DGR-046: Define the V4 typed architecture boundary schema #30

New Issue

popov · 2026-07-16T20:36:04Z

popov commented

2026-07-16 20:36:04 +00:00

DGR-046: Define the V4 typed architecture boundary schema

Status / triage: specification only; ready-for-agent; passes: false
Execution mode: AFK
Milestone: M3
Dependencies: DGR-021, DGR-045
Blocks (derived): DGR-047, DGR-048, DGR-049
Labels: area:deepseek-v4, area:boundary, type:protocol, priority:p0, ready-for-agent
Evidence class: model-free
Hardware: none
Model: deepseek-v4-flash
Upstream: yes

Objective / description

Fresh Ralph session: read .scratch/distributed-gguf-runtime/RALPH-CONTEXT.md, source issue .scratch/distributed-gguf-runtime/issues/046-define-the-v4-typed-architecture-boundary-schema.md, and evidence READMEs for dependencies (DGR-021, DGR-045) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Define the exact cross-stage V4 architecture boundary while keeping per-layer attention and auxiliary caches shard-local.

Acceptance criteria

Define a versioned named bundle for the mHC 4×4096 residual boundary, positions, token-ID sideband where required, and schema/cache expectations.
Explicitly exclude per-layer CSA, HCA, SWA, indexer, compressor, KV, and MTP caches/state from the WAN boundary; those remain local to the owning shard and session/epoch.
Reserve typed MTP boundary fields but mark MTP execution unsupported and unroutable for alpha.
Fingerprint independently of quant/topology and fail closed on missing, incompatible, incorrectly shaped, or stale boundary/cache expectations.
Applicable shared quality gates in prd.json pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.

Shared quality gates

Targeted deterministic tests pass; Python changes also pass python -m compileall packages tests.
git diff --check passes.
Default tests are model-download-free, API-credit-free, and GPU-free.
Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.

Evidence handoff

Write and verify .scratch/distributed-gguf-runtime/evidence/DGR-046/README.md. Until every criterion and applicable gate has real evidence, this story remains passes: false. Legacy evidence is provenance only, not completion credit.

# DGR-046: Define the V4 typed architecture boundary schema - **Status / triage:** specification only; `ready-for-agent`; `passes: false` - **Execution mode:** `AFK` - **Milestone:** `M3` - **Dependencies:** `DGR-021`, `DGR-045` - **Blocks (derived):** `DGR-047`, `DGR-048`, `DGR-049` - **Labels:** `area:deepseek-v4`, `area:boundary`, `type:protocol`, `priority:p0`, `ready-for-agent` - **Evidence class:** `model-free` - **Hardware:** `none` - **Model:** `deepseek-v4-flash` - **Upstream:** `yes` ## Objective / description Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/046-define-the-v4-typed-architecture-boundary-schema.md`, and evidence READMEs for dependencies (DGR-021, DGR-045) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Define the exact cross-stage V4 architecture boundary while keeping per-layer attention and auxiliary caches shard-local. ## Acceptance criteria - [ ] Define a versioned named bundle for the mHC 4×4096 residual boundary, positions, token-ID sideband where required, and schema/cache expectations. - [ ] Explicitly exclude per-layer CSA, HCA, SWA, indexer, compressor, KV, and MTP caches/state from the WAN boundary; those remain local to the owning shard and session/epoch. - [ ] Reserve typed MTP boundary fields but mark MTP execution unsupported and unroutable for alpha. - [ ] Fingerprint independently of quant/topology and fail closed on missing, incompatible, incorrectly shaped, or stale boundary/cache expectations. - [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff. ## Shared quality gates - Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`. - `git diff --check` passes. - Default tests are model-download-free, API-credit-free, and GPU-free. - Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit. ## Evidence handoff Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-046/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.

popov added this to the M3 milestone 2026-07-16 20:36:04 +00:00

popov added the type:protocol area:boundary area:deepseek-v4 ready-for-agent priority:p0 status:blocked labels 2026-07-16 20:36:04 +00:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: popov/neuron-tai#30