Merge branch 'upstream/main' into fix/java-enum-extraction and resolve conflict in extract_defs.c

Author: sahil-mangla

.github/issue-labeler.yml

@@ -1,17 +1,21 @@
-# Config for github/issue-labeler (.github/workflows/issue-labeler.yml).
-# Non-versioned format: one regex per label, matched against title + body.
+# Config for the Issue area labeler (.github/workflows/issue-labeler.yml).
+# FORMAT (parsed line-wise by the workflow): one rule per line, exactly
+#   "label": 'regex'
+# Patterns are compiled as JavaScript RegExp with the `i` flag applied by
+# the workflow — do NOT use PCRE-only syntax like inline `(?i)` groups
+# (that broke every run, #764). Matched against issue title + body.
 # Additive only — these never remove a maintainer's manual label.
 
-"windows": '(?i)\b(windows|win\s?1[01]|powershell|\.ps1|mapped drive|smb share|unc path)\b'
+"windows": '\b(windows|win\s?1[01]|powershell|\.ps1|mapped drive|smb share|unc path)\b'
 
-"stability/performance": '(?i)(out of memory|\boom\b|memory leak|segfault|sigsegv|sigbus|crash(es|ed|ing)?|core dumped|\bhang(s|ing)?\b|deadlock|freezes?|time(s)?\s?out|timeout|never finishes|cgroup)'
+"stability/performance": '(out of memory|\boom\b|memory leak|segfault|sigsegv|sigbus|crash(es|ed|ing)?|core dumped|\bhang(s|ing)?\b|deadlock|freezes?|time(s)?\s?out|timeout|never finishes|cgroup)'
 
-"parsing/quality": '(?i)(trace_path|query_graph|search_graph|calls? edge|missing (edges|nodes)|false positive|zero edges|0 edges|module node|not indexed|extraction|wrong (node|label))'
+"parsing/quality": '(trace_path|query_graph|search_graph|calls? edge|missing (edges|nodes)|false positive|zero edges|0 edges|module node|not indexed|extraction|wrong (node|label))'
 
-"editor/integration": '(?i)(cursor|vscode|vs code|opencode|codex|claude code|gemini cli|antigravity|mcp client|\.mcp\.json|installer)'
+"editor/integration": '(cursor|vscode|vs code|opencode|codex|claude code|gemini cli|antigravity|mcp client|\.mcp\.json|installer)'
 
-"ux/behavior": '(?i)(web ui|\bui\b|dashboard|3d graph|visuali[sz]ation|watcher|project name|frontend)'
+"ux/behavior": '(web ui|\bui\b|dashboard|3d graph|visuali[sz]ation|watcher|project name|frontend)'
 
-"cypher": '(?i)\bcypher\b'
+"cypher": '\bcypher\b'
 
-"language-request": '(?i)(language support|hybrid lsp|new language support|support for \w+ language)'
+"language-request": '(language support|hybrid lsp|new language support|support for \w+ language)'

.github/workflows/issue-labeler.yml

@@ -1,9 +1,15 @@
 name: Issue area labeler
 
 # Adds area labels to new/edited issues based on keyword regexes in
-# .github/issue-labeler.yml. Additive only (sync-labels off): it never
-# removes a label a maintainer set by hand. Base bug/enhancement labels
-# already come from the issue forms.
+# .github/issue-labeler.yml. Additive only (addLabels never removes): it
+# never touches a label a maintainer set by hand. Base bug/enhancement
+# labels already come from the issue forms.
+#
+# Implemented with first-party actions/github-script (not a third-party
+# labeler action) so every pattern is compiled as a JavaScript RegExp with
+# the `i` flag applied centrally — inline `(?i)` groups are PCRE-only and
+# threw `SyntaxError: Invalid group` on every issue (#764). A pattern that
+# fails to compile now fails the run loudly instead of silently no-oping.
 
 on:
   issues:
@@ -16,13 +22,38 @@ jobs:
   triage:
     runs-on: ubuntu-latest
     permissions:
+      contents: read
       issues: write
     steps:
-      - uses: github/issue-labeler@c1b0f9f52a63158c4adc09425e858e87b32e9685 # v3.4
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+      - uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
-          configuration-path: .github/issue-labeler.yml
-          enable-versioned-regex: 0
-          include-title: 1
-          include-body: 1
-          sync-labels: 0
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            const text = [context.payload.issue.title, context.payload.issue.body]
+              .filter(Boolean).join('\n');
+            const rules = [];
+            const bad = [];
+            // Config format: one rule per line — "label": 'regex' (see the
+            // header comment in .github/issue-labeler.yml).
+            for (const line of fs.readFileSync('.github/issue-labeler.yml', 'utf8').split('\n')) {
+              const m = line.match(/^"([^"]+)":\s*'(.*)'\s*$/);
+              if (!m) continue;
+              try { rules.push({ label: m[1], re: new RegExp(m[2], 'i') }); }
+              catch (e) { bad.push(`${m[1]}: ${e.message}`); }
+            }
+            if (rules.length === 0 && bad.length === 0) {
+              core.setFailed('no labeling rules parsed from .github/issue-labeler.yml');
+              return;
+            }
+            const labels = rules.filter(r => r.re.test(text)).map(r => r.label);
+            if (labels.length) {
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.issue.number,
+                labels,
+              });
+            }
+            core.info(`matched: ${labels.join(', ') || '(none)'}`);
+            if (bad.length) core.setFailed(`invalid label regex(es): ${bad.join('; ')}`);

.github/workflows/pr.yml

@@ -51,7 +51,9 @@ jobs:
           PR: ${{ github.event.pull_request.number }}
           REPO: ${{ github.repository }}
         run: |
-          FILES=$(gh pr diff "$PR" --repo "$REPO" --name-only)
+          # The full .diff endpoint rejects large-but-valid PRs at 20k lines.
+          # The paginated files endpoint remains filename-only for this gate.
+          FILES=$(gh api --paginate "repos/$REPO/pulls/$PR/files?per_page=100" --jq '.[].filename')
           printf '%s\n' "$FILES"
           if printf '%s\n' "$FILES" | grep -qE '^(src/|internal/|scripts/build\.sh|scripts/smoke-test\.sh|scripts/env\.sh|Makefile\.cbm)'; then
             echo "product=true" >> "$GITHUB_OUTPUT"

Makefile.cbm

@@ -63,12 +63,15 @@ CXXFLAGS_PROD = $(CXXFLAGS_COMMON) -O2
 
 # Test flags: debug + sanitizers (override SANITIZE= to disable on Windows)
 SANITIZE = -fsanitize=address,undefined -fno-omit-frame-pointer
-CFLAGS_TEST = $(CFLAGS_COMMON) -g -O1 $(SANITIZE)
+EDITOR_TEST_DEFINES = -DCBM_JSON_LIKE_ENABLE_TEST_API=1 \
+	-DCBM_TOML_EDIT_ENABLE_TEST_API=1 -DCBM_YAML_ENABLE_TEST_API=1 \
+	-DCBM_TEXT_EDIT_ENABLE_TEST_API=1 -DCBM_CLI_ENABLE_TEST_API=1
+CFLAGS_TEST = $(CFLAGS_COMMON) $(EDITOR_TEST_DEFINES) -g -O1 $(SANITIZE)
 CXXFLAGS_TEST = $(CXXFLAGS_COMMON) -g -O1 $(SANITIZE)
 
 # TSan (can't combine with ASan)
 TSAN_SANITIZE = -fsanitize=thread -fno-omit-frame-pointer
-CFLAGS_TSAN = $(CFLAGS_COMMON) -g -O1 \
+CFLAGS_TSAN = $(CFLAGS_COMMON) $(EDITOR_TEST_DEFINES) -g -O1 \
               $(TSAN_SANITIZE)
 CXXFLAGS_TSAN = $(CXXFLAGS_COMMON) -g -O1 \
                 $(TSAN_SANITIZE)
@@ -132,6 +135,8 @@ EXTRACTION_SRCS = \
     $(CBM_DIR)/extract_k8s.c \
     $(CBM_DIR)/helpers.c \
     $(CBM_DIR)/lang_specs.c \
+    $(CBM_DIR)/macro_table.c \
+    $(CBM_DIR)/iris_export_xml.c \
     $(CBM_DIR)/service_patterns.c
 
 # LSP resolvers (compiled as one unit via lsp_all.c)
@@ -174,7 +179,7 @@ STORE_SRCS = src/store/store.c
 CYPHER_SRCS = src/cypher/cypher.c
 
 # MCP server module (new)
-MCP_SRCS = src/mcp/mcp.c src/mcp/index_supervisor.c
+MCP_SRCS = src/mcp/mcp.c src/mcp/index_supervisor.c src/mcp/compact_out.c
 
 # Discover module (new)
 DISCOVER_SRCS = \
@@ -237,7 +242,10 @@ WATCHER_SRCS = src/watcher/watcher.c
 GIT_SRCS = src/git/git_context.c
 
 # CLI module (new)
-CLI_SRCS = src/cli/cli.c src/cli/progress_sink.c src/cli/hook_augment.c
+CLI_SRCS = src/cli/cli.c src/cli/progress_sink.c src/cli/hook_augment.c \
+	src/cli/agent_clients.c src/cli/agent_profiles.c \
+	src/cli/config_json_like.c src/cli/config_toml_edit.c src/cli/config_yaml_edit.c \
+	src/cli/config_text_edit.c
 
 # UI module (graph visualization)
 UI_SRCS = \
@@ -369,6 +377,8 @@ TEST_CS_LSP_SRCS = tests/test_cs_lsp.c
 
 TEST_CS_LSP_BENCH_SRCS = tests/test_cs_lsp_bench.c
 
+TEST_PERL_LSP_SRCS = tests/test_perl_lsp.c
+
 TEST_SCOPE_SRCS = tests/test_scope.c
 
 TEST_TYPE_REP_SRCS = tests/test_type_rep.c
@@ -391,7 +401,9 @@ TEST_INTEGRATION_SRCS = tests/test_integration.c tests/test_incremental.c tests/
 TEST_TRACES_SRCS = tests/test_traces.c
 
 
-TEST_CLI_SRCS = tests/test_cli.c
+TEST_CLI_SRCS = tests/test_cli.c tests/test_agent_clients.c tests/test_agent_profiles.c \
+	tests/test_config_json_like.c \
+	tests/test_config_toml_edit.c tests/test_config_yaml_edit.c tests/test_config_text_edit.c
 
 TEST_MEM_SRCS = tests/test_mem.c
 
@@ -448,6 +460,7 @@ TEST_REPRO_SRCS = \
     tests/repro/repro_issue581.c \
     tests/repro/repro_issue787.c \
     tests/repro/repro_issue842.c \
+    tests/repro/repro_issue964.c \
     tests/repro/repro_invariant_calls.c \
     tests/repro/repro_invariant_graph.c \
     tests/repro/repro_invariant_breadth.c \
@@ -472,7 +485,7 @@ TEST_REPRO_SRCS = \
     tests/repro/repro_lsp_java_cs.c \
     tests/repro/repro_lsp_kt_php_rust.c
 
-ALL_TEST_SRCS =$(TEST_FOUNDATION_SRCS) $(TEST_EXTRACTION_SRCS) $(TEST_STORE_SRCS) $(TEST_CYPHER_SRCS) $(TEST_MCP_SRCS) $(TEST_DISCOVER_SRCS) $(TEST_GRAPH_BUFFER_SRCS) $(TEST_PIPELINE_SRCS) $(TEST_WATCHER_SRCS) $(TEST_LZ4_SRCS) $(TEST_ZSTD_SRCS) $(TEST_ARTIFACT_SRCS) $(TEST_SQLITE_WRITER_SRCS) $(TEST_GO_LSP_SRCS) $(TEST_C_LSP_SRCS) $(TEST_PHP_LSP_SRCS) $(TEST_CS_LSP_SRCS) $(TEST_CS_LSP_BENCH_SRCS) $(TEST_SCOPE_SRCS) $(TEST_TYPE_REP_SRCS) $(TEST_PY_LSP_SRCS) $(TEST_PY_LSP_BENCH_SRCS) $(TEST_PY_LSP_STRESS_SRCS) $(TEST_PY_LSP_SCALE_SRCS) $(TEST_TS_LSP_SRCS) $(TEST_JAVA_LSP_SRCS) $(TEST_KOTLIN_LSP_SRCS) $(TEST_RUST_LSP_SRCS) $(TEST_TRACES_SRCS) $(TEST_CLI_SRCS) $(TEST_MEM_SRCS) $(TEST_UI_SRCS) $(TEST_HTTPD_SRCS) $(TEST_SECURITY_SRCS) $(TEST_YAML_SRCS) $(TEST_SEMANTIC_SRCS) $(TEST_AST_PROFILE_SRCS) $(TEST_SLAB_ALLOC_SRCS) $(TEST_SIMHASH_SRCS) $(TEST_STACK_OVERFLOW_SRCS) $(TEST_INTEGRATION_SRCS)
+ALL_TEST_SRCS =$(TEST_FOUNDATION_SRCS) $(TEST_EXTRACTION_SRCS) $(TEST_STORE_SRCS) $(TEST_CYPHER_SRCS) $(TEST_MCP_SRCS) $(TEST_DISCOVER_SRCS) $(TEST_GRAPH_BUFFER_SRCS) $(TEST_PIPELINE_SRCS) $(TEST_WATCHER_SRCS) $(TEST_LZ4_SRCS) $(TEST_ZSTD_SRCS) $(TEST_ARTIFACT_SRCS) $(TEST_SQLITE_WRITER_SRCS) $(TEST_GO_LSP_SRCS) $(TEST_C_LSP_SRCS) $(TEST_PHP_LSP_SRCS) $(TEST_CS_LSP_SRCS) $(TEST_CS_LSP_BENCH_SRCS) $(TEST_PERL_LSP_SRCS) $(TEST_SCOPE_SRCS) $(TEST_TYPE_REP_SRCS) $(TEST_PY_LSP_SRCS) $(TEST_PY_LSP_BENCH_SRCS) $(TEST_PY_LSP_STRESS_SRCS) $(TEST_PY_LSP_SCALE_SRCS) $(TEST_TS_LSP_SRCS) $(TEST_JAVA_LSP_SRCS) $(TEST_KOTLIN_LSP_SRCS) $(TEST_RUST_LSP_SRCS) $(TEST_TRACES_SRCS) $(TEST_CLI_SRCS) $(TEST_MEM_SRCS) $(TEST_UI_SRCS) $(TEST_HTTPD_SRCS) $(TEST_SECURITY_SRCS) $(TEST_YAML_SRCS) $(TEST_SEMANTIC_SRCS) $(TEST_AST_PROFILE_SRCS) $(TEST_SLAB_ALLOC_SRCS) $(TEST_SIMHASH_SRCS) $(TEST_STACK_OVERFLOW_SRCS) $(TEST_INTEGRATION_SRCS)
 
 
 # ── Build directories ────────────────────────────────────────────
@@ -626,6 +639,14 @@ $(BUILD_DIR)/test-runner: $(ALL_TEST_SRCS) $(PROD_SRCS) $(EXTRACTION_SRCS) $(AC_
 test: $(BUILD_DIR)/test-runner
 	cd $(CURDIR) && $(BUILD_DIR)/test-runner
 
+# Focused native development is intentionally a separate, explicit target so
+# an inherited TEST_SUITES value cannot silently narrow the gating test target.
+TEST_SUITES ?=
+test-focused: $(BUILD_DIR)/test-runner
+	@test -n "$(strip $(TEST_SUITES))" || \
+		(echo "TEST_SUITES is required for test-focused"; exit 2)
+	cd $(CURDIR) && $(BUILD_DIR)/test-runner $(TEST_SUITES)
+
 # ── Cumulative bug-reproduction runner (RED by design, non-gating) ──
 # Mirrors test-runner's link line but uses repro_main.c (own main + counters)
 # and TEST_REPRO_SRCS instead of ALL_TEST_SRCS. Exits non-zero while any bug is