openai: shared MCP layer + openclaw-tools bridge [Adolf P5]

- adolf-llm/server.js now loads SHARED_MCP_SERVERS from the mounted
  /shared-mcp.json instead of a hardcoded stub, so adding a shared MCP
  server is a one-file change. Verified end-to-end: a real chat-completions
  turn writes a session .mcp.json containing both cognee and openclaw-tools
  entries (kimi itself still needs `kimi login` in adolf-llm-home, unrelated
  to this change).
- Documented the Gate-1 transport reconciliation: decompiled the installed
  @moonshot-ai/kimi-code package to confirm its .mcp.json schema keys remote
  servers on `transport` ("stdio"/"http"/"sse", inferred as "http" from a
  bare `url`, never "sse"), while OpenClaw's own canonical mcp.servers schema
  uses different literals ("streamable-http"/"sse") for the same field name
  and treats `type` as a CLI-native alias it normalizes itself. `type: "http"`
  is the one shape both consumers tolerate, so shared-mcp.json keeps it.
- New openai/openclaw-tools/ service: a stateless MCP-over-Streamable-HTTP
  bridge (Node, @modelcontextprotocol/sdk) exposing message_send, cron_create,
  cron_list, nodes_invoke, and browser_invoke, each proxying to the OpenClaw
  gateway's POST /tools/invoke. Verified initialize + tools/list handshake and
  a tools/call against the not-yet-running `adolf` gateway returns a clean
  isError content instead of breaking the MCP connection. Documented that
  cron/nodes are hard-denied on that HTTP surface by default until P6 adds
  them to gateway.tools.allow; message/browser are not similarly restricted.
- Wired openclaw-tools into docker-compose.yml (openai network, :8020) and
  added its shared-mcp.json entry alongside cognee.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LeqyaxJF2nbRXJtae2kNB2

openai/adolf-llm/server.js

@@ -19,21 +19,45 @@ fs.mkdirSync(STATE_DIR, { recursive: true });
 
 // ---------------------------------------------------------------------------
 // Shared MCP layer (Gate 1). Kimi Code CLI has NO `--mcp-config-file` flag and
-// no `kimi mcp` subcommand; it auto-discovers a project-root `.mcp.json`
-// (Claude-Code-compatible schema) by walking up from its cwd. So we drop a
-// `.mcp.json` into each session's working directory before spawning kimi.
+// no `kimi mcp` subcommand; it auto-discovers a project-root `.mcp.json` by
+// walking up from its cwd to the nearest `.git` (falling back to cwd itself
+// when none is found). So we drop a `.mcp.json` into each session's working
+// directory before spawning kimi.
 //
-// STUB: the server list is empty for now. cognee-mcp (memory_search/add/cognify,
-// P4) and the openclaw-tools bridge (P5) do not exist yet. Wiring them later is
-// a one-line change here — add entries to SHARED_MCP_SERVERS and every future
-// session dir picks them up automatically. Schema per server, e.g.:
-//   cognee:        { command, args, env }                       (stdio)
-//   openclaw-tools:{ type: "sse"|"http", url, headers }          (remote)
-// TODO(P4/P5): populate SHARED_MCP_SERVERS from cognee-mcp + openclaw-tools.
-const SHARED_MCP_SERVERS = {
-  // TODO(P4): "cognee": { command: "...", args: [...], env: {...} },
-  // TODO(P5): "openclaw-tools": { type: "sse", url: "http://openclaw:.../mcp" },
-};
+// Single source of truth: `/shared-mcp.json` (mounted read-only from the repo
+// root's `shared-mcp.json`, the same file P6 wires into OpenClaw's own
+// `mcp.servers` registry). Adding a server is then a one-file change — no
+// server list is hardcoded here anymore.
+//
+// Gate-1 transport finding (P5, verified by decompiling the installed
+// @moonshot-ai/kimi-code package, packages/agent-core/src/config/schema.ts's
+// McpServerConfigSchema): Kimi's own field name for remote MCP servers is
+// `transport` (literal "stdio" | "http" | "sse"), not `type`. When `transport`
+// is omitted, Kimi's config preprocessor infers it from shape: `command` ->
+// "stdio", `url` -> "http" (never "sse" — sse requires an explicit
+// `transport: "sse"`). It does NOT recognize a `type` key at all; unknown keys
+// are silently stripped by the (non-strict) zod schema.
+// OpenClaw's own canonical `mcp.servers` schema (docs/gateway/
+// configuration-reference.md) uses different literals for the same
+// transport: `transport: "streamable-http"` or `"sse"`, with `type: "http"`
+// documented as a *CLI-native alias* that `openclaw mcp set` / `openclaw
+// doctor --fix` normalize into canonical `transport: "streamable-http"`.
+// So the two consumers disagree on the literal value for HTTP streaming
+// ("http" vs "streamable-http") under the same field name `transport` --
+// writing `transport` explicitly in shared-mcp.json would satisfy at most one
+// side. `type: "http"` is the one shape both sides tolerate today: Kimi
+// ignores the unrecognized `type` key and correctly infers transport "http"
+// from the `url` field alone; OpenClaw recognizes `type` as its documented
+// alias and normalizes it on its own terms (P6 concern, not touched here).
+// Hence shared-mcp.json intentionally keeps `"type": "http"` for both cognee
+// and openclaw-tools rather than switching to `transport`.
+let SHARED_MCP_SERVERS = {};
+try {
+  const raw = fs.readFileSync('/shared-mcp.json', '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`);
+}
 
 function writeMcpConfig(dir) {
   const cfg = { mcpServers: SHARED_MCP_SERVERS };