feat(okf): in-import cross-link graph — extract/resolve/reject links, dangling-link signal (T5a/A, TDD, +10)

tests/test_okf.py

@@ -26,11 +26,15 @@ from llm_ingestion_guard.okf import (
     trust_for,
     format_log_entry,
     import_bundle,
+    extract_link_targets,
+    resolve_link,
+    link_graph,
     Origin,
     Channel,
     OKFFrontmatterError,
     OKFPathError,
     OKFResourceError,
+    OKFLinkError,
 )
 from llm_ingestion_guard.report import Report
 from llm_ingestion_guard.disposition import Trust, Disposition
@@ -378,3 +382,65 @@ def test_import_bundle_records_origin_channel_on_stamp():
     assert stamp.trust is Trust.TRUSTED
     assert stamp.origin is Origin.INTERNAL
     assert stamp.channel is Channel.MANUAL
+
+
+# --- T5a/A: cross-link extraction, target validation, in-import resolution ----
+# OKF links are markdown `.md` paths, bundle-absolute (`/x.md`, recommended) or
+# relative (`./x.md`); verified against SPEC.md. In-import graph only (A); the
+# cross-run persisted graph (B) is deferred to stream 2 (see docs/PLAN.md).
+
+def test_extract_link_targets_pulls_markdown_destinations():
+    body = "See [users](/tables/users.md) and [orders](./orders.md) for detail."
+    assert extract_link_targets(body) == ["/tables/users.md", "./orders.md"]
+
+
+def test_resolve_link_bundle_absolute_to_concept_id():
+    assert resolve_link("/tables/customers.md", "docs/intro") == "tables/customers"
+
+
+def test_resolve_link_relative_to_concept_id():
+    assert resolve_link("./other.md", "tables/users") == "tables/other"
+
+
+def test_resolve_link_relative_parent_stays_in_bundle():
+    assert resolve_link("../ops/runbook.md", "tables/users") == "ops/runbook"
+
+
+def test_resolve_link_external_https_is_not_a_concept_edge():
+    assert resolve_link("https://example.com/page", "tables/users") is None
+
+
+def test_resolve_link_rejects_dangerous_scheme():
+    with pytest.raises(OKFLinkError):
+        resolve_link("javascript:alert(1)", "tables/users")
+
+
+def test_resolve_link_rejects_bundle_escape():
+    with pytest.raises(OKFLinkError):
+        resolve_link("../../etc/passwd.md", "tables/users")
+
+
+def test_link_graph_flags_dangling_link():
+    # a/main links to a not-yet-existent b/target -> dormant-injection signal (§7.2)
+    bundle = {
+        "a/main.md": "---\ntype: t\n---\nSee [later](/b/target.md).\n",
+        "a/other.md": "---\ntype: t\n---\nNothing linked.\n",
+    }
+    graph = link_graph(bundle)
+    assert ("a/main", "b/target") in graph.dangling
+
+
+def test_link_graph_resolves_present_target():
+    bundle = {
+        "a/main.md": "---\ntype: t\n---\nSee [here](/b/target.md).\n",
+        "b/target.md": "---\ntype: t\n---\nThe target concept.\n",
+    }
+    graph = link_graph(bundle)
+    assert ("a/main", "b/target") in graph.resolved
+    assert graph.dangling == ()
+
+
+def test_link_graph_records_rejected_dangerous_link():
+    bundle = {"a/main.md": "---\ntype: t\n---\n[x](javascript:alert(1))\n"}
+    graph = link_graph(bundle)
+    assert any(from_id == "a/main" for from_id, _target, _reason in graph.rejected)