Method buildFlowFromNamedSymbols

src/mcp/tools.ts:1847–2106

* Flow-from-named-symbols: an agent's codegraph_explore query is a bag of * symbol names that usually spans the flow it's investigating (e.g. * "PmsProductController getList PmsProductService list PmsProductServiceImpl"). * Surface the longest call chain AMONG those named symbols — scoped t

(cg: CodeGraph, query: string)

   * dropping unrelated `OmsOrderService::list`.
   */
  private buildFlowFromNamedSymbols(cg: CodeGraph, query: string): { text: string; pathNodeIds: Set<string>; namedNodeIds: Set<string>; uniqueNamedNodeIds: Set<string>; spineCallSites: Map<string, number> } {
    // spineCallSites: for each spine node, the line where it CALLS the next hop —
    // lets the source assembler window an oversize spine method (e.g. n8n's 962-line
    // processRunExecutionData) to the call site instead of dumping the whole body.
    const EMPTY = { text: '', pathNodeIds: new Set<string>(), namedNodeIds: new Set<string>(), uniqueNamedNodeIds: new Set<string>(), spineCallSites: new Map<string, number>() };
    try {
      const CALLABLE = new Set(['method', 'function', 'component', 'constructor']);
      // Strip only a REAL file extension (Create.cs → Create); KEEP qualified
      // names (Class.method / Class::method) — the agent's most precise input,
      // resolved exactly by findAllSymbols. (The old strip mangled Class.method
      // into Class, throwing the method away.)
      const FILE_EXT = /\.(?:java|kt|kts|ts|tsx|js|jsx|mjs|cjs|cs|py|go|rb|php|swift|rs|cpp|cc|cxx|c|h|hpp|scala|lua|dart|vue|svelte|astro)$/i;
      const tokens = [...new Set(
        query.split(/[\s,()[\]]+/)
          .map((t) => t.replace(FILE_EXT, '').trim())
          .filter((t) => t.length >= 3 && /^[A-Za-z_$][\w$]*(?:(?:::|\.)[\w$]+)*$/.test(t))
      )].slice(0, 16);
      if (tokens.length < 2) return EMPTY;
      // Pool of name SEGMENTS (Class + method from every token) used to
      // disambiguate an ambiguous SIMPLE name: keep a candidate only if its
      // CONTAINER class is itself named in the query.
      const segPool = new Set<string>();
      for (const t of tokens) for (const s of t.toLowerCase().split(/::|\./)) if (s) segPool.add(s);
      const named = new Map<string, Node>();
      // Nodes whose token is SPECIFIC — a (near-)unique callable name (<=3 defs in
      // the whole graph). These are safe to SPARE a file on: the agent named THIS
      // method (`getResponseWithInterceptorChain`, 1 def). A hyper-polymorphic name
      // (`as_sql`, 110 defs across every Expression/Compiler subclass) is NOT here,
      // so naming it doesn't keep every backend variant full and flood the budget.
      const uniqueNamedNodeIds = new Set<string>();
      // token → resolved node ids: drives the token-coverage check that gates
      // the dynamic-boundary scan (a token is covered when ANY of its nodes
      // lands on the main chain — overloads off the chain don't count against).
      const tokenNodes = new Map<string, string[]>();
      // token → its full same-name callable family (before the container filter).
      // A LARGE family that fails to connect on the chain is a polymorphic
      // interface/registry dispatch — surfaced by buildPolymorphicBoundaries below.
      const tokenFamily = new Map<string, Node[]>();
      // Non-callable endpoints (CONSTANT/VARIABLE/FIELD) connected by a SYNTHESIZED
      // edge. RTK thunks are `const X = createAsyncThunk(...)`, so a thunk→thunk hop
      // is constant→constant — the CALLABLE-only `named` set can't hold it, and
      // without this the hop is invisible to the Flow path at every tier (the
      // Relationships section catches it only on repos ≥500 files). Kept SEPARATE
      // from `named` (which drives the call-chain + source sizing, callable-only);
      // fed only to the dynamic-dispatch-links scan below.
      const dynNamed = new Map<string, Node>();
      const DYN_KINDS = new Set(['constant', 'variable', 'field', 'property']);
      const hasHeuristicEdge = (id: string): boolean =>
        [...cg.getCallers(id), ...cg.getCallees(id)].some(({ edge }) => edge.provenance === 'heuristic');
      for (const t of tokens) {
        const hits = this.findAllSymbols(cg, t).nodes;
        const cands = hits.filter((n) => CALLABLE.has(n.kind));
        tokenFamily.set(t, cands);
        // A qualified or otherwise-specific name (<=3 hits) keeps all; an
        // ambiguous simple name keeps only candidates whose container is named.
        const specific = cands.length <= 3;
        const pick = specific
          ? cands