feat: Prosa ist kein Identifier - Link-Taxonomie als Enum, generierte Regionen mit Markern (4.0.0)

Files changed:
- .gitea/workflows/ci.yml
- AGENTS.md
- CHANGES.md
- VERSION
- instructions/CONTRACT.md
- instructions/link-taxonomy.md
- instructions/migrations/4.0.0-link-taxonomy.md
- instructions/setup-instance.md
- kb/CONTRACT.md
- kb/CONVENTIONS.md
- kb/CONVENTIONS.md.template
- kb/comparisons/COLLECTION.md
- kb/concepts/COLLECTION.md
- kb/entities/COLLECTION.md
- kb/sources/COLLECTION.md
- tools/CONTRACT.md
- tools/README.md
- tools/chemenu/blocks.py
- tools/chemenu/cli.py
- tools/chemenu/commands/cite_cmd.py
- tools/chemenu/commands/dist_cmd.py
- tools/chemenu/commands/docs_verify.py
- tools/chemenu/commands/doctor.py
- tools/chemenu/commands/links_cmd.py
- tools/chemenu/commands/migrate_cmd.py
- tools/chemenu/commands/new_page.py
- tools/chemenu/commands/page_ops.py
- tools/chemenu/commands/run_budget.py
- tools/chemenu/commands/xref.py
- tools/chemenu/conventions.py
- tools/chemenu/corpus_diff.py
- tools/chemenu/frontmatter_io.py
- tools/chemenu/kb_collections.py
- tools/chemenu/kb_state.py
- tools/chemenu/links.py
- tools/chemenu/lint_core.py
- tools/chemenu/provenance.py
- tools/chemenu/sections.py
- tools/chemenu/tests/conftest.py
- tools/chemenu/tests/test_blocks.py
- tools/chemenu/tests/test_cite_cmd.py
- tools/chemenu/tests/test_conventions.py
- tools/chemenu/tests/test_dist_cmd.py
- tools/chemenu/tests/test_doctor.py
- tools/chemenu/tests/test_migrate_cmd.py
- tools/chemenu/tests/test_new_page.py
- tools/chemenu/tests/test_pipeline_l0.py
- tools/chemenu/tests/test_types_cmd.py
- tools/chemenu/tests/test_xref.py
- types/concept.schema.yaml
- types/entity.md
- types/entity.schema.yaml
- types/instruction.schema.yaml
- types/type-spec.md
- work/link-taxonomy-migration/README.md
- work/link-taxonomy-migration/plan.md

tools/chemenu/lint_core.py

@@ -16,7 +16,7 @@ from __future__ import annotations
 from datetime import date
 from pathlib import Path
 
-from chemenu import config
+from chemenu import blocks, config, kb_collections, links
 from chemenu.frontmatter_io import frontmatter_error
 from chemenu.markdown_code import strip_code_spans
 from chemenu.provenance import broken_raw_refs as find_broken_raw_refs
@@ -164,7 +164,16 @@ def run_lint(kb_dir: Path) -> dict:
     # propagated, a deleted page, or a URL pasted where a title belongs - used
     # to pass every check. Which fields hold page titles is declared by each
     # type-spec's `page_ref_fields:`, not hardcoded here.
+    def _collection_of(page):
+        try:
+            return page.path.relative_to(config.KB_DIR).parts[0]
+        except (ValueError, IndexError):
+            return None
+
     dangling_frontmatter_refs = []
+    malformed_edges: list[dict] = []
+    unlabelled_edges: list[dict] = []
+    unauthorised_labels: list[dict] = []
     for title, page in sorted(pages.items()):
         type_path = page.frontmatter.get("type")
         if not type_path:
@@ -174,11 +183,53 @@ def run_lint(kb_dir: Path) -> dict:
         except ValueError:
             continue  # unresolvable type is already reported as type_resolution_errors
         for field in ref_fields:
-            for target in page.frontmatter.get(field) or []:
+            # Through `links` so a labelled edge (`- depends-on: Hermes`) is read
+            # as its target rather than as a mapping - the entry carries the
+            # label alongside the title now, and comparing the whole entry would
+            # report every declared edge as dangling.
+            for target in links.targets(page.frontmatter, field):
                 if target not in pages:
                     dangling_frontmatter_refs.append(
                         {"page": title, "field": field, "target": target}
                     )
+            for entry in links.malformed(page.frontmatter, field):
+                malformed_edges.append(
+                    {"page": title, "field": field, "entry": str(entry)}
+                )
+        # Labels are checked on `related:` only. `sources:`/`entities:`/
+        # `concepts:` are the provenance path, unlabelled by construction.
+        if "related" in ref_fields:
+            source_collection = _collection_of(page)
+            for edge in links.edges(page.frontmatter, "related"):
+                if not edge.is_labelled:
+                    unlabelled_edges.append({"page": title, "target": edge.target})
+                    continue
+                target_page = pages.get(edge.target)
+                if source_collection is None or target_page is None:
+                    continue
+                destination = _collection_of(target_page)
+                if destination is None:
+                    continue
+                allowed = kb_collections.authorised_labels(source_collection, destination)
+                if edge.label not in allowed:
+                    unauthorised_labels.append(
+                        {
+                            "page": title,
+                            "target": edge.target,
+                            "label": edge.label,
+                            "destination": destination,
+                        }
+                    )
+
+    # A generated region whose markers do not pair up is not a tidiness problem:
+    # the next write appends a second region beside it instead of replacing it,
+    # and the page then carries two. An agent rewriting prose at the boundary is
+    # how a marker goes missing, which is why this is a hard error.
+    unbalanced_marker_findings = [
+        {"page": title, "region": name}
+        for title, page in sorted(pages.items())
+        for name in blocks.unbalanced_markers(page.body)
+    ]
 
     quote_limit_violations = []
     for title, page in sorted(pages.items()):
@@ -238,6 +289,10 @@ def run_lint(kb_dir: Path) -> dict:
         "undefined_footnote_refs": undefined_footnote_refs,
         "orphan_footnote_defs": orphan_footnote_defs,
         "dangling_frontmatter_refs": dangling_frontmatter_refs,
+        "malformed_edges": malformed_edges,
+        "unlabelled_edges": unlabelled_edges,
+        "unauthorised_labels": unauthorised_labels,
+        "unbalanced_markers": unbalanced_marker_findings,
         "quote_limit_violations": quote_limit_violations,
         "invalid_type_paths": invalid_type_paths,
         "type_resolution_errors": type_resolution_errors,
@@ -322,6 +377,23 @@ def render_markdown(report: dict) -> str:
         lines, "Orphan Footnote Definitions", report["orphan_footnote_defs"],
         lambda i: f"[[{i['page']}]] defines `[^{i['id']}]` (-> [[{i['source']}]]) but nothing references it - run `wikitool cite sync`",
     )
+    _section(
+        lines, "Malformed Edges", report.get("malformed_edges", []),
+        lambda i: f"[[{i['page']}]] `{i['field']}`: {i['entry']}",
+    )
+    _section(
+        lines, "Unbalanced Generated-Region Markers", report.get("unbalanced_markers", []),
+        lambda i: f"[[{i['page']}]]: `{i['region']}`",
+    )
+    _section(
+        lines, "Unlabelled Edges", report.get("unlabelled_edges", []),
+        lambda i: f"[[{i['page']}]] -> [[{i['target']}]]",
+    )
+    _section(
+        lines, "Labels Not Authorised by the Source Collection",
+        report.get("unauthorised_labels", []),
+        lambda i: f"[[{i['page']}]] `{i['label']}` -> kb/{i['destination']}/ ([[{i['target']}]])",
+    )
     _section(
         lines, "Dangling Frontmatter References", report["dangling_frontmatter_refs"],
         lambda i: f"[[{i['page']}]] `{i['field']}:` names `{i['target']}`, which is not a page",
@@ -406,6 +478,16 @@ def default_report_path(report: dict) -> Path:
 # through the index or navigation only. `quote_limit_violations` is advisory
 # too - it flags a habit, not a broken tree.
 #
+# `unlabelled_edges` and `unauthorised_labels` are advisory **for now**, and
+# that is a dated decision rather than a judgment about severity: they describe
+# exactly the state a corpus is in between the 4.0.0 machinery landing and the
+# migration reaching each page, which is the window `.wikitool-kb.json` exists
+# to represent. They become hard errors once the migration is recorded - the
+# same path `legacy_citation_markers` took.
+#
+# `malformed_edges` and `unbalanced_markers` are hard from the start: neither
+# describes an unconverted page, only a broken one.
+#
 # One definition, used by `lint --fail-on-error` and by the eval scorecard: if
 # the two disagreed, a run could pass its score while lint refused it.
 HARD_ERROR_KEYS = (
@@ -421,6 +503,8 @@ HARD_ERROR_KEYS = (
     "undefined_footnote_refs",
     "orphan_footnote_defs",
     "dangling_frontmatter_refs",
+    "malformed_edges",
+    "unbalanced_markers",
     "invalid_type_paths",
     "type_resolution_errors",
     "schema_validation_errors",