homegraph 1.5.1 → 1.5.2

package/dist/db/schema.sql

@@ -1,203 +1,203 @@
--- HomeGraph SQLite Schema
--- Version 1
-
--- Schema version tracking
-CREATE TABLE IF NOT EXISTS schema_versions (
-    version INTEGER PRIMARY KEY,
-    applied_at INTEGER NOT NULL,
-    description TEXT
-);
-
--- Insert initial version
-INSERT INTO schema_versions (version, applied_at, description)
-VALUES (1, strftime('%s', 'now') * 1000, 'Initial schema');
-
--- =============================================================================
--- Core Tables
--- =============================================================================
-
--- Nodes: Code symbols (functions, classes, variables, etc.)
-CREATE TABLE IF NOT EXISTS nodes (
-    id TEXT PRIMARY KEY,
-    kind TEXT NOT NULL,
-    name TEXT NOT NULL,
-    qualified_name TEXT NOT NULL,
-    file_path TEXT NOT NULL,
-    language TEXT NOT NULL,
-    start_line INTEGER NOT NULL,
-    end_line INTEGER NOT NULL,
-    start_column INTEGER NOT NULL,
-    end_column INTEGER NOT NULL,
-    docstring TEXT,
-    signature TEXT,
-    visibility TEXT,
-    is_exported INTEGER DEFAULT 0,
-    is_async INTEGER DEFAULT 0,
-    is_static INTEGER DEFAULT 0,
-    is_abstract INTEGER DEFAULT 0,
-    decorators TEXT, -- JSON array
-    type_parameters TEXT, -- JSON array
-    return_type TEXT, -- normalized return/result type name (e.g. C++ method return, for receiver-type inference)
-    updated_at INTEGER NOT NULL
-);
-
--- Edges: Relationships between nodes
-CREATE TABLE IF NOT EXISTS edges (
-    id INTEGER PRIMARY KEY AUTOINCREMENT,
-    source TEXT NOT NULL,
-    target TEXT NOT NULL,
-    kind TEXT NOT NULL,
-    metadata TEXT, -- JSON object
-    line INTEGER,
-    col INTEGER,
-    provenance TEXT DEFAULT NULL,
-    FOREIGN KEY (source) REFERENCES nodes(id) ON DELETE CASCADE,
-    FOREIGN KEY (target) REFERENCES nodes(id) ON DELETE CASCADE
-);
-
--- Files: Tracked source files
-CREATE TABLE IF NOT EXISTS files (
-    path TEXT PRIMARY KEY,
-    content_hash TEXT NOT NULL,
-    language TEXT NOT NULL,
-    size INTEGER NOT NULL,
-    modified_at INTEGER NOT NULL,
-    indexed_at INTEGER NOT NULL,
-    node_count INTEGER DEFAULT 0,
-    errors TEXT -- JSON array
-);
-
--- Unresolved References: References that need resolution after full indexing.
--- status lifecycle: rows are inserted 'pending' by extraction; a completed
--- resolution pass either deletes a row (resolved) or marks it 'failed'
--- (attempted, no match — kept so a later sync can retry it when a changed
--- file introduces a symbol that could satisfy it, #1240). name_tail is the
--- last segment of reference_name ('util.greet' → 'greet'), written when a
--- row is marked failed, so the retry lookup matches new node names against
--- dotted refs too. Rows follow their from_node via ON DELETE CASCADE, so
--- re-extracting or deleting a file clears its stale rows in any status.
-CREATE TABLE IF NOT EXISTS unresolved_refs (
-    id INTEGER PRIMARY KEY AUTOINCREMENT,
-    from_node_id TEXT NOT NULL,
-    reference_name TEXT NOT NULL,
-    reference_kind TEXT NOT NULL,
-    line INTEGER NOT NULL,
-    col INTEGER NOT NULL,
-    candidates TEXT, -- JSON array
-    file_path TEXT NOT NULL DEFAULT '',
-    language TEXT NOT NULL DEFAULT 'unknown',
-    status TEXT NOT NULL DEFAULT 'pending',
-    name_tail TEXT NOT NULL DEFAULT '',
-    FOREIGN KEY (from_node_id) REFERENCES nodes(id) ON DELETE CASCADE
-);
-
--- =============================================================================
--- Indexes for Query Performance
--- =============================================================================
-
--- Node indexes
-CREATE INDEX IF NOT EXISTS idx_nodes_kind ON nodes(kind);
-CREATE INDEX IF NOT EXISTS idx_nodes_name ON nodes(name);
-CREATE INDEX IF NOT EXISTS idx_nodes_qualified_name ON nodes(qualified_name);
-CREATE INDEX IF NOT EXISTS idx_nodes_file_path ON nodes(file_path);
-CREATE INDEX IF NOT EXISTS idx_nodes_language ON nodes(language);
-CREATE INDEX IF NOT EXISTS idx_nodes_file_line ON nodes(file_path, start_line);
-CREATE INDEX IF NOT EXISTS idx_nodes_lower_name ON nodes(lower(name));
-
--- Full-text search index on node names, docstrings, and signatures
-CREATE VIRTUAL TABLE IF NOT EXISTS nodes_fts USING fts5(
-    id,
-    name,
-    qualified_name,
-    docstring,
-    signature,
-    content='nodes',
-    content_rowid='rowid'
-);
-
--- Triggers to keep FTS index in sync
-CREATE TRIGGER IF NOT EXISTS nodes_ai AFTER INSERT ON nodes BEGIN
-    INSERT INTO nodes_fts(rowid, id, name, qualified_name, docstring, signature)
-    VALUES (NEW.rowid, NEW.id, NEW.name, NEW.qualified_name, NEW.docstring, NEW.signature);
-END;
-
-CREATE TRIGGER IF NOT EXISTS nodes_ad AFTER DELETE ON nodes BEGIN
-    INSERT INTO nodes_fts(nodes_fts, rowid, id, name, qualified_name, docstring, signature)
-    VALUES ('delete', OLD.rowid, OLD.id, OLD.name, OLD.qualified_name, OLD.docstring, OLD.signature);
-END;
-
-CREATE TRIGGER IF NOT EXISTS nodes_au AFTER UPDATE ON nodes BEGIN
-    INSERT INTO nodes_fts(nodes_fts, rowid, id, name, qualified_name, docstring, signature)
-    VALUES ('delete', OLD.rowid, OLD.id, OLD.name, OLD.qualified_name, OLD.docstring, OLD.signature);
-    INSERT INTO nodes_fts(rowid, id, name, qualified_name, docstring, signature)
-    VALUES (NEW.rowid, NEW.id, NEW.name, NEW.qualified_name, NEW.docstring, NEW.signature);
-END;
-
--- Prose-word → symbol-name lookup for the prompt hook's graph-derived gate.
--- One row per (segment, name): segment is a lowercased word of a symbol name
--- ("OrderStateMachine" → order, state, machine — see identifier-segments.ts),
--- which lets natural-language prompt words be verified against the graph in
--- any language whose technical nouns are Latin script. File nodes are
--- excluded — a file's basename duplicates the symbols inside it and skews the
--- singleton-vs-cluster rarity statistics. FTS can't serve this lookup (its
--- tokenizer keeps camelCase names as single tokens), so segments are
--- materialized on the node write path.
--- Deletions leave orphan rows ON PURPOSE: rows are PROPOSALS, always
--- re-verified against nodes before being surfaced (HomeGraph.getSegmentMatches),
--- and a full index clears the table at its start. Populated lazily on old
--- databases (empty until the next index/sync heals it).
-CREATE TABLE IF NOT EXISTS name_segment_vocab (
-    segment TEXT NOT NULL,
-    name TEXT NOT NULL,
-    PRIMARY KEY (segment, name)
-) WITHOUT ROWID;
-
--- Edge indexes.
--- idx_edges_source / idx_edges_target are intentionally omitted —
--- the (source, kind) and (target, kind) composites below cover the
--- corresponding source-only / target-only lookups via SQLite's
--- left-prefix scan, so the narrow indexes are dead weight on writes.
--- Migration v4 drops them on existing databases.
-CREATE INDEX IF NOT EXISTS idx_edges_kind ON edges(kind);
-CREATE INDEX IF NOT EXISTS idx_edges_source_kind ON edges(source, kind);
-CREATE INDEX IF NOT EXISTS idx_edges_target_kind ON edges(target, kind);
-
--- Edge identity uniqueness. An edge IS uniquely (source, target, kind, line,
--- col); insertEdge uses `INSERT OR IGNORE`, but without something UNIQUE to
--- conflict on it behaved like a plain INSERT, so two passes emitting the same
--- edge produced byte-identical duplicate rows that inflated counts and flowed
--- into callers/impact (#1034). IFNULL folds the nullable line/col so
--- coordinate-less edges (synthesized / file-level) dedup too — SQLite treats
--- each NULL as distinct otherwise. Migration v6 dedups existing rows + adds
--- this on older databases.
-CREATE UNIQUE INDEX IF NOT EXISTS idx_edges_identity
-  ON edges(source, target, kind, IFNULL(line, -1), IFNULL(col, -1));
-
--- File indexes
-CREATE INDEX IF NOT EXISTS idx_files_language ON files(language);
-CREATE INDEX IF NOT EXISTS idx_files_modified_at ON files(modified_at);
-
--- Unresolved refs indexes
-CREATE INDEX IF NOT EXISTS idx_unresolved_from_node ON unresolved_refs(from_node_id);
-CREATE INDEX IF NOT EXISTS idx_unresolved_name ON unresolved_refs(reference_name);
-CREATE INDEX IF NOT EXISTS idx_unresolved_file_path ON unresolved_refs(file_path);
-CREATE INDEX IF NOT EXISTS idx_unresolved_from_name ON unresolved_refs(from_node_id, reference_name);
-CREATE INDEX IF NOT EXISTS idx_unresolved_status ON unresolved_refs(status);
-CREATE INDEX IF NOT EXISTS idx_unresolved_failed_tail ON unresolved_refs(name_tail) WHERE status = 'failed';
-CREATE INDEX IF NOT EXISTS idx_edges_provenance ON edges(provenance);
-
--- Project metadata for version/provenance tracking
-CREATE TABLE IF NOT EXISTS project_metadata (
-    key TEXT PRIMARY KEY,
-    value TEXT NOT NULL,
-    updated_at INTEGER NOT NULL
-);
-
--- MCP tool response cache (invalidated wholesale on index stamp change)
-CREATE TABLE IF NOT EXISTS mcp_query_cache (
-    cache_key   TEXT PRIMARY KEY,
-    tool        TEXT NOT NULL,
-    response    TEXT NOT NULL,
-    created_at  INTEGER NOT NULL
-);
-CREATE INDEX IF NOT EXISTS idx_mcp_query_cache_tool ON mcp_query_cache(tool);
+-- HomeGraph SQLite Schema
+-- Version 1
+
+-- Schema version tracking
+CREATE TABLE IF NOT EXISTS schema_versions (
+    version INTEGER PRIMARY KEY,
+    applied_at INTEGER NOT NULL,
+    description TEXT
+);
+
+-- Insert initial version
+INSERT INTO schema_versions (version, applied_at, description)
+VALUES (1, strftime('%s', 'now') * 1000, 'Initial schema');
+
+-- =============================================================================
+-- Core Tables
+-- =============================================================================
+
+-- Nodes: Code symbols (functions, classes, variables, etc.)
+CREATE TABLE IF NOT EXISTS nodes (
+    id TEXT PRIMARY KEY,
+    kind TEXT NOT NULL,
+    name TEXT NOT NULL,
+    qualified_name TEXT NOT NULL,
+    file_path TEXT NOT NULL,
+    language TEXT NOT NULL,
+    start_line INTEGER NOT NULL,
+    end_line INTEGER NOT NULL,
+    start_column INTEGER NOT NULL,
+    end_column INTEGER NOT NULL,
+    docstring TEXT,
+    signature TEXT,
+    visibility TEXT,
+    is_exported INTEGER DEFAULT 0,
+    is_async INTEGER DEFAULT 0,
+    is_static INTEGER DEFAULT 0,
+    is_abstract INTEGER DEFAULT 0,
+    decorators TEXT, -- JSON array
+    type_parameters TEXT, -- JSON array
+    return_type TEXT, -- normalized return/result type name (e.g. C++ method return, for receiver-type inference)
+    updated_at INTEGER NOT NULL
+);
+
+-- Edges: Relationships between nodes
+CREATE TABLE IF NOT EXISTS edges (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    source TEXT NOT NULL,
+    target TEXT NOT NULL,
+    kind TEXT NOT NULL,
+    metadata TEXT, -- JSON object
+    line INTEGER,
+    col INTEGER,
+    provenance TEXT DEFAULT NULL,
+    FOREIGN KEY (source) REFERENCES nodes(id) ON DELETE CASCADE,
+    FOREIGN KEY (target) REFERENCES nodes(id) ON DELETE CASCADE
+);
+
+-- Files: Tracked source files
+CREATE TABLE IF NOT EXISTS files (
+    path TEXT PRIMARY KEY,
+    content_hash TEXT NOT NULL,
+    language TEXT NOT NULL,
+    size INTEGER NOT NULL,
+    modified_at INTEGER NOT NULL,
+    indexed_at INTEGER NOT NULL,
+    node_count INTEGER DEFAULT 0,
+    errors TEXT -- JSON array
+);
+
+-- Unresolved References: References that need resolution after full indexing.
+-- status lifecycle: rows are inserted 'pending' by extraction; a completed
+-- resolution pass either deletes a row (resolved) or marks it 'failed'
+-- (attempted, no match — kept so a later sync can retry it when a changed
+-- file introduces a symbol that could satisfy it, #1240). name_tail is the
+-- last segment of reference_name ('util.greet' → 'greet'), written when a
+-- row is marked failed, so the retry lookup matches new node names against
+-- dotted refs too. Rows follow their from_node via ON DELETE CASCADE, so
+-- re-extracting or deleting a file clears its stale rows in any status.
+CREATE TABLE IF NOT EXISTS unresolved_refs (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    from_node_id TEXT NOT NULL,
+    reference_name TEXT NOT NULL,
+    reference_kind TEXT NOT NULL,
+    line INTEGER NOT NULL,
+    col INTEGER NOT NULL,
+    candidates TEXT, -- JSON array
+    file_path TEXT NOT NULL DEFAULT '',
+    language TEXT NOT NULL DEFAULT 'unknown',
+    status TEXT NOT NULL DEFAULT 'pending',
+    name_tail TEXT NOT NULL DEFAULT '',
+    FOREIGN KEY (from_node_id) REFERENCES nodes(id) ON DELETE CASCADE
+);
+
+-- =============================================================================
+-- Indexes for Query Performance
+-- =============================================================================
+
+-- Node indexes
+CREATE INDEX IF NOT EXISTS idx_nodes_kind ON nodes(kind);
+CREATE INDEX IF NOT EXISTS idx_nodes_name ON nodes(name);
+CREATE INDEX IF NOT EXISTS idx_nodes_qualified_name ON nodes(qualified_name);
+CREATE INDEX IF NOT EXISTS idx_nodes_file_path ON nodes(file_path);
+CREATE INDEX IF NOT EXISTS idx_nodes_language ON nodes(language);
+CREATE INDEX IF NOT EXISTS idx_nodes_file_line ON nodes(file_path, start_line);
+CREATE INDEX IF NOT EXISTS idx_nodes_lower_name ON nodes(lower(name));
+
+-- Full-text search index on node names, docstrings, and signatures
+CREATE VIRTUAL TABLE IF NOT EXISTS nodes_fts USING fts5(
+    id,
+    name,
+    qualified_name,
+    docstring,
+    signature,
+    content='nodes',
+    content_rowid='rowid'
+);
+
+-- Triggers to keep FTS index in sync
+CREATE TRIGGER IF NOT EXISTS nodes_ai AFTER INSERT ON nodes BEGIN
+    INSERT INTO nodes_fts(rowid, id, name, qualified_name, docstring, signature)
+    VALUES (NEW.rowid, NEW.id, NEW.name, NEW.qualified_name, NEW.docstring, NEW.signature);
+END;
+
+CREATE TRIGGER IF NOT EXISTS nodes_ad AFTER DELETE ON nodes BEGIN
+    INSERT INTO nodes_fts(nodes_fts, rowid, id, name, qualified_name, docstring, signature)
+    VALUES ('delete', OLD.rowid, OLD.id, OLD.name, OLD.qualified_name, OLD.docstring, OLD.signature);
+END;
+
+CREATE TRIGGER IF NOT EXISTS nodes_au AFTER UPDATE ON nodes BEGIN
+    INSERT INTO nodes_fts(nodes_fts, rowid, id, name, qualified_name, docstring, signature)
+    VALUES ('delete', OLD.rowid, OLD.id, OLD.name, OLD.qualified_name, OLD.docstring, OLD.signature);
+    INSERT INTO nodes_fts(rowid, id, name, qualified_name, docstring, signature)
+    VALUES (NEW.rowid, NEW.id, NEW.name, NEW.qualified_name, NEW.docstring, NEW.signature);
+END;
+
+-- Prose-word → symbol-name lookup for the prompt hook's graph-derived gate.
+-- One row per (segment, name): segment is a lowercased word of a symbol name
+-- ("OrderStateMachine" → order, state, machine — see identifier-segments.ts),
+-- which lets natural-language prompt words be verified against the graph in
+-- any language whose technical nouns are Latin script. File nodes are
+-- excluded — a file's basename duplicates the symbols inside it and skews the
+-- singleton-vs-cluster rarity statistics. FTS can't serve this lookup (its
+-- tokenizer keeps camelCase names as single tokens), so segments are
+-- materialized on the node write path.
+-- Deletions leave orphan rows ON PURPOSE: rows are PROPOSALS, always
+-- re-verified against nodes before being surfaced (HomeGraph.getSegmentMatches),
+-- and a full index clears the table at its start. Populated lazily on old
+-- databases (empty until the next index/sync heals it).
+CREATE TABLE IF NOT EXISTS name_segment_vocab (
+    segment TEXT NOT NULL,
+    name TEXT NOT NULL,
+    PRIMARY KEY (segment, name)
+) WITHOUT ROWID;
+
+-- Edge indexes.
+-- idx_edges_source / idx_edges_target are intentionally omitted —
+-- the (source, kind) and (target, kind) composites below cover the
+-- corresponding source-only / target-only lookups via SQLite's
+-- left-prefix scan, so the narrow indexes are dead weight on writes.
+-- Migration v4 drops them on existing databases.
+CREATE INDEX IF NOT EXISTS idx_edges_kind ON edges(kind);
+CREATE INDEX IF NOT EXISTS idx_edges_source_kind ON edges(source, kind);
+CREATE INDEX IF NOT EXISTS idx_edges_target_kind ON edges(target, kind);
+
+-- Edge identity uniqueness. An edge IS uniquely (source, target, kind, line,
+-- col); insertEdge uses `INSERT OR IGNORE`, but without something UNIQUE to
+-- conflict on it behaved like a plain INSERT, so two passes emitting the same
+-- edge produced byte-identical duplicate rows that inflated counts and flowed
+-- into callers/impact (#1034). IFNULL folds the nullable line/col so
+-- coordinate-less edges (synthesized / file-level) dedup too — SQLite treats
+-- each NULL as distinct otherwise. Migration v6 dedups existing rows + adds
+-- this on older databases.
+CREATE UNIQUE INDEX IF NOT EXISTS idx_edges_identity
+  ON edges(source, target, kind, IFNULL(line, -1), IFNULL(col, -1));
+
+-- File indexes
+CREATE INDEX IF NOT EXISTS idx_files_language ON files(language);
+CREATE INDEX IF NOT EXISTS idx_files_modified_at ON files(modified_at);
+
+-- Unresolved refs indexes
+CREATE INDEX IF NOT EXISTS idx_unresolved_from_node ON unresolved_refs(from_node_id);
+CREATE INDEX IF NOT EXISTS idx_unresolved_name ON unresolved_refs(reference_name);
+CREATE INDEX IF NOT EXISTS idx_unresolved_file_path ON unresolved_refs(file_path);
+CREATE INDEX IF NOT EXISTS idx_unresolved_from_name ON unresolved_refs(from_node_id, reference_name);
+CREATE INDEX IF NOT EXISTS idx_unresolved_status ON unresolved_refs(status);
+CREATE INDEX IF NOT EXISTS idx_unresolved_failed_tail ON unresolved_refs(name_tail) WHERE status = 'failed';
+CREATE INDEX IF NOT EXISTS idx_edges_provenance ON edges(provenance);
+
+-- Project metadata for version/provenance tracking
+CREATE TABLE IF NOT EXISTS project_metadata (
+    key TEXT PRIMARY KEY,
+    value TEXT NOT NULL,
+    updated_at INTEGER NOT NULL
+);
+
+-- MCP tool response cache (invalidated wholesale on index stamp change)
+CREATE TABLE IF NOT EXISTS mcp_query_cache (
+    cache_key   TEXT PRIMARY KEY,
+    tool        TEXT NOT NULL,
+    response    TEXT NOT NULL,
+    created_at  INTEGER NOT NULL
+);
+CREATE INDEX IF NOT EXISTS idx_mcp_query_cache_tool ON mcp_query_cache(tool);

package/dist/directory.js

@@ -599,11 +599,11 @@ function planFrontload(cwd, prompt) {
  * explicit allowlist that never listed `daemon.pid` or the socket, so those
  * runtime files were silently committed.
  */
-const GITIGNORE_CONTENT = `# HomeGraph data files — local to each machine, not for committing.
-# Ignore everything in .homegraph/ except this file itself, so transient
-# files (the database, daemon.pid, sockets, logs) never show up in git.
-*
-!.gitignore
+const GITIGNORE_CONTENT = `# HomeGraph data files — local to each machine, not for committing.
+# Ignore everything in .homegraph/ except this file itself, so transient
+# files (the database, daemon.pid, sockets, logs) never show up in git.
+*
+!.gitignore
 `;
 /** Header line that prefixes every .gitignore HomeGraph has auto-generated. */
 const GITIGNORE_MARKER = '# HomeGraph data files';

package/dist/extraction/index.d.ts

@@ -12,7 +12,7 @@ export { buildDefaultIgnore } from './default-ignore';
  * Progress callback for indexing operations
  */
 export interface IndexProgress {
-    phase: 'scanning' | 'parsing' | 'arkts-batch' | 'storing' | 'resolving' | 'linking';
+    phase: 'scanning' | 'parsing' | 'arkts-batch' | 'ohos-api' | 'storing' | 'resolving' | 'linking';
     current: number;
     total: number;
     currentFile?: string;

package/dist/extraction/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/extraction/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,KAAK,EAAE,MAAM,IAAI,CAAC;AAMzB,OAAO,EAGL,gBAAgB,EAChB,eAAe,EAKhB,MAAM,UAAU,CAAC;AAClB,OAAO,EAAE,YAAY,EAAE,MAAM,eAAe,CAAC;AAU7C,OAAe,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAGxC,OAAO,EAAE,kBAAkB,EAAE,MAAM,kBAAkB,CAAC;AAgDtD;;GAEG;AACH,MAAM,WAAW,aAAa;IAC5B,KAAK,EAAE,UAAU,GAAG,SAAS,GAAG,aAAa,GAAG,SAAS,GAAG,WAAW,GAAG,SAAS,CAAC;IACpF,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,8DAA8D;IAC9D,QAAQ,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;CAChC;AAED;;GAEG;AACH,MAAM,WAAW,WAAW;IAC1B,OAAO,EAAE,OAAO,CAAC;IACjB,YAAY,EAAE,MAAM,CAAC;IACrB,YAAY,EAAE,MAAM,CAAC;IACrB,YAAY,EAAE,MAAM,CAAC;IACrB,4EAA4E;IAC5E,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,YAAY,EAAE,MAAM,CAAC;IACrB,YAAY,EAAE,MAAM,CAAC;IACrB,MAAM,EAAE,eAAe,EAAE,CAAC;IAC1B,UAAU,EAAE,MAAM,CAAC;CACpB;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,YAAY,EAAE,MAAM,CAAC;IACrB,UAAU,EAAE,MAAM,CAAC;IACnB,aAAa,EAAE,MAAM,CAAC;IACtB,YAAY,EAAE,MAAM,CAAC;IACrB,YAAY,EAAE,MAAM,CAAC;IACrB,UAAU,EAAE,MAAM,CAAC;IACnB,gBAAgB,CAAC,EAAE,MAAM,EAAE,CAAC;CAC7B;AAED;;GAEG;AACH,wBAAgB,WAAW,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,CAEnD;AAyTD;;;;;;;;;;GAUG;AACH,qBAAa,WAAW;IAIpB,OAAO,CAAC,WAAW;IAEnB;;;;OAIG;IACH,OAAO,CAAC,OAAO;IACf;;;;;;;;OAQG;IACH,OAAO,CAAC,OAAO;IACf,OAAO,CAAC,YAAY;IArBtB,OAAO,CAAC,QAAQ,CAA2C;IAC3D,OAAO,CAAC,QAAQ,CAAgC;gBAEtC,WAAW,EAAE,MAAM,EAC3B,QAAQ,EAAE,KAAK,CAAC;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,CAAC;IAClD;;;;OAIG;IACK,OAAO,GAAE,MAAM,GAAG,IAAW;IACrC;;;;;;;;OAQG;IACK,OAAO,GAAE,MAAM,GAAG,IAAW,EAC7B,YAAY,GAAE,MAAM,EAAO;IAMrC,OAAO,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO;CAiC9B;AAED;;;;GAIG;AACH,wBAAgB,gBAAgB,CAAC,OAAO,EAAE,MAAM,EAAE,aAAa,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,GAAG,WAAW,CAU/F;AAoCD;;;;;;;;GAQG;AACH,wBAAgB,yBAAyB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,EAAE,CAgDnE;AASD;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,yBAAyB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,EAAE,CAkBnE;AAiXD;;;;;;GAMG;AACH,wBAAgB,aAAa,CAC3B,OAAO,EAAE,MAAM,EACf,UAAU,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,KAAK,IAAI,GACnD,MAAM,EAAE,CAqBV;AAED;;;GAGG;AACH,wBAAsB,kBAAkB,CACtC,OAAO,EAAE,MAAM,EACf,UAAU,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,KAAK,IAAI,GACnD,OAAO,CAAC,MAAM,EAAE,CAAC,CAuBnB;AA+KD;;GAEG;AACH,qBAAa,sBAAsB;IACjC,OAAO,CAAC,OAAO,CAAS;IACxB,OAAO,CAAC,OAAO,CAAe;IAC9B;;;;;OAKG;IACH,OAAO,CAAC,sBAAsB,CAAyB;gBAE3C,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,YAAY;IAKlD;;;;;OAKG;IACH,OAAO,CAAC,qBAAqB;IAkD7B;;;;OAIG;IACH,OAAO,CAAC,wBAAwB;IAQhC;;OAEG;IACG,QAAQ,CACZ,UAAU,CAAC,EAAE,CAAC,QAAQ,EAAE,aAAa,KAAK,IAAI,EAC9C,MAAM,CAAC,EAAE,WAAW,EACpB,OAAO,CAAC,EAAE,OAAO,EACjB,eAAe,CAAC,EAAE,MAAM,OAAO,CAAC,IAAI,CAAC,GAAG,IAAI,EAC5C,eAAe,CAAC,EAAE;QAAE,MAAM,EAAE,MAAM,CAAC;QAAC,QAAQ,EAAE,OAAO,CAAA;KAAE,GAAG,IAAI,GAC7D,OAAO,CAAC,WAAW,CAAC;IA6hBvB;;OAEG;IACG,UAAU,CAAC,SAAS,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,WAAW,CAAC;IA4C3D;;OAEG;IACG,SAAS,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,gBAAgB,CAAC;IAwChE;;;OAGG;IACG,oBAAoB,CACxB,YAAY,EAAE,MAAM,EACpB,OAAO,EAAE,MAAM,EACf,KAAK,EAAE,EAAE,CAAC,KAAK,GACd,OAAO,CAAC,gBAAgB,CAAC;IAmE5B;;OAEG;YACW,qBAAqB;IAiGnC,OAAO,CAAC,eAAe;IAoBvB,OAAO,CAAC,qBAAqB;IAe7B,OAAO,CAAC,sBAAsB;IA2B9B;;;;;;;OAOG;IACG,IAAI,CACR,UAAU,CAAC,EAAE,CAAC,QAAQ,EAAE,aAAa,KAAK,IAAI,EAC9C,WAAW,CAAC,EAAE,MAAM,EAAE,GACrB,OAAO,CAAC,UAAU,CAAC;IA+MtB;;;OAGG;IACH,eAAe,IAAI;QAAE,KAAK,EAAE,MAAM,EAAE,CAAC;QAAC,QAAQ,EAAE,MAAM,EAAE,CAAC;QAAC,OAAO,EAAE,MAAM,EAAE,CAAA;KAAE;CAwF9E;AAGD,OAAO,EAAE,iBAAiB,EAAE,MAAM,eAAe,CAAC;AAClD,OAAO,EAAE,cAAc,EAAE,YAAY,EAAE,mBAAmB,EAAE,eAAe,EAAE,qBAAqB,EAAE,YAAY,EAAE,wBAAwB,EAAE,eAAe,EAAE,MAAM,YAAY,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/extraction/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,KAAK,EAAE,MAAM,IAAI,CAAC;AAMzB,OAAO,EAGL,gBAAgB,EAChB,eAAe,EAKhB,MAAM,UAAU,CAAC;AAClB,OAAO,EAAE,YAAY,EAAE,MAAM,eAAe,CAAC;AAU7C,OAAe,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAGxC,OAAO,EAAE,kBAAkB,EAAE,MAAM,kBAAkB,CAAC;AAkDtD;;GAEG;AACH,MAAM,WAAW,aAAa;IAC5B,KAAK,EAAE,UAAU,GAAG,SAAS,GAAG,aAAa,GAAG,UAAU,GAAG,SAAS,GAAG,WAAW,GAAG,SAAS,CAAC;IACjG,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,8DAA8D;IAC9D,QAAQ,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;CAChC;AAED;;GAEG;AACH,MAAM,WAAW,WAAW;IAC1B,OAAO,EAAE,OAAO,CAAC;IACjB,YAAY,EAAE,MAAM,CAAC;IACrB,YAAY,EAAE,MAAM,CAAC;IACrB,YAAY,EAAE,MAAM,CAAC;IACrB,4EAA4E;IAC5E,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,YAAY,EAAE,MAAM,CAAC;IACrB,YAAY,EAAE,MAAM,CAAC;IACrB,MAAM,EAAE,eAAe,EAAE,CAAC;IAC1B,UAAU,EAAE,MAAM,CAAC;CACpB;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,YAAY,EAAE,MAAM,CAAC;IACrB,UAAU,EAAE,MAAM,CAAC;IACnB,aAAa,EAAE,MAAM,CAAC;IACtB,YAAY,EAAE,MAAM,CAAC;IACrB,YAAY,EAAE,MAAM,CAAC;IACrB,UAAU,EAAE,MAAM,CAAC;IACnB,gBAAgB,CAAC,EAAE,MAAM,EAAE,CAAC;CAC7B;AAED;;GAEG;AACH,wBAAgB,WAAW,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,CAEnD;AAyTD;;;;;;;;;;GAUG;AACH,qBAAa,WAAW;IAIpB,OAAO,CAAC,WAAW;IAEnB;;;;OAIG;IACH,OAAO,CAAC,OAAO;IACf;;;;;;;;OAQG;IACH,OAAO,CAAC,OAAO;IACf,OAAO,CAAC,YAAY;IArBtB,OAAO,CAAC,QAAQ,CAA2C;IAC3D,OAAO,CAAC,QAAQ,CAAgC;gBAEtC,WAAW,EAAE,MAAM,EAC3B,QAAQ,EAAE,KAAK,CAAC;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,CAAC;IAClD;;;;OAIG;IACK,OAAO,GAAE,MAAM,GAAG,IAAW;IACrC;;;;;;;;OAQG;IACK,OAAO,GAAE,MAAM,GAAG,IAAW,EAC7B,YAAY,GAAE,MAAM,EAAO;IAMrC,OAAO,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO;CAiC9B;AAED;;;;GAIG;AACH,wBAAgB,gBAAgB,CAAC,OAAO,EAAE,MAAM,EAAE,aAAa,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,GAAG,WAAW,CAU/F;AAoCD;;;;;;;;GAQG;AACH,wBAAgB,yBAAyB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,EAAE,CAgDnE;AASD;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,yBAAyB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,EAAE,CAkBnE;AAiXD;;;;;;GAMG;AACH,wBAAgB,aAAa,CAC3B,OAAO,EAAE,MAAM,EACf,UAAU,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,KAAK,IAAI,GACnD,MAAM,EAAE,CAqBV;AAED;;;GAGG;AACH,wBAAsB,kBAAkB,CACtC,OAAO,EAAE,MAAM,EACf,UAAU,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,KAAK,IAAI,GACnD,OAAO,CAAC,MAAM,EAAE,CAAC,CAuBnB;AA+KD;;GAEG;AACH,qBAAa,sBAAsB;IACjC,OAAO,CAAC,OAAO,CAAS;IACxB,OAAO,CAAC,OAAO,CAAe;IAC9B;;;;;OAKG;IACH,OAAO,CAAC,sBAAsB,CAAyB;gBAE3C,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,YAAY;IAKlD;;;;;OAKG;IACH,OAAO,CAAC,qBAAqB;IAkD7B;;;;OAIG;IACH,OAAO,CAAC,wBAAwB;IAQhC;;OAEG;IACG,QAAQ,CACZ,UAAU,CAAC,EAAE,CAAC,QAAQ,EAAE,aAAa,KAAK,IAAI,EAC9C,MAAM,CAAC,EAAE,WAAW,EACpB,OAAO,CAAC,EAAE,OAAO,EACjB,eAAe,CAAC,EAAE,MAAM,OAAO,CAAC,IAAI,CAAC,GAAG,IAAI,EAC5C,eAAe,CAAC,EAAE;QAAE,MAAM,EAAE,MAAM,CAAC;QAAC,QAAQ,EAAE,OAAO,CAAA;KAAE,GAAG,IAAI,GAC7D,OAAO,CAAC,WAAW,CAAC;IA+iBvB;;OAEG;IACG,UAAU,CAAC,SAAS,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,WAAW,CAAC;IA4C3D;;OAEG;IACG,SAAS,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,gBAAgB,CAAC;IAwChE;;;OAGG;IACG,oBAAoB,CACxB,YAAY,EAAE,MAAM,EACpB,OAAO,EAAE,MAAM,EACf,KAAK,EAAE,EAAE,CAAC,KAAK,GACd,OAAO,CAAC,gBAAgB,CAAC;IAmE5B;;OAEG;YACW,qBAAqB;IAiGnC,OAAO,CAAC,eAAe;IAoBvB,OAAO,CAAC,qBAAqB;IAe7B,OAAO,CAAC,sBAAsB;IA2B9B;;;;;;;OAOG;IACG,IAAI,CACR,UAAU,CAAC,EAAE,CAAC,QAAQ,EAAE,aAAa,KAAK,IAAI,EAC9C,WAAW,CAAC,EAAE,MAAM,EAAE,GACrB,OAAO,CAAC,UAAU,CAAC;IA+MtB;;;OAGG;IACH,eAAe,IAAI;QAAE,KAAK,EAAE,MAAM,EAAE,CAAC;QAAC,QAAQ,EAAE,MAAM,EAAE,CAAC;QAAC,OAAO,EAAE,MAAM,EAAE,CAAA;KAAE;CAwF9E;AAGD,OAAO,EAAE,iBAAiB,EAAE,MAAM,eAAe,CAAC;AAClD,OAAO,EAAE,cAAc,EAAE,YAAY,EAAE,mBAAmB,EAAE,eAAe,EAAE,qBAAqB,EAAE,YAAY,EAAE,wBAAwB,EAAE,eAAe,EAAE,MAAM,YAAY,CAAC"}

package/dist/extraction/index.js

@@ -1314,57 +1314,25 @@ class ExtractionOrchestrator {
                     durationMs: Date.now() - startTime,
                 };
             }
-            // Phase 2: Parse files in a worker thread (keeps main thread unblocked for UI)
+            // Do NOT emit `parsing` before the ArkTS Scene batch — that makes the
+            // shimmer print "Parsing code - done" when Scene starts, which looks like
+            // a restart. Parsing progress starts after primeArkTSBatch below.
             const total = files.length;
             let processed = 0;
-            // Emit parsing phase immediately so the progress bar appears during worker setup.
-            // The yield lets the shimmer worker flush the phase transition to stdout before
-            // the main thread starts synchronous grammar detection work.
-            onProgress?.({
-                phase: 'parsing',
-                current: 0,
-                total,
-            });
-            await new Promise(resolve => setImmediate(resolve));
-            // Detect needed languages and load grammars in the parse worker
+            // Detect needed languages. Parse workers start AFTER the ArkTS Scene batch
+            // so peak RSS is not Scene IR + N×WASM grammars at once.
             const neededLanguages = [...new Set(files.map((f) => (0, grammars_1.detectLanguage)(f, undefined, overrides)))];
             // .h files default to 'c' but may be C++ — ensure cpp grammar is loaded when c is needed
             if (neededLanguages.includes('c') && !neededLanguages.includes('cpp')) {
                 neededLanguages.push('cpp');
             }
-            // Parse files on a pool of worker threads (keeps the main thread free for UI
-            // and uses every core). Falls back to in-process parsing when the compiled
-            // worker is unavailable (e.g. running from source in tests).
             const parseWorkerPath = path.join(__dirname, 'parse-worker.js');
             const useWorker = fs.existsSync(parseWorkerPath);
+            // Assigned after ArkTS batch (see below).
             let pool = null;
-            if (useWorker) {
-                // CODEGRAPH_PARSE_WORKERS: explicit worker count; 1 = the old single-worker
-                // behaviour (the conservative rollback). Unset → clamp(cores-1, 1, 8).
-                const poolSize = (0, parse_pool_1.resolveParsePoolSize)(process.env.CODEGRAPH_PARSE_WORKERS, os.cpus().length);
-                pool = new parse_pool_1.ParseWorkerPool({
-                    languages: neededLanguages,
-                    size: poolSize,
-                    workerScriptPath: parseWorkerPath,
-                    recycleInterval: WORKER_RECYCLE_INTERVAL,
-                    parseTimeoutMs: PARSE_TIMEOUT_MS,
-                    log,
-                });
-                log(`Parse worker pool: ${poolSize} worker(s)`);
-            }
-            else {
-                // In-process fallback: load grammars locally and parse on the main thread.
-                await (0, grammars_1.loadGrammarsForLanguages)(neededLanguages);
-            }
-            const storeWorkerPath = path.join(__dirname, 'store-worker.js');
             let storeWriter = null;
-            if (storeWriterOpts &&
-                process.env.HOMEGRAPH_NO_STORE_WORKER !== '1' &&
-                fs.existsSync(storeWorkerPath)) {
-                storeWriter = new store_writer_1.StoreWriter(storeWorkerPath, storeWriterOpts.dbPath, storeWriterOpts.fastInit);
-                log('Store writer thread active');
-            }
             const STORE_WRITER_WINDOW = 64;
+            let windowSize = 1;
             /**
              * Parse one file: on the pool when available (the promise REJECTS on a worker
              * crash/timeout — the caller records it and the retry pass re-attempts), or
@@ -1387,8 +1355,7 @@ class ExtractionOrchestrator {
             // stable commit order keeps the resulting graph deterministic — byte-identical
             // to the single-worker path — instead of drifting with parse timing. The
             // `completed` buffer holds at most ~windowSize out-of-order results, so memory
-            // stays bounded.
-            const windowSize = pool ? Math.max(4, pool.size * 2) : 1;
+            // stays bounded. windowSize is set when the parse pool starts (after ArkTS).
             const inFlight = new Set();
             const completed = new Map();
             let nextSeq = 0; // file-order sequence assigned at dispatch
@@ -1507,6 +1474,46 @@ class ExtractionOrchestrator {
                 await (0, arkts_1.primeArkTSBatch)(this.rootDir, this.queries, firstEtsFile);
                 errors.push(...(0, arkts_1.drainArkTSIndexNotices)());
             }
+            // Start parse pool only after Scene teardown — most .ets are already in DB.
+            const remainingToParse = files.filter((f) => !((0, arkts_1.isArkTSBatchPersisted)(f) || ((0, arkts_1.isArkTSBatchCommitted)() && (0, arkts_1.isArkAnalyzerSourcePath)(f)))).length;
+            if (useWorker) {
+                // CODEGRAPH_PARSE_WORKERS: explicit worker count; 1 = the old single-worker
+                // behaviour (the conservative rollback). Unset → clamp(cores-1, 1, 8).
+                let poolSize = (0, parse_pool_1.resolveParsePoolSize)(process.env.CODEGRAPH_PARSE_WORKERS, os.cpus().length);
+                if (!process.env.CODEGRAPH_PARSE_WORKERS?.trim() && remainingToParse < 500) {
+                    poolSize = Math.min(poolSize, 2);
+                }
+                else if (!process.env.CODEGRAPH_PARSE_WORKERS?.trim() && remainingToParse < 2000) {
+                    poolSize = Math.min(poolSize, 4);
+                }
+                pool = new parse_pool_1.ParseWorkerPool({
+                    languages: neededLanguages,
+                    size: poolSize,
+                    workerScriptPath: parseWorkerPath,
+                    recycleInterval: WORKER_RECYCLE_INTERVAL,
+                    parseTimeoutMs: PARSE_TIMEOUT_MS,
+                    log,
+                });
+                windowSize = Math.max(4, pool.size * 2);
+                log(`Parse worker pool: ${poolSize} worker(s) (remaining files≈${remainingToParse})`);
+            }
+            else {
+                await (0, grammars_1.loadGrammarsForLanguages)(neededLanguages);
+            }
+            const storeWorkerPath = path.join(__dirname, 'store-worker.js');
+            if (storeWriterOpts &&
+                process.env.HOMEGRAPH_NO_STORE_WORKER !== '1' &&
+                fs.existsSync(storeWorkerPath)) {
+                storeWriter = new store_writer_1.StoreWriter(storeWorkerPath, storeWriterOpts.dbPath, storeWriterOpts.fastInit);
+                log('Store writer thread active');
+            }
+            // Parsing progress only after ArkTS batch (avoids false "Parsing - done").
+            onProgress?.({
+                phase: 'parsing',
+                current: 0,
+                total,
+            });
+            await new Promise((resolve) => setImmediate(resolve));
             for (let i = 0; i < files.length; i += FILE_IO_BATCH_SIZE) {
                 if (signal?.aborted) {
                     aborted = true;
@@ -1515,7 +1522,8 @@ class ExtractionOrchestrator {
                 const batch = files.slice(i, i + FILE_IO_BATCH_SIZE);
                 // Read files in parallel (with path validation before any I/O)
                 const fileContents = await Promise.all(batch.map(async (fp) => {
-                    if ((0, arkts_1.isArkTSBatchPersisted)(fp)) {
+                    if ((0, arkts_1.isArkTSBatchPersisted)(fp) ||
+                        ((0, arkts_1.isArkTSBatchCommitted)() && (0, arkts_1.isArkAnalyzerSourcePath)(fp))) {
                         return {
                             filePath: fp,
                             content: null,
@@ -1550,7 +1558,9 @@ class ExtractionOrchestrator {
                         aborted = true;
                         break;
                     }
-                    if ((0, arkts_1.isArkTSBatchPersisted)(filePath) || arktsBatchSkipped) {
+                    if ((0, arkts_1.isArkTSBatchPersisted)(filePath) ||
+                        arktsBatchSkipped ||
+                        ((0, arkts_1.isArkTSBatchCommitted)() && (0, arkts_1.isArkAnalyzerSourcePath)(filePath))) {
                         processed++;
                         filesIndexed++;
                         onProgress?.({ phase: 'parsing', current: processed, total, currentFile: filePath });
@@ -1748,6 +1758,7 @@ class ExtractionOrchestrator {
             // Shut down the parse worker pool.
             if (pool)
                 await pool.destroy();
+            (0, arkts_1.shrinkArkTSBatchPostParse)();
             return {
                 success: filesIndexed > 0 || errors.filter((e) => e.severity === 'error').length === 0,
                 filesIndexed,