@colbymchenry/codegraph 1.2.0 → 1.3.1

package/README.md

@@ -41,6 +41,29 @@ Follow [@getcodegraph](https://x.com/getcodegraph) on X for updates.
 
 </div>
 
+## Contents
+
+- [Get Started](#get-started)
+- [Language Support](#language-support)
+- [Why CodeGraph?](#why-codegraph)
+- [Key Features](#key-features)
+- [Framework-aware Routes](#framework-aware-routes)
+- [Mixed iOS / React Native / Expo bridging](#mixed-ios--react-native--expo-bridging)
+- [Quick Start](#quick-start)
+- [How It Works](#how-it-works)
+- [CLI Reference](#cli-reference)
+- [MCP Tools](#mcp-tools)
+- [Library Usage](#library-usage)
+- [Configuration](#configuration)
+- [Telemetry](#telemetry)
+- [Supported Platforms](#supported-platforms)
+- [Supported Agents](#supported-agents)
+- [Supported Languages](#supported-languages)
+- [Measured cross-file coverage](#measured-cross-file-coverage)
+- [Troubleshooting](#troubleshooting)
+- [Star History](#star-history)
+- [License](#license)
+
 ## Get Started
 
 ### 1. Install the CLI
@@ -109,6 +132,51 @@ codegraph uninstall
 
 ---
 
+## Language Support
+
+Every language below gets the same treatment — full structural extraction and cross-file resolution into one graph, no per-language setup:
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/typescript.svg?v=1" width="104" height="104" alt="TypeScript" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/javascript.svg?v=1" width="104" height="104" alt="JavaScript" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/arkts.svg?v=1" width="104" height="104" alt="ArkTS" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/python.svg?v=1" width="104" height="104" alt="Python" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/go.svg?v=1" width="104" height="104" alt="Go" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/rust.svg?v=1" width="104" height="104" alt="Rust" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/java.svg?v=1" width="104" height="104" alt="Java" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/csharp.svg?v=1" width="104" height="104" alt="C#" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/php.svg?v=1" width="104" height="104" alt="PHP" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/ruby.svg?v=1" width="104" height="104" alt="Ruby" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/c.svg?v=1" width="104" height="104" alt="C" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/cpp.svg?v=1" width="104" height="104" alt="C++" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/objective-c.svg?v=1" width="104" height="104" alt="Objective-C" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/metal.svg?v=1" width="104" height="104" alt="Metal" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/cuda.svg?v=1" width="104" height="104" alt="CUDA" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/swift.svg?v=1" width="104" height="104" alt="Swift" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/kotlin.svg?v=1" width="104" height="104" alt="Kotlin" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/scala.svg?v=1" width="104" height="104" alt="Scala" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/dart.svg?v=1" width="104" height="104" alt="Dart" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/svelte.svg?v=1" width="104" height="104" alt="Svelte" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/vue.svg?v=1" width="104" height="104" alt="Vue" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/astro.svg?v=1" width="104" height="104" alt="Astro" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/liquid.svg?v=1" width="104" height="104" alt="Liquid" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/delphi.svg?v=1" width="104" height="104" alt="Pascal / Delphi" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/lua.svg?v=1" width="104" height="104" alt="Lua" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/r.svg?v=1" width="104" height="104" alt="R" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/luau.svg?v=1" width="104" height="104" alt="Luau" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/cfml.svg?v=1" width="104" height="104" alt="CFML" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/cobol.svg?v=1" width="104" height="104" alt="COBOL" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/vbnet.svg?v=1" width="104" height="104" alt="Visual Basic .NET" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/erlang.svg?v=1" width="104" height="104" alt="Erlang" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/solidity.svg?v=1" width="104" height="104" alt="Solidity" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/terraform.svg?v=1" width="104" height="104" alt="Terraform / OpenTofu" />
+  <img src="https://raw.githubusercontent.com/colbymchenry/codegraph/main/assets/languages/nix.svg?v=1" width="104" height="104" alt="Nix" />
+</p>
+
+<sub>Per-language details — extensions, frameworks, and what exactly gets extracted — in [Supported Languages](#supported-languages).</sub>
+
+---
+
 ## Why CodeGraph?
 
 When an AI agent needs to understand code — to answer a question or make a change — it discovers structure the slow way: grep, glob, and Read, one file at a time, rebuilding call paths and dependencies by hand. That's a pile of tool calls and round-trips before it even starts the real work.
@@ -244,7 +312,7 @@ The reliable, universal payoff is **surgical context and speed**: CodeGraph coll
 | **Full-Text Search** | Find code by name instantly across your entire codebase, powered by FTS5 |
 | **Impact Analysis** | Trace callers, callees, and the full impact radius of any symbol before making changes |
 | **Always Fresh** | File watcher uses native OS events (FSEvents/inotify/ReadDirectoryChangesW) with debounced auto-sync — the graph stays current as you code, zero config |
-| **20+ Languages** | TypeScript, JavaScript, Python, Go, Rust, Java, C#, PHP, Ruby, C, C++, Objective-C, Swift, Kotlin, Scala, Dart, Lua, Luau, R, Svelte, Vue, Astro, Liquid, Pascal/Delphi |
+| **20+ Languages** | TypeScript, JavaScript, ArkTS, Python, Go, Rust, Java, C#, VB.NET, PHP, Ruby, C, C++, CUDA, Objective-C, Metal, Swift, Kotlin, Scala, Dart, Lua, Luau, R, Nix, Erlang, CFML, COBOL, Solidity, Terraform/OpenTofu, Svelte, Vue, Astro, Liquid, Pascal/Delphi |
 | **Framework-aware Routes** | Recognizes web-framework routing files and links URL patterns to their handlers across 17 frameworks |
 | **Mixed iOS / React Native / Expo** | Closes cross-language flows that static parsing misses: Swift ↔ ObjC bridging, React Native legacy bridge + TurboModules + Fabric view components, native → JS event emitters, Expo Modules |
 | **100% Local** | No data leaves your machine. No API keys. No external services. SQLite database only |
@@ -618,6 +686,21 @@ watch:
 }
 ```
 
+Conversely, when real source is gitignored on purpose — a project under a second
+VCS (SVN, Perforce) that `.gitignore`s its own source so it stays out of Git —
+force it back in with `include` (the opposite of `exclude`; `includeIgnored`
+only revives embedded git repos, not plain source):
+
+```json
+{
+  "include": ["Tools/", "Local/typescript/"]
+}
+```
+
+CodeGraph discovers those files off disk, overriding `.gitignore`, on index,
+sync, and watch. An explicit `exclude` still wins, and built-in skips
+(`node_modules`, `dist`, `.git`) are never re-included.
+
 ### Custom file extensions
 
 If your project uses a non-standard extension for a [supported
@@ -692,6 +775,7 @@ is written):
 |----------|-----------|--------|
 | TypeScript | `.ts`, `.tsx` | Full support |
 | JavaScript | `.js`, `.jsx`, `.mjs` | Full support |
+| ArkTS (HarmonyOS) | `.ets` | Full support (everything TypeScript has, plus `@Component`/`@ComponentV2` structs with their ArkUI decorators (`@State`/`@Prop`/`@Link`/`@Local`/`@Builder`/…), `build()` view trees — parent→child component edges, chained-attribute links to `@Extend`/`@Styles` functions, `.onClick(this.handler)` event bindings — dynamic-dispatch bridges for state→`build()` re-renders, `@ohos.events.emitter` emit→subscriber pairs (static event keys only), and `router.pushUrl` literal urls → the target page struct; ohpm workspace modules resolve bare `import { X } from "data"` through `oh-package.json5` `file:` dependencies, honoring each module's `main` entry) |
 | Python | `.py` | Full support |
 | Go | `.go` | Full support |
 | Rust | `.rs` | Full support |
@@ -702,6 +786,8 @@ is written):
 | C | `.c`, `.h` | Full support |
 | C++ | `.cpp`, `.hpp`, `.cc` | Full support |
 | Objective-C | `.m`, `.mm`, `.h` | Partial support (classes, protocols, methods, `@property`, `#import`, message sends; `.mm` ObjC++ may parse incompletely) |
+| Metal | `.metal` | Full support (vertex/fragment/kernel functions, structs, type aliases, call edges — MSL parses as C++, with `[[attribute]]` annotations handled) |
+| CUDA | `.cu`, `.cuh` | Full support (kernels and device/host functions, structs, classes, host→kernel call edges through `<<<grid, block>>>` launch syntax — templated launches, function-pointer launches (`auto kernel = &fn<...>`), `dim3{...}` configs, and macro-defined kernels included; `__global__`/`__device__`/`__launch_bounds__` specifiers handled; CUDA in plain `.h`/`.hpp` headers recognized by content) |
 | Swift | `.swift` | Full support |
 | Kotlin | `.kt`, `.kts` | Full support |
 | Scala | `.scala`, `.sc` | Full support (classes, traits, methods, type aliases, Scala 3 enums) |
@@ -714,6 +800,13 @@ is written):
 | Lua | `.lua` | Full support (functions, methods with receivers, local variables, `require` imports, call edges) |
 | R | `.R` `.r` | Full support (functions in every assignment form, S4/R5/R6 classes with methods, `library`/`require` imports, `source()` file references, call edges) |
 | Luau | `.luau` | Full support (everything in Lua, plus `type`/`export type` aliases, typed signatures, and Roblox instance-path `require`) |
+| CFML | `.cfc`, `.cfm`, `.cfs` | Full support (tag-based `<cfcomponent>`/`<cffunction>` and bare-script `component { ... }` styles, `extends`/`implements`, embedded `<cfscript>` delegation, call edges) |
+| COBOL | `.cbl`, `.cob`, `.cpy` | Full support (programs, sections/paragraphs with PERFORM/GO TO call edges, CALL 'literal' cross-program calls, COPY copybook imports — including standalone `.cpy` files — DATA DIVISION records/fields/88-levels, EXEC CICS LINK/XCTL and EXEC SQL INCLUDE targets; fixed and free format) |
+| Visual Basic .NET | `.vb` | Full support (classes, Modules, interfaces, structures, enums, properties, events, `Declare` P/Invoke, `Handles`/`WithEvents`, `Inherits`/`Implements` edges, call edges through VB's call/index paren ambiguity, `As New` instantiation, interpolated strings, LINQ, Unicode identifiers) |
+| Erlang | `.erl`, `.hrl`, `.escript`, `.app.src`, `.app` | Full support (functions with multi-clause/multi-arity grouping, `-spec` signatures, records with fields, `-type`/`-opaque` aliases, `-define` macros, `-include`/`-include_lib`/`-import` edges, local and `mod:fn` remote call edges, `fun name/arity` references, `spawn`/`apply`/`proc_lib`/`timer`/`rpc` MFA-argument call edges, `gen_server:call/cast(?MODULE)` → own `handle_call`/`handle_cast` links, `-behaviour` links, `-export`-based visibility) |
+| Solidity | `.sol` | Full support (contracts, libraries, interfaces, structs, enums, modifiers, events, errors, state variables, `import`/`using` directives, `emit`/`revert` calls) |
+| Terraform / OpenTofu | `.tf`, `.tfvars`, `.tofu` | Full support (resources, data sources, modules, variables, outputs, providers incl. aliases, `locals`; `var.`/`local.`/`module.`/resource references with Terraform's per-directory scoping enforced; module calls bridged across the boundary — inputs to the child module's variables, `module.M.out` to the child's output, `source` to the module's files; cloudposse/atmos `remote-state` cross-component wiring when the component is statically named; `provider = aws.east` selections resolved up the module tree; `moved`/`import`/`removed`/`check` block references; `.tfvars` assignments linked to the variables they set) |
+| Nix | `.nix` | Full support (functions with simple/destructured/curried params, `let`/attrset bindings, `inherit`, `import ./path` file edges — `./dir` resolving through `default.nix` — plus NixOS module `imports = [ ./x.nix ]` lists and `callPackage ./pkg.nix` file edges; call edges; module-system option wiring — a config write like `launchd.user.agents.x = { ... }` links to the module declaring `options.launchd.user.agents`, so option flows trace across modules) |
 
 ## Measured cross-file coverage
 

package/dist/bin/codegraph.d.ts

@@ -22,5 +22,5 @@
  *   codegraph affected [files]   Find test files affected by changes
  *   codegraph upgrade [version]  Update CodeGraph to the latest release
  */
-export {};
+import '../mcp/early-ppid';
 //# sourceMappingURL=codegraph.d.ts.map

package/dist/db/index.d.ts

@@ -73,8 +73,8 @@ export declare class DatabaseConnection {
      */
     optimize(): void;
     /**
-     * Lightweight, non-blocking maintenance to run after bulk writes
-     * (indexAll, sync). Two operations:
+     * Lightweight maintenance to run after bulk writes (indexAll, sync).
+     * Two operations:
      *
      *   - `PRAGMA optimize` — incremental ANALYZE; SQLite only re-analyzes
      *     tables whose row counts changed materially since the last
@@ -86,10 +86,22 @@ export declare class DatabaseConnection {
      *     unboundedly between automatic checkpoints (auto-fires at 1000
      *     pages by default; large indexAll runs blow past that).
      *
-     * Both operations are silently swallowed on failure — they're a
-     * best-effort optimization, never load-bearing for correctness.
+     * Runs on a WORKER THREAD with its own connection: on a multi-GB index
+     * these pragmas are minutes of synchronous IO (a 95k-file kernel index
+     * left a 593MB WAL whose checkpoint alone blew the #850 watchdog's 60s
+     * window and got a COMPLETED index SIGKILLed at the finish line). WAL
+     * checkpointing from a second connection is standard SQLite; `PRAGMA
+     * optimize` persists its statistics in sqlite_stat tables, so the main
+     * connection benefits the same. The main thread just awaits a message,
+     * so the event loop — and the watchdog heartbeat — keep turning.
+     *
+     * Everything is silently swallowed on failure — best-effort
+     * optimization, never load-bearing for correctness. If worker threads
+     * are unavailable, falls back to a bounded in-line `PRAGMA optimize`
+     * and SKIPS the checkpoint (the final close() checkpoints after the
+     * CLI has already disarmed its watchdog).
      */
-    runMaintenance(): void;
+    runMaintenance(): Promise<void>;
     /**
      * Close the database connection
      */

package/dist/db/migrations.d.ts

@@ -7,7 +7,7 @@ import { SqliteDatabase } from './sqlite-adapter';
 /**
  * Current schema version
  */
-export declare const CURRENT_SCHEMA_VERSION = 6;
+export declare const CURRENT_SCHEMA_VERSION = 7;
 /**
  * Migration definition
  */

package/dist/db/queries.d.ts

@@ -4,7 +4,7 @@
  * Prepared statements for CRUD operations on the knowledge graph.
  */
 import { SqliteDatabase } from './sqlite-adapter';
-import { Node, Edge, FileRecord, UnresolvedReference, NodeKind, EdgeKind, GraphStats, SearchOptions, SearchResult } from '../types';
+import { Node, Edge, FileRecord, UnresolvedReference, NodeKind, EdgeKind, Language, GraphStats, SearchOptions, SearchResult } from '../types';
 /**
  * Query builder for the knowledge graph database
  */
@@ -14,6 +14,8 @@ export declare class QueryBuilder {
     private nodeCache;
     private readonly maxCacheSize;
     private stmts;
+    private segmentedNames;
+    private static readonly MAX_SEGMENTED_NAMES;
     constructor(db: SqliteDatabase);
     /** Set the normalized project-name tokens used to down-weight non-discriminative
      * query words in path scoring (#720). Called once when the project opens. */
@@ -24,6 +26,12 @@ export declare class QueryBuilder {
      * Insert a new node
      */
     insertNode(node: Node): void;
+    /** Which node kinds contribute their name to the segment vocabulary — the
+     *  single gate shared by insertNode, updateNode, and the rebuild page query
+     *  (getDistinctNodeNames), so the write paths can't drift apart. */
+    private isSegmentableKind;
+    /** Write `name`'s segments into name_segment_vocab (idempotent). */
+    private insertNameSegments;
     /**
      * Insert multiple nodes in a transaction
      */
@@ -40,6 +48,44 @@ export declare class QueryBuilder {
      * Delete all nodes for a file
      */
     deleteNodesByFile(filePath: string): void;
+    /** Wipe the segment vocabulary. A full index calls this at its start; the
+     *  node write path repopulates it as files (re-)index, so the end state is
+     *  exactly the current names with no orphan rows. */
+    clearNameSegmentVocab(): void;
+    /** True when the vocab has no rows — an index built before the table existed.
+     *  `sync` uses this to heal such databases (see rebuildNameSegmentVocabFrom). */
+    isNameSegmentVocabEmpty(): boolean;
+    /** One page of distinct segmentable node names, for batched vocab rebuilds
+     *  (file basenames and import specifiers are excluded from the vocab — see
+     *  insertNode). */
+    getDistinctNodeNames(limit: number, offset: number): string[];
+    /** Insert segments for a batch of names in one transaction (vocab heal path). */
+    insertNameSegmentsBatch(names: string[]): void;
+    /**
+     * Names whose segments cover at least `minWords` distinct PROMPT WORDS —
+     * the co-occurrence probe behind the prompt hook's medium tier: the words
+     * "state" and "machine" both being segments of `OrderStateMachine` is strong
+     * evidence the prompt names that symbol in prose. Ordered by coverage.
+     *
+     * Takes (segment variant → original word) pairs and folds variants back to
+     * their word INSIDE the SQL: a name matching both `service` and `services`
+     * counts ONE word, not two. Counting raw variants let plural-variant pairs
+     * of a single word tie with genuine two-word matches and — because ORDER
+     * BY/LIMIT run here, before any JS-side re-check — crowd a real match past
+     * the LIMIT on vocab-heavy repos (#1146).
+     */
+    getSegmentCoOccurrence(variants: Array<{
+        segment: string;
+        word: string;
+    }>, minWords: number, limit: number): Array<{
+        name: string;
+        matches: number;
+    }>;
+    /** How many distinct names each segment appears in — the rarity signal that
+     *  separates a discriminative word ("checkout") from a ubiquitous one ("state"). */
+    getSegmentNameCounts(segments: string[]): Map<string, number>;
+    /** Names containing the given segment (rare-single-word tier). */
+    getNamesForSegment(segment: string, limit: number): string[];
     /**
      * Get a node by ID
      */
@@ -152,10 +198,32 @@ export declare class QueryBuilder {
      * Get all nodes in the database
      */
     getAllNodes(): Node[];
+    /**
+     * Stream nodes of one language whose `decorators` JSON array contains
+     * `decorator`. The LIKE on the JSON text is a cheap index-free pre-filter
+     * (a decorator name can appear as a substring of another), so callers must
+     * still exact-check `node.decorators.includes(decorator)`. Exists so the
+     * kotlin expect/actual synthesizer never materializes the whole node table
+     * the way `getAllNodes().filter(...)` did — that array alone OOM'd Node's
+     * default heap on a 2M-node graph (#1212).
+     */
+    iterateNodesByLanguageWithDecorator(language: Language, decorator: string): IterableIterator<Node>;
+    /**
+     * Distinct languages present in the files table. One indexed aggregate —
+     * lets the dynamic-edge synthesizers skip passes for languages the project
+     * doesn't contain at all (a Kotlin pass has no work on a pure-C repo), so
+     * their cost is zero rather than a full-graph scan that finds nothing (#1212).
+     */
+    getDistinctFileLanguages(): Set<string>;
     /**
      * Get nodes by exact name match (uses idx_nodes_name index)
      */
     getNodesByName(name: string): Node[];
+    /**
+     * Nodes whose name starts with `prefix`, by index range scan (a LIKE would
+     * skip idx_nodes_name under SQLite's default case-insensitive LIKE).
+     */
+    getNodesByNamePrefix(prefix: string, limit?: number): Node[];
     /**
      * Get nodes by exact qualified name match (uses idx_nodes_qualified_name index)
      */
@@ -344,6 +412,13 @@ export declare class QueryBuilder {
      * Get all distinct node names (lightweight — just name strings for pre-filtering)
      */
     getAllNodeNames(): string[];
+    /**
+     * Stream the distinct node names one row at a time — the incremental
+     * counterpart to {@link getAllNodeNames} for callers that need to yield
+     * to the event loop mid-scan (resolver cache warm-up on multi-million-node
+     * indexes). Fresh statement per call: the iterator holds an open cursor.
+     */
+    iterateNodeNames(): IterableIterator<string>;
     /**
      * Get unresolved references scoped to specific file paths.
      * Uses the idx_unresolved_file_path index for efficient lookup.

package/dist/directory.d.ts

@@ -86,10 +86,14 @@ export declare function findIndexedSubprojectRoots(root: string, opts?: {
     max?: number;
 }): string[];
 /**
- * Does `prompt` contain an explicit structural keyword (English or CJK)? A
- * keyword is a strong, self-contained signal, so the front-load hook fires on it
- * directly — no graph check needed. (A *code-token* match, by contrast, is only
- * a candidate the hook verifies against the graph first; see {@link extractCodeTokens}.)
+ * Does `prompt` contain an explicit structural keyword? A keyword is a strong,
+ * self-contained signal, so the front-load hook fires on it directly — no graph
+ * check needed. (A *code-token* match, by contrast, is only a candidate the
+ * hook verifies against the graph first; see {@link extractCodeTokens}.)
+ * Coverage is multilingual (#994, #1126): the ~29 languages with the largest
+ * developer populations, across Latin, Cyrillic, Greek, CJK, Hangul, Arabic,
+ * Hebrew, Thai, and Devanagari scripts. Languages beyond the keyword table
+ * still fire through the language-agnostic code-token path.
  */
 export declare function hasStructuralKeyword(prompt: string): boolean;
 /**
@@ -110,7 +114,7 @@ export declare function extractCodeTokens(prompt: string): string[];
 /**
  * Cheap, graph-free candidate gate for the front-load hook: could `prompt` be a
  * structural / flow / impact / "where-how" question worth front-loading context
- * for? True on an explicit keyword (English or CJK, issue #994) OR an
+ * for? True on an explicit keyword in any covered language (#994, #1126) OR an
  * identifier-shaped token. A keyword is sufficient to fire on its own; a
  * token-only match is only a candidate the hook then verifies against the graph
  * (a brand name like `JavaScript` is token-shaped but isn't a symbol). Every

package/dist/extraction/cfml-extractor.d.ts

@@ -0,0 +1,107 @@
+import { ExtractionResult, Language } from '../types';
+/**
+ * CfmlExtractor - Extracts code relationships from CFML source (.cfc/.cfm).
+ *
+ * tree-sitter-cfml splits CFML into two related grammars: `cfml` (tag-based —
+ * `<cfcomponent>`/`<cffunction>`/HTML) and `cfscript` (modern bare-script
+ * `component { ... }` syntax). The `cfml` grammar's own injections.scm treats
+ * bare-script content as an opaque blob meant to be re-parsed by `cfscript` —
+ * that re-parsing only happens at the editor/highlighting layer, not in the
+ * raw AST, so this extractor replicates it: a file whose first real token
+ * isn't `<` is delegated wholesale to the cfscript grammar (the dominant
+ * modern style); otherwise the file is walked tag-by-tag with the cfml
+ * grammar, delegating any `<cfscript>` tag bodies the same way.
+ */
+export declare class CfmlExtractor {
+    private filePath;
+    private source;
+    private language;
+    private nodes;
+    private edges;
+    private unresolvedReferences;
+    private errors;
+    /** `language` is the file's detected language — `'cfml'` for `.cfc`/`.cfm`, `'cfscript'` for `.cfs`. Both dialect-switch internally; this only controls the language tag stamped onto emitted nodes/refs. */
+    constructor(filePath: string, source: string, language?: Language);
+    extract(): ExtractionResult;
+    /** Modern bare-script `.cfc`/`.cfm`: delegate the whole file to the cfscript grammar. */
+    private extractBareScript;
+    /** Legacy tag-based CFML: walk `<cfcomponent>`/`<cffunction>`, delegating `<cfscript>` bodies. */
+    private extractTagBased;
+    /** Build the file's own `kind:'file'` node, spanning the whole source. Tag-based files need this explicitly — unlike `extractBareScript` (which delegates the whole file to `TreeSitterExtractor` and inherits its file node), `extractTagBased` walks the tree itself and has no other source of one. */
+    private createFileNode;
+    /**
+     * Walks `program`'s named children with a single forward cursor (not an
+     * index loop) — `extractComponent` consumes a variable run of FOLLOWING
+     * siblings as the component body (see its doc comment), so this must
+     * resume from whatever it last consumed rather than revisiting those same
+     * cffunction/cfscript siblings a second time as bogus top-level symbols.
+     */
+    private walkProgram;
+    /**
+     * `<cfcomponent extends="Base" implements="IFoo,IBar">...</cfcomponent>`.
+     * The grammar's implicit-end-tag scanner means component body content
+     * (cffunction tags, cfscript tags, etc.) appears as the open tag's FOLLOWING
+     * siblings in `program`, not nested children — walk forward to the matching
+     * cf_component_close_tag.
+     */
+    private extractComponent;
+    /**
+     * `<cffunction name="..." access="..." returntype="...">...</cffunction>`.
+     * `parentClassId` decides `method` vs top-level `function`; `containerId` is
+     * the `contains`-edge target (the class when inside one, otherwise the file
+     * node for a bare top-level cffunction) — kept separate so a top-level
+     * function still gets a containment edge without being misclassified as a
+     * method of the file. A method's qualifiedName is scoped under
+     * `parentClassName` (`TagService::save`, the same `Class::member` shape the
+     * generic extractor produces) so type-validated method resolution can match.
+     */
+    private extractFunctionTag;
+    /**
+     * Recursively delegates any `cf_script_tag`/`cf_query_tag` found within
+     * `node`'s subtree — e.g. a `<cfscript>`/`<cfquery>` nested inside
+     * `<cfif>`/`<cfloop>`/`<cftry>` control-flow tags, which (unlike
+     * `<cfcomponent>`'s body — see the implicit-end-tag note on `extractComponent`)
+     * ARE normal children, just possibly several levels deep, so a direct-children
+     * check misses them. Does not descend into a nested `cf_function_tag` — that
+     * has its own scope and is walked separately. `parentClassName` rides along
+     * so a `<cfscript>` at component scope classifies its functions as methods
+     * scoped under the component.
+     */
+    private delegateNestedTags;
+    /**
+     * Delegate a `<cfscript>...</cfscript>` tag body to the cfscript grammar.
+     * With `parentClassName` set (the block sits at component scope), functions
+     * declared at the script's top level are the component's methods
+     * (`<cfcomponent><cfscript>function configure(){}` — the standard ColdBox
+     * ModuleConfig shape): they're re-kinded `function` → `method`, and every
+     * merged symbol's qualifiedName is prefixed with the component scope
+     * (`configure` → `ModuleConfig::configure`) so type-validated method
+     * resolution can match them. Functions nested inside another function
+     * (closures) keep kind `function`.
+     */
+    private delegateScriptTag;
+    /**
+     * Delegate a `<cfquery>...</cfquery>` tag's SQL body to the `cfquery` grammar.
+     * `#hash#` expressions inside the SQL (e.g. `#getCurrentUser().getId()#` in a
+     * WHERE clause) are real CFML calls/references — tree-sitter-cfml's `cfquery`
+     * grammar parses them structurally (same `call_expression`/`member_expression`
+     * shape as cfscript), so without this delegation they're silently dropped as
+     * opaque SQL text. The grammar models no other symbols, so only call/reference
+     * extraction is relevant here — unlike `delegateScriptTag`, there are no nodes
+     * or contains-edges to merge.
+     */
+    private delegateQueryTag;
+    /** Read a `cf_attribute`'s value by name from a tag node's direct `cf_attribute`/`cf_tag_attributes` children. */
+    private tagAttr;
+    private componentNameFromPath;
+}
+/**
+ * Sniff whether CFML source is bare-script (`component { ... }`, modern style)
+ * vs tag-based (`<cfcomponent>`, `<cfif>`, HTML). Skips a leading UTF-8 BOM
+ * (endemic in CFML's Windows-editor history — 17% of ColdBox's files carry
+ * one; both grammars parse fine with it once routed correctly), whitespace,
+ * and `//`/`/* *\/` comments to find the first real token; tag-based files
+ * start with `<`, script-based files don't.
+ */
+export declare function isBareScriptCfml(source: string): boolean;
+//# sourceMappingURL=cfml-extractor.d.ts.map

package/dist/extraction/grammars.d.ts

@@ -28,6 +28,15 @@ export declare function isSourceFile(filePath: string, overrides?: Record<string
  * extractor links them. (config/ + locales/ JSON have no section refs.)
  */
 export declare function isShopifyLiquidJson(filePath: string): boolean;
+/**
+ * OTP application resource file: `<app>.app.src` (checked into every rebar3/
+ * erlang.mk app) or its compiled `<app>.app`. Erlang TERMS, not forms — the
+ * grammar parses them as top-level expressions, and the Erlang extractor's
+ * application-tuple handler turns `{mod, {Mod, _}}` and `{applications, […]}`
+ * into entry-module and dependency edges. Routed by full suffix because the
+ * last-dot extension (`.src`) is far too generic for EXTENSION_MAP.
+ */
+export declare function isErlangAppFile(filePath: string): boolean;
 /**
  * Play Framework routes file: the extensionless `conf/routes` (and included
  * `conf/*.routes`). No grammar — route extraction is done by the Play framework

package/dist/extraction/index.d.ts

@@ -24,6 +24,14 @@ export interface IndexResult {
     filesIndexed: number;
     filesSkipped: number;
     filesErrored: number;
+    /**
+     * How many indexable files the scan discovered — the ground truth the
+     * indexed/skipped/errored tallies must add up to. A shortfall means files
+     * were silently dropped mid-pipeline (e.g. a killed worker under load) and
+     * the index is PARTIAL; callers surface that rather than trusting the
+     * counts. Only set by full-index runs (indexAll), not indexFiles/sync.
+     */
+    filesDiscovered?: number;
     nodesCreated: number;
     edgesCreated: number;
     errors: ExtractionError[];
@@ -72,6 +80,17 @@ export declare class ScopeIgnore {
      * exclude applies even to tracked files and even inside embedded repos.
      */
     private exclude;
+    /**
+     * Project `codegraph.json` `include` patterns — first-party source forced
+     * INTO the index despite `.gitignore`. When a path matches, it is NOT
+     * ignored (so the watcher watches it), overriding `.gitignore`/`rootMatcher`
+     * — but never `exclude` (checked first) and never a built-in default-ignored
+     * dir. `includeRoots` are the static prefixes so a gitignored ANCESTOR
+     * directory of an included subtree still isn't pruned by the directory
+     * walker/watcher.
+     */
+    private include;
+    private includeRoots;
     private embedded;
     private defaults;
     constructor(rootMatcher: Ignore, embedded: Array<{
@@ -83,7 +102,17 @@ export declare class ScopeIgnore {
      * full root-relative path. Wins over everything else — an explicit user
      * exclude applies even to tracked files and even inside embedded repos.
      */
-    exclude?: Ignore | null);
+    exclude?: Ignore | null, 
+    /**
+     * Project `codegraph.json` `include` patterns — first-party source forced
+     * INTO the index despite `.gitignore`. When a path matches, it is NOT
+     * ignored (so the watcher watches it), overriding `.gitignore`/`rootMatcher`
+     * — but never `exclude` (checked first) and never a built-in default-ignored
+     * dir. `includeRoots` are the static prefixes so a gitignored ANCESTOR
+     * directory of an included subtree still isn't pruned by the directory
+     * walker/watcher.
+     */
+    include?: Ignore | null, includeRoots?: string[]);
     ignores(rel: string): boolean;
 }
 /**
@@ -102,6 +131,22 @@ export declare function buildScopeIgnore(rootDir: string, embeddedRoots?: Iterab
  * there already.
  */
 export declare function discoverEmbeddedRepoRoots(rootDir: string): string[];
+/**
+ * The INVERSE of the gitignored side of {@link discoverEmbeddedRepoRoots}:
+ * nested git repositories under a gitignored directory that the project has NOT
+ * opted into via `codegraph.json` `includeIgnored`. These are real repos the
+ * default `init`/`index` deliberately skips because `.gitignore` excludes them
+ * (#970, #976) — most visibly the "super-repo `.gitignore`s its child repos"
+ * layout (#1156), where `init` at the parent correctly indexes ~nothing while
+ * `init` inside each child works. The CLI uses this to turn that silent empty
+ * index into an actionable hint: it names the skipped repos and offers to opt
+ * them in. Paths are `rootDir`-relative and trailing-slashed (valid
+ * `includeIgnored` patterns as-is). Returns `[]` for a non-git root (a
+ * filesystem walk already descends into nested repos there), skips built-in
+ * default-ignored dirs (`node_modules`, …), and is bounded so it never stalls
+ * on a giant ignored tree.
+ */
+export declare function findUnindexedIgnoredRepos(rootDir: string): string[];
 /**
  * Recursively scan a directory for source files.
  *

package/dist/extraction/languages/arkts.d.ts

@@ -0,0 +1,3 @@
+import type { LanguageExtractor } from '../tree-sitter-types';
+export declare const arktsExtractor: LanguageExtractor;
+//# sourceMappingURL=arkts.d.ts.map

package/dist/extraction/languages/c-cpp.d.ts

@@ -64,5 +64,47 @@ export declare function blankCppInlineMacros(source: string): string;
  * that is a bare primitive/keyword rather than a real identifier.
  */
 export declare function recoverMangledCppName(name: string): string;
+export declare function blankMetalAttributes(source: string): string;
+/**
+ * Blank annotation-style macro invocations that decorate a declaration but carry
+ * NO terminating semicolon — the pervasive Unreal-Engine reflection markup
+ * (`UPROPERTY(...)`, `UFUNCTION(...)`, `UCLASS(...)`, `GENERATED_BODY()`,
+ * `UE_DEPRECATED_FORGAME(...)`, `DECLARE_DELEGATE_*(...)`, …) that sits on its
+ * own line right before a member/type. tree-sitter's C++ grammar doesn't know
+ * these are macros, so each one drops into error recovery; in a big reflected
+ * class (`CharacterMovementComponent.h` has ~240 of them) the errors accumulate
+ * until the enclosing `class_specifier` can't close and collapses into an ERROR
+ * node — the whole class definition, its members, and its `extends` edges vanish
+ * from the graph. Neither `blankCppExportMacros` (class-header export macros) nor
+ * `blankCppInlineMacros` (return-type inline specifiers) touches these in-body
+ * markup macros. Replacing each with equal-length spaces preserves every byte
+ * offset (so line/column stay exact) and the class then parses normally.
+ *
+ * Deliberately name-list-FREE — UE alone has hundreds of such macros and projects
+ * add their own — so it keys on structure, not a curated list, matched tightly to
+ * avoid touching legitimate C++:
+ *  - the macro must be the FIRST non-whitespace token on its line (`^[ \t]*`),
+ *    which is where declaration markup lives — so a macro used inside an
+ *    expression or condition (`if (CHECK(x))`, `x = MACRO(a) + b`) is never
+ *    matched (it isn't line-leading);
+ *  - the name must be ALL-CAPS (`[A-Z][A-Z0-9_]{2,}`), since ordinary
+ *    function/type names called at line start are lower/mixed case;
+ *  - the char after the balanced `(...)` must START A DECLARATION — a letter,
+ *    `_`, `~` (destructor), or `#` (a following directive). Declaration markup is
+ *    always followed by the thing it decorates (`UPROPERTY(...)\n float X;`,
+ *    `UE_DEPRECATED(...) UPROPERTY(...)`), whereas a statement call is followed by
+ *    `;` (`FOO(x);`), an init-list item by `,`/`{`, and an expression fragment by
+ *    an operator (`MAKE(a) + 1`) — all rejected. String/char literals inside the
+ *    args are skipped so an embedded `)` can't mis-close the balance.
+ *
+ * C++-only (wired into cppExtractor). A blanked macro inside a block comment is
+ * harmless (comments don't parse), and the rare line-leading no-semicolon
+ * ALL-CAPS call that isn't markup only loses that one annotation, never a whole
+ * class.
+ */
+export declare function blankCppAnnotationMacroCalls(source: string): string;
+export declare function blankCppApiPrefixMacros(source: string): string;
+export declare function blankCppInlineAnnotationMacros(source: string): string;
+export declare function blankCudaConstructs(source: string): string;
 export declare const cppExtractor: LanguageExtractor;
 //# sourceMappingURL=c-cpp.d.ts.map

package/dist/extraction/languages/cfquery.d.ts

@@ -0,0 +1,12 @@
+import type { LanguageExtractor } from '../tree-sitter-types';
+/**
+ * `<cfquery>` SQL bodies: `#hash#` expressions inside the SQL text are real
+ * CFML expressions (tree-sitter-cfml's `cfquery` grammar parses them
+ * structurally — `call_expression`/`member_expression`, same shape as
+ * cfscript's), so a call like `#getCurrentUser().getId()#` embedded in a
+ * WHERE clause is a genuine call edge. The surrounding SQL keywords/
+ * identifiers aren't symbols CodeGraph models — only `call_expression` is
+ * mapped, so extraction yields call references and nothing else.
+ */
+export declare const cfqueryExtractor: LanguageExtractor;
+//# sourceMappingURL=cfquery.d.ts.map

package/dist/extraction/languages/cfscript.d.ts

@@ -0,0 +1,3 @@
+import type { LanguageExtractor } from '../tree-sitter-types';
+export declare const cfscriptExtractor: LanguageExtractor;
+//# sourceMappingURL=cfscript.d.ts.map