@orangepro/orangepro-mcp 0.2.2 → 0.2.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -19,8 +19,20 @@ const MAX_PROMPT_ENTRIES = 60;
19
19
  const MAX_PROMPT_SYMBOLS = 300;
20
20
  const MAX_COMPLETION_TOKENS = 3000;
21
21
  export function aiFlowsPath(root) {
22
+ return join(workspacePaths(root).dir, "flows.json");
23
+ }
24
+ function legacyAiFlowsPath(root) {
22
25
  return join(workspacePaths(root).dir, "ai", "flows.json");
23
26
  }
27
+ function readAiFlowsArtifact(root) {
28
+ const path = aiFlowsPath(root);
29
+ const current = readArtifact(path);
30
+ if (current.artifact || current.invalid)
31
+ return { ...current, path };
32
+ const legacy = legacyAiFlowsPath(root);
33
+ const fallback = readArtifact(legacy);
34
+ return { ...fallback, path: fallback.artifact || fallback.invalid ? legacy : path };
35
+ }
24
36
  function buildAnchorContext(graph) {
25
37
  const entries = dedupeEntries([
26
38
  ...endpointEntries(graph.nodes, graph.edges),
@@ -210,12 +222,12 @@ export async function generateAiFlows(root, graph, provider, clock) {
210
222
  node_set_hash: nodeSetHash
211
223
  }));
212
224
  const path = aiFlowsPath(root);
213
- const cached = readArtifact(path);
225
+ const cached = readAiFlowsArtifact(root);
214
226
  if (cached.artifact?.cache_key === cacheKey) {
215
227
  const hit = cached.artifact;
216
228
  return {
217
229
  mode: "generate",
218
- ai_flows_path: path,
230
+ ai_flows_path: cached.path,
219
231
  cache_hit: true,
220
232
  model_provider: hit.model_provider,
221
233
  model_name: hit.model_name,
@@ -306,8 +318,7 @@ export async function generateAiFlows(root, graph, provider, clock) {
306
318
  * edges/candidate_edges/nodes/analysis.flows.
307
319
  */
308
320
  export function applyAiFlows(root, graph) {
309
- const path = aiFlowsPath(root);
310
- const { artifact, invalid } = readArtifact(path);
321
+ const { path, artifact, invalid } = readAiFlowsArtifact(root);
311
322
  if (invalid) {
312
323
  throw new Error(`AI flows artifact at ${path} is invalid or corrupted; re-run \`opro ai-flows\` to regenerate it.`);
313
324
  }
@@ -413,7 +424,7 @@ function toCandidateFlow(flow, entriesById, knownEdges, provenance) {
413
424
  ...(flow.rationale ? { rationale: flow.rationale } : {}),
414
425
  provenance: {
415
426
  source_scope_id: `ai:${provenance.cache_key}`,
416
- source_ref: ".orangepro/ai/flows.json",
427
+ source_ref: ".orangepro/flows.json",
417
428
  detector: "ai_flows",
418
429
  model_provider: provenance.model_provider,
419
430
  model_name: provenance.model_name,
@@ -9,7 +9,9 @@
9
9
  * The graph is built directly by OrangePro; it does not depend on any
10
10
  * third-party graph product or format.
11
11
  */
12
- export const LOCAL_GRAPH_SCHEMA_VERSION = "orangepro.local_graph.v1";
12
+ // v2: Go method symbol ids are receiver-qualified (`sym:file.go#Recv.M`) — old
13
+ // graphs hold bare-name method ids and must force-rebuild (loadGraph hard-fails).
14
+ export const LOCAL_GRAPH_SCHEMA_VERSION = "orangepro.local_graph.v2";
13
15
  /** Node kinds that map to behaviors/requirements for scoring + gaps + generation. */
14
16
  export const BEHAVIOR_KINDS = new Set([
15
17
  "Requirement",
package/dist/local/mcp.js CHANGED
@@ -407,7 +407,7 @@ export function createLocalServer() {
407
407
  });
408
408
  server.registerTool("orangepro_ai_flows", {
409
409
  title: "Stage/apply AI candidate flows",
410
- description: "Opt-in AI lane: propose candidate behavior-flow chains over existing deterministic entry and CodeSymbol ids. Generate writes .orangepro/ai/flows.json only; apply=true stores survivors under analysis.candidate_flows. Candidate flows are a verify-these worklist and never affect Proven, deterministic flow counts, tiers, or coverage.",
410
+ description: "Opt-in AI lane: propose candidate behavior-flow chains over existing deterministic entry and CodeSymbol ids. Generate writes .orangepro/flows.json only; apply=true stores survivors under analysis.candidate_flows. Candidate flows are a verify-these worklist and never affect Proven, deterministic flow counts, tiers, or coverage.",
411
411
  inputSchema: {
412
412
  ...Workspace,
413
413
  apply: z.boolean().optional().describe("Apply staged flows into analysis.candidate_flows. Default false stages flows only."),
@@ -273,11 +273,14 @@ function symbolTargetParts(symExtId) {
273
273
  throw new Error(`Cannot derive dynamic proof target from symbol id: ${symExtId}`);
274
274
  }
275
275
  const [, file, symbolName] = match;
276
- const method = symbolName.split(".").filter(Boolean).pop();
276
+ const segments = symbolName.split(".").filter(Boolean);
277
+ const method = segments.pop();
277
278
  if (!file || !method) {
278
279
  throw new Error(`Cannot derive dynamic proof target from symbol id: ${symExtId}`);
279
280
  }
280
- return { file, method };
281
+ // The owner qualifier of a member id (TS `Class.method`, Go `Recv.M`). The Go
282
+ // lane passes it as --recv so the mutator matches the exact receiver.
283
+ return { file, method, ...(segments.length ? { memberQualifier: segments.join(".") } : {}) };
281
284
  }
282
285
  function assertProofTargetMatchesSymbol(opts, symbolTarget) {
283
286
  if (opts.target_path !== undefined && opts.target_path !== "") {
@@ -560,8 +563,9 @@ export function opAnalyze(root, opts = {}, deps = defaultDeps()) {
560
563
  ? (!opts.suppressProgress && reportProgress("coverage: generating local runtime coverage before graph build", { current: 2, total: 4 }),
561
564
  prepareRuntimeCoverage(scanRoot, { generate: true, timeoutMs: opts.coverageTimeoutMs, runner: deps.coverageRunner }))
562
565
  : undefined;
563
- if (!workspaceInitialized(root))
564
- initWorkspace(root, now);
566
+ // Idempotent for existing workspaces and also applies conservative migrations
567
+ // to untouched generated workspace files (for example .orangeproignore).
568
+ initWorkspace(root, now);
565
569
  if (!opts.suppressProgress) {
566
570
  reportProgress("analyze: parsing source and building deterministic graph", {
567
571
  current: opts.generateCoverage ? 3 : 2,
@@ -1007,6 +1011,10 @@ export function opDynamicProof(root, opts, deps = defaultDeps()) {
1007
1011
  // Slice 2: bind a runtime-named subtest's mutant failure to the exact assertion line.
1008
1012
  if (opts.go_assertion_line !== undefined)
1009
1013
  args.push("--go-assertion-line", String(opts.go_assertion_line));
1014
+ // Receiver-qualified method target (`sym:file.go#Recv.M`) → the mutator must
1015
+ // match the exact receiver, never a same-named decl on another type.
1016
+ if (symbolTarget.memberQualifier)
1017
+ args.push("--recv", symbolTarget.memberQualifier);
1010
1018
  const run = (deps.dynamicProofRunner ?? defaultDynamicProofRunner)(args, {
1011
1019
  cwd: goRoot,
1012
1020
  scriptPath: dynamicProofSpikePathFor("go")
@@ -1458,6 +1466,28 @@ export function autoProveChangedScope(graph, changed, baseRef) {
1458
1466
  });
1459
1467
  return hasEligibleTarget ? meaningful : undefined; // no eligible provable target in scope → global top-5
1460
1468
  }
1469
+ function writeStartStaticSnapshot(root, baseRef, warnings) {
1470
+ let behaviorCoveragePath;
1471
+ try {
1472
+ reportProgress("artifacts: writing static behavior view (proof still running)", { current: 4, total: 8 });
1473
+ behaviorCoveragePath = opBehaviorCoverageHtml(root, `${WORKSPACE_DIR}/behavior-coverage.html`, {
1474
+ attempted: 0,
1475
+ proven: 0,
1476
+ needsSetup: []
1477
+ }).behavior_coverage_path;
1478
+ }
1479
+ catch (error) {
1480
+ warnings.push(`static behavior view not written: ${error instanceof Error ? error.message : String(error)}`);
1481
+ }
1482
+ try {
1483
+ reportProgress("artifacts: writing static RTM (proof still running)", { current: 4, total: 8 });
1484
+ opRtm(root, { format: "md", baseRef, limit: START_RTM_LIMIT });
1485
+ }
1486
+ catch (error) {
1487
+ warnings.push(`static RTM not written: ${error instanceof Error ? error.message : String(error)}`);
1488
+ }
1489
+ return behaviorCoveragePath ? { behaviorCoveragePath } : {};
1490
+ }
1461
1491
  export async function opStart(root, opts = {}, deps = defaultDeps()) {
1462
1492
  const providerOpts = startProviderOverride(root, opts);
1463
1493
  const scanRoot = opts.source ? resolve(opts.source) : resolve(root);
@@ -1475,6 +1505,7 @@ export async function opStart(root, opts = {}, deps = defaultDeps()) {
1475
1505
  }, deps);
1476
1506
  const warnings = [...analyze.warnings];
1477
1507
  reportProgress("start: deterministic graph is ready", { current: 4, total: 8 });
1508
+ const staticSnapshot = writeStartStaticSnapshot(root, opts.baseRef, warnings);
1478
1509
  const providerConfigured = deps.aiProvider !== undefined || resolveProviderConfig(providerEnv, providerOpts) !== null;
1479
1510
  let aiLinks = { status: "skipped", reason: "AI candidate links disabled for this run." };
1480
1511
  if (opts.ai !== false) {
@@ -1611,7 +1642,7 @@ export async function opStart(root, opts = {}, deps = defaultDeps()) {
1611
1642
  catch (error) {
1612
1643
  warnings.push(`coverage report not written: ${error instanceof Error ? error.message : String(error)}`);
1613
1644
  }
1614
- let coverageHtml;
1645
+ let coverageHtml = staticSnapshot.behaviorCoveragePath;
1615
1646
  try {
1616
1647
  reportProgress("artifacts: writing behavior coverage view", { current: 7, total: 8 });
1617
1648
  // Forward THIS-RUN dynamic-proof outcome so the report can name the dominant setup/runnability
@@ -66,20 +66,21 @@ export function loadIgnore(root) {
66
66
  const line = raw.trim();
67
67
  if (!line || line.startsWith("#") || line.startsWith("!"))
68
68
  continue;
69
+ const rootAnchored = line.startsWith("/");
69
70
  const cleaned = line.replace(/^\/+/, "").replace(/\/+$/, "");
70
71
  if (!cleaned)
71
72
  continue;
72
- if (!cleaned.includes("/") && !cleaned.includes("*")) {
73
+ if (!rootAnchored && !cleaned.includes("/") && !cleaned.includes("*")) {
73
74
  names.add(cleaned);
74
75
  }
75
76
  else {
76
- matchers.push(globToRegExp(cleaned));
77
+ matchers.push(globToRegExp(cleaned, rootAnchored));
77
78
  }
78
79
  }
79
80
  }
80
81
  return { names, matchers };
81
82
  }
82
- function globToRegExp(glob) {
83
+ function globToRegExp(glob, rootAnchored = false) {
83
84
  // Use a plain-ASCII sentinel for `**` so the file stays text (no NUL bytes)
84
85
  // and `*` substitution does not re-match the globstar.
85
86
  const GLOBSTAR = "__ORANGEPRO_GLOBSTAR__";
@@ -90,7 +91,7 @@ function globToRegExp(glob) {
90
91
  .split(GLOBSTAR)
91
92
  .join(".*")
92
93
  .replace(/\?/g, "[^/]");
93
- return new RegExp(`(^|/)${escaped}(/|$)`);
94
+ return new RegExp(`${rootAnchored ? "^" : "(^|/)"}${escaped}(/|$)`);
94
95
  }
95
96
  function isIgnored(relPath, baseName, rules) {
96
97
  if (rules.names.has(baseName))
@@ -375,7 +375,6 @@ function riskRows(risks, graph) {
375
375
  firstRowForFile.set(r.file, r.id);
376
376
  return risks.map((risk, idx) => {
377
377
  const methodMatch = risk.title.match(/^(GET|POST|PUT|PATCH|DELETE)\s+(.+)$/i);
378
- const pathMatch = risk.file.match(/\/api\/(.+)$/);
379
378
  const tags = [];
380
379
  const bucket = riskBucket(risk.risk_score);
381
380
  if (bucket)
@@ -394,8 +393,8 @@ function riskRows(risks, graph) {
394
393
  applicableCategories: [...new Set(generatedTests.map((t) => t.concern).filter((c) => Boolean(c)))]
395
394
  };
396
395
  })(),
397
- verb: methodMatch?.[1]?.toUpperCase() ?? (risk.entry_point ? "ENTRY" : "CODE"),
398
- path: methodMatch?.[2] ?? (pathMatch ? `/${pathMatch[1]}` : risk.file),
396
+ verb: methodMatch?.[1]?.toUpperCase() ?? "BEHAVIOR",
397
+ path: methodMatch?.[2] ?? risk.title,
399
398
  desc: risk.reasons.join(" · "),
400
399
  tags,
401
400
  todo: "Write an integration or behavior test that calls this behavior and asserts the observable outcome."
@@ -470,8 +470,9 @@ if(cf&&cf.flows.length){
470
470
  }
471
471
 
472
472
  // risks + generated test samples
473
- let activeRiskFilter="all";
474
473
  const riskList=$("#risk-list"),riskTools=$("#risk-tools");
474
+ const generatedRiskCount=D.risks.filter(r=>r.generatedTests&&r.generatedTests.length).length;
475
+ let activeRiskFilter=generatedRiskCount?"generated":"all";
475
476
  function riskMatchesFilter(r){
476
477
  const hasGenerated=Boolean(r.generatedTests&&r.generatedTests.length);
477
478
  if(activeRiskFilter==="generated")return hasGenerated;
@@ -481,7 +482,7 @@ function riskMatchesFilter(r){
481
482
  function renderRiskFilters(){
482
483
  const options=[
483
484
  ["all","All",D.risks.length],
484
- ["generated","Generated tests",D.risks.filter(r=>r.generatedTests&&r.generatedTests.length).length],
485
+ ["generated","Flows with tests",generatedRiskCount],
485
486
  ["missing","No generated tests",D.risks.filter(r=>!(r.generatedTests&&r.generatedTests.length)).length]
486
487
  ];
487
488
  riskTools.innerHTML=options.map(([key,label,count])=>\`<button class="risk-filter" type="button" data-risk-filter="\${key}" aria-pressed="\${key===activeRiskFilter}">\${label} <span class="gc">\${count}</span></button>\`).join("");
@@ -519,16 +520,16 @@ function renderRisks(){
519
520
  riskList.innerHTML="";
520
521
  D.risks.filter(riskMatchesFilter).forEach(r=>riskList.append(el("div","risk-card",riskCardHtml(r))));
521
522
  if(activeRiskFilter==="all"&&D.generatedTotal){
522
- const hiddenGenerated=Math.max(0,D.generatedTotal-D.shownCount);
523
- const remainingRiskFlows=Math.max(0,D.risks.length-D.generatedTotal);
523
+ const hiddenGeneratedFlows=Math.max(0,generatedRiskCount-D.risks.filter(riskMatchesFilter).length);
524
+ const remainingRiskFlows=Math.max(0,D.risks.length-generatedRiskCount);
524
525
  riskList.append(el("div","paywall",
525
- hiddenGenerated
526
- ? \`<div class="paywall-num">\${hiddenGenerated} more tests generated</div>
527
- <div class="paywall-txt">OrangePro generated tests for \${D.generatedTotal} behaviors across your highest-risk flows. You're seeing \${D.shownCount}.</div>
526
+ hiddenGeneratedFlows
527
+ ? \`<div class="paywall-num">\${hiddenGeneratedFlows} more flows with tests</div>
528
+ <div class="paywall-txt">OrangePro accepted \${D.generatedTotal} runnable generated test\${D.generatedTotal===1?"":"s"} across \${generatedRiskCount} high-risk flow\${generatedRiskCount===1?"":"s"}. Use the “Flows with tests” filter to review them first.</div>
528
529
  <a class="paywall-btn" href="https://app.orangepro.ai" target="_blank">View all on OrangePro Platform &rarr;</a>\`
529
530
  : remainingRiskFlows
530
531
  ? \`<div class="paywall-num">\${remainingRiskFlows} high-risk flows left</div>
531
- <div class="paywall-txt">The local MCP accepted \${D.generatedTotal} runnable generated test\${D.generatedTotal===1?"":"s"} for this report. Generate the remaining high-risk flow tests on OrangePro Platform.</div>
532
+ <div class="paywall-txt">The local MCP accepted \${D.generatedTotal} runnable generated test\${D.generatedTotal===1?"":"s"} across \${generatedRiskCount} high-risk flow\${generatedRiskCount===1?"":"s"}. Generate the remaining high-risk flow tests on OrangePro Platform.</div>
532
533
  <a class="paywall-btn" href="https://app.orangepro.ai" target="_blank">Generate remaining tests on Platform &rarr;</a>\`
533
534
  : \`<div class="paywall-num">All generated tests are shown</div>
534
535
  <div class="paywall-txt">OrangePro generated tests for every high-risk flow in this report, and every generated test is visible here.</div>\`));
@@ -0,0 +1,29 @@
1
+ /**
2
+ * G6 — the coverage-vs-proof reveal line for the start summary.
3
+ *
4
+ * Compares ONLY same-scope numbers: both sides are RTM counts over the SAME
5
+ * denominator (`summary.total`). The proven side is `coverage_confirmed` — the
6
+ * IN-DENOMINATOR proven count — never `summary.proven`, which also counts
7
+ * off-denominator proofs (relaxed hard-edge targets below the entry-point bar)
8
+ * and can exceed `total` (a 5/3 = 167% render). The signature omits `proven`
9
+ * entirely so the off-denominator number cannot be passed by mistake.
10
+ *
11
+ * `runtime_covered` is the DISJOINT runtime tier — behaviors a repo coverage
12
+ * report executed that are NOT dynamically proven. Runtime coverage only proves
13
+ * EXECUTION, and the unproven side may simply be unattempted or unrunnable —
14
+ * the line says so and never blames the tests outright. Source-report
15
+ * line-coverage totals (lcov LF/LH etc.) are NOT retained by ingestion and are
16
+ * never invented here (spec G6 guardrail). Never implies proven SHOULD equal
17
+ * coverage — they measure different things.
18
+ *
19
+ * Null when no runtime coverage was ingested (nothing to reveal) or the
20
+ * denominator is empty.
21
+ */
22
+ export function coverageRevealLine(summary) {
23
+ if (summary.runtime_covered <= 0 || summary.total <= 0)
24
+ return null;
25
+ const pct = (n) => Math.round((n / summary.total) * 100);
26
+ return (`Coverage vs proof: ${summary.runtime_covered}/${summary.total} behaviors are runtime-covered but not Dynamically Proven ` +
27
+ `(${pct(summary.runtime_covered)}%) vs ${summary.coverage_confirmed}/${summary.total} Dynamically Proven (${pct(summary.coverage_confirmed)}%) — ` +
28
+ `coverage only proves execution; the unproven side may be unattempted, blocked, or covered by tests that never assert these behaviors.`);
29
+ }
@@ -21,7 +21,7 @@ export function workspaceInitialized(root) {
21
21
  export function graphExists(root) {
22
22
  return existsSync(workspacePaths(root).graphPath);
23
23
  }
24
- const ORANGEPROIGNORE_TEMPLATE = `# .orangeproignore — paths the OrangePro local proof kit should never read.
24
+ const ORANGEPROIGNORE_PREAMBLE = `# .orangeproignore — paths the OrangePro local proof kit should never read.
25
25
  # Same spirit as .gitignore. Secrets and large assets are excluded by default.
26
26
  *.env
27
27
  *.pem
@@ -32,7 +32,8 @@ secrets/
32
32
 
33
33
  # Product-denominator defaults: example/demo apps are useful references, but
34
34
  # they usually should not count as product behavior coverage.
35
- examples/
35
+ `;
36
+ export const LEGACY_ORANGEPROIGNORE_TEMPLATE = `${ORANGEPROIGNORE_PREAMBLE}examples/
36
37
  example/
37
38
  demos/
38
39
  demo/
@@ -42,6 +43,16 @@ docs/examples/
42
43
  docs/demo/
43
44
  docs/demos/
44
45
  `;
46
+ export const ORANGEPROIGNORE_TEMPLATE = `${ORANGEPROIGNORE_PREAMBLE}/examples/
47
+ /example/
48
+ /demos/
49
+ /demo/
50
+ /samples/
51
+ /sample/
52
+ /docs/examples/
53
+ /docs/demo/
54
+ /docs/demos/
55
+ `;
45
56
  export function initWorkspace(root, now) {
46
57
  const paths = workspacePaths(root);
47
58
  mkdirSync(paths.dir, { recursive: true });
@@ -58,6 +69,18 @@ export function initWorkspace(root, now) {
58
69
  if (!existsSync(ignorePath)) {
59
70
  writeFileSync(ignorePath, ORANGEPROIGNORE_TEMPLATE, "utf8");
60
71
  }
72
+ else {
73
+ // Upgrade only the untouched generated template. A user-edited ignore file
74
+ // is configuration and must never be rewritten implicitly.
75
+ try {
76
+ if (readFileSync(ignorePath, "utf8") === LEGACY_ORANGEPROIGNORE_TEMPLATE) {
77
+ writeFileSync(ignorePath, ORANGEPROIGNORE_TEMPLATE, "utf8");
78
+ }
79
+ }
80
+ catch {
81
+ // A read-only or transiently unavailable ignore file must not fail init.
82
+ }
83
+ }
61
84
  return { paths, config: loadConfig(paths) };
62
85
  }
63
86
  export function loadConfig(paths) {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@orangepro/orangepro-mcp",
3
- "version": "0.2.2",
3
+ "version": "0.2.4",
4
4
  "private": false,
5
5
  "description": "OrangePro (`opro`) — a local-first, BYOK CLI + MCP server that builds an evidence graph from a local checkout, ingests runtime coverage, and generates grounded tests. Metadata-only exports; no source upload; generated tests stay local.",
6
6
  "license": "MIT",
@@ -85,7 +85,11 @@
85
85
  "test:integration:go:auto:slow": "OPRO_SLOW_GO_AUTO=1 vitest run tests/local/autoProveGo.test.ts --pool=forks --poolOptions.forks.maxForks=1",
86
86
  "test:integration:java:1": "vitest run tests/local/javaProveIntegration.test.ts -t \"^(?!.*(no-false-Proven|mints the same Proven)).*\" --pool=forks --poolOptions.forks.maxForks=1",
87
87
  "test:integration:java:2": "vitest run tests/local/javaProveIntegration.test.ts -t \"no-false-Proven|mints the same Proven\" --pool=forks --poolOptions.forks.maxForks=1",
88
- "test:integration:java:3": "vitest run tests/local/autoProveJava.test.ts --pool=forks --poolOptions.forks.maxForks=1",
88
+ "test:integration:java:3": "npm run test:integration:java:3:unit && npm run test:integration:java:3:prove && npm run test:integration:java:3:survivor && npm run test:integration:java:3:refused",
89
+ "test:integration:java:3:unit": "vitest run tests/local/autoProveJava.test.ts -t \"javaTestForTarget|isEligibleProvableTarget\" --pool=forks --poolOptions.forks.maxForks=1",
90
+ "test:integration:java:3:prove": "vitest run tests/local/autoProveJava.test.ts -t \"mints DP\" --pool=forks --poolOptions.forks.maxForks=1",
91
+ "test:integration:java:3:survivor": "vitest run tests/local/autoProveJava.test.ts -t \"equivalent survivor\" --pool=forks --poolOptions.forks.maxForks=1",
92
+ "test:integration:java:3:refused": "vitest run tests/local/autoProveJava.test.ts -t \"refused-shape\" --pool=forks --poolOptions.forks.maxForks=1",
89
93
  "typecheck": "tsc -p tsconfig.json --noEmit",
90
94
  "smoke:gap-fill": "npm run build && node scripts/smoke-gap-fill-loop.mjs",
91
95
  "smoke:generate-prove": "npm run build && node scripts/smoke-generate-prove-e2e.mjs",
@@ -1,7 +1,8 @@
1
1
  #!/usr/bin/env node
2
2
  // go-dynamic-proof-spike.mjs — Go dynamic-proof MECHANISM (G-1).
3
3
  //
4
- // Proves ONE free function 0->1 on a single Go module by mutation: it byte-copies
4
+ // Proves ONE free function or receiver method 0->1 on a single Go module by
5
+ // mutation: it byte-copies
5
6
  // the module into a hermetic sandbox, runs `go test -json` baseline, replaces the
6
7
  // target function body with a signature-derived sentinel (via go-mutate.go), reruns
7
8
  // the SAME test, and classifies. It emits a JSON verdict mirroring the TS/JS spike's
@@ -21,12 +22,13 @@
21
22
  // assertion call (`t.Error`/`t.Errorf`, or testify `assert.`/`require.`), NOT a
22
23
  // `t.Fatal`/`t.Fatalf`/`t.FailNow`/`t.SkipNow` hard-stop or a helper call. A build
23
24
  // error, a panic, a t.Fatal precondition, a setup/helper failure, an unbindable
24
- // failure, and an ambiguous/method/no-return name all classify as `unrunnable`,
25
+ // failure, and an ambiguous or no-return name all classify as `unrunnable`,
25
26
  // never `proven`. An equivalent-value mutation survives -> `associated_survived`.
26
27
  //
27
- // This is a spike harness only: it writes no graph edges or product artifacts and is
28
- // NOT wired into autoProve / cert / RTM / the mint path. Use only on trusted checkouts
29
- // for local measurement.
28
+ // PRODUCT-WIRED: `opro` routes Go dynamic proof through this script (operations.ts
29
+ // dynamicProofSpikePathFor("go")). The script itself writes no graph edges or product
30
+ // artifacts it emits a JSON verdict; the orchestrator is the sole interpreter and
31
+ // the only place proof is minted.
30
32
  import { spawnSync } from "node:child_process";
31
33
  import { cpSync, existsSync, lstatSync, mkdtempSync, mkdirSync, readFileSync, rmSync, symlinkSync } from "node:fs";
32
34
  import { tmpdir } from "node:os";
@@ -39,11 +41,12 @@ function usage() {
39
41
  return [
40
42
  "Usage: node scripts/spikes/go-dynamic-proof-spike.mjs --root <module> --test-run <^TestName$> --target <rel.go> --func <name> [--json]",
41
43
  "",
42
- "Runs a Go baseline test, mutates the target free function body in an isolated byte-copy, reruns the same test, and classifies the result.",
44
+ "Runs a Go baseline test, mutates the target free function or method body in an isolated byte-copy, reruns the same test, and classifies the result.",
43
45
  "--test-run is passed verbatim to `go test -run` and should anchor a single test, e.g. '^TestCompute$'.",
46
+ "--recv <T> (optional): receiver base type — mutate only `func (x T) <name>` / `func (x *T) <name>`, so a same-named method on another receiver (or a free function) can never be the mutation target.",
44
47
  "--go-assertion-line <n> (optional): 1-based test-source line of the target's assertion. When set, the mutant's failure must bind to a frame at EXACTLY that line and subtest frames are considered — so a runtime-named subtest can prove while a sibling asserting elsewhere is refused.",
45
- "G-1 scope: FREE FUNCTIONS ONLY. Methods are refused (unrunnable). Equivalent-value mutations survive (associated_survived).",
46
- "This is a spike harness only; it does not write graph edges or product artifacts and is not wired into prove/RTM/mint."
48
+ "Scope: free functions and receiver methods. Without --recv the name must resolve to exactly ONE declaration in the target file; with --recv exactly one declaration on the selected base receiver must match. Ambiguity within the filtered receiver and generic receivers still fail closed. Equivalent-value mutations survive (associated_survived).",
49
+ "Product wiring: opro prove/auto-prove invokes this script for Go targets; it writes no graph edges or product artifacts itself the caller interprets the JSON verdict."
47
50
  ].join("\n");
48
51
  }
49
52
 
@@ -460,9 +463,9 @@ function redactSecrets(text) {
460
463
  // Run the AST mutator (go run go-mutate.go). Because `go run` collapses any
461
464
  // non-zero child status to 1, we classify on the MUTATE_ERROR:<code> marker the
462
465
  // helper prints to stderr, not the exit code.
463
- function mutateFunc({ targetAbs, func, mode, cacheRoot, timeoutMs }) {
466
+ function mutateFunc({ targetAbs, func, recv, mode, cacheRoot, timeoutMs }) {
464
467
  const helper = path.join(path.dirname(fileURLToPath(import.meta.url)), "go-mutate.go");
465
- const result = spawnSync(goBin(), ["run", helper, "--file", targetAbs, "--func", func, "--mode", mode], {
468
+ const result = spawnSync(goBin(), ["run", helper, "--file", targetAbs, "--func", func, ...(recv ? ["--recv", recv] : []), "--mode", mode], {
466
469
  encoding: "utf8",
467
470
  timeout: timeoutMs,
468
471
  env: hermeticEnv(cacheRoot),
@@ -481,9 +484,9 @@ function mutateFunc({ targetAbs, func, mode, cacheRoot, timeoutMs }) {
481
484
 
482
485
  function mutateErrorReason(code) {
483
486
  switch (code) {
484
- case 3: return "target function name is ambiguous (more than one free function)";
485
- case 4: return "target free function was not found";
486
- case 5: return "target is a method (out of scope for G-1)";
487
+ case 3: return "target name is ambiguous (more than one free function or method)";
488
+ case 4: return "target free function or method was not found";
489
+ // code 5 (method out of scope) is retired methods are mutable now, never emitted.
487
490
  case 6: return "target function has no return value (not mutable)";
488
491
  default: return "mutation could not be applied";
489
492
  }
@@ -565,6 +568,7 @@ function main() {
565
568
  const mutation = mutateFunc({
566
569
  targetAbs: path.join(mutantCopy.repoRoot, targetRel),
567
570
  func: args.func,
571
+ recv: args.recv,
568
572
  mode: args.mode,
569
573
  cacheRoot: mutantCopy.tmpRoot,
570
574
  timeoutMs
@@ -2,11 +2,16 @@
2
2
 
3
3
  // go-mutate.go — AST-based body replacer for the Go dynamic-proof spike (G-1).
4
4
  //
5
- // Locates ONE free function `func Name(params) rets { ... }` by exact name and
6
- // replaces its BODY with a signature-derived sentinel, then writes the mutated
7
- // file. It is a spike helper only: it writes no product artifacts and is not
8
- // wired into prove/RTM/mint. G-1 scope is FREE FUNCTIONS ONLY — methods
9
- // (`func (r Recv) M()`) are recognized and refused as out-of-scope (G-2).
5
+ // Locates ONE function declaration by exact name — a free function `func Name(...)`
6
+ // or a receiver method `func (r Recv) Name(...)` and replaces its BODY with a
7
+ // signature-derived sentinel, then writes the mutated file. Invoked by
8
+ // go-dynamic-proof-spike.mjs (the product Go proof path); it writes ONLY the
9
+ // mutated file inside the sandbox copy no graph or product artifacts. The
10
+ // name must resolve to exactly ONE declaration — in the whole file without
11
+ // --recv, or on the selected base receiver with --recv <T> (receiver-exact
12
+ // selection for receiver-qualified `Recv.M` targets — never the wrong decl,
13
+ // so A.M and B.M can coexist and still be individually mutable). Ambiguity
14
+ // within that filter fails(3); generic receivers are refused (not found).
10
15
  //
11
16
  // Modes:
12
17
  // sentinel — replace body with a type-compatible, deliberately-wrong value
@@ -19,9 +24,10 @@
19
24
  // Exit codes (distinct, so the Node orchestrator can classify precisely):
20
25
  // 0 ok, mutated file written
21
26
  // 2 usage / IO / parse error
22
- // 3 ambiguous: more than one free function with that name
23
- // 4 not found: no free function with that name
24
- // 5 out of scope: a METHOD with that name exists (G-2, refused in G-1)
27
+ // 3 ambiguous: more than one declaration (free and/or method) with that name
28
+ // 4 not found: no free function or method with that name
29
+ // 5 RETIRED was "method out of scope (G-2)" before methods became mutable;
30
+ // no longer emitted (kept so codes 3/4/6 stay stable for the orchestrator)
25
31
  // 6 not mutable: the function has no return values (no signature-derived
26
32
  // sentinel is possible) -> fail closed, never mutated
27
33
  package main
@@ -35,6 +41,7 @@ import (
35
41
  "go/printer"
36
42
  "go/token"
37
43
  "os"
44
+ "strings"
38
45
  )
39
46
 
40
47
  // fail prints a stable, machine-readable marker plus a human message and exits
@@ -50,7 +57,8 @@ func fail(code int, format string, args ...any) {
50
57
 
51
58
  func main() {
52
59
  file := flag.String("file", "", "path to the Go source file to mutate")
53
- fn := flag.String("func", "", "exact name of the free function to mutate")
60
+ fn := flag.String("func", "", "exact name of the free function or method to mutate")
61
+ recv := flag.String("recv", "", "receiver base type name; when set, match only methods on this receiver")
54
62
  out := flag.String("out", "", "path to write the mutated file (defaults to --file)")
55
63
  mode := flag.String("mode", "sentinel", "sentinel | equivalent")
56
64
  flag.Parse()
@@ -72,31 +80,47 @@ func main() {
72
80
  fail(2, "parse error: %v", err)
73
81
  }
74
82
 
75
- var freeMatches []*ast.FuncDecl
76
- methodMatch := false
83
+ // Collect BOTH free functions and methods named *fn. The proof lane only ever
84
+ // targets a method whose name is UNIQUE in its package (the analyzer's
85
+ // uniqueGoPackageSymbol refuses cross-file collisions before an edge is minted);
86
+ // this file-scoped count is the in-file backstop, so free+method or two-method
87
+ // collisions fail(3) as ambiguous — never a mislabeled mutation. A lone decl
88
+ // (free OR method) is mutated identically via the receiver-agnostic sentinel.
89
+ var matches []*ast.FuncDecl
77
90
  for _, decl := range astFile.Decls {
78
91
  fd, ok := decl.(*ast.FuncDecl)
79
92
  if !ok || fd.Name == nil || fd.Name.Name != *fn {
80
93
  continue
81
94
  }
82
- if fd.Recv != nil { // method -> out of scope for G-1
83
- methodMatch = true
95
+ // Refuse generic receivers (r T[U]) receiver base type is not a bare Ident.
96
+ if fd.Recv != nil && recvBaseIdent(fd) == nil {
84
97
  continue
85
98
  }
86
- freeMatches = append(freeMatches, fd)
99
+ // Receiver-exact selection: when --recv is set, only a method on that base
100
+ // receiver type matches — a free function or another receiver never can, so
101
+ // a receiver-qualified target can never mutate the wrong declaration.
102
+ if *recv != "" {
103
+ if fd.Recv == nil {
104
+ continue
105
+ }
106
+ if id := recvBaseIdent(fd); id == nil || id.Name != *recv {
107
+ continue
108
+ }
109
+ }
110
+ matches = append(matches, fd)
87
111
  }
88
112
 
89
- if len(freeMatches) > 1 {
90
- fail(3, "ambiguous: %d free functions named %q", len(freeMatches), *fn)
113
+ if len(matches) > 1 {
114
+ fail(3, "ambiguous: %d declarations named %q (free and/or methods)", len(matches), *fn)
91
115
  }
92
- if len(freeMatches) == 0 {
93
- if methodMatch {
94
- fail(5, "out of scope: %q is a method (G-2); G-1 handles free functions only", *fn)
116
+ if len(matches) == 0 {
117
+ if *recv != "" {
118
+ fail(4, "not found: no method named %q on receiver %q", *fn, *recv)
95
119
  }
96
- fail(4, "not found: no free function named %q", *fn)
120
+ fail(4, "not found: no free function or method named %q", *fn)
97
121
  }
98
122
 
99
- target := freeMatches[0]
123
+ target := matches[0]
100
124
  results := target.Type.Results
101
125
  if results == nil || len(results.List) == 0 {
102
126
  fail(6, "not mutable: %q has no return values; no signature-derived sentinel is possible", *fn)
@@ -104,6 +128,15 @@ func main() {
104
128
 
105
129
  if *mode == "sentinel" {
106
130
  target.Body = sentinelBody(results)
131
+ // The sentinel body can orphan imports the original body used (Go
132
+ // rejects unused imports, so the mutant would fail to BUILD and the
133
+ // oracle would refuse — an honest but useless verdict for most real
134
+ // functions). Rewrite now-unused imports to blank imports: package
135
+ // init side effects are preserved, no behavior is added, and the
136
+ // repair is fail-safe in both directions — over-blanking a used
137
+ // import still fails the build (refusal, never proof), and a missed
138
+ // unused import is exactly today's behavior.
139
+ blankUnusedImports(astFile)
107
140
  }
108
141
  // equivalent mode: leave target.Body untouched (semantically identical).
109
142
 
@@ -117,6 +150,55 @@ func main() {
117
150
  }
118
151
  }
119
152
 
153
+ // blankUnusedImports renames imports whose package qualifier is no longer
154
+ // referenced anywhere in the file to blank imports (`_ "path"`). Dot imports
155
+ // and existing blank imports are left untouched. Qualifier detection is
156
+ // syntactic (selector bases), which over-approximates "used" — the safe
157
+ // direction: we only ever blank an import nothing references.
158
+ func blankUnusedImports(f *ast.File) {
159
+ used := map[string]bool{}
160
+ ast.Inspect(f, func(n ast.Node) bool {
161
+ if sel, ok := n.(*ast.SelectorExpr); ok {
162
+ if id, ok := sel.X.(*ast.Ident); ok {
163
+ used[id.Name] = true
164
+ }
165
+ }
166
+ return true
167
+ })
168
+ for _, imp := range f.Imports {
169
+ if imp.Name != nil {
170
+ if imp.Name.Name == "_" || imp.Name.Name == "." {
171
+ continue
172
+ }
173
+ if !used[imp.Name.Name] {
174
+ imp.Name = ast.NewIdent("_")
175
+ }
176
+ continue
177
+ }
178
+ path := strings.Trim(imp.Path.Value, "\"")
179
+ base := path[strings.LastIndex(path, "/")+1:]
180
+ if !used[base] {
181
+ imp.Name = ast.NewIdent("_")
182
+ }
183
+ }
184
+ }
185
+
186
+ // recvBaseIdent returns the receiver type's base identifier for a method decl
187
+ // (unwrapping a pointer receiver `*T` to `T`), or nil for a generic/unsupported
188
+ // receiver. Used only to refuse generic receivers; value-vs-pointer is irrelevant
189
+ // to body mutation (Go auto-(de)refs at the call site).
190
+ func recvBaseIdent(fd *ast.FuncDecl) *ast.Ident {
191
+ if fd.Recv == nil || len(fd.Recv.List) != 1 {
192
+ return nil
193
+ }
194
+ t := fd.Recv.List[0].Type
195
+ if star, ok := t.(*ast.StarExpr); ok {
196
+ t = star.X
197
+ }
198
+ id, _ := t.(*ast.Ident)
199
+ return id
200
+ }
201
+
120
202
  // sentinelBody builds `{ return <zero>, <zero>, ... }` matching the function's
121
203
  // result signature so the mutant COMPILES. Zero values are type-derived and
122
204
  // deliberately wrong for any function whose real return is non-zero; when a