neuron-tai/.scratch/distributed-gguf-runtime/issues/064-add-negotiated-activation-compression.md

DGR-064: Add negotiated activation compression

• Status / triage: specification only; ready-for-agent; passes: false
• Execution mode: AFK
• Milestone: M4
• Dependencies: DGR-060, DGR-063
• Blocks (derived): DGR-066, DGR-070
• Labels: area:protocol, area:compression, type:optimization, priority:p1, ready-for-agent
• Evidence class: real-hardware
• Hardware: required
• Model: deepseek-v4-flash
• Upstream: no

Objective / description

Fresh Ralph session: read .scratch/distributed-gguf-runtime/RALPH-CONTEXT.md, source issue .scratch/distributed-gguf-runtime/issues/064-add-negotiated-activation-compression.md, and evidence READMEs for dependencies (DGR-060, DGR-063) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Reduce V4 seam cost only when a certified compression recipe improves end-to-end performance acceptably.

Acceptance criteria

• Negotiate compression through recipe identity; unnegotiated or mismatched compression fails closed.
• Preserve names, shapes, semantic axes, token-ID sideband, and checksums.
• Measure quality drift, encode/decode cost, bytes, TTFT, and throughput against uncompressed boundaries.
• Compression remains dark unless it meets pre-locked quality and speed thresholds.
• 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-064/README.md. Until every criterion and applicable gate has real evidence, this story remains passes: false. Legacy evidence is provenance only, not completion credit.