…detection

Add Matrix bridge mirroring telegram.py pattern, wrapped around matrix-nio
AsyncClient inside a dedicated asyncio loop on a worker thread.

Features:
- A2A envelope auto-detection: content.lstrip().startswith('{"a2a":"1"')
- Corr_id pending map + results dict for SafeRL-Lab#35 corr_id poll pattern prep
- Sync mx_send() helper schedules coroutines via run_coroutine_threadsafe
- Graceful degradation when matrix-nio not installed (clear stderr msg)
- MATRIX_BRIDGE export dict for cmd_matrix slash command registration
- register_a2a_handler hook for SafeRL-Lab#35 native a2a_delegate tool wiring

Not added to pyproject.toml dependencies yet (matrix-nio = follow-up
optional dep commit to keep core deps minimal).

Pending wiring: _drain_mx_queue() must be hooked into main REPL tick
loop (caller integration, not this commit's scope). Subagent scaffold
410L (~210 dense, ~200 docstring/blank) per architech review.

refs SafeRL-Lab#33 SafeRL-Lab#35

Native cheetahclaws A2A v1 delegation via Matrix bridge (SafeRL-Lab#33).

a2a_delegate(target_mxid, task, ...): emits delegate envelope via
mx_send, registers corr_id in _mx_a2a_pending, returns immediately.
Agent stays free to continue other work.

a2a_poll_result(correlation_id, timeout_sec=90): blocks on pending
event until result envelope arrives OR timeout. One-shot consume
(pop pending+result). Returns timeout status on deadline, error on
unknown/consumed corr_id.

Design addresses pilot SafeRL-Lab#6: sync tool exec blocked main loop for
30-120s on round-trips. Poll pattern decouples submit from await.

Smoke tests PASS: registration + schema + no-bridge + missing-param
+ unknown-corr + E2E mock roundtrip (0.5s roundtrip) + timeout path.

Pending wiring: register_a2a_handler runtime init hook, matrix-nio
optional-dependencies add.

refs SafeRL-Lab#33 SafeRL-Lab#35

Pre-POC bundle wires Silverhawk fork MVP core into cheetahclaws runtime:

1. cheetahclaws.py: import bridges.matrix + tools.a2a_delegate,
   COMMANDS['matrix']=cmd_matrix, COMMAND_HELP entry
2. web/api.py: add bridges.matrix to bridge auto-discovery
3. pyproject.toml: silverhawk-matrix optional = matrix-nio>=0.24.0
4. bootstrap.py: step 2.b register_a2a_handler logging POC handler,
   non-fatal if bridge absent

Smoke PASS: COMMANDS wired, tools registered, bootstrap runs clean,
pip install -e '.[silverhawk-matrix]' installable.

MVP core pre-POC wiring complete. Ready SafeRL-Lab#38 E2E.

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

… attribution

Add SILVERHAWK-FORK.md explaining:
- Why Silverhawk forks cheetahclaws (V2 chat brick pivot per user directive)
- What's customized (5 commits mapped: license, MCP, Matrix, a2a, wiring)
- Integration map pointers (docs/cheetahclaws-arch-map.md,
  docs-silverhawk/mcp-silverhawk-plug.md)
- Upstream tracking + contribution-back candidates (license fix)
- License Apache-2.0 matches upstream

Separate from upstream README.md (preserved as-is) to keep delta clear.

refs SafeRL-Lab#32 SafeRL-Lab#33 SafeRL-Lab#34 SafeRL-Lab#35 SafeRL-Lab#46 SafeRL-Lab#53

…-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