codeblast 0.2.0 → 0.3.0

package/README.md

@@ -94,9 +94,10 @@ Replayed against 50 real commits: 42 correctly stayed silent, 87.5% of comments
 
 - **TypeScript at function level: zero missed impact within statically analyzable scope.** Verified by mutation testing:
   inject mutations into a real repo → run the full test suite to get the ground-truth impact set → compare against predictions.
-  Current benchmark (tRPC, 950 files): **28/28 mutations, 100% recall**, average precision 0.36 — favoring
-  false positives over false negatives is a deliberate trade: in a controlled experiment, dropping the conservative edges
-  raises precision to 0.70 but recall collapses to 14%. Data lives in [`eval/`](eval/).
+  Two benchmarks, both hard gates in the weekly acceptance workflow: **tRPC** (vitest, 950 files) **28/28**
+  and **graphql-tools** (jest + npm workspaces, 353 files) **10/10** — 100% recall on each, average precision
+  0.33–0.36. Favoring false positives over false negatives is a deliberate trade: in a controlled experiment,
+  dropping the conservative edges raises precision to 0.70 but recall collapses to 14%. Data lives in [`eval/`](eval/).
 - **Blind spots are explicitly flagged.** A blind spot is any call or import that static analysis cannot resolve to an in-repo target — dynamic calls, unresolved calls, failed external-dependency resolution, subprocess boundaries, test-framework globals — not just dynamic calls; each is recorded in `blind_spots` with an "impact may be underestimated" warning, never silently dropped.
 - **Python is file-level.** Dynamic typing makes function-level zero-miss guarantees impossible in principle, and we don't pretend otherwise.
 

package/SKILL.md

@@ -148,8 +148,9 @@ Replayed over 50 real commits: 42 stayed silent, 87.5% of the comments posted we
 
 - TypeScript, function level: **zero missed impact within statically analyzable scope**, checked by
   mutation testing (inject a fault, run the real test suite, compare failing tests to the prediction).
-  tRPC benchmark, 950 files: 28/28 mutations recalled, precision 0.36 overall / ≈ 0.70 on the call channel.
-  The weekly acceptance workflow re-runs this and opens an issue if recall drops below 100%.
+  Two benchmarks: tRPC (vitest, 950 files) 28/28, graphql-tools (jest, 353 files) 10/10 — precision
+  0.33–0.36 overall, ≈ 0.70–0.92 on the call channel. Both are hard gates in the weekly acceptance
+  workflow, which opens an issue if either drops below 100%.
 - Conservative edges over-approximate on purpose (an interface method call fans out to every implementer).
 - Python: file-level; typed calls (`b = Builder(); b.method()`, annotated parameters) are function-level;
   untyped attribute chains fall back to file level and are recorded as blind spots.

package/dist/bin.js

@@ -1058,7 +1058,47 @@ var init_impact = __esm(() => {
 
 // src/impact-cli.ts
 var exports_impact_cli = {};
-var dbPath2, query, maxFlag, maxNodes, db2, targetId, exact, t02, result, ms, byLevel, callItems, fileNamed, fileUnnamed, ordered;
+function printHuman() {
+  const byLevel = { direct: 0, indirect: 0, tests: 0 };
+  for (const it of result.items)
+    byLevel[it.level]++;
+  const callItems = result.items.filter((it) => it.channel === "call");
+  const fileNamed = result.items.filter((it) => it.channel === "file" && !it.named_miss);
+  const fileUnnamed = result.items.filter((it) => it.channel === "file" && it.named_miss);
+  console.log(`target: ${result.target}`);
+  console.log(`impact: ${result.items.length} nodes (direct=${byLevel.direct} indirect=${byLevel.indirect} tests=${byLevel.tests})${result.truncated ? " [TRUNCATED — wide impact, run the full suite]" : ""}`);
+  console.log(`  ├─ call-graph reachable (high confidence): ${callItems.length}`);
+  console.log(`  ├─ reachable via named import: ${fileNamed.length}`);
+  console.log(`  └─ reachable via unnamed import (execution closure, conservative — do not skip): ${fileUnnamed.length}`);
+  if (result.blind_spot_count > 0)
+    console.log(`blind spots in target file: ${result.blind_spot_count} (impact may be underestimated)`);
+  if (result.co_change_hints.length > 0) {
+    console.log(`co-change hints (no static edge, but historically changed together):`);
+    for (const h of result.co_change_hints)
+      console.log(`  ~ ${h.file} (${h.co_commits} co-commits, ${h.evidence})`);
+  }
+  console.log(`query: ${ms}ms
+`);
+  const testItems = result.items.filter((it) => it.level === "tests");
+  const callNonTest = callItems.filter((it) => it.level !== "tests");
+  const fileNonTest = [...fileNamed, ...fileUnnamed].filter((it) => it.level !== "tests");
+  const shown = showAll ? [...callItems, ...fileNamed, ...fileUnnamed] : [...callNonTest, ...testItems];
+  const LIMIT = 40;
+  for (const it of shown.slice(0, LIMIT)) {
+    const conf = it.confidence === "conservative" ? " ~" : "";
+    const ch = it.channel === "file" ? it.named_miss ? " ·closure" : " ·import" : "";
+    console.log(`  [${it.level}${conf}${ch}] ${it.id}  (${it.kind}, ${it.hops} hop, via ${it.via_file}:${it.via_line})`);
+  }
+  if (shown.length > LIMIT)
+    console.log(`  ... and ${shown.length - LIMIT} more`);
+  if (!showAll && fileNonTest.length > 0) {
+    const files = new Set(fileNonTest.map((it) => it.file)).size;
+    console.log(`
+  + ${fileNonTest.length} conservative items across ${files} files reachable only via imports — --all to list them.`);
+    console.log(`    They are part of the no-false-negative promise: run the tests above, do not treat this list as noise.`);
+  }
+}
+var dbPath2, query, maxFlag, maxNodes, showAll, db2, targetId, exact, t02, result, ms;
 var init_impact_cli = __esm(() => {
   init_db();
   init_impact();
@@ -1069,6 +1109,7 @@ var init_impact_cli = __esm(() => {
   }
   maxFlag = process.argv.indexOf("--max");
   maxNodes = maxFlag >= 0 ? Number(process.argv[maxFlag + 1]) : 500;
+  showAll = process.argv.includes("--all");
   db2 = openDatabase(dbPath2, { readonly: true });
   targetId = query;
   exact = db2.prepare("SELECT id FROM nodes WHERE id = ?").get(query);
@@ -1090,37 +1131,13 @@ var init_impact_cli = __esm(() => {
   result = impact(db2, targetId, maxNodes);
   ms = (performance.now() - t02).toFixed(0);
   if (process.argv.includes("--json")) {
-    console.log(JSON.stringify(result));
-    process.exit(0);
-  }
-  byLevel = { direct: 0, indirect: 0, tests: 0 };
-  for (const it of result.items)
-    byLevel[it.level]++;
-  callItems = result.items.filter((it) => it.channel === "call");
-  fileNamed = result.items.filter((it) => it.channel === "file" && !it.named_miss);
-  fileUnnamed = result.items.filter((it) => it.channel === "file" && it.named_miss);
-  console.log(`target: ${result.target}`);
-  console.log(`impact: ${result.items.length} nodes (direct=${byLevel.direct} indirect=${byLevel.indirect} tests=${byLevel.tests})${result.truncated ? " [TRUNCATED — wide impact, run the full suite]" : ""}`);
-  console.log(`  ├─ call-graph reachable (high confidence): ${callItems.length}`);
-  console.log(`  ├─ reachable via named import: ${fileNamed.length}`);
-  console.log(`  └─ reachable via unnamed import (execution closure, conservative — do not skip): ${fileUnnamed.length}`);
-  if (result.blind_spot_count > 0)
-    console.log(`blind spots in target file: ${result.blind_spot_count} (impact may be underestimated)`);
-  if (result.co_change_hints.length > 0) {
-    console.log(`co-change hints (no static edge, but historically changed together):`);
-    for (const h of result.co_change_hints)
-      console.log(`  ~ ${h.file} (${h.co_commits}  co-commits, ${h.evidence})`);
-  }
-  console.log(`query: ${ms}ms
+    process.stdout.write(JSON.stringify(result) + `
 `);
-  ordered = [...callItems, ...fileNamed, ...fileUnnamed];
-  for (const it of ordered.slice(0, 40)) {
-    const conf = it.confidence === "conservative" ? " ~" : "";
-    const ch = it.channel === "file" ? it.named_miss ? " ·closure" : " ·import" : "";
-    console.log(`  [${it.level}${conf}${ch}] ${it.id}  (${it.kind}, ${it.hops} hop, via ${it.via_file}:${it.via_line})`);
+    db2.close();
+    process.exitCode = 0;
+  } else {
+    printHuman();
   }
-  if (ordered.length > 40)
-    console.log(`  ... and ${ordered.length - 40} more`);
 });
 
 // src/graph-diff.ts

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codeblast",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "description": "Know what breaks before you merge — mutation-tested code graph with architecture, change & impact maps. Evidence on every edge. For humans and AI agents.",
   "keywords": [
     "impact-analysis",