Wire silverhawk-mcp TS stdio MCP server (13+ tools) into cheetahclaws fork
via native cc_mcp client config (.mcp.json, project-scope).

Raw JSON-RPC handshake validated against silverhawk-mcp v0.1.0:
- initialize → protocolVersion=2024-11-05, serverInfo=silverhawk-mcp
- tools/list → all 13+ tools returned with schemas
- boot.health.ok + server.connected + clean SIGTERM shutdown rc=0

Known gap flagged in docs-silverhawk/mcp-silverhawk-plug.md: cc_mcp
MCPManager.connect_all hangs on handshake via managed path despite raw
handshake succeeding in 200ms. 75/75 test_mcp.py upstream still pass so
likely client-side race for this server's output timing. Plug config
validated via raw transport proof; cc_mcp debug deferred post-POC.

Container deploy spec for devop-master SafeRL-Lab#37 included.

Local fork commit, not pushed pending GitLab namespace confirm.

refs SafeRL-Lab#34 SafeRL-Lab#37

…-serve.py + launch runbook

Wire Path B option δ for POC SafeRL-Lab#38: cheetahclaws runs standalone Matrix
agent bypassing chat-server-bin.

Adds:
- CLAUDE.md at fork root: pilot role overlay (Cas A forward-verbatim +
  MXID roster + A2A rules) sourced from DevopMaster agent/roles/prompts/
  pilot.md. Cheetahclaws reads it as system context.
- scripts/silverhawk-matrix-serve.py: standalone launcher binding matrix
  bridge inbound queue → agent.run() → mx_send outbound reply. Bypasses
  chat-server-bin entirely. SIGTERM-safe, accept_all permissions for POC.
- docs-silverhawk/poc-38-launch-spec.md: runbook for devop-master (new
  Matrix token generation via Dendrite login, stop classic supervisor
  units, launch cheetahclaws standalone, smoke probe, observation setup,
  POC run plan, rollback).

Closes wiring gap flagged post-SafeRL-Lab#37 (cheetahclaws installed but not
active runtime). Enables true POC thesis validation.

refs SafeRL-Lab#33 SafeRL-Lab#34 SafeRL-Lab#35 SafeRL-Lab#37 SafeRL-Lab#38

…Lab#56

Add scripts/silverhawk-launch.sh (bash wrapper):
- Sources /usr/local/bin/glm to export ANTHROPIC_AUTH_TOKEN + BASE_URL
  (z.ai gateway Anthropic-compat for glm-* models)
- Parses /home/ide/.config/matrix/credentials.json for MATRIX_*
- Uses pkill pattern for stop-start swap (supervisorctl broken in
  these containers per preflight audit SafeRL-Lab#56)
- Execs silverhawk-matrix-serve.py in foreground

Update runbook poc-38-launch-spec.md per preflight findings:
- No new Matrix token generation needed (reuse credentials.json +
  stop-start swap frees the @testbot session cleanly)
- pkill stop pattern (supervisord lacks [supervisorctl] section)
- Cred sourcing inline from /usr/local/bin/glm + credentials.json
- Simplified 6-step checklist (fork pull → matrix-nio install →
  creds confirm → stop classic via launcher → launch → smoke)
- Rollback procedure (pkill serve + nohup restart classic)

refs SafeRL-Lab#33 SafeRL-Lab#34 SafeRL-Lab#35 SafeRL-Lab#37 SafeRL-Lab#38 SafeRL-Lab#56