Merge branch 'main' into fix/2604-rust-trait-object-dispatch

eval/tests/test_proposer_sandbox.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import json
 import os
+import shutil
 import stat
 import subprocess
 import sys
@@ -19,11 +20,13 @@ from workflow_bench.process_control import ManagedProcessResult, run_managed
 from workflow_bench.proposer_sandbox import (
     MAX_BUNDLE_BYTES,
     MAX_EVIDENCE_FILE_BYTES,
+    SANDBOX_NODE,
     SANDBOX_PYTHON3,
     SANDBOX_SHELL_PREFIX,
     SANDBOX_USER_SKILLS,
     ReadOnlyMount,
     SandboxError,
+    _runtime_mount_args,
     build_claude_settings,
     build_sandbox_environment,
     prepare_sandbox,
@@ -191,6 +194,36 @@ def test_sandbox_command_has_minimal_mounts_and_no_host_root_bind(tmp_path: Path
     assert not private_root.exists()
 
 
+def test_runtime_mounts_bind_the_resolved_node_to_a_fresh_sandbox_path(monkeypatch) -> None:
+    # sanitized_graph.py and runner_sessions.py invoke the sandboxed graph CLI
+    # via SANDBOX_NODE. node's real host location varies (GitHub-hosted
+    # runner images happen to have one under /usr/local/bin; a self-hosted
+    # runner's actions/setup-node installs into its own tool-cache directory
+    # instead), so this must bind to a FRESH sandbox path like /opt/claude/...
+    # rather than anywhere under /usr, /bin, /lib, or /lib64: those are
+    # already read-only bound by this same function, and bwrap can't create
+    # a new mount-point file inside an already-read-only tree when the real
+    # path doesn't already exist there on the host (observed empirically:
+    # "bwrap: Can't create file at /usr/local/bin/node: Read-only file
+    # system" when this bind first targeted that path on a self-hosted
+    # runner where node isn't really there).
+    monkeypatch.setattr(
+        "workflow_bench.proposer_sandbox.shutil.which",
+        lambda name: "/opt/hostedtoolcache/node/22.18.0/x64/bin/node" if name == "node" else None,
+    )
+    args = _runtime_mount_args()
+    node_index = args.index("/opt/hostedtoolcache/node/22.18.0/x64/bin/node")
+    assert args[node_index - 1] == "--ro-bind"
+    assert args[node_index + 1] == SANDBOX_NODE
+    assert not any(SANDBOX_NODE.startswith(bound + "/") for bound in ("/usr", "/bin", "/lib", "/lib64"))
+
+
+def test_runtime_mounts_skip_the_node_bind_when_node_is_unresolvable(monkeypatch) -> None:
+    monkeypatch.setattr("workflow_bench.proposer_sandbox.shutil.which", lambda name: None)
+    args = _runtime_mount_args()
+    assert SANDBOX_NODE not in args
+
+
 def test_stricter_prefix_freezes_evaluated_skills_and_can_unshare_network(tmp_path: Path) -> None:
     clone = tmp_path / "clone"
     skill = clone / ".claude" / "skills" / "gitnexus-work"
@@ -219,6 +252,43 @@ def test_stricter_prefix_freezes_evaluated_skills_and_can_unshare_network(tmp_pa
     assert prefix[user_index - 2] == "--ro-bind"
 
 
+@pytest.mark.skipif(
+    os.environ.get("GITNEXUS_REQUIRE_BWRAP_CANARY") != "1",
+    reason="real Bubblewrap canary is mandatory in the named Ubuntu CI job",
+)
+def test_real_bubblewrap_runs_node_from_outside_the_bound_trees(tmp_path: Path, monkeypatch) -> None:
+    # Reproduces the self-hosted-runner failure directly: node resolved from
+    # a path outside /usr, /bin, /lib, /lib64 (actions/setup-node's own
+    # tool-cache convention) must still be reachable inside the sandbox at
+    # SANDBOX_NODE. A real node copied to a fresh, non-system location stands
+    # in for the tool-cache install; argv-construction tests alone can't
+    # catch a bwrap-level "Can't create file ...: Read-only file system"
+    # (the actual error this fix resolves), only a real bwrap invocation can.
+    real_node = shutil.which("node")
+    if not real_node:
+        pytest.skip("no node on PATH to relocate for this canary")
+    toolcache = tmp_path / "toolcache"
+    toolcache.mkdir()
+    relocated_node = toolcache / "node"
+    shutil.copy2(real_node, relocated_node)
+    relocated_node.chmod(0o755)
+    # Only fake "node"'s resolution -- prepare_sandbox's own bwrap/claude
+    # lookups (_resolve_executable) also go through shutil.which, and must
+    # keep resolving for real or preflight fails before the sandbox is even
+    # built.
+    real_which = shutil.which
+    monkeypatch.setattr(
+        "workflow_bench.proposer_sandbox.shutil.which",
+        lambda name: str(relocated_node) if name == "node" else real_which(name),
+    )
+
+    clone = tmp_path / "clone"
+    clone.mkdir()
+    with prepare_sandbox(clone=clone, claude_bin=Path(sys.executable), preflight=True) as sandbox:
+        result = sandbox.run([SANDBOX_NODE, "--version"], timeout=10)
+    assert result.ok, result.stderr_tail
+
+
 @pytest.mark.skipif(
     os.environ.get("GITNEXUS_REQUIRE_BWRAP_CANARY") != "1",
     reason="real Bubblewrap canary is mandatory in the named Ubuntu CI job",
@@ -772,4 +842,3 @@ for line in sys.stdin:
     assert bash_result.get("is_error") is not True, bash_result
     assert (clone / "bash-called").read_text() == "canary"
     assert (clone / "mcp-called").read_text() == "ok"
-

eval/tests/test_workflow_bench_sessions.py

@@ -438,11 +438,11 @@ def test_real_bubblewrap_runtime_mount_imports_cli_without_exposing_checkout(tmp
         preflight=True,
     ) as sandbox:
         visibility = sandbox.run(
-            ["/usr/local/bin/node", "-e", visibility_script],
+            [runner.SANDBOX_NODE, "-e", visibility_script],
             timeout=10,
         )
         imported = sandbox.run(
-            ["/usr/local/bin/node", runner.SANDBOX_GITNEXUS_ENTRYPOINT, "--version"],
+            [runner.SANDBOX_NODE, runner.SANDBOX_GITNEXUS_ENTRYPOINT, "--version"],
             timeout=10,
         )
         # --version never reaches the `analyze` command, which is loaded via a
@@ -451,7 +451,7 @@ def test_real_bubblewrap_runtime_mount_imports_cli_without_exposing_checkout(tmp
         # resolve-analyze-cmd.cjs. Require the compiled analyze module
         # directly so this canary actually exercises that chain.
         analyze_imported = sandbox.run(
-            ["/usr/local/bin/node", "-e", f"require('{runner.SANDBOX_GITNEXUS}/dist/cli/analyze.js')"],
+            [runner.SANDBOX_NODE, "-e", f"require('{runner.SANDBOX_GITNEXUS}/dist/cli/analyze.js')"],
             timeout=10,
         )
 

eval/workflow_bench/proposer_sandbox.py

@@ -27,6 +27,7 @@ SANDBOX_TMP = "/tmp"
 SANDBOX_CLAUDE = "/opt/claude/claude"
 SANDBOX_SHELL_PREFIX = "/opt/claude/shell-prefix"
 SANDBOX_PYTHON3 = "/opt/claude/python3"
+SANDBOX_NODE = "/opt/claude/node"
 SANDBOX_PATH = "/opt/claude:/usr/local/bin:/usr/bin:/bin"
 SANDBOX_GITNEXUS = "/opt/gitnexus"
 SANDBOX_GITNEXUS_SHARED = "/opt/gitnexus-shared"
@@ -354,6 +355,20 @@ def _runtime_mount_args() -> list[str]:
         path = Path(raw)
         if path.exists():
             args += ["--ro-bind", raw, raw]
+    # sanitized_graph.py and runner_sessions.py invoke the sandboxed graph
+    # CLI via SANDBOX_NODE. Bind whatever `node` actually resolves to on PATH
+    # there -- true node location varies by host (GitHub-hosted runner images
+    # happen to have one under /usr/local/bin; a self-hosted runner's
+    # actions/setup-node installs into its own tool-cache directory instead).
+    # Target must be a fresh path like /opt/claude/... rather than anywhere
+    # under /usr, /bin, /lib, or /lib64: those are already read-only bound
+    # above, and bwrap can't create a new mount-point file inside an
+    # already-read-only tree when the real path doesn't already exist there
+    # (the exact case a self-hosted runner hits, and the reason this bind
+    # exists at all).
+    node_bin = shutil.which("node")
+    if node_bin:
+        args += ["--ro-bind", node_bin, SANDBOX_NODE]
     for raw in (
         "/etc/ssl",
         "/etc/hosts",
@@ -398,7 +413,7 @@ def _create_python3_wrapper(private_root: Path) -> Path:
     """
 
     wrapper = private_root / "python3"
-    wrapper.write_text("#!/bin/bash\nset -eu\nexec /usr/bin/python3 \"$@\"\n")
+    wrapper.write_text('#!/bin/bash\nset -eu\nexec /usr/bin/python3 "$@"\n')
     wrapper.chmod(0o500)
     return wrapper
 

eval/workflow_bench/runner.py

@@ -78,6 +78,7 @@ from .proposer_sandbox import (
     SANDBOX_GITNEXUS as SANDBOX_GITNEXUS,
     SANDBOX_GITNEXUS_REGISTRY,
     SANDBOX_GITNEXUS_SHARED as SANDBOX_GITNEXUS_SHARED,
+    SANDBOX_NODE as SANDBOX_NODE,
     SANDBOX_WORKSPACE,
     ReadOnlyMount,
     SandboxError,

eval/workflow_bench/runner_sessions.py

@@ -18,6 +18,7 @@ from .proposer_sandbox import (
     SANDBOX_GITNEXUS,
     SANDBOX_GITNEXUS_REGISTRY,
     SANDBOX_HOME,
+    SANDBOX_NODE,
     SANDBOX_TMP,
     SANDBOX_WORKSPACE,
     SandboxError,
@@ -50,6 +51,8 @@ def measured_cost(raw: Any) -> float | None:
     if not math.isfinite(raw) or raw < 0:
         return None
     return float(raw)
+
+
 SANDBOX_GITNEXUS_ENTRYPOINT = f"{SANDBOX_GITNEXUS}/dist/cli/index.js"
 SENSITIVE_EVENT_KEYS = frozenset(
     {
@@ -113,7 +116,7 @@ def sandbox_mcp_config() -> str:
                     "PATH=/usr/local/bin:/usr/bin:/bin",
                     "LANG=C.UTF-8",
                     "GIT_TERMINAL_PROMPT=0",
-                    "/usr/local/bin/node",
+                    SANDBOX_NODE,
                     SANDBOX_GITNEXUS_ENTRYPOINT,
                     "mcp",
                 ],

eval/workflow_bench/sanitized_graph.py

@@ -16,6 +16,7 @@ from .process_control import ManagedProcessError, run_managed
 from .proposer_sandbox import (
     SANDBOX_GITNEXUS,
     SANDBOX_HOME,
+    SANDBOX_NODE,
     SANDBOX_WORKSPACE,
     ReadOnlyMount,
     SandboxError,
@@ -248,7 +249,7 @@ def _run_graph_cli(
 ) -> bytes | None:
     command = [
         *prefix,
-        "/usr/local/bin/node",
+        SANDBOX_NODE,
         SANDBOX_GITNEXUS_ENTRYPOINT,
         *arguments,
     ]

gitnexus/bench/scope-capture/baselines.json

@@ -89,7 +89,7 @@
     "_rebaselined": "#1919 review CF3 fix: extended kotlin-local-property-owner (init/accessor destructuring) + new dart-accessor-owner fixture (getter/setter ownership). Fingerprint-only corpus drift; scaling ~1.0."
   },
   "java": {
-    "fingerprint": "85fc7af9c3c1bceac76cb4f27214410b04967682a2eaa7e468e26efd1f4e2537",
+    "fingerprint": "d04298a91beec76d0fa7099b3d71265723be60c1df688969aa954f135dd49686",
     "scaling_budget": 1.5,
     "_rebaselined_callable_flow_2522_review": "PR #2522 review hardening: callable operands retain expression/qualified identity and formals retain signature metadata; same-name lexical regions use an O(ancestor-depth) ID-set lookup. Prior d5c59d7dc9e206637515d5aea1163f7c1cdd76410c38c5fe6143d13d19677d6a -> 004a3592998dca1193bd1429a8284513725de7764f2a3eceedaaa984cfd763b4; scaling 0.992 < 1.5.",
     "_rebaselined_callable_flow_2522_followup": "PR #2522 follow-up: Java method-reference/SAM callable flow facts with invocation-result suppression. Prior 062d754764aaa8a6772fb90875c710502a63e3e7a300e633942381ed914faada -> d5c59d7dc9e206637515d5aea1163f7c1cdd76410c38c5fe6143d13d19677d6a; scaling 1.074 < 1.5.",
@@ -98,7 +98,8 @@
     "_rebaselined_2522_review_fixes": "PR #2522 review fixes: get/test dropped from callableProtocolMethods. Prior 004a3592998dca1193bd1429a8284513725de7764f2a3eceedaaa984cfd763b4 -> f3b4f4b6610e07c3ac90deb1c53d3572b6ad55a36e5d7134984876d30031ff67; scaling ratio re-verified within budget.",
     "_rebaselined_2550_instance_model": "PR #2549 (#2550): anonymous class bodies emit synthesized @declaration.class/@declaration.name (Worker$N), an @reference.inherits to the constructed type, and receiver @type-binding.* captures; six new java-* fixtures joined the corpus. Prior f3b4f4b6610e07c3ac90deb1c53d3572b6ad55a36e5d7134984876d30031ff67 -> d79c3b92acfc866094981499b977388ca14f90839bca0c040342ab1cec00aa90; scaling 1.058 < 1.5.",
     "_rebaselined_2555_enum_constant_bodies": "PR for #2555: enum constant bodies emit synthesized E$N classes + @reference.inherits to the host enum; anonymous naming follows JLS 13.1 immediately-enclosing-type chains INCLUDING anonymous enclosing types (NestHost$1$1, N$1$1); six new java-* fixtures joined the corpus. Prior d79c3b92acfc866094981499b977388ca14f90839bca0c040342ab1cec00aa90 -> 975b68aaac6d06094260fb0c67f9b1bc03692ba7220669d192aca9dccd5fc0ca; scaling 1.05 < 1.5.",
-    "_rebaselined_2564_record_capture": "PR for #2564: JAVA_QUERIES gained a (record_declaration name: (identifier) @name) @definition.record capture, previously entirely missing (record_declaration had no structure-phase capture at all, unlike class/interface/enum) - a record's methods existed as ownerless Method nodes with no HAS_METHOD edge. Two new java-* fixtures (java-record-methods, java-new-expr-chain-call) joined the corpus. Prior 975b68aaac6d06094260fb0c67f9b1bc03692ba7220669d192aca9dccd5fc0ca -> 85fc7af9c3c1bceac76cb4f27214410b04967682a2eaa7e468e26efd1f4e2537; scaling 1.059 < 1.5."
+    "_rebaselined_2564_record_capture": "PR for #2564: JAVA_QUERIES gained a (record_declaration name: (identifier) @name) @definition.record capture, previously entirely missing (record_declaration had no structure-phase capture at all, unlike class/interface/enum) - a record's methods existed as ownerless Method nodes with no HAS_METHOD edge. Two new java-* fixtures (java-record-methods, java-new-expr-chain-call) joined the corpus. Prior 975b68aaac6d06094260fb0c67f9b1bc03692ba7220669d192aca9dccd5fc0ca -> 85fc7af9c3c1bceac76cb4f27214410b04967682a2eaa7e468e26efd1f4e2537; scaling 1.059 < 1.5.",
+    "_rebaselined_2561_enum_constant_receiver": "PR for #2561: synthesizeJavaAnonymousClassDeclarations now emits a class-scope @type-binding.annotation/name/type per enum constant (constant simple name -> its E$N synthesized class when bodied, else the host enum) so E.CONST.method() resolves through the existing compound-receiver chain walk. Two drivers of the drift, both in the java-enum-constant-body fixture (this bench's corpus IS test/fixtures/lang-resolution): (1) one extra type-binding match per enum_constant from the capture change; (2) review follow-up added a body-less Plain.java enum + EnumConst.dispatchToConstant/dispatchInherited methods (bodied-override, inherited-via-MRO, and body-less dispatch call sites). The review's fail-safe hardening (bodied constant binds ONLY to E$N, never the host enum, when name synthesis fails on a malformed tree) is output-neutral on this well-formed corpus (verified: fingerprint identical with and without it). Prior 85fc7af9c3c1bceac76cb4f27214410b04967682a2eaa7e468e26efd1f4e2537 -> d04298a91beec76d0fa7099b3d71265723be60c1df688969aa954f135dd49686; scaling < 1.5."
   },
   "typescript": {
     "fingerprint": "3280b13d3f9378ab23eee31c2edc779b5a9ae1e7bb510c23a24855b44406d2f4",

gitnexus/src/core/ingestion/languages/java/captures.ts

@@ -372,23 +372,49 @@ function synthesizeJavaAnonymousClassDeclarations(rootNode: SyntaxNode): Capture
   // constant's class extends its HOST ENUM (javac semantics), so the
   // inherits reference names the enum — giving `mroFor(E$N) ∋ E` and
   // keeping bare calls from the body to the enum's own helpers alive
-  // through the ownership gate's MRO arm. No receiver typeBinding piece:
-  // constants are not variable initializers; `E.A.hook()` dispatch rides
-  // the existing enum receiver machinery.
+  // through the ownership gate's MRO arm.
   for (const constant of rootNode.descendantsOfType('enum_constant')) {
-    const name = synthesizeJavaAnonymousClassName(constant);
-    if (name === undefined) continue;
-    const body = constant.childForFieldName?.('body');
-    if (body === null || body === undefined || body.type !== 'class_body') continue;
-    out.push({
-      '@declaration.class': nodeToCapture('@declaration.class', body),
-      '@declaration.name': syntheticCapture('@declaration.name', body, name),
-    });
     const hostEnum = javaEnclosingEnumNameOf(constant);
-    if (hostEnum !== undefined) {
+    const bodyNode = constant.childForFieldName?.('body');
+    const isBodied = bodyNode !== null && bodyNode !== undefined && bodyNode.type === 'class_body';
+    const bodiedName = synthesizeJavaAnonymousClassName(constant);
+    if (bodiedName !== undefined && isBodied) {
       out.push({
-        '@reference.inherits': nodeToCapture('@reference.inherits', body),
-        '@reference.name': syntheticCapture('@reference.name', body, hostEnum),
+        '@declaration.class': nodeToCapture('@declaration.class', bodyNode),
+        '@declaration.name': syntheticCapture('@declaration.name', bodyNode, bodiedName),
+      });
+      if (hostEnum !== undefined) {
+        out.push({
+          '@reference.inherits': nodeToCapture('@reference.inherits', bodyNode),
+          '@reference.name': syntheticCapture('@reference.name', bodyNode, hostEnum),
+        });
+      }
+    }
+
+    // Receiver dispatch (#2561): `E.CONST.method()` resolves through the
+    // generic compound-receiver chain walk, which looks up each dotted
+    // segment via the owning class scope's `typeBindings` map — the same
+    // mechanism a field declaration uses (`private User user;` binds
+    // `user` on the class scope). Binding the constant's own simple name
+    // there — to its synthesized `E$N` class when bodied (MRO includes E,
+    // so members inherited from the enum still resolve), or to the host
+    // enum itself when body-less — makes `E.CONST.method()` resolve with
+    // no changes to the shared receiver-binding machinery.
+    //
+    // A bodied constant binds ONLY to its `E$N` class, never the host enum:
+    // if name synthesis fails on a malformed/error-recovery tree (`bodiedName`
+    // undefined despite a real body), emit nothing rather than silently
+    // misattributing an OVERRIDING constant's receiver to the enum's own
+    // (non-overridden) method — a wrong edge is worse than no edge. Mirrors
+    // the `object_creation_expression` branch, which skips on synthesis
+    // failure. `hostEnum` is used only for genuinely body-less constants.
+    const constantNameNode = constant.childForFieldName?.('name');
+    const constantType = isBodied ? bodiedName : hostEnum;
+    if (constantNameNode !== null && constantNameNode !== undefined && constantType !== undefined) {
+      out.push({
+        '@type-binding.annotation': nodeToCapture('@type-binding.annotation', constant),
+        '@type-binding.name': nodeToCapture('@type-binding.name', constantNameNode),
+        '@type-binding.type': syntheticCapture('@type-binding.type', constant, constantType),
       });
     }
   }

gitnexus/test/fixtures/lang-resolution/java-enum-constant-body/src/EnumConst.java

@@ -21,4 +21,12 @@ class Unrelated {
     public void caller() {
         hook();
     }
+
+    public void dispatchToConstant() {
+        EnumConst.A.hook();
+    }
+
+    public void dispatchInherited() {
+        EnumConst.A.log();
+    }
 }

gitnexus/test/fixtures/lang-resolution/java-enum-constant-body/src/Plain.java

@@ -0,0 +1,13 @@
+public enum Plain {
+    A;
+
+    public void m() {
+        System.out.println("plain m");
+    }
+}
+
+class PlainCaller {
+    public void callPlain() {
+        Plain.A.m();
+    }
+}

gitnexus/test/integration/resolvers/java.test.ts

@@ -3055,3 +3055,43 @@ describe('Java enum constant bodies (#2555)', () => {
     expect(misattributed).toBeUndefined();
   }, 60000);
 });
+
+// ---------------------------------------------------------------------------
+// #2561: E.CONST.method() emits no CALLS edge — the receiver-side follow-up
+// to #2555. A bodied constant's receiver must resolve to its synthesized
+// E$N class; a body-less constant's receiver must resolve to the host enum
+// itself.
+// ---------------------------------------------------------------------------
+
+describe('Java enum-constant receiver dispatch (#2561)', () => {
+  let result: PipelineResult;
+
+  beforeAll(async () => {
+    result = await runPipelineFromRepo(path.join(FIXTURES, 'java-enum-constant-body'), () => {});
+  }, 60000);
+
+  it('resolves EnumConst.A.hook() to the bodied constant override (EnumConst$1.hook#0)', () => {
+    const calls = getRelationships(result, 'CALLS');
+    const dispatch = calls.find((c) => c.source === 'dispatchToConstant' && c.target === 'hook');
+    expect(dispatch).toBeDefined();
+    expect(dispatch!.rel.targetId).toBe('Method:src/EnumConst.java:EnumConst$1.hook#0');
+  });
+
+  it("resolves EnumConst.A.log() to the host enum's inherited method via E$N's MRO (EnumConst.log#0)", () => {
+    // A's body overrides hook() but NOT log(); log() lives only on the enum.
+    // The bodied constant's receiver binds to EnumConst$1, whose MRO includes
+    // EnumConst (via @reference.inherits), so the qualified call reaches the
+    // host enum's own method — the inherited-dispatch capability the fix enables.
+    const calls = getRelationships(result, 'CALLS');
+    const dispatch = calls.find((c) => c.source === 'dispatchInherited' && c.target === 'log');
+    expect(dispatch).toBeDefined();
+    expect(dispatch!.rel.targetId).toBe('Method:src/EnumConst.java:EnumConst.log#0');
+  });
+
+  it("resolves Plain.A.m() to the body-less constant's inherited enum method (Plain.m#0)", () => {
+    const calls = getRelationships(result, 'CALLS');
+    const dispatch = calls.find((c) => c.source === 'callPlain' && c.target === 'm');
+    expect(dispatch).toBeDefined();
+    expect(dispatch!.rel.targetId).toBe('Method:src/Plain.java:Plain.m#0');
+  });
+});