neuron-tai/.scratch/distributed-gguf-runtime/issues/068-package-reproducible-native-worker-releases.md

DGR-068: Package reproducible native worker releases

• Status / triage: specification only; ready-for-agent; passes: false
• Execution mode: AFK
• Milestone: M5
• Dependencies: DGR-030, DGR-054, DGR-067
• Blocks (derived): DGR-070
• Labels: area:packaging, area:release, type:delivery, priority:p1, ready-for-agent
• Evidence class: release
• Hardware: optional
• Model: generic
• Upstream: yes

Objective / description

Fresh Ralph session: read .scratch/distributed-gguf-runtime/RALPH-CONTEXT.md, source issue .scratch/distributed-gguf-runtime/issues/068-package-reproducible-native-worker-releases.md, and evidence READMEs for dependencies (DGR-030, DGR-054, DGR-067) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Produce installable worker packages that preserve exact source, patch, protocol, and certification identity.

Acceptance criteria

• Package worker binaries/configuration for supported host/backend combinations without bundling an unverified llama.cpp tree.
• Embed protocol, engine, upstream pin, patch-stack, build-toolchain, and certification fingerprints.
• Installation/startup refuses mismatched artifacts, runtime recipes, or unsupported hardware lanes.
• Produce checksums, SBOM/license attribution, reproducible build instructions, and smoke tests.
• 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.
• Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
• Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never /home.
• Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.

Evidence handoff

Write and verify .scratch/distributed-gguf-runtime/evidence/DGR-068/README.md. Until every criterion and applicable gate has real evidence, this story remains passes: false. Legacy evidence is provenance only, not completion credit.