Commit Graph

20 Commits

Author SHA1 Message Date
Dobromir Popov
377346c301 [verified] feat: complete Ralph task workstreams 2026-07-12 11:17:03 +03:00
Dobromir Popov
f54ea100fb issues, chat FPS; optimisations 2026-07-10 01:30:07 +03:00
Dobromir Popov
81057dd795 doctor docs 2026-07-09 23:41:11 +03:00
Dobromir Popov
08826f6ace Merge branch 'master' of https://git.d-popov.com/popov/neuron-tai 2026-07-09 00:06:01 +03:00
Dobromir Popov
daddbaa4a3 distributd cache 2026-07-08 22:53:03 +02:00
Dobromir Popov
94046f1102 misc 2026-07-08 23:32:51 +03:00
Dobromir Popov
518c259cd3 routing improvements - dynamic (wip) 2026-07-07 21:25:28 +02:00
Dobromir Popov
e2b20883ca Stream chat responses in the dashboard with live progress and unified styles
Chat now sends stream=true and renders SSE tokens incrementally with live
tok/s status, a stop button (AbortController), and a blinking cursor; because
streamed requests emit tracker 'proxy progress' events, the Call wall now
shows in-flight requests with live TPS too. Chat colors route through :root
tokens instead of hardcoded hex values.

ADR-0020 documents the changes and the mixed-topology routing flaw: a partial
GPU head (0-21) + full CPU node (0-39) gets downstream start_layer=0 instead
of 22, corrupting activations into 1-token generations that were billed and
polluted throughput stats. Fix steps recorded, not yet implemented.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-07 19:48:43 +02:00
D.Popov
68e057209c Add alpha-hardening ADRs and issue plan from pre-release audit.
Lock alpha scope, tracker auth, TOPLOC fraud verification, and deferred multi-tracker money-path work; supersede legacy fraud issues with ADR-0018.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-04 23:12:09 +03:00
Dobromir Popov
a938c19a82 dash works !!! good data. billing seems to work 2026-07-02 23:07:41 +02:00
Dobromir Popov
416ceba0f6 refine blockchain integration and protocols 2026-07-02 21:14:15 +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
1bdfce657d inference working 2026-06-29 23:54:35 +03:00
Dobromir Popov
cd9e3686a5 docs(adr-0002): lock TAI tokenomics — 1B supply, revenue-backed, 90% floor
Locked decisions:
- 1 billion TAI hard cap, no minting, halving-style emission decay
- No transfer tax; spread-only revenue, decreases with volume
- Buyback floor = 90% of current organic backing price (ratcheting up)
- Wind-down guarantee: 90% floor always funded by protocol spread
- Post-listing speculative risk acknowledged and accepted
- Node bootstrap: probationary period = stake-free entry (no loan/grant)
- Listing threshold (provisional): $50k volume AND 25 nodes / 15+ operators

Open parameters noted: halving schedule, dynamic spread curve, listing %, legal.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-29 15:34:15 +03:00
Dobromir Popov
202b579bd1 docs(adr-0002): rewrite TAI tokenomics with revenue-backed model
- Token named TAI, fixed supply (BTC-inspired), no open market during bootstrap
- Price anchored to inference revenue: team holds ~100% → 36% over ~5 years
- 95% soft buyback floor; ~10% protocol spread funds wind-down reserve
- Wind-down guarantee: protocol can always buy back all issued TAI at issue price
- Open questions section captures unresolved parameters for token launch

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-29 15:15:15 +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
a2aa22fc08 docs: clarify validation slash model 2026-06-29 02:47:36 +03:00
Dobromir Popov
8900990193 docs: clarify contract boundary 2026-06-29 02:31:23 +03:00
Dobromir Popov
2f1f9717be tasks 2026-06-29 00:10:21 +03:00
Dobromir Popov
0f24a1d4f9 iinit 2026-06-28 23:49:11 +03:00