7.5 KiB
Alpha hardening — planning index
Pre-release alpha audit + grilling (2026-07-04). Bucket 1 trust-boundary blockers + fraud arc: done (16/22 original issues). Bucket 2 (12-15, multi-tracker) and 17 (doc dedup) remain deferred/human-gated — not launch blockers.
Launch-readiness grilling (2026-07-06): locked plan is devnet dev/test run now, then real mainnet SOL/USDT for the first cohort — friends (API clients) + hired VPS/VPC hosts (own test infra, not third-party volunteers, stake-free). No new public token; TAI stays dormant per ADR-0002's existing volume/legal gates. Two new issues came out of this session:
- 21 — Honest-noise calibration corpus — rescoped from "prod gate" to a hard alpha-release blocker.
Status: ready-for-human— engineering (audit.py raw divergence, tracker dispatch endpoint, SQLite corpus, p99 envelope) done 2026-07-06; blocked on a human running the calibration job against the real hired-VPS fleet before launch. - 23 — Dynamic HF-benchmarked pricing — new, high priority but not a release blocker.
Status: done— engineering complete 2026-07-06 (hf_pricing.py, opt-in daily refresh loop, GET /v1/pricing/hf/history); realhf_aliasescuration per model is a follow-up human sign-off, not a completion blocker.
Locked scope: one settlement tracker, open node join, devnet mock-USDT, reputation carries forward → fraud must be bounded. See ADR-0016.
Resume task (2026-07-07): 24 - Routing telemetry resume is ready-for-agent. Learned-routing commit 518c259 is already present; dirty tree contains current-request heartbeat/dashboard telemetry and a known import-time annotation crash in server.py:1490.
Perf follow-up (2026-07-08): 25 — Sharded per-node KV cache for distributed generation is implemented (ADR-0022): per-generation session ids, prefill/decode wire protocol (X-Meshnet-Cache/X-Meshnet-Past-Len), per-node sharded DynamicCache(config=…) (hybrid-attention-aware), TTL+LRU eviction with 409 cache-miss → full re-prefill fallback. Golden test proves token-identical output vs the stateless path; CPU two-shard measurement: 7.05 tps decaying 32% → 18.93 tps flat (2.68×). Remaining: re-measure on the live 2-node GPU topology and the Qwen3.6-35B-A3B mixed topology.
Artifacts
| Path | Status |
|---|---|
| research-verifiable-inference.md | Complete — SOTA research, §8 layered scheme, TOPLOC adopt |
| handoff.md | Session handoff — locked decisions, env notes |
| docs/adr/0016–0019 | Alpha scope, auth, fraud, multi-tracker design |
| issues/ | 25 work items (Buckets 1–3 + perf follow-ups) |
ADRs (this feature)
| ADR | Title |
|---|---|
| 0016 | Alpha scope & known limitations |
| 0017 | Tracker authentication & authorization |
| 0018 | Fraud detection, verification & reputation (flagship) |
| 0019 | Money-path consistency — design accepted, impl deferred |
| 0002 | Amended — settlement superseded by 0015 |
| 0010 | Amended — TLS alpha reality (relay only) |
Recommended implementation order
Implement Bucket 1 first. Fraud arc depends on auth foundation (02 + 20), hive gossip enforcement (01), and persistence (05).
Phase 1 — Trust boundary (alpha blockers)
| Order | Issue | ID | Depends on |
|---|---|---|---|
| 1 | Unified auth boundary + Validator service token | A2, — | — |
| 2 | C1 hive gossip auth enforcement | C1 | 02 |
| 3 | Persist strike/ban/reputation | A1/A5 | 02 |
| 4 | Starting credit 0 + spend cap | C5, M1 | 02 |
| 5 | Tracker-authoritative accounting | H2 | 02 |
| 6 | Wallet binding proof | C6 | 02, 03 |
Phase 2 — Fraud arc (after Phase 1)
| Order | Issue | Depends on |
|---|---|---|
| 6 | TOPLOC integration | 05 |
| 7 | Commitment + bisection blame | 06 |
| 8 | Reputation model | 05, 07 |
| 9 | Routing + adaptive audit | 08 |
| 10 | Penalty calibration wiring | 07, 08, 02 |
Prod gate: 21 honest-noise calibration corpus must complete before enabling production TOPLOC audit thresholds (issues 09–10 in prod). Dev/staging TOPLOC wiring (06–08) may proceed in parallel.
Phase 3 — Bucket 2 (post-alpha, design tracked)
| Issue | ADR |
|---|---|
| 12 C2 on-chain idempotency | 0019 §1 |
| 13 C3/C4 consensus-gated settlement | 0019 §2 |
| 14 A3 durable Raft term/vote | 0019 §3 |
| 15 H1 commutative forfeit | 0019 §4 |
Phase 4 — Doc hygiene (parallel anytime)
| Issue |
|---|
| 16 US-006 + fraud issue reconciliation |
| 17 Duplicate US-020 dedup |
| 18 Operational runbooks |
| 19 Cryptography + test env |
| 22 MEMORY + project-status index (done) |
| 21 Honest-noise calibration corpus (ops; prod gate for audits) |
Phase 5 — Distributed-inference performance (post-routing-fix)
| Issue | Depends on |
|---|---|
| 25 Sharded per-node KV cache | ADR-0020 routing fix (done), 24 routing telemetry resume |
First 3 to implement
- 02 + 20 — Unified auth boundary + validator service token (shared helper and roles)
- 01 — Apply hive auth to billing/accounts/stats gossip endpoints
- 05 — Persist strike/ban/reputation (penalties must survive restart)
Research anchor
Fraud design cites .scratch/alpha-hardening/research-verifiable-inference.md:
- ADOPT TOPLOC (§8–9, build-vs-adopt table)
- On-demand commitments, not every request (§8 layer 1 footnote; ADR-0018 §3)
- 5% audit budget as target, not cap (§1.1, §6)
- 19× deterrence via full pending forfeiture (§1.1)
- Hop bisection blame pattern (§1.2, §8 layer 3)
- Honest-noise corpus before prod thresholds (§8 layer 3; issue 21)
- Roadmap-only: zkML, TEE, Gensyn RepOps (§9)