feat(pair-corpus-honesty): add vibe-py, vfc-js and agent-vfc slices with mechanism vocabulary

Tasks 1.1, 5.1, 5.2, 5.4 and the data half of 5.3.

- mechanisms.toml: closed vocabulary v1 (20 ids) every expected row cites.
- vibe-py: 35 Real-Vuln-Benchmark pairs (Apache-2.0), human provenance only
  because the LLM-generated repositories carry no license (escalated).
- vfc-js: 17 Node fix-commit pairs harvested upstream (MIT/Apache-2.0),
  SecBench.js itself is not vendored (no license); sinks derived on 13/17.
- agent-vfc: 29 agent-trailer fixes as catalog-candidates.toml plus
  REVIEW.md; the loaded catalog stays empty until a human reviews them.
- datasets.toml and README document every slice and its review status.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG

benchmarks/pairs/agent-vfc/registry-proxy-worker-426847/fixed.js

@@ -0,0 +1,43 @@
+// Provenance: agents-repo/registry-proxy  (fixed).
+// repo: agents-repo/registry-proxy
+// commit: 426847899eb2ee94ae4e5a3aacc50423e36d2dc8
+// parent: 6d5937972510cdb5ebca30607b538fdc2e280094
+// commit_url: https://github.com/agents-repo/registry-proxy/commit/426847899eb2ee94ae4e5a3aacc50423e36d2dc8
+// cve: 
+// license: MIT
+// function: buildUpstreamRequest
+// relpath: src/worker.js
+// provenance: agent
+// mechanism: permissive_default
+
+function buildUpstreamRequest(target, env, requestHeaders) {
+  const headers = new Headers();
+  const requestAccept = requestHeaders.get("Accept") || "*/*";
+  headers.set("User-Agent", UPSTREAM_USER_AGENT);
+
+  const ifNoneMatch = requestHeaders.get("If-None-Match");
+  if (ifNoneMatch) {
+    headers.set("If-None-Match", ifNoneMatch);
+  }
+
+  const ifModifiedSince = requestHeaders.get("If-Modified-Since");
+  if (ifModifiedSince) {
+    headers.set("If-Modified-Since", ifModifiedSince);
+  }
+
+  if (env.GITHUB_TOKEN) {
+    headers.set("Accept", "application/vnd.github.raw");
+    headers.set("Authorization", `Bearer ${env.GITHUB_TOKEN}`);
+    return {
+      url: buildContentsApiUrl(target.ref, target.targetPath),
+      headers,
+    };
+  }
+
+  headers.set("Accept", requestAccept);
+
+  return {
+    url: buildUpstreamUrl(target.ref, target.targetPath),
+    headers,
+  };
+}

benchmarks/pairs/agent-vfc/registry-proxy-worker-426847/vuln.js

@@ -0,0 +1,33 @@
+// Provenance: agents-repo/registry-proxy  (vuln).
+// repo: agents-repo/registry-proxy
+// commit: 6d5937972510cdb5ebca30607b538fdc2e280094
+// parent: 6d5937972510cdb5ebca30607b538fdc2e280094
+// commit_url: https://github.com/agents-repo/registry-proxy/commit/426847899eb2ee94ae4e5a3aacc50423e36d2dc8
+// cve: 
+// license: MIT
+// function: buildUpstreamRequest
+// relpath: src/worker.js
+// provenance: agent
+// mechanism: permissive_default
+
+function buildUpstreamRequest(target, env, requestHeaders) {
+  const headers = new Headers();
+  const requestAccept = requestHeaders.get("Accept") || "*/*";
+  headers.set("User-Agent", UPSTREAM_USER_AGENT);
+
+  if (env.GITHUB_TOKEN) {
+    headers.set("Accept", "application/vnd.github.raw");
+    headers.set("Authorization", `Bearer ${env.GITHUB_TOKEN}`);
+    return {
+      url: buildContentsApiUrl(target.ref, target.targetPath),
+      headers,
+    };
+  }
+
+  headers.set("Accept", requestAccept);
+
+  return {
+    url: buildUpstreamUrl(target.ref, target.targetPath),
+    headers,
+  };
+}