Merge branch 'main' into fix/quarantine-exit-nonzero

Author: shashwatMishra96

Makefile.cbm

@@ -356,6 +356,7 @@ PIPELINE_SRCS = \
     src/pipeline/pass_complexity.c \
     src/pipeline/pass_cross_repo.c \
     src/pipeline/artifact.c \
+    src/pipeline/pass_ensemble_routing.c \
     src/pipeline/pass_pkgmap.c
 
 # SimHash / MinHash module

README.md

@@ -16,7 +16,7 @@
 
 **The fastest and most efficient code intelligence engine for AI coding agents.** Full-indexes an average repository in milliseconds, the Linux kernel (28M LOC, 75K files) in 3 minutes. Answers structural queries in under 1ms. Ships as a native executable with a small verified runtime-asset set for macOS, Linux, and Windows — download, run `install`, done.
 
-High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across all 158 languages, enhanced with [**Hybrid LSP** semantic type resolution](#hybrid-lsp) for Python, TypeScript / JavaScript / JSX / TSX, PHP, C#, Go, C, C++, Java, Kotlin, Rust, and Perl — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 15 MCP tools. No language runtime, hosted service, or API key. Plug and play across 43 supported automatic/conditional client surfaces.
+High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across all 158 languages, enhanced with [**Hybrid LSP** semantic type resolution](#hybrid-lsp) for Python, TypeScript / JavaScript / JSX / TSX, PHP, C#, Go, C, C++, Java, Kotlin, Rust, and Perl — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 15 MCP tools. No language runtime, hosted service, or API key. Plug and play across 44 supported automatic/conditional client surfaces.
 
 > **Research** — The design and benchmarks behind this project are described in the preprint [*Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP*](https://arxiv.org/abs/2603.27277) (arXiv:2603.27277). Evaluated across 31 real-world repositories: 83% answer quality, 10× fewer tokens, 2.1× fewer tool calls vs. file-by-file exploration.
 
@@ -34,7 +34,7 @@ High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-si
 - **Plug and play** — native executable plus authenticated release-owned assets for macOS (arm64/amd64), Linux (arm64/amd64), and Windows (amd64). The native install needs no Docker, language runtime, or API keys. Download → `install` → restart agent → done.
 - **158 languages** — vendored tree-sitter grammars compiled into the binary. Nothing to install, nothing that breaks.
 - **120x fewer tokens** — 5 structural queries: ~3,400 tokens vs ~412,000 via file-by-file search. One graph query replaces dozens of grep/read cycles.
-- **43 supported automatic/conditional client surfaces** — `install` configures detected clients and safely activates conditional clients only when their documented platform, marker, or explicit existing config path is present. See [Multi-Agent Support](#multi-agent-support) for the complete matrix and manual/UI-only boundaries.
+- **44 supported automatic/conditional client surfaces** — `install` configures detected clients and safely activates conditional clients only when their documented platform, marker, or explicit existing config path is present. See [Multi-Agent Support](#multi-agent-support) for the complete matrix and manual/UI-only boundaries.
 - **Built-in graph visualization** — 3D interactive UI at `localhost:9749`, served from the binary itself.
 - **Infrastructure-as-code indexing** — Dockerfiles, Kubernetes manifests, and Kustomize overlays indexed as graph nodes with cross-references. `Resource` nodes for K8s kinds, `Module` nodes for Kustomize overlays with `IMPORTS` edges to referenced resources.
 - **15 MCP tools** — search, trace, architecture, impact analysis, targeted index-coverage checks, Cypher queries, dead code detection, cross-service HTTP linking, ADR management, and more.
@@ -425,7 +425,7 @@ Restart your agent. Verify with `/mcp` — you should see `codebase-memory-mcp`
 
 ## Multi-Agent Support
 
-`install` configures 43 client surfaces: 37 detected automatically and 6
+`install` configures 44 client surfaces: 38 detected automatically and 6
 conditional or explicit. “Conditional” means the installer writes only when the
 documented platform or an explicit, already-existing config path proves the
 target is active. It never flips experimental feature flags, enables plugins,
@@ -473,6 +473,7 @@ overwrite user-modified agents.
 | Crush | Detected | `.config/crush/crush.json` | Managed context path with explicit parent-to-child handoff |
 | Goose | Detected | `.config/goose/config.yaml` | `.goosehints` |
 | Mistral Vibe | Detected | `$VIBE_HOME/config.toml` | `AGENTS.md`, skill, and three matched agent/prompt pairs with explicit read-only graph-tool allowlists |
+| Grok Build | Detected | `$GROK_HOME/config.toml` | Owned `rules/codebase-memory.md`, skill, three graph agents with named-server `mcpInheritance` and exact `server__tool` dispatcher ids; context hooks withheld because its passive hook events discard stdout |
 | Qoder CLI | Detected | `~/.qoder/settings.json` | Skill, three directly MCP-attached agents with named-server scoping and exact per-tier graph-tool lists; `SessionStart`, `SubagentStart`, and post-`Read` coverage, including documented PowerShell execution on Windows |
 | Kimi Code CLI | Detected | `$KIMI_CODE_HOME/mcp.json` (default `~/.kimi-code`) | Same-root `AGENTS.md` + skill; fail-open `UserPromptSubmit` hook in `config.toml` |
 | GitLab Duo CLI | Detected | `$GLAB_CONFIG_DIR/duo/mcp.json` or platform fallback | Fail-open user `SessionStart` on macOS/Linux; hook withheld on Windows; no experimental global skill enablement |
@@ -521,7 +522,7 @@ carry the contract across fresh sessions and compaction: verify the graph projec
 and index freshness, query structural facts in the parent, then pass the project,
 qualified symbols, paths, and call-chain evidence in every delegated task.
 Claude, Codex, Gemini, Kiro, Qwen, Copilot, CodeBuddy, OpenCode, Kilo, Vibe,
-Qoder, Junie, and Factory receive Scout, Verify, and Auditor graph profiles.
+Qoder, Junie, Factory, and Grok Build receive Scout, Verify, and Auditor graph profiles.
 Kiro embeds this MCP server with `--tool-profile scout` for Scout and
 `--tool-profile analysis` for Verify/Auditor. Junie registers equivalent named
 server aliases because its subagent schema filters by server rather than by
@@ -547,7 +548,12 @@ project or plugin agents before user agents with the same name; reload the
 client after installation or profile changes.
 Cursor context
 hooks are withheld: session context injection has a known race, `subagentStart`
-is control-only, and read-only subagents cannot safely receive MCP access. Rovo
+is control-only, and read-only subagents cannot safely receive MCP access. Grok Build's
+passive hook events (`SessionStart`, `SubagentStart`, `PostToolUse`) discard
+stdout and `PreToolUse` honors only deny/rewrite decisions, so its context hooks
+are withheld; Grok also reads Claude and Cursor MCP, skill, and hook files
+through its compat layer, and the native `config.toml` entry shadows that copy
+by name. Rovo
 has no documented session context-output hook, and Bob
 documents neither a suitable hook nor a custom-agent surface. Those surfaces are
 not approximated with invented augmentation. Kimi plugins, Amp plugins, and
@@ -778,7 +784,7 @@ src/
   main.c              Entry point (MCP stdio server + CLI + install/update/config)
   daemon/             Per-account session coordination, IPC, lifecycle, shared jobs/watchers
   mcp/                MCP server (15 tools, JSON-RPC 2.0, session detection, auto-index)
-  cli/                Install/uninstall/update/config (43 client surfaces, hooks, instructions)
+  cli/                Install/uninstall/update/config (44 client surfaces, hooks, instructions)
   store/              SQLite graph storage (nodes, edges, traversal, search, Louvain)
   pipeline/           Multi-pass indexing (structure → definitions → calls → HTTP links → config → tests)
   cypher/             Cypher query lexer, parser, planner, executor

THIRD_PARTY.md

@@ -64,6 +64,21 @@ License summary:
   base, MIT, (c) 2014 Max Brunsfeld) with (c) 2026 DeusData ArkTS additions;
   its grammar source lives in `tools/tree-sitter-arkts/`.
 
+### tree-sitter-plsql
+
+- **Project:** [AndreasMaierDe/tree-sitter-plsql](https://github.com/AndreasMaierDe/tree-sitter-plsql)
+- **License:** MIT
+- **Copyright:** (c) 2022 AndreasMaierDe
+- **Vendored at:** `internal/cbm/vendored/grammars/plsql/`
+- **Pinned commit:** `28aebef209be`
+- **Notes:** Community-maintained grammar for Oracle PL/SQL; not in the
+  nvim-treesitter or Helix registries (`community-niche` in the manifest). No
+  external scanner. One local patch: `parser.c`'s
+  `#include <tree_sitter/parser.h>` is changed to the quoted form used by every
+  other vendored grammar, as documented in
+  `internal/cbm/vendored/grammars/MANIFEST.md`. PL/SQL support was originally
+  contributed in PR #1033 by Oğuz (@ouzsrcm).
+
 ### tree-sitter-objectscript (UDL + routine)
 
 - **Project:** [intersystems/tree-sitter-objectscript](https://github.com/intersystems/tree-sitter-objectscript)

docs/index.html

@@ -4,7 +4,7 @@
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <title>codebase-memory-mcp — Code Intelligence Knowledge Graph for AI Coding Agents</title>
-    <meta name="description" content="codebase-memory-mcp is an open-source MCP server that indexes any codebase into a persistent knowledge graph so AI coding agents answer structural questions with ~120x fewer tokens. 158 languages, Hybrid LSP type resolution, local semantic vector search, code-clone detection, sub-1ms queries, Linux kernel indexed in 3 minutes. Native executable with verified assets and no language runtime. One command configures 43 automatic/conditional client surfaces.">
+    <meta name="description" content="codebase-memory-mcp is an open-source MCP server that indexes any codebase into a persistent knowledge graph so AI coding agents answer structural questions with ~120x fewer tokens. 158 languages, Hybrid LSP type resolution, local semantic vector search, code-clone detection, sub-1ms queries, Linux kernel indexed in 3 minutes. Native executable with verified assets and no language runtime. One command configures 44 automatic/conditional client surfaces.">
     <meta name="keywords" content="MCP server, code intelligence, knowledge graph, tree-sitter, Hybrid LSP, semantic code search, code embeddings, code clone detection, cross-repo analysis, data-flow analysis, Claude Code, Codex CLI, Gemini CLI, Cursor, Zed, code exploration, token reduction, call graph, dead code detection">
     <meta name="author" content="DeusData">
     <meta name="robots" content="index, follow, max-image-preview:large, max-snippet:-1">
@@ -68,7 +68,7 @@
         "Infrastructure-as-code indexing for Dockerfiles, Kubernetes, and Kustomize",
         "Built-in 3D graph visualization UI",
         "Auto-sync background watcher for incremental re-indexing",
-        "One command configures 43 automatic/conditional client surfaces"
+        "One command configures 44 automatic/conditional client surfaces"
       ],
       "author": {
         "@type": "Organization",
@@ -157,7 +157,7 @@
           "name": "Which AI coding agents work with codebase-memory-mcp?",
           "acceptedAnswer": {
             "@type": "Answer",
-            "text": "A single install command configures 43 automatic/conditional client surfaces. The 37 detected surfaces are Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, and Pi. Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE, and Sourcegraph Cody are conditional or explicit integrations. Qodo, Warp MCP, JetBrains AI/ACP, GitHub Copilot coding agent, Jules, CodeRabbit, Replit, BLACKBOX AI, Plandex, and SWE-agent require manual, UI, cloud, or repository-managed setup and are not counted among the 43."
+            "text": "A single install command configures 44 automatic/conditional client surfaces. The 38 detected surfaces are Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Grok Build, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, and Pi. Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE, and Sourcegraph Cody are conditional or explicit integrations. Qodo, Warp MCP, JetBrains AI/ACP, GitHub Copilot coding agent, Jules, CodeRabbit, Replit, BLACKBOX AI, Plandex, and SWE-agent require manual, UI, cloud, or repository-managed setup and are not counted among the 43."
           }
         },
         {
@@ -527,10 +527,10 @@ <h2>How do I install codebase-memory-mcp?</h2>
             <span class="cmd">"Index this project"</span>
         </div>
         <p class="muted">
-            One command configures 43 automatic/conditional client surfaces. <strong>Detected automatically (37):</strong>
+            One command configures 44 automatic/conditional client surfaces. <strong>Detected automatically (38):</strong>
             Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor,
             Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code,
-            GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI,
+            GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Grok Build, Qoder CLI, Kimi Code CLI,
             GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE,
             CodeBuddy Code CLI, IBM Bob Shell, Pochi, and Pi.
         </p>

docs/llms.txt

@@ -12,7 +12,7 @@
 - Semantic & similarity edges: SEMANTICALLY_RELATED (vocabulary-mismatch matches) and SIMILAR_TO (MinHash + LSH near-clone / duplicate detection).
 - Cross-repo intelligence: CROSS_* edges link nodes across multiple repos indexed in one store; multi-galaxy 3D layout and cross-repo architecture summary.
 - Cross-service linking: HTTP route ↔ call-site matching, plus gRPC/GraphQL/tRPC detection and pub/sub channels (EMITS/LISTENS_ON for Socket.IO, EventEmitter, generic buses).
-- Supported agents: 43 automatic/conditional client surfaces (37 automatically detected + 6 conditional/explicit): Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Continue / cn, Visual Studio, TRAE, Roo Code, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob IDE, IBM Bob Shell, Pochi, Pi, and Sourcegraph Cody.
+- Supported agents: 44 automatic/conditional client surfaces (38 automatically detected + 6 conditional/explicit): Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Grok Build, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Continue / cn, Visual Studio, TRAE, Roo Code, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob IDE, IBM Bob Shell, Pochi, Pi, and Sourcegraph Cody.
 - Agent profiles: documented custom-agent formats receive Scout (fast/provisional), Verify (default/task-directed), and Auditor (bounded/full verification) definitions. Every direct tier checks exact path/scope coverage with check_index_coverage and falls back to source for flagged gaps; unsafe child-MCP formats use explicit parent handoff. Kiro and Junie use positive-allowlist Scout/Analysis server profiles (7/11 tools); Qoder combines named-server selection with exact tier-specific MCP tool IDs, while Factory uses exact registered IDs without additive whole-server exposure. Foreign Junie aliases are preserved and force parent handoff.
 - Performance: Linux kernel (28M LOC, 75K files) full index in 3 minutes → 4.81M nodes, 7.72M edges; Cypher queries in under 1ms.
 - Distribution: verified runtime set (native executable plus authenticated release-owned assets); fully static Linux builds are available in the `-portable` archives. Also available through npm, PyPI, Homebrew, Scoop, Winget, Chocolatey, AUR, and `go install`.

internal/cbm/cbm.h

@@ -175,6 +175,7 @@ typedef enum {
     CBM_LANG_OBJECTSCRIPT_ROUTINE, // InterSystems ObjectScript routine (.mac/.int/.rtn/.inc)
     CBM_LANG_OBJECTSCRIPT_EXPORT,  // InterSystems Studio Export XML (<Export generator="Cache">)
     CBM_LANG_ARKTS, // ArkTS (HarmonyOS/OpenHarmony .ets — TypeScript superset + ArkUI)
+    CBM_LANG_PLSQL, // Oracle PL/SQL
     CBM_LANG_COUNT
 } CBMLanguage;
 

internal/cbm/extract_calls.c

@@ -826,6 +826,32 @@ static char *extract_ada_callee(CBMArena *a, TSNode node, const char *source, co
     return NULL;
 }
 
+/* PL/SQL: ref_call → referenced_element. Package-qualified calls use
+ * ref_name_parent.ref_name (e.g. UTIL_PKG.CALC_SALARY); bare calls use
+ * ref_name alone. */
+static char *extract_plsql_callee(CBMArena *a, TSNode node, const char *source, const char *nk) {
+    if (strcmp(nk, "ref_call") != 0) {
+        return NULL;
+    }
+    TSNode ref = cbm_find_child_by_kind(node, "referenced_element");
+    if (ts_node_is_null(ref)) {
+        return NULL;
+    }
+    TSNode parent = ts_node_child_by_field_name(ref, TS_FIELD("ref_name_parent"));
+    TSNode name = ts_node_child_by_field_name(ref, TS_FIELD("ref_name"));
+    if (!ts_node_is_null(parent) && !ts_node_is_null(name)) {
+        char *p = cbm_node_text(a, parent, source);
+        char *n = cbm_node_text(a, name, source);
+        if (p && n && p[0] && n[0]) {
+            return cbm_arena_sprintf(a, "%s.%s", p, n);
+        }
+    }
+    if (!ts_node_is_null(name)) {
+        return cbm_node_text(a, name, source);
+    }
+    return cbm_node_text(a, ref, source);
+}
+
 // Solidity: a call_expression's callee is on the `function` field, wrapped in an
 // `expression` node (call_expression -> function:expression -> identifier). Descend
 // left-most through expression wrappers until we reach the identifier/member.
@@ -1369,6 +1395,9 @@ static char *extract_callee_lang_specific(CBMArena *a, TSNode node, const char *
     if (lang == CBM_LANG_ADA) {
         return extract_ada_callee(a, node, source, nk);
     }
+    if (lang == CBM_LANG_PLSQL) {
+        return extract_plsql_callee(a, node, source, nk);
+    }
     if (lang == CBM_LANG_SOLIDITY) {
         return extract_solidity_callee(a, node, source, nk);
     }