codegraph/src/resolution/callback-synthesizer.ts

/**
 * Callback / observer edge synthesis — Phase 1 + 2.
 *
 * Closes dynamic-dispatch holes where a dispatcher invokes callbacks registered
 * elsewhere. Two channel shapes:
 *
 *  (1) Field-backed observer (Phase 1):
 *      onUpdate(cb) { this.callbacks.add(cb); }            // registrar
 *      triggerUpdate() { for (cb of this.callbacks) cb(); } // dispatcher
 *      scene.onUpdate(this.triggerRender)                  // registration
 *      → synthesize triggerUpdate → triggerRender
 *
 *  (2) String-keyed EventEmitter (Phase 2):
 *      this.on('mount', function onmount(){...})           // registration
 *      fn.emit('mount', this)                              // dispatch
 *      → synthesize (method containing emit('mount')) → onmount
 *
 * Whole-graph pass after base resolution. High-precision/low-recall by design:
 * named callbacks only; field channels paired by file+field; EventEmitter
 * channels capped by event fan-out (generic names like 'error' skipped — they
 * need receiver-type matching, deferred to Phase 3). All synthesized edges are
 * tagged `provenance:'heuristic'`. See docs/design/callback-edge-synthesis.md.
 */
import type { Edge, Node } from '../types';
import type { QueryBuilder } from '../db/queries';
import type { ResolutionContext } from './types';

const REGISTRAR_NAME = /^(on[A-Z]\w*|subscribe|addListener|addEventListener|register|watch|listen|addCallback)$/;
const DISPATCHER_NAME = /(emit|trigger|notify|dispatch|fire|publish|flush)/i;
const MAX_CALLBACKS_PER_CHANNEL = 40;
const EVENT_FANOUT_CAP = 6; // skip events with more handlers/dispatchers than this (too generic without type info)

const ON_RE = /\.(?:on|once|addListener)\(\s*['"]([^'"]+)['"]\s*,\s*(?:function\s+(\w+)|(?:this\.)?(\w+))/g;
const EMIT_RE = /\.(?:emit|fire|dispatchEvent)\(\s*['"]([^'"]+)['"]/g;

function sliceLines(content: string, startLine?: number, endLine?: number): string | null {
  if (!startLine || !endLine) return null;
  return content.split('\n').slice(startLine - 1, endLine).join('\n');
}

function registrarField(src: string): string | null {
  const m = src.match(/this\.(\w+)\.(?:add|push|set)\(/);
  return m ? m[1]! : null;
}

function dispatcherField(src: string): string | null {
  const forOf = src.match(/\bof\s+(?:Array\.from\(\s*)?this\.(\w+)/);
  if (forOf && /\b\w+\s*\(/.test(src)) return forOf[1]!;
  const forEach = src.match(/this\.(\w+)\.forEach\(/);
  if (forEach) return forEach[1]!;
  return null;
}

const FN_KINDS = new Set(['method', 'function', 'component']);

/** Innermost function/method node whose line range contains `line`. */
function enclosingFn(nodesInFile: Node[], line: number): Node | null {
  let best: Node | null = null;
  for (const n of nodesInFile) {
    if (!FN_KINDS.has(n.kind)) continue;
    const end = n.endLine ?? n.startLine;
    if (n.startLine <= line && end >= line) {
      if (!best || n.startLine >= best.startLine) best = n; // prefer the tightest (latest-starting) encloser
    }
  }
  return best;
}

/** Phase 1: field-backed observer channels (registrar/dispatcher share a store). */
function fieldChannelEdges(queries: QueryBuilder, ctx: ResolutionContext): Edge[] {
  const candidates = [...queries.getNodesByKind('method'), ...queries.getNodesByKind('function')];
  const registrars: Array<{ node: Node; field: string }> = [];
  const dispatchers: Array<{ node: Node; field: string }> = [];

  for (const m of candidates) {
    const isReg = REGISTRAR_NAME.test(m.name);
    const isDisp = DISPATCHER_NAME.test(m.name);
    if (!isReg && !isDisp) continue;
    const content = ctx.readFile(m.filePath);
    const src = content && sliceLines(content, m.startLine, m.endLine);
    if (!src) continue;
    if (isReg) { const f = registrarField(src); if (f) registrars.push({ node: m, field: f }); }
    if (isDisp) { const f = dispatcherField(src); if (f) dispatchers.push({ node: m, field: f }); }
  }

  const edges: Edge[] = [];
  const seen = new Set<string>();
  for (const reg of registrars) {
    const chDispatchers = dispatchers.filter(
      (d) => d.node.filePath === reg.node.filePath && d.field === reg.field
    );
    if (chDispatchers.length === 0) continue;
    const argRe = new RegExp(`${reg.node.name}\\s*\\(\\s*(?:this\\.)?(\\w+)`);
    let added = 0;
    for (const e of queries.getIncomingEdges(reg.node.id, ['calls'])) {
      if (added >= MAX_CALLBACKS_PER_CHANNEL) break;
      if (!e.line) continue;
      const caller = queries.getNodeById(e.source);
      if (!caller) continue;
      const line = ctx.readFile(caller.filePath)?.split('\n')[e.line - 1];
      const am = line?.match(argRe);
      if (!am) continue;
      const fn = ctx.getNodesByName(am[1]!).find((n) => n.kind === 'method' || n.kind === 'function');
      if (!fn) continue;
      for (const disp of chDispatchers) {
        if (disp.node.id === fn.id) continue;
        const key = `${disp.node.id}>${fn.id}`;
        if (seen.has(key)) continue;
        seen.add(key);
        edges.push({
          source: disp.node.id, target: fn.id, kind: 'calls', line: disp.node.startLine,
          provenance: 'heuristic',
          metadata: {
            synthesizedBy: 'callback', via: reg.node.name, field: reg.field,
            // Where the callback was wired up (`scene.onUpdate(this.triggerRender)`).
            // This is the #1 thing an agent reads/greps to explain the flow — surface
            // it so node/trace/context can show it without a callers() + Read round-trip.
            registeredAt: `${caller.filePath}:${e.line}`,
          },
        });
        added++;
      }
    }
  }
  return edges;
}

/** Phase 2: string-keyed EventEmitter channels (on('e', fn) ↔ emit('e')). */
function eventEmitterEdges(ctx: ResolutionContext): Edge[] {
  const emitsByEvent = new Map<string, Set<string>>();          // event → dispatcher node ids
  const handlersByEvent = new Map<string, Map<string, string>>(); // event → handler id → registration site (file:line)

  for (const file of ctx.getAllFiles()) {
    const content = ctx.readFile(file);
    if (!content) continue;
    const hasEmit = content.includes('.emit(') || content.includes('.fire(') || content.includes('.dispatchEvent(');
    const hasOn = content.includes('.on(') || content.includes('.once(') || content.includes('.addListener(');
    if (!hasEmit && !hasOn) continue;
    const nodesInFile = ctx.getNodesInFile(file);
    const lineOf = (idx: number) => content.slice(0, idx).split('\n').length;

    if (hasEmit) {
      EMIT_RE.lastIndex = 0;
      let m: RegExpExecArray | null;
      while ((m = EMIT_RE.exec(content))) {
        const disp = enclosingFn(nodesInFile, lineOf(m.index));
        if (!disp) continue;
        const set = emitsByEvent.get(m[1]!) ?? new Set<string>();
        set.add(disp.id); emitsByEvent.set(m[1]!, set);
      }
    }
    if (hasOn) {
      ON_RE.lastIndex = 0;
      let m: RegExpExecArray | null;
      while ((m = ON_RE.exec(content))) {
        const handlerName = m[2] || m[3];
        if (!handlerName) continue;
        const handler = ctx.getNodesByName(handlerName).find((n) => n.kind === 'function' || n.kind === 'method');
        if (!handler) continue;
        const map = handlersByEvent.get(m[1]!) ?? new Map<string, string>();
        map.set(handler.id, `${file}:${lineOf(m.index)}`); handlersByEvent.set(m[1]!, map);
      }
    }
  }

  const edges: Edge[] = [];
  const seen = new Set<string>();
  for (const [event, dispatchers] of emitsByEvent) {
    const handlers = handlersByEvent.get(event);
    if (!handlers) continue;
    // Precision guard: a generic event name with many handlers/dispatchers can't
    // be matched without receiver-type info (Phase 3) — skip rather than over-link.
    if (dispatchers.size > EVENT_FANOUT_CAP || handlers.size > EVENT_FANOUT_CAP) continue;
    for (const d of dispatchers) for (const [h, registeredAt] of handlers) {
      if (d === h) continue;
      const key = `${d}>${h}`;
      if (seen.has(key)) continue;
      seen.add(key);
      edges.push({ source: d, target: h, kind: 'calls', provenance: 'heuristic', metadata: { synthesizedBy: 'event-emitter', event, registeredAt } });
    }
  }
  return edges;
}

/**
 * Synthesize dispatcher→callback edges (field observers + EventEmitters).
 * Returns the count added. Never throws into indexing — callers wrap in try/catch.
 */
export function synthesizeCallbackEdges(queries: QueryBuilder, ctx: ResolutionContext): number {
  const fieldEdges = fieldChannelEdges(queries, ctx);
  const emitterEdges = eventEmitterEdges(ctx);

  const merged: Edge[] = [];
  const seen = new Set<string>();
  for (const e of [...fieldEdges, ...emitterEdges]) {
    const key = `${e.source}>${e.target}`;
    if (seen.has(key)) continue;
    seen.add(key);
    merged.push(e);
  }
  if (merged.length > 0) queries.insertEdges(merged);
  return merged.length;
}