assert result[0].needs[0].need == "REQ_1"
+    assert result[0].needs[0].links.CodeLinks[0].full_line == "# req-Id: REQ_1"
+
+
+def test_group_needs_mixed_codelinks_and_testlinks():
+    """Happy path: Needs with both code and test links are handled correctly"""
+    needlink = NeedLink(
+        file=Path("src/impl.py"),
+        line=5,
+        tag="# req-Id:",
+        need="REQ_1",
+        full_line="# req-Id: REQ_1",
+        module_name="module_a",
+        url="https://github.com/test/repo",
+        hash="hash1",
+    )
+    testlink = DataForTestLink(
+        name="test_impl",
+        file=Path("tests/test_impl.py"),
+        need="REQ_1",
+        line=10,
+        verify_type="fully",
+        result="passed",
+        result_text="",
+        module_name="module_a",
+        url="https://github.com/test/repo",
+        hash="hash1",
+    )
+
+    scl = SourceCodeLinks(
+        need="REQ_1",
+        links=NeedSourceLinks(CodeLinks=[needlink], TestLinks=[testlink]),
+    )
+
+    result = group_needs_by_module([scl])
+
+    assert len(result) == 1
+    assert len(result[0].needs[0].links.CodeLinks) == 1
+    assert len(result[0].needs[0].links.TestLinks) == 1
diff --git a/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py b/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
new file mode 100644
index 000000000..60c217c25
--- /dev/null
+++ b/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
@@ -0,0 +1,456 @@
+# *******************************************************************************
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+import contextlib
+import json
+import os
+import shutil
+import subprocess
+from collections.abc import Callable
+from pathlib import Path
+
+import pytest
+from pytest import TempPathFactory
+from sphinx.testing.util import SphinxTestApp
+
+from src.extensions.score_source_code_linker.module_source_links import (
+    ModuleInfo,
+    ModuleSourceLinks_JSON_Decoder,
+    load_module_source_links_json,
+)
+from src.helper_lib import find_ws_root
+
+
+"""
+                        ────────────────INFORMATION───────────────
+
+#              ╭──────────────────────────────────────────────────────────╮
+#              │                  boiler plate generated                  │
+#              │                Human screened and adapted                │
+#              │            though still be aware of mistakes             │
+#              ╰──────────────────────────────────────────────────────────╯
+
+"""
+
+
+@pytest.fixture(scope="session")
+def sphinx_base_dir(tmp_path_factory: TempPathFactory) -> Path:
+    return tmp_path_factory.mktemp("test_module_links_repo")
+
+
+@pytest.fixture(scope="session")
+def git_repo_setup(sphinx_base_dir: Path) -> Path:
+    """Creating git repo, to make testing possible"""
+    repo_path = sphinx_base_dir
+    _ = subprocess.run(["git", "init"], cwd=repo_path, check=True)
+    _ = subprocess.run(
+        ["git", "config", "user.name", "Test User"], cwd=repo_path, check=True
+    )
+    _ = subprocess.run(
+        ["git", "config", "user.email", "test@example.com"], cwd=repo_path, check=True
+    )
+    _ = subprocess.run(
+        ["git", "remote", "add", "origin", "https://github.com/testorg/modulerepo.git"],
+        cwd=repo_path,
+        check=True,
+    )
+    os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(repo_path)
+    return repo_path
+
+
+@pytest.fixture(scope="session")
+def create_demo_files(sphinx_base_dir: Path, git_repo_setup: Path):
+    repo_path = sphinx_base_dir
+
+    # Create source files
+    source_dir = repo_path / "src"
+    source_dir.mkdir()
+
+    _ = (source_dir / "module_a_impl.py").write_text(make_module_a_source())
+    _ = (source_dir / "module_b_impl.py").write_text(make_module_b_source())
+
+    # Create docs directory
+    docs_dir = repo_path / "docs"
+    docs_dir.mkdir()
+    _ = (docs_dir / "index.rst").write_text(basic_needs())
+    _ = (docs_dir / "conf.py").write_text(basic_conf())
+
+    # Create test.xml files
+    bazel_testdir = repo_path / "bazel-testlogs" / "src"
+    bazel_testdir.mkdir(parents=True)
+    _ = (bazel_testdir / "test.xml").write_text(make_test_xml())
+
+    curr_dir = Path(__file__).absolute().parent
+    _ = shutil.copyfile(
+        curr_dir / "expected_module_grouped.json",
+        repo_path / ".expected_module_grouped.json",
+    )
+
+    # Commit everything
+    _ = subprocess.run(["git", "add", "."], cwd=repo_path, check=True)
+    _ = subprocess.run(
+        ["git", "commit", "-m", "Initial commit with module test files"],
+        cwd=repo_path,
+        check=True,
+    )
+
+
+def make_module_a_source():
+    return """
+# Module A implementation
+# req-Id: MOD_REQ_1
+def module_a_function():
+    pass
+
+# req-Id: MOD_REQ_2
+class ModuleAClass:
+    pass
+"""
+
+
+def make_module_b_source():
+    return """
+# Module B implementation
+# req-Id: MOD_REQ_1
+def module_b_function():
+    pass
+
+# req-Id: MOD_REQ_3
+def another_module_b_function():
+    pass
+"""
+
+
+def make_test_xml():
+    return """
+<testsuites>
+  <testsuite name="ModuleTests" tests="2" failures="0" errors="0" time="0.123">
+    <testcase name="test_module_a" classname="" file="src/test_module_a.py" line="10" time="0.056">
+      <properties>
+        <property name="FullyVerifies" value="MOD_REQ_1"/>
+        <property name="TestType" value="unit-test"/>
+        <property name="DerivationTechnique" value="requirements-analysis"/>
+      </properties>
+    </testcase>
+    <testcase name="test_module_b" classname="" file="src/test_module_b.py" line="20" time="0.067">
+      <properties>
+        <property name="PartiallyVerifies" value="MOD_REQ_3"/>
+        <property name="TestType" value="integration-test"/>
+        <property name="DerivationTechnique" value="design-analysis"/>
+      </properties>
+    </testcase>
+  </testsuite>
+</testsuites>
+"""
+
+
+def basic_conf():
+    return """
+extensions = [
+    "sphinx_needs",
+    "score_source_code_linker",
+]
+needs_types = [
+    dict(
+        directive="mod_req",
+        title="Module Requirement",
+        prefix="MOD_REQ_",
+        color="#BFD8D2",
+        style="node",
+    ),
+]
+needs_extra_options = ["source_code_link", "testlink"]
+needs_extra_links = [{
+      "option": "partially_verifies",
+      "incoming": "paritally_verified_by",
+      "outgoing": "paritally_verifies",
+   },
+   {
+      "option": "fully_verifies",
+      "incoming": "fully_verified_by",
+      "outgoing": "fully_verifies",
+   }]
+"""
+
+
+def basic_needs():
+    return """
+MODULE TESTING
+==============
+
+.. mod_req:: Module Requirement 1
+   :id: MOD_REQ_1
+   :status: valid
+
+.. mod_req:: Module Requirement 2
+   :id: MOD_REQ_2
+   :status: open
+
+.. mod_req:: Module Requirement 3
+   :id: MOD_REQ_3
+   :status: open
+"""
+
+
+@pytest.fixture()
+def sphinx_app_setup(
+    sphinx_base_dir: Path, create_demo_files: None, git_repo_setup: Path
+) -> Callable[[], SphinxTestApp]:
+    def _create_app():
+        base_dir = sphinx_base_dir
+        docs_dir = base_dir / "docs"
+
+        original_cwd = None
+        with contextlib.suppress(FileNotFoundError):
+            original_cwd = os.getcwd()
+
+        os.chdir(base_dir)
+        try:
+            return SphinxTestApp(
+                freshenv=True,
+                srcdir=docs_dir,
+                confdir=docs_dir,
+                outdir=sphinx_base_dir / "out",
+                buildername="html",
+                warningiserror=True,
+            )
+        finally:
+            if original_cwd is not None:
+                with contextlib.suppress(FileNotFoundError, OSError):
+                    os.chdir(original_cwd)
+
+    return _create_app
+
+
+def test_module_grouped_cache_generated(
+    sphinx_app_setup: Callable[[], SphinxTestApp],
+    sphinx_base_dir: Path,
+    git_repo_setup: Path,
+    create_demo_files: None,
+):
+    """Happy path: Module grouped cache file is generated after Sphinx build"""
+    app = sphinx_app_setup()
+    try:
+        os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
+        app.build()
+
+        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
+        assert module_cache.exists(), "Module grouped cache was not created"
+
+        # Load and verify structure
+        loaded = load_module_source_links_json(module_cache)
+        assert isinstance(loaded, list)
+        assert len(loaded) > 0, "Module cache should contain at least one module"
+
+        # Verify each item is a ModuleSourceLinks
+        for item in loaded:
+            assert hasattr(item, "module")
+            assert hasattr(item, "needs")
+            assert isinstance(item.module, ModuleInfo)
+
+    finally:
+        app.cleanup()
+
+
+def test_module_grouping_preserves_metadata(
+    sphinx_app_setup: Callable[[], SphinxTestApp],
+    sphinx_base_dir: Path,
+    git_repo_setup: Path,
+    create_demo_files: None,
+):
+    """Happy path: Module metadata (name, hash, url) is preserved in cache"""
+    app = sphinx_app_setup()
+    try:
+        os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
+        app.build()
+
+        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
+        loaded = load_module_source_links_json(module_cache)
+
+        # Verify that each module has proper metadata
+        for module_links in loaded:
+            assert module_links.module.name is not None
+            assert isinstance(module_links.module.name, str)
+            # Hash and URL might be empty strings for local module
+            assert module_links.module.hash is not None
+            assert module_links.module.url is not None
+
+    finally:
+        app.cleanup()
+
+
+def test_module_grouping_multiple_needs_per_module(
+    sphinx_app_setup: Callable[[], SphinxTestApp],
+    sphinx_base_dir: Path,
+    git_repo_setup: Path,
+    create_demo_files: None,
+):
+    """Happy path: Multiple needs from same module are grouped together"""
+    app = sphinx_app_setup()
+    try:
+        os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
+        app.build()
+
+        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
+        loaded = load_module_source_links_json(module_cache)
+
+        # Find the local_module (should have all 3 requirements)
+        local_module = None
+        for m in loaded:
+            if m.module.name == "local_module":
+                local_module = m
+                break
+
+        assert local_module is not None, "local_module not found in grouped cache"
+
+        # All 3 MOD_REQ should be in this module
+        need_ids = {need.need for need in local_module.needs}
+        assert (
+            "MOD_REQ_1" in need_ids
+            or "MOD_REQ_2" in need_ids
+            or "MOD_REQ_3" in need_ids
+        )
+
+    finally:
+        app.cleanup()
+
+
+def test_module_cache_json_format(
+    sphinx_app_setup: Callable[[], SphinxTestApp],
+    sphinx_base_dir: Path,
+    git_repo_setup: Path,
+    create_demo_files: None,
+):
+    """Edge case: Module cache JSON has correct structure and excludes metadata from links"""
+    app = sphinx_app_setup()
+    try:
+        os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
+        app.build()
+
+        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
+
+        # Load as raw JSON to check structure
+        with open(module_cache) as f:
+            raw_json = json.load(f)
+
+        assert isinstance(raw_json, list)
+        assert len(raw_json) > 0
+
+        # Check first module structure
+        first_module = raw_json[0]
+        assert "module" in first_module
+        assert "needs" in first_module
+        assert "name" in first_module["module"]
+        assert "hash" in first_module["module"]
+        assert "url" in first_module["module"]
+
+        # Check that needlinks don't have metadata
+        if first_module["needs"]:
+            first_need = first_module["needs"][0]
+            if "links" in first_need:
+                if first_need["links"].get("CodeLinks"):
+                    codelink = first_need["links"]["CodeLinks"][0]
+                    assert "module_name" not in codelink, (
+                        "CodeLinks should not contain module_name metadata"
+                    )
+                    assert "hash" not in codelink, (
+                        "CodeLinks should not contain hash metadata"
+                    )
+                    assert "url" not in codelink, (
+                        "CodeLinks should not contain url metadata"
+                    )
+
+    finally:
+        app.cleanup()
+
+
+def test_module_cache_rebuilds_when_missing(
+    sphinx_app_setup: Callable[[], SphinxTestApp],
+    sphinx_base_dir: Path,
+    git_repo_setup: Path,
+    create_demo_files: None,
+):
+    """Edge case: Module cache is regenerated if deleted"""
+    app = sphinx_app_setup()
+    try:
+        os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
+        app.build()
+
+        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
+        assert module_cache.exists()
+
+        # Delete the cache
+        module_cache.unlink()
+        assert not module_cache.exists()
+
+        # Build again - should regenerate
+        app2 = sphinx_app_setup()
+        app2.build()
+
+        assert module_cache.exists(), "Cache should be regenerated on rebuild"
+
+        # Verify it's valid
+        loaded = load_module_source_links_json(module_cache)
+        assert len(loaded) > 0
+
+        app2.cleanup()
+    finally:
+        app.cleanup()
+
+
+def test_module_grouping_with_golden_file(
+    sphinx_app_setup: Callable[[], SphinxTestApp],
+    sphinx_base_dir: Path,
+    git_repo_setup: Path,
+    create_demo_files: None,
+):
+    """Happy path: Generated module cache matches expected golden file"""
+    app = sphinx_app_setup()
+    try:
+        os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
+        app.build()
+
+        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
+        expected_file = sphinx_base_dir / ".expected_module_grouped.json"
+
+        assert module_cache.exists()
+        assert expected_file.exists(), "Golden file not found"
+
+        with open(module_cache) as f1:
+            actual = json.load(f1, object_hook=ModuleSourceLinks_JSON_Decoder)
+        with open(expected_file) as f2:
+            expected = json.load(f2, object_hook=ModuleSourceLinks_JSON_Decoder)
+
+        assert len(actual) == len(expected), (
+            f"Module count mismatch. Actual: {len(actual)}, Expected: {len(expected)}"
+        )
+
+        # Compare module by module
+        actual_by_name = {m.module.name: m for m in actual}
+        expected_by_name = {m.module.name: m for m in expected}
+
+        assert set(actual_by_name.keys()) == set(expected_by_name.keys()), (
+            f"Module names don't match. "
+            f"Actual: {set(actual_by_name.keys())}, "
+            f"Expected: {set(expected_by_name.keys())}"
+        )
+
+        for module_name in actual_by_name:
+            actual_module = actual_by_name[module_name]
+            expected_module = expected_by_name[module_name]
+
+            assert actual_module.module.hash == expected_module.module.hash
+            assert actual_module.module.url == expected_module.module.url
+            assert len(actual_module.needs) == len(expected_module.needs)
+
+    finally:
+        app.cleanup()
diff --git a/src/extensions/score_source_code_linker/tests/test_testlink.py b/src/extensions/score_source_code_linker/tests/test_testlink.py
index de6811183..c134c5ad6 100644
--- a/src/extensions/score_source_code_linker/tests/test_testlink.py
+++ b/src/extensions/score_source_code_linker/tests/test_testlink.py
@@ -10,8 +10,14 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 # *******************************************************************************
+
+# ╓                                                          ╖
+# ║ Some portions generated by Co-Pilot                      ║
+# ╙                                                          ╜
+
 import json
 from pathlib import Path
+import pytest
 
 # This depends on the `attribute_plugin` in our tooling repository
 from attribute_plugin import add_test_properties  # type: ignore[import-untyped]
@@ -23,6 +29,10 @@
     DataOfTestCase,
     load_test_xml_parsed_json,
     store_test_xml_parsed_json,
+    store_data_of_test_case_json,
+    load_data_of_test_case_json,
+    DataOfTestCase_JSON_Encoder,
+    DataOfTestCase_JSON_Decoder,
 )
 
 
@@ -174,3 +184,221 @@ def test_store_and_load_testlinks_roundtrip(tmp_path: Path):
     assert reloaded == links
     for link in reloaded:
         assert isinstance(link, DataForTestLink)
+
+
+def test_datafortestlink_to_dict_full():
+    """Cover line 85: to_dict_full includes all fields"""
+    link = DataForTestLink(
+        name="test_full",
+        file=Path("src/test.py"),
+        line=10,
+        need="REQ_1",
+        verify_type="fully",
+        result="passed",
+        result_text="All good",
+        module_name="test_module",
+        hash="abc123",
+        url="https://github.com/test/repo",
+    )
+    result = link.to_dict_full()
+
+    assert result["module_name"] == "test_module"
+    assert result["hash"] == "abc123"
+    assert result["url"] == "https://github.com/test/repo"
+    assert result["name"] == "test_full"
+
+
+def test_datafortestlink_equality_with_non_testlink():
+    """Cover line 69: __eq__ with non-DataForTestLink returns NotImplemented"""
+    link = DataForTestLink(
+        name="test",
+        file=Path("src/test.py"),
+        line=10,
+        need="REQ_1",
+        verify_type="fully",
+        result="passed",
+    )
+
+    result = link.__eq__("not a testlink")
+    assert result is NotImplemented
+
+
+#            ──────────────────────[ DataOfTestCase ]──────────────────────
+
+
+def test_dataoftestcase_check_verifies_fields_missing_both():
+    """Cover lines 200-206: check_verifies_fields returns False when both are None"""
+    case = DataOfTestCase(
+        name="TC_Missing",
+        file="src/test.py",
+        line="10",
+        result="passed",
+        TestType="unit",
+        DerivationTechnique="manual",
+        result_text="",
+        PartiallyVerifies=None,
+        FullyVerifies=None,
+        module_name="mod",
+        hash="h",
+        url="u",
+    )
+
+    assert case.check_verifies_fields() is False
+
+
+def test_dataoftestcase_is_valid_fails_on_none_field():
+    """Cover lines 232-238: is_valid returns False when required field is None"""
+    case = DataOfTestCase(
+        name="TC_Invalid",
+        file=None,  # Missing required field
+        line="10",
+        result="passed",
+        TestType="unit",
+        DerivationTechnique="manual",
+        result_text="",
+        PartiallyVerifies="REQ_1",
+        module_name="mod",
+        hash="h",
+        url="u",
+    )
+
+    assert case.is_valid() is False
+
+
+def test_dataoftestcase_get_test_links_returns_empty_when_invalid():
+    """Cover line 245: get_test_links returns [] when is_valid is False"""
+    case = DataOfTestCase(
+        name="TC_Invalid",
+        file=None,  # Invalid
+        line="10",
+        result="passed",
+        TestType="unit",
+        DerivationTechnique="manual",
+        PartiallyVerifies="REQ_1",
+    )
+
+    links = case.get_test_links()
+    assert links == []
+
+
+def test_dataoftestcase_decoder_valid_dict():
+    """Cover lines 314-324: Decoder reconstructs DataOfTestCase from valid dict"""
+    json_data = {
+        "name": "TC_01",
+        "file": "src/test.py",
+        "line": "10",
+        "result": "passed",
+        "TestType": "unit",
+        "DerivationTechnique": "manual",
+        "result_text": "Good",
+        "PartiallyVerifies": "REQ_1",
+        "FullyVerifies": "REQ_2",
+        "module_name": "mod",
+        "hash": "h",
+        "url": "u",
+    }
+    result = DataOfTestCase_JSON_Decoder(json_data)
+
+    assert isinstance(result, DataOfTestCase)
+    assert result.name == "TC_01"
+    assert result.file == "src/test.py"
+
+
+def test_dataoftestcase_decoder_non_testcase_dict():
+    """Cover line 326: Decoder returns dict unchanged for non-TestCase data"""
+    json_data = {"some": "other", "data": "here"}
+    result = DataOfTestCase_JSON_Decoder(json_data)
+    assert result == json_data
+
+
+def test_store_and_load_data_of_test_case_roundtrip(tmp_path: Path):
+    """Cover lines 376-386: store and load DataOfTestCase roundtrip"""
+    test_cases = [
+        DataOfTestCase(
+            name="TC_A",
+            file="src/a.py",
+            line="5",
+            result="passed",
+            TestType="unit",
+            DerivationTechnique="manual",
+            result_text="OK",
+            PartiallyVerifies="REQ_A",
+            FullyVerifies=None,
+            module_name="mod_a",
+            hash="hash_a",
+            url="url_a",
+        ),
+        DataOfTestCase(
+            name="TC_B",
+            file="src/b.py",
+            line="15",
+            result="failed",
+            TestType="integration",
+            DerivationTechnique="auto",
+            result_text="Failed",
+            PartiallyVerifies=None,
+            FullyVerifies="REQ_B",
+            module_name="mod_b",
+            hash="hash_b",
+            url="url_b",
+        ),
+    ]
+
+    test_file = tmp_path / "test_cases.json"
+    store_data_of_test_case_json(test_file, test_cases)
+    loaded = load_data_of_test_case_json(test_file)
+
+    assert len(loaded) == 2
+    assert loaded[0].name == "TC_A"
+    assert loaded[1].name == "TC_B"
+
+
+def test_load_data_of_test_case_validates_list(tmp_path: Path):
+    """Cover line 380: Load validates result is a list"""
+    test_file = tmp_path / "not_list.json"
+    test_file.write_text('{"name": "TC_01"}')
+
+    with pytest.raises(AssertionError, match="should be a list"):
+        _ = load_data_of_test_case_json(test_file)
+
+
+def test_load_data_of_test_case_validates_items(tmp_path: Path):
+    """Cover line 383: Load validates all items are DataOfTestCase"""
+    test_file = tmp_path / "invalid_items.json"
+    test_file.write_text('[{"invalid": "structure"}]')
+
+    with pytest.raises(AssertionError, match="should be TestCaseNeed objects"):
+        _ = load_data_of_test_case_json(test_file)
+
+
+def test_dataoftestcase_encoder_fallback():
+    """Cover line 299: Encoder falls back to parent for unknown types"""
+    encoder = DataOfTestCase_JSON_Encoder()
+
+    # This should trigger the super().default() call
+    with pytest.raises(TypeError):
+        _ = encoder.default(object())
+
+
+def test_datafortestlink_encoder_fallback():
+    """Cover line 103: DataForTestLink encoder falls back to parent for unknown types"""
+    from src.extensions.score_source_code_linker.testlink import (
+        DataForTestLink_JSON_Encoder,
+    )
+
+    encoder = DataForTestLink_JSON_Encoder()
+
+    # This should trigger the super().default() call
+    with pytest.raises(TypeError):
+        _ = encoder.default(object())
+
+
+def test_datafortestlink_decoder_non_testlink_dict():
+    """Cover line 132: DataForTestLink decoder returns dict unchanged"""
+    from src.extensions.score_source_code_linker.testlink import (
+        DataForTestLink_JSON_Decoder,
+    )
+
+    json_data = {"random": "data", "other": "stuff"}
+    result = DataForTestLink_JSON_Decoder(json_data)
+    assert result == json_data

From 7cda52e70d4201881f9a1622d160b184d200155a Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 10:23:53 +0100
Subject: [PATCH 17/34] Remove debug print statements

---
 .../generate_source_code_links_json.py                       | 5 -----
 .../score_source_code_linker/module_source_links.py          | 3 ---
 2 files changed, 8 deletions(-)

diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index 87e4aa554..dd0080450 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -58,11 +58,6 @@ def _extract_references_from_file(
         external/score_docs_as_code+/src/extensions/score_source_code_linker/testlink.py
     #FILE PATH NAME:  testlink.py
     """
-    print("ROOT: ", root)
-    print("FILE_PATH: ", file_path)
-    print("FILE_PATH_NAME: ", file_path_name)
-    output = subprocess.run(["ls", "-la", f"{root}"], capture_output=True)
-    print(output)
     assert root.is_absolute(), "Root path must be absolute"
     assert not file_path_name.is_absolute(), "File path must be relative to the root"
     # assert file_path.is_relative_to(root), (
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index cc4e39165..103959bb6 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -113,9 +113,6 @@ def load_module_source_links_json(file: Path) -> list[ModuleSourceLinks]:
     assert isinstance(links, list), (
         "The ModuleSourceLink json should be a list of ModuleSourceLink objects."
     )
-    for link in links:
-        if not isinstance(link, ModuleSourceLinks):
-            print(f"Link not module_sourcelink: {link}")
     assert all(isinstance(link, ModuleSourceLinks) for link in links), (
         "All items in module source link cache should be ModuleSourceLink objects."
     )

From 1d74ad06022eae2b1c94b9e819344e824d37d7f0 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 10:58:47 +0100
Subject: [PATCH 18/34] Fixed linter warnings

---
 .../generate_source_code_links_json.py        |  1 -
 .../module_source_links.py                    | 10 +++---
 .../need_source_links.py                      |  2 +-
 .../score_source_code_linker/needlinks.py     |  6 ++--
 .../score_source_code_linker/testlink.py      |  2 +-
 .../tests/test_codelink.py                    | 25 +++++++--------
 .../tests/test_helpers.py                     | 12 +++----
 .../tests/test_module_source_links.py         |  8 +++--
 .../test_module_source_links_integration.py   | 32 ++++++++++---------
 .../test_source_code_link_integration.py      |  4 +--
 .../tests/test_testlink.py                    |  9 +++---
 11 files changed, 55 insertions(+), 56 deletions(-)

diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index dd0080450..cf9457c82 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -19,7 +19,6 @@
 
 import os
 from pathlib import Path
-import subprocess
 
 from sphinx_needs.logging import get_logger
 
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index 103959bb6..a24e279ac 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -40,7 +40,7 @@ class ModuleSourceLinks:
 
 
 class ModuleSourceLinks_JSON_Encoder(json.JSONEncoder):
-    def default(self, o: object):
+    def default(self, o: object) -> str | dict[str, Any]:
         if isinstance(o, Path):
             return str(o)
         # We do not want to save the metadata inside the codelink or testlink
@@ -48,9 +48,9 @@ def default(self, o: object):
         # (hash, module_name, url)
         if isinstance(o, NeedLink | DataForTestLink):
             return o.to_dict_without_metadata()
-        # We need to split this up, otherwise the nested 
-        # dictionaries won't get split up and we will not 
-        # run into the 'to_dict_without_metadata' as 
+        # We need to split this up, otherwise the nested
+        # dictionaries won't get split up and we will not
+        # run into the 'to_dict_without_metadata' as
         # everything will be converted to a normal dictionary
         if isinstance(o, ModuleSourceLinks):
             return {
@@ -92,7 +92,7 @@ def ModuleSourceLinks_JSON_Decoder(
 def store_module_source_links_json(
     file: Path, source_code_links: list[ModuleSourceLinks]
 ):
-    # After `rm -rf _build` or on clean builds the directory does not exist, 
+    # After `rm -rf _build` or on clean builds the directory does not exist,
     # so we need to create it. We create any folder that might be missing
     file.parent.mkdir(exist_ok=True, parents=True)
     with open(file, "w") as f:
diff --git a/src/extensions/score_source_code_linker/need_source_links.py b/src/extensions/score_source_code_linker/need_source_links.py
index a0b79d796..9a5d3c29e 100644
--- a/src/extensions/score_source_code_linker/need_source_links.py
+++ b/src/extensions/score_source_code_linker/need_source_links.py
@@ -82,7 +82,7 @@ def SourceCodeLinks_JSON_Decoder(d: dict[str, Any]) -> SourceCodeLinks | dict[st
 def store_source_code_links_combined_json(
     file: Path, source_code_links: list[SourceCodeLinks]
 ):
-    # After `rm -rf _build` or on clean builds the directory does not exist, 
+    # After `rm -rf _build` or on clean builds the directory does not exist,
     # so we need to create it. We create any folder that might be missing
     file.parent.mkdir(exist_ok=True, parents=True)
     with open(file, "w") as f:
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index 588c95fef..52f424830 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -59,7 +59,7 @@ def __hash__(self):
             )
         )
 
-    def __eq__(self, other):
+    def __eq__(self, other: Any):
         if not isinstance(other, NeedLink):
             return NotImplemented
         return (
@@ -140,7 +140,7 @@ def store_source_code_links_with_metadata_json(
     """
     payload: list[object] = [metadata, *needlist]
 
-    # After `rm -rf _build` or on clean builds the directory does not exist, 
+    # After `rm -rf _build` or on clean builds the directory does not exist,
     # so we need to create it. We create any folder that might be missing
     file.parent.mkdir(exist_ok=True,parents=True)
     with open(file, "w", encoding="utf-8") as f:
@@ -153,7 +153,7 @@ def store_source_code_links_json(file: Path, needlist: list[NeedLink]) -> None:
       [ needlink1, needlink2, ... ]
     """
 
-    # After `rm -rf _build` or on clean builds the directory does not exist, 
+    # After `rm -rf _build` or on clean builds the directory does not exist,
     # so we need to create it. We create any folder that might be missing
     file.parent.mkdir(exist_ok=True, parents=True)
     with open(file, "w", encoding="utf-8") as f:
diff --git a/src/extensions/score_source_code_linker/testlink.py b/src/extensions/score_source_code_linker/testlink.py
index 170bd0ad4..0dc1557f3 100644
--- a/src/extensions/score_source_code_linker/testlink.py
+++ b/src/extensions/score_source_code_linker/testlink.py
@@ -64,7 +64,7 @@ def __hash__(self):
             )
         )
 
-    def __eq__(self, other):
+    def __eq__(self, other: Any):
         if not isinstance(other, DataForTestLink):
             return NotImplemented
         return (
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index e65adcb08..85277ef93 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -17,7 +17,6 @@
 
 import json
 import os
-from pkgutil import ModuleInfo
 import subprocess
 import tempfile
 from collections.abc import Generator
@@ -29,8 +28,6 @@
 
 # S-CORE plugin to allow for properties/attributes in xml
 # Enables Testlinking
-from attribute_plugin import add_test_properties  # type: ignore[import-untyped]
-
 from sphinx_needs.data import NeedsInfoType, NeedsMutable
 from sphinx_needs.need_item import (
     NeedItem,
@@ -43,11 +40,11 @@
     get_cache_filename,
     group_by_need,
 )
-
+from src.extensions.score_source_code_linker.helpers import (
+    get_github_link,
+)
 from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
-
 from src.extensions.score_source_code_linker.needlinks import (
-    DefaultNeedLink,
     MetaData,
     NeedLink,
     NeedLinkEncoder,
@@ -62,11 +59,6 @@
     get_current_git_hash,
 )
 
-from src.extensions.score_source_code_linker.helpers import (
-    get_github_link_from_git,
-    get_github_link,
-)
-
 
 def test_need(**kwargs: Any) -> NeedItem:
     """Convenience function to create a NeedItem object with some defaults."""
@@ -626,6 +618,7 @@ def test_needlink_encoder_includes_metadata():
     )
     result = encoder.default(needlink)
 
+    assert isinstance(result, dict)
     assert result["module_name"] == "test_module"
     assert result["hash"] == "abc123"
     assert result["url"] == "https://github.com/test/repo"
@@ -638,7 +631,7 @@ def test_needlink_encoder_includes_metadata():
 
 def test_needlink_decoder_with_all_fields():
     """Decoder reconstructs NeedLink with all fields"""
-    json_data = {
+    json_data: dict[str, Any] = {
         "file": "src/test.py",
         "line": 10,
         "tag": "# req-Id:",
@@ -791,7 +784,9 @@ def test_load_with_metadata_invalid_items_after_metadata(tmp_path: Path):
 #            ────────────────[ File Path Resolution Tests ]────────────────
 
 
-def test_load_resolves_relative_path_with_env_var(tmp_path: Path, monkeypatch):
+def test_load_resolves_relative_path_with_env_var(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+):
     """Edge case: Relative path is resolved using BUILD_WORKSPACE_DIRECTORY"""
     workspace = tmp_path / "workspace"
     workspace.mkdir()
@@ -818,7 +813,9 @@ def test_load_resolves_relative_path_with_env_var(tmp_path: Path, monkeypatch):
     assert loaded[0].need == "REQ_1"
 
 
-def test_load_with_metadata_resolves_relative_path(tmp_path: Path, monkeypatch):
+def test_load_with_metadata_resolves_relative_path(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+):
     """Edge case: load_with_metadata resolves relative paths using env var"""
     workspace = tmp_path / "workspace"
     workspace.mkdir()
diff --git a/src/extensions/score_source_code_linker/tests/test_helpers.py b/src/extensions/score_source_code_linker/tests/test_helpers.py
index 593253583..9ad02bc39 100644
--- a/src/extensions/score_source_code_linker/tests/test_helpers.py
+++ b/src/extensions/score_source_code_linker/tests/test_helpers.py
@@ -12,16 +12,12 @@
 # *******************************************************************************
 import json
 import os
-from pathlib import Path
+import subprocess
 import tempfile
 from collections.abc import Generator
+from pathlib import Path
 
 import pytest
-import subprocess
-
-from src.helper_lib import get_current_git_hash 
-from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
-from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink
 
 from src.extensions.score_source_code_linker.helpers import (
     get_github_link,
@@ -29,7 +25,9 @@
     parse_info_from_known_good,
     parse_module_name_from_path,
 )
-
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
+from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink
+from src.helper_lib import get_current_git_hash
 
 #              ╭──────────────────────────────────────────────────────────╮
 #              │          Tests for parse_module_name_from_path           │
diff --git a/src/extensions/score_source_code_linker/tests/test_module_source_links.py b/src/extensions/score_source_code_linker/tests/test_module_source_links.py
index 5119c3f0e..85acca4a6 100644
--- a/src/extensions/score_source_code_linker/tests/test_module_source_links.py
+++ b/src/extensions/score_source_code_linker/tests/test_module_source_links.py
@@ -10,8 +10,8 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 # *******************************************************************************
-import json
 from pathlib import Path
+from typing import Any
 
 import pytest
 
@@ -31,7 +31,6 @@
 from src.extensions.score_source_code_linker.needlinks import NeedLink
 from src.extensions.score_source_code_linker.testlink import DataForTestLink
 
-
 """
                         ────────────────INFORMATION───────────────
 
@@ -64,6 +63,7 @@ def test_json_encoder_removes_metadata_from_needlink():
     )
     result = encoder.default(needlink)
 
+    assert isinstance(result, dict)
     assert "module_name" not in result
     assert "url" not in result
     assert "hash" not in result
@@ -88,6 +88,8 @@ def test_json_encoder_removes_metadata_from_testlink():
     )
     result = encoder.default(testlink)
 
+
+    assert isinstance(result, dict)
     assert "module_name" not in result
     assert "url" not in result
     assert "hash" not in result
@@ -110,7 +112,7 @@ def test_json_encoder_converts_path_to_string():
 
 def test_json_decoder_reconstructs_module_source_links():
     """Happy path: Valid JSON dict is decoded into ModuleSourceLinks"""
-    json_data = {
+    json_data: dict[str,Any] = {
         "module": {"name": "test_module", "hash": "hash1", "url": "url1"},
         "needs": [
             {
diff --git a/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py b/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
index 60c217c25..d209a7d5c 100644
--- a/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
@@ -27,8 +27,6 @@
     ModuleSourceLinks_JSON_Decoder,
     load_module_source_links_json,
 )
-from src.helper_lib import find_ws_root
-
 
 """
                         ────────────────INFORMATION───────────────
@@ -131,6 +129,7 @@ def another_module_b_function():
 
 
 def make_test_xml():
+    # ruff: noqa: E501 (start)
     return """
 <testsuites>
   <testsuite name="ModuleTests" tests="2" failures="0" errors="0" time="0.123">
@@ -151,6 +150,7 @@ def make_test_xml():
   </testsuite>
 </testsuites>
 """
+    # ruff: noqa: E501 (finish)
 
 
 def basic_conf():
@@ -330,7 +330,10 @@ def test_module_cache_json_format(
     git_repo_setup: Path,
     create_demo_files: None,
 ):
-    """Edge case: Module cache JSON has correct structure and excludes metadata from links"""
+    """
+    Module cache JSON has correct
+    structure and excludes metadata from links
+    """
     app = sphinx_app_setup()
     try:
         os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
@@ -356,18 +359,17 @@ def test_module_cache_json_format(
         # Check that needlinks don't have metadata
         if first_module["needs"]:
             first_need = first_module["needs"][0]
-            if "links" in first_need:
-                if first_need["links"].get("CodeLinks"):
-                    codelink = first_need["links"]["CodeLinks"][0]
-                    assert "module_name" not in codelink, (
-                        "CodeLinks should not contain module_name metadata"
-                    )
-                    assert "hash" not in codelink, (
-                        "CodeLinks should not contain hash metadata"
-                    )
-                    assert "url" not in codelink, (
-                        "CodeLinks should not contain url metadata"
-                    )
+            if "links" in first_need and first_need["links"].get("CodeLinks"):
+                codelink = first_need["links"]["CodeLinks"][0]
+                assert "module_name" not in codelink, (
+                    "CodeLinks should not contain module_name metadata"
+                )
+                assert "hash" not in codelink, (
+                    "CodeLinks should not contain hash metadata"
+                )
+                assert "url" not in codelink, (
+                    "CodeLinks should not contain url metadata"
+                )
 
     finally:
         app.cleanup()
diff --git a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
index e49d856da..b6e1ded0b 100644
--- a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
@@ -25,8 +25,9 @@
 from sphinx.testing.util import SphinxTestApp
 from sphinx_needs.data import SphinxNeedsData
 
-from src.extensions.score_source_code_linker.needlinks import NeedLink
+from src.extensions.score_source_code_linker.helpers import get_github_link
 from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
+from src.extensions.score_source_code_linker.needlinks import NeedLink
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
     DataForTestLink_JSON_Decoder,
@@ -38,7 +39,6 @@
     SourceCodeLinks_TEST_JSON_Decoder,
 )
 from src.helper_lib import find_ws_root, get_github_base_url
-from src.extensions.score_source_code_linker.helpers import get_github_link
 
 
 @pytest.fixture(scope="session")
diff --git a/src/extensions/score_source_code_linker/tests/test_testlink.py b/src/extensions/score_source_code_linker/tests/test_testlink.py
index c134c5ad6..1916f5c0d 100644
--- a/src/extensions/score_source_code_linker/tests/test_testlink.py
+++ b/src/extensions/score_source_code_linker/tests/test_testlink.py
@@ -17,6 +17,7 @@
 
 import json
 from pathlib import Path
+
 import pytest
 
 # This depends on the `attribute_plugin` in our tooling repository
@@ -27,12 +28,12 @@
     DataForTestLink_JSON_Decoder,
     DataForTestLink_JSON_Encoder,
     DataOfTestCase,
+    DataOfTestCase_JSON_Decoder,
+    DataOfTestCase_JSON_Encoder,
+    load_data_of_test_case_json,
     load_test_xml_parsed_json,
-    store_test_xml_parsed_json,
     store_data_of_test_case_json,
-    load_data_of_test_case_json,
-    DataOfTestCase_JSON_Encoder,
-    DataOfTestCase_JSON_Decoder,
+    store_test_xml_parsed_json,
 )
 
 

From ddfa34c6b6f5b31d6a602bec8f2752779183dc81 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 11:02:46 +0100
Subject: [PATCH 19/34] Fix copyright year

---
 src/extensions/score_source_code_linker/tests/test_codelink.py  | 2 +-
 src/extensions/score_source_code_linker/tests/test_testlink.py  | 2 +-
 .../score_source_code_linker/tests/test_xml_parser.py           | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 85277ef93..26a9b9058 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -1,5 +1,5 @@
 # *******************************************************************************
-# Copyright (c) 2025-2026 Contributors to the Eclipse Foundation
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
 #
 # See the NOTICE file(s) distributed with this work for additional
 # information regarding copyright ownership.
diff --git a/src/extensions/score_source_code_linker/tests/test_testlink.py b/src/extensions/score_source_code_linker/tests/test_testlink.py
index 1916f5c0d..7e49b8983 100644
--- a/src/extensions/score_source_code_linker/tests/test_testlink.py
+++ b/src/extensions/score_source_code_linker/tests/test_testlink.py
@@ -1,5 +1,5 @@
 # *******************************************************************************
-# Copyright (c) 2025-2026 Contributors to the Eclipse Foundation
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
 #
 # See the NOTICE file(s) distributed with this work for additional
 # information regarding copyright ownership.
diff --git a/src/extensions/score_source_code_linker/tests/test_xml_parser.py b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
index c283aada5..76958122b 100644
--- a/src/extensions/score_source_code_linker/tests/test_xml_parser.py
+++ b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
@@ -1,5 +1,5 @@
 # *******************************************************************************
-# Copyright (c) 2025-2026 Contributors to the Eclipse Foundation
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
 #
 # See the NOTICE file(s) distributed with this work for additional
 # information regarding copyright ownership.

From 6230c47a4704153e25742219e991a3d4420195a2 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 11:49:45 +0100
Subject: [PATCH 20/34] Fix scl finding test needs

---
 .../module_source_links.py                    |   4 +-
 .../tests/expected_module_grouped.json        |  16 +-
 .../tests/test_codelink.py                    |  76 +++++-----
 .../tests/test_module_source_links.py         | 138 +++++++++++++++---
 .../test_module_source_links_integration.py   |   8 +-
 5 files changed, 167 insertions(+), 75 deletions(-)

diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index a24e279ac..1521f6868 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -39,7 +39,7 @@ class ModuleSourceLinks:
     needs: list[SourceCodeLinks] = field(default_factory=list)
 
 
-class ModuleSourceLinks_JSON_Encoder(json.JSONEncoder):
+class ModuleSourceLinks_TEST_JSON_Encoder(json.JSONEncoder):
     def default(self, o: object) -> str | dict[str, Any]:
         if isinstance(o, Path):
             return str(o)
@@ -99,7 +99,7 @@ def store_module_source_links_json(
         json.dump(
             source_code_links,
             f,
-            cls=ModuleSourceLinks_JSON_Encoder,
+            cls=ModuleSourceLinks_TEST_JSON_Encoder,
             indent=2,
             ensure_ascii=False,
         )
diff --git a/src/extensions/score_source_code_linker/tests/expected_module_grouped.json b/src/extensions/score_source_code_linker/tests/expected_module_grouped.json
index fd1ebfd79..ef91784bf 100644
--- a/src/extensions/score_source_code_linker/tests/expected_module_grouped.json
+++ b/src/extensions/score_source_code_linker/tests/expected_module_grouped.json
@@ -13,16 +13,16 @@
             {
               "file": "src/module_a_impl.py",
               "line": 3,
-              "tag": "# req-Id:",
+              "tag": "#-----req-Id:",
               "need": "MOD_REQ_1",
-              "full_line": "# req-Id: MOD_REQ_1"
+              "full_line": "#-----req-Id: MOD_REQ_1"
             },
             {
               "file": "src/module_b_impl.py",
               "line": 3,
-              "tag": "# req-Id:",
+              "tag": "#-----req-Id:",
               "need": "MOD_REQ_1",
-              "full_line": "# req-Id: MOD_REQ_1"
+              "full_line": "#-----req-Id: MOD_REQ_1"
             }
           ],
           "TestLinks": [
@@ -45,9 +45,9 @@
             {
               "file": "src/module_a_impl.py",
               "line": 7,
-              "tag": "# req-Id:",
+              "tag": "#-----req-Id:",
               "need": "MOD_REQ_2",
-              "full_line": "# req-Id: MOD_REQ_2"
+              "full_line": "#-----req-Id: MOD_REQ_2"
             }
           ],
           "TestLinks": []
@@ -60,9 +60,9 @@
             {
               "file": "src/module_b_impl.py",
               "line": 7,
-              "tag": "# req-Id:",
+              "tag": "#-----req-Id:",
               "need": "MOD_REQ_3",
-              "full_line": "# req-Id: MOD_REQ_3"
+              "full_line": "#-----req-Id: MOD_REQ_3"
             }
           ],
           "TestLinks": [
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 26a9b9058..1328e1fa2 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -564,9 +564,9 @@ def test_needlink_to_dict_without_metadata():
     needlink = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#"+" req-Id: REQ_1",
         module_name="test_module",
         url="https://github.com/test/repo",
         hash="abc123",
@@ -585,9 +585,9 @@ def test_needlink_to_dict_full():
     needlink = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
         module_name="test_module",
         url="https://github.com/test/repo",
         hash="abc123",
@@ -609,9 +609,9 @@ def test_needlink_encoder_includes_metadata():
     needlink = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
         module_name="test_module",
         url="https://github.com/test/repo",
         hash="abc123",
@@ -634,9 +634,9 @@ def test_needlink_decoder_with_all_fields():
     json_data: dict[str, Any] = {
         "file": "src/test.py",
         "line": 10,
-        "tag": "# req-Id:",
+        "tag":"#" + " req-Id:",
         "need": "REQ_1",
-        "full_line": "# req-Id: REQ_1",
+        "full_line": "#" +" req-Id: REQ_1",
         "module_name": "test_module",
         "hash": "abc123",
         "url": "https://github.com/test/repo",
@@ -665,9 +665,9 @@ def test_store_and_load_source_code_links(tmp_path: Path):
         NeedLink(
             file=Path("src/impl.py"),
             line=42,
-            tag="# req-Id:",
+            tag="#" + " req-Id:",
             need="REQ_1",
-            full_line="# req-Id: REQ_1",
+            full_line="#" + " req-Id: REQ_1",
             module_name="mod",
             url="url",
             hash="hash",
@@ -715,9 +715,9 @@ def test_store_and_load_with_metadata(tmp_path: Path):
         NeedLink(
             file=Path("src/impl.py"),
             line=10,
-            tag="# req-Id:",
+            tag="#" + " req-Id:",
             need="REQ_1",
-            full_line="# req-Id: REQ_1",
+            full_line="#"+" req-Id: REQ_1",
             module_name="",  # Will be filled from metadata
             url="",
             hash="",
@@ -725,9 +725,9 @@ def test_store_and_load_with_metadata(tmp_path: Path):
         NeedLink(
             file=Path("src/impl2.py"),
             line=20,
-            tag="# req-Id:",
+            tag="#" + " req-Id:",
             need="REQ_2",
-            full_line="# req-Id: REQ_2",
+            full_line="#"+" req-Id: REQ_2",
             module_name="",
             url="",
             hash="",
@@ -753,9 +753,9 @@ def test_load_with_metadata_missing_metadata_dict(tmp_path: Path):
         NeedLink(
             file=Path("src/test.py"),
             line=1,
-            tag="# req-Id:",
+            tag="#" + " req-Id:",
             need="REQ_1",
-            full_line="# req-Id: REQ_1",
+            full_line="#" +" req-Id: REQ_1",
         )
     ]
 
@@ -795,9 +795,9 @@ def test_load_resolves_relative_path_with_env_var(
         NeedLink(
             file=Path("src/test.py"),
             line=1,
-            tag="# req-Id:",
+            tag="#"+" req-Id:",
             need="REQ_1",
-            full_line="# req-Id: REQ_1",
+            full_line="#"+" req-Id: REQ_1",
         )
     ]
 
@@ -829,9 +829,9 @@ def test_load_with_metadata_resolves_relative_path(
         NeedLink(
             file=Path("src/test.py"),
             line=1,
-            tag="# req-Id:",
+            tag="#"+"  req-Id:",
             need="REQ_1",
-            full_line="# req-Id: REQ_1",
+            full_line="#"+" req-Id: REQ_1",
         )
     ]
 
@@ -854,9 +854,9 @@ def test_roundtrip_standard_format(tmp_path: Path):
         NeedLink(
             file=Path("src/file1.py"),
             line=10,
-            tag="# req-Id:",
+            tag="#"+" req-Id:",
             need="REQ_A",
-            full_line="# req-Id: REQ_A",
+            full_line="#"+" req-Id: REQ_A",
             module_name="mod_a",
             url="url_a",
             hash="hash_a",
@@ -864,9 +864,9 @@ def test_roundtrip_standard_format(tmp_path: Path):
         NeedLink(
             file=Path("src/file2.py"),
             line=20,
-            tag="# req-Id:",
+            tag="#"+" req-Id:",
             need="REQ_B",
-            full_line="# req-Id: REQ_B",
+            full_line="#"+" req-Id: REQ_B",
             module_name="mod_b",
             url="url_b",
             hash="hash_b",
@@ -893,16 +893,16 @@ def test_roundtrip_metadata_format_applies_metadata(tmp_path: Path):
         NeedLink(
             file=Path("src/f1.py"),
             line=5,
-            tag="# req-Id:",
+            tag="#"+" req-Id:",
             need="R1",
-            full_line="# req-Id: R1",
+            full_line="#"+" req-Id: R1",
         ),
         NeedLink(
             file=Path("src/f2.py"),
             line=15,
-            tag="# req-Id:",
+            tag="#"+" req-Id:",
             need="R2",
-            full_line="# req-Id: R2",
+            full_line="#"+" req-Id: R2",
         ),
     ]
 
@@ -940,9 +940,9 @@ def test_json_format_with_metadata_has_separate_dict(tmp_path: Path):
     needlink = NeedLink(
         file=Path("src/test.py"),
         line=1,
-        tag="# req-Id:",
+        tag="#"+" req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#"+" req-Id: REQ_1",
     )
 
     test_file = tmp_path / "metadata_format.json"
@@ -967,9 +967,9 @@ def test_needlink_equality_same_values():
     link1 = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#"+" req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#"+" req-Id: REQ_1",
         module_name="mod",
         url="url",
         hash="hash",
@@ -977,9 +977,9 @@ def test_needlink_equality_same_values():
     link2 = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#"+" req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#"+" req-Id: REQ_1",
         module_name="mod",
         url="url",
         hash="hash",
@@ -994,16 +994,16 @@ def test_needlink_inequality_different_values():
     link1 = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#"+" req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#"+" req-Id: REQ_1",
     )
     link2 = NeedLink(
         file=Path("src/test.py"),
         line=20,  # Different line
-        tag="# req-Id:",
+        tag="#"+" req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#"+" req-Id: REQ_1",
     )
 
     assert link1 != link2
diff --git a/src/extensions/score_source_code_linker/tests/test_module_source_links.py b/src/extensions/score_source_code_linker/tests/test_module_source_links.py
index 85acca4a6..0da7594b8 100644
--- a/src/extensions/score_source_code_linker/tests/test_module_source_links.py
+++ b/src/extensions/score_source_code_linker/tests/test_module_source_links.py
@@ -12,6 +12,8 @@
 # *******************************************************************************
 from pathlib import Path
 from typing import Any
+import json
+from dataclasses import asdict
 
 import pytest
 
@@ -19,7 +21,6 @@
     ModuleInfo,
     ModuleSourceLinks,
     ModuleSourceLinks_JSON_Decoder,
-    ModuleSourceLinks_JSON_Encoder,
     group_needs_by_module,
     load_module_source_links_json,
     store_module_source_links_json,
@@ -48,15 +49,107 @@
 #              ╰──────────────────────────────────────────────────────────╯
 
 
+def encode_comment(s: str) -> str:
+    return s.replace(" ", "-----", 1)
+
+
+def decode_comment(s: str) -> str:
+    return s.replace("-----", " ", 1)
+
+
+def SourceCodeLinks_TEST_JSON_Decoder(
+    d: dict[str, Any],
+) -> SourceCodeLinks | dict[str, Any]:
+    if "need" in d and "links" in d:
+        links = d["links"]
+
+        # Decode CodeLinks
+        code_links = []
+        for cl in links.get("CodeLinks", []):
+            # Decode the tag and full_line fields
+            if "tag" in cl:
+                cl["tag"] = decode_comment(cl["tag"])
+            if "full_line" in cl:
+                cl["full_line"] = decode_comment(cl["full_line"])
+            code_links.append(NeedLink(**cl))
+
+        # Decode TestLinks
+        return SourceCodeLinks(
+            need=d["need"],
+            links=NeedSourceLinks(
+                CodeLinks=code_links,
+                TestLinks=[DataForTestLink(**tl) for tl in links.get("TestLinks", [])],
+            ),
+        )
+    return d
+
+
+class ModuleSourceLinks_TEST_JSON_Encoder(json.JSONEncoder):
+    def default(self, o: object) -> str | dict[str, Any]:
+        if isinstance(o, Path):
+            return str(o)
+        # We do not want to save the metadata inside the codelink or testlink
+        # As we save this already in a structure above it
+        # (hash, module_name, url)
+        if isinstance(o, NeedLink | DataForTestLink):
+            d = o.to_dict_without_metadata()
+            tag = d.get("tag", "")
+            full_line = d.get("full_line", "")
+            assert isinstance(tag, str)
+            assert isinstance(full_line, str)
+            d["tag"] = encode_comment(tag)
+            d["full_line"] = encode_comment(full_line)
+            return d
+        # We need to split this up, otherwise the nested
+        # dictionaries won't get split up and we will not
+        # run into the 'to_dict_without_metadata' as
+        # everything will be converted to a normal dictionary
+        if isinstance(o, ModuleSourceLinks):
+            return {
+                "module": asdict(o.module),
+                "needs": o.needs,  # Let the encoder handle the list
+            }
+        if isinstance(o, SourceCodeLinks):
+            return {
+                "need": o.need,
+                "links": o.links,
+            }
+        if isinstance(o, NeedSourceLinks):
+            return {
+                "CodeLinks": o.CodeLinks,
+                "TestLinks": o.TestLinks,
+            }
+        return super().default(o)
+
+
+def ModuleSourceLinks_TEST_JSON_Decoder(
+    d: dict[str, Any],
+) -> ModuleSourceLinks | dict[str, Any]:
+    if "module" in d and "needs" in d:
+        module = d["module"]
+        needs = d["needs"]
+        return ModuleSourceLinks(
+            module=ModuleInfo(
+                name=module.get("name"),
+                hash=module.get("hash"),
+                url=module.get("url"),
+            ),
+            # We know this can only be list[SourceCodeLinks] and nothing else
+            # Therefore => we ignore the type error here
+            needs=[SourceCodeLinks_TEST_JSON_Decoder(need) for need in needs],  # type: ignore
+        )
+    return d
+
+
 def test_json_encoder_removes_metadata_from_needlink():
     """Happy path: NeedLink metadata fields are excluded from JSON output"""
-    encoder = ModuleSourceLinks_JSON_Encoder()
+    encoder = ModuleSourceLinks_TEST_JSON_Encoder()
     needlink = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
         module_name="test_module",
         url="https://github.com/test/repo",
         hash="abc123",
@@ -73,7 +166,7 @@ def test_json_encoder_removes_metadata_from_needlink():
 
 def test_json_encoder_removes_metadata_from_testlink():
     """Happy path: DataForTestLink metadata fields are excluded from JSON output"""
-    encoder = ModuleSourceLinks_JSON_Encoder()
+    encoder = ModuleSourceLinks_TEST_JSON_Encoder()
     testlink = DataForTestLink(
         name="test_something",
         file=Path("src/test_file.py"),
@@ -88,7 +181,6 @@ def test_json_encoder_removes_metadata_from_testlink():
     )
     result = encoder.default(testlink)
 
-
     assert isinstance(result, dict)
     assert "module_name" not in result
     assert "url" not in result
@@ -99,7 +191,7 @@ def test_json_encoder_removes_metadata_from_testlink():
 
 def test_json_encoder_converts_path_to_string():
     """Happy path: Path objects are converted to strings"""
-    encoder = ModuleSourceLinks_JSON_Encoder()
+    encoder = ModuleSourceLinks_TEST_JSON_Encoder()
     result = encoder.default(Path("/test/path/file.py"))
     assert result == "/test/path/file.py"
     assert isinstance(result, str)
@@ -112,7 +204,7 @@ def test_json_encoder_converts_path_to_string():
 
 def test_json_decoder_reconstructs_module_source_links():
     """Happy path: Valid JSON dict is decoded into ModuleSourceLinks"""
-    json_data: dict[str,Any] = {
+    json_data: dict[str, Any] = {
         "module": {"name": "test_module", "hash": "hash1", "url": "url1"},
         "needs": [
             {
@@ -148,9 +240,9 @@ def test_store_and_load_roundtrip(tmp_path: Path):
     needlink = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
         module_name="test_module",
         url="url1",
         hash="hash1",
@@ -219,9 +311,9 @@ def test_group_needs_single_module_with_codelinks():
     needlink1 = NeedLink(
         file=Path("src/file1.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
         module_name="shared_module",
         url="https://github.com/test/repo",
         hash="hash1",
@@ -229,9 +321,9 @@ def test_group_needs_single_module_with_codelinks():
     needlink2 = NeedLink(
         file=Path("src/file2.py"),
         line=20,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_2",
-        full_line="# req-Id: REQ_2",
+        full_line="#" + " req-Id: REQ_2",
         module_name="shared_module",
         url="https://github.com/test/repo",
         hash="hash1",
@@ -259,9 +351,9 @@ def test_group_needs_multiple_modules():
     needlink_a = NeedLink(
         file=Path("src/a.py"),
         line=10,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
         module_name="module_a",
         url="https://github.com/a/repo",
         hash="hash_a",
@@ -269,9 +361,9 @@ def test_group_needs_multiple_modules():
     needlink_b = NeedLink(
         file=Path("src/b.py"),
         line=20,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_2",
-        full_line="# req-Id: REQ_2",
+        full_line="#" + " req-Id: REQ_2",
         module_name="module_b",
         url="https://github.com/b/repo",
         hash="hash_b",
@@ -409,9 +501,9 @@ def test_group_needs_skips_needs_without_links():
                 NeedLink(
                     file=Path("src/test.py"),
                     line=10,
-                    tag="# req-Id:",
+                    tag="#" + " req-Id:",
                     need="REQ_1",
-                    full_line="# req-Id: REQ_1",
+                    full_line="#" + " req-Id: REQ_1",
                     module_name="module_a",
                     url="url1",
                     hash="hash1",
@@ -429,7 +521,7 @@ def test_group_needs_skips_needs_without_links():
 
     assert len(result) == 1
     assert result[0].needs[0].need == "REQ_1"
-    assert result[0].needs[0].links.CodeLinks[0].full_line == "# req-Id: REQ_1"
+    assert result[0].needs[0].links.CodeLinks[0].full_line == "#" + " req-Id: REQ_1"
 
 
 def test_group_needs_mixed_codelinks_and_testlinks():
@@ -437,9 +529,9 @@ def test_group_needs_mixed_codelinks_and_testlinks():
     needlink = NeedLink(
         file=Path("src/impl.py"),
         line=5,
-        tag="# req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="# req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
         module_name="module_a",
         url="https://github.com/test/repo",
         hash="hash1",
diff --git a/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py b/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
index d209a7d5c..895a8eb56 100644
--- a/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
@@ -105,11 +105,11 @@ def create_demo_files(sphinx_base_dir: Path, git_repo_setup: Path):
 def make_module_a_source():
     return """
 # Module A implementation
-# req-Id: MOD_REQ_1
+# """+"""req-Id: MOD_REQ_1
 def module_a_function():
     pass
 
-# req-Id: MOD_REQ_2
+# """+"""req-Id: MOD_REQ_2
 class ModuleAClass:
     pass
 """
@@ -118,11 +118,11 @@ class ModuleAClass:
 def make_module_b_source():
     return """
 # Module B implementation
-# req-Id: MOD_REQ_1
+# """+"""req-Id: MOD_REQ_1
 def module_b_function():
     pass
 
-# req-Id: MOD_REQ_3
+# """+"""req-Id: MOD_REQ_3
 def another_module_b_function():
     pass
 """

From a8ce766ad5ac6fa027041a7a5d14363d7d8e09c7 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 11:50:28 +0100
Subject: [PATCH 21/34] Formatting

---
 .../tests/test_module_source_links.py                         | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/extensions/score_source_code_linker/tests/test_module_source_links.py b/src/extensions/score_source_code_linker/tests/test_module_source_links.py
index 0da7594b8..293cdc76e 100644
--- a/src/extensions/score_source_code_linker/tests/test_module_source_links.py
+++ b/src/extensions/score_source_code_linker/tests/test_module_source_links.py
@@ -10,10 +10,10 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 # *******************************************************************************
-from pathlib import Path
-from typing import Any
 import json
 from dataclasses import asdict
+from pathlib import Path
+from typing import Any
 
 import pytest
 

From 740b019460819e30a8ed2250954a04b2a011a826 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 15:00:57 +0100
Subject: [PATCH 22/34] Fix: Testlinks didn't clean filepath properly

---
 .../tests/test_xml_parser.py                  | 52 +++++++++++++++++++
 .../score_source_code_linker/xml_parser.py    | 42 ++++++++++++++-
 2 files changed, 92 insertions(+), 2 deletions(-)

diff --git a/src/extensions/score_source_code_linker/tests/test_xml_parser.py b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
index 76958122b..b33000121 100644
--- a/src/extensions/score_source_code_linker/tests/test_xml_parser.py
+++ b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
@@ -10,6 +10,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 # *******************************************************************************
+# Some portions generated by CoPilot
 """
 Tests for the xml_parser.py file.
 Keep in mind that this is with the 'assertions' inside xml_parser disabled so far.
@@ -326,3 +327,54 @@ def test_short_hash_consistency_and_format():
     assert h1 == h2
     assert h1.isalpha()
     assert len(h1) == 5
+
+
+#            ─────────────[ Boilerplate generated by CoPilot ]─────────────
+
+
+def test_clean_test_file_name_local_path():
+    raw_path = Path(
+        "/home/root/folder/docs-as-code/bazel-testlogs/src/extensions/score_any_folder/score_any_folder_tests/test.xml"
+    )
+    result = xml_parser.clean_test_file_name(raw_path)
+    assert result == Path(
+        "src/extensions/score_any_folder/score_any_folder_tests/test.xml"
+    )
+
+
+def test_clean_test_file_name_combo_path():
+    raw_path = Path(
+        "/root/bazel-testlogs/external/score_docs_as_code+/src/extensions/score_any_folder/score_any_folder_tests/test.xml"
+    )
+    result = xml_parser.clean_test_file_name(raw_path)
+    assert result == Path(
+        "external/score_docs_as_code+/src/extensions/score_any_folder/score_any_folder_tests/test.xml"
+    )
+
+
+def test_clean_test_file_name_tests_report_path():
+    raw_path = Path("/some/path/tests-report/test-report/unit/test_module.xml")
+    result = xml_parser.clean_test_file_name(raw_path)
+    assert result == Path("unit/test_module.xml")
+
+
+def test_clean_test_file_name_nested_bazel_testlogs():
+    raw_path = Path("/deeply/nested/bazel-testlogs/bazel-testlogs/final/path.xml")
+    result = xml_parser.clean_test_file_name(raw_path)
+    assert result == Path("final/path.xml")
+
+
+def test_clean_test_file_name_invalid_path_raises_error():
+    raw_path = Path("/invalid/path/without/markers/test.xml")
+    with pytest.raises(
+        ValueError, match="Filepath does not have 'bazel-testlogs' nor 'test-report'"
+    ):
+        xml_parser.clean_test_file_name(raw_path)
+
+
+def test_clean_test_file_name_empty_path_raises_error():
+    raw_path = Path("")
+    with pytest.raises(
+        ValueError, match="Filepath does not have 'bazel-testlogs' nor 'test-report'"
+    ):
+        xml_parser.clean_test_file_name(raw_path)
diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index 7347429ce..af80c76be 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -53,7 +53,31 @@
 logger.setLevel("DEBUG")
 
 
-def get_metadata_from_test_path(filepath: Path) -> MetaData:
+def clean_test_file_name(raw_filepath: Path) -> Path:
+    """
+    incoming path:
+    `local`
+        <root>/docs-as-code/bazel-testlogs/src/extensions/score_any_folder/score_any_folder_tests/test.xml
+    `combo`
+        <root>/bazel-testlogs/external/score_docs_as_code+/src/extensions/score_any_folder/score_any_folder_tests/test.xml
+
+    outgoing path:
+    `local`
+        src/extensions/score_any_folder/score_any_folder_tests/test.xml
+    `combo`
+        external/score_docs_as_code+/src/extensions/score_any_folder/score_any_folder_tests/test.xml
+    """
+    if "bazel-testlogs" in str(raw_filepath):
+        return Path(str(raw_filepath).split("bazel-testlogs/")[-1])
+    elif "tests-report" in str(raw_filepath):
+        return Path(str(raw_filepath).split("test-report/")[-1])
+    else:
+        raise ValueError(
+            f"Filepath does not have 'bazel-testlogs' nor 'test-report'. Filepath: {raw_filepath}"
+        )
+
+
+def get_metadata_from_test_path(raw_filepath: Path) -> MetaData:
     """
     Will parse out the metadata from the testpath.
     If test is local then the metadata will be:
@@ -70,9 +94,23 @@ def get_metadata_from_test_path(filepath: Path) -> MetaData:
           "hash": "c1207676afe6cafd25c35d420e73279a799515d8",
           "url": "https://github.com/eclipse-score/docs-as-code"
 
+    The file name passed into here is:
+
+    For combo builds: something like:
+    <root path>/bazel-testlogs/external/score_docs_as_code+/
+    src/extensions/score_any_folder/score_any_folder_tests/test.xml
+
+    For local builds:
+    <root path>/bazel-testlogs/src/extensions/score_any_folder/score_any_folder_tests/test.xml
+
+    Therefore will we 'clean' it before passing it to the parse_module func.
+    Removing everything up to and including 'bazel-testlogs' or 'tests-report'
     """
+    #print("THIs IS FILEPATH IN GET MD FROm TestPATH: ", raw_filepath)
     known_good_json = os.environ.get("KNOWN_GOOD_JSON")
-    module_name = parse_module_name_from_path(filepath)
+    clean_filepath = clean_test_file_name(raw_filepath)
+    #print(f"This is the cleaned filepath: {clean_filepath}")
+    module_name = parse_module_name_from_path(clean_filepath)
     md: MetaData = {
         "module_name": module_name,
         "hash": "",

From 691528337508f45e6eda731696235b8a9c05e8f9 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 15:06:35 +0100
Subject: [PATCH 23/34] Linting errors

---
 .../score_source_code_linker/xml_parser.py       | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index af80c76be..d44f0854c 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -69,12 +69,12 @@ def clean_test_file_name(raw_filepath: Path) -> Path:
     """
     if "bazel-testlogs" in str(raw_filepath):
         return Path(str(raw_filepath).split("bazel-testlogs/")[-1])
-    elif "tests-report" in str(raw_filepath):
+    if "tests-report" in str(raw_filepath):
         return Path(str(raw_filepath).split("test-report/")[-1])
-    else:
-        raise ValueError(
-            f"Filepath does not have 'bazel-testlogs' nor 'test-report'. Filepath: {raw_filepath}"
-        )
+    raise ValueError(
+        "Filepath does not have 'bazel-testlogs' nor "
+        f"'test-report'. Filepath: {raw_filepath}"
+    )
 
 
 def get_metadata_from_test_path(raw_filepath: Path) -> MetaData:
@@ -101,15 +101,15 @@ def get_metadata_from_test_path(raw_filepath: Path) -> MetaData:
     src/extensions/score_any_folder/score_any_folder_tests/test.xml
 
     For local builds:
-    <root path>/bazel-testlogs/src/extensions/score_any_folder/score_any_folder_tests/test.xml
+    <root path>/bazel-testlogs/src/ext/score_.../score_any_folder_tests/test.xml
 
     Therefore will we 'clean' it before passing it to the parse_module func.
     Removing everything up to and including 'bazel-testlogs' or 'tests-report'
     """
-    #print("THIs IS FILEPATH IN GET MD FROm TestPATH: ", raw_filepath)
+    # print("THIs IS FILEPATH IN GET MD FROm TestPATH: ", raw_filepath)
     known_good_json = os.environ.get("KNOWN_GOOD_JSON")
     clean_filepath = clean_test_file_name(raw_filepath)
-    #print(f"This is the cleaned filepath: {clean_filepath}")
+    # print(f"This is the cleaned filepath: {clean_filepath}")
     module_name = parse_module_name_from_path(clean_filepath)
     md: MetaData = {
         "module_name": module_name,

From a836298041b982e130fad2b915b9fb60417a9266 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Tue, 17 Mar 2026 15:11:45 +0100
Subject: [PATCH 24/34] Make comment more visibile

---
 .../score_source_code_linker/tests/test_xml_parser.py       | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/src/extensions/score_source_code_linker/tests/test_xml_parser.py b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
index b33000121..3c328fedf 100644
--- a/src/extensions/score_source_code_linker/tests/test_xml_parser.py
+++ b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
@@ -10,7 +10,11 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 # *******************************************************************************
-# Some portions generated by CoPilot
+
+# ╓                                                          ╖
+# ║ Some portions generated by CoPilot                       ║
+# ╙                                                          ╜
+
 """
 Tests for the xml_parser.py file.
 Keep in mind that this is with the 'assertions' inside xml_parser disabled so far.

From 133a44df7ae25aabae45c6c668c8ee639f4f3976 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Wed, 18 Mar 2026 10:42:32 +0100
Subject: [PATCH 25/34] Small cleanup

---
 scripts_bazel/merge_sourcelinks.py                   |  2 +-
 src/extensions/score_source_code_linker/__init__.py  |  9 ++++++---
 .../generate_source_code_links_json.py               | 12 ++++++++----
 3 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index a6cc03e29..147c02d11 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -48,7 +48,7 @@ def main():
     _ = parser.add_argument(
         "--known_good",
         required=True,
-        help="Optional path to a 'known good' JSON file (provided by Bazel).",
+        help="Path to a required 'known good' JSON file (provided by Bazel).",
     )
     _ = parser.add_argument(
         "files",
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index d80754036..679dc0a81 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -256,9 +256,12 @@ def setup_module_linker(app: Sphinx, _: BuildEnvironment):
     grouped_cache = get_cache_filename(
         app.outdir, "score_module_grouped_scl_cache.json"
     )
-    gruped_cache_exists = grouped_cache.exists()
+    grouped_cache_exists = grouped_cache.exists()
     # TODO this cache should be done via Bazel
-    if not gruped_cache_exists or not app.config.skip_rescanning_via_source_code_linker:
+    if (
+        not grouped_cache_exists
+        or not app.config.skip_rescanning_via_source_code_linker
+    ):
         LOGGER.debug(
             "Did not find combined json 'score_module_grouped_scl_cache.json' "
             "in _build. Generating new one"
@@ -291,7 +294,7 @@ def setup_once(app: Sphinx):
     register_combined_linker(app)
     register_module_linker(app)
 
-    # Priorty=515 to ensure it's called after the test code linker & combined connection
+    # Priority=515 to ensure it's called after the test linker & combined connection
     app.connect("env-updated", inject_links_into_needs, priority=525)
 
 
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index cf9457c82..7c48de9ee 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -130,10 +130,14 @@ def find_all_need_references(search_path: Path) -> list[NeedLink]:
 
     # Use os.walk to have better control over directory traversal
     for file in iterate_files_recursively(search_path):
-        print("Search_path: ", search_path)
-        print("File.name: ", file.name)
-        print("File: ", file)
-        references = _extract_references_from_file(search_path,Path(file), file)
+        LOGGER.debug(
+            f"Scanning file by the name of: {file.name} "
+            f"in path: {search_path} with the file being: {file}"
+        )
+        # print("Search_path: ", search_path)
+        # print("File.name: ", file.name)
+        # print("File: ", file)
+        references = _extract_references_from_file(search_path, Path(file), file)
         all_need_references.extend(references)
 
     elapsed_time = os.times().elapsed - start_time

From 748467da975fd6f75dd8f0078c7986676b2aaabb Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Fri, 20 Mar 2026 10:53:58 +0100
Subject: [PATCH 26/34] Renaming module => repo

---
 scripts_bazel/generate_sourcelinks_cli.py     |  13 +-
 scripts_bazel/merge_sourcelinks.py            |  18 +-
 src/extensions/score_source_code_linker/BUILD |   2 +-
 .../score_source_code_linker/__init__.py      |  34 +--
 .../score_source_code_linker/helpers.py       |  20 +-
 .../score_source_code_linker/needlinks.py     |  32 +--
 ...e_source_links.py => repo_source_links.py} |  82 ++++---
 .../score_source_code_linker/testlink.py      |  24 +-
 .../tests/expected_codelink.json              |   8 +-
 .../tests/expected_grouped.json               |  18 +-
 ...rouped.json => expected_repo_grouped.json} |  20 +-
 .../tests/expected_testlink.json              |  10 +-
 .../tests/test_codelink.py                    | 176 +++++++--------
 .../tests/test_helpers.py                     |  97 ++++----
 ...y => test_repo_source_link_integration.py} | 208 +++++++++---------
 ...rce_links.py => test_repo_source_links.py} | 186 ++++++++--------
 .../test_source_code_link_integration.py      |  40 ++--
 .../tests/test_testlink.py                    |  24 +-
 .../tests/test_xml_parser.py                  |   6 +-
 .../score_source_code_linker/xml_parser.py    |  28 ++-
 20 files changed, 517 insertions(+), 529 deletions(-)
 rename src/extensions/score_source_code_linker/{module_source_links.py => repo_source_links.py} (62%)
 rename src/extensions/score_source_code_linker/tests/{expected_module_grouped.json => expected_repo_grouped.json} (80%)
 rename src/extensions/score_source_code_linker/tests/{test_module_source_links_integration.py => test_repo_source_link_integration.py} (64%)
 rename src/extensions/score_source_code_linker/tests/{test_module_source_links.py => test_repo_source_links.py} (76%)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 89898d0ee..e5b134a45 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -25,9 +25,9 @@
 from src.extensions.score_source_code_linker.generate_source_code_links_json import (
     _extract_references_from_file,  # pyright: ignore[reportPrivateUsage] TODO: move it out of the extension and into this script
 )
-from src.extensions.score_source_code_linker.helpers import parse_module_name_from_path
+from src.extensions.score_source_code_linker.helpers import parse_repo_name_from_path
 from src.extensions.score_source_code_linker.needlinks import (
-    MetaData,
+    DefaultMetaData,
     store_source_code_links_with_metadata_json,
 )
 
@@ -71,15 +71,12 @@ def main():
     args = parser.parse_args()
 
     all_need_references = []
-    metadata: MetaData = {
-        "module_name": "",
-        "hash": "",
-        "url": "",
-    }
+
+    metadata = DefaultMetaData()
     metadata_set = False
     for file_path in args.files:
         if "known_good.json" not in str(file_path) and not metadata_set:
-            metadata["module_name"] = parse_module_name_from_path(file_path)
+            metadata["repo_name"] = parse_repo_name_from_path(file_path)
             metadata_set = True
         abs_file_path = file_path.resolve()
         assert abs_file_path.exists(), abs_file_path
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index 147c02d11..88499d11a 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -27,14 +27,6 @@
 logger = logging.getLogger(__name__)
 
 
-"""
-if bazel-out/k8-fastbuild/bin/external/ in file_path => module is external
-otherwise it's local
-if local => module_name & hash == empty
-if external => parse thing for module_name => look up known_good json for hash & url
-"""
-
-
 def main():
     parser = argparse.ArgumentParser(
         description="Merge multiple sourcelinks JSON files into one"
@@ -68,21 +60,21 @@ def main():
             if not data:
                 continue
             metadata = data[0]
-            if not isinstance(metadata, dict) or "module_name" not in metadata:
+            if not isinstance(metadata, dict) or "repo_name" not in metadata:
                 logger.warning(
                     f"Unexpected schema in sourcelinks file '{json_file}': "
                     "expected first element to be a metadata dict "
-                    "with a 'module_name' key. "
+                    "with a 'repo_name' key. "
                 )
                 # As we can't deal with bad JSON structure we just skip it
                 continue
-            if metadata["module_name"] and metadata["module_name"] != "local_module":
+            if metadata["repo_name"] and metadata["repo_name"] != "local_repo":
                 hash, repo = parse_info_from_known_good(
-                    known_good_json=args.known_good, module_name=metadata["module_name"]
+                    known_good_json=args.known_good, repo_name=metadata["repo_name"]
                 )
                 metadata["hash"] = hash
                 metadata["url"] = repo
-            # In the case that 'metadata[module_name]' is 'local_module'
+            # In the case that 'metadata[repo_name]' is 'local_module'
             # hash & url are already existing and empty inside of 'metadata'
             # Therefore all 3 keys will be written to needlinks in each branch
 
diff --git a/src/extensions/score_source_code_linker/BUILD b/src/extensions/score_source_code_linker/BUILD
index 85b8f222b..e9e3528f7 100644
--- a/src/extensions/score_source_code_linker/BUILD
+++ b/src/extensions/score_source_code_linker/BUILD
@@ -55,7 +55,7 @@ py_library(
         "testlink.py",
         "xml_parser.py",
         "helpers.py",
-        "module_source_links.py",
+        "repo_source_links.py",
     ],
     imports = ["."],
     visibility = ["//visibility:public"],
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index 679dc0a81..59d336ceb 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -35,10 +35,10 @@
     generate_source_code_links_json,
 )
 from src.extensions.score_source_code_linker.helpers import get_github_link
-from src.extensions.score_source_code_linker.module_source_links import (
-    group_needs_by_module,
-    load_module_source_links_json,
-    store_module_source_links_json,
+from src.extensions.score_source_code_linker.repo_source_links import (
+    group_needs_by_repo,
+    load_repo_source_links_json,
+    store_repo_source_links_json,
 )
 from src.extensions.score_source_code_linker.need_source_links import (
     group_by_need,
@@ -235,26 +235,26 @@ def setup_combined_linker(app: Sphinx, _: BuildEnvironment):
         build_and_save_combined_file(app.outdir)
 
 
-def register_module_linker(app: Sphinx):
+def register_repo_linker(app: Sphinx):
     # Registering the combined linker to Sphinx
     # priority is set to make sure it is called in the right order.
     # Needs to be called after xml parsing & codelink
-    app.connect("env-updated", setup_module_linker, priority=520)
+    app.connect("env-updated", setup_repo_linker, priority=520)
 
 
-def build_and_save_module_scl_file(outdir: Path):
+def build_and_save_repo_scl_file(outdir: Path):
     scl_links = load_source_code_links_combined_json(
         get_cache_filename(outdir, "score_scl_grouped_cache.json")
     )
-    mcl_links = group_needs_by_module(scl_links)
-    store_module_source_links_json(
-        outdir / "score_module_grouped_scl_cache.json", mcl_links
+    mcl_links = group_needs_by_repo(scl_links)
+    store_repo_source_links_json(
+        outdir / "score_repo_grouped_scl_cache.json", mcl_links
     )
 
 
-def setup_module_linker(app: Sphinx, _: BuildEnvironment):
+def setup_repo_linker(app: Sphinx, _: BuildEnvironment):
     grouped_cache = get_cache_filename(
-        app.outdir, "score_module_grouped_scl_cache.json"
+        app.outdir, "score_repo_grouped_scl_cache.json"
     )
     grouped_cache_exists = grouped_cache.exists()
     # TODO this cache should be done via Bazel
@@ -266,7 +266,7 @@ def setup_module_linker(app: Sphinx, _: BuildEnvironment):
             "Did not find combined json 'score_module_grouped_scl_cache.json' "
             "in _build. Generating new one"
         )
-        build_and_save_module_scl_file(app.outdir)
+        build_and_save_repo_scl_file(app.outdir)
 
 
 def setup_once(app: Sphinx):
@@ -292,7 +292,7 @@ def setup_once(app: Sphinx):
     setup_source_code_linker(app, ws_root)
     register_test_code_linker(app)
     register_combined_linker(app)
-    register_module_linker(app)
+    register_repo_linker(app)
 
     # Priority=515 to ensure it's called after the test linker & combined connection
     app.connect("env-updated", inject_links_into_needs, priority=525)
@@ -350,8 +350,8 @@ def inject_links_into_needs(app: Sphinx, env: BuildEnvironment) -> None:
                     f"?? Need {id} already has testlink: {need.get('testlink')}"
                 )
 
-    scl_by_module = load_module_source_links_json(
-        get_cache_filename(app.outdir, "score_module_grouped_scl_cache.json")
+    scl_by_module = load_repo_source_links_json(
+        get_cache_filename(app.outdir, "score_repo_grouped_scl_cache.json")
     )
     for module_grouped_needs in scl_by_module:
         for source_code_links in module_grouped_needs.needs:
@@ -373,7 +373,7 @@ def inject_links_into_needs(app: Sphinx, env: BuildEnvironment) -> None:
                 continue
 
             need_as_dict = cast(dict[str, object], need)
-            metadata = module_grouped_needs.module
+            metadata = module_grouped_needs.repo
             need_as_dict["source_code_link"] = ", ".join(
                 f"{get_github_link(metadata, n)}<>{n.file}:{n.line}"
                 for n in source_code_links.links.CodeLinks
diff --git a/src/extensions/score_source_code_linker/helpers.py b/src/extensions/score_source_code_linker/helpers.py
index a186754ac..b41b7cc56 100644
--- a/src/extensions/score_source_code_linker/helpers.py
+++ b/src/extensions/score_source_code_linker/helpers.py
@@ -13,7 +13,7 @@
 import json
 from pathlib import Path
 
-from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 
 # Import types that depend on score_source_code_linker
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink, NeedLink
@@ -29,7 +29,7 @@
 
 
 def get_github_link(
-    metadata: ModuleInfo,
+    metadata: RepoInfo,
     link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
 ) -> str:
     if link is None:
@@ -55,7 +55,7 @@ def get_github_link_from_git(
 
 
 def get_github_link_from_json(
-    metadata: ModuleInfo,
+    metadata: RepoInfo,
     link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
 ) -> str:
     if link is None:
@@ -65,7 +65,7 @@ def get_github_link_from_json(
     return f"{base_url}/blob/{current_hash}/{link.file}#L{link.line}"
 
 
-def parse_module_name_from_path(path: Path) -> str:
+def parse_repo_name_from_path(path: Path) -> str:
     """
     Parse out the Module-Name from the filename:
     Combo Example:
@@ -73,7 +73,7 @@ def parse_module_name_from_path(path: Path) -> str:
         => score_docs_as_code
     Local:
         Path: src/helper_lib/test_helper_lib.py
-        => local_module
+        => local_repo
 
     """
 
@@ -85,11 +85,11 @@ def parse_module_name_from_path(path: Path) -> str:
         filepath_split = str(module_raw).split("/", maxsplit=1)
         return str(filepath_split[0].removesuffix("+"))
     # We return this when we are in a local build `//:docs` the rest of DaC knows
-    return "local_module"
+    return "local_repo"
 
 
 def parse_info_from_known_good(
-    known_good_json: Path, module_name: str
+    known_good_json: Path, repo_name: str
 ) -> tuple[str, str]:
     with open(known_good_json) as f:
         kg_json = json.load(f)
@@ -106,7 +106,7 @@ def parse_info_from_known_good(
     )
 
     for category in kg_json["modules"].values():
-        if module_name in category:
-            m = category[module_name]
+        if repo_name in category:
+            m = category[repo_name]
             return (m["hash"], m["repo"].removesuffix(".git"))
-    raise KeyError(f"Module {module_name!r} not found in known_good_json.")
+    raise KeyError(f"Module {repo_name} not found in known_good_json.")
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index 52f424830..fb099e14a 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -20,14 +20,19 @@
 
 
 class MetaData(TypedDict):
-    module_name: str
+    repo_name: str
     hash: str
     url: str
 
 
+def DefaultMetaData() -> MetaData:
+    md: MetaData = {"repo_name": "local_repo", "hash": "", "url": ""}
+    return md
+
+
 def is_metadata(x: object) -> TypeGuard[MetaData]:
     # Make this as strict/loose as you want; at minimum, it must be a dict.
-    return isinstance(x, dict) and {"module_name", "hash", "url"} <= x.keys()
+    return isinstance(x, dict) and {"repo_name", "hash", "url"} <= x.keys()
 
 
 @dataclass(order=True)
@@ -39,12 +44,13 @@ class NeedLink:
     tag: str
     need: str
     full_line: str
-    module_name: str = "local_module"
+    repo_name: str = "local_repo"
     hash: str = ""
     url: str = ""
 
     # Adding hashing & equality as this is needed to make comparisions.
     # Since the Dataclass is not 'frozen = true' it isn't automatically hashable
+    # This is used in tests
     def __hash__(self):
         return hash(
             (
@@ -53,7 +59,7 @@ def __hash__(self):
                 self.tag,
                 self.need,
                 self.full_line,
-                self.module_name,
+                self.repo_name,
                 self.hash,
                 self.url,
             )
@@ -68,7 +74,7 @@ def __eq__(self, other: Any):
             and self.tag == other.tag
             and self.need == other.need
             and self.full_line == other.full_line
-            and self.module_name == other.module_name
+            and self.repo_name == other.repo_name
             and self.hash == other.hash
             and self.url == other.url
         )
@@ -78,10 +84,10 @@ def to_dict_full(self) -> dict[str, str | Path | int]:
         return asdict(self)
 
     # Drops MetaData fields for saving the Dataclass (saving space in json)
-    # The information is in the 'Module_Source_Link' in the end
+    # The information is in the 'Repo_Source_Link' in the end
     def to_dict_without_metadata(self) -> dict[str, str | Path | int]:
         d = asdict(self)
-        d.pop("module_name", None)
+        d.pop("repo_name", None)
         d.pop("hash", None)
         d.pop("url", None)
         return d
@@ -98,7 +104,7 @@ def DefaultNeedLink() -> NeedLink:
         tag="",
         need="",
         full_line="",
-        # Module_name, hash, url are defaulted to ""
+        # Repo_name, hash, url are defaulted to ""
         # therefore not needed to be listed
     )
 
@@ -120,7 +126,7 @@ def needlink_decoder(d: dict[str, Any]) -> NeedLink | dict[str, Any]:
             tag=d["tag"],
             need=d["need"],
             full_line=d["full_line"],
-            module_name=d.get("module_name", ""),
+            repo_name=d.get("repo_name", ""),
             hash=d.get("hash", ""),
             url=d.get("url", ""),
         )
@@ -136,13 +142,13 @@ def store_source_code_links_with_metadata_json(
       [ meta_dict, needlink1, needlink2, ... ]
 
     meta_dict must include:
-      module_name, hash, url
+      repo_name, hash, url
     """
     payload: list[object] = [metadata, *needlist]
 
     # After `rm -rf _build` or on clean builds the directory does not exist,
     # so we need to create it. We create any folder that might be missing
-    file.parent.mkdir(exist_ok=True,parents=True)
+    file.parent.mkdir(exist_ok=True, parents=True)
     with open(file, "w", encoding="utf-8") as f:
         json.dump(payload, f, cls=NeedLinkEncoder, indent=2, ensure_ascii=False)
 
@@ -197,7 +203,7 @@ def load_source_code_links_with_metadata_json(file: Path) -> list[NeedLink]:
             f"metadata must decode to NeedLink objects. File: {file}"
         )
     for d in links:
-        d.module_name = metadata["module_name"]
+        d.repo_name = metadata["repo_name"]
         d.hash = metadata["hash"]
         d.url = metadata["url"]
     return links
@@ -206,7 +212,7 @@ def load_source_code_links_with_metadata_json(file: Path) -> list[NeedLink]:
 def load_source_code_links_json(file: Path) -> list[NeedLink]:
     """
     Expects the JSON array with needlinks
-    *that already have extra info in them* (module_name, hash, url):
+    *that already have extra info in them* (repo_name, hash, url):
       [ needlink1, needlink2, ... ]
     Returns:
       [NeedLink, NeedLink, ...]
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/repo_source_links.py
similarity index 62%
rename from src/extensions/score_source_code_linker/module_source_links.py
rename to src/extensions/score_source_code_linker/repo_source_links.py
index 1521f6868..841c20780 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/repo_source_links.py
@@ -27,19 +27,23 @@
 
 
 @dataclass
-class ModuleInfo:
+class RepoInfo:
     name: str
     hash: str
     url: str
 
 
+def DefaultRepoInfo() -> RepoInfo:
+    return RepoInfo(name="local_repo", hash="", url="")
+
+
 @dataclass
-class ModuleSourceLinks:
-    module: ModuleInfo
+class RepoSourceLinks:
+    repo: RepoInfo
     needs: list[SourceCodeLinks] = field(default_factory=list)
 
 
-class ModuleSourceLinks_TEST_JSON_Encoder(json.JSONEncoder):
+class RepoSourceLinks_TEST_JSON_Encoder(json.JSONEncoder):
     def default(self, o: object) -> str | dict[str, Any]:
         if isinstance(o, Path):
             return str(o)
@@ -52,9 +56,9 @@ def default(self, o: object) -> str | dict[str, Any]:
         # dictionaries won't get split up and we will not
         # run into the 'to_dict_without_metadata' as
         # everything will be converted to a normal dictionary
-        if isinstance(o, ModuleSourceLinks):
+        if isinstance(o, RepoSourceLinks):
             return {
-                "module": asdict(o.module),
+                "repo": asdict(o.repo),
                 "needs": o.needs,  # Let the encoder handle the list
             }
         if isinstance(o, SourceCodeLinks):
@@ -70,17 +74,17 @@ def default(self, o: object) -> str | dict[str, Any]:
         return super().default(o)
 
 
-def ModuleSourceLinks_JSON_Decoder(
+def RepoSourceLinks_JSON_Decoder(
     d: dict[str, Any],
-) -> ModuleSourceLinks | dict[str, Any]:
-    if "module" in d and "needs" in d:
-        module = d["module"]
+) -> RepoSourceLinks | dict[str, Any]:
+    if "repo" in d and "needs" in d:
+        repo = d["repo"]
         needs = d["needs"]
-        return ModuleSourceLinks(
-            module=ModuleInfo(
-                name=module.get("name"),
-                hash=module.get("hash"),
-                url=module.get("url"),
+        return RepoSourceLinks(
+            repo=RepoInfo(
+                name=repo.get("name"),
+                hash=repo.get("hash"),
+                url=repo.get("url"),
             ),
             # We know this can only be list[SourceCodeLinks] and nothing else
             # Therefore => we ignore the type error here
@@ -89,8 +93,8 @@ def ModuleSourceLinks_JSON_Decoder(
     return d
 
 
-def store_module_source_links_json(
-    file: Path, source_code_links: list[ModuleSourceLinks]
+def store_repo_source_links_json(
+    file: Path, source_code_links: list[RepoSourceLinks]
 ):
     # After `rm -rf _build` or on clean builds the directory does not exist,
     # so we need to create it. We create any folder that might be missing
@@ -99,31 +103,31 @@ def store_module_source_links_json(
         json.dump(
             source_code_links,
             f,
-            cls=ModuleSourceLinks_TEST_JSON_Encoder,
+            cls=RepoSourceLinks_TEST_JSON_Encoder,
             indent=2,
             ensure_ascii=False,
         )
 
 
-def load_module_source_links_json(file: Path) -> list[ModuleSourceLinks]:
-    links: list[ModuleSourceLinks] = json.loads(
+def load_repo_source_links_json(file: Path) -> list[RepoSourceLinks]:
+    links: list[RepoSourceLinks] = json.loads(
         file.read_text(encoding="utf-8"),
-        object_hook=ModuleSourceLinks_JSON_Decoder,
+        object_hook=RepoSourceLinks_JSON_Decoder,
     )
     assert isinstance(links, list), (
-        "The ModuleSourceLink json should be a list of ModuleSourceLink objects."
+        "The RepoSourceLink json should be a list of RepoSourceLink objects."
     )
-    assert all(isinstance(link, ModuleSourceLinks) for link in links), (
-        "All items in module source link cache should be ModuleSourceLink objects."
+    assert all(isinstance(link, RepoSourceLinks) for link in links), (
+        "All items in repo source link cache should be RepoSourceLink objects."
     )
     return links
 
 
-def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLinks]:
-    module_groups: dict[str, ModuleSourceLinks] = {}
+def group_needs_by_repo(links: list[SourceCodeLinks]) -> list[RepoSourceLinks]:
+    repo_groups: dict[str, RepoSourceLinks] = {}
 
     for source_link in links:
-        # Check if we can take moduleInfo from code or testlinks
+        # Check if we can take repoInfo from code or testlinks
         if source_link.links.CodeLinks:
             first_link = source_link.links.CodeLinks[0]
         elif source_link.links.TestLinks:
@@ -131,28 +135,22 @@ def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLink
         else:
             # This should not happen?
             continue
-        module_key = first_link.module_name
+        repo_key = first_link.repo_name
 
-        if module_key not in module_groups:
-            module_groups[module_key] = ModuleSourceLinks(
-                module=ModuleInfo(
-                    name=module_key, hash=first_link.hash, url=first_link.url
+        if repo_key not in repo_groups:
+            repo_groups[repo_key] = RepoSourceLinks(
+                repo=RepoInfo(
+                    name=repo_key, hash=first_link.hash, url=first_link.url
                 )
             )
 
         # TODO: Add an assert that checks if needs only are
-        # in a singular module (not allowed to be in multiple)
-        module_groups[module_key].needs.append(source_link)
+        # in a singular repo (not allowed to be in multiple)
+        repo_groups[repo_key].needs.append(source_link)
 
     return [
-        ModuleSourceLinks(module=group.module, needs=group.needs)
-        for group in module_groups.values()
+        RepoSourceLinks(repo=group.repo, needs=group.needs)
+        for group in repo_groups.values()
     ]
 
 
-# # Pouplate Metadata
-# # Since all metadata inside the Codelinks is the same
-# # we can just arbitrarily grab the first one
-# module_name=need_links.CodeLinks[0].module_name,
-# hash=need_links.CodeLinks[0].hash,
-# url=need_links.CodeLinks[0].url,
diff --git a/src/extensions/score_source_code_linker/testlink.py b/src/extensions/score_source_code_linker/testlink.py
index 0dc1557f3..32f5cca8a 100644
--- a/src/extensions/score_source_code_linker/testlink.py
+++ b/src/extensions/score_source_code_linker/testlink.py
@@ -42,7 +42,7 @@ class DataForTestLink:
     verify_type: str
     result: str
     result_text: str = ""
-    module_name: str = "local_module"
+    repo_name: str = "local_repo"
     hash: str = ""
     url: str = ""
 
@@ -58,7 +58,7 @@ def __hash__(self):
                 self.verify_type,
                 self.result,
                 self.result_text,
-                self.module_name,
+                self.repo_name,
                 self.hash,
                 self.url,
             )
@@ -75,7 +75,7 @@ def __eq__(self, other: Any):
             and self.verify_type == other.verify_type
             and self.result == other.result
             and self.result_text == other.result_text
-            and self.module_name == other.module_name
+            and self.repo_name == other.repo_name
             and self.hash == other.hash
             and self.url == other.url
         )
@@ -85,10 +85,10 @@ def to_dict_full(self) -> dict[str, str | Path | int]:
         return asdict(self)
 
     # Drops MetaData fields for saving the Dataclass (saving space in json)
-    # The information is in the 'Module_Source_Link' in the end
+    # The information is in the 'Repo_Source_Link' in the end
     def to_dict_without_metadata(self) -> dict[str, str | Path | int]:
         d = asdict(self)
-        d.pop("module_name", None)
+        d.pop("repo_name", None)
         d.pop("hash", None)
         d.pop("url", None)
         return d
@@ -110,7 +110,7 @@ def DataForTestLink_JSON_Decoder(d: dict[str, Any]) -> DataForTestLink | dict[st
         "line",
         "need",
         "verify_type",
-        "module_name",
+        "repo_name",
         "hash",
         "url",
         "result",
@@ -121,7 +121,7 @@ def DataForTestLink_JSON_Decoder(d: dict[str, Any]) -> DataForTestLink | dict[st
             file=Path(d["file"]),
             line=d["line"],
             need=d["need"],
-            module_name=d.get("module_name", ""),
+            repo_name=d.get("repo_name", ""),
             hash=d.get("hash", ""),
             url=d.get("url", ""),
             verify_type=d["verify_type"],
@@ -139,7 +139,7 @@ class DataOfTestCase:
     file: str | None = None
     line: str | None = None
     result: str | None = None  # passed | falied | skipped | disabled
-    module_name: str | None = None
+    repo_name: str | None = None
     hash: str | None = None
     url: str | None = None
     # Intentionally not snakecase to make dict parsing simple
@@ -157,7 +157,7 @@ def from_dict(cls, data: dict[str, Any]):  # type-ignore
             file=data.get("file"),
             line=data.get("line"),
             result=data.get("result"),
-            module_name=data.get("module_name"),
+            repo_name=data.get("repo_name"),
             hash=data.get("hash"),
             url=data.get("url"),
             TestType=data.get("TestType"),
@@ -221,7 +221,7 @@ def is_valid(self) -> bool:
         #         and self.DerivationTechnique is not None
         # ):
         # Hash & URL are explictily allowed to be empty but not none.
-        # module_name has to be always filled or something went wrong
+        # repo_name has to be always filled or something went wrong
         fields = [
             x
             for x in self.__dataclass_fields__
@@ -263,7 +263,7 @@ def parse_attributes(verify_field: str | None, verify_type: str):
             assert self.file is not None
             assert self.line is not None
             assert self.result is not None
-            assert self.module_name is not None
+            assert self.repo_name is not None
             assert self.hash is not None
             assert self.url is not None
             assert self.result_text is not None
@@ -279,7 +279,7 @@ def parse_attributes(verify_field: str | None, verify_type: str):
                     verify_type=verify_type,
                     result=self.result,
                     result_text=self.result_text,
-                    module_name=self.module_name,
+                    repo_name=self.repo_name,
                     hash=self.hash,
                     url=self.url,
                 )
diff --git a/src/extensions/score_source_code_linker/tests/expected_codelink.json b/src/extensions/score_source_code_linker/tests/expected_codelink.json
index 4ff1f14bb..422e88352 100644
--- a/src/extensions/score_source_code_linker/tests/expected_codelink.json
+++ b/src/extensions/score_source_code_linker/tests/expected_codelink.json
@@ -5,7 +5,7 @@
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_1",
         "full_line": "#-----req-Id: TREQ_ID_1",
-        "module_name": "local_module",
+        "repo_name": "local_repo",
         "hash": "",
         "url": ""
     },
@@ -15,7 +15,7 @@
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_1",
         "full_line": "#-----req-Id: TREQ_ID_1",
-        "module_name": "local_module",
+        "repo_name": "local_repo",
         "hash": "",
         "url": ""
     },
@@ -25,7 +25,7 @@
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_2",
         "full_line":"#-----req-Id: TREQ_ID_2",
-        "module_name": "local_module",
+        "repo_name": "local_repo",
         "hash": "",
         "url": ""
     },
@@ -35,7 +35,7 @@
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_200",
         "full_line":"#-----req-Id: TREQ_ID_200",
-        "module_name": "local_module",
+        "repo_name": "local_repo",
         "hash": "",
         "url": ""
     }
diff --git a/src/extensions/score_source_code_linker/tests/expected_grouped.json b/src/extensions/score_source_code_linker/tests/expected_grouped.json
index bd6df7e40..e2668e476 100644
--- a/src/extensions/score_source_code_linker/tests/expected_grouped.json
+++ b/src/extensions/score_source_code_linker/tests/expected_grouped.json
@@ -9,7 +9,7 @@
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_1",
         "full_line": "#-----req-Id: TREQ_ID_1",
-        "module_name": "local_module",
+        "repo_name": "local_repo",
         "hash": "",
         "url": ""
     },
@@ -19,7 +19,7 @@
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_1",
         "full_line": "#-----req-Id: TREQ_ID_1",
-        "module_name": "local_module",
+        "repo_name": "local_repo",
         "hash": "",
         "url": ""
     }
@@ -34,7 +34,7 @@
     "verify_type": "fully",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   }
@@ -51,7 +51,7 @@
         "tag":"#-----req-Id:",
         "need": "TREQ_ID_2",
         "full_line":"#-----req-Id: TREQ_ID_2",
-        "module_name": "local_module",
+        "repo_name": "local_repo",
         "hash": "",
         "url": ""
     }
@@ -66,7 +66,7 @@
     "verify_type": "partially",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   },
@@ -78,7 +78,7 @@
     "verify_type": "partially",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   }
@@ -99,7 +99,7 @@
     "verify_type": "partially",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   },
@@ -111,7 +111,7 @@
     "verify_type": "partially",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   }
@@ -128,7 +128,7 @@
             "tag":"#-----req-Id:",
             "need": "TREQ_ID_200",
             "full_line":"#-----req-Id: TREQ_ID_200",
-            "module_name": "local_module",
+            "repo_name": "local_repo",
             "hash": "",
             "url": ""
         }
diff --git a/src/extensions/score_source_code_linker/tests/expected_module_grouped.json b/src/extensions/score_source_code_linker/tests/expected_repo_grouped.json
similarity index 80%
rename from src/extensions/score_source_code_linker/tests/expected_module_grouped.json
rename to src/extensions/score_source_code_linker/tests/expected_repo_grouped.json
index ef91784bf..3d0523121 100644
--- a/src/extensions/score_source_code_linker/tests/expected_module_grouped.json
+++ b/src/extensions/score_source_code_linker/tests/expected_repo_grouped.json
@@ -1,7 +1,7 @@
 [
   {
-    "module": {
-      "name": "local_module",
+    "repo": {
+      "name": "local_repo",
       "hash": "",
       "url": ""
     },
@@ -11,14 +11,14 @@
         "links": {
           "CodeLinks": [
             {
-              "file": "src/module_a_impl.py",
+              "file": "src/repo_a_impl.py",
               "line": 3,
               "tag": "#-----req-Id:",
               "need": "MOD_REQ_1",
               "full_line": "#-----req-Id: MOD_REQ_1"
             },
             {
-              "file": "src/module_b_impl.py",
+              "file": "src/repo_b_impl.py",
               "line": 3,
               "tag": "#-----req-Id:",
               "need": "MOD_REQ_1",
@@ -27,8 +27,8 @@
           ],
           "TestLinks": [
             {
-              "name": "test_module_a",
-              "file": "src/test_module_a.py",
+              "name": "test_repo_a",
+              "file": "src/test_repo_a.py",
               "line": 10,
               "need": "MOD_REQ_1",
               "verify_type": "fully",
@@ -43,7 +43,7 @@
         "links": {
           "CodeLinks": [
             {
-              "file": "src/module_a_impl.py",
+              "file": "src/repo_a_impl.py",
               "line": 7,
               "tag": "#-----req-Id:",
               "need": "MOD_REQ_2",
@@ -58,7 +58,7 @@
         "links": {
           "CodeLinks": [
             {
-              "file": "src/module_b_impl.py",
+              "file": "src/repo_b_impl.py",
               "line": 7,
               "tag": "#-----req-Id:",
               "need": "MOD_REQ_3",
@@ -67,8 +67,8 @@
           ],
           "TestLinks": [
             {
-              "name": "test_module_b",
-              "file": "src/test_module_b.py",
+              "name": "test_repo_b",
+              "file": "src/test_repo_b.py",
               "line": 20,
               "need": "MOD_REQ_3",
               "verify_type": "partially",
diff --git a/src/extensions/score_source_code_linker/tests/expected_testlink.json b/src/extensions/score_source_code_linker/tests/expected_testlink.json
index 145c31c31..23fbbe395 100644
--- a/src/extensions/score_source_code_linker/tests/expected_testlink.json
+++ b/src/extensions/score_source_code_linker/tests/expected_testlink.json
@@ -7,7 +7,7 @@
     "verify_type": "partially",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   },
@@ -19,7 +19,7 @@
     "verify_type": "partially",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   },
@@ -31,7 +31,7 @@
     "verify_type": "partially",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   },
@@ -43,7 +43,7 @@
     "verify_type": "partially",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   },
@@ -55,7 +55,7 @@
     "verify_type": "fully",
     "result": "passed",
     "result_text": "",
-    "module_name": "local_module",
+    "repo_name": "local_repo",
     "hash": "",
     "url": ""
   }
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 1328e1fa2..25387e7ec 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -23,6 +23,8 @@
 from dataclasses import asdict
 from pathlib import Path
 from typing import Any
+from collections import Counter
+from collections.abc import Callable
 
 import pytest
 
@@ -43,7 +45,7 @@
 from src.extensions.score_source_code_linker.helpers import (
     get_github_link,
 )
-from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.needlinks import (
     MetaData,
     NeedLink,
@@ -137,7 +139,7 @@ def needlink_test_decoder(d: dict[str, Any]) -> NeedLink | dict[str, Any]:
         "tag",
         "need",
         "full_line",
-        "module_name",
+        "repo_name",
         "hash",
         "url",
     } <= d.keys():
@@ -147,7 +149,7 @@ def needlink_test_decoder(d: dict[str, Any]) -> NeedLink | dict[str, Any]:
             tag=decode_comment(d["tag"]),
             need=d["need"],
             full_line=decode_comment(d["full_line"]),
-            module_name=d.get("module_name", ""),
+            repo_name=d.get("repo_name", ""),
             hash=d.get("hash", ""),
             url=d.get("url", ""),
         )
@@ -200,7 +202,7 @@ def sample_needlinks() -> list[NeedLink]:
             tag="#" + " req-Id:",
             need="TREQ_ID_1",
             full_line="#" + " req-Id: TREQ_ID_1",
-            module_name="local_module",
+            repo_name="local_repo",
             hash="",
             url="",
         ),
@@ -210,7 +212,7 @@ def sample_needlinks() -> list[NeedLink]:
             tag="#" + " req-Id:",
             need="TREQ_ID_1",
             full_line="#" + " req-Id: TREQ_ID_1",
-            module_name="local_module",
+            repo_name="local_repo",
             hash="",
             url="",
         ),
@@ -220,7 +222,7 @@ def sample_needlinks() -> list[NeedLink]:
             tag="#" + " req-Id:",
             need="TREQ_ID_2",
             full_line="#" + " req-Id: TREQ_ID_2",
-            module_name="local_module",
+            repo_name="local_repo",
             hash="",
             url="",
         ),
@@ -230,7 +232,7 @@ def sample_needlinks() -> list[NeedLink]:
             tag="#" + " req-Id:",
             need="TREQ_ID_200",
             full_line="#" + " req-Id: TREQ_ID_200",
-            module_name="local_module",
+            repo_name="local_repo",
             hash="",
             url="",
         ),
@@ -368,7 +370,7 @@ def test_cache_file_with_encoded_comments(temp_dir: Path) -> None:
             tag="#" + " req-Id:",
             need="TEST_001",
             full_line="#" + " req-Id: TEST_001",
-            module_name="local_module",
+            repo_name="local_repo",
             hash="",
             url="",
         )
@@ -462,7 +464,7 @@ def another_function():
             tag="#" + " req-Id:",
             need="TREQ_ID_1",
             full_line="#" + " req-Id: TREQ_ID_1",
-            module_name="local_module",
+            repo_name="local_repo",
             hash="",
             url="",
         ),
@@ -472,7 +474,7 @@ def another_function():
             tag="#" + " req-Id:",
             need="TREQ_ID_2",
             full_line="#" + " req-Id: TREQ_ID_2",
-            module_name="local_module",
+            repo_name="local_repo",
             hash="",
             url="",
         ),
@@ -482,7 +484,7 @@ def another_function():
             tag="#" + " req-Id:",
             need="TREQ_ID_1",
             full_line="#" + " req-Id: TREQ_ID_1",
-            module_name="local_module",
+            repo_name="local_repo",
             hash="",
             url="",
         ),
@@ -508,7 +510,7 @@ def another_function():
     # Test GitHub link generation
     # Have to change directories in order to ensure that we get the right/any .git file
     os.chdir(Path(git_repo).absolute())
-    metadata = ModuleInfo(name="local_module", hash="", url="")
+    metadata = RepoInfo(name="local_repo", hash="", url="")
     for needlink in loaded_links:
         github_link = get_github_link(metadata, needlink)
         assert "https://github.com/test-user/test-repo/blob/" in github_link
@@ -544,7 +546,7 @@ def test_multiple_commits_hash_consistency(git_repo: Path) -> None:
         full_line="#" + " req-Id: TREQ_ID_1",
     )
 
-    metadata = ModuleInfo(name="local_module", hash="", url="")
+    metadata = RepoInfo(name="local_repo", hash="", url="")
     os.chdir(Path(git_repo).absolute())
     github_link = get_github_link(metadata, needlink)
     assert new_hash in github_link
@@ -552,7 +554,7 @@ def test_multiple_commits_hash_consistency(git_repo: Path) -> None:
 
 def test_is_metadata_missing_keys():
     """Bad path: Dict missing required keys returns False"""
-    incomplete = {"module_name": "test", "hash": "abc"}
+    incomplete = {"repo_name": "test", "hash": "abc"}
     assert is_metadata(incomplete) is False
 
 
@@ -566,14 +568,14 @@ def test_needlink_to_dict_without_metadata():
         line=10,
         tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="#"+" req-Id: REQ_1",
-        module_name="test_module",
+        full_line="#" + " req-Id: REQ_1",
+        repo_name="test_repo",
         url="https://github.com/test/repo",
         hash="abc123",
     )
     result = needlink.to_dict_without_metadata()
 
-    assert "module_name" not in result
+    assert "repo_name" not in result
     assert "hash" not in result
     assert "url" not in result
     assert result["need"] == "REQ_1"
@@ -588,13 +590,13 @@ def test_needlink_to_dict_full():
         tag="#" + " req-Id:",
         need="REQ_1",
         full_line="#" + " req-Id: REQ_1",
-        module_name="test_module",
+        repo_name="test_repo",
         url="https://github.com/test/repo",
         hash="abc123",
     )
     result = needlink.to_dict_full()
 
-    assert result["module_name"] == "test_module"
+    assert result["repo_name"] == "test_repo"
     assert result["hash"] == "abc123"
     assert result["url"] == "https://github.com/test/repo"
     assert result["need"] == "REQ_1"
@@ -612,14 +614,14 @@ def test_needlink_encoder_includes_metadata():
         tag="#" + " req-Id:",
         need="REQ_1",
         full_line="#" + " req-Id: REQ_1",
-        module_name="test_module",
+        repo_name="test_repo",
         url="https://github.com/test/repo",
         hash="abc123",
     )
     result = encoder.default(needlink)
 
     assert isinstance(result, dict)
-    assert result["module_name"] == "test_module"
+    assert result["repo_name"] == "test_repo"
     assert result["hash"] == "abc123"
     assert result["url"] == "https://github.com/test/repo"
 
@@ -634,10 +636,10 @@ def test_needlink_decoder_with_all_fields():
     json_data: dict[str, Any] = {
         "file": "src/test.py",
         "line": 10,
-        "tag":"#" + " req-Id:",
+        "tag": "#" + " req-Id:",
         "need": "REQ_1",
-        "full_line": "#" +" req-Id: REQ_1",
-        "module_name": "test_module",
+        "full_line": "#" + " req-Id: REQ_1",
+        "repo_name": "test_repo",
         "hash": "abc123",
         "url": "https://github.com/test/repo",
     }
@@ -646,7 +648,7 @@ def test_needlink_decoder_with_all_fields():
     assert isinstance(result, NeedLink)
     assert result.file == Path("src/test.py")
     assert result.line == 10
-    assert result.module_name == "test_module"
+    assert result.repo_name == "test_repo"
 
 
 def test_needlink_decoder_non_needlink_dict():
@@ -659,30 +661,6 @@ def test_needlink_decoder_non_needlink_dict():
 #            ───────────────[ Testing Encoding / Decoding ]─────────────
 
 
-def test_store_and_load_source_code_links(tmp_path: Path):
-    """Happy path: Store and load without metadata"""
-    needlinks = [
-        NeedLink(
-            file=Path("src/impl.py"),
-            line=42,
-            tag="#" + " req-Id:",
-            need="REQ_1",
-            full_line="#" + " req-Id: REQ_1",
-            module_name="mod",
-            url="url",
-            hash="hash",
-        )
-    ]
-
-    test_file = tmp_path / "standard.json"
-    store_source_code_links_json(test_file, needlinks)
-    loaded = load_source_code_links_json(test_file)
-
-    assert len(loaded) == 1
-    assert loaded[0].need == "REQ_1"
-    assert loaded[0].module_name == "mod"
-
-
 def test_load_validates_list_type(tmp_path: Path):
     """Bad path: Non-list JSON fails validation"""
     test_file = tmp_path / "not_list.json"
@@ -707,7 +685,7 @@ def test_load_validates_all_items_are_needlinks(tmp_path: Path):
 def test_store_and_load_with_metadata(tmp_path: Path):
     """Happy path: Store with metadata dict and load correctly"""
     metadata: MetaData = {
-        "module_name": "external_module",
+        "repo_name": "external_repo",
         "hash": "commit_xyz",
         "url": "https://github.com/external/repo",
     }
@@ -717,8 +695,8 @@ def test_store_and_load_with_metadata(tmp_path: Path):
             line=10,
             tag="#" + " req-Id:",
             need="REQ_1",
-            full_line="#"+" req-Id: REQ_1",
-            module_name="",  # Will be filled from metadata
+            full_line="#" + " req-Id: REQ_1",
+            repo_name="",  # Will be filled from metadata
             url="",
             hash="",
         ),
@@ -727,8 +705,8 @@ def test_store_and_load_with_metadata(tmp_path: Path):
             line=20,
             tag="#" + " req-Id:",
             need="REQ_2",
-            full_line="#"+" req-Id: REQ_2",
-            module_name="",
+            full_line="#" + " req-Id: REQ_2",
+            repo_name="",
             url="",
             hash="",
         ),
@@ -740,14 +718,17 @@ def test_store_and_load_with_metadata(tmp_path: Path):
 
     assert len(loaded) == 2
     # Verify metadata was applied to all links
-    assert loaded[0].module_name == "external_module"
-    assert loaded[0].hash == "commit_xyz"
-    assert loaded[0].url == "https://github.com/external/repo"
-    assert loaded[1].module_name == "external_module"
+    for nl in loaded:
+        assert nl.repo_name == "external_repo"
+        assert nl.url == "https://github.com/external/repo"
+        assert nl.hash == "commit_xyz"
 
 
 def test_load_with_metadata_missing_metadata_dict(tmp_path: Path):
-    """Bad path: Loading file without metadata dict raises TypeError"""
+    """
+    Test if loading file without metadata dict via
+    the scl_with_metadata loader raises TypeError
+    """
     # Store without metadata (just needlinks)
     needlinks = [
         NeedLink(
@@ -755,7 +736,7 @@ def test_load_with_metadata_missing_metadata_dict(tmp_path: Path):
             line=1,
             tag="#" + " req-Id:",
             need="REQ_1",
-            full_line="#" +" req-Id: REQ_1",
+            full_line="#" + " req-Id: REQ_1",
         )
     ]
 
@@ -768,12 +749,12 @@ def test_load_with_metadata_missing_metadata_dict(tmp_path: Path):
 
 
 def test_load_with_metadata_invalid_items_after_metadata(tmp_path: Path):
-    """Bad path: Items after metadata dict are not NeedLinks"""
+    """Test wrong JSON structure"""
     test_file = tmp_path / "bad_items.json"
     # Manually create invalid JSON
     _ = test_file.write_text(
         json.dumps(
-            [{"module_name": "mod", "hash": "h", "url": "u"}, {"invalid": "structure"}]
+            [{"repo_name": "mod", "hash": "h", "url": "u"}, {"invalid": "structure"}]
         )
     )
 
@@ -787,7 +768,7 @@ def test_load_with_metadata_invalid_items_after_metadata(tmp_path: Path):
 def test_load_resolves_relative_path_with_env_var(
     tmp_path: Path, monkeypatch: pytest.MonkeyPatch
 ):
-    """Edge case: Relative path is resolved using BUILD_WORKSPACE_DIRECTORY"""
+    """Test if relative path is resolved using BUILD_WORKSPACE_DIRECTORY"""
     workspace = tmp_path / "workspace"
     workspace.mkdir()
 
@@ -795,9 +776,9 @@ def test_load_resolves_relative_path_with_env_var(
         NeedLink(
             file=Path("src/test.py"),
             line=1,
-            tag="#"+" req-Id:",
+            tag="#" + " req-Id:",
             need="REQ_1",
-            full_line="#"+" req-Id: REQ_1",
+            full_line="#" + " req-Id: REQ_1",
         )
     ]
 
@@ -821,7 +802,7 @@ def test_load_with_metadata_resolves_relative_path(
     workspace.mkdir()
 
     metadata: MetaData = {
-        "module_name": "mod",
+        "repo_name": "mod",
         "hash": "h",
         "url": "u",
     }
@@ -829,9 +810,9 @@ def test_load_with_metadata_resolves_relative_path(
         NeedLink(
             file=Path("src/test.py"),
             line=1,
-            tag="#"+"  req-Id:",
+            tag="#" + "  req-Id:",
             need="REQ_1",
-            full_line="#"+" req-Id: REQ_1",
+            full_line="#" + " req-Id: REQ_1",
         )
     ]
 
@@ -842,7 +823,7 @@ def test_load_with_metadata_resolves_relative_path(
     loaded = load_source_code_links_with_metadata_json(Path("metadata_cache.json"))
 
     assert len(loaded) == 1
-    assert loaded[0].module_name == "mod"
+    assert loaded[0].repo_name == "mod"
 
 
 #            ─────────────────────[ Roundtrip Tests ]───────────────────
@@ -854,20 +835,20 @@ def test_roundtrip_standard_format(tmp_path: Path):
         NeedLink(
             file=Path("src/file1.py"),
             line=10,
-            tag="#"+" req-Id:",
+            tag="#" + " req-Id:",
             need="REQ_A",
-            full_line="#"+" req-Id: REQ_A",
-            module_name="mod_a",
+            full_line="#" + " req-Id: REQ_A",
+            repo_name="mod_a",
             url="url_a",
             hash="hash_a",
         ),
         NeedLink(
             file=Path("src/file2.py"),
             line=20,
-            tag="#"+" req-Id:",
+            tag="#" + " req-Id:",
             need="REQ_B",
-            full_line="#"+" req-Id: REQ_B",
-            module_name="mod_b",
+            full_line="#" + " req-Id: REQ_B",
+            repo_name="mod_b",
             url="url_b",
             hash="hash_b",
         ),
@@ -878,14 +859,15 @@ def test_roundtrip_standard_format(tmp_path: Path):
     loaded = load_source_code_links_json(test_file)
 
     assert len(loaded) == 2
-    assert loaded[0].module_name == "mod_a"
-    assert loaded[1].module_name == "mod_b"
+    assert needlinks == loaded
+    assert loaded[0].repo_name == "mod_a"
+    assert loaded[1].repo_name == "mod_b"
 
 
 def test_roundtrip_metadata_format_applies_metadata(tmp_path: Path):
     """Happy path: Metadata format applies metadata to all links"""
     metadata: MetaData = {
-        "module_name": "shared_module",
+        "repo_name": "shared_repo",
         "hash": "shared_hash",
         "url": "https://github.com/shared/repo",
     }
@@ -893,16 +875,16 @@ def test_roundtrip_metadata_format_applies_metadata(tmp_path: Path):
         NeedLink(
             file=Path("src/f1.py"),
             line=5,
-            tag="#"+" req-Id:",
+            tag="#" + " req-Id:",
             need="R1",
-            full_line="#"+" req-Id: R1",
+            full_line="#" + " req-Id: R1",
         ),
         NeedLink(
             file=Path("src/f2.py"),
             line=15,
-            tag="#"+" req-Id:",
+            tag="#" + " req-Id:",
             need="R2",
-            full_line="#"+" req-Id: R2",
+            full_line="#" + " req-Id: R2",
         ),
     ]
 
@@ -913,7 +895,7 @@ def test_roundtrip_metadata_format_applies_metadata(tmp_path: Path):
     assert len(loaded) == 2
     # Both should have the same metadata applied
     for link in loaded:
-        assert link.module_name == "shared_module"
+        assert link.repo_name == "shared_repo"
         assert link.hash == "shared_hash"
         assert link.url == "https://github.com/shared/repo"
 
@@ -933,16 +915,16 @@ def test_roundtrip_empty_lists(tmp_path: Path):
 def test_json_format_with_metadata_has_separate_dict(tmp_path: Path):
     """Edge case: Verify metadata format has metadata as first element"""
     metadata: MetaData = {
-        "module_name": "test_mod",
+        "repo_name": "test_mod",
         "hash": "test_hash",
         "url": "test_url",
     }
     needlink = NeedLink(
         file=Path("src/test.py"),
         line=1,
-        tag="#"+" req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="#"+" req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
     )
 
     test_file = tmp_path / "metadata_format.json"
@@ -954,7 +936,7 @@ def test_json_format_with_metadata_has_separate_dict(tmp_path: Path):
     assert isinstance(raw_json, list)
     assert len(raw_json) == 2  # metadata + 1 needlink
     # First element should be metadata dict
-    assert raw_json[0]["module_name"] == "test_mod"
+    assert raw_json[0]["repo_name"] == "test_mod"
     assert raw_json[0]["hash"] == "test_hash"
     assert raw_json[0]["url"] == "test_url"
 
@@ -967,20 +949,20 @@ def test_needlink_equality_same_values():
     link1 = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="#"+" req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="#"+" req-Id: REQ_1",
-        module_name="mod",
+        full_line="#" + " req-Id: REQ_1",
+        repo_name="mod",
         url="url",
         hash="hash",
     )
     link2 = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="#"+" req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="#"+" req-Id: REQ_1",
-        module_name="mod",
+        full_line="#" + " req-Id: REQ_1",
+        repo_name="mod",
         url="url",
         hash="hash",
     )
@@ -994,16 +976,16 @@ def test_needlink_inequality_different_values():
     link1 = NeedLink(
         file=Path("src/test.py"),
         line=10,
-        tag="#"+" req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="#"+" req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
     )
     link2 = NeedLink(
         file=Path("src/test.py"),
         line=20,  # Different line
-        tag="#"+" req-Id:",
+        tag="#" + " req-Id:",
         need="REQ_1",
-        full_line="#"+" req-Id: REQ_1",
+        full_line="#" + " req-Id: REQ_1",
     )
 
     assert link1 != link2
diff --git a/src/extensions/score_source_code_linker/tests/test_helpers.py b/src/extensions/score_source_code_linker/tests/test_helpers.py
index 9ad02bc39..d55e4517b 100644
--- a/src/extensions/score_source_code_linker/tests/test_helpers.py
+++ b/src/extensions/score_source_code_linker/tests/test_helpers.py
@@ -23,66 +23,66 @@
     get_github_link,
     get_github_link_from_json,
     parse_info_from_known_good,
-    parse_module_name_from_path,
+    parse_repo_name_from_path,
 )
-from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink
 from src.helper_lib import get_current_git_hash
 
 #              ╭──────────────────────────────────────────────────────────╮
-#              │          Tests for parse_module_name_from_path           │
+#              │          Tests for parse_repo_name_from_path             │
 #              ╰──────────────────────────────────────────────────────────╯
 
 
-def test_parse_module_name_from_external_path():
-    """Test parsing module name from external/combo build path."""
+def test_parse_repo_name_from_external_path():
+    """Test parsing repo name from external/combo build path."""
     path = Path("external/score_docs_as_code+/src/helper_lib/test_helper_lib.py")
 
-    result = parse_module_name_from_path(path)
+    result = parse_repo_name_from_path(path)
 
     assert result == "score_docs_as_code"
 
 
-def test_parse_module_name_from_external_path_2():
+def test_parse_repo_name_from_external_path_2():
     """Test that an extra 'external' in the path does not change the output"""
     path = Path(
         "external/score_docs_as_code+/src/external/helper_lib/test_helper_lib.py"
     )
 
-    result = parse_module_name_from_path(path)
+    result = parse_repo_name_from_path(path)
 
     assert result == "score_docs_as_code"
 
 
-def test_parse_module_name_from_local_path():
-    """Test parsing module name from local build path."""
+def test_parse_repo_name_from_local_path():
+    """Test parsing repo name from local build path."""
     path = Path("src/helper_lib/test_helper_lib.py")
 
-    result = parse_module_name_from_path(path)
+    result = parse_repo_name_from_path(path)
 
-    assert result == "local_module"
+    assert result == "local_repo"
 
 
-def test_parse_module_name_from_empty_path():
-    """Test parsing module name from an empty path."""
+def test_parse_repo_name_from_empty_path():
+    """Test parsing repo name from an empty path."""
     path = Path("")
 
-    result = parse_module_name_from_path(path)
+    result = parse_repo_name_from_path(path)
 
-    assert result == "local_module"
+    assert result == "local_repo"
 
 
-def test_parse_module_name_without_plus_suffix():
+def test_parse_repo_name_without_plus_suffix():
     """
-    Test parsing external module without plus suffix.
+    Test parsing external repo without plus suffix.
     This should never happen (due to bazel adding the '+')
     But testing this edge case anyway
     """
-    path = Path("external/module_without_plus/file.py")
+    path = Path("external/repo_without_plus/file.py")
 
-    result = parse_module_name_from_path(path)
+    result = parse_repo_name_from_path(path)
 
-    assert result == "module_without_plus"
+    assert result == "repo_without_plus"
 
 
 #              ╭──────────────────────────────────────────────────────────╮
@@ -126,7 +126,7 @@ def known_good_json(tmp_path: Path):
 
 # Tests for parse_info_from_known_good
 def test_parse_info_from_known_good_happy_path(known_good_json: Path):
-    """Test parsing module info from valid known_good.json."""
+    """Test parsing repo info from valid known_good.json."""
     hash_result, repo_result = parse_info_from_known_good(
         known_good_json, "score_baselibs"
     )
@@ -136,7 +136,7 @@ def test_parse_info_from_known_good_happy_path(known_good_json: Path):
 
 
 def test_parse_info_from_known_good_different_category(known_good_json: Path):
-    """Test finding module in different category."""
+    """Test finding repo in different category."""
     hash_result, repo_result = parse_info_from_known_good(
         known_good_json, "score_docs_as_code"
     )
@@ -145,14 +145,14 @@ def test_parse_info_from_known_good_different_category(known_good_json: Path):
     assert repo_result == "https://github.com/eclipse-score/docs-as-code"
 
 
-def test_parse_info_from_known_good_module_not_found(known_good_json: Path):
-    """Test that KeyError is raised when module doesn't exist."""
-    with pytest.raises(KeyError, match="Module 'nonexistent' not found"):
+def test_parse_info_from_known_good_repo_not_found(known_good_json: Path):
+    """Test that KeyError is raised when repo doesn't exist."""
+    with pytest.raises(KeyError, match="Module nonexistent not found"):
         parse_info_from_known_good(known_good_json, "nonexistent")
 
 
 def test_parse_info_from_known_good_empty_json(tmp_path: Path):
-    """Test with empty JSON file."""
+    """Test that it errors when given an empty JSON file."""
     json_file = tmp_path / "example.json"
     _ = json_file.write_text("{}")
 
@@ -160,11 +160,11 @@ def test_parse_info_from_known_good_empty_json(tmp_path: Path):
         AssertionError,
         match=f"Known good json at: {json_file} is empty. This is not allowed",
     ):
-        parse_info_from_known_good(json_file, "any_module")
+        parse_info_from_known_good(json_file, "any_repo")
 
 
-def test_parse_info_from_known_good_no_module_in_json(tmp_path: Path):
-    """Test that assertion works when module not in top level keys"""
+def test_parse_info_from_known_good_no_repo_in_json(tmp_path: Path):
+    """Test that assertion works when repo not in top level keys"""
     json_file = tmp_path / "example.json"
     _ = json_file.write_text(
         '{"another_key": {"a": "b"}, "second_key": ["a" , "b", "c"]}'
@@ -174,11 +174,11 @@ def test_parse_info_from_known_good_no_module_in_json(tmp_path: Path):
         AssertionError,
         match=f"Known good json at: {json_file} is missing the 'modules' key",
     ):
-        parse_info_from_known_good(json_file, "any_module")
+        parse_info_from_known_good(json_file, "any_repo")
 
 
-def test_parse_info_from_known_good_empty_module_dict_in_json(tmp_path: Path):
-    """Test that assertion works if module dictionary is empty"""
+def test_parse_info_from_known_good_empty_repo_dict_in_json(tmp_path: Path):
+    """Test that assertion works if repo dictionary is empty"""
     json_file = tmp_path / "emample.json"
     _ = json_file.write_text('{"another_key": {"a": "b"}, "modules": {}}')
 
@@ -186,13 +186,16 @@ def test_parse_info_from_known_good_empty_module_dict_in_json(tmp_path: Path):
         AssertionError,
         match=f"Known good json at: {json_file} has an empty 'modules' dictionary",
     ):
-        parse_info_from_known_good(json_file, "any_module")
+        parse_info_from_known_good(json_file, "any_repo")
 
 
 # Tests for get_github_link_from_json
 def test_get_github_link_from_json_happy_path():
-    """Test generating GitHub link from metadata."""
-    metadata = ModuleInfo(
+    """
+    Test generating GitHub link with fully filled metadata
+    =>this happens in combo builds
+    """
+    metadata = RepoInfo(
         name="project_name",
         url="https://github.com/eclipse/project",
         hash="commit123abc",
@@ -212,7 +215,7 @@ def test_get_github_link_from_json_happy_path():
 
 def test_get_github_link_from_json_with_none_link():
     """Test that None link creates DefaultNeedLink."""
-    metadata = ModuleInfo(
+    metadata = RepoInfo(
         name="test_repo", url="https://github.com/test/repo", hash="def456"
     )
 
@@ -224,7 +227,7 @@ def test_get_github_link_from_json_with_none_link():
 
 def test_get_github_link_from_json_with_line_zero():
     """Test generating link with line number 0."""
-    metadata = ModuleInfo(
+    metadata = RepoInfo(
         name="test_repo", url="https://github.com/test/repo", hash="hash123"
     )
 
@@ -240,8 +243,8 @@ def test_get_github_link_from_json_with_line_zero():
 # Tests for get_github_link
 def test_get_github_link_with_hash():
     """Test get_github_link uses json method when hash is present."""
-    metadata = ModuleInfo(
-        name="some_module", url="https://github.com/org/repo", hash="commit_hash_123"
+    metadata = RepoInfo(
+        name="some_repo", url="https://github.com/org/repo", hash="commit_hash_123"
     )
 
     link = DefaultNeedLink()
@@ -254,12 +257,14 @@ def test_get_github_link_with_hash():
         result == "https://github.com/org/repo/blob/commit_hash_123/src/example.py#L42"
     )
 
+
 @pytest.fixture
 def temp_dir() -> Generator[Path, None, None]:
     """Create a temporary directory for tests."""
     with tempfile.TemporaryDirectory() as temp_dir:
         yield Path(temp_dir)
 
+
 @pytest.fixture
 def git_repo(temp_dir: Path) -> Path:
     """Create a real git repository for testing."""
@@ -295,9 +300,9 @@ def git_repo(temp_dir: Path) -> Path:
 def test_get_github_link_with_real_repo(git_repo: Path) -> None:
     """
     Test generating GitHub link without url/hash.
-    This expects to be in a git module
+    This expects to be in a git repo
     """
-    metadata = ModuleInfo(name="some_module", url="", hash="")
+    metadata = RepoInfo(name="some_repo", url="", hash="")
 
     link = DefaultNeedLink()
     link.file = Path("src/example.py")
@@ -323,16 +328,16 @@ def test_complete_workflow(known_good_json: Path):
 
     # Parse path
     path = Path("external/score_docs_as_code+/src/helper_lib/test_helper_lib.py")
-    module_name = parse_module_name_from_path(path)
-    assert module_name == "score_docs_as_code"
+    repo_name = parse_repo_name_from_path(path)
+    assert repo_name == "score_docs_as_code"
 
     # Get metadata
-    hash_val, repo_url = parse_info_from_known_good(known_good_json, module_name)
+    hash_val, repo_url = parse_info_from_known_good(known_good_json, repo_name)
     assert hash_val == "c1207676afe6cafd25c35d420e73279a799515d8"
     assert repo_url == "https://github.com/eclipse-score/docs-as-code"
 
     # Generate link
-    metadata = ModuleInfo(name=module_name, url=repo_url, hash=hash_val)
+    metadata = RepoInfo(name=repo_name, url=repo_url, hash=hash_val)
     link = DefaultNeedLink()
     link.file = Path("src/helper_lib/test_helper_lib.py")
     link.line = 75
diff --git a/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py b/src/extensions/score_source_code_linker/tests/test_repo_source_link_integration.py
similarity index 64%
rename from src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
rename to src/extensions/score_source_code_linker/tests/test_repo_source_link_integration.py
index 895a8eb56..270fef076 100644
--- a/src/extensions/score_source_code_linker/tests/test_module_source_links_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_repo_source_link_integration.py
@@ -22,10 +22,10 @@
 from pytest import TempPathFactory
 from sphinx.testing.util import SphinxTestApp
 
-from src.extensions.score_source_code_linker.module_source_links import (
-    ModuleInfo,
-    ModuleSourceLinks_JSON_Decoder,
-    load_module_source_links_json,
+from src.extensions.score_source_code_linker.repo_source_links import (
+    RepoInfo,
+    RepoSourceLinks_JSON_Decoder,
+    load_repo_source_links_json,
 )
 
 """
@@ -73,8 +73,8 @@ def create_demo_files(sphinx_base_dir: Path, git_repo_setup: Path):
     source_dir = repo_path / "src"
     source_dir.mkdir()
 
-    _ = (source_dir / "module_a_impl.py").write_text(make_module_a_source())
-    _ = (source_dir / "module_b_impl.py").write_text(make_module_b_source())
+    _ = (source_dir / "repo_a_impl.py").write_text(make_repo_a_source())
+    _ = (source_dir / "repo_b_impl.py").write_text(make_repo_b_source())
 
     # Create docs directory
     docs_dir = repo_path / "docs"
@@ -89,8 +89,8 @@ def create_demo_files(sphinx_base_dir: Path, git_repo_setup: Path):
 
     curr_dir = Path(__file__).absolute().parent
     _ = shutil.copyfile(
-        curr_dir / "expected_module_grouped.json",
-        repo_path / ".expected_module_grouped.json",
+        curr_dir / "expected_repo_grouped.json",
+        repo_path / ".expected_repo_grouped.json",
     )
 
     # Commit everything
@@ -102,45 +102,53 @@ def create_demo_files(sphinx_base_dir: Path, git_repo_setup: Path):
     )
 
 
-def make_module_a_source():
-    return """
-# Module A implementation
-# """+"""req-Id: MOD_REQ_1
-def module_a_function():
+def make_repo_a_source():
+    return (
+        """
+# Repo A implementation
+# """
+        + """req-Id: MOD_REQ_1
+def repo_a_function():
     pass
 
-# """+"""req-Id: MOD_REQ_2
-class ModuleAClass:
+# """
+        + """req-Id: MOD_REQ_2
+class RepoAClass:
     pass
 """
+    )
 
 
-def make_module_b_source():
-    return """
-# Module B implementation
-# """+"""req-Id: MOD_REQ_1
-def module_b_function():
+def make_repo_b_source():
+    return (
+        """
+# Repo B implementation
+# """
+        + """req-Id: MOD_REQ_1
+def repo_b_function():
     pass
 
-# """+"""req-Id: MOD_REQ_3
-def another_module_b_function():
+# """
+        + """req-Id: MOD_REQ_3
+def another_repo_b_function():
     pass
 """
+    )
 
 
 def make_test_xml():
     # ruff: noqa: E501 (start)
     return """
 <testsuites>
-  <testsuite name="ModuleTests" tests="2" failures="0" errors="0" time="0.123">
-    <testcase name="test_module_a" classname="" file="src/test_module_a.py" line="10" time="0.056">
+  <testsuite name="RepoTests" tests="2" failures="0" errors="0" time="0.123">
+    <testcase name="test_repo_a" classname="" file="src/test_repo_a.py" line="10" time="0.056">
       <properties>
         <property name="FullyVerifies" value="MOD_REQ_1"/>
         <property name="TestType" value="unit-test"/>
         <property name="DerivationTechnique" value="requirements-analysis"/>
       </properties>
     </testcase>
-    <testcase name="test_module_b" classname="" file="src/test_module_b.py" line="20" time="0.067">
+    <testcase name="test_repo_b" classname="" file="src/test_repo_b.py" line="20" time="0.067">
       <properties>
         <property name="PartiallyVerifies" value="MOD_REQ_3"/>
         <property name="TestType" value="integration-test"/>
@@ -162,7 +170,7 @@ def basic_conf():
 needs_types = [
     dict(
         directive="mod_req",
-        title="Module Requirement",
+        title="Repo Requirement",
         prefix="MOD_REQ_",
         color="#BFD8D2",
         style="node",
@@ -187,15 +195,15 @@ def basic_needs():
 MODULE TESTING
 ==============
 
-.. mod_req:: Module Requirement 1
+.. mod_req:: Repo Requirement 1
    :id: MOD_REQ_1
    :status: valid
 
-.. mod_req:: Module Requirement 2
+.. mod_req:: Repo Requirement 2
    :id: MOD_REQ_2
    :status: open
 
-.. mod_req:: Module Requirement 3
+.. mod_req:: Repo Requirement 3
    :id: MOD_REQ_3
    :status: open
 """
@@ -231,89 +239,89 @@ def _create_app():
     return _create_app
 
 
-def test_module_grouped_cache_generated(
+def test_repo_grouped_cache_generated(
     sphinx_app_setup: Callable[[], SphinxTestApp],
     sphinx_base_dir: Path,
     git_repo_setup: Path,
     create_demo_files: None,
 ):
-    """Happy path: Module grouped cache file is generated after Sphinx build"""
+    """Happy path: Repo grouped cache file is generated after Sphinx build"""
     app = sphinx_app_setup()
     try:
         os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
         app.build()
 
-        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
-        assert module_cache.exists(), "Module grouped cache was not created"
+        repo_cache = app.outdir / "score_repo_grouped_scl_cache.json"
+        assert repo_cache.exists(), "Repo grouped cache was not created"
 
         # Load and verify structure
-        loaded = load_module_source_links_json(module_cache)
+        loaded = load_repo_source_links_json(repo_cache)
         assert isinstance(loaded, list)
-        assert len(loaded) > 0, "Module cache should contain at least one module"
+        assert len(loaded) > 0, "Repo cache should contain at least one repo"
 
-        # Verify each item is a ModuleSourceLinks
+        # Verify each item is a RepoSourceLinks
         for item in loaded:
-            assert hasattr(item, "module")
+            assert hasattr(item, "repo")
             assert hasattr(item, "needs")
-            assert isinstance(item.module, ModuleInfo)
+            assert isinstance(item.repo, RepoInfo)
 
     finally:
         app.cleanup()
 
 
-def test_module_grouping_preserves_metadata(
+def test_repo_grouping_preserves_metadata(
     sphinx_app_setup: Callable[[], SphinxTestApp],
     sphinx_base_dir: Path,
     git_repo_setup: Path,
     create_demo_files: None,
 ):
-    """Happy path: Module metadata (name, hash, url) is preserved in cache"""
+    """Happy path: Repo metadata (name, hash, url) is preserved in cache"""
     app = sphinx_app_setup()
     try:
         os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
         app.build()
 
-        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
-        loaded = load_module_source_links_json(module_cache)
+        repo_cache = app.outdir / "score_repo_grouped_scl_cache.json"
+        loaded = load_repo_source_links_json(repo_cache)
 
         # Verify that each module has proper metadata
-        for module_links in loaded:
-            assert module_links.module.name is not None
-            assert isinstance(module_links.module.name, str)
+        for repo_links in loaded:
+            assert repo_links.repo.name is not None
+            assert isinstance(repo_links.repo.name, str)
             # Hash and URL might be empty strings for local module
-            assert module_links.module.hash is not None
-            assert module_links.module.url is not None
+            assert repo_links.repo.hash is not None
+            assert repo_links.repo.url is not None
 
     finally:
         app.cleanup()
 
 
-def test_module_grouping_multiple_needs_per_module(
+def test_repo_grouping_multiple_needs_per_repo(
     sphinx_app_setup: Callable[[], SphinxTestApp],
     sphinx_base_dir: Path,
     git_repo_setup: Path,
     create_demo_files: None,
 ):
-    """Happy path: Multiple needs from same module are grouped together"""
+    """Happy path: Multiple needs from same repo are grouped together"""
     app = sphinx_app_setup()
     try:
         os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
         app.build()
 
-        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
-        loaded = load_module_source_links_json(module_cache)
+        repo_cache = app.outdir / "score_repo_grouped_scl_cache.json"
+        loaded = load_repo_source_links_json(repo_cache)
 
-        # Find the local_module (should have all 3 requirements)
-        local_module = None
+        # Find the local_repo (should have all 3 requirements)
+        local_repo = None
         for m in loaded:
-            if m.module.name == "local_module":
-                local_module = m
+            if m.repo.name == "local_repo":
+                local_repo = m
                 break
 
-        assert local_module is not None, "local_module not found in grouped cache"
+        assert local_repo is not None, "local_repo not found in grouped cache"
 
-        # All 3 MOD_REQ should be in this module
-        need_ids = {need.need for need in local_module.needs}
+        # All 3 MOD_REQ should be in this repo
+        need_ids = {need.need for need in local_repo.needs}
         assert (
             "MOD_REQ_1" in need_ids
             or "MOD_REQ_2" in need_ids
@@ -324,14 +332,14 @@ def test_module_grouping_multiple_needs_per_module(
         app.cleanup()
 
 
-def test_module_cache_json_format(
+def test_repo_cache_json_format(
     sphinx_app_setup: Callable[[], SphinxTestApp],
     sphinx_base_dir: Path,
     git_repo_setup: Path,
     create_demo_files: None,
 ):
     """
-    Module cache JSON has correct
+    Repo cache JSON has correct
     structure and excludes metadata from links
     """
     app = sphinx_app_setup()
@@ -339,30 +347,30 @@ def test_module_cache_json_format(
         os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
         app.build()
 
-        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
+        repo_cache = app.outdir / "score_repo_grouped_scl_cache.json"
 
         # Load as raw JSON to check structure
-        with open(module_cache) as f:
+        with open(repo_cache) as f:
             raw_json = json.load(f)
 
         assert isinstance(raw_json, list)
         assert len(raw_json) > 0
 
-        # Check first module structure
-        first_module = raw_json[0]
-        assert "module" in first_module
-        assert "needs" in first_module
-        assert "name" in first_module["module"]
-        assert "hash" in first_module["module"]
-        assert "url" in first_module["module"]
+        # Check first repo structure
+        first_repo = raw_json[0]
+        assert "repo" in first_repo
+        assert "needs" in first_repo
+        assert "name" in first_repo["repo"]
+        assert "hash" in first_repo["repo"]
+        assert "url" in first_repo["repo"]
 
         # Check that needlinks don't have metadata
-        if first_module["needs"]:
-            first_need = first_module["needs"][0]
+        if first_repo["needs"]:
+            first_need = first_repo["needs"][0]
             if "links" in first_need and first_need["links"].get("CodeLinks"):
                 codelink = first_need["links"]["CodeLinks"][0]
-                assert "module_name" not in codelink, (
-                    "CodeLinks should not contain module_name metadata"
+                assert "repo_name" not in codelink, (
+                    "CodeLinks should not contain repo_name metadata"
                 )
                 assert "hash" not in codelink, (
                     "CodeLinks should not contain hash metadata"
@@ -375,33 +383,33 @@ def test_module_cache_json_format(
         app.cleanup()
 
 
-def test_module_cache_rebuilds_when_missing(
+def test_repo_cache_rebuilds_when_missing(
     sphinx_app_setup: Callable[[], SphinxTestApp],
     sphinx_base_dir: Path,
     git_repo_setup: Path,
     create_demo_files: None,
 ):
-    """Edge case: Module cache is regenerated if deleted"""
+    """Edge case: Repo cache is regenerated if deleted"""
     app = sphinx_app_setup()
     try:
         os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
         app.build()
 
-        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
-        assert module_cache.exists()
+        repo_cache = app.outdir / "score_repo_grouped_scl_cache.json"
+        assert repo_cache.exists()
 
         # Delete the cache
-        module_cache.unlink()
-        assert not module_cache.exists()
+        repo_cache.unlink()
+        assert not repo_cache.exists()
 
         # Build again - should regenerate
         app2 = sphinx_app_setup()
         app2.build()
 
-        assert module_cache.exists(), "Cache should be regenerated on rebuild"
+        assert repo_cache.exists(), "Cache should be regenerated on rebuild"
 
         # Verify it's valid
-        loaded = load_module_source_links_json(module_cache)
+        loaded = load_repo_source_links_json(repo_cache)
         assert len(loaded) > 0
 
         app2.cleanup()
@@ -409,50 +417,50 @@ def test_module_cache_rebuilds_when_missing(
         app.cleanup()
 
 
-def test_module_grouping_with_golden_file(
+def test_repo_grouping_with_golden_file(
     sphinx_app_setup: Callable[[], SphinxTestApp],
     sphinx_base_dir: Path,
     git_repo_setup: Path,
     create_demo_files: None,
 ):
-    """Happy path: Generated module cache matches expected golden file"""
+    """Happy path: Generated repo cache matches expected golden file"""
     app = sphinx_app_setup()
     try:
         os.environ["BUILD_WORKSPACE_DIRECTORY"] = str(sphinx_base_dir)
         app.build()
 
-        module_cache = app.outdir / "score_module_grouped_scl_cache.json"
-        expected_file = sphinx_base_dir / ".expected_module_grouped.json"
+        repo_cache = app.outdir / "score_repo_grouped_scl_cache.json"
+        expected_file = sphinx_base_dir / ".expected_repo_grouped.json"
 
-        assert module_cache.exists()
+        assert repo_cache.exists()
         assert expected_file.exists(), "Golden file not found"
 
-        with open(module_cache) as f1:
-            actual = json.load(f1, object_hook=ModuleSourceLinks_JSON_Decoder)
+        with open(repo_cache) as f1:
+            actual = json.load(f1, object_hook=RepoSourceLinks_JSON_Decoder)
         with open(expected_file) as f2:
-            expected = json.load(f2, object_hook=ModuleSourceLinks_JSON_Decoder)
+            expected = json.load(f2, object_hook=RepoSourceLinks_JSON_Decoder)
 
         assert len(actual) == len(expected), (
-            f"Module count mismatch. Actual: {len(actual)}, Expected: {len(expected)}"
+            f"Repo count mismatch. Actual: {len(actual)}, Expected: {len(expected)}"
         )
 
-        # Compare module by module
-        actual_by_name = {m.module.name: m for m in actual}
-        expected_by_name = {m.module.name: m for m in expected}
+        # Compare repo by repo
+        actual_by_name = {m.repo.name: m for m in actual}
+        expected_by_name = {m.repo.name: m for m in expected}
 
         assert set(actual_by_name.keys()) == set(expected_by_name.keys()), (
-            f"Module names don't match. "
+            f"Repo names don't match. "
             f"Actual: {set(actual_by_name.keys())}, "
             f"Expected: {set(expected_by_name.keys())}"
         )
 
-        for module_name in actual_by_name:
-            actual_module = actual_by_name[module_name]
-            expected_module = expected_by_name[module_name]
+        for repo_name in actual_by_name:
+            actual_repo = actual_by_name[repo_name]
+            expected_repo = expected_by_name[repo_name]
 
-            assert actual_module.module.hash == expected_module.module.hash
-            assert actual_module.module.url == expected_module.module.url
-            assert len(actual_module.needs) == len(expected_module.needs)
+            assert actual_repo.repo.hash == expected_repo.repo.hash
+            assert actual_repo.repo.url == expected_repo.repo.url
+            assert len(actual_repo.needs) == len(expected_repo.needs)
 
     finally:
         app.cleanup()
diff --git a/src/extensions/score_source_code_linker/tests/test_module_source_links.py b/src/extensions/score_source_code_linker/tests/test_repo_source_links.py
similarity index 76%
rename from src/extensions/score_source_code_linker/tests/test_module_source_links.py
rename to src/extensions/score_source_code_linker/tests/test_repo_source_links.py
index 293cdc76e..bcb7a7661 100644
--- a/src/extensions/score_source_code_linker/tests/test_module_source_links.py
+++ b/src/extensions/score_source_code_linker/tests/test_repo_source_links.py
@@ -17,13 +17,13 @@
 
 import pytest
 
-from src.extensions.score_source_code_linker.module_source_links import (
-    ModuleInfo,
-    ModuleSourceLinks,
-    ModuleSourceLinks_JSON_Decoder,
-    group_needs_by_module,
-    load_module_source_links_json,
-    store_module_source_links_json,
+from src.extensions.score_source_code_linker.repo_source_links import (
+    RepoInfo,
+    RepoSourceLinks,
+    RepoSourceLinks_JSON_Decoder,
+    group_needs_by_repo,
+    load_repo_source_links_json,
+    store_repo_source_links_json,
 )
 from src.extensions.score_source_code_linker.need_source_links import (
     NeedSourceLinks,
@@ -84,13 +84,13 @@ def SourceCodeLinks_TEST_JSON_Decoder(
     return d
 
 
-class ModuleSourceLinks_TEST_JSON_Encoder(json.JSONEncoder):
+class repoSourceLinks_TEST_JSON_Encoder(json.JSONEncoder):
     def default(self, o: object) -> str | dict[str, Any]:
         if isinstance(o, Path):
             return str(o)
         # We do not want to save the metadata inside the codelink or testlink
         # As we save this already in a structure above it
-        # (hash, module_name, url)
+        # (hash, repo_name, url)
         if isinstance(o, NeedLink | DataForTestLink):
             d = o.to_dict_without_metadata()
             tag = d.get("tag", "")
@@ -104,9 +104,9 @@ def default(self, o: object) -> str | dict[str, Any]:
         # dictionaries won't get split up and we will not
         # run into the 'to_dict_without_metadata' as
         # everything will be converted to a normal dictionary
-        if isinstance(o, ModuleSourceLinks):
+        if isinstance(o, RepoSourceLinks):
             return {
-                "module": asdict(o.module),
+                "repo": asdict(o.repo),
                 "needs": o.needs,  # Let the encoder handle the list
             }
         if isinstance(o, SourceCodeLinks):
@@ -122,17 +122,17 @@ def default(self, o: object) -> str | dict[str, Any]:
         return super().default(o)
 
 
-def ModuleSourceLinks_TEST_JSON_Decoder(
+def repoSourceLinks_TEST_JSON_Decoder(
     d: dict[str, Any],
-) -> ModuleSourceLinks | dict[str, Any]:
-    if "module" in d and "needs" in d:
-        module = d["module"]
+) -> RepoSourceLinks | dict[str, Any]:
+    if "repo" in d and "needs" in d:
+        repo = d["repo"]
         needs = d["needs"]
-        return ModuleSourceLinks(
-            module=ModuleInfo(
-                name=module.get("name"),
-                hash=module.get("hash"),
-                url=module.get("url"),
+        return RepoSourceLinks(
+            repo=RepoInfo(
+                name=repo.get("name"),
+                hash=repo.get("hash"),
+                url=repo.get("url"),
             ),
             # We know this can only be list[SourceCodeLinks] and nothing else
             # Therefore => we ignore the type error here
@@ -143,21 +143,21 @@ def ModuleSourceLinks_TEST_JSON_Decoder(
 
 def test_json_encoder_removes_metadata_from_needlink():
     """Happy path: NeedLink metadata fields are excluded from JSON output"""
-    encoder = ModuleSourceLinks_TEST_JSON_Encoder()
+    encoder = repoSourceLinks_TEST_JSON_Encoder()
     needlink = NeedLink(
         file=Path("src/test.py"),
         line=10,
         tag="#" + " req-Id:",
         need="REQ_1",
         full_line="#" + " req-Id: REQ_1",
-        module_name="test_module",
+        repo_name="test_repo",
         url="https://github.com/test/repo",
         hash="abc123",
     )
     result = encoder.default(needlink)
 
     assert isinstance(result, dict)
-    assert "module_name" not in result
+    assert "repo_name" not in result
     assert "url" not in result
     assert "hash" not in result
     assert result["need"] == "REQ_1"
@@ -166,7 +166,7 @@ def test_json_encoder_removes_metadata_from_needlink():
 
 def test_json_encoder_removes_metadata_from_testlink():
     """Happy path: DataForTestLink metadata fields are excluded from JSON output"""
-    encoder = ModuleSourceLinks_TEST_JSON_Encoder()
+    encoder = repoSourceLinks_TEST_JSON_Encoder()
     testlink = DataForTestLink(
         name="test_something",
         file=Path("src/test_file.py"),
@@ -175,14 +175,14 @@ def test_json_encoder_removes_metadata_from_testlink():
         verify_type="fully",
         result="passed",
         result_text="",
-        module_name="test_module",
+        repo_name="test_repo",
         url="https://github.com/test/repo",
         hash="abc123",
     )
     result = encoder.default(testlink)
 
     assert isinstance(result, dict)
-    assert "module_name" not in result
+    assert "repo_name" not in result
     assert "url" not in result
     assert "hash" not in result
     assert result["name"] == "test_something"
@@ -191,7 +191,7 @@ def test_json_encoder_removes_metadata_from_testlink():
 
 def test_json_encoder_converts_path_to_string():
     """Happy path: Path objects are converted to strings"""
-    encoder = ModuleSourceLinks_TEST_JSON_Encoder()
+    encoder = repoSourceLinks_TEST_JSON_Encoder()
     result = encoder.default(Path("/test/path/file.py"))
     assert result == "/test/path/file.py"
     assert isinstance(result, str)
@@ -202,10 +202,10 @@ def test_json_encoder_converts_path_to_string():
 # ============================================================================
 
 
-def test_json_decoder_reconstructs_module_source_links():
-    """Happy path: Valid JSON dict is decoded into ModuleSourceLinks"""
+def test_json_decoder_reconstructs_repo_source_links():
+    """Happy path: Valid JSON dict is decoded into repoSourceLinks"""
     json_data: dict[str, Any] = {
-        "module": {"name": "test_module", "hash": "hash1", "url": "url1"},
+        "repo": {"name": "test_repo", "hash": "hash1", "url": "url1"},
         "needs": [
             {
                 "need": "REQ_1",
@@ -213,19 +213,19 @@ def test_json_decoder_reconstructs_module_source_links():
             }
         ],
     }
-    result = ModuleSourceLinks_JSON_Decoder(json_data)
+    result = RepoSourceLinks_JSON_Decoder(json_data)
 
-    assert isinstance(result, ModuleSourceLinks)
-    assert result.module.name == "test_module"
-    assert result.module.hash == "hash1"
-    assert result.module.url == "url1"
+    assert isinstance(result, RepoSourceLinks)
+    assert result.repo.name == "test_repo"
+    assert result.repo.hash == "hash1"
+    assert result.repo.url == "url1"
     assert len(result.needs) == 1
 
 
-def test_json_decoder_returns_unchanged_for_non_module_dict():
-    """Edge case: Non-ModuleSourceLinks dicts are returned unchanged"""
+def test_json_decoder_returns_unchanged_for_non_repo_dict():
+    """Edge case: Non-repoSourceLinks dicts are returned unchanged"""
     json_data = {"some": "data", "other": "values"}
-    result = ModuleSourceLinks_JSON_Decoder(json_data)
+    result = RepoSourceLinks_JSON_Decoder(json_data)
     assert result == json_data
 
 
@@ -236,14 +236,14 @@ def test_json_decoder_returns_unchanged_for_non_module_dict():
 
 def test_store_and_load_roundtrip(tmp_path: Path):
     """Happy path: Store and load preserves data correctly"""
-    module = ModuleInfo(name="test_module", hash="hash1", url="url1")
+    repo = RepoInfo(name="test_repo", hash="hash1", url="url1")
     needlink = NeedLink(
         file=Path("src/test.py"),
         line=10,
         tag="#" + " req-Id:",
         need="REQ_1",
         full_line="#" + " req-Id: REQ_1",
-        module_name="test_module",
+        repo_name="test_repo",
         url="url1",
         hash="hash1",
     )
@@ -251,24 +251,24 @@ def test_store_and_load_roundtrip(tmp_path: Path):
         need="REQ_1",
         links=NeedSourceLinks(CodeLinks=[needlink], TestLinks=[]),
     )
-    module_links = ModuleSourceLinks(module=module, needs=[scl])
+    repo_links = RepoSourceLinks(repo=repo, needs=[scl])
 
     test_file = tmp_path / "test.json"
-    store_module_source_links_json(test_file, [module_links])
-    loaded = load_module_source_links_json(test_file)
+    store_repo_source_links_json(test_file, [repo_links])
+    loaded = load_repo_source_links_json(test_file)
 
     assert len(loaded) == 1
-    assert loaded[0].module.name == "test_module"
+    assert loaded[0].repo.name == "test_repo"
     assert loaded[0].needs[0].need == "REQ_1"
 
 
 def test_store_creates_parent_directories(tmp_path: Path):
     """Edge case: Parent directories are created if they don't exist"""
     nested_path = tmp_path / "nested" / "deeply" / "test.json"
-    module = ModuleInfo(name="test", hash="h", url="u")
-    module_links = ModuleSourceLinks(module=module, needs=[])
+    repo = RepoInfo(name="test", hash="h", url="u")
+    repo_links = RepoSourceLinks(repo=repo, needs=[])
 
-    store_module_source_links_json(nested_path, [module_links])
+    store_repo_source_links_json(nested_path, [repo_links])
 
     assert nested_path.exists()
     assert nested_path.parent.exists()
@@ -277,19 +277,19 @@ def test_store_creates_parent_directories(tmp_path: Path):
 def test_load_empty_list(tmp_path: Path):
     """Edge case: Loading empty list returns empty list"""
     test_file = tmp_path / "empty.json"
-    store_module_source_links_json(test_file, [])
+    store_repo_source_links_json(test_file, [])
 
-    loaded = load_module_source_links_json(test_file)
+    loaded = load_repo_source_links_json(test_file)
     assert loaded == []
 
 
 def test_load_validates_is_list(tmp_path: Path):
     """Bad path: Loading non-list JSON fails validation"""
     test_file = tmp_path / "not_list.json"
-    test_file.write_text('{"module": {}, "needs": []}')
+    test_file.write_text('{"repo": {}, "needs": []}')
 
     with pytest.raises(AssertionError, match="should be a list"):
-        load_module_source_links_json(test_file)
+        load_repo_source_links_json(test_file)
 
 
 def test_load_validates_items_are_correct_type(tmp_path: Path):
@@ -297,24 +297,24 @@ def test_load_validates_items_are_correct_type(tmp_path: Path):
     test_file = tmp_path / "invalid_items.json"
     test_file.write_text('[{"invalid": "structure"}]')
 
-    with pytest.raises(AssertionError, match="should be ModuleSourceLink objects"):
-        load_module_source_links_json(test_file)
+    with pytest.raises(AssertionError, match="should be RepoSourceLink objects"):
+        load_repo_source_links_json(test_file)
 
 
 # ============================================================================
-# group_needs_by_module Tests
+# group_needs_by_repo Tests
 # ============================================================================
 
 
-def test_group_needs_single_module_with_codelinks():
-    """Happy path: Multiple needs from same module are grouped together"""
+def test_group_needs_single_repo_with_codelinks():
+    """Happy path: Multiple needs from same repo are grouped together"""
     needlink1 = NeedLink(
         file=Path("src/file1.py"),
         line=10,
         tag="#" + " req-Id:",
         need="REQ_1",
         full_line="#" + " req-Id: REQ_1",
-        module_name="shared_module",
+        repo_name="shared_repo",
         url="https://github.com/test/repo",
         hash="hash1",
     )
@@ -324,7 +324,7 @@ def test_group_needs_single_module_with_codelinks():
         tag="#" + " req-Id:",
         need="REQ_2",
         full_line="#" + " req-Id: REQ_2",
-        module_name="shared_module",
+        repo_name="shared_repo",
         url="https://github.com/test/repo",
         hash="hash1",
     )
@@ -336,25 +336,25 @@ def test_group_needs_single_module_with_codelinks():
         need="REQ_2", links=NeedSourceLinks(CodeLinks=[needlink2], TestLinks=[])
     )
 
-    result = group_needs_by_module([scl1, scl2])
+    result = group_needs_by_repo([scl1, scl2])
 
     assert len(result) == 1
-    assert result[0].module.name == "shared_module"
-    assert result[0].module.hash == "hash1"
+    assert result[0].repo.name == "shared_repo"
+    assert result[0].repo.hash == "hash1"
     assert len(result[0].needs) == 2
     assert len(result[0].needs[0].links.CodeLinks) == 1
     assert len(result[0].needs[1].links.CodeLinks) == 1
 
 
-def test_group_needs_multiple_modules():
-    """Happy path: Needs from different modules create separate groups"""
+def test_group_needs_multiple_repos():
+    """Happy path: Needs from different repos create separate groups"""
     needlink_a = NeedLink(
         file=Path("src/a.py"),
         line=10,
         tag="#" + " req-Id:",
         need="REQ_1",
         full_line="#" + " req-Id: REQ_1",
-        module_name="module_a",
+        repo_name="repo_a",
         url="https://github.com/a/repo",
         hash="hash_a",
     )
@@ -364,7 +364,7 @@ def test_group_needs_multiple_modules():
         tag="#" + " req-Id:",
         need="REQ_2",
         full_line="#" + " req-Id: REQ_2",
-        module_name="module_b",
+        repo_name="repo_b",
         url="https://github.com/b/repo",
         hash="hash_b",
     )
@@ -376,15 +376,15 @@ def test_group_needs_multiple_modules():
         need="REQ_2", links=NeedSourceLinks(CodeLinks=[needlink_b], TestLinks=[])
     )
 
-    result = group_needs_by_module([scl1, scl2])
+    result = group_needs_by_repo([scl1, scl2])
 
     assert len(result) == 2
-    assert result[0].module.name == "module_a"
-    assert result[0].module.hash == "hash_a"
-    assert result[0].module.url == "https://github.com/a/repo"
-    assert result[1].module.name == "module_b"
-    assert result[1].module.hash == "hash_b"
-    assert result[1].module.url == "https://github.com/b/repo"
+    assert result[0].repo.name == "repo_a"
+    assert result[0].repo.hash == "hash_a"
+    assert result[0].repo.url == "https://github.com/a/repo"
+    assert result[1].repo.name == "repo_b"
+    assert result[1].repo.hash == "hash_b"
+    assert result[1].repo.url == "https://github.com/b/repo"
 
 
 def test_group_needs_with_testlinks_only():
@@ -397,7 +397,7 @@ def test_group_needs_with_testlinks_only():
         verify_type="fully",
         result="passed",
         result_text="",
-        module_name="test_module",
+        repo_name="test_repo",
         url="https://github.com/test/repo",
         hash="hash1",
     )
@@ -409,7 +409,7 @@ def test_group_needs_with_testlinks_only():
         verify_type="partially",
         result="passed",
         result_text="",
-        module_name="test_module",
+        repo_name="test_repo",
         url="https://github.com/test/repo",
         hash="hash1",
     )
@@ -423,10 +423,10 @@ def test_group_needs_with_testlinks_only():
         links=NeedSourceLinks(CodeLinks=[], TestLinks=[testlink2]),
     )
 
-    result = group_needs_by_module([scl, scl2])
+    result = group_needs_by_repo([scl, scl2])
 
     assert len(result) == 1
-    assert result[0].module.name == "test_module"
+    assert result[0].repo.name == "test_repo"
     assert len(result[0].needs) == 2
     needs = [x.need for x in result[0].needs]
     assert "REQ_1" in needs
@@ -435,8 +435,8 @@ def test_group_needs_with_testlinks_only():
     assert len(result[0].needs[1].links.TestLinks) == 1
 
 
-def test_group_needs_with_testlinks_different_modules():
-    """Testing Testlinks grouping for different modules"""
+def test_group_needs_with_testlinks_different_repos():
+    """Testing Testlinks grouping for different repos"""
     testlink = DataForTestLink(
         name="test_feature",
         file=Path("tests/test.py"),
@@ -445,7 +445,7 @@ def test_group_needs_with_testlinks_different_modules():
         verify_type="fully",
         result="passed",
         result_text="",
-        module_name="module_a",
+        repo_name="repo_a",
         url="https://github.com/test_a/repo_a",
         hash="hash_a",
     )
@@ -457,7 +457,7 @@ def test_group_needs_with_testlinks_different_modules():
         verify_type="partially",
         result="passed",
         result_text="",
-        module_name="module_b",
+        repo_name="repo_b",
         url="https://github.com/test_b/repo_b",
         hash="hash_b",
     )
@@ -471,20 +471,20 @@ def test_group_needs_with_testlinks_different_modules():
         links=NeedSourceLinks(CodeLinks=[], TestLinks=[testlink2]),
     )
 
-    result = group_needs_by_module([scl, scl2])
+    result = group_needs_by_repo([scl, scl2])
 
     assert len(result) == 2
-    assert result[0].module.name == "module_a"
-    assert result[0].module.hash == "hash_a"
-    assert result[0].module.url == "https://github.com/test_a/repo_a"
-    assert result[1].module.name == "module_b"
-    assert result[1].module.hash == "hash_b"
-    assert result[1].module.url == "https://github.com/test_b/repo_b"
+    assert result[0].repo.name == "repo_a"
+    assert result[0].repo.hash == "hash_a"
+    assert result[0].repo.url == "https://github.com/test_a/repo_a"
+    assert result[1].repo.name == "repo_b"
+    assert result[1].repo.hash == "hash_b"
+    assert result[1].repo.url == "https://github.com/test_b/repo_b"
 
 
 def test_group_needs_empty_list():
     """Edge case: Empty list returns empty result"""
-    result = group_needs_by_module([])
+    result = group_needs_by_repo([])
     assert result == []
 
 
@@ -504,7 +504,7 @@ def test_group_needs_skips_needs_without_links():
                     tag="#" + " req-Id:",
                     need="REQ_1",
                     full_line="#" + " req-Id: REQ_1",
-                    module_name="module_a",
+                    repo_name="repo_a",
                     url="url1",
                     hash="hash1",
                 )
@@ -517,7 +517,7 @@ def test_group_needs_skips_needs_without_links():
         links=NeedSourceLinks(CodeLinks=[], TestLinks=[]),
     )
 
-    result = group_needs_by_module([scl_with_links, scl_without_links])
+    result = group_needs_by_repo([scl_with_links, scl_without_links])
 
     assert len(result) == 1
     assert result[0].needs[0].need == "REQ_1"
@@ -532,7 +532,7 @@ def test_group_needs_mixed_codelinks_and_testlinks():
         tag="#" + " req-Id:",
         need="REQ_1",
         full_line="#" + " req-Id: REQ_1",
-        module_name="module_a",
+        repo_name="repo_a",
         url="https://github.com/test/repo",
         hash="hash1",
     )
@@ -544,7 +544,7 @@ def test_group_needs_mixed_codelinks_and_testlinks():
         verify_type="fully",
         result="passed",
         result_text="",
-        module_name="module_a",
+        repo_name="repo_a",
         url="https://github.com/test/repo",
         hash="hash1",
     )
@@ -554,7 +554,7 @@ def test_group_needs_mixed_codelinks_and_testlinks():
         links=NeedSourceLinks(CodeLinks=[needlink], TestLinks=[testlink]),
     )
 
-    result = group_needs_by_module([scl])
+    result = group_needs_by_repo([scl])
 
     assert len(result) == 1
     assert len(result[0].needs[0].links.CodeLinks) == 1
diff --git a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
index b6e1ded0b..a92d96311 100644
--- a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
@@ -26,7 +26,7 @@
 from sphinx_needs.data import SphinxNeedsData
 
 from src.extensions.score_source_code_linker.helpers import get_github_link
-from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.needlinks import NeedLink
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
@@ -313,7 +313,7 @@ def example_source_link_text_all_ok(sphinx_base_dir: Path) -> dict[str, list[Nee
                 tag="#" + " req-Id:",
                 need="TREQ_ID_1",
                 full_line="#" + " req-Id: TREQ_ID_1",
-                module_name="local_module",
+                repo_name="local_repo",
                 url="",
                 hash="",
             ),
@@ -323,7 +323,7 @@ def example_source_link_text_all_ok(sphinx_base_dir: Path) -> dict[str, list[Nee
                 tag="#" + " req-Id:",
                 need="TREQ_ID_1",
                 full_line="#" + " req-Id: TREQ_ID_1",
-                module_name="local_module",
+                repo_name="local_repo",
                 url="",
                 hash="",
             ),
@@ -335,7 +335,7 @@ def example_source_link_text_all_ok(sphinx_base_dir: Path) -> dict[str, list[Nee
                 tag="#" + " req-Id:",
                 need="TREQ_ID_2",
                 full_line="#" + " req-Id: TREQ_ID_2",
-                module_name="local_module",
+                repo_name="local_repo",
                 url="",
                 hash="",
             )
@@ -356,7 +356,7 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="fully",
                 result="passed",
                 result_text="",
-                module_name="local_module",
+                repo_name="local_repo",
                 url="",
                 hash="",
             ),
@@ -370,7 +370,7 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="partially",
                 result="passed",
                 result_text="",
-                module_name="local_module",
+                repo_name="local_repo",
                 url="",
                 hash="",
             ),
@@ -382,7 +382,7 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="partially",
                 result="passed",
                 result_text="",
-                module_name="local_module",
+                repo_name="local_repo",
                 url="",
                 hash="",
             ),
@@ -396,7 +396,7 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="partially",
                 result="passed",
                 result_text="",
-                module_name="local_module",
+                repo_name="local_repo",
                 url="",
                 hash="",
             ),
@@ -408,7 +408,7 @@ def example_test_link_text_all_ok(sphinx_base_dir: Path):
                 verify_type="partially",
                 result="passed",
                 result_text="",
-                module_name="local_module",
+                repo_name="local_repo",
                 url="",
                 hash="",
             ),
@@ -434,21 +434,23 @@ def example_source_link_text_non_existent(sphinx_base_dir: Path):
 
 
 def make_source_link(needlinks: list[NeedLink]):
-    metadata= ModuleInfo(
-                name="local_module",
-                url="",
-                hash="",
+    metadata = RepoInfo(
+        name="local_repo",
+        url="",
+        hash="",
+    )
+    return ", ".join(
+        f"{get_github_link(metadata, n)}<>{n.file}:{n.line}" for n in needlinks
     )
-    return ", ".join(f"{get_github_link(metadata,n)}<>{n.file}:{n.line}" for n in needlinks)
 
 
 def make_test_link(testlinks: list[DataForTestLink]):
-    metadata= ModuleInfo(
-                name="local_module",
-                url="",
-                hash="",
+    metadata = RepoInfo(
+        name="local_repo",
+        url="",
+        hash="",
     )
-    return ", ".join(f"{get_github_link(metadata,n)}<>{n.name}" for n in testlinks)
+    return ", ".join(f"{get_github_link(metadata, n)}<>{n.name}" for n in testlinks)
 
 
 def compare_json_files(
diff --git a/src/extensions/score_source_code_linker/tests/test_testlink.py b/src/extensions/score_source_code_linker/tests/test_testlink.py
index 7e49b8983..9d3e8ecab 100644
--- a/src/extensions/score_source_code_linker/tests/test_testlink.py
+++ b/src/extensions/score_source_code_linker/tests/test_testlink.py
@@ -53,7 +53,7 @@ def test_testlink_serialization_roundtrip():
         result="passed",
         result_text="All good",
         # ADAPTED: Added new fields
-        module_name="test_module",
+        repo_name="test_repo",
         hash="abc12345",
         url="https://github.com/org/repo",
     )
@@ -117,7 +117,7 @@ def test_testcaseneed_to_dict_multiple_links():
         PartiallyVerifies="REQ-1, REQ-2",
         FullyVerifies="REQ-3",
         # ADAPTED: Added new fields which are now required for valid TestLinks
-        module_name="test_module",
+        repo_name="test_repo",
         hash="hash123",
         url="http://github.com",
     )
@@ -134,7 +134,7 @@ def test_testcaseneed_to_dict_multiple_links():
         assert link.name == "TC_01"
         assert link.result == "failed"
         # ADAPTED: Verify new fields are propagated
-        assert link.module_name == "test_module"
+        assert link.repo_name == "test_repo"
         assert link.hash == "hash123"
         assert link.url == "http://github.com"
 
@@ -158,7 +158,7 @@ def test_store_and_load_testlinks_roundtrip(tmp_path: Path):
             result="passed",
             result_text="Looks good",
             # ADAPTED: Added new fields
-            module_name="mod1",
+            repo_name="mod1",
             hash="h1",
             url="u1",
         ),
@@ -171,7 +171,7 @@ def test_store_and_load_testlinks_roundtrip(tmp_path: Path):
             result="failed",
             result_text="Needs work",
             # ADAPTED: Added new fields
-            module_name="mod2",
+            repo_name="mod2",
             hash="h2",
             url="u2",
         ),
@@ -197,13 +197,13 @@ def test_datafortestlink_to_dict_full():
         verify_type="fully",
         result="passed",
         result_text="All good",
-        module_name="test_module",
+        repo_name="test_repo",
         hash="abc123",
         url="https://github.com/test/repo",
     )
     result = link.to_dict_full()
 
-    assert result["module_name"] == "test_module"
+    assert result["repo_name"] == "test_repo"
     assert result["hash"] == "abc123"
     assert result["url"] == "https://github.com/test/repo"
     assert result["name"] == "test_full"
@@ -239,7 +239,7 @@ def test_dataoftestcase_check_verifies_fields_missing_both():
         result_text="",
         PartiallyVerifies=None,
         FullyVerifies=None,
-        module_name="mod",
+        repo_name="mod",
         hash="h",
         url="u",
     )
@@ -258,7 +258,7 @@ def test_dataoftestcase_is_valid_fails_on_none_field():
         DerivationTechnique="manual",
         result_text="",
         PartiallyVerifies="REQ_1",
-        module_name="mod",
+        repo_name="mod",
         hash="h",
         url="u",
     )
@@ -294,7 +294,7 @@ def test_dataoftestcase_decoder_valid_dict():
         "result_text": "Good",
         "PartiallyVerifies": "REQ_1",
         "FullyVerifies": "REQ_2",
-        "module_name": "mod",
+        "repo_name": "mod",
         "hash": "h",
         "url": "u",
     }
@@ -325,7 +325,7 @@ def test_store_and_load_data_of_test_case_roundtrip(tmp_path: Path):
             result_text="OK",
             PartiallyVerifies="REQ_A",
             FullyVerifies=None,
-            module_name="mod_a",
+            repo_name="mod_a",
             hash="hash_a",
             url="url_a",
         ),
@@ -339,7 +339,7 @@ def test_store_and_load_data_of_test_case_roundtrip(tmp_path: Path):
             result_text="Failed",
             PartiallyVerifies=None,
             FullyVerifies="REQ_B",
-            module_name="mod_b",
+            repo_name="mod_b",
             hash="hash_b",
             url="url_b",
         ),
diff --git a/src/extensions/score_source_code_linker/tests/test_xml_parser.py b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
index 3c328fedf..7f0438b31 100644
--- a/src/extensions/score_source_code_linker/tests/test_xml_parser.py
+++ b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
@@ -269,7 +269,7 @@ def test_parse_properties():
     derivation_technique="requirements-analysis",
 )
 # ADAPTED: Added patching for metadata functions
-@patch("src.extensions.score_source_code_linker.xml_parser.parse_module_name_from_path")
+@patch("src.extensions.score_source_code_linker.xml_parser.parse_repo_name_from_path")
 def test_read_test_xml_file(
     mock_parse_module: Any,
     tmp_xml_dirs: Callable[..., tuple[Path, Path, Path, Path, Path]],
@@ -278,7 +278,7 @@ def test_read_test_xml_file(
     # ADAPTED: Mock return value to ensure metadata is populated.
     # 'local_module' triggers the path where hash/url are empty strings,
     # which is valid but avoids the need to mock parse_info_from_known_good.
-    mock_parse_module.return_value = "local_module"
+    mock_parse_module.return_value = "local_repo"
 
     _: Path
     dir1: Path
@@ -291,7 +291,7 @@ def test_read_test_xml_file(
     assert isinstance(tcneed, DataOfTestCase)
     assert tcneed.result == "failed"
     # ADAPTED: Verify metadata fields were populated
-    assert tcneed.module_name == "local_module"
+    assert tcneed.repo_name == "local_repo"
     assert tcneed.hash == ""
     assert tcneed.url == ""
 
diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index d44f0854c..2aa791056 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -36,10 +36,11 @@
 from src.extensions.score_source_code_linker.helpers import (
     get_github_link,
     parse_info_from_known_good,
-    parse_module_name_from_path,
+    parse_repo_name_from_path,
 )
-from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.needlinks import (
+    DefaultMetaData,
     MetaData,
 )
 from src.extensions.score_source_code_linker.testlink import (
@@ -82,15 +83,15 @@ def get_metadata_from_test_path(raw_filepath: Path) -> MetaData:
     Will parse out the metadata from the testpath.
     If test is local then the metadata will be:
 
-        "module_name": "local_module",
+        "repo_name": "local_repo",
         "hash": "",
         "url": "",
 
-    Else it will parse the module_name e.g. `score_docs_as_code`
+    Else it will parse the repo_name e.g. `score_docs_as_code`
     match this in the known_good_json and grab the accompanying
     hash, url as well and return metadata like so for example:
 
-          "module_name": "score_docs_as_code",
+          "repo_name": "score_docs_as_code",
           "hash": "c1207676afe6cafd25c35d420e73279a799515d8",
           "url": "https://github.com/eclipse-score/docs-as-code"
 
@@ -110,15 +111,12 @@ def get_metadata_from_test_path(raw_filepath: Path) -> MetaData:
     known_good_json = os.environ.get("KNOWN_GOOD_JSON")
     clean_filepath = clean_test_file_name(raw_filepath)
     # print(f"This is the cleaned filepath: {clean_filepath}")
-    module_name = parse_module_name_from_path(clean_filepath)
-    md: MetaData = {
-        "module_name": module_name,
-        "hash": "",
-        "url": "",
-    }
-    if module_name != "local_module" and known_good_json:
+    repo_name = parse_repo_name_from_path(clean_filepath)
+    md = DefaultMetaData()
+    md["repo_name"] = repo_name
+    if repo_name != "local_repo" and known_good_json:
         md["hash"], md["url"] = parse_info_from_known_good(
-            Path(known_good_json), module_name
+            Path(known_good_json), repo_name
         )
     return md
 
@@ -346,11 +344,11 @@ def construct_and_add_need(app: Sphinx, tn: DataOfTestCase):
     # and either 'Fully' or 'PartiallyVerifies' should not be None here
     assert tn.file is not None
     assert tn.name is not None
-    assert tn.module_name is not None
+    assert tn.repo_name is not None
     assert tn.hash is not None
     assert tn.url is not None
     # Have to build metadata here for the gh link func
-    metadata = ModuleInfo(name=tn.module_name, hash=tn.hash, url=tn.url)
+    metadata = RepoInfo(name=tn.repo_name, hash=tn.hash, url=tn.url)
     # IDK if this is ideal or not
     with contextlib.suppress(BaseException):
         _ = add_external_need(

From ae5969df84b953a6e52a7c26a7780daa5f516e69 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Fri, 20 Mar 2026 10:55:35 +0100
Subject: [PATCH 27/34] Formating & Linting

---
 src/extensions/score_source_code_linker/__init__.py    | 10 +++++-----
 src/extensions/score_source_code_linker/helpers.py     |  3 +--
 .../score_source_code_linker/repo_source_links.py      |  2 --
 .../score_source_code_linker/tests/test_codelink.py    |  4 +---
 .../score_source_code_linker/tests/test_helpers.py     |  2 +-
 .../tests/test_repo_source_links.py                    | 10 +++++-----
 .../tests/test_source_code_link_integration.py         |  2 +-
 src/extensions/score_source_code_linker/xml_parser.py  |  2 +-
 8 files changed, 15 insertions(+), 20 deletions(-)

diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index 59d336ceb..24a2a1bee 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -35,11 +35,6 @@
     generate_source_code_links_json,
 )
 from src.extensions.score_source_code_linker.helpers import get_github_link
-from src.extensions.score_source_code_linker.repo_source_links import (
-    group_needs_by_repo,
-    load_repo_source_links_json,
-    store_repo_source_links_json,
-)
 from src.extensions.score_source_code_linker.need_source_links import (
     group_by_need,
     load_source_code_links_combined_json,
@@ -49,6 +44,11 @@
     load_source_code_links_json,
     load_source_code_links_with_metadata_json,
 )
+from src.extensions.score_source_code_linker.repo_source_links import (
+    group_needs_by_repo,
+    load_repo_source_links_json,
+    store_repo_source_links_json,
+)
 from src.extensions.score_source_code_linker.testlink import (
     load_data_of_test_case_json,
     load_test_xml_parsed_json,
diff --git a/src/extensions/score_source_code_linker/helpers.py b/src/extensions/score_source_code_linker/helpers.py
index b41b7cc56..5311717eb 100644
--- a/src/extensions/score_source_code_linker/helpers.py
+++ b/src/extensions/score_source_code_linker/helpers.py
@@ -13,10 +13,9 @@
 import json
 from pathlib import Path
 
-from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
-
 # Import types that depend on score_source_code_linker
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink, NeedLink
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
     DataOfTestCase,
diff --git a/src/extensions/score_source_code_linker/repo_source_links.py b/src/extensions/score_source_code_linker/repo_source_links.py
index 841c20780..4fbd2adaa 100644
--- a/src/extensions/score_source_code_linker/repo_source_links.py
+++ b/src/extensions/score_source_code_linker/repo_source_links.py
@@ -152,5 +152,3 @@ def group_needs_by_repo(links: list[SourceCodeLinks]) -> list[RepoSourceLinks]:
         RepoSourceLinks(repo=group.repo, needs=group.needs)
         for group in repo_groups.values()
     ]
-
-
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 25387e7ec..b6a277335 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -23,8 +23,6 @@
 from dataclasses import asdict
 from pathlib import Path
 from typing import Any
-from collections import Counter
-from collections.abc import Callable
 
 import pytest
 
@@ -45,7 +43,6 @@
 from src.extensions.score_source_code_linker.helpers import (
     get_github_link,
 )
-from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.needlinks import (
     MetaData,
     NeedLink,
@@ -57,6 +54,7 @@
     store_source_code_links_json,
     store_source_code_links_with_metadata_json,
 )
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.helper_lib import (
     get_current_git_hash,
 )
diff --git a/src/extensions/score_source_code_linker/tests/test_helpers.py b/src/extensions/score_source_code_linker/tests/test_helpers.py
index d55e4517b..86fca65ad 100644
--- a/src/extensions/score_source_code_linker/tests/test_helpers.py
+++ b/src/extensions/score_source_code_linker/tests/test_helpers.py
@@ -25,8 +25,8 @@
     parse_info_from_known_good,
     parse_repo_name_from_path,
 )
-from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.helper_lib import get_current_git_hash
 
 #              ╭──────────────────────────────────────────────────────────╮
diff --git a/src/extensions/score_source_code_linker/tests/test_repo_source_links.py b/src/extensions/score_source_code_linker/tests/test_repo_source_links.py
index bcb7a7661..33a3d0384 100644
--- a/src/extensions/score_source_code_linker/tests/test_repo_source_links.py
+++ b/src/extensions/score_source_code_linker/tests/test_repo_source_links.py
@@ -17,6 +17,11 @@
 
 import pytest
 
+from src.extensions.score_source_code_linker.need_source_links import (
+    NeedSourceLinks,
+    SourceCodeLinks,
+)
+from src.extensions.score_source_code_linker.needlinks import NeedLink
 from src.extensions.score_source_code_linker.repo_source_links import (
     RepoInfo,
     RepoSourceLinks,
@@ -25,11 +30,6 @@
     load_repo_source_links_json,
     store_repo_source_links_json,
 )
-from src.extensions.score_source_code_linker.need_source_links import (
-    NeedSourceLinks,
-    SourceCodeLinks,
-)
-from src.extensions.score_source_code_linker.needlinks import NeedLink
 from src.extensions.score_source_code_linker.testlink import DataForTestLink
 
 """
diff --git a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
index a92d96311..9d604a43a 100644
--- a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
@@ -26,8 +26,8 @@
 from sphinx_needs.data import SphinxNeedsData
 
 from src.extensions.score_source_code_linker.helpers import get_github_link
-from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.needlinks import NeedLink
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
     DataForTestLink_JSON_Decoder,
diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index 2aa791056..f6472a9f8 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -38,11 +38,11 @@
     parse_info_from_known_good,
     parse_repo_name_from_path,
 )
-from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.needlinks import (
     DefaultMetaData,
     MetaData,
 )
+from src.extensions.score_source_code_linker.repo_source_links import RepoInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataOfTestCase,
     store_data_of_test_case_json,

From 78b0095b00934871944d33947ecddcb27435aceb Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Mon, 23 Mar 2026 10:21:50 +0100
Subject: [PATCH 28/34] Rename helpers file

---
 src/extensions/score_draw_uml_funcs/__init__.py                 | 2 +-
 .../score_draw_uml_funcs/{helpers.py => draw_helpers.py}        | 0
 2 files changed, 1 insertion(+), 1 deletion(-)
 rename src/extensions/score_draw_uml_funcs/{helpers.py => draw_helpers.py} (100%)

diff --git a/src/extensions/score_draw_uml_funcs/__init__.py b/src/extensions/score_draw_uml_funcs/__init__.py
index d4a95f39d..3388463b7 100644
--- a/src/extensions/score_draw_uml_funcs/__init__.py
+++ b/src/extensions/score_draw_uml_funcs/__init__.py
@@ -32,7 +32,7 @@
 from pathlib import Path
 from typing import Any, cast
 
-from score_draw_uml_funcs.helpers import (
+from score_draw_uml_funcs.draw_helpers import (
     gen_header,
     gen_interface_element,
     gen_link_text,
diff --git a/src/extensions/score_draw_uml_funcs/helpers.py b/src/extensions/score_draw_uml_funcs/draw_helpers.py
similarity index 100%
rename from src/extensions/score_draw_uml_funcs/helpers.py
rename to src/extensions/score_draw_uml_funcs/draw_helpers.py

From 9c35436dc7ce03760fb641eb399b0c5118e03620 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Mon, 23 Mar 2026 15:57:16 +0100
Subject: [PATCH 29/34] Fix: Bugfixing action

Incremental was passed into every build target regardless if it was
correct or not
---
 docs.bzl | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/docs.bzl b/docs.bzl
index 9eca87261..a7a730e83 100644
--- a/docs.bzl
+++ b/docs.bzl
@@ -189,13 +189,11 @@ def docs(source_dir = "docs", data = [], deps = [], scan_code = [], known_good =
     docs_env = {
         "SOURCE_DIRECTORY": source_dir,
         "DATA": str(data),
-        "ACTION": "incremental",
         "SCORE_SOURCELINKS": "$(location :sourcelinks_json)",
     }
     docs_sources_env = {
         "SOURCE_DIRECTORY": source_dir,
         "DATA": str(data_with_docs_sources),
-        "ACTION": "incremental",
         "SCORE_SOURCELINKS": "$(location :merged_sourcelinks)",
     }
     if known_good:
@@ -204,15 +202,18 @@ def docs(source_dir = "docs", data = [], deps = [], scan_code = [], known_good =
         docs_data.append(known_good)
         combo_data.append(known_good)
 
+    docs_env["ACTION"] = "incremental"
+
     py_binary(
         name = "docs",
         tags = ["cli_help=Build documentation:\nbazel run //:docs"],
         srcs = ["@score_docs_as_code//src:incremental.py"],
         data = docs_data,
         deps = deps,
-        env = docs_env,
+        env = docs_env
     )
 
+    docs_sources_env["ACTION"] = "incremental"
     py_binary(
         name = "docs_combo",
         tags = ["cli_help=Build full documentation with all dependencies:\nbazel run //:docs_combo"],
@@ -228,6 +229,7 @@ def docs(source_dir = "docs", data = [], deps = [], scan_code = [], known_good =
         deprecation = "Target '//:docs_combo_experimental' is deprecated. Use '//:docs_combo' instead.",
     )
 
+    docs_env["ACTION"] = "linkcheck"
     py_binary(
         name = "docs_link_check",
         tags = ["cli_help=Verify Links inside Documentation:\nbazel run //:link_check\n (Note: this could take a long time)"],
@@ -237,24 +239,27 @@ def docs(source_dir = "docs", data = [], deps = [], scan_code = [], known_good =
         env = docs_env
     )
 
+    docs_env["ACTION"] = "check"
     py_binary(
         name = "docs_check",
         tags = ["cli_help=Verify documentation:\nbazel run //:docs_check"],
         srcs = ["@score_docs_as_code//src:incremental.py"],
         data = docs_data,
         deps = deps,
-        env = docs_env,
+        env = docs_env
     )
 
+    docs_env["ACTION"] = "live_preview"
     py_binary(
         name = "live_preview",
         tags = ["cli_help=Live preview documentation in the browser:\nbazel run //:live_preview"],
         srcs = ["@score_docs_as_code//src:incremental.py"],
         data = docs_data,
         deps = deps,
-        env = docs_env,
+        env = docs_env
     )
 
+    docs_sources_env["ACTION"] = "live_preview"
     py_binary(
         name = "live_preview_combo_experimental",
         tags = ["cli_help=Live preview full documentation with all dependencies in the browser:\nbazel run //:live_preview_combo_experimental"],

From fdfeb2be850092fbf4113948c7274e1779b62486 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Mon, 23 Mar 2026 17:21:22 +0100
Subject: [PATCH 30/34] Remove emoji headers

---
 src/extensions/docs/source_code_linker.md | 321 +++++++++++++---------
 1 file changed, 196 insertions(+), 125 deletions(-)

diff --git a/src/extensions/docs/source_code_linker.md b/src/extensions/docs/source_code_linker.md
index e97c4b6f9..d283f1c7f 100644
--- a/src/extensions/docs/source_code_linker.md
+++ b/src/extensions/docs/source_code_linker.md
@@ -8,64 +8,118 @@ This extension integrates with **Bazel** and **sphinx-needs** to automatically g
 
 ## Overview
 
-The extension is split into two main components:
+The feature is split into **two layers**:
 
-- **CodeLink** – Parses source files for template strings and links them to needs.
-- **TestLink** – Parses test.xml outputs inside `bazel-testlogs` to link test cases to requirements.
+1. **Bazel pre-processing (before Sphinx runs)**
+   Generates and aggregates JSON caches containing the raw `source_code_link` findings (and, if available, repository metadata like `repo_name/hash/url`).
 
-Each component stores intermediate data in JSON caches under `_build/` to optimize performance and speed up incremental builds.
+2. **Sphinx extension (during the Sphinx build)**
+   Reads the aggregated JSON, validates and adapts it, and finally injects the links into Sphinx needs in the final layout (**RepoSourceLink**).
+
+This separation makes combo builds faster and more deterministic, because the expensive repository scanning/parsing happens **outside** the Sphinx process.
 
 ---
 
 ## How It Works
 
-### ✅ CodeLink: Source Code Integration
+### Bazel Pre-processing: Source Code Integration (CodeLinks)
+
+The Bazel parts are responsible for producing the **intermediate caches** that the source_code_linker extension later will consumes.
 
-CodeLink scans repository files (excluding `_`, `.`, and binary formats) for requirement tags such as:
+#### Step 1: Per-repository cache generation
 
+All files provided via the `scan_code` attribute to the docs macro will be scanned for the requirement tags.
+A *per repository JSON cache* will be generated and saved.
+This script `scripts_bazel/generate_sourcelinks_cli.py` finds all codelinks per file, and gathers them into
+one JSON cache per repository.
+It also adds metadata to each needlink that is needed in further steps.
+
+Example of requirement tags:
 ```python
 # Choose one or the other, both mentioned here to avoid detection
 # req-Id/req-traceability: <NEED_ID>
 ```
 
-These tags are extracted and matched to Sphinx needs via the `source_code_link` attribute. If a need ID does not exist, a build warning will be raised.
-
-#### Data Flow
-
-1. **File Scanning** (`generate_source_code_links_json.py`)
-   - Filters out files starting with `_`, `.`, or ending in `.pyc`, `.so`, `.exe`, `.bin`.
-   - Searches for template tags: `#<!-- comment prevents parsing this occurance --> req-Id:` and `#<!-- comment prevents parsing this occurance --> req-traceability:`.
-   - Extracts:
-     - File path
-     - Line number
-     - Tag and full line
-     - Associated need ID
-   - Saves data as JSON via `needlinks.py`.
-
-2. **Link Creation**
-   - Git info (file hash) is used to build a GitHub URL to the line in the source file.
-   - Links are injected into needs via the `source_code_link` attribute during the Sphinx build process.
+- Extracts for each match:
+  - File path
+  - Line number
+  - Tag + full line
+  - Associated need ID
+  - Repository Metadata:
+    - repo_name (parsed from filepath) (local_repo if non combo build)
+    - hash (at this stage always blank)
+    - url (at this stage always blank)
 
-#### Example JSON Cache (CodeLinks)
+##### Example JSON cache (per repository)
 
-```
+```json
 [
   {
     "file": "src/extensions/score_metamodel/metamodel.yaml",
     "line": 17,
-    "tag": "#--req-Id:", # added `--` to avoid detection
+    "tag": "#--req-Id:",
     "need": "tool_req__docs_dd_link_source_code_link",
-    "full_line": "#--req-Id: tool_req__docs_dd_link_source_code_link" # added `--` to avoid detection
+    "full_line": "#--req-Id: tool_req__docs_dd_link_source_code_link",
+    "repo_name": "local_repo",
+    "hash": "",
+    "url": ""
   }
 ]
 ```
 
+> Note: `--` is shown in the examples to avoid accidental detection by the parser.
+
+---
+
+#### Step 2: Cache merge step (multi-repo aggregation)
+
+In a second Bazel step `scripts_bazel/merge_sourcelinks.py`, **all per-repo caches** are merged into a **single combined JSON**.
+
+- Input: N JSON caches (one per repo)
+- Output: 1 merged JSON containing all found source_code_links
+
+This step also fills in url & hash if there is a known_good_json provided (e.g. in a combo build)
+
+
+#### Repo metadata rules
+Here are some basic rules regarding the MetaData information
+
+In a combo build, a known_good_json **must** be provided.
+If known_good_json is found then the hash & url will be filled for each need by the script.
+
+Combo build:
+  - `repo_name`: repository name (parsed from filepath in step 1)
+  - `hash`: revision/commit hash (as provided by the known_good_json)
+  - `url`: repository remote URL (as provided by the known_good_json)
+
+Local build:
+  - `repo_name`: 'local_repo'
+  - `hash`: will be empty at this point, and later filled via parsing the git commands
+  - `url`: will be empty at this point, and later filled via parsing the git commands
+
 ---
 
-### ✅ TestLink: Test Result Integration
+### Source Code Linker Extension
+
+1a. **Reads the merged JSON** produced by Bazel
+1b. **Reads test.xml files and generates testlinks JSON**
+2. **Validates and adapts** both JSON cache files
+3. **Merges and converts** them into the final structure: **RepoSourceLink**
 
-TestLink scans test result XMLs from Bazel (bazel-testlogs) or in the folder 'tests-report' and converts each test case with metadata into Sphinx external needs, allowing links from tests to requirements.
+#### Codelinks
+
+Since these are all found in [Bazel step 1](#step-1-per-repository-cache-generation) this essentially does not run
+anymore inside of the source_code_linker extension.
+
+#### Testlinks
+
+TestLink scans test result XMLs from Bazel (bazel-testlogs) or from the folder 'tests-report' and converts each test case with metadata into Sphinx external needs, allowing links from tests to requirements.
 This depends on the `attribute_plugin` in our tooling repository, find it [here](https://github.com/eclipse-score/tooling/tree/main/python_basics/score_pytest)
+
+:::attention
+If TestLinks should be generated in a combo build please ensure that you have the known_good_json added to the docs macro.
+:::
+
 #### Test Tagging Options
 
 ```python
@@ -90,7 +144,7 @@ def test_feature():
 #### Data Flow
 
 1. **XML Parsing** (`xml_parser.py`)
-   - Scans `bazel-testlogs/` for `test.xml` files.
+   - Scans `bazel-testlogs/` or `tests-report` for `test.xml` files.
    - Parses test cases and extracts:
      - Name & Classname
      - File path
@@ -98,6 +152,7 @@ def test_feature():
      - Result (e.g. passed, failed, skipped)
      - Result text (if failed/skipped will check if message was attached to it)
      - Verifications (`PartiallyVerifies`, `FullyVerifies`)
+    - Also parses metadata according to the [metadata rules](#repo-metadata-rules)
 
    - Cases without metadata are logged out as info (not errors).
    - Test cases with metadata are converted into:
@@ -125,17 +180,23 @@ The DataFromTestCase depicts the information gathered about one testcase.
     "result_text": "",
     "PartiallyVerifies": "tool_req__docs_common_attr_title, tool_req__docs_common_attr_description",
     "FullyVerifies": null
+    "repo_name": "local_module",
+    "hash": "",
+    "url": "",
   }
 ]
 ```
 
 ---
 
-## 🔗 Combined Links
 
-During the Sphinx build process, both CodeLink and TestLink data are combined and applied to needs.
+### Early-Combined Links
+
+During the Sphinx build process, both CodeLink and TestLink data are combined and grouped by needs.
+This will allow us to have an easier time building the final JSON which will eliminate the metadata from each link,
+and group all needs according to the appropriate repository.
 
-This is handled in `__init__.py` using the `NeedSourceLinks` and `SourceCodeLinks` dataclasses from `need_source_links.py`.
+This all is handled in `need_source_links.py`.
 
 ### Combined JSON Example
 
@@ -150,7 +211,11 @@ This is handled in `__init__.py` using the `NeedSourceLinks` and `SourceCodeLink
           "line": 33,
           "tag": "#--req-Id:",# added `--` to avoid detection
           "need": "tool_req__docs_common_attr_title",
-          "full_line": "#--req-Id: tool_req__docs_common_attr_title" # added `--` to avoid detection
+          "full_line": "#--req-Id: tool_req__docs_common_attr_title", # added `--` to avoid detection
+          "repo_name": "local_module",
+          "hash": "",
+          "url": "",
+
         }
       ],
       "TestLinks": [
@@ -161,7 +226,10 @@ This is handled in `__init__.py` using the `NeedSourceLinks` and `SourceCodeLink
           "need": "tool_req__docs_common_attr_title",
           "verify_type": "partially",
           "result": "passed",
-          "result_text": ""
+          "result_text": "",
+          "repo_name": "local_module",
+          "hash": "",
+          "url": "",
         }
       ]
     }
@@ -169,36 +237,117 @@ This is handled in `__init__.py` using the `NeedSourceLinks` and `SourceCodeLink
 ]
 ```
 
+#### Final layout: RepoSourceLink
+
+Instead of repeating `repo_name/hash/url` for every single link entry, the final output groups links **by repository**:
+
+- Repository metadata appears **once per repository**
+- All links belonging to that repository are stored beneath it
+
+This somewhat looks like this:
+```json
+[
+  {
+    "repo": {
+      "name": "local_repo",
+      "hash": "",
+      "url": ""
+    },
+    "needs": [
+      {
+        "need": "tool_req__docs_common_attr_id_scheme",
+        "links": {
+          "CodeLinks": [
+            {
+              "file": "src/extensions/score_metamodel/checks/attributes_format.py",
+              "line": 30,
+              "tag": "# req-Id:",
+              "need": "tool_req__docs_common_attr_id_scheme",
+              "full_line": "# req-Id: tool_req__docs_common_attr_id_scheme"
+            }
+          ],
+          "TestLinks": ...
+        }
+      },
+    ],
+    { ... }
+```
+Due to not saving the `repo_name, url and hash` in each link but grouping them we can eleminate a lot of unnecessary
+length to the JSON document here.
+
+This is the structure the extension uses to attach links to needs (via the `source_code_link` attribute), while keeping the resulting data compact and normalized.
+
+:::hint
+Currently if the repo is the local one, SCL is still using the hash and url it gets from executing the git functions parsing.
+This is a known inefficiency and will be improved upon later
+:::
+
+---
+
+## Result: Traceability Links in Needs
+
+During the Sphinx build process, the extension applies the computed links to needs:
+
+- Each need’s `source_code_link` and `testlink` attribute is filled from the (repo-grouped) RepoSourceLink data where applicable.
+- If a referenced need ID does not exist, a build warning will be raised.
 
 ---
 
-## ⚠️ Known Limitations
+## Known Limitations
 
-### CodeLink
+### General
+-  In combo builds, known_good_json is required.
+-  inefficiencies in creating the links and saving the JSON caches
+-  Not compatible with **Esbonio/Live_preview**
 
-- ❌ Not compatible with **Esbonio/Live_preview**
-- 🔗 GitHub links may 404 if the commit isn’t pushed
-- 🧪 Tags must match exactly (e.g. #<!-- comment prevents parsing this occurance --> req-Id)
-- 👀 `source_code_link` isn’t visible until the full Sphinx build is completed
+### Codelinks
+-  GitHub links may 404 if the commit isn’t pushed
+-  Tags must match exactly (e.g. #<!-- comment prevents parsing this occurance --> req-Id)
+-  `source_code_link` isn’t visible until the full Sphinx build is completed
 
 ### TestLink
 
-- ❌ Not compatible with **Esbonio/Live_preview**
-- 🔗 GitHub links may 404 if the commit isn’t pushed
-- 🧪 XML structure must be followed exactly (e.g. `properties & attributes`)
-- 🗂 Relies on test to be executed first
+-  GitHub links may 404 if the commit isn’t pushed
+-  XML structure must be followed exactly (e.g. `properties & attributes`)
+-  Relies on test to be executed first
 
+---
+
+## High-level Data Flow Summary
 
+1. **Bazel Script #1**: scan + parse → write **per-repo cache** (includes repo metadata if known)
+2. **Bazel Script #2**: merge caches → write **single merged JSON**
+3. **Sphinx Extension**: read merged JSON → adapt to **RepoSourceLink** → inject source_code_link and testlink into needs
 
 ---
 
-## 🏗️ Internal Module Overview
+## Clearing Cache Manually
+
+To clear the build cache, run:
 
+```bash
+rm -rf _build/
+```
+
+## Internal  Overview
+
+The bazel part:
+```
+scripts_bazel/
+├── BUILD   # Declare libraries and filegroups needed for bazel
+├── generate_sourcelinks_cli.py # Bazel step 1 => Parses sourcefiles for tags
+├── merge_sourcelinks.py
+└── tests
+│   └── ...
+```
+The Sphinx extension
 ```
 score_source_code_linker/
 ├── __init__.py                   # Main Sphinx extension; combines CodeLinks + TestLinks
-├── generate_source_code_links_json.py  # Parses source files for tags
+├── generate_source_code_links_json.py  # Most functionality moved to 'scripts_bazel/generate_sourcelinks_cli'
 ├── need_source_links.py         # Data model for combined links
+├── repo_source_links.py         # Data model for Repo combined links (Final output JSON)
+├── helpers.py                   # Misc. functions used throughout SCL
 ├── needlinks.py                 # CodeLink dataclass & JSON encoder/decoder
 ├── testlink.py                  # DataForTestLink definition & logic
 ├── xml_parser.py                # Parses XML files into test case data
@@ -222,81 +371,3 @@ To see working examples for CodeLinks & TestLinks, take a look at the Docs-As-Co
 [Example CodeLink](https://eclipse-score.github.io/docs-as-code/main/requirements/requirements.html#tool_req__docs_common_attr_status)
 
 [Example TestLink](https://eclipse-score.github.io/docs-as-code/main/requirements/requirements.html#tool_req__docs_dd_link_source_code_link)
-
-## Flow-Overview
-```{mermaid}
-flowchart TD
-    %% Entry Point
-    A[source_code_linker] --> B{Check for Grouped JSON Cache}
-
-    %% If cache exists
-    B --> |✅| C[Load Grouped JSON Cache]
-    B --> |🔴| N9[Proceed Without Cache]
-
-    %% --- NeedLink Path ---
-    N9 --> D1[needslink.py<br/><b>NeedLink</b>]
-    D1 --> E1{Check for CodeLink JSON Cache}
-
-    E1 --> |✅| F1[Load CodeLink JSON Cache]
-    F1 --> Z[Grouped JSON Cache]
-
-    E1 --> |🔴| G1[Parse all files in repository]
-    G1 --> H1[Build & Save<br/>CodeLink JSON Cache]
-    H1 --> Z
-
-    %% --- TestLink Path ---
-    N9 --> D2[testlink.py<br/><b>DFTL</b>]
-    D2 --> E2{Check for DFTL JSON Cache}
-
-    E2 --> |✅| F2[Load DFTL JSON Cache]
-    F2 --> J2[Load DOTC JSON Cache]
-    J2 --> K2[Add as External Needs]
-
-    E2 --> |🔴| G2[Parse test.xml Files]
-    G2 --> H2[Convert TestCases<br/>to DOTC]
-    H2 --> I2[Build & Save<br/>DOTC JSON Cache]
-    I2 --> K2
-
-    H2 --> M2[Convert to DFTL]
-    M2 --> N2[Build & Save<br/>DFTL JSON Cache]
-    N2 --> Z
-
-    %% Final step
-    Z --> FINAL[<b>Add links to needs</b>]
-
-    %% Legend
-    subgraph Legend["Legend"]
-        direction TB
-        L1[NeedLink Operations]
-        L2[TestLink Operations]
-        L4[DTFL = DataForTestLink]
-        L3[TestCaseNeed Operations]
-        L5[DOTC = DataOfTestCase]
-        L1 ~~~ L2
-        L2 ~~~ L4
-        L4 ~~~ L3
-        L3 ~~~ L5
-    end
-
-    %% Node Styling
-    classDef needlink fill:#3b82f6,color:#ffffff,stroke:#1d4ed8,stroke-width:2px
-    classDef testlink fill:#8b5cf6,color:#ffffff,stroke:#6d28d9,stroke-width:2px
-    classDef dotc fill:#f59e0b,color:#ffffff,stroke:#b45309,stroke-width:2px
-    classDef grouped fill:#10b981,color:#ffffff,stroke:#047857,stroke-width:2px
-    classDef final fill:#f43f5e,color:#ffffff,stroke:#be123c,stroke-width:2px
-
-    %% Class assignments
-    class D1,E1,F1,G1,H1 needlink
-    class D2,E2,F2,G2,M2,N2 testlink
-    class J2,H2,I2,K2 dotc
-    class Z grouped
-    class FINAL final
-    class L1 needlink
-    class L2,L4 testlink
-    class L3,L5 dotc
-
-    %% Edge/Arrow Styling
-    linkStyle default stroke:#22d3ee,stroke-width:2px,color:#22d3ee
-    %% Ensure links in the Legend do not show up
-    linkStyle 23,24,25,26 opacity:0
-```

From 8c7aee6b3b9b7f18ae5c5ce3625fbcbc6c41b550 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 26 Mar 2026 09:25:29 +0100
Subject: [PATCH 31/34] Bugfix, id's should not be uppercase

---
 src/extensions/score_source_code_linker/xml_parser.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index f6472a9f8..ad00c9360 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -356,7 +356,7 @@ def construct_and_add_need(app: Sphinx, tn: DataOfTestCase):
             need_type="testcase",
             title=tn.name,
             tags="TEST",
-            id=f"testcase__{tn.name}_{short_hash(tn.file + tn.name).upper()}",
+            id=f"testcase__{tn.name}_{short_hash(tn.file + tn.name)}",
             name=tn.name,
             external_url=get_github_link(metadata, tn),
             fully_verifies=tn.FullyVerifies if tn.FullyVerifies is not None else "",

From 9473852d9ea838d6bc92b69b71951c3c1577291a Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 26 Mar 2026 09:42:31 +0100
Subject: [PATCH 32/34] Fix myst errors

---
 src/extensions/docs/source_code_linker.md | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/src/extensions/docs/source_code_linker.md b/src/extensions/docs/source_code_linker.md
index d283f1c7f..f6f827669 100644
--- a/src/extensions/docs/source_code_linker.md
+++ b/src/extensions/docs/source_code_linker.md
@@ -26,6 +26,7 @@ This separation makes combo builds faster and more deterministic, because the ex
 
 The Bazel parts are responsible for producing the **intermediate caches** that the source_code_linker extension later will consumes.
 
+(step-1-per-repository-cache-generation)=
 #### Step 1: Per-repository cache generation
 
 All files provided via the `scan_code` attribute to the docs macro will be scanned for the requirement tags.
@@ -52,7 +53,7 @@ Example of requirement tags:
 
 ##### Example JSON cache (per repository)
 
-```json
+```{code-block} json
 [
   {
     "file": "src/extensions/score_metamodel/metamodel.yaml",
@@ -80,7 +81,7 @@ In a second Bazel step `scripts_bazel/merge_sourcelinks.py`, **all per-repo cach
 
 This step also fills in url & hash if there is a known_good_json provided (e.g. in a combo build)
 
-
+(repo-metadata-rules)=
 #### Repo metadata rules
 Here are some basic rules regarding the MetaData information
 
@@ -245,7 +246,7 @@ Instead of repeating `repo_name/hash/url` for every single link entry, the final
 - All links belonging to that repository are stored beneath it
 
 This somewhat looks like this:
-```json
+```{code-block} json
 [
   {
     "repo": {
@@ -266,11 +267,10 @@ This somewhat looks like this:
               "full_line": "# req-Id: tool_req__docs_common_attr_id_scheme"
             }
           ],
-          "TestLinks": ...
+          "TestLinks": []
         }
       },
     ],
-    { ... }
 ```
 Due to not saving the `repo_name, url and hash` in each link but grouping them we can eleminate a lot of unnecessary
 length to the JSON document here.

From feb98632754466426547a7d24d2a46b3f13bc1d5 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 26 Mar 2026 10:16:19 +0100
Subject: [PATCH 33/34] Add config value

---
 src/extensions/score_source_code_linker/__init__.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index 24a2a1bee..29628b5ca 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -301,6 +301,7 @@ def setup_once(app: Sphinx):
 def setup(app: Sphinx) -> dict[str, str | bool]:
     # Esbonio will execute setup() on every iteration.
     # setup_once will only be called once.
+    app.add_config_value("KNOWN_GOOD_JSON", default="",rebuild="env",types=str)
     setup_once(app)
 
     return {

From 2d58de23747cdd103e47fd34bd30c87fbdd62577 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 26 Mar 2026 12:11:15 +0100
Subject: [PATCH 34/34] Fix several small things found by copilot

Fixing assertion
Fixing wrong split in path
Fixing pytest global arguments
---
 pyproject.toml                                        |  1 -
 .../score_source_code_linker/tests/test_helpers.py    |  1 +
 .../tests/test_repo_source_link_integration.py        | 11 ++++++-----
 .../score_source_code_linker/tests/test_xml_parser.py |  6 +++---
 src/extensions/score_source_code_linker/xml_parser.py |  4 ++--
 5 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 8dd24d16b..6aa48c6f3 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -23,7 +23,6 @@ extend-exclude = [
     ".venv*/**",
 ]
 [tool.pytest.ini_options]
-addopts = ["-v", "-s"]
 log_cli = true
 log_cli_level = "Debug"
 log_cli_format = "[%(asctime)s.%(msecs)03d] [%(levelname)-3s] [%(name)s] %(message)s"
diff --git a/src/extensions/score_source_code_linker/tests/test_helpers.py b/src/extensions/score_source_code_linker/tests/test_helpers.py
index 86fca65ad..ab5207bb3 100644
--- a/src/extensions/score_source_code_linker/tests/test_helpers.py
+++ b/src/extensions/score_source_code_linker/tests/test_helpers.py
@@ -323,6 +323,7 @@ def test_get_github_link_with_real_repo(git_repo: Path) -> None:
     assert hash_from_link == actual_hash
 
 
+
 def test_complete_workflow(known_good_json: Path):
     """Test complete workflow from path to GitHub link."""
 
diff --git a/src/extensions/score_source_code_linker/tests/test_repo_source_link_integration.py b/src/extensions/score_source_code_linker/tests/test_repo_source_link_integration.py
index 270fef076..79360e902 100644
--- a/src/extensions/score_source_code_linker/tests/test_repo_source_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_repo_source_link_integration.py
@@ -10,6 +10,11 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 # *******************************************************************************
+
+# ╓                                                          ╖
+# ║ Some portions generated by CoPilot                       ║
+# ╙                                                          ╜
+
 import contextlib
 import json
 import os
@@ -322,11 +327,7 @@ def test_repo_grouping_multiple_needs_per_repo(
 
         # All 3 MOD_REQ should be in this repo
         need_ids = {need.need for need in local_repo.needs}
-        assert (
-            "MOD_REQ_1" in need_ids
-            or "MOD_REQ_2" in need_ids
-            or "MOD_REQ_3" in need_ids
-        )
+        assert {"MOD_REQ_1", "MOD_REQ_2", "MOD_REQ_3"}.issubset(need_ids)
 
     finally:
         app.cleanup()
diff --git a/src/extensions/score_source_code_linker/tests/test_xml_parser.py b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
index 7f0438b31..3a2e110c7 100644
--- a/src/extensions/score_source_code_linker/tests/test_xml_parser.py
+++ b/src/extensions/score_source_code_linker/tests/test_xml_parser.py
@@ -359,7 +359,7 @@ def test_clean_test_file_name_combo_path():
 def test_clean_test_file_name_tests_report_path():
     raw_path = Path("/some/path/tests-report/test-report/unit/test_module.xml")
     result = xml_parser.clean_test_file_name(raw_path)
-    assert result == Path("unit/test_module.xml")
+    assert result == Path("test-report/unit/test_module.xml")
 
 
 def test_clean_test_file_name_nested_bazel_testlogs():
@@ -371,7 +371,7 @@ def test_clean_test_file_name_nested_bazel_testlogs():
 def test_clean_test_file_name_invalid_path_raises_error():
     raw_path = Path("/invalid/path/without/markers/test.xml")
     with pytest.raises(
-        ValueError, match="Filepath does not have 'bazel-testlogs' nor 'test-report'"
+        ValueError, match="Filepath does not have 'bazel-testlogs' nor 'tests-report'"
     ):
         xml_parser.clean_test_file_name(raw_path)
 
@@ -379,6 +379,6 @@ def test_clean_test_file_name_invalid_path_raises_error():
 def test_clean_test_file_name_empty_path_raises_error():
     raw_path = Path("")
     with pytest.raises(
-        ValueError, match="Filepath does not have 'bazel-testlogs' nor 'test-report'"
+        ValueError, match="Filepath does not have 'bazel-testlogs' nor 'tests-report'"
     ):
         xml_parser.clean_test_file_name(raw_path)
diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index ad00c9360..cfa41f7f3 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -71,10 +71,10 @@ def clean_test_file_name(raw_filepath: Path) -> Path:
     if "bazel-testlogs" in str(raw_filepath):
         return Path(str(raw_filepath).split("bazel-testlogs/")[-1])
     if "tests-report" in str(raw_filepath):
-        return Path(str(raw_filepath).split("test-report/")[-1])
+        return Path(str(raw_filepath).split("tests-report/")[-1])
     raise ValueError(
         "Filepath does not have 'bazel-testlogs' nor "
-        f"'test-report'. Filepath: {raw_filepath}"
+        + f"'tests-report'. Filepath: {raw_filepath}"
     )