Skip to content

Add artifact evidence index #156

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ProfRandom92 merged 1 commit into from
May 20, 2026
Merged

Add artifact evidence index #156

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
200 changes: 200 additions & 0 deletions artifacts/evidence_index.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,200 @@
{
"artifact_id": "evidence_index_v1",
"generated_by": "EvidenceIndexGenerator",
"version": "1.0",
"evaluation_mode": "deterministic",
"llm_judges": "none",
"external_apis": "none",
"artifacts": [
{
"path": "artifacts/capability_boundary_replay_results.json",
"format": "json",
"generator": "scripts/generate_capability_boundary_replay_artifact.py",
"evidence_category": "capability_boundary_replay",
"evidence_role": "capability boundary drift replay evidence",
"fixture_families": [
"coding_workflow_pr_review",
"cross_domain_operational_dependency_workflow",
"incident_response_page_triage",
"mcp_trace_replay"
],
"top_level_keys": [
"artifact_id",
"evaluation_mode",
"external_apis",
"families",
"generated_by",
"global_summary",
"llm_judges",
"version"
],
"deterministic_evaluation": true,
"llm_judges": "none",
"external_apis": "none",
"manifest_aligned": true,
"evidence_bearing": true,
"visualization_only": false
},
{
"path": "artifacts/graph_diff_results.json",
"format": "json",
"generator": "scripts/generate_graph_diff_artifact.py",
"evidence_category": "graph_diff",
"evidence_role": "relational replay graph evidence",
"fixture_families": [
"coding_workflow_pr_review",
"cross_domain_operational_dependency_workflow",
"incident_response_page_triage",
"mcp_trace_replay"
],
"top_level_keys": [
"artifact_id",
"evaluation_mode",
"external_apis",
"families",
"generated_by",
"global_summary",
"llm_judges",
"version"
],
"deterministic_evaluation": true,
"llm_judges": "none",
"external_apis": "none",
"manifest_aligned": true,
"evidence_bearing": true,
"visualization_only": false
},
{
"path": "artifacts/mcp_trace_replay_results.json",
"format": "json",
"generator": "scripts/generate_mcp_trace_replay_artifact.py",
"evidence_category": "mcp_trace_replay",
"evidence_role": "single-family MCP trace replay evidence",
"fixture_families": [
"mcp_trace_replay"
],
"top_level_keys": [
"artifact_id",
"family",
"fixtures",
"generated_by",
"summary",
"version"
],
"deterministic_evaluation": true,
"llm_judges": "none",
"external_apis": "none",
"manifest_aligned": false,
"evidence_bearing": true,
"visualization_only": false
},
{
"path": "artifacts/multi_family_admissibility_curves.svg",
"format": "svg",
"generator": "scripts/render_multi_family_admissibility_svg.py",
"evidence_category": "multi_family_admissibility_visualization",
"evidence_role": "visualization of admissibility outcomes",
"fixture_families": [],
"top_level_keys": [],
"deterministic_evaluation": true,
"llm_judges": "none",
"external_apis": "none",
"manifest_aligned": false,
"evidence_bearing": false,
"visualization_only": true
},
{
"path": "artifacts/multi_family_admissibility_results.json",
"format": "json",
"generator": "scripts/generate_multi_family_admissibility_artifact.py",
"evidence_category": "multi_family_admissibility",
"evidence_role": "cross-family admissibility evidence",
"fixture_families": [
"coding_workflow_pr_review",
"cross_domain_operational_dependency_workflow",
"incident_response_page_triage",
"mcp_trace_replay"
],
"top_level_keys": [
"artifact_id",
"families",
"generated_by",
"version"
],
"deterministic_evaluation": true,
"llm_judges": "none",
"external_apis": "none",
"manifest_aligned": true,
"evidence_bearing": true,
"visualization_only": false
},
{
"path": "artifacts/replay_semantic_integrity_results.json",
"format": "json",
"generator": "scripts/generate_replay_semantic_integrity_artifact.py",
"evidence_category": "replay_semantic_integrity",
"evidence_role": "semantic replay integrity evidence",
"fixture_families": [
"coding_workflow_pr_review",
"cross_domain_operational_dependency_workflow",
"incident_response_page_triage",
"mcp_trace_replay"
],
"top_level_keys": [
"artifact_id",
"evaluation_mode",
"external_apis",
"families",
"generated_by",
"global_summary",
"llm_judges",
"version"
],
"deterministic_evaluation": true,
"llm_judges": "none",
"external_apis": "none",
"manifest_aligned": true,
"evidence_bearing": true,
"visualization_only": false
},
{
"path": "artifacts/tool_ordering_replay_results.json",
"format": "json",
"generator": "scripts/generate_tool_ordering_replay_artifact.py",
"evidence_category": "tool_ordering_replay",
"evidence_role": "tool-order replay drift evidence",
"fixture_families": [
"coding_workflow_pr_review",
"cross_domain_operational_dependency_workflow",
"incident_response_page_triage",
"mcp_trace_replay"
],
"top_level_keys": [
"artifact_id",
"evaluation_mode",
"external_apis",
"families",
"generated_by",
"global_summary",
"llm_judges",
"version"
],
"deterministic_evaluation": true,
"llm_judges": "none",
"external_apis": "none",
"manifest_aligned": true,
"evidence_bearing": true,
"visualization_only": false
}
],
"global_summary": {
"artifact_count": 7,
"json_artifact_count": 6,
"svg_artifact_count": 1,
"evidence_bearing_count": 6,
"visualization_only_count": 1,
"deterministic_artifact_count": 7,
"llm_free_artifact_count": 7,
"external_api_free_artifact_count": 7
}
}
171 changes: 171 additions & 0 deletions scripts/generate_evidence_index.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,171 @@
"""Generate deterministic evidence index for committed artifacts."""

from __future__ import annotations

import json
from pathlib import Path
from typing import Any

REPO_ROOT = Path(__file__).resolve().parents[1]
MANIFEST_PATH = REPO_ROOT / "fixtures" / "manifest.json"
OUTPUT_PATH = REPO_ROOT / "artifacts" / "evidence_index.json"

ARTIFACT_SPECS: tuple[dict[str, Any], ...] = (
{
"path": "artifacts/capability_boundary_replay_results.json",
"format": "json",
"generator": "scripts/generate_capability_boundary_replay_artifact.py",
"evidence_category": "capability_boundary_replay",
"evidence_role": "capability boundary drift replay evidence",
"evidence_bearing": True,
"visualization_only": False,
},
{
"path": "artifacts/graph_diff_results.json",
"format": "json",
"generator": "scripts/generate_graph_diff_artifact.py",
"evidence_category": "graph_diff",
"evidence_role": "relational replay graph evidence",
"evidence_bearing": True,
"visualization_only": False,
},
{
"path": "artifacts/mcp_trace_replay_results.json",
"format": "json",
"generator": "scripts/generate_mcp_trace_replay_artifact.py",
"evidence_category": "mcp_trace_replay",
"evidence_role": "single-family MCP trace replay evidence",
"evidence_bearing": True,
"visualization_only": False,
},
{
"path": "artifacts/multi_family_admissibility_curves.svg",
"format": "svg",
"generator": "scripts/render_multi_family_admissibility_svg.py",
"evidence_category": "multi_family_admissibility_visualization",
"evidence_role": "visualization of admissibility outcomes",
"evidence_bearing": False,
"visualization_only": True,
},
{
"path": "artifacts/multi_family_admissibility_results.json",
"format": "json",
"generator": "scripts/generate_multi_family_admissibility_artifact.py",
"evidence_category": "multi_family_admissibility",
"evidence_role": "cross-family admissibility evidence",
"evidence_bearing": True,
"visualization_only": False,
},
{
"path": "artifacts/replay_semantic_integrity_results.json",
"format": "json",
"generator": "scripts/generate_replay_semantic_integrity_artifact.py",
"evidence_category": "replay_semantic_integrity",
"evidence_role": "semantic replay integrity evidence",
"evidence_bearing": True,
"visualization_only": False,
},
{
"path": "artifacts/tool_ordering_replay_results.json",
"format": "json",
"generator": "scripts/generate_tool_ordering_replay_artifact.py",
"evidence_category": "tool_ordering_replay",
"evidence_role": "tool-order replay drift evidence",
"evidence_bearing": True,
"visualization_only": False,
},
)


def _load_json(path: Path) -> dict[str, Any]:
return json.loads(path.read_text(encoding="utf-8"))


def _manifest_families() -> set[str]:
manifest = _load_json(MANIFEST_PATH)
return {str(fixture["family"]) for fixture in manifest["fixtures"]}


def _extract_fixture_families(payload: dict[str, Any]) -> list[str]:
families: set[str] = set()
if isinstance(payload.get("families"), list):
for family in payload["families"]:
if isinstance(family, dict) and isinstance(family.get("family"), str):
families.add(family["family"])
if isinstance(payload.get("family"), str):
families.add(payload["family"])
return sorted(families)


def _build_artifact_entry(spec: dict[str, Any], manifest_families: set[str]) -> dict[str, Any] | None:
artifact_path = REPO_ROOT / spec["path"]
if not artifact_path.exists():
return None

entry = {
"path": spec["path"],
"format": spec["format"],
"generator": spec["generator"],
"evidence_category": spec["evidence_category"],
"evidence_role": spec["evidence_role"],
"fixture_families": [],
"top_level_keys": [],
"deterministic_evaluation": True,
"llm_judges": "none",
"external_apis": "none",
"manifest_aligned": False,
"evidence_bearing": spec["evidence_bearing"],
"visualization_only": spec["visualization_only"],
}

if spec["format"] == "json":
payload = _load_json(artifact_path)
families = _extract_fixture_families(payload)
entry["fixture_families"] = families
entry["top_level_keys"] = sorted(payload.keys())
entry["deterministic_evaluation"] = payload.get("evaluation_mode", "deterministic") == "deterministic"
entry["llm_judges"] = payload.get("llm_judges", "none")
entry["external_apis"] = payload.get("external_apis", "none")
if families:
entry["manifest_aligned"] = set(families) == manifest_families

return entry


def generate_evidence_index(output_path: Path = OUTPUT_PATH) -> Path:
manifest_families = _manifest_families()
artifacts = [
entry
for spec in sorted(ARTIFACT_SPECS, key=lambda item: item["path"])
for entry in [_build_artifact_entry(spec, manifest_families)]
if entry is not None
]
Comment on lines +137 to +142

@gemini-code-assist gemini-code-assist Bot May 20, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The nested list comprehension used here to filter None values is a bit convoluted. Since the project targets Python 3.9+ (as evidenced by the use of dict[str, Any]), you can use the assignment expression (walrus operator) to make this more readable and idiomatic.

    artifacts = [
        entry
        for spec in sorted(ARTIFACT_SPECS, key=lambda item: item["path"])
        if (entry := _build_artifact_entry(spec, manifest_families)) is not None
    ]


index = {
"artifact_id": "evidence_index_v1",
"generated_by": "EvidenceIndexGenerator",
"version": "1.0",
"evaluation_mode": "deterministic",
"llm_judges": "none",
"external_apis": "none",
"artifacts": artifacts,
"global_summary": {
"artifact_count": len(artifacts),
"json_artifact_count": sum(1 for item in artifacts if item["format"] == "json"),
"svg_artifact_count": sum(1 for item in artifacts if item["format"] == "svg"),
"evidence_bearing_count": sum(1 for item in artifacts if item["evidence_bearing"]),
"visualization_only_count": sum(1 for item in artifacts if item["visualization_only"]),
"deterministic_artifact_count": sum(1 for item in artifacts if item["deterministic_evaluation"]),
"llm_free_artifact_count": sum(1 for item in artifacts if item["llm_judges"] == "none"),
"external_api_free_artifact_count": sum(1 for item in artifacts if item["external_apis"] == "none"),
},
}

output_path.parent.mkdir(parents=True, exist_ok=True)
output_path.write_text(json.dumps(index, indent=2) + "\n", encoding="utf-8")
return output_path


if __name__ == "__main__":
path = generate_evidence_index()
print(path.relative_to(REPO_ROOT).as_posix())
Loading
Loading