DGR-031: Introduce the project-owned ShardEngine interface #15

Open
opened 2026-07-16 20:36:02 +00:00 by popov · 2 comments
Owner

DGR-031: Introduce the project-owned ShardEngine interface

  • Status / triage: specification only; ready-for-agent; passes: false
  • Execution mode: AFK
  • Milestone: M1
  • Dependencies: DGR-021, DGR-025
  • Blocks (derived): DGR-032, DGR-034, DGR-035, DGR-037
  • Labels: area:engine, type:architecture, priority:p0, ready-for-agent
  • Evidence class: model-free
  • Hardware: none
  • Model: generic
  • Upstream: no

Objective / description

Fresh Ralph session: read .scratch/distributed-gguf-runtime/RALPH-CONTEXT.md, source issue .scratch/distributed-gguf-runtime/issues/031-introduce-the-project-owned-shardengine-interface.md, and evidence READMEs for dependencies (DGR-021, DGR-025) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Isolate worker/protocol code from llama.cpp internals behind a stable project-owned engine contract.

Acceptance criteria

  • Define load, capabilities, prefill/decode, boundary/logits result, cancel, release, health, and metrics operations.
  • Use project-owned request/result/state types; expose no ggml_tensor, llama context, scheduler, or ABI-owned structure.
  • Reserve typed MTP and architecture auxiliary-state hooks without enabling them.
  • Add contract tests proving fake and future llama implementations obey identical lifecycle semantics.
  • 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-031/README.md. Until every criterion and applicable gate has real evidence, this story remains passes: false. Legacy evidence is provenance only, not completion credit.

<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. --> # DGR-031: Introduce the project-owned `ShardEngine` interface - **Status / triage:** specification only; `ready-for-agent`; `passes: false` - **Execution mode:** `AFK` - **Milestone:** `M1` - **Dependencies:** `DGR-021`, `DGR-025` - **Blocks (derived):** `DGR-032`, `DGR-034`, `DGR-035`, `DGR-037` - **Labels:** `area:engine`, `type:architecture`, `priority:p0`, `ready-for-agent` - **Evidence class:** `model-free` - **Hardware:** `none` - **Model:** `generic` - **Upstream:** `no` ## Objective / description Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/031-introduce-the-project-owned-shardengine-interface.md`, and evidence READMEs for dependencies (DGR-021, DGR-025) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Isolate worker/protocol code from llama.cpp internals behind a stable project-owned engine contract. ## Acceptance criteria - [ ] Define load, capabilities, prefill/decode, boundary/logits result, cancel, release, health, and metrics operations. - [ ] Use project-owned request/result/state types; expose no `ggml_tensor`, llama context, scheduler, or ABI-owned structure. - [ ] Reserve typed MTP and architecture auxiliary-state hooks without enabling them. - [ ] Add contract tests proving fake and future llama implementations obey identical lifecycle semantics. - [ ] 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-031/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit. <!-- ralph-story-id: DGR-031 -->
popov added this to the M1 milestone 2026-07-16 20:36:02 +00:00
deploy added status:ready and removed status:blocked labels 2026-07-17 20:20:30 +00:00
Collaborator

Dependency reconciliation: all declared prerequisites (DGR-021, DGR-025) are now closed/completed. Moving this issue to status:ready.

Dependency reconciliation: all declared prerequisites (DGR-021, DGR-025) are now closed/completed. Moving this issue to `status:ready`.
deploy added status:in-progress and removed status:ready labels 2026-07-17 20:30:05 +00:00
deploy added status:blocked and removed status:in-progressready-for-agent labels 2026-07-17 20:44:13 +00:00
Collaborator

Temporarily returned to status:blocked: dependency DGR-025 was reopened after reproducible exact-identity findings. No downstream completion credit may rely on it until reverified.

Temporarily returned to `status:blocked`: dependency DGR-025 was reopened after reproducible exact-identity findings. No downstream completion credit may rely on it until reverified.
popov added ready-for-agentstatus:ready and removed status:blocked labels 2026-07-21 18:54:13 +00:00
Sign in to join this conversation.
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: popov/neuron-tai#15