Commit Graph

60 Commits

Author SHA1 Message Date
Dobromir Popov
dbf856f497 feat: tracker-as-first-layer-node inference entry point (US-014)
- Tracker: add GET /v1/tracker-nodes/<model> returning nodes registered
  with tracker_mode=true whose shard_start matches the model's first layer
- Node: StubNodeServer and TorchNodeServer accept tracker_mode/tracker_url;
  when tracker_mode=True (or auto-detected via shard_start==0 for Torch),
  /v1/chat/completions is served alongside /forward
- TorchNodeServer: full pipeline implementation — encode_prompt → route
  selection via tracker → binary forward through remaining hops → decode
- Gateway: _handle_chat_completions checks _get_tracker_nodes() first and
  proxies round-robin to tracker-nodes; falls back to existing direct
  pipeline when none found (preserves all US-005 backward compat)
- CLI: --tracker-mode and --tracker-url flags added to meshnet-node start
- Test: two stub tracker-nodes + two mid-shard nodes for gpt2; 10 requests;
  round-robin 5/5 split verified; all OpenAI-format responses validated
- All 78 tests pass

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-29 16:59:32 +03:00
Dobromir Popov
753f553766 feat: coverage-first tracker shard assignment (US-013)
Recovered from interrupted Codex session (ended 13:02, changes uncommitted).
All 74 tests pass.

- Tracker accepts vram_bytes, ram_bytes, quantizations[], benchmark_tokens_per_sec
  in node registration payload
- GET /v1/coverage/<model_preset> returns [{start_layer, end_layer, node_count}]
- Coverage-first bin-packing: fills gaps before adding redundancy
- Speed-weighted assignment: faster nodes get wider shard ranges
- LOAD_SHARD/DROP_SHARD rebalance directives delivered via heartbeat responses
- Model is unroutable when any layer range has node_count=0
- model_presets.json config for bytes_per_layer at each quantization level

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-29 16:37:48 +03:00
Dobromir Popov
3286f77e27 feat: add meshnet python sdk 2026-06-29 10:29:19 +03:00
Dobromir Popov
e9c9bf63bc feat: add p2p shard swarm 2026-06-29 10:15:01 +03:00
Dobromir Popov
792a9fd97f feat: add probation and ban enforcement 2026-06-29 09:58:32 +03:00
Dobromir Popov
e24c2e3cea feat: add settlement contract boundary 2026-06-29 02:46:25 +03:00
Dobromir Popov
3b7ef2743d feat: add OpenAI-compatible gateway
- GET /v1/health, GET /v1/models, POST /v1/chat/completions (streaming + non-streaming)
- OpenAI SDK, LangChain ChatOpenAI, and SSE streaming integration tests
- Tracker-backed GET /v1/models endpoint
- OpenAI-format errors for unavailable model (503) and pipeline failures
- Malformed JSON body handled with 400 instead of crash
- Test deps (openai, langchain-openai) declared in root pyproject dev extras

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-29 01:52:45 +03:00
Dobromir Popov
0199c99f6b feat: add node startup flow 2026-06-29 01:30:12 +03:00
Dobromir Popov
15897d5c95 feat: add tracker registration routing 2026-06-29 01:16:48 +03:00
Dobromir Popov
1141b51286 feat: scaffold meshnet monorepo 2026-06-29 00:28:29 +03:00