Documents the complete feature lifecycle: grilling → to-prd → to-issues
into .scratch/, then /close-feature graduates to docs/. Covers conventions
for both active and closed features, and the proactive close-feature trigger.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- New /close-feature skill graduates .scratch/<slug>/ to docs/ when all
issues are done; also offers to run proactively when it detects a complete
feature. Documents machine setup steps (Linux/Mac, Windows, Codex, new skill
install) in the skill itself.
- Fix AGENTS.md issue-tracker line to reflect the .scratch → docs/ workflow.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Move issues (01–29) and PRD from .scratch/distributed-inference-network/
into docs/issues/ and docs/. Update ralph_progress.py DEFAULT_PRD path
and rewrite docs/agents/issue-tracker.md to reflect the new layout.
The distributed_inference_network.egg-info/docs/ mirror is a build
artifact already covered by *.egg-info/ in .gitignore — not committed.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- cli.py: change default --quantization from bfloat16 to int8; saves
~50% VRAM/RAM for new nodes that don't specify a quantization
- startup.py: display memory budget and GPU info in GB (e.g. 124.9 GB RAM)
instead of MB; show remaining headroom after full model load
- test_tracker_routing.py: add test_shard_heal_cycle_surviving_node_covers_dead_peers_gap
— end-to-end proof that:
1. tracker purges expired node A and queues LOAD_SHARD for node B
2. node B receives directive on next heartbeat
3. TorchNodeServer.apply_tracker_directives hot-swaps the backend
4. node B re-registers covering the full model; coverage gap closed
Test runs in <1s with monkeypatched _load_backend (no GPU needed)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Replace stale "only this works" PowerShell comment with accurate relay
one-liner that works from behind NAT without --advertise-host
- Expand "Public tracker + WSS relay" into a full architecture section:
nginx proxy paths, start commands, relay hop sequence, Base64 encoding
- Add WSL2 two-node relay test scenario with curl examples
- Document startup output when relay connects (Relay connected line)
- Remove "Start the relay node" stub; fold into the main relay section
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Nodes behind NAT (5G, WSL2, home routers) can now participate in
distributed pipeline inference over the internet via the relay server.
- torch_server: add module-level _relay_hop() that opens a WebSocket
to relay.../rpc/{peer_id}, sends the binary activation with
body_base64 encoding, and returns (status, headers, body)
- torch_server: _get_remaining_route returns list[dict] (was list[tuple])
preserving relay_addr from injected X-Meshnet-Route header and
from /v1/route slow-path node info
- torch_server: _run_downstream_pipeline dispatches via _relay_hop
when hop has relay_addr; falls back to direct HTTP on relay error
- tracker server: downstream_hops dicts include relay_addr when node
has one registered, so head node knows how to reach each peer
- relay_bridge: binary bodies (bfloat16 activations) use body_base64;
response preserves all X-Meshnet-* headers
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Nodes running inside WSL2 or Docker have a virtual network interface whose IP
(172.16-31.x.x) is not reachable from physical machines on the LAN. The UDP
socket probe for outbound IP returns this virtual IP, which gets registered with
the tracker — causing downstream pipeline hops to time out with "urlopen error
timed out".
_warn_virtual_network_ip() now prints a clear multi-line warning at startup
when the auto-detected advertise IP falls in 172.16.0.0/12, including the
fix: --advertise-host <LAN-ip>.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
