AgapHost/ai/adolf-llm/server.js

const http = require('http');
const fs = require('fs');
const path = require('path');
const crypto = require('crypto');
const { spawn } = require('child_process');

// Both overridable purely so the wrapper can be exercised outside the
// container (the defaults are the in-container values).
const PORT = Number(process.env.PORT) || 8010;
const SHARED_MCP_PATH = process.env.SHARED_MCP_PATH || '/shared-mcp.json';
const MODEL_ID = 'adolf';
const TIMEOUT_MS = 15 * 60 * 1000;

const WORKSPACE = process.env.WORKSPACE || '/workspace';
const CONV_ROOT = path.join(WORKSPACE, 'conversations');
const STATE_DIR = path.join(WORKSPACE, '.adolf-llm');
const MAP_FILE = path.join(STATE_DIR, 'sessions.json');
const MAX_ENTRIES = 1000; // prune oldest beyond this

fs.mkdirSync(CONV_ROOT, { recursive: true });
fs.mkdirSync(STATE_DIR, { recursive: true });

// ---------------------------------------------------------------------------
// Shared MCP layer. Unlike Kimi Code CLI (which had no --mcp-config-file flag
// and forced a per-session `.mcp.json` dropped into each working directory),
// Codex reads MCP servers from `$CODEX_HOME/config.toml` under `[mcp_servers.*]`
// tables. So this is now written ONCE at startup instead of per session.
//
// Single source of truth is unchanged: `/shared-mcp.json` (mounted read-only
// from the repo root's `shared-mcp.json`, the same file OpenClaw's own
// `mcp.servers` registry uses). Adding a server stays a one-file change.
//
// Transport mapping. shared-mcp.json entries are either:
//   { command, args, env }  -> stdio server
//   { url, type: "http" }   -> remote streamable-http server
// Codex expresses stdio servers as `command`/`args`/`env`, and remote servers
// as `url` with an optional `bearer_token_env_var`. It has no `type` key; the
// shape (command vs url) selects the transport, same inference Kimi did. The
// `type: "http"` key that shared-mcp.json carries for OpenClaw's benefit is
// simply not emitted here.
const CODEX_HOME = process.env.CODEX_HOME || '/root/.codex';

let SHARED_MCP_SERVERS = {};
try {
  const raw = fs.readFileSync(SHARED_MCP_PATH, 'utf8');
  SHARED_MCP_SERVERS = JSON.parse(raw).mcpServers || {};
} catch (err) {
  console.error(`shared-mcp.json not loaded (${err.message}); sessions will get no shared MCP servers`);
}

// Minimal TOML emitter — we only ever emit strings, string arrays and flat
// string maps, so a full TOML library would be dead weight.
function tomlString(s) {
  return JSON.stringify(String(s)); // TOML basic strings share JSON escaping
}
function tomlValue(v) {
  if (Array.isArray(v)) return `[${v.map(tomlString).join(', ')}]`;
  return tomlString(v);
}

function renderMcpToml(servers) {
  const lines = [
    '# GENERATED by adolf-llm from /shared-mcp.json — do not edit by hand.',
    '# Regenerated on every container start; manual edits are lost.',
    '',
  ];
  for (const [name, cfg] of Object.entries(servers)) {
    lines.push(`[mcp_servers.${name}]`);
    if (cfg.command) {
      lines.push(`command = ${tomlValue(cfg.command)}`);
      if (cfg.args && cfg.args.length) lines.push(`args = ${tomlValue(cfg.args)}`);
    } else if (cfg.url) {
      lines.push(`url = ${tomlValue(cfg.url)}`);
    } else {
      console.error(`shared-mcp.json: server "${name}" has neither command nor url; skipped`);
      lines.pop();
      continue;
    }
    // Field-name translation, Kimi -> Codex. shared-mcp.json is written in
    // Kimi/OpenClaw's camelCase dialect; Codex's RawMcpServerConfig uses
    // snake_case. Both keys are load-bearing:
    //   bearerTokenEnvVar -> bearer_token_env_var  (agap + marketplace auth;
    //     without it every tool call on those servers returns HTTP 401)
    //   enabledTools      -> enabled_tools         (the capability allow-list
    //     that ai/agent-registry.yaml's mcp_tool_filter is validated against;
    //     dropping it would silently widen Adolf's tool access)
    if (cfg.bearerTokenEnvVar) {
      lines.push(`bearer_token_env_var = ${tomlValue(cfg.bearerTokenEnvVar)}`);
    }
    if (cfg.enabledTools && cfg.enabledTools.length) {
      lines.push(`enabled_tools = ${tomlValue(cfg.enabledTools)}`);
    }
    if (cfg.env && Object.keys(cfg.env).length) {
      lines.push(`[mcp_servers.${name}.env]`);
      for (const [k, v] of Object.entries(cfg.env)) lines.push(`${k} = ${tomlValue(v)}`);
    }
    lines.push('');
  }
  return lines.join('\n');
}

// Write the Codex config once at startup: MCP servers + the headless-operation
// settings. `approval_policy = "never"` and `sandbox_mode` are load-bearing —
// Codex defaults to asking for approval before running a tool, and nobody is
// there to answer, so without these a turn hangs until the 15-minute timeout
// instead of failing loudly.
function writeCodexConfig() {
  fs.mkdirSync(CODEX_HOME, { recursive: true });
  const header = [
    'approval_policy = "never"',
    'sandbox_mode = "danger-full-access"',
    '',
  ].join('\n');
  fs.writeFileSync(path.join(CODEX_HOME, 'config.toml'), header + renderMcpToml(SHARED_MCP_SERVERS));
}
writeCodexConfig();

// ---------------------------------------------------------------------------
// Memory lives at the OpenClaw layer, not here (P8). The Adolf gateway loads
// the `cognee-memory` OpenClaw plugin, which owns all memory touchpoints:
//   - before_prompt_build => LLM-free cognee graph recall, injected into the
//     prompt this wrapper then receives from OpenClaw.
//   - agent_end           => raw `add` of the turn to cognee.
//   - background sweep     => async `cognify` on cognee-llm (Kimi).
//   - cognee_recall tool + cognee-mcp `recall` for on-demand deep queries.
// This wrapper is therefore a dumb model endpoint again: it must never call
// cognee itself. The former cogneeSearch/cogneeAdd stubs (and their call sites)
// were deleted when the plugin took over (P8).

// ---------------------------------------------------------------------------
// Persistent conversation -> Codex session (thread) map.
// Primary key: `chat:<chat_id>` parsed from OpenClaw's "Conversation info" block
// (Gate 2). Fallback key: `hist:<sha256(prior history)>` when no chat_id is
// present (e.g. webchat surface / future OpenClaw layout change).
// value = { convId, sessionId, dir, ts }
let sessionMap = {};
try {
  sessionMap = JSON.parse(fs.readFileSync(MAP_FILE, 'utf8'));
} catch {
  sessionMap = {};
}

let writeQueue = Promise.resolve();
function persistMap() {
  // prune to the MAX_ENTRIES most-recently-used before writing
  const keys = Object.keys(sessionMap);
  if (keys.length > MAX_ENTRIES) {
    keys.sort((a, b) => (sessionMap[a].ts || 0) - (sessionMap[b].ts || 0));
    for (const k of keys.slice(0, keys.length - MAX_ENTRIES)) delete sessionMap[k];
  }
  const snapshot = JSON.stringify(sessionMap);
  writeQueue = writeQueue.then(
    () => fs.promises.writeFile(MAP_FILE, snapshot),
    () => fs.promises.writeFile(MAP_FILE, snapshot),
  );
  return writeQueue;
}

// ---------------------------------------------------------------------------
// Message helpers.
function textOf(msg) {
  const c = msg.content;
  if (Array.isArray(c)) return c.map(p => (typeof p === 'string' ? p : p.text || '')).join('\n');
  return c == null ? '' : String(c);
}

// only user/assistant turns define conversation identity (system is constant)
function convTurns(messages) {
  return messages.filter(m => m.role === 'user' || m.role === 'assistant');
}

function historyKey(turns) {
  const norm = turns.map(m => ({ role: m.role, text: textOf(m).trim() }));
  return crypto.createHash('sha256').update(JSON.stringify(norm)).digest('hex');
}

function renderTranscript(turns) {
  return turns
    .map(m => `${m.role === 'assistant' ? 'Assistant' : 'User'}: ${textOf(m)}`)
    .join('\n\n');
}

// ---------------------------------------------------------------------------
// Gate 2 — parse the stable chat_id out of OpenClaw's untrusted-metadata block.
// OpenClaw injects, into the *user-role* content, a block that looks like:
//   Conversation info (untrusted metadata):
//   ```json
//   { "chat_id": "matrix:!room:server", "message_id": "...", ... }
//   ```
// We grep on the label string (never a fixed line offset) then pull the first
// balanced JSON object after it and read chat_id. Robust to edited/truncated
// history, which is exactly why it beats a history hash for the common case.
const CONV_INFO_LABEL = 'Conversation info (untrusted metadata):';

function extractBalancedJson(str, from) {
  const start = str.indexOf('{', from);
  if (start === -1) return null;
  let depth = 0;
  let inStr = false;
  let esc = false;
  for (let i = start; i < str.length; i++) {
    const ch = str[i];
    if (inStr) {
      if (esc) esc = false;
      else if (ch === '\\') esc = true;
      else if (ch === '"') inStr = false;
      continue;
    }
    if (ch === '"') inStr = true;
    else if (ch === '{') depth++;
    else if (ch === '}') {
      depth--;
      if (depth === 0) return str.slice(start, i + 1);
    }
  }
  return null;
}

function extractChatId(userMsg) {
  const text = textOf(userMsg);
  const at = text.indexOf(CONV_INFO_LABEL);
  if (at === -1) return null;
  const jsonStr = extractBalancedJson(text, at + CONV_INFO_LABEL.length);
  if (!jsonStr) return null;
  try {
    const obj = JSON.parse(jsonStr);
    const id = obj.chat_id;
    return typeof id === 'string' && id ? id : null;
  } catch {
    return null;
  }
}

// ---------------------------------------------------------------------------
// Gate 3 — media. Persist inbound image parts into the session dir and return
// relative path references; the CLI autonomously calls its built-in
// ReadMediaFile tool on referenced paths (no flag/placeholder syntax needed).
const MIME_EXT = {
  'image/png': 'png',
  'image/jpeg': 'jpg',
  'image/jpg': 'jpg',
  'image/webp': 'webp',
  'image/gif': 'gif',
  'image/bmp': 'bmp',
  'image/heic': 'heic',
  'image/heif': 'heif',
};

function extFromMime(mime) {
  return MIME_EXT[(mime || '').toLowerCase()] || 'img';
}

// Persist one image_url part; returns "./img_N.ext" or null if it couldn't.
async function persistImage(url, dir, n) {
  if (typeof url !== 'string' || !url) return null;
  if (url.startsWith('data:')) {
    const m = /^data:([^;,]+)?(;base64)?,(.*)$/s.exec(url);
    if (!m) return null;
    const mime = m[1] || 'application/octet-stream';
    const isB64 = !!m[2];
    const ext = extFromMime(mime);
    const name = `img_${n}.${ext}`;
    const buf = isB64
      ? Buffer.from(m[3], 'base64')
      : Buffer.from(decodeURIComponent(m[3]), 'utf8');
    fs.writeFileSync(path.join(dir, name), buf);
    return `./${name}`;
  }
  // Remote URL: best-effort fetch so the CLI gets a local path to ReadMediaFile.
  // On any failure fall back to handing the raw URL to the model as text.
  if (/^https?:\/\//i.test(url)) {
    try {
      const resp = await fetch(url);
      if (!resp.ok) return url;
      const mime = resp.headers.get('content-type') || '';
      const ext = extFromMime(mime.split(';')[0].trim());
      const name = `img_${n}.${ext}`;
      const buf = Buffer.from(await resp.arrayBuffer());
      fs.writeFileSync(path.join(dir, name), buf);
      return `./${name}`;
    } catch {
      return url;
    }
  }
  return null;
}

// Build the prompt for the current user turn: join text parts, persist any
// image parts, append path references.
async function buildPrompt(userMsg, dir) {
  const content = userMsg.content;
  const textParts = [];
  const imageRefs = [];

  if (Array.isArray(content)) {
    let n = 0;
    for (const part of content) {
      if (typeof part === 'string') {
        textParts.push(part);
      } else if (part && (part.type === 'text' || typeof part.text === 'string')) {
        textParts.push(part.text || '');
      } else if (part && part.type === 'image_url' && part.image_url && part.image_url.url) {
        n++;
        const ref = await persistImage(part.image_url.url, dir, n);
        if (ref) imageRefs.push(ref);
      } else if (part && part.type === 'input_image' && (part.image_url || part.url)) {
        n++;
        const u = typeof part.image_url === 'string' ? part.image_url : part.url;
        const ref = await persistImage(u, dir, n);
        if (ref) imageRefs.push(ref);
      }
    }
  } else {
    textParts.push(content == null ? '' : String(content));
  }

  let prompt = textParts.join('\n');
  if (imageRefs.length) {
    prompt += '\n\n' + imageRefs.map(r => `See attached image: ${r}`).join('\n');
  }
  return prompt;
}

// ---------------------------------------------------------------------------
// Codex invocation with REAL streaming. Parses `codex exec --json` incrementally:
// each complete stdout line is one JSON event.
//
// Codex 0.146 ships TWO event schemas and which one `--json` emits can change
// between releases, so we handle both rather than pinning to one:
//
//   legacy "msg" schema:
//     {"id":..,"msg":{"type":"agent_message_delta","delta":"..."}}   -> delta
//     {"id":..,"msg":{"type":"agent_message","message":"..."}}       -> full text
//     {"id":..,"msg":{"type":"session_configured","session_id":".."}}-> session id
//   newer thread/turn/item schema:
//     {"type":"thread.started","thread_id":"..."}                    -> session id
//     {"type":"item.completed","item":{"type":"agent_message",...}}  -> full text
//
// Non-assistant items (reasoning, command execution, MCP tool calls) are
// deliberately ignored — Adolf's users see the answer, not the agent's work.
//
// Sequencing note: when a run emits streaming deltas AND a terminal full-text
// message, the full text is the same content already streamed. We therefore
// prefer deltas when any arrived, and fall back to the terminal message only
// when none did — otherwise the reply would be duplicated.
//
// onDelta(chunk) is called per assistant content fragment as it arrives.
// Resolves { text, sessionId } once the process closes.
function runCodex({ prompt, cwd, resumeId, onDelta, signal }) {
  return new Promise((resolve, reject) => {
    if (signal?.aborted) { reject(new Error('aborted before start')); return; }
    // `exec resume <id>` must come before the prompt; `--skip-git-repo-check`
    // is required because session dirs under /workspace are not git repos.
    //
    // `-C/--cd` is accepted by `codex exec` but NOT by `codex exec resume` —
    // passing it there fails with "unexpected argument '-C' found" and breaks
    // every follow-up turn while first turns still work. The spawn cwd below
    // already puts the process in the right directory, so -C is only an
    // explicit belt-and-braces on the fresh-session path.
    const args = ['exec'];
    if (resumeId) {
      args.push('resume', resumeId, '--json', '--skip-git-repo-check', prompt);
    } else {
      args.push('--json', '--skip-git-repo-check', '-C', cwd, prompt);
    }

    // stdin MUST be 'ignore'. With the default 'pipe', codex prints "Reading
    // additional input from stdin..." and blocks waiting for EOF on a pipe this
    // wrapper never writes to or closes — every turn would hang until the
    // 15-minute timeout. (Kimi's CLI did not read stdin, so this is new.)
    const child = spawn('codex', args, {
      cwd,
      timeout: TIMEOUT_MS,
      stdio: ['ignore', 'pipe', 'pipe'],
    });

    let buf = '';
    let stderr = '';
    const parts = [];       // streamed deltas, in order
    let finalText = null;   // terminal full-text message, if the run emits one
    let errText = null;     // structured error reported on the event stream
    let sessionId = null;
    let settled = false;
    let aborted = false;

    // If the caller aborts (the gateway/client disconnected — e.g. its idle
    // watchdog gave up), kill the child so it doesn't keep grinding an
    // orphaned agent turn to completion, wasting Codex quota and streaming into
    // a dead socket. SIGTERM first, hard SIGKILL if it lingers.
    const onAbort = () => {
      aborted = true;
      try { child.kill('SIGTERM'); } catch {}
      setTimeout(() => { try { child.kill('SIGKILL'); } catch {} }, 3000).unref();
    };
    if (signal) signal.addEventListener('abort', onAbort, { once: true });

    function handleLine(line) {
      const t = line.trim();
      if (!t) return;
      let obj;
      try { obj = JSON.parse(t); } catch { return; }

      // --- legacy "msg" schema -------------------------------------------
      const msg = obj.msg;
      if (msg && typeof msg.type === 'string') {
        if (msg.type === 'agent_message_delta' && typeof msg.delta === 'string' && msg.delta) {
          parts.push(msg.delta);
          if (onDelta) onDelta(msg.delta);
        } else if (msg.type === 'agent_message' && typeof msg.message === 'string' && msg.message) {
          finalText = msg.message;
        } else if (msg.type === 'session_configured' && msg.session_id) {
          sessionId = msg.session_id;
        } else if (msg.type === 'error' && msg.message) {
          errText = msg.message;
        }
        return;
      }

      // --- newer thread/turn/item schema ----------------------------------
      if (obj.type === 'thread.started' && obj.thread_id) {
        sessionId = obj.thread_id;
      } else if (obj.type === 'item.completed' && obj.item) {
        const item = obj.item;
        if (item.type === 'agent_message') {
          const text = typeof item.text === 'string' ? item.text : item.message;
          if (typeof text === 'string' && text) finalText = text;
        }
      } else if (obj.type === 'turn.failed') {
        errText = (obj.error && (obj.error.message || obj.error)) || 'turn.failed';
      }
    }

    child.stdout.on('data', d => {
      buf += d;
      let nl;
      while ((nl = buf.indexOf('\n')) !== -1) {
        const line = buf.slice(0, nl);
        buf = buf.slice(nl + 1);
        handleLine(line);
      }
    });
    child.stderr.on('data', d => { stderr += d; });

    child.on('error', err => {
      if (settled) return;
      settled = true;
      if (signal) signal.removeEventListener('abort', onAbort);
      reject(err);
    });
    child.on('close', code => {
      if (settled) return;
      settled = true;
      if (signal) signal.removeEventListener('abort', onAbort);
      if (buf) handleLine(buf); // flush any trailing partial line
      // Deltas win when present — the terminal agent_message repeats content
      // already streamed to the client. Only fall back to it if nothing streamed.
      const streamed = parts.join('').trim();
      const text = streamed || (finalText || '').trim();
      // A non-streaming run still has to reach the client: emit the terminal
      // message as one delta so callers relying on onDelta aren't left empty.
      if (!streamed && text && onDelta) onDelta(text);
      if (aborted) {
        reject(new Error('aborted: client disconnected'));
      } else if (!text && code !== 0) {
        reject(new Error(`codex exited ${code}: ${(errText || stderr).slice(0, 2000)}`));
      } else if (!text && errText) {
        reject(new Error(`codex error: ${errText.slice(0, 2000)}`));
      } else {
        resolve({ text, sessionId });
      }
    });
  });
}

// ---------------------------------------------------------------------------
// One turn: resolve session (chat_id primary, history-hash fallback), persist
// media, run codex (streaming through onDelta), record the mapping,
// and fire the async cognee ingest. Returns { text }.
async function handleTurn(messages, onDelta, signal) {
  const turns = convTurns(messages);
  let lastUserIdx = -1;
  for (let i = turns.length - 1; i >= 0; i--) {
    if (turns[i].role === 'user') { lastUserIdx = i; break; }
  }
  if (lastUserIdx === -1) throw new Error('no user message found');

  const userMsg = turns[lastUserIdx];
  const prior = turns.slice(0, lastUserIdx);
  const chatId = extractChatId(userMsg);

  // Resolve the session key + working dir + resume id.
  let key;
  let convId;
  let dir;
  let resumeId = null;
  let reseed = false; // when true, prompt with the full transcript to rebuild continuity

  if (chatId) {
    key = `chat:${chatId}`;
    const entry = sessionMap[key];
    if (entry) {
      convId = entry.convId;
      dir = entry.dir;
      resumeId = entry.sessionId;
    } else {
      convId = crypto.randomUUID();
      dir = path.join(CONV_ROOT, convId);
      // First time we see this chat_id but history exists (server restart / lost
      // map): reseed the fresh session with the transcript so context survives.
      reseed = prior.length > 0;
    }
  } else {
    // Fallback: no chat_id -> forward history-hash mapping.
    if (prior.length === 0) {
      convId = crypto.randomUUID();
      dir = path.join(CONV_ROOT, convId);
    } else {
      const entry = sessionMap[`hist:${historyKey(prior)}`];
      if (entry) {
        convId = entry.convId;
        dir = entry.dir;
        resumeId = entry.sessionId;
      } else {
        convId = crypto.randomUUID();
        dir = path.join(CONV_ROOT, convId);
        reseed = true;
      }
    }
  }

  fs.mkdirSync(dir, { recursive: true });

  let prompt;
  if (reseed) {
    // Rebuild the whole conversation for a fresh session, plus current media.
    const base = renderTranscript(turns.slice(0, lastUserIdx + 1));
    const media = await buildPrompt(userMsg, dir);
    // buildPrompt already includes the current user text; for reseed we want the
    // transcript to carry it, so only append image refs.
    prompt = base;
    const extra = media.replace(textOf(userMsg), '').trim();
    if (extra) prompt += `\n\n${extra}`;
  } else {
    prompt = await buildPrompt(userMsg, dir);
  }

  const { text, sessionId } = await runCodex({ prompt, cwd: dir, resumeId, onDelta, signal });

  // Record the forward mapping.
  const entry = { convId, sessionId: sessionId || resumeId, dir, ts: Date.now() };
  if (chatId) {
    sessionMap[`chat:${chatId}`] = entry;
  } else {
    const forward = turns.slice(0, lastUserIdx + 1).concat([{ role: 'assistant', content: text }]);
    sessionMap[`hist:${historyKey(forward)}`] = entry;
  }
  persistMap();

  return { text };
}

// ---------------------------------------------------------------------------
// Quota readout. The Kimi-specific implementation (kb #62/#87) was removed with
// the Codex migration: it authenticated against Kimi's managed-usage API using
// the Kimi CLI's OAuth creds file, and neither the endpoint nor the credential
// exists on this backend. Codex exposes no equivalent machine-readable quota
// endpoint, so /usage now reports "unsupported" rather than inventing numbers.
//
// The two consumers (kimi-quota-footer-plugin, quota-command-openclaw-plugin)
// both treat a non-OK /usage as "no data" and degrade quietly -- the footer is
// simply omitted. They still need a decision: retire them, or repoint them at
// whatever quota signal the Codex/ChatGPT plan actually exposes.
const USAGE_UNSUPPORTED = {
  error: 'usage_unsupported',
  backend: 'codex',
  detail: 'Codex backend exposes no machine-readable quota endpoint.',
};

// ---------------------------------------------------------------------------
// OpenAI-compatible HTTP surface.
function completionBody(text) {
  return {
    id: `chatcmpl-${Date.now()}`,
    object: 'chat.completion',
    created: Math.floor(Date.now() / 1000),
    model: MODEL_ID,
    choices: [{
      index: 0,
      message: { role: 'assistant', content: text },
      finish_reason: 'stop',
    }],
  };
}

function sseChunk(id, created, delta, finishReason) {
  return `data: ${JSON.stringify({
    id, object: 'chat.completion.chunk', created, model: MODEL_ID,
    choices: [{ index: 0, delta, finish_reason: finishReason }],
  })}\n\n`;
}

const server = http.createServer((req, res) => {
  if (req.method === 'GET' && req.url === '/v1/models') {
    res.writeHead(200, { 'Content-Type': 'application/json' });
    res.end(JSON.stringify({
      object: 'list',
      data: [{ id: MODEL_ID, object: 'model', owned_by: 'openai' }],
    }));
    return;
  }

  if (req.method === 'GET' && req.url === '/usage') {
    // 501 rather than 502: this is not a transient upstream failure, it is a
    // capability the codex backend does not have. Consumers already treat any
    // non-OK response as "no data" and omit the quota footer.
    res.writeHead(501, { 'Content-Type': 'application/json' });
    res.end(JSON.stringify(USAGE_UNSUPPORTED));
    return;
  }

  if (req.method === 'POST' && req.url === '/v1/chat/completions') {
    let body = '';
    req.on('data', d => { body += d; });
    req.on('end', async () => {
      let parsed;
      try {
        parsed = JSON.parse(body);
      } catch {
        res.writeHead(400, { 'Content-Type': 'application/json' });
        res.end(JSON.stringify({ error: 'invalid JSON body' }));
        return;
      }

      const messages = parsed.messages || [];

      if (parsed.stream) {
        // Real streaming: open SSE, emit role chunk, then forward codex deltas.
        res.writeHead(200, {
          'Content-Type': 'text/event-stream',
          'Cache-Control': 'no-cache',
          Connection: 'keep-alive',
        });
        const id = `chatcmpl-${Date.now()}`;
        const created = Math.floor(Date.now() / 1000);

        // Heartbeat keepalive: OpenClaw's LLM idle watchdog aborts a turn on
        // any >120s gap between SSE stream events (default timeoutSeconds),
        // not on total run length. During long thinking/tool/MCP phases Codex
        // emits stream-json events we don't forward, so the SSE stream can go
        // silent well past that window. Every write resets `lastWrite`; a 5s
        // ticker emits an empty-content delta once 25s of silence elapses —
        // still a stream event (resets the watchdog) but appends nothing
        // visible to the rendered reply or cognee-persisted text.
        let lastWrite = Date.now();
        const write = (delta, finish) => {
          if (res.writableEnded || res.destroyed) return;
          res.write(sseChunk(id, created, delta, finish));
          lastWrite = Date.now();
        };
        write({ role: 'assistant' }, null);
        const hb = setInterval(() => {
          if (Date.now() - lastWrite >= 25_000) write({ content: '' }, null);
        }, 5_000);

        // Propagate a client/gateway disconnect down to the codex child so an
        // abandoned turn (e.g. OpenClaw's idle watchdog gave up) is killed
        // instead of finishing invisibly and burning quota. `done` guards
        // against the normal res.end() 'close' also aborting.
        const ac = new AbortController();
        let done = false;
        res.on('close', () => { if (!done) ac.abort(); });

        try {
          await handleTurn(messages, delta => write({ content: delta }, null), ac.signal);
          done = true;
          write({}, 'stop');
          res.write('data: [DONE]\n\n');
        } catch (err) {
          done = true;
          // Headers already sent — surface the error inside the stream (unless
          // the socket is already gone, in which case there is nowhere to write).
          if (!res.writableEnded && !res.destroyed) {
            write({ content: `\n[error: ${String(err.message || err)}]` }, 'stop');
            res.write('data: [DONE]\n\n');
          }
        } finally {
          clearInterval(hb);
          if (!res.writableEnded) res.end();
        }
        return;
      }

      const ac = new AbortController();
      let done = false;
      res.on('close', () => { if (!done) ac.abort(); });
      try {
        const { text } = await handleTurn(messages, null, ac.signal);
        done = true;
        res.writeHead(200, { 'Content-Type': 'application/json' });
        res.end(JSON.stringify(completionBody(text)));
      } catch (err) {
        done = true;
        if (!res.writableEnded && !res.destroyed) {
          res.writeHead(500, { 'Content-Type': 'application/json' });
          res.end(JSON.stringify({ error: String(err.message || err) }));
        }
      }
    });
    return;
  }

  res.writeHead(404, { 'Content-Type': 'application/json' });
  res.end(JSON.stringify({ error: 'not found' }));
});

server.listen(PORT, () => console.log(`adolf-llm wrapper listening on :${PORT}`));