docs: capture all session changes — port conflict, health check, streaming

Updated contracts to reflect all infrastructure changes made 2026-07-05/06:

gpu-fleet.prose.md:
  - Port conflict detection on all 3 GPU wrappers
  - Ghost process root cause documented (.8 stale pid 25836)

infrastructure-control.prose.md:
  - Section 7: Agent Health Check (consolidated, non-disruptive)
  - Disabled scripts documented (zulip-watchdog, zulip-monitor)

hermes-agent-baseline.prose.md:
  - Health verification section + GPU port conflict detection
  - Change log updated

zulip-health.prose.md:
  - Streaming support section (edit_message + PATCH API)

gpu-fleet.prose.md

@@ -27,6 +27,7 @@ triggers:
 - benchmarks: { tok_per_sec: map, baseline: map, history: array } — Inference speed benchmarks tracked over time
 - grafana: { status: "running", dashboards: ["gpu-fleet"] } — Grafana on CT 116 (:3001)
 - prometheus: { status: "running", targets: 5 } — Scrapes GPU :9400 exporters + LiteLLM
+- port_conflict_detection: { status: "active" } — All 3 GPU wrappers detect ghost processes before binding
 
 ## Fleet Topology (Current — June 2026)
 
@@ -171,6 +172,7 @@ If no SSH access, send Zulip DM via abiba-bot.
 - **RTX 3090 optimization**: `--parallel 2 --batch-size 4096` — doubled concurrent throughput.
 - **RTX 5070 optimization**: Removed draft model freed ~2GB VRAM for vision tasks. `--parallel 2`.
 - **Strix Halo GPU**: Vulkan is the working backend (ROCm/HIP path abandoned — HSA runtime blocked on Debian 13). Build at `/root/llama.cpp/build-vk/`, commit `4fc4ec5` (2026-07-01), ggml 0.15.3 shared-lib arch. Mesa RADV 25.0.7, KHR_coopmat fast path active. ~70 tok/s gen, 532 tok/s prompt. Service: `ornith-server.service` on port 8080, 256K context, flash-attn + q8 KV.
+- **Port conflict detection (2026-07-05)**: All 3 GPU wrappers now detect ghost processes squatting port 8080 before starting. `.8` and `.110` use inline pre-start check in `llama-wrapper.sh`; `.15` uses `/usr/local/bin/port-cleanup.sh` ExecStartPre. Replaces the blanket `pkill -9 -x llama-server` on .15 which would kill ALL llama-server instances regardless of port. Ghost detection was the root cause of .8 crash-looping for 27+ restarts (stale pid 25836 squatting 8080 after OOM kill).
 - **Strix Halo thermal safeguard (2026-07-02)**: `ornith-server.service` has `-n 8192` (hard generation cap per request). Without it, `--predict` defaults to -1 (infinity) — a runaway request from .123 (Mumuni) decoded 39,868 tokens over 24 min, pushing Tctl to 98°C (crit 89.8°C) and throttling 70→29 t/s. The cap bounds worst-case generation to ~5 min. Do NOT remove `-n` without a replacement ceiling. Sustained load hits ~84°C even at 92s; the APU is fanless/low-flow. Clients MUST also set `max_tokens`.
 - **Port 8080 firewall**: amdpve iptables restricts 8080 to 192.168.68.116 (LiteLLM/router host) only. All inbound connections are from .116 (LiteLLM proxied via nginx). Localhost curls hang (SYN dropped). Always test from .116.
 - **Router sidecar fallback**: `router.py` `check_gpu_health()` now probes GPU `/health` directly when sidecar at :8090 is absent. Sidecar JSON exporters not deployed on any GPU host — router relies on GPU-direct fallback.