feat(migrate): v116 — backfill NULL edge source_id + index from_symbol_qualified

1. Backfill: edges written before the stamping fix sit at source_id=NULL
   and stay invisible to scoped call-graph queries until repaired. Derive
   each edge's source from its own from_chunk's page (pages.source_id is
   NOT NULL DEFAULT 'default'). Same SQL verified live on a 2,122-edge
   production brain.
2. Indexes: getCalleesOf filters both edge tables on from_symbol_qualified,
   which had no index — every callee lookup was a seq scan, amplified
   per-BFS-node by the recursive code walk. With NULL edges repaired,
   scoped walks actually expand, so the latent cost becomes real.
   Mirrored into src/schema.sql; schema-embedded.ts regenerated.

src/core/migrate.ts

@@ -5186,6 +5186,52 @@ export const MIGRATIONS: Migration[] = [
       );
     `,
   },
+  {
+    version: 116,
+    name: 'code_edges_source_backfill_and_callee_index',
+    // Repair + index pass for the call graph:
+    //
+    // 1. BACKFILL: importCodeFile built CodeEdgeInput rows without source_id,
+    //    so every extracted edge landed NULL. getCallersOf/getCalleesOf add
+    //    `AND source_id = <scoped>` whenever a worktree pin / --source is in
+    //    play — NULL never matches, so scoped call-graph queries silently
+    //    returned 0 rows on multi-source brains even though the edges
+    //    existed. The write path now stamps `sourceId ?? 'default'`; this
+    //    backfill repairs rows written before the fix by deriving each
+    //    edge's source from its own from_chunk's page (pages.source_id is
+    //    NOT NULL DEFAULT 'default', so COALESCE is belt-and-braces only).
+    //
+    // 2. INDEXES: getCalleesOf filters BOTH edge tables on
+    //    from_symbol_qualified, which had no index anywhere — every callee
+    //    lookup was a sequential scan, amplified per-BFS-node by the
+    //    recursive code walk (one getCalleesOf per frontier node, up to
+    //    maxNodes). With NULL edges repaired, scoped walks actually expand,
+    //    so the latent seq-scan cost becomes real. Plain CREATE INDEX (not
+    //    CONCURRENTLY): edge tables are modest (mirrors the v58 resolver
+    //    index). Keep in sync with src/schema.sql.
+    idempotent: true,
+    sql: `
+      UPDATE code_edges_symbol e
+         SET source_id = COALESCE(p.source_id, 'default')
+        FROM content_chunks c
+        JOIN pages p ON p.id = c.page_id
+       WHERE c.id = e.from_chunk_id
+         AND e.source_id IS NULL;
+
+      UPDATE code_edges_chunk e
+         SET source_id = COALESCE(p.source_id, 'default')
+        FROM content_chunks c
+        JOIN pages p ON p.id = c.page_id
+       WHERE c.id = e.from_chunk_id
+         AND e.source_id IS NULL;
+
+      CREATE INDEX IF NOT EXISTS idx_code_edges_symbol_from_symbol
+        ON code_edges_symbol (from_symbol_qualified);
+
+      CREATE INDEX IF NOT EXISTS idx_code_edges_chunk_from_symbol
+        ON code_edges_chunk (from_symbol_qualified);
+    `,
+  },
 ];
 
 export const LATEST_VERSION = MIGRATIONS.length > 0

src/core/schema-embedded.ts

@@ -390,6 +390,11 @@ CREATE INDEX IF NOT EXISTS idx_code_edges_chunk_to
   ON code_edges_chunk(to_chunk_id, edge_type);
 CREATE INDEX IF NOT EXISTS idx_code_edges_chunk_to_symbol
   ON code_edges_chunk(to_symbol_qualified, edge_type);
+-- getCalleesOf filters on from_symbol_qualified; without this index every
+-- callee lookup is a sequential scan, amplified per-BFS-node by the
+-- recursive code walk. Mirrors migration v116.
+CREATE INDEX IF NOT EXISTS idx_code_edges_chunk_from_symbol
+  ON code_edges_chunk(from_symbol_qualified);
 
 CREATE TABLE IF NOT EXISTS code_edges_symbol (
   id                    SERIAL PRIMARY KEY,
@@ -407,16 +412,32 @@ CREATE INDEX IF NOT EXISTS idx_code_edges_symbol_from
   ON code_edges_symbol(from_chunk_id, edge_type);
 CREATE INDEX IF NOT EXISTS idx_code_edges_symbol_to
   ON code_edges_symbol(to_symbol_qualified, edge_type);
+-- getCalleesOf companion to idx_code_edges_chunk_from_symbol above.
+-- Mirrors migration v116.
+CREATE INDEX IF NOT EXISTS idx_code_edges_symbol_from_symbol
+  ON code_edges_symbol(from_symbol_qualified);
 
 -- ============================================================
 -- links: cross-references between pages
 -- ============================================================
--- Provenance model (v0.13, extended issue #972):
---   link_source       — 'markdown' | 'frontmatter' | 'manual' | 'wikilink-resolved' | NULL
---                       'wikilink-resolved' is the opt-in
---                       (link_resolution.global_basename) basename-match
---                       provenance — see issue #972 / migration v113.
---                       (NULL = legacy row written before v0.13; unknown source)
+-- Provenance model (v0.13; opened to kebab provenance in v114 / issue #1941):
+--   link_source       — open kebab-case provenance tag, NOT a closed allowlist.
+--                       Format gate (CHECK): ^[a-z][a-z0-9]*(-[a-z0-9]+)*\$ and
+--                       char_length <= 64. NULL = legacy row (pre-v0.13).
+--                       Reconciliation-managed built-ins written internally:
+--                         'markdown'         — body markdown links
+--                         'frontmatter'      — YAML frontmatter edges (see origin_*)
+--                         'mentions'         — auto-linked body-text mentions
+--                         'wikilink-resolved'— opt-in global-basename [[name]] (#972)
+--                       User/tool-facing:
+--                         'manual'           — hand- or tool-created edges (the
+--                                              add_link op default + CLI link-add)
+--                         '<your-tag>'       — external derivers, e.g. 'citation-graph',
+--                                              stamp their own kebab tag (no migration).
+--                       The add_link OP forbids callers from passing the four
+--                       managed built-ins (they imply reconciliation semantics a
+--                       hand-created row can't honor); the DB CHECK still admits
+--                       them because internal writers use them. See operations.ts.
 --   origin_page_id    — for link_source='frontmatter', the page whose YAML
 --                       frontmatter created this edge; scopes reconciliation
 --   origin_field      — the frontmatter field name (e.g. 'key_people')
@@ -424,21 +445,21 @@ CREATE INDEX IF NOT EXISTS idx_code_edges_symbol_to
 -- The unique constraint includes link_source + origin_page_id so a manual edge
 -- and a frontmatter-derived edge with the same (from, to, type) tuple coexist.
 -- Reconciliation on put_page filters by (link_source='frontmatter' AND
--- origin_page_id = written_page) — never touches other pages' edges.
+-- origin_page_id = written_page) — never touches other pages' edges. (This is
+-- exactly why a CLI-forged 'frontmatter' row with NULL origin would be a phantom
+-- edge reconciliation never cleans — hence the op-layer guard.)
 CREATE TABLE IF NOT EXISTS links (
   id             SERIAL PRIMARY KEY,
   from_page_id   INTEGER NOT NULL REFERENCES pages(id) ON DELETE CASCADE,
   to_page_id     INTEGER NOT NULL REFERENCES pages(id) ON DELETE CASCADE,
   link_type      TEXT    NOT NULL DEFAULT '',
   context        TEXT    NOT NULL DEFAULT '',
-  -- v114 (#1941): link_source is an open kebab-case provenance, not a closed
-  -- allowlist — external derivers (e.g. 'citation-graph') stamp their own tag
-  -- without a gbrain migration. Format gate only: lowercase kebab, <=64 chars.
-  -- The reconciliation-managed built-ins ('markdown','frontmatter','mentions',
-  -- 'wikilink-resolved') still satisfy this and are written internally; the
-  -- add_link op forbids CALLERS from forging them (see operations.ts). 'manual'
-  -- is the user-facing default for hand/tool-created edges.
-  link_source    TEXT    CHECK (link_source IS NULL OR (link_source ~ '^[a-z][a-z0-9]*(-[a-z0-9]+)*$' AND char_length(link_source) <= 64)),
+  -- v0.41.18.0: 'mentions' added for auto-linked body-text mentions
+  -- (gbrain extract links --by-mention). Filtered OUT of backlink-count
+  -- for search ranking; only counts toward orphan-ratio + graph traversal.
+  -- v0.40.8.2 (#972): 'wikilink-resolved' added for opt-in global-basename
+  -- wikilink resolution (bare [[name]] resolved by slug tail).
+  link_source    TEXT    CHECK (link_source IS NULL OR (link_source ~ '^[a-z][a-z0-9]*(-[a-z0-9]+)*\$' AND char_length(link_source) <= 64)),
   -- v0.41.18.0: nullable link_kind distinguishes "plain body mention" from
   -- "verb-pattern-derived typed link" within link_source='mentions'.
   -- Codex finding #12 design: keep link_source stable; add link_kind
@@ -675,8 +696,11 @@ CREATE TABLE IF NOT EXISTS op_checkpoints (
 CREATE INDEX IF NOT EXISTS op_checkpoints_updated_at_idx
   ON op_checkpoints (updated_at);
 
--- #1794: append-only delta storage (one row per completed path). FK cascade
--- drops children with the parent. Mirrors migration v115 + src/schema.sql.
+-- #1794: append-only delta storage. One row per completed path; sync's
+-- appendCompleted INSERTs only the delta instead of rewriting the whole
+-- completed_keys JSONB array each flush (O(N^2) -> O(delta)). FK cascade drops
+-- children with the parent (clearOpCheckpoint + 7-day purge). PK prefix
+-- (op,fingerprint) serves all reads; no separate index. Mirrors migration v115.
 CREATE TABLE IF NOT EXISTS op_checkpoint_paths (
   op          TEXT NOT NULL,
   fingerprint TEXT NOT NULL,

src/schema.sql

@@ -386,6 +386,11 @@ CREATE INDEX IF NOT EXISTS idx_code_edges_chunk_to
   ON code_edges_chunk(to_chunk_id, edge_type);
 CREATE INDEX IF NOT EXISTS idx_code_edges_chunk_to_symbol
   ON code_edges_chunk(to_symbol_qualified, edge_type);
+-- getCalleesOf filters on from_symbol_qualified; without this index every
+-- callee lookup is a sequential scan, amplified per-BFS-node by the
+-- recursive code walk. Mirrors migration v116.
+CREATE INDEX IF NOT EXISTS idx_code_edges_chunk_from_symbol
+  ON code_edges_chunk(from_symbol_qualified);
 
 CREATE TABLE IF NOT EXISTS code_edges_symbol (
   id                    SERIAL PRIMARY KEY,
@@ -403,6 +408,10 @@ CREATE INDEX IF NOT EXISTS idx_code_edges_symbol_from
   ON code_edges_symbol(from_chunk_id, edge_type);
 CREATE INDEX IF NOT EXISTS idx_code_edges_symbol_to
   ON code_edges_symbol(to_symbol_qualified, edge_type);
+-- getCalleesOf companion to idx_code_edges_chunk_from_symbol above.
+-- Mirrors migration v116.
+CREATE INDEX IF NOT EXISTS idx_code_edges_symbol_from_symbol
+  ON code_edges_symbol(from_symbol_qualified);
 
 -- ============================================================
 -- links: cross-references between pages