Sync ctx 0d3237d (part 3)

GitHub commit: 0d3237df9965b8142d0f74ea4c4bea30f3ef16c9

src/tests/test_feature_user_story_tracker.py

@@ -13,7 +13,9 @@ from ctx.monitor import routes as monitor_routes  # noqa: E402
 TRACKER = repo_root / "docs" / "qa" / "feature-user-story-status.csv"
 README = repo_root / "README.md"
 PASS_STATUSES = {"Tested Pass", "Retested Pass"}
-ACTIONABLE_STATUSES = PASS_STATUSES | {"Needs Fix"}
+VALIDATION_STATUSES = {"Needs Validation"}
+FIX_STATUSES = {"Needs Fix"}
+ACTIONABLE_STATUSES = PASS_STATUSES | VALIDATION_STATUSES | FIX_STATUSES
 
 
 def _tracker_rows() -> list[dict[str, str]]:
@@ -44,12 +46,17 @@ def test_feature_user_story_tracker_has_no_empty_core_fields() -> None:
         for key in required:
             assert row[key].strip(), f"{row.get('feature_id', '<unknown>')} missing {key}"
         assert row["status"] in ACTIONABLE_STATUSES
-        if row["status"] not in PASS_STATUSES:
+        if row["status"] in FIX_STATUSES:
             for key in ("error_id", "error_summary", "fix_status"):
                 assert row[key].strip(), (
                     f"{row.get('feature_id', '<unknown>')} has "
                     f"{row['status']} without {key}"
                 )
+        if row["status"] in VALIDATION_STATUSES:
+            assert row["notes"].strip(), (
+                f"{row.get('feature_id', '<unknown>')} needs validation "
+                "without a validation note"
+            )
 
 
 def test_feature_user_story_tracker_covers_all_console_scripts() -> None:
@@ -76,6 +83,38 @@ def test_feature_user_story_tracker_covers_monitor_route_inventory() -> None:
     assert [route for route in route_patterns if route not in tracker] == []
 
 
+def test_feature_user_story_tracker_covers_distribution_workflows() -> None:
+    workflows = (
+        ".github/workflows/test.yml",
+        ".github/workflows/docs.yml",
+        ".github/workflows/huggingface-sync.yml",
+        ".github/workflows/publish.yml",
+        ".github/workflows/clean-host-contract.yml",
+        ".github/workflows/xdist-experiment.yml",
+    )
+    tracker = _tracker_text()
+
+    assert [workflow for workflow in workflows if workflow not in tracker] == []
+
+
+def test_feature_user_story_tracker_covers_maintainer_scripts() -> None:
+    scripts = sorted((repo_root / "scripts").glob("*.py"))
+    tracker = _tracker_text()
+    script_paths = [script.relative_to(repo_root).as_posix() for script in scripts]
+
+    assert scripts
+    assert [path for path in script_paths if path not in tracker] == []
+
+
+def test_feature_user_story_tracker_covers_public_docs_assets() -> None:
+    assets = sorted((repo_root / "docs" / "assets" / "javascripts").glob("*.js"))
+    tracker = _tracker_text()
+    asset_paths = [asset.relative_to(repo_root).as_posix() for asset in assets]
+
+    assert assets
+    assert [path for path in asset_paths if path not in tracker] == []
+
+
 def test_readme_shows_user_story_examples_from_tracker() -> None:
     readme = README.read_text(encoding="utf-8")
 

src/tests/test_huggingface_sync.py

@@ -160,10 +160,12 @@ def test_hf_sync_workflow_uses_secret_and_hardened_script() -> None:
     assert "HF_TOKEN: ${{ secrets.HF_TOKEN }}" in text
     assert "lfs: false" in text
     assert "git lfs pull" not in text
-    assert "gh release download" in text
+    assert "Resolving graph artifacts from matching release assets" in text
+    assert 'tag_name.startswith("graph-artifacts-")' in text
+    assert "latest_tag" not in text
     for artifact in _required_hydrated_artifacts():
         assert artifact.as_posix() in text
-        assert f"--pattern {artifact.name}" in text
+        assert f'hydrate_from_release("{artifact.as_posix()}"' in text
     assert "scripts/sync_huggingface.py" in text
     assert "Classify sync scope" in text
     assert "card_only_files" in text

src/tests/test_maintainer_script_bom_inputs.py

@@ -0,0 +1,91 @@
+from __future__ import annotations
+
+import json
+import sqlite3
+import sys
+import zlib
+from pathlib import Path
+
+from scripts import audit_backup
+from scripts.build_dashboard_graph_index import build_dashboard_index
+
+
+def test_audit_backup_accepts_bom_manifest(
+    tmp_path: Path,
+    monkeypatch,
+    capsys,
+) -> None:
+    claude_home = tmp_path / "home" / ".claude"
+    claude_home.mkdir(parents=True)
+    config = claude_home / "skill-system-config.json"
+    config.write_text('{"ok": true}', encoding="utf-8")
+    snapshot = tmp_path / "snapshot"
+    snapshot.mkdir()
+    manifest = {
+        "entries": [
+            {
+                "source": str(config),
+                "dest": "skill-system-config.json",
+                "size": config.stat().st_size,
+            }
+        ]
+    }
+    (snapshot / "manifest.json").write_text(json.dumps(manifest), encoding="utf-8-sig")
+
+    monkeypatch.setattr(audit_backup, "CLAUDE_HOME", claude_home)
+    monkeypatch.setattr(sys, "argv", ["audit_backup.py", str(snapshot)])
+
+    assert audit_backup.main() == 0
+    output = capsys.readouterr().out
+    assert "entries:   1" in output
+    assert "OK:" in output
+
+
+def test_dashboard_graph_index_accepts_bom_graph_json(tmp_path: Path) -> None:
+    graph_json = tmp_path / "graph.json"
+    output = tmp_path / "dashboard.sqlite3"
+    graph_json.write_text(
+        json.dumps({
+            "graph": {"export_id": "fixture"},
+            "nodes": [
+                {
+                    "id": "skill:alpha",
+                    "label": "Alpha",
+                    "type": "skill",
+                    "tags": ["python", "test"],
+                    "quality_score": 0.9,
+                },
+                {
+                    "id": "mcp-server:github",
+                    "label": "GitHub",
+                    "type": "mcp-server",
+                    "tags": ["github"],
+                },
+            ],
+            "links": [
+                {
+                    "source": "skill:alpha",
+                    "target": "mcp-server:github",
+                    "weight": 0.77,
+                    "shared_tags": ["github"],
+                    "reasons": ["fixture"],
+                }
+            ],
+        }),
+        encoding="utf-8-sig",
+    )
+
+    build_dashboard_index(graph_json, output, top_k=5)
+
+    conn = sqlite3.connect(output)
+    try:
+        assert conn.execute(
+            "SELECT value FROM meta WHERE key='nodes_count'",
+        ).fetchone() == ("2",)
+        payload = conn.execute(
+            "SELECT payload FROM neighbors WHERE source='skill:alpha'",
+        ).fetchone()[0]
+    finally:
+        conn.close()
+    neighbors = json.loads(zlib.decompress(payload).decode("utf-8"))
+    assert neighbors[0]["target"] == "mcp-server:github"

src/tests/test_pack_full_wiki_tar.py

@@ -0,0 +1,75 @@
+from __future__ import annotations
+
+import io
+import json
+import tarfile
+from pathlib import Path
+
+from ctx.core.wiki.wiki_packs import load_merged_wiki_pages
+from scripts.pack_full_wiki_tar import repack_full_wiki_tar
+
+
+def _add_text(tf: tarfile.TarFile, name: str, text: str) -> None:
+    payload = text.encode("utf-8")
+    info = tarfile.TarInfo(name)
+    info.size = len(payload)
+    tf.addfile(info, io.BytesIO(payload))
+
+
+def test_repack_full_wiki_tar_moves_high_fanout_pages_into_wiki_pack(
+    tmp_path: Path,
+) -> None:
+    source = tmp_path / "wiki-graph.tar.gz"
+    target = tmp_path / "wiki-graph-packed.tar.gz"
+    with tarfile.open(source, "w:gz") as tf:
+        _add_text(tf, "index.md", "# Wiki\n")
+        _add_text(tf, "entities/skills/current.md", "# Current Skill\n")
+        _add_text(tf, "entities/skills/empty.md", "")
+        _add_text(tf, "entities/agents/reviewer.md", "# Reviewer Agent\n")
+        _add_text(tf, "entities/mcp-servers/github.md", "# GitHub MCP\n")
+        _add_text(tf, "entities/harnesses/langgraph.md", "# LangGraph Harness\n")
+        _add_text(tf, "concepts/empty.md", "")
+        _add_text(
+            tf,
+            "graphify-out/graph-export-manifest.json",
+            json.dumps({"export_id": "test-export"}),
+        )
+        _add_text(tf, "graphify-out/graph-report.md", "# Graph Report\n")
+        _add_text(tf, "graphify-out/graph.json", json.dumps({"nodes": [], "edges": []}))
+        _add_text(tf, "external-catalogs/skills-sh/catalog.json", json.dumps({"skills": []}))
+
+    stats = repack_full_wiki_tar(source, target)
+
+    assert stats.removed_expanded_markdown_pages == 5
+    assert stats.packed_pages == 8
+    with tarfile.open(target, "r:gz") as tf:
+        names = {member.name for member in tf.getmembers()}
+        tf.extractall(tmp_path / "extracted")
+
+    assert "entities/skills/current.md" not in names
+    assert "entities/skills/empty.md" not in names
+    assert "entities/agents/reviewer.md" not in names
+    assert "entities/mcp-servers/github.md" not in names
+    assert "entities/harnesses/langgraph.md" in names
+    assert "concepts/empty.md" not in names
+    assert "graphify-out/graph-report.md" in names
+    assert "wiki-packs/base-test-export/wiki-pack-manifest.json" in names
+    assert "wiki-packs/base-test-export/pages.jsonl" in names
+
+    pages = load_merged_wiki_pages(tmp_path / "extracted" / "wiki-packs")
+    assert pages["entities/skills/current.md"] == "# Current Skill\n"
+    assert pages["entities/skills/empty.md"] == "<!-- empty markdown page -->\n"
+    assert pages["entities/agents/reviewer.md"] == "# Reviewer Agent\n"
+    assert pages["entities/mcp-servers/github.md"] == "# GitHub MCP\n"
+    assert pages["concepts/empty.md"] == "<!-- empty markdown page -->\n"
+
+    second_target = tmp_path / "wiki-graph-packed-again.tar.gz"
+    repack_full_wiki_tar(target, second_target)
+    with tarfile.open(second_target, "r:gz") as tf:
+        second_names = {member.name for member in tf.getmembers()}
+        tf.extractall(tmp_path / "extracted-again")
+    assert "graphify-out/graph-report.md" in second_names
+    repacked_pages = load_merged_wiki_pages(tmp_path / "extracted-again" / "wiki-packs")
+    assert repacked_pages["entities/skills/current.md"] == "# Current Skill\n"
+    assert repacked_pages["entities/agents/reviewer.md"] == "# Reviewer Agent\n"
+    assert repacked_pages["entities/mcp-servers/github.md"] == "# GitHub MCP\n"

src/tests/test_update_repo_stats.py

@@ -522,12 +522,12 @@ def test_github_about_description_uses_entity_counts() -> None:
 
     description = urs.build_github_about_description(stats)
 
-    assert description.startswith("Not a catalog or marketplace.")
+    assert description.startswith("Not an Amazon-style catalog or marketplace.")
     assert "recommendation layer" in description
     assert "bring your org tools" in description
     assert "use the shipped graph" in description
-    assert "per dev window" in description
-    assert "cutting token and compute waste" in description
+    assert "only for the current dev window" in description
+    assert "cutting token bills and local compute waste" in description
     assert "123,456-node LLM-wiki graph" in description
     assert "4,321 skills" in description
     assert "56 agents" in description

src/tests/test_validate_graph_artifacts.py

@@ -17,7 +17,11 @@ from ctx.core.graph.graph_packs import build_pack_manifest, write_base_pack, wri
 from ctx.core.wiki.wiki_packs import write_wiki_base_pack
 from scripts.ci_preflight import GRAPH_VALIDATE_ARGS
 from validate_graph_artifacts import (
+    DEFAULT_MIN_EDGES,
     DEFAULT_HARNESSES,
+    DEFAULT_MIN_NODES,
+    DEFAULT_MIN_SEMANTIC_EDGES,
+    DEFAULT_MIN_SKILLS_SH_NODES,
     GraphArtifactError,
     _validate_root_entity_overlay,
     _safe_tar_name,
@@ -1478,6 +1482,24 @@ def test_graph_only_workflow_uses_preflight_graph_contract() -> None:
     assert parsed == expected
 
 
+def test_validator_default_floors_match_preflight_contract() -> None:
+    args = GRAPH_VALIDATE_ARGS[1:]
+    values: dict[str, str] = {}
+    i = 0
+    while i < len(args):
+        flag = args[i]
+        if i + 1 >= len(args) or args[i + 1].startswith("--"):
+            i += 1
+            continue
+        values[flag] = args[i + 1]
+        i += 2
+
+    assert values["--min-nodes"] == str(DEFAULT_MIN_NODES)
+    assert values["--min-edges"] == str(DEFAULT_MIN_EDGES)
+    assert values["--min-skills-sh-nodes"] == str(DEFAULT_MIN_SKILLS_SH_NODES)
+    assert values["--min-semantic-edges"] == str(DEFAULT_MIN_SEMANTIC_EDGES)
+
+
 def test_graph_only_workflow_waits_for_release_asset_upload() -> None:
     workflow = yaml.safe_load(Path(".github/workflows/test.yml").read_text(
         encoding="utf-8"

src/update_repo_stats.py

@@ -1222,12 +1222,12 @@ def build_github_about_description(stats: Mapping[str, int | None]) -> str:
     if not all((nodes, skills, agents, mcps, harnesses)):
         raise ValueError("missing graph stats for GitHub About description")
     return (
-        "Not a catalog or marketplace. ctx is a recommendation layer: bring "
-        "your org tools or use the shipped graph to load the right skills, "
-        "agents, MCPs, and harnesses per dev window, cutting token and compute "
-        f"waste: {nodes:,}-node LLM-wiki graph, "
-        f"{skills:,} skills, {agents:,} agents, {mcps:,} MCPs, "
-        f"{harnesses:,} harnesses."
+        "Not an Amazon-style catalog or marketplace. ctx is a recommendation "
+        "layer: bring your org tools or use the shipped graph to load the "
+        "right skills, agents, MCPs, and harnesses only for the current dev "
+        "window, cutting token bills and local compute waste: "
+        f"{nodes:,}-node LLM-wiki graph, {skills:,} skills, "
+        f"{agents:,} agents, {mcps:,} MCPs, {harnesses:,} harnesses."
     )
 
 

src/validate_graph_artifacts.py

@@ -28,6 +28,10 @@ from ctx.core.wiki.wiki_packs import (
 )
 
 GIT_LFS_POINTER_PREFIX = b"version https://git-lfs.github.com/spec/v1"
+DEFAULT_MIN_NODES = 79_000
+DEFAULT_MIN_EDGES = 1_700_000
+DEFAULT_MIN_SKILLS_SH_NODES = 67_000
+DEFAULT_MIN_SEMANTIC_EDGES = 1_000_000
 DEFAULT_HARNESSES = {
     "agentops",
     "autogen",
@@ -798,10 +802,10 @@ def validate_graph_artifacts(
     graph_dir: Path,
     *,
     deep: bool = False,
-    min_nodes: int = 100_000,
-    min_edges: int = 2_000_000,
-    min_skills_sh_nodes: int = 89_000,
-    min_semantic_edges: int = 1_000_000,
+    min_nodes: int = DEFAULT_MIN_NODES,
+    min_edges: int = DEFAULT_MIN_EDGES,
+    min_skills_sh_nodes: int = DEFAULT_MIN_SKILLS_SH_NODES,
+    min_semantic_edges: int = DEFAULT_MIN_SEMANTIC_EDGES,
     expected_harnesses: set[str] | None = None,
     line_threshold: int = 180,
     max_stage_lines: int = 40,
@@ -1408,10 +1412,10 @@ def main() -> None:
     parser = argparse.ArgumentParser(description=__doc__)
     parser.add_argument("--graph-dir", type=Path, default=Path("graph"))
     parser.add_argument("--deep", action="store_true")
-    parser.add_argument("--min-nodes", type=int, default=100_000)
-    parser.add_argument("--min-edges", type=int, default=2_000_000)
-    parser.add_argument("--min-skills-sh-nodes", type=int, default=89_000)
-    parser.add_argument("--min-semantic-edges", type=int, default=1_000_000)
+    parser.add_argument("--min-nodes", type=int, default=DEFAULT_MIN_NODES)
+    parser.add_argument("--min-edges", type=int, default=DEFAULT_MIN_EDGES)
+    parser.add_argument("--min-skills-sh-nodes", type=int, default=DEFAULT_MIN_SKILLS_SH_NODES)
+    parser.add_argument("--min-semantic-edges", type=int, default=DEFAULT_MIN_SEMANTIC_EDGES)
     parser.add_argument("--line-threshold", type=int, default=180)
     parser.add_argument("--max-stage-lines", type=int, default=40)
     parser.add_argument("--expected-nodes", type=int)