@saluzi/codegraph 0.1.0 → 0.2.1

package/dist/index.js

@@ -42,9 +42,10 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
     for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
 };
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.CodeGraph = exports.MCPServer = exports.FileWatcher = exports.MemoryMonitor = exports.throttle = exports.debounce = exports.processInBatches = exports.FileLock = exports.Mutex = exports.defaultLogger = exports.silentLogger = exports.getLogger = exports.setLogger = exports.ConfigError = exports.VectorError = exports.SearchError = exports.DatabaseError = exports.ParseError = exports.FileError = exports.CodeGraphError = exports.loadAllGrammars = exports.loadGrammarsForLanguages = exports.initGrammars = exports.getSupportedLanguages = exports.isGrammarLoaded = exports.isLanguageSupported = exports.detectLanguage = exports.CODEGRAPH_DIR = exports.findNearestCodeGraphRoot = exports.isInitialized = exports.getCodeGraphDir = exports.getDatabasePath = void 0;
+exports.CodeGraph = exports.MCPServer = exports.LockUnavailableError = exports.FileWatcher = exports.MemoryMonitor = exports.throttle = exports.debounce = exports.processInBatches = exports.FileLock = exports.Mutex = exports.defaultLogger = exports.silentLogger = exports.getLogger = exports.setLogger = exports.ConfigError = exports.VectorError = exports.SearchError = exports.DatabaseError = exports.ParseError = exports.FileError = exports.CodeGraphError = exports.loadAllGrammars = exports.loadGrammarsForLanguages = exports.initGrammars = exports.getSupportedLanguages = exports.isGrammarLoaded = exports.isLanguageSupported = exports.detectLanguage = exports.CODEGRAPH_DIR = exports.findNearestCodeGraphRoot = exports.isInitialized = exports.getCodeGraphDir = exports.QueryBuilder = exports.DatabaseConnection = exports.getDatabasePath = void 0;
 const path = __importStar(require("path"));
 const db_1 = require("./db");
+const wal_valve_1 = require("./db/wal-valve");
 const queries_1 = require("./db/queries");
 const directory_1 = require("./directory");
 const extraction_1 = require("./extraction");
@@ -53,15 +54,28 @@ const graph_1 = require("./graph");
 const context_1 = require("./context");
 const utils_1 = require("./utils");
 const sync_1 = require("./sync");
+const extraction_version_1 = require("./extraction/extraction-version");
+const directory_2 = require("./directory");
+const query_utils_1 = require("./search/query-utils");
+const version_1 = require("./mcp/version");
+const identifier_segments_1 = require("./search/identifier-segments");
+const cooperative_yield_1 = require("./resolution/cooperative-yield");
 // Re-export types for consumers
 __exportStar(require("./types"), exports);
+// Storage building blocks for embedded/SDK consumers that drive the graph
+// directly (open a DB, run prepared queries) rather than through the CodeGraph
+// facade. Exposed from the package entry so they no longer require deep imports
+// into dist/ (issue #354).
 var db_2 = require("./db");
 Object.defineProperty(exports, "getDatabasePath", { enumerable: true, get: function () { return db_2.getDatabasePath; } });
-var directory_2 = require("./directory");
-Object.defineProperty(exports, "getCodeGraphDir", { enumerable: true, get: function () { return directory_2.getCodeGraphDir; } });
-Object.defineProperty(exports, "isInitialized", { enumerable: true, get: function () { return directory_2.isInitialized; } });
-Object.defineProperty(exports, "findNearestCodeGraphRoot", { enumerable: true, get: function () { return directory_2.findNearestCodeGraphRoot; } });
-Object.defineProperty(exports, "CODEGRAPH_DIR", { enumerable: true, get: function () { return directory_2.CODEGRAPH_DIR; } });
+Object.defineProperty(exports, "DatabaseConnection", { enumerable: true, get: function () { return db_2.DatabaseConnection; } });
+var queries_2 = require("./db/queries");
+Object.defineProperty(exports, "QueryBuilder", { enumerable: true, get: function () { return queries_2.QueryBuilder; } });
+var directory_3 = require("./directory");
+Object.defineProperty(exports, "getCodeGraphDir", { enumerable: true, get: function () { return directory_3.getCodeGraphDir; } });
+Object.defineProperty(exports, "isInitialized", { enumerable: true, get: function () { return directory_3.isInitialized; } });
+Object.defineProperty(exports, "findNearestCodeGraphRoot", { enumerable: true, get: function () { return directory_3.findNearestCodeGraphRoot; } });
+Object.defineProperty(exports, "CODEGRAPH_DIR", { enumerable: true, get: function () { return directory_3.CODEGRAPH_DIR; } });
 var extraction_2 = require("./extraction");
 Object.defineProperty(exports, "detectLanguage", { enumerable: true, get: function () { return extraction_2.detectLanguage; } });
 Object.defineProperty(exports, "isLanguageSupported", { enumerable: true, get: function () { return extraction_2.isLanguageSupported; } });
@@ -91,6 +105,9 @@ Object.defineProperty(exports, "throttle", { enumerable: true, get: function ()
 Object.defineProperty(exports, "MemoryMonitor", { enumerable: true, get: function () { return utils_2.MemoryMonitor; } });
 var sync_2 = require("./sync");
 Object.defineProperty(exports, "FileWatcher", { enumerable: true, get: function () { return sync_2.FileWatcher; } });
+Object.defineProperty(exports, "LockUnavailableError", { enumerable: true, get: function () { return sync_2.LockUnavailableError; } });
+var mcp_1 = require("./mcp");
+Object.defineProperty(exports, "MCPServer", { enumerable: true, get: function () { return mcp_1.MCPServer; } });
 /**
  * Main CodeGraph class
  *
@@ -100,6 +117,9 @@ class CodeGraph {
     db;
     queries;
     projectRoot;
+    // Assigned via wireLayers() from the constructor (and again on reopen) — the
+    // `!` tells TS these are definitely set even though the assignment is one
+    // method call away from the constructor body.
     orchestrator;
     resolver;
     graphManager;
@@ -115,12 +135,63 @@ class CodeGraph {
         this.db = db;
         this.queries = queries;
         this.projectRoot = projectRoot;
-        this.fileLock = new utils_1.FileLock(path.join(projectRoot, '.codegraph', 'codegraph.lock'));
-        this.orchestrator = new extraction_1.ExtractionOrchestrator(projectRoot, queries);
-        this.resolver = (0, resolution_1.createResolver)(projectRoot, queries);
-        this.graphManager = new graph_1.GraphQueryManager(queries);
-        this.traverser = new graph_1.GraphTraverser(queries);
-        this.contextBuilder = (0, context_1.createContextBuilder)(projectRoot, queries, this.traverser);
+        this.fileLock = new utils_1.FileLock(path.join((0, directory_2.getCodeGraphDir)(projectRoot), 'codegraph.lock'));
+        this.wireLayers();
+    }
+    /**
+     * (Re)build the query/extraction/graph layers over the current `this.queries`
+     * (which wraps `this.db`). Factored out of the constructor so `reopenIfReplaced`
+     * can rebuild them against a fresh connection without duplicating the wiring.
+     * The path-based `fileLock` is independent of the DB handle, so it stays put.
+     */
+    wireLayers() {
+        // Down-weight the project name as a query term in search ranking — it names
+        // the whole repo, not a symbol, so it has no discriminative value (#720).
+        try {
+            this.queries.setProjectNameTokens((0, query_utils_1.deriveProjectNameTokens)(this.projectRoot));
+        }
+        catch {
+            // Best-effort: ranking still works without it.
+        }
+        this.orchestrator = new extraction_1.ExtractionOrchestrator(this.projectRoot, this.queries);
+        this.resolver = (0, resolution_1.createResolver)(this.projectRoot, this.queries);
+        this.graphManager = new graph_1.GraphQueryManager(this.queries);
+        this.traverser = new graph_1.GraphTraverser(this.queries);
+        this.contextBuilder = (0, context_1.createContextBuilder)(this.projectRoot, this.queries, this.traverser);
+    }
+    /**
+     * Heal a stale database handle in place. If `.codegraph/` was removed and
+     * recreated at the SAME path while this instance held the DB open — a git
+     * worktree removed and re-added, or `rm -rf .codegraph` + `codegraph init` —
+     * our open fd points at the now-unlinked inode and can never see the new
+     * index, so every query returns the pre-removal snapshot until the process
+     * restarts (#925). When that's detected, open the live file at the same path,
+     * rebuild the query layers, and swap them IN PLACE, so every holder of this
+     * instance (the MCP daemon's default project, cached projectPath connections)
+     * heals without a restart. Returns true iff it reopened.
+     *
+     * POSIX-only in practice: `isReplacedOnDisk` never fires on Windows (an open
+     * file can't be unlinked there, and st_ino is unreliable).
+     */
+    reopenIfReplaced() {
+        if (!this.db.isReplacedOnDisk())
+            return false;
+        const dbPath = this.db.getPath();
+        // Open the live file FIRST — if that throws (e.g. mid-recreate), the old
+        // handle stays in place and the caller retries on the next query, rather
+        // than leaving this instance with no connection at all.
+        const fresh = db_1.DatabaseConnection.open(dbPath);
+        const stale = this.db;
+        this.db = fresh;
+        this.queries = new queries_1.QueryBuilder(fresh.getDb());
+        this.wireLayers();
+        // Releasing the dead handle also frees the leaked db/-wal/-shm fds that were
+        // pinning the unlinked inode (#925).
+        try {
+            stale.close();
+        }
+        catch { /* the old inode is gone; closing just frees fds */ }
+        return true;
     }
     // ===========================================================================
     // Lifecycle Methods
@@ -201,6 +272,48 @@ class CodeGraph {
         }
         return instance;
     }
+    /**
+     * Rebuild the project's database from scratch and return a fresh, empty
+     * instance — the "same result as a fresh init" semantics that `codegraph
+     * index` documents.
+     *
+     * Unlike `open()` followed by `clear()`, this DISCARDS the existing
+     * `.codegraph/codegraph.db` (and its `-wal`/`-shm` sidecars) before
+     * re-initializing, instead of opening the old database and DELETE-ing every
+     * row. On a large or pre-fix poisoned index — e.g. an old graph that scanned
+     * an ignored gitlink corpus (#1065) into ~1.6M nodes with a multi-GB WAL —
+     * the per-row `nodes_fts` delete-trigger churn blocks the main thread long
+     * enough to trip the #850 liveness watchdog before indexing even starts, so a
+     * full re-index could never recover the bad state (#1067). Discarding the
+     * files is O(1) regardless of size, reclaims the disk, and sidesteps opening
+     * (and running migrations against) the poisoned database entirely.
+     */
+    static async recreate(projectRoot) {
+        await (0, extraction_1.initGrammars)();
+        const resolvedRoot = path.resolve(projectRoot);
+        // Check if initialized — recreate REBUILDS an existing project; it is not a
+        // first-time `init`.
+        if (!(0, directory_1.isInitialized)(resolvedRoot)) {
+            throw new Error(`CodeGraph not initialized in ${resolvedRoot}. Run init() first.`);
+        }
+        const dbPath = (0, db_1.getDatabasePath)(resolvedRoot);
+        try {
+            (0, db_1.removeDatabaseFiles)(dbPath);
+        }
+        catch (err) {
+            // POSIX unlinks an open file fine; this fires mainly on Windows when a
+            // live daemon/MCP server still holds the database. Turn the raw EBUSY into
+            // an actionable instruction instead of a generic failure.
+            const reason = err instanceof Error ? err.message : String(err);
+            throw new Error(`Could not rebuild the index — the database file is in use (${reason}). ` +
+                `Stop any running CodeGraph MCP server/daemon for this project and retry, ` +
+                `or remove the ${(0, directory_2.getCodeGraphDir)(resolvedRoot)} directory and run "codegraph init".`);
+        }
+        // Re-create an empty, freshly-schema'd database at the same path.
+        const db = db_1.DatabaseConnection.initialize(dbPath);
+        const queries = new queries_1.QueryBuilder(db.getDb());
+        return new CodeGraph(db, queries, resolvedRoot);
+    }
     /**
      * Open synchronously (without sync)
      */
@@ -258,8 +371,62 @@ class CodeGraph {
             catch {
                 return { success: false, filesIndexed: 0, filesSkipped: 0, filesErrored: 0, nodesCreated: 0, edgesCreated: 0, errors: [{ message: 'Could not acquire file lock - another process may be indexing', severity: 'error' }], durationMs: 0 };
             }
+            // Defer WAL auto-checkpointing for the whole bulk run (#1231): the
+            // default 1000-page interval re-writes hot pages into the main DB file
+            // over and over — ~95% of all disk I/O during a bulk index, and a
+            // 19+min → 45s difference on HDD-class storage. The valve bounds WAL
+            // growth by backfilling PASSIVEly on a worker thread (never blocking
+            // the writer or the #850 watchdog heartbeat); runMaintenance below does
+            // the final fold-up before the interval is restored in the finally.
+            // Kill switch: CODEGRAPH_NO_WAL_DEFER=1. Non-WAL journal modes (some
+            // network filesystems) have no WAL to defer — skip.
+            const deferWal = process.env.CODEGRAPH_NO_WAL_DEFER !== '1' && this.db.getJournalMode() === 'wal';
+            let walValve = null;
+            let priorAutocheckpoint = 1000;
+            if (deferWal) {
+                priorAutocheckpoint = this.db.getWalAutocheckpoint();
+                this.db.setWalAutocheckpoint(0);
+                walValve = new wal_valve_1.WalCheckpointValve(this.db, undefined, undefined, options.verbose ? (m) => console.log(`[wal-valve] ${m}`) : undefined);
+                walValve.start();
+            }
             try {
-                const result = await this.orchestrator.indexAll(options.onProgress, options.signal, options.verbose);
+                const before = this.queries.getNodeAndEdgeCount();
+                // Mark the index as in-flight BEFORE any writes: a run killed
+                // mid-index (OOM, SIGKILL, the #850 liveness watchdog) leaves this
+                // marker behind, so `codegraph status` can tell a truncated index
+                // from a completed one instead of silently serving partial results.
+                try {
+                    this.queries.setMetadata('index_state', 'indexing');
+                }
+                catch { /* metadata is advisory */ }
+                // Segment vocabulary starts empty and is repopulated by the node write
+                // path as every file (re-)indexes below — so a full index is also the
+                // orphan-cleanup pass for names deleted since the last one.
+                try {
+                    this.queries.clearNameSegmentVocab();
+                }
+                catch { /* vocab is advisory — never fail an index over it */ }
+                const result = await this.orchestrator.indexAll(options.onProgress, options.signal, options.verbose, walValve ? () => walValve.backpressure() : undefined);
+                // Fold the parse phase's WAL BEFORE the first post-parse reads
+                // (resolver re-init and resolution both read on the main thread):
+                // paging a bulk-write-sized WAL there is what blew the #850
+                // watchdog's 60s window in the #1231 repro. Off-thread + awaited,
+                // so the event loop keeps turning.
+                if (walValve)
+                    await walValve.foldNow();
+                // Re-detect frameworks now that the index is populated. The resolver
+                // is constructed with createResolver() before any files exist, so
+                // framework resolvers whose detect() consults the indexed file list
+                // (e.g. UIKit/SwiftUI scanning for imports, swift-objc-bridge looking
+                // for both Swift and ObjC files) all return false on that initial pass
+                // and silently drop themselves. Re-initializing here gives them a
+                // chance to see the actual project before resolution runs.
+                if (result.success && result.filesIndexed > 0) {
+                    this.resolver.initialize();
+                    // Cross-file finalization (e.g. NestJS RouterModule prefixes). Runs
+                    // before resolution so updated names show up in subsequent reads.
+                    this.resolver.runPostExtract();
+                }
                 // Resolve references to create call/import/extends edges
                 if (result.success && result.filesIndexed > 0) {
                     // Get count without loading all refs into memory
@@ -276,15 +443,112 @@ class CodeGraph {
                             total,
                         });
                     });
+                    // Second pass: chained calls whose method lives on a supertype the
+                    // receiver conforms to (protocol-extension / inherited / default-
+                    // interface). Needs the implements/extends edges the main pass just
+                    // built, so it runs after resolution (#750).
+                    const tChained = Date.now();
+                    await this.resolver.resolveChainedCallsViaConformance();
+                    if (process.env.CODEGRAPH_SYNTH_TIMINGS)
+                        console.error(`[synth-timing] chainedConformance: ${Date.now() - tChained}ms`);
+                    // Same lifecycle for `this.<member>` callback registrations whose
+                    // member is inherited from a supertype (#808).
+                    const tDeferred = Date.now();
+                    await this.resolver.resolveDeferredThisMemberRefs();
+                    if (process.env.CODEGRAPH_SYNTH_TIMINGS)
+                        console.error(`[synth-timing] deferredThisMember: ${Date.now() - tDeferred}ms`);
                 }
                 // Refresh planner stats + checkpoint the WAL after bulk writes.
-                // Cheap and non-blocking; never load-bearing for correctness.
+                // Off-thread (worker connection): on a multi-GB index this is minutes
+                // of IO, and inline it starved the #850 watchdog AFTER a fully
+                // successful index. Never load-bearing for correctness.
+                if (result.success && result.filesIndexed > 0) {
+                    const tMaint = Date.now();
+                    // Quiesce the valve first so its in-flight checkpoint and the
+                    // maintenance checkpoint don't contend for the checkpointer lock
+                    // (the loser would silently no-op and leave the WAL unfolded).
+                    if (walValve) {
+                        walValve.stop();
+                        await walValve.drain();
+                    }
+                    await this.db.runMaintenance();
+                    if (process.env.CODEGRAPH_SYNTH_TIMINGS)
+                        console.error(`[phase-timing] maintenance: ${Date.now() - tMaint}ms`);
+                }
+                // The orchestrator only sees extraction-phase counts; resolution and
+                // synthesizer edges (often >50% of the graph on JVM repos) come later.
+                // Recompute against the DB so the CLI summary reports the true totals.
                 if (result.success && result.filesIndexed > 0) {
-                    this.db.runMaintenance();
+                    const tCount = Date.now();
+                    const after = this.queries.getNodeAndEdgeCount();
+                    if (process.env.CODEGRAPH_SYNTH_TIMINGS)
+                        console.error(`[phase-timing] count-recompute: ${Date.now() - tCount}ms`);
+                    result.nodesCreated = after.nodes - before.nodes;
+                    result.edgesCreated = after.edges - before.edges;
+                }
+                // Stamp the index with the engine that built it, so `codegraph status`
+                // and `codegraph upgrade` can recommend a re-index when the running
+                // engine produces richer extraction than the one on disk. Only on a
+                // real full index — a sync touches a subset, so it must NOT advance the
+                // extraction stamp (the bulk would still be stale). See extraction-version.ts.
+                if (result.success && result.filesIndexed > 0) {
+                    try {
+                        this.queries.setMetadata('indexed_with_version', version_1.CodeGraphPackageVersion);
+                        this.queries.setMetadata('indexed_with_extraction_version', String(extraction_version_1.EXTRACTION_VERSION));
+                    }
+                    catch { /* metadata is advisory — never fail an index over it */ }
+                }
+                // Reconcile the scan's ground truth against what the pipeline
+                // accounted for. A shortfall means files were silently dropped
+                // (observed in the wild: a run under heavy load came up 37 files
+                // short with no error) — record it and tell the user, don't let the
+                // index pass as complete.
+                try {
+                    if (!result.success) {
+                        this.queries.setMetadata('index_state', 'failed');
+                    }
+                    else {
+                        const accounted = result.filesIndexed + result.filesSkipped + result.filesErrored;
+                        const discovered = result.filesDiscovered;
+                        const shortfall = discovered !== undefined ? discovered - accounted : 0;
+                        if (discovered !== undefined && shortfall > 0) {
+                            this.queries.setMetadata('index_state', 'partial');
+                            this.queries.setMetadata('index_files_discovered', String(discovered));
+                            this.queries.setMetadata('index_files_accounted', String(accounted));
+                            result.errors.push({
+                                message: `Index is missing ${shortfall} of ${discovered} discovered files (indexed ${result.filesIndexed}, skipped ${result.filesSkipped}, errored ${result.filesErrored}). The index is PARTIAL — re-run \`codegraph index\`.`,
+                                severity: 'warning',
+                                code: 'index_partial',
+                            });
+                        }
+                        else {
+                            this.queries.setMetadata('index_state', 'complete');
+                            if (discovered !== undefined) {
+                                this.queries.setMetadata('index_files_discovered', String(discovered));
+                                this.queries.setMetadata('index_files_accounted', String(accounted));
+                            }
+                        }
+                    }
                 }
+                catch { /* metadata is advisory — never fail an index over it */ }
                 return result;
             }
             finally {
+                // Restore the auto-checkpoint interval AFTER the fold-up above so the
+                // next ordinary write doesn't inherit a giant inline checkpoint. On
+                // the error path the WAL may still be large; correctness is unchanged
+                // (SQLite replays the WAL on the next open) and the follow-up write
+                // that folds it is the known cost of a failed run.
+                if (walValve) {
+                    walValve.stop();
+                    await walValve.drain();
+                }
+                if (deferWal) {
+                    try {
+                        this.db.setWalAutocheckpoint(priorAutocheckpoint);
+                    }
+                    catch { /* connection may be closing */ }
+                }
                 this.fileLock.release();
             }
         });
@@ -324,12 +588,45 @@ class CodeGraph {
                 return { filesChecked: 0, filesAdded: 0, filesModified: 0, filesRemoved: 0, nodesUpdated: 0, durationMs: 0 };
             }
             try {
+                // Captured BEFORE the sync runs: the sync's own incremental writes
+                // populate vocab rows for the files it touches, so an end-of-sync
+                // emptiness check would see "non-empty" and skip the backfill forever,
+                // leaving every unchanged file's names unsegmented.
+                const vocabWasEmpty = (() => {
+                    try {
+                        return this.queries.isNameSegmentVocabEmpty();
+                    }
+                    catch {
+                        return false;
+                    }
+                })();
                 const result = await this.orchestrator.sync(options.onProgress);
-                // Resolve references if files were updated
+                // Cross-file finalization (e.g. NestJS RouterModule prefixes). Run on
+                // every sync that touched files so edits to `app.module.ts` propagate
+                // to controllers in unchanged files. The pass is idempotent and cheap
+                // (regex over *.module.ts only).
                 if (result.filesAdded > 0 || result.filesModified > 0) {
+                    this.resolver.runPostExtract();
+                }
+                else if (result.filesRemoved > 0) {
+                    // A pure-removal sync still resolves refs below — the deletion path
+                    // resurrects the removed file's incoming edges as pending refs
+                    // (#1240 removal case) and the orphan sweep consumes them. In a
+                    // long-lived process (daemon) the resolver's name caches were
+                    // warmed against the pre-removal graph; drop them so resolution
+                    // sees the post-removal state. (runPostExtract above clears caches
+                    // itself, so the changed-files branch is already covered.)
+                    this.resolver.clearCaches();
+                }
+                // Resolve references if files were updated
+                const filesChanged = result.filesAdded > 0 || result.filesModified > 0;
+                if (filesChanged) {
                     if (result.changedFilePaths) {
                         // Scope resolution to changed files (git fast path — bounded set)
+                        const tRefLoad = Date.now();
                         const unresolvedRefs = this.queries.getUnresolvedReferencesByFiles(result.changedFilePaths);
+                        if (process.env.CODEGRAPH_SYNTH_TIMINGS)
+                            console.error(`[phase-timing] sync-ref-load: ${Date.now() - tRefLoad}ms (${unresolvedRefs.length} refs)`);
                         options.onProgress?.({
                             phase: 'resolving',
                             current: 0,
@@ -342,6 +639,32 @@ class CodeGraph {
                                 total,
                             });
                         });
+                        // Retry previously-failed refs the changed files may now satisfy
+                        // (#1240). Scoped resolution above only re-resolves refs FROM the
+                        // changed files — but when a changed file gains an export/symbol,
+                        // refs in UNCHANGED files that failed against the old graph can
+                        // now resolve, and nothing else ever revisits them (their rows
+                        // were parked as status='failed' by an earlier completed pass).
+                        // Look them up by the symbol names the changed files now carry
+                        // and re-resolve just that set. On a sync where no failed ref
+                        // matches, this is one indexed lookup.
+                        const tRetry = Date.now();
+                        const retryable = this.queries.getRetryableFailedReferences(this.queries.getNodeNamesByFiles(result.changedFilePaths));
+                        if (retryable.length > 0) {
+                            options.onProgress?.({
+                                phase: 'resolving',
+                                current: 0,
+                                total: retryable.length,
+                            });
+                            await this.resolver.resolveAndPersistListYielding(retryable);
+                            options.onProgress?.({
+                                phase: 'resolving',
+                                current: retryable.length,
+                                total: retryable.length,
+                            });
+                        }
+                        if (process.env.CODEGRAPH_SYNTH_TIMINGS)
+                            console.error(`[phase-timing] sync-failed-ref-retry: ${Date.now() - tRetry}ms (${retryable.length} refs)`);
                     }
                     else {
                         // No git info — use batched resolution to avoid OOM
@@ -360,10 +683,60 @@ class CodeGraph {
                         });
                     }
                 }
+                // Orphan sweep (#1187). A resolution pass that dies mid-run — the #850
+                // daemon liveness watchdog's SIGKILL (#1122), Ctrl-C, a crash — leaves
+                // the refs it never reached in unresolved_refs, and the git-scoped fast
+                // path above never revisits them (it reads only the changed files'
+                // rows). Those files' call edges were then missing PERMANENTLY, with
+                // nothing to see except a too-small blast radius, until a full
+                // re-index. A completed pass takes every row it processed out of the
+                // PENDING set (resolved rows are deleted, unresolvable ones parked as
+                // status='failed' for the #1240 retry above), so any pending row now
+                // is such an orphan — or a row from an older engine's scoped pass.
+                // Grind them down with the batched resolver; this also makes a bare
+                // `codegraph sync` the recovery command for a wedged index. On a
+                // healthy index this is one COUNT query.
+                const orphanCount = this.queries.getUnresolvedReferencesCount();
+                if (orphanCount > 0) {
+                    options.onProgress?.({
+                        phase: 'resolving',
+                        current: 0,
+                        total: orphanCount,
+                    });
+                    await this.resolveReferencesBatched((current, total) => {
+                        options.onProgress?.({
+                            phase: 'resolving',
+                            current,
+                            total,
+                        });
+                    });
+                }
+                if (filesChanged || orphanCount > 0) {
+                    // Second pass: chained calls whose method lives on a supertype the
+                    // receiver conforms to (protocol-extension / inherited). Needs the
+                    // implements/extends edges built above (#750).
+                    await this.resolver.resolveChainedCallsViaConformance();
+                    // Same lifecycle for `this.<member>` callback registrations whose
+                    // member is inherited from a supertype (#808).
+                    await this.resolver.resolveDeferredThisMemberRefs();
+                }
                 // Refresh planner stats + checkpoint the WAL after bulk writes.
-                if (result.filesAdded > 0 || result.filesModified > 0 || result.filesRemoved > 0) {
-                    this.db.runMaintenance();
+                // Off-thread — see indexAll's call site.
+                if (filesChanged || result.filesRemoved > 0 || orphanCount > 0) {
+                    await this.db.runMaintenance();
                 }
+                // Heal the segment vocabulary on indexes built before the table
+                // existed (upgrade path): incremental writes above only cover changed
+                // files, so a vocab that was empty when this sync STARTED means the
+                // bulk was never segmented — backfill it (INSERT OR IGNORE, so the
+                // rows the sync just wrote are fine). Batched + yielding — sync can
+                // run on the daemon's liveness-watchdog thread (#850/#1091).
+                try {
+                    if (vocabWasEmpty && this.queries.getNodeAndEdgeCount().nodes > 0) {
+                        await this.rebuildNameSegmentVocab();
+                    }
+                }
+                catch { /* vocab is advisory — never fail a sync over it */ }
                 return result;
             }
             finally {
@@ -394,6 +767,14 @@ class CodeGraph {
             return true;
         this.watcher = new sync_1.FileWatcher(this.projectRoot, async () => {
             const result = await this.sync();
+            // sync() returns this exact zero-shape iff it failed to acquire the
+            // file lock (a real empty sync always has filesChecked > 0 because
+            // scanDirectory ran). Surface that to the watcher as a typed error
+            // so it keeps pendingFiles + reschedules instead of clearing them
+            // (#449).
+            if (result.filesChecked === 0 && result.durationMs === 0) {
+                throw new sync_1.LockUnavailableError();
+            }
             const filesChanged = result.filesAdded + result.filesModified + result.filesRemoved;
             return { filesChanged, durationMs: result.durationMs };
         }, options);
@@ -414,12 +795,98 @@ class CodeGraph {
     isWatching() {
         return this.watcher?.isActive() ?? false;
     }
+    /**
+     * True once live watching has permanently degraded (OS watch-resource
+     * exhaustion, or a write lock held past the retry budget) and auto-sync is
+     * disabled until the next {@link watch} call. Distinct from `!isWatching()`:
+     * a stopped/never-started watcher is inactive but NOT degraded. MCP tools use
+     * this to surface a whole-index "results may be stale" notice, since
+     * `getPendingFiles()` goes empty once watching stops (#876).
+     */
+    isWatcherDegraded() {
+        return this.watcher?.isDegraded() ?? false;
+    }
+    /** The reason live watching degraded, or null if it is healthy (#876). */
+    getWatcherDegradedReason() {
+        return this.watcher?.getDegradedReason() ?? null;
+    }
+    /**
+     * Files seen by the file watcher since the last successful sync —
+     * the per-file "stale" signal MCP tools attach to responses so an agent
+     * can fall back to {@link Read} for just the affected file without
+     * waiting for a debounced sync to complete (issue #403).
+     *
+     * Returns an empty list when the watcher isn't active, or no events have
+     * arrived. Each entry includes `firstSeenMs` and `lastSeenMs` (wall-clock
+     * `Date.now()` values) so callers can render "edited Nms ago", plus an
+     * `indexing` flag indicating whether the in-flight sync (if any) will
+     * absorb that file.
+     */
+    getPendingFiles() {
+        return this.watcher?.getPendingFiles() ?? [];
+    }
+    /**
+     * Resolves once the file watcher has installed its watch set. Useful for
+     * tests that need a deterministic boundary before asserting on
+     * `getPendingFiles()`. Resolves immediately when no watcher is active.
+     */
+    waitUntilWatcherReady(timeoutMs) {
+        return this.watcher ? this.watcher.waitUntilReady(timeoutMs) : Promise.resolve();
+    }
     /**
      * Get files that have changed since last index
      */
     getChangedFiles() {
         return this.orchestrator.getChangedFiles();
     }
+    /**
+     * Most recent index timestamp (ms since epoch) across all tracked files, or
+     * null when nothing is indexed yet. Lets library consumers check index
+     * freshness without shelling out to `codegraph status --json`. (#329)
+     */
+    getLastIndexedAt() {
+        return this.queries.getLastIndexedAt();
+    }
+    /**
+     * Completeness of the last full index run. `'complete'` is the only good
+     * state. `'indexing'` after the fact means a run was killed mid-index (OOM,
+     * SIGKILL, liveness watchdog) and the on-disk index is truncated;
+     * `'partial'` means the run finished but silently dropped files
+     * (discovered > indexed+skipped+errored); `'failed'` means it reported
+     * failure. `null` = index predates this marker. Surfaced by
+     * `codegraph status`.
+     */
+    getIndexState() {
+        const raw = this.queries.getMetadata('index_state');
+        return raw === 'indexing' || raw === 'complete' || raw === 'partial' || raw === 'failed'
+            ? raw
+            : null;
+    }
+    /**
+     * Which engine built the current index: the package version + extraction
+     * version stamped at the last full `indexAll`. Either field is null for an
+     * index built before stamping existed (treated as stale). See
+     * `extraction-version.ts` and `isIndexStale()`.
+     */
+    getIndexBuildInfo() {
+        const version = this.queries.getMetadata('indexed_with_version');
+        const ev = this.queries.getMetadata('indexed_with_extraction_version');
+        const parsed = ev != null ? parseInt(ev, 10) : NaN;
+        return { version, extractionVersion: Number.isFinite(parsed) ? parsed : null };
+    }
+    /**
+     * True when the on-disk index was built by an engine whose extraction is
+     * older than the one now running — i.e. a re-index would add data a migration
+     * can't backfill. False when there's no index yet (nothing to refresh) or the
+     * stamp is current. This is the signal behind `codegraph status`'s re-index
+     * hint and `codegraph upgrade`'s reminder.
+     */
+    isIndexStale() {
+        if (this.queries.getLastIndexedAt() == null)
+            return false;
+        const { extractionVersion } = this.getIndexBuildInfo();
+        return extractionVersion == null || extractionVersion < extraction_version_1.EXTRACTION_VERSION;
+    }
     /**
      * Extract nodes and edges from source code (without storing)
      */
@@ -450,6 +917,16 @@ class CodeGraph {
     async resolveReferencesBatched(onProgress) {
         return this.resolver.resolveAndPersistBatched(onProgress);
     }
+    /**
+     * References extracted but never attempted by a resolution pass. Zero on a
+     * healthy index — a completed pass consumes every pending row (resolving it
+     * or parking it as failed, #1240). Non-zero at rest means a pass was
+     * interrupted mid-run (killed indexer, crash — #1187), so some files' call
+     * edges are missing; the next `sync` sweeps them.
+     */
+    getPendingReferenceCount() {
+        return this.queries.getUnresolvedReferencesCount();
+    }
     /**
      * Get detected frameworks in the project
      */
@@ -511,12 +988,226 @@ class CodeGraph {
     getNodesByKind(kind) {
         return this.queries.getNodesByKind(kind);
     }
+    /**
+     * Get ALL nodes with an exact name (direct index lookup, not FTS-ranked/capped).
+     * Used to enumerate every overload of a heavily-overloaded name so the specific
+     * definition the caller wants is never dropped below a search cut.
+     */
+    getNodesByName(name) {
+        return this.queries.getNodesByName(name);
+    }
+    /** Nodes whose name starts with `prefix` (index range scan, capped). */
+    getNodesByNamePrefix(prefix, limit = 20) {
+        return this.queries.getNodesByNamePrefix(prefix, limit);
+    }
     /**
      * Search nodes by text
      */
     searchNodes(query, options) {
         return this.queries.searchNodes(query, options);
     }
+    /**
+     * Graph-derived prompt matching for the front-load hook's MEDIUM tier:
+     * which indexed symbols do these prose words name? "state machine des
+     * commandes" → `OrderStateMachine`, in any human language whose technical
+     * nouns are Latin script — no keyword list involved.
+     *
+     * Precision comes from the repo's own naming statistics, not vocabulary:
+     * - CO-OCCURRENCE: ≥2 words that are segments of the SAME name ("state" +
+     *   "machine" → OrderStateMachine) is strong evidence and always qualifies.
+     * - RARITY: a single matched word qualifies only when its segment is
+     *   discriminative here (≤ {@link SEGMENT_RARITY_CEILING} distinct names) —
+     *   "checkout" in a shop backend yes, "state" in a react app no.
+     * Every candidate is re-verified against `nodes` before being returned
+     * (vocab rows are proposals; deletions leave orphans by design), so a
+     * returned symbol is guaranteed to exist right now.
+     */
+    getSegmentMatches(words, limit = 6) {
+        if (words.length === 0)
+            return [];
+        // Variant → original word (plural folding), for coverage accounting.
+        const variantToWord = new Map();
+        for (const word of words) {
+            for (const variant of (0, identifier_segments_1.segmentLookupVariants)(word)) {
+                if (!variantToWord.has(variant))
+                    variantToWord.set(variant, word);
+            }
+        }
+        const variants = [...variantToWord.keys()];
+        // Tier A: co-occurrence. The SQL folds variants back to their original
+        // word (#1146), so minWords=2 means two distinct PROMPT WORDS — a name
+        // matching both `service` and `services` can't tie with (or crowd past
+        // the LIMIT) a genuine two-word match. The JS re-check below recomputes
+        // the fold from live segments as the honesty layer.
+        const variantPairs = [...variantToWord.entries()].map(([segment, word]) => ({ segment, word }));
+        const candidates = [];
+        for (const hit of this.queries.getSegmentCoOccurrence(variantPairs, 2, 24)) {
+            const matched = this.wordsMatchingName(hit.name, variantToWord);
+            if (matched.size >= 2)
+                candidates.push({ name: hit.name, matchedWords: matched });
+        }
+        // Tier B: single rare word. Only when co-occurrence found nothing — a
+        // co-occurring name is categorically stronger evidence — and under
+        // stricter rules, because one word is thin: the word must be ≥5 chars
+        // (measured FPs: "this", "typo"); the segment must appear in AT LEAST TWO
+        // names (a concept the codebase is about clusters across names —
+        // CheckoutService/CheckoutController — while a prose coincidence is a
+        // singleton: measured FP "deploy to PRODUCTION" → the one name
+        // matchesNonProductionDir); and the candidate name must have ≥2 segments
+        // (a bare common verb matching a bare function name — "write" → `write` —
+        // is prose coincidence, not the user naming a symbol).
+        if (candidates.length === 0) {
+            const singleWordVariants = variants.filter((v) => variantToWord.get(v).length >= 5);
+            const counts = this.queries.getSegmentNameCounts(singleWordVariants);
+            const rare = [...counts.entries()]
+                .filter(([, n]) => n >= 2 && n <= CodeGraph.SEGMENT_RARITY_CEILING)
+                .sort((a, b) => a[1] - b[1])
+                .slice(0, 2);
+            for (const [variant] of rare) {
+                const word = variantToWord.get(variant);
+                for (const name of this.queries.getNamesForSegment(variant, 12)) {
+                    if ((0, identifier_segments_1.splitIdentifierSegments)(name).length < 2)
+                        continue;
+                    candidates.push({ name, matchedWords: new Set([word]) });
+                }
+            }
+        }
+        // Verify against nodes (the honesty gate) and pick a representative
+        // definition per name. A name whose only nodes are file/import kind has
+        // no real definition to point at — surfacing the import statement instead
+        // reads as a matched symbol but isn't one (#1144) — so it's skipped, the
+        // same way an orphaned vocab row is. (Import names no longer enter the
+        // vocab at write time, but rows written before that exclusion persist
+        // until the next full index.)
+        const out = [];
+        const seen = new Set();
+        candidates.sort((a, b) => b.matchedWords.size - a.matchedWords.size || a.name.length - b.name.length);
+        for (const candidate of candidates) {
+            if (out.length >= limit)
+                break;
+            if (seen.has(candidate.name))
+                continue;
+            seen.add(candidate.name);
+            const nodes = this.queries.getNodesByName(candidate.name);
+            if (nodes.length === 0)
+                continue; // orphaned vocab row — name no longer exists
+            const rep = nodes.find((n) => n.kind !== 'file' && n.kind !== 'import');
+            if (!rep)
+                continue; // no real definition — don't surface an import/file as one
+            out.push({
+                name: candidate.name,
+                kind: rep.kind,
+                filePath: rep.filePath,
+                startLine: rep.startLine ?? 0,
+                matchedWords: [...candidate.matchedWords].sort(),
+            });
+        }
+        return out;
+    }
+    /** A single word ("state") can match hundreds of names in a big repo — that
+     *  is noise, not signal. Ceiling for the single-word tier; co-occurrence is
+     *  exempt because two words on one name is already discriminative. */
+    static SEGMENT_RARITY_CEILING = 25;
+    /** Which of the prompt's original words match `name`'s segments (via
+     *  variants). Segments are recomputed in JS — a name-keyed vocab lookup
+     *  would scan the (segment, name) primary key. */
+    wordsMatchingName(name, variantToWord) {
+        const segments = new Set((0, identifier_segments_1.splitIdentifierSegments)(name));
+        const matched = new Set();
+        for (const [variant, word] of variantToWord) {
+            if (segments.has(variant))
+                matched.add(word);
+        }
+        return matched;
+    }
+    /**
+     * One-shot upgrade heal for callers that open the graph WITHOUT syncing —
+     * concretely the prompt hook, whose MEDIUM tier reads the segment
+     * vocabulary: a database migrated from before the vocab table existed
+     * starts with it empty, and the only other backfill lives inside `sync()`,
+     * which such callers never run (#1142). Returns true when the vocab is
+     * usable (already populated — the overwhelmingly common one-SELECT case —
+     * or healed here); false when it isn't (empty graph, or another process
+     * holds the index lock — that process's own sync heals it).
+     */
+    async healSegmentVocabIfEmpty() {
+        const empty = (() => {
+            try {
+                return this.queries.isNameSegmentVocabEmpty();
+            }
+            catch {
+                return false;
+            }
+        })();
+        if (!empty)
+            return true;
+        if (this.queries.getNodeAndEdgeCount().nodes === 0)
+            return false;
+        return this.indexMutex.withLock(async () => {
+            try {
+                this.fileLock.acquire();
+            }
+            catch {
+                return false; // an index/sync is running — it backfills the vocab itself
+            }
+            try {
+                if (!this.queries.isNameSegmentVocabEmpty())
+                    return true; // raced: healed meanwhile
+                await this.rebuildNameSegmentVocab();
+                return true;
+            }
+            finally {
+                this.fileLock.release();
+            }
+        });
+    }
+    /**
+     * Rebuild the segment vocabulary from the current graph, batched and
+     * yielding — the upgrade-heal path for indexes built before the vocab table
+     * existed. Runs inside the index mutex/lock (sync and
+     * healSegmentVocabIfEmpty hold them).
+     */
+    async rebuildNameSegmentVocab() {
+        const maybeYield = (0, cooperative_yield_1.createYielder)();
+        const BATCH = 2000;
+        for (let offset = 0;; offset += BATCH) {
+            const names = this.queries.getDistinctNodeNames(BATCH, offset);
+            if (names.length === 0)
+                break;
+            this.queries.insertNameSegmentsBatch(names);
+            await maybeYield();
+        }
+    }
+    /**
+     * Normalized project-name tokens (go.mod / package.json / repo dir) used to
+     * down-weight the non-discriminative project name in search ranking (#720).
+     * Exposed so explore can exclude it from the PascalCase type-disambiguation
+     * bias, which would otherwise pull overloaded tokens toward whichever stack
+     * embeds the project name.
+     */
+    getProjectNameTokens() {
+        return this.queries.getProjectNameTokens();
+    }
+    /**
+     * Find the project's "primary route file" — the file with the densest
+     * concentration of framework-emitted `route` nodes (≥3 routes, ≥30%
+     * of all non-test routes). Used to inline the routing config in
+     * `codegraph_explore` responses on small realworld template repos
+     * (rails-realworld, laravel-realworld, drupal-admintoolbar, …) where
+     * Glob+Read of `routes.rb`/`urls.py`/etc. otherwise beats codegraph.
+     */
+    getTopRouteFile() {
+        return this.queries.getTopRouteFile();
+    }
+    /**
+     * Build a URL → handler routing manifest from the index. Each entry
+     * pairs a route node (URL + method) with its handler function/method
+     * via the `references` edge that framework resolvers emit. Returns
+     * null when fewer than 3 valid (non-test) routes exist.
+     */
+    getRoutingManifest(limit) {
+        return this.queries.getRoutingManifest(limit);
+    }
     // ===========================================================================
     // Edge Operations
     // ===========================================================================