popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
90 Commits 7 Branches 0 Tags
b448dd037f991c6ff1637beb628442144fc161ed
Commit Graph

9 Commits

Author SHA1 Message Date
Dobromir Popov
94d2216a28 Merge branch 'master' of https://git.d-popov.com/popov/neuron-tai 2026-06-30 21:19:49 +02:00
Dobromir Popov
344f432880 tasks 2026-06-30 21:19:47 +02:00
Dobromir Popov
2b439e8a5f docs: add US-020–029 issue files, ADR 0011–0014, update prd.json to 29/29 
Issue files (.scratch/issues/20-29): retrospective specs for all work
done in the current sprint — hardening, route-timeout, start-layer
protocol, heartbeat stats, availability map, rolling RPM, smart
assignment, throughput routing, routing tests, relay outbound client.

ADRs (docs/adr/0011-0014):
  0011 — Auto-shard from memory budget and tracker network assignment
  0012 — X-Meshnet-Start-Layer overlapping shard execution protocol
  0013 — Rolling RPM statistics, smart assignment scoring, throughput routing
  0014 — Relay outbound client for NAT/internet pipeline hops

prd.json: US-020 through US-029 added, all marked done. ralph_progress.py
now shows 29/29 complete (100%).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-30 22:15:41 +03:00
Dobromir Popov
df473ef278 fix LAN discovery/connection 2026-06-30 16:16:20 +02:00
Dobromir Popov
1bdfce657d inference working 2026-06-29 23:54:35 +03:00
Dobromir Popov
8ea70ff6a0 docs(us-015): add Part 4 — per-story agent/worktree/summary in dashboard 
Each story shows an optional second line:
  agent · status · worktree path (if not main) · last output summary

Sources: git worktree list, agent-config.json, session.json,
completionNotes, git log on feat/<id> branch, iteration logs.
--compact flag suppresses metadata lines.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-29 16:21:57 +03:00
Dobromir Popov
d3bb50a894 feat(prd): add US-015 — Ralph agent-agnostic runner + status-field dashboard 
Status-field awareness:
- Replace passes:bool with status field in ralph_progress.py
- Six buckets: done, attention, active, in-design, ready, blocked
- Dashboard shows ⚠ Attention Required section for to-revise/needs-review
- auto skips attention stories by default; --include-revise overrides

Agent agnosticism:
- --agent codex|claude|openrouter|custom on all run commands
- Persistent config in .ralph-tui/agent-config.json via set-agent subcommand
- OpenRouter adapter: calls API directly when ralph-tui lacks native plugin
- custom: --agent-cmd <script> receives prompt file as $1

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-29 16:10:28 +03:00
Dobromir Popov
b02e07d308 docs: add ADRs and user stories for real model inference stack (US-011–014) 
ADR-0008: binary activation wire format — raw bfloat16 over HTTP, zstd compression,
128-token chunked prefill; replaces base64 JSON (~33% overhead removed).

ADR-0009: coverage-first shard assignment and tracker-as-first-layer-node —
any node serving layers[0..k] becomes the inference entry point for that model;
bin-packing fills all coverage gaps before adding redundancy; tracker issues
LOAD_SHARD/DROP_SHARD rebalance directives; nodes declare VRAM + quantization.

US-011: binary wire format migration
US-012: real PyTorch layer execution (transformers + bitsandbytes, test on GPT-2)
US-013: coverage-first tracker bin-packing with VRAM-aware shard assignment
US-014: tracker-as-node (tracker node serves first layers + handles client requests)

CONTEXT.md: Tracker Node, Coverage Map, Rebalance Directive terms added.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-29 14:43:54 +03:00
Dobromir Popov
2f1f9717be tasks 2026-06-29 00:10:21 +03:00