From 0c7d475335f116eb6cecd34f9be8dd607cf503b4 Mon Sep 17 00:00:00 2001 From: Dobromir Popov Date: Sun, 26 Jul 2026 22:33:37 +0300 Subject: [PATCH] chore: remove Ralph lane runtime artifacts --- .gitignore | 1 + .ralph-lane/controller.log | 3 - .ralph-lane/controller.pid | 1 - .ralph-lane/current-prd.json | 2210 ---------------------------------- 4 files changed, 1 insertion(+), 2214 deletions(-) delete mode 100644 .ralph-lane/controller.log delete mode 100644 .ralph-lane/controller.pid delete mode 100644 .ralph-lane/current-prd.json diff --git a/.gitignore b/.gitignore index 3c6cbc2..b978be7 100644 --- a/.gitignore +++ b/.gitignore @@ -12,6 +12,7 @@ dist/ # Ralph local runtime state .ralph-tui/* !.ralph-tui/config.toml +.ralph-lane/ .env diff --git a/.ralph-lane/controller.log b/.ralph-lane/controller.log deleted file mode 100644 index 89e6c61..0000000 --- a/.ralph-lane/controller.log +++ /dev/null @@ -1,3 +0,0 @@ -[2026-07-25T19:19:43+00:00] START lane=opus agent=claude model=opus branch=ralph/distributed-gguf-opus -[2026-07-25T19:19:43+00:00] CLAIM DGR-033: Build a standalone fake C++ gRPC Shard worker -[2026-07-25T19:19:43+00:00] $ ralph-tui run --prd /run/media/popov/d/DEV/repos/d-popov.com/AI/.claude/worktrees/distributed-gguf-opus/.ralph-lane/current-prd.json --agent claude --model opus --iterations 1 --no-tui --no-setup --verify --cwd /run/media/popov/d/DEV/repos/d-popov.com/AI/.claude/worktrees/distributed-gguf-opus --output-dir /run/media/popov/d/DEV/repos/d-popov.com/AI/.claude/worktrees/distributed-gguf-opus/.ralph-lane/iterations --progress-file /run/media/popov/d/DEV/repos/d-popov.com/AI/.claude/worktrees/distributed-gguf-opus/.ralph-lane/progress.md diff --git a/.ralph-lane/controller.pid b/.ralph-lane/controller.pid deleted file mode 100644 index 8479f9a..0000000 --- a/.ralph-lane/controller.pid +++ /dev/null @@ -1 +0,0 @@ -205508 diff --git a/.ralph-lane/current-prd.json b/.ralph-lane/current-prd.json deleted file mode 100644 index cf36dcf..0000000 --- a/.ralph-lane/current-prd.json +++ /dev/null @@ -1,2210 +0,0 @@ -{ - "name": "Distributed GGUF Runtime", - "description": "Benchmark-gated distributed GGUF Shards using existing Meshnet control-plane routing and a standalone C++ gRPC worker around pinned upstream llama.cpp, targeting DeepSeek V4 Flash without hardcoded quantization or topology.", - "branchName": "ralph/distributed-gguf-runtime", - "userStories": [ - { - "id": "DGR-017", - "title": "Reconcile and clean the superseded DGR backlog", - "priority": 1, - "milestone": "M0", - "executionMode": "AFK", - "labels": [ - "area:provenance", - "area:cleanup", - "type:audit", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-017/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/017-reconcile-and-clean-the-superseded-dgr-backlog.md`, and evidence READMEs for dependencies (none) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Audit implementation reality, void inherited completion credit, and clean misleading backlog/stub baggage while preserving attributable evidence and accepted research.", - "acceptanceCriteria": [ - "Compare the branch, old DGR-001..016 issue/pass states, evidence, and actual runtime sources; classify each output as reusable, reference-only, blocked, obsolete, or absent.", - "Record an authoritative old-to-new disposition and provenance; explicitly give no completion credit to any new story and note absent implementation/evidence.", - "Remove or archive only artifacts the audit proves obsolete while preserving accepted ADRs, useful research, raw benchmark evidence, and attributable reusable work.", - "Protect ignored build workspaces, generated protobuf outputs, Ralph logs, and model artifacts from accidental commits, and document every retained legacy artifact.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative.", - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/017-reconcile-and-clean-the-superseded-dgr-backlog.md; prd.json is authoritative.", - "blocks": [ - "DGR-018", - "DGR-019", - "DGR-027", - "DGR-054" - ] - }, - { - "id": "DGR-018", - "title": "Define canonical Ralph and Gitea metadata schema", - "priority": 2, - "milestone": "M0", - "executionMode": "AFK", - "labels": [ - "area:planning", - "area:gitea", - "type:infrastructure", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-018/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-017" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/018-define-canonical-ralph-and-gitea-metadata-schema.md`, and evidence READMEs for dependencies (DGR-017) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Make `prd.json` the validated source from which Markdown and Gitea issues can later be generated losslessly.", - "acceptanceCriteria": [ - "Define fields for stable ID/title, labels, milestone, type, `dependsOn`, derived `blocks`, triage, evidence class, and hardware/model/upstream flags.", - "Validate that all stories start `passes: false`, use known dependencies, and have unique stable IDs.", - "Reject cycles, missing dependencies, mismatched generated `blocks`, duplicate titles/IDs, and generated artifacts claiming authority over `prd.json`.", - "Add deterministic model-free tests for parse, validation, and generation round trips.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative.", - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/018-define-canonical-ralph-and-gitea-metadata-schema.md; prd.json is authoritative.", - "blocks": [ - "DGR-021", - "DGR-025" - ] - }, - { - "id": "DGR-019", - "title": "Lock alpha and beta performance contracts", - "priority": 3, - "milestone": "M0", - "executionMode": "HITL", - "labels": [ - "area:performance", - "type:contract", - "priority:p0", - "gate:hitl", - "ready-for-human" - ], - "evidenceClass": "release", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-019/README.md", - "hardware": "required", - "model": "generic+deepseek-v4", - "upstream": "no", - "dependsOn": [ - "DGR-017" - ], - "triage": "ready-for-human", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/019-lock-alpha-and-beta-performance-contracts.md`, and evidence READMEs for dependencies (DGR-017) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Freeze useful speed, correctness, memory-fit, and stop/go thresholds before implementation results are visible.", - "acceptanceCriteria": [ - "Define controlled safetensors, whole-model GGUF, dense distributed GGUF, and V4 Flash distributed lanes with fixed prompts, context/output lengths, sampling, concurrency, hardware, and metrics.", - "Alpha requires correctness plus a human-approved useful-speed threshold; beta adds concurrency, long-context, failure, and sustained-throughput thresholds.", - "Separate quantization/model-fit gains from runtime, transport, batching, and kernel gains.", - "Treat quants and 2–4/10+ stage counts only as named certification scenarios; no product logic may hardcode them.", - "Lock thresholds and stop conditions in versioned machine-readable data before benchmark result ingestion.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/019-lock-alpha-and-beta-performance-contracts.md; prd.json is authoritative.", - "blocks": [ - "DGR-020", - "DGR-044", - "DGR-054" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-020", - "title": "Run the controlled whole-model GGUF baseline", - "priority": 4, - "milestone": "M0", - "executionMode": "HITL", - "labels": [ - "area:performance", - "type:benchmark", - "priority:p0", - "gate:hitl", - "ready-for-human" - ], - "evidenceClass": "real-hardware", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-020/README.md", - "hardware": "required", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-019" - ], - "triage": "ready-for-human", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/020-run-the-controlled-whole-model-gguf-baseline.md`, and evidence READMEs for dependencies (DGR-019) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Execute the locked safetensors and whole-model llama.cpp lanes before distributed implementation results can influence the decision.", - "acceptanceCriteria": [ - "Run the exact DGR-019 safetensors and whole-model llama.cpp benchmark lanes with locked prompts, lengths, sampling, concurrency, hardware, and artifact/runtime identities.", - "Record raw machine-readable correctness, TTFT, prefill/decode, throughput, latency, memory, artifact-size, failure, and quality-drift metrics without ingesting distributed implementation results.", - "Separate quantization/model-fit effects from runtime/kernel effects and preserve failed or unavailable lanes honestly.", - "Publish a threshold-based `go`, `optimize baseline`, or `stop` decision without changing the locked contract.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/020-run-the-controlled-whole-model-gguf-baseline.md; prd.json is authoritative.", - "blocks": [ - "DGR-054" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-021", - "title": "Define the versioned named-tensor stream envelope", - "priority": 5, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:protocol", - "type:infrastructure", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-021/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-018" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/021-define-the-versioned-named-tensor-stream-envelope.md`, and evidence READMEs for dependencies (DGR-018) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Establish the backend-neutral protobuf envelope used by direct and relayed Shard activation traffic.", - "acceptanceCriteria": [ - "Define schema version, request/work ID, route session/epoch, shard range/effective start, phase, position, and idempotency step.", - "Define named tensors with shape, dtype, byte order, bounded fragments, compression identity, and checksum.", - "Reserve extensible fields for token-ID sidebands, architecture state, recurrent state, and MTP without claiming implementations.", - "Add deterministic serialization, fragmentation, checksum, unknown-field, and size-limit tests.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative.", - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/021-define-the-versioned-named-tensor-stream-envelope.md; prd.json is authoritative.", - "blocks": [ - "DGR-022", - "DGR-023", - "DGR-025", - "DGR-031", - "DGR-035", - "DGR-046" - ] - }, - { - "id": "DGR-022", - "title": "Define Shard lifecycle and structured status RPCs", - "priority": 6, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:protocol", - "area:lifecycle", - "type:infrastructure", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-022/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-021" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/022-define-shard-lifecycle-and-structured-status-rpcs.md`, and evidence READMEs for dependencies (DGR-021) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Complete the gRPC contract for worker capability, health, sessions, cancellation, release, and metrics.", - "acceptanceCriteria": [ - "Define capability, health, bidirectional session stream, cancellation, release, and metrics RPCs.", - "Specify deadlines, cancellation propagation, bounded flow control, cache expectations/results, and structured error taxonomy.", - "Specify TLS/auth hooks without moving Meshnet authentication or billing into the worker.", - "Add compatibility tests for supported versions and fail-closed tests for unsupported versions and malformed lifecycle transitions.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Completed from isolated DGR-022 Ralph worktree; verified with 17 focused pytest cases and retained DGR-021 envelope compatibility.", - "blocks": [ - "DGR-024", - "DGR-033", - "DGR-037" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-023", - "title": "Make Python and C++ protobuf generation reproducible", - "priority": 7, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:protocol", - "area:build", - "type:tooling", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-023/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-021" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/023-make-python-and-c-protobuf-generation-reproducible.md`, and evidence READMEs for dependencies (DGR-021) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Generate identical Python/C++ protocol bindings without manual copying or checked-in build debris.", - "acceptanceCriteria": [ - "Pin protoc, gRPC, and plugin versions or declare a verified compatible range.", - "Generate Python and C++ bindings into out-of-tree build/package locations through documented commands.", - "Add Python↔C++ round-trip and descriptor compatibility tests.", - "A clean checkout regenerates bindings deterministically or fails with an actionable toolchain error.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Completed from Gitea #7 after controller provisioned and exercised the exact Python/C++ toolchains. Verified deterministic generation, native CMake/CTest, Python↔C++ byte parity, compileall, and diff checks; fixed relative bootstrap prefix resolution.", - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative.", - "blocks": [ - "DGR-024", - "DGR-037" - ] - }, - { - "id": "DGR-024", - "title": "Implement real generated-gRPC protocol harness", - "priority": 8, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:protocol", - "area:testing", - "type:vertical-slice", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-024/README.md", - "hardware": "none", - "model": "none", - "upstream": "no", - "dependsOn": [ - "DGR-022", - "DGR-023" - ], - "triage": "ready-for-agent", - "description": "Build a real generated-gRPC protocol harness around the versioned shard_runtime.proto contract. Use generated Python and C++ stubs over an actual localhost transport and real process lifecycle; exercise captured deterministic protocol vectors and serialized protobuf bytes before a real model worker exists. Do not implement an in-memory fake transport, synthetic model outputs, or a production-looking stub/demo service.", - "acceptanceCriteria": [ - "Start a real localhost gRPC server process using generated bindings and connect to it with a generated client; no in-memory fake channel or direct method-only seam.", - "Exercise prefill fragments, decode frames, release, cancel, flow-control, deadlines, malformed input, checksum failure, duplicates, and stale epochs using serialized protocol messages and captured deterministic vectors.", - "Prove direct and opaque-relay paths preserve identical protobuf bytes by recording and comparing actual wire frames at both boundaries.", - "Use real process/socket lifecycle and fail closed on transport, schema, epoch, size, cache, and deadline violations; do not claim model or accelerator behavior that is not exercised.", - "Applicable shared quality gates pass, and evidence records exact commands, raw outputs, generated artifact identities, wire-frame hashes, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/024-implement-real-generated-grpc-protocol-harness.md; prd.json is authoritative.", - "blocks": [ - "DGR-033", - "DGR-042" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-025", - "title": "Define exact artifact and runtime recipe identity", - "priority": 9, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:identity", - "area:admission", - "type:domain", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-025/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-018", - "DGR-021" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/025-define-exact-artifact-and-runtime-recipe-identity.md`, and evidence READMEs for dependencies (DGR-018, DGR-021) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Ensure the tracker and worker only combine numerically and operationally compatible shards.", - "acceptanceCriteria": [ - "Fingerprint source artifact SHA, tokenizer revision, architecture adapter/version, boundary schema, runtime pin/patch stack, backend, quant, activation/compute dtype, and KV/state layout.", - "Bind each shard to an exact half-open range without hardcoding a topology or quant.", - "Fail closed on any artifact, adapter, boundary, cache, backend, or runtime mismatch.", - "Unsupported recipes remain registered-but-dark until real-hardware evidence certifies them.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/025-define-exact-artifact-and-runtime-recipe-identity.md; prd.json is authoritative.", - "blocks": [ - "DGR-026", - "DGR-031", - "DGR-041", - "DGR-044" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-026", - "title": "Provision exact split-GGUF artifacts outside /home", - "priority": 10, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:artifacts", - "area:provenance", - "type:tooling", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-026/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-025" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/026-provision-exact-split-gguf-artifacts-outside-home.md`, and evidence READMEs for dependencies (DGR-025) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Make exact split-GGUF inputs reproducibly available from mounted-drive storage without embedding a quantization or topology assumption in product code.", - "acceptanceCriteria": [ - "Create an exact manifest that binds the source artifact, tokenizer/revision, every split file name, size, range/role, and cryptographic hash.", - "Provide resumable, hash-verifying download/provision tooling targeting configured mounted-drive storage; refuse paths under `/home` and incomplete or mismatched splits.", - "Keep quantization and split topology as manifest/recipe inputs with no hardcoded quant, node count, or range layout.", - "Add deterministic model-download-free tests using tiny local split fixtures, including interrupted resume, missing split, hash mismatch, and `/home` rejection.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/026-provision-exact-split-gguf-artifacts-outside-home.md; prd.json is authoritative.", - "blocks": [ - "DGR-044", - "DGR-045" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-027", - "title": "Add exact llama.cpp provenance manifest and fetch workspace", - "priority": 11, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:upstream", - "area:build", - "type:provenance", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-027/README.md", - "hardware": "none", - "model": "generic", - "upstream": "yes", - "dependsOn": [ - "DGR-017" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/027-add-exact-llama-cpp-provenance-manifest-and-fetch-workspace.md`, and evidence READMEs for dependencies (DGR-017) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Pin llama.cpp exactly through an in-repo manifest while fetching source only into an ignored build workspace.", - "acceptanceCriteria": [ - "Manifest records upstream URL, exact commit, expected source archive/tree hash, license, and retrieval method.", - "Fetch tooling verifies identity before use and refuses an unpinned branch/tag.", - "Source is fetched into an ignored build workspace; no submodule, vendored source tree, or permanent fork is introduced.", - "Offline reuse is supported only after the cached tree’s exact identity is verified.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Completed from Gitea #11 via the Terra Ralph lane; independently reviewed after fail-closed cache identity hardening. Verified 7 focused tests, exact real-cache reuse, compileall, and diff-check. The pre-existing malformed 0002 patch is handed to DGR-028.", - "blocks": [ - "DGR-028", - "DGR-029", - "DGR-044" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-028", - "title": "Implement numbered patch-stack apply and verification", - "priority": 12, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:upstream", - "area:patches", - "type:tooling", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-028/README.md", - "hardware": "none", - "model": "generic", - "upstream": "yes", - "dependsOn": [ - "DGR-027" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/028-implement-numbered-patch-stack-apply-and-verification.md`, and evidence READMEs for dependencies (DGR-027) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Maintain a minimal auditable llama.cpp delta with one numbered patch per concern.", - "acceptanceCriteria": [ - "Add deterministic apply/check/reverse verification against the exact manifest pin.", - "Separate range loading, boundary I/O, filtered state, and worker hooks into scoped patches.", - "Record upstream file/API assumptions and fail with the first incompatible patch when the pin changes.", - "Verify license/attribution and prove no Meshnet routing, billing, relay, or authentication code enters the patch stack.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/028-implement-numbered-patch-stack-apply-and-verification.md; prd.json is authoritative.", - "blocks": [ - "DGR-029", - "DGR-034", - "DGR-069" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-029", - "title": "Create the native CMake skeleton and deterministic CPU lane", - "priority": 13, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:build", - "type:toolchain", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-029/README.md", - "hardware": "none", - "model": "generic", - "upstream": "yes", - "dependsOn": [ - "DGR-027", - "DGR-028" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/029-create-the-native-cmake-skeleton-and-deterministic-cpu-lane.md`, and evidence READMEs for dependencies (DGR-027, DGR-028) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Establish an out-of-tree standalone native build with a deterministic CPU lane before accelerator matrix work.", - "acceptanceCriteria": [ - "Create the standalone native CMake target/skeleton and isolated out-of-tree configure/build preset for CPU.", - "Build and run a deterministic model-free CPU smoke/CTest lane from a clean checkout with actionable toolchain failures.", - "Keep fetched upstream sources, generated bindings, and all build outputs ignored and out of tree.", - "Ensure build success alone does not advertise any backend/model/recipe capability.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/029-create-the-native-cmake-skeleton-and-deterministic-cpu-lane.md; prd.json is authoritative.", - "blocks": [ - "DGR-030", - "DGR-034" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-030", - "title": "Add accelerator build presets and native CI matrix", - "priority": 14, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:build", - "area:hardware", - "type:toolchain", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-030/README.md", - "hardware": "optional", - "model": "generic", - "upstream": "yes", - "dependsOn": [ - "DGR-029" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/030-add-accelerator-build-presets-and-native-ci-matrix.md`, and evidence READMEs for dependencies (DGR-029) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Compile all required accelerator lanes reproducibly while keeping untested real-hardware capabilities registered-dark.", - "acceptanceCriteria": [ - "Add isolated out-of-tree presets for CUDA, ROCm, Vulkan, and Metal without changing the deterministic CPU default.", - "Add a native CI/build matrix that reports unavailable SDKs as explicit unavailable/skipped lanes rather than false success.", - "Compile each available lane and preserve exact compiler, SDK, upstream pin, patch-stack, and build-option evidence.", - "Keep every backend/model/recipe lane registered-dark until a separate real-hardware certification record exists.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/030-add-accelerator-build-presets-and-native-ci-matrix.md; prd.json is authoritative.", - "blocks": [ - "DGR-053", - "DGR-067", - "DGR-068" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-031", - "title": "Introduce the project-owned `ShardEngine` interface", - "priority": 15, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:engine", - "type:architecture", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-031/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-021", - "DGR-025" - ], - "triage": "ready-for-agent", - "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.", - "acceptanceCriteria": [ - "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." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/031-introduce-the-project-owned-shardengine-interface.md; prd.json is authoritative.", - "blocks": [ - "DGR-032", - "DGR-034", - "DGR-035", - "DGR-037" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-032", - "title": "Implement deterministic fake `ShardEngine`", - "priority": 16, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:engine", - "area:testing", - "type:fixture", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-032/README.md", - "hardware": "none", - "model": "fake", - "upstream": "no", - "dependsOn": [ - "DGR-031" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/032-implement-deterministic-fake-shardengine.md`, and evidence READMEs for dependencies (DGR-031) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Provide an engine fixture that deterministically transforms typed boundary bundles and session state.", - "acceptanceCriteria": [ - "Support head, middle, tail, prefill, decode, cancellation, and release with deterministic outputs.", - "Model isolated session/epoch state and deterministic cache-miss/stale-epoch failures.", - "Support configurable delay, memory pressure, malformed output, and crash injection.", - "Contract tests distinguish fixture evidence from real-model certification.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/032-implement-deterministic-fake-shardengine.md; prd.json is authoritative.", - "blocks": [ - "DGR-033" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-033", - "title": "Build a standalone fake C++ gRPC Shard worker", - "priority": 17, - "milestone": "M1", - "executionMode": "AFK", - "labels": [ - "area:worker", - "area:grpc", - "type:vertical-slice", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-033/README.md", - "hardware": "none", - "model": "fake", - "upstream": "no", - "dependsOn": [ - "DGR-022", - "DGR-024", - "DGR-032" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/033-build-a-standalone-fake-c-grpc-shard-worker.md`, and evidence READMEs for dependencies (DGR-022, DGR-024, DGR-032) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove the standalone worker process, stream, lifecycle, and supervision shape before llama.cpp integration.", - "acceptanceCriteria": [ - "A standalone C++ executable serves the complete lifecycle and stream RPC contract using the fake engine.", - "Python integration tests cover startup, health, capability, fragmented prefill, decode, release, cancellation, and graceful shutdown.", - "Bounded messages, deadlines, flow control, and independent session cancellation are enforced.", - "The worker exposes neither llama.cpp RPC nor arbitrary graph execution.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/033-build-a-standalone-fake-c-grpc-shard-worker.md; prd.json is authoritative.", - "blocks": [ - "DGR-036", - "DGR-040" - ], - "completionNotes": "Completed by agent" - }, - { - "id": "DGR-034", - "title": "Implement dense-Llama range-aware GGUF ownership", - "priority": 18, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:llama", - "area:weights", - "type:runtime", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-034/README.md", - "hardware": "optional", - "model": "dense-llama", - "upstream": "yes", - "dependsOn": [ - "DGR-028", - "DGR-029", - "DGR-031" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/034-implement-dense-llama-range-aware-gguf-ownership.md`, and evidence READMEs for dependencies (DGR-028, DGR-029, DGR-031) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Load only the dense-Llama tensors owned by a shard range.", - "acceptanceCriteria": [ - "Load only `blk.N.*` tensors in the assigned range, embeddings only at the head, and norm/output or tied output only at the tail.", - "Derive authoritative range and endpoint ownership from the loaded engine state.", - "Reject invalid/gapped/out-of-model ranges and unexpected required tensors.", - "Real-model evidence shows mapped/resident memory scales with owned tensors rather than full artifact size.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/034-implement-dense-llama-range-aware-gguf-ownership.md; prd.json is authoritative.", - "blocks": [ - "DGR-035", - "DGR-037", - "DGR-051" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-035", - "title": "Implement dense architecture boundary input/output", - "priority": 19, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:llama", - "area:boundary", - "type:runtime", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-035/README.md", - "hardware": "optional", - "model": "dense-llama", - "upstream": "yes", - "dependsOn": [ - "DGR-021", - "DGR-031", - "DGR-034" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/035-implement-dense-architecture-boundary-input-output.md`, and evidence READMEs for dependencies (DGR-021, DGR-031, DGR-034) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Execute dense head/middle/tail ranges through an architecture-defined residual boundary.", - "acceptanceCriteria": [ - "Head accepts token IDs and owns embedding; middle/tail bypass embedding and accept a named boundary bundle.", - "Non-tail returns the unnormalized residual before final norm/head and before tail-only row pruning.", - "Tail returns logits or sampled-token output under an explicit contract.", - "Uncertified architectures and incompatible boundary schemas fail closed.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/035-implement-dense-architecture-boundary-input-output.md; prd.json is authoritative.", - "blocks": [ - "DGR-036", - "DGR-037", - "DGR-069" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-036", - "title": "Prove dense fixture and real-model range parity", - "priority": 20, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:parity", - "area:testing", - "type:certification", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-036/README.md", - "hardware": "optional", - "model": "dense-llama", - "upstream": "yes", - "dependsOn": [ - "DGR-033", - "DGR-035" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/036-prove-dense-fixture-and-real-model-range-parity.md`, and evidence READMEs for dependencies (DGR-033, DGR-035) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove the engine/protocol seam before adding session concurrency.", - "acceptanceCriteria": [ - "Model-free two-stage tests pass through two fake worker processes with disjoint ranges.", - "A small real dense GGUF passes whole-model versus two-range prefill parity.", - "At least 32 greedy decode tokens match the locked tolerance.", - "Evidence distinguishes deterministic fixture proof from opt-in real-model proof.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/036-prove-dense-fixture-and-real-model-range-parity.md; prd.json is authoritative.", - "blocks": [ - "DGR-039" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-037", - "title": "Bind llama.cpp to the standalone worker", - "priority": 21, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:worker", - "area:llama", - "type:vertical-slice", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-037/README.md", - "hardware": "optional", - "model": "dense-llama", - "upstream": "yes", - "dependsOn": [ - "DGR-022", - "DGR-023", - "DGR-031", - "DGR-034", - "DGR-035" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/037-bind-llama-cpp-to-the-standalone-worker.md`, and evidence READMEs for dependencies (DGR-022, DGR-023, DGR-031, DGR-034, DGR-035) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Replace the fake engine with the pinned llama.cpp `ShardEngine` implementation without changing the public worker contract.", - "acceptanceCriteria": [ - "Worker loads exactly one artifact/recipe/range identity and rejects mismatched stream requests.", - "All execution passes through `ShardEngine`; llama.cpp implementation types remain private.", - "Health and metrics expose loaded identity, authoritative ownership, memory, and execution state.", - "Graceful shutdown releases model/session resources; injected process death is observable and bounded.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/037-bind-llama-cpp-to-the-standalone-worker.md; prd.json is authoritative.", - "blocks": [ - "DGR-038", - "DGR-039", - "DGR-040", - "DGR-051" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-038", - "title": "Implement isolated shard-local Hot KV State", - "priority": 22, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:kv-cache", - "area:concurrency", - "type:runtime", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-038/README.md", - "hardware": "optional", - "model": "dense-llama", - "upstream": "yes", - "dependsOn": [ - "DGR-037" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/038-implement-isolated-shard-local-hot-kv-state.md`, and evidence READMEs for dependencies (DGR-037) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Map each route session and epoch to isolated state containing only locally owned layers.", - "acceptanceCriteria": [ - "Map `(route_session_id, route_epoch)` to an isolated llama sequence or bounded context.", - "Support prefill/decode append, truncate, release, TTL/LRU eviction, cache miss, and stale-epoch rejection.", - "Four concurrent sessions complete without token, KV, position, or cancellation cross-talk.", - "Release/eviction returns memory to the configured budget without affecting other sessions.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/038-implement-isolated-shard-local-hot-kv-state.md; prd.json is authoritative.", - "blocks": [ - "DGR-039", - "DGR-052", - "DGR-055", - "DGR-069" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-039", - "title": "Pass local two-process dense acceptance", - "priority": 23, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:integration", - "area:parity", - "type:certification", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-039/README.md", - "hardware": "optional", - "model": "dense-llama", - "upstream": "yes", - "dependsOn": [ - "DGR-036", - "DGR-037", - "DGR-038" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/039-pass-local-two-process-dense-acceptance.md`, and evidence READMEs for dependencies (DGR-036, DGR-037, DGR-038) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Establish the first real, independently executing distributed GGUF route on one host.", - "acceptanceCriteria": [ - "Two worker processes open disjoint dense ranges and both execute real prefill/decode work.", - "Whole-model parity, 32-token greedy decode, four-session isolation, cancellation, and cleanup pass.", - "Record TTFT, prefill/decode rates, seam bytes/latency, RSS/VRAM, KV, queue, and failure metrics.", - "Killing one worker returns a bounded structured failure rather than hanging.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/039-pass-local-two-process-dense-acceptance.md; prd.json is authoritative.", - "blocks": [ - "DGR-054" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-040", - "title": "Add node-side native worker supervision", - "priority": 24, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:node", - "area:supervision", - "type:integration", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-040/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-033", - "DGR-037" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/040-add-node-side-native-worker-supervision.md`, and evidence READMEs for dependencies (DGR-033, DGR-037) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Let the existing node service safely start, probe, stop, and restart the standalone worker.", - "acceptanceCriteria": [ - "Supervision owns process startup, readiness, log capture, graceful shutdown, and bounded forced termination.", - "Startup verifies worker binary, artifact identity, recipe, and range before registration.", - "Crashes or health loss make the capability unavailable without corrupting the Transformers backend.", - "Tests use the fake worker and deterministic crash injection.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/040-add-node-side-native-worker-supervision.md; prd.json is authoritative.", - "blocks": [ - "DGR-041", - "DGR-042", - "DGR-055", - "DGR-058" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-041", - "title": "Register native Shard capabilities without redesigning Meshnet", - "priority": 25, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:meshnet", - "area:admission", - "type:integration", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-041/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-025", - "DGR-040" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/041-register-native-shard-capabilities-without-redesigning-meshnet.md`, and evidence READMEs for dependencies (DGR-025, DGR-040) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Adapt native worker identity and capacity to existing backend-agnostic capability admission.", - "acceptanceCriteria": [ - "Registration carries exact recipe fingerprint, authoritative range, backend, memory/KV capacity, concurrency, and certification status.", - "Existing tracker, billing, routing, telemetry, and provider semantics remain backend-agnostic.", - "Uncertified backend/model/recipe combinations are visible but unroutable.", - "Existing Transformers registration and route tests remain unchanged in behavior.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/041-register-native-shard-capabilities-without-redesigning-meshnet.md; prd.json is authoritative.", - "blocks": [ - "DGR-043" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-042", - "title": "Carry native frames through direct and existing relay seams", - "priority": 26, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:meshnet", - "area:relay", - "area:grpc", - "type:integration", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-042/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-024", - "DGR-040" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/042-carry-native-frames-through-direct-and-existing-relay-seams.md`, and evidence READMEs for dependencies (DGR-024, DGR-040) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Use direct gRPC where available and the existing relay as opaque protobuf transport without redesigning relay behavior.", - "acceptanceCriteria": [ - "Direct paths use the long-lived gRPC activation stream.", - "Relayed paths carry byte-identical versioned protobuf frames through the existing relay contract.", - "Request/work identity, cancellation, deadlines, telemetry, billing correlation, and per-node attribution survive both paths.", - "Fake-worker tests cover direct, relay, disconnect, cancellation, and bounded buffering.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/042-carry-native-frames-through-direct-and-existing-relay-seams.md; prd.json is authoritative.", - "blocks": [ - "DGR-054", - "DGR-058" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-043", - "title": "Expose GGUF compatibility and measured cost inputs to existing routing", - "priority": 27, - "milestone": "M2", - "executionMode": "AFK", - "labels": [ - "area:tracker", - "area:routing", - "type:integration", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-043/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-041" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/043-expose-gguf-compatibility-and-measured-cost-inputs-to-existing-routing.md`, and evidence READMEs for dependencies (DGR-041) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Adapt exact GGUF recipe/range compatibility and measured capacity, queue, seam-cost, health, and reliability data into the existing backend-agnostic routing inputs without redesigning routing or load balancing.", - "acceptanceCriteria": [ - "Expose exact recipe, range coverage, capacity, queue/load, seam-cost, health, reliability, backend, and certification measurements through existing tracker input contracts.", - "Prove existing routing forms complete compatible coverage and excludes dark or mismatched candidates using its current backend-agnostic mechanisms.", - "Regression-test unchanged Transformers behavior and unchanged tracker routing, load-balancing, billing, relay, and provider semantics.", - "Regression-test that no quant, stage count, fixed split, architecture, backend sequence, or DeepSeek-specific policy is hardcoded.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/043-expose-gguf-compatibility-and-measured-cost-inputs-to-existing-routing.md; prd.json is authoritative.", - "blocks": [ - "DGR-053", - "DGR-054", - "DGR-059", - "DGR-061" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-044", - "title": "Pin the DeepSeek V4 Flash target contract", - "priority": 28, - "milestone": "M3", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:provenance", - "type:contract", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-044/README.md", - "hardware": "none", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-019", - "DGR-025", - "DGR-026", - "DGR-027" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/044-pin-the-deepseek-v4-flash-target-contract.md`, and evidence READMEs for dependencies (DGR-019, DGR-025, DGR-026, DGR-027) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Fix the alpha/beta model identity and upstream maturity assumptions before implementing the adapter.", - "acceptanceCriteria": [ - "Pin Hugging Face target SHA `60d8d70770c6776ff598c94bb586a859a38244f1`.", - "Record the selected GGUF provenance and exact source binding without assuming one quant.", - "Record that llama.cpp support began with PR 24162/commit `8c146a8` and remains maturing; the build manifest still pins one exact validated upstream commit.", - "Record 43 main layers plus MTP and all known architecture-specific state obligations.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/044-pin-the-deepseek-v4-flash-target-contract.md; prd.json is authoritative.", - "blocks": [ - "DGR-045" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-045", - "title": "Inventory V4 GGUF tensors and layer ownership", - "priority": 29, - "milestone": "M3", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:weights", - "type:research-spike", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-045/README.md", - "hardware": "none", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-026", - "DGR-044" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/045-inventory-v4-gguf-tensors-and-layer-ownership.md`, and evidence READMEs for dependencies (DGR-026, DGR-044) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Derive exact head, repeated-layer, tail, expert, auxiliary-state, and MTP ownership from the pinned artifact.", - "acceptanceCriteria": [ - "Produce a machine-readable inventory tied to the target SHA and exact GGUF artifact.", - "Classify embeddings, 43 main layers, final head, MTP, mHC, attention variants, indexer/compressor, and MoE tensors.", - "Validate half-open range ownership and fail on unclassified required tensors.", - "Inventory tooling works across quants without embedding quant names in architecture logic.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/045-inventory-v4-gguf-tensors-and-layer-ownership.md; prd.json is authoritative.", - "blocks": [ - "DGR-046", - "DGR-047", - "DGR-050" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-046", - "title": "Define the V4 typed architecture boundary schema", - "priority": 30, - "milestone": "M3", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:boundary", - "type:protocol", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "model-free", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-046/README.md", - "hardware": "none", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-021", - "DGR-045" - ], - "triage": "ready-for-agent", - "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.", - "acceptanceCriteria": [ - "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." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/046-define-the-v4-typed-architecture-boundary-schema.md; prd.json is authoritative.", - "blocks": [ - "DGR-047", - "DGR-048", - "DGR-049" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-047", - "title": "Adapt the upstream V4 mHC boundary for ranged ownership", - "priority": 31, - "milestone": "M3", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:mhc", - "type:runtime", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-047/README.md", - "hardware": "optional", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-045", - "DGR-046" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/047-adapt-the-upstream-v4-mhc-boundary-for-ranged-ownership.md`, and evidence READMEs for dependencies (DGR-045, DGR-046) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Add range-boundary adapters around upstream llama.cpp V4 mHC execution without reimplementing the V4 graph or kernels.", - "acceptanceCriteria": [ - "Represent and validate the upstream V4 4×4096 mHC boundary without flattening semantic axes.", - "Add only head/intermediate/tail range ownership and boundary conversion hooks around the pinned upstream llama.cpp graph.", - "Compare deterministic fixture vectors and single-process ranged outputs with upstream whole-model execution.", - "Document that llama.cpp owns V4 mHC graph/kernels and that quantized storage does not alter the logical boundary schema.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/047-adapt-the-upstream-v4-mhc-boundary-for-ranged-ownership.md; prd.json is authoritative.", - "blocks": [ - "DGR-048", - "DGR-049", - "DGR-050", - "DGR-051" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-048", - "title": "Carry token-ID sideband through the first three hash-routed layers", - "priority": 32, - "milestone": "M3", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:routing-state", - "type:runtime", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-048/README.md", - "hardware": "optional", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-046", - "DGR-047" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/048-carry-token-id-sideband-through-the-first-three-hash-routed-layers.md`, and evidence READMEs for dependencies (DGR-046, DGR-047) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Ensure any stage containing the first three hash-routed layers receives exact token identities.", - "acceptanceCriteria": [ - "Head emits token IDs in the typed sideband for boundaries that require them.", - "Intermediate stages preserve or consume the sideband according to their layer range.", - "Routes splitting before, within, and after the first three layers pass deterministic partition tests.", - "Missing or mismatched token IDs fail closed rather than silently selecting incorrect experts.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/048-carry-token-id-sideband-through-the-first-three-hash-routed-layers.md; prd.json is authoritative.", - "blocks": [ - "DGR-051" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-049", - "title": "Keep V4 attention and auxiliary state shard-local", - "priority": 33, - "milestone": "M3", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:attention", - "type:runtime", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-049/README.md", - "hardware": "optional", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-046", - "DGR-047" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/049-keep-v4-attention-and-auxiliary-state-shard-local.md`, and evidence READMEs for dependencies (DGR-046, DGR-047) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Bind V4 CSA/HCA/SWA/indexer/compressor and KV state to the owning shard session/epoch rather than transferring caches over the WAN.", - "acceptanceCriteria": [ - "Map CSA, HCA, SWA, indexer, compressor, and KV ownership from the pinned upstream graph to each owned layer range.", - "Key all such caches/state by route session and epoch with bounded lifecycle, memory accounting, stale-epoch rejection, release, and eviction.", - "Prove cross-stage messages carry only the typed architecture boundary and cache expectations, never per-layer cache contents.", - "On route change or state loss, use explicit cache miss and re-prefill/restart; do not migrate V4 caches across workers.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/049-keep-v4-attention-and-auxiliary-state-shard-local.md; prd.json is authoritative.", - "blocks": [ - "DGR-051" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-050", - "title": "Validate upstream V4 MoE and hash-routing execution under ranged ownership", - "priority": 34, - "milestone": "M3", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:moe", - "type:runtime", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-050/README.md", - "hardware": "optional", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-045", - "DGR-047" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/050-validate-upstream-v4-moe-and-hash-routing-execution-under-ranged-ownership.md`, and evidence READMEs for dependencies (DGR-045, DGR-047) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Validate the pinned upstream llama.cpp V4 MoE and hash-routing graph when layers are range-owned, without reimplementing routing or expert kernels in Meshnet.", - "acceptanceCriteria": [ - "Load range-owned tensors for 256 routed plus one shared expert and validate upstream execution activates six routed experts where specified.", - "Validate the first three upstream hash-routed layers receive exact token-ID sideband across splits before, within, and after them.", - "Compare upstream whole-model and ranged router/expert outputs, shared-expert contribution, and malformed sideband failures.", - "Document that llama.cpp owns V4 MoE, attention, hash routing, graph, and kernels; no expert-parallel WAN collective or Meshnet reimplementation is introduced.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/050-validate-upstream-v4-moe-and-hash-routing-execution-under-ranged-ownership.md; prd.json is authoritative.", - "blocks": [ - "DGR-051" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-051", - "title": "Assemble the DeepSeek V4 Flash `ShardEngine` adapter", - "priority": 35, - "milestone": "M3", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:engine", - "type:vertical-slice", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-051/README.md", - "hardware": "optional", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-034", - "DGR-037", - "DGR-047", - "DGR-048", - "DGR-049", - "DGR-050" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/051-assemble-the-deepseek-v4-flash-shardengine-adapter.md`, and evidence READMEs for dependencies (DGR-034, DGR-037, DGR-047, DGR-048, DGR-049, DGR-050) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Assemble range ownership hooks and boundary/local-state adapters around upstream llama.cpp V4 execution behind the stable ShardEngine interface.", - "acceptanceCriteria": [ - "Support valid head, middle, tail, and whole-model ranges over all 43 main layers using the pinned upstream llama.cpp V4 graph/kernels.", - "Integrate exact range ownership, mHC boundary, positions, required token-ID sideband, and shard-local session/epoch state adapters.", - "Report MTP reserved-but-not-executable for alpha and reject unsupported split points or cache expectations.", - "Include exact adapter/schema/runtime/artifact identity and valid split restrictions without reimplementing V4 MoE, attention, mHC, or hash routing.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/051-assemble-the-deepseek-v4-flash-shardengine-adapter.md; prd.json is authoritative.", - "blocks": [ - "DGR-052", - "DGR-060", - "DGR-065", - "DGR-069" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-052", - "title": "Pass local V4 whole-model versus ranged parity", - "priority": 36, - "milestone": "M3", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:parity", - "type:certification", - "priority:p0", - "ready-for-agent" - ], - "evidenceClass": "real-model", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-052/README.md", - "hardware": "optional", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-038", - "DGR-051" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/052-pass-local-v4-whole-model-versus-ranged-parity.md`, and evidence READMEs for dependencies (DGR-038, DGR-051) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove V4 prefill and decode correctness locally before network certification.", - "acceptanceCriteria": [ - "Compare pinned whole-model llama.cpp with at least two valid ranged partitions.", - "Prefill intermediates and locked-length greedy decode pass architecture-specific tolerances.", - "Test splits around the first three hash-routed layers and at least one CSA/HCA/SWA/indexer/compressor transition.", - "Four concurrent sessions pass KV/state isolation and cleanup.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/052-pass-local-v4-whole-model-versus-ranged-parity.md; prd.json is authoritative.", - "blocks": [ - "DGR-053", - "DGR-054" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-053", - "title": "Certify a real 2–4-stage V4 route", - "priority": 37, - "milestone": "M3", - "executionMode": "HITL", - "labels": [ - "area:deepseek-v4", - "area:hardware", - "type:certification", - "priority:p0", - "gate:hitl", - "ready-for-human" - ], - "evidenceClass": "real-hardware", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-053/README.md", - "hardware": "required", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-030", - "DGR-043", - "DGR-052" - ], - "triage": "ready-for-human", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/053-certify-a-real-2-4-stage-v4-route.md`, and evidence READMEs for dependencies (DGR-030, DGR-043, DGR-052) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove real Tracker-selected V4 execution across physical machines before alpha.", - "acceptanceCriteria": [ - "Run one documented 2–4-stage certification scenario using exact compatible artifacts/recipes; the count and chosen quant are evidence inputs, not product constants.", - "Actual CPU/GPU work executes on every stage; fake workers do not satisfy acceptance.", - "Record parity, TTFT, prefill/decode speed, seam cost, memory, cache/state isolation, cancellation, and cleanup.", - "Tracker selection remains dynamic and rejects an injected incompatible backend/recipe.", - "Only the exact real-hardware lanes exercised become eligible for advertisement.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/053-certify-a-real-2-4-stage-v4-route.md; prd.json is authoritative.", - "blocks": [ - "DGR-054", - "DGR-062", - "DGR-067" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-054", - "title": "Enforce the DeepSeek V4 Flash alpha gate", - "priority": 38, - "milestone": "M3", - "executionMode": "HITL", - "labels": [ - "area:deepseek-v4", - "area:release", - "milestone:alpha", - "priority:p0", - "gate:hitl", - "ready-for-human" - ], - "evidenceClass": "release", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-054/README.md", - "hardware": "required", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-017", - "DGR-019", - "DGR-020", - "DGR-039", - "DGR-042", - "DGR-043", - "DGR-052", - "DGR-053" - ], - "triage": "ready-for-human", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/054-enforce-the-deepseek-v4-flash-alpha-gate.md`, and evidence READMEs for dependencies (DGR-017, DGR-019, DGR-020, DGR-039, DGR-042, DGR-043, DGR-052, DGR-053) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Release alpha only when V4 is correct and clears the pre-locked useful-speed requirement.", - "acceptanceCriteria": [ - "Evaluate correctness, model fit, TTFT, prefill/decode speed, seam cost, memory, and failure rate against DGF-004 without changing thresholds.", - "Separate quant/model-fit gains from runtime/transport gains.", - "Decision is `alpha`, `optimize measured bottleneck`, or `stop`; failures cannot be relabeled as certification.", - "Alpha documentation states MTP is reserved but not implemented and identifies every dark hardware lane.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/054-enforce-the-deepseek-v4-flash-alpha-gate.md; prd.json is authoritative.", - "blocks": [ - "DGR-055", - "DGR-065", - "DGR-066", - "DGR-068" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-055", - "title": "Implement compatible continuous decode batching", - "priority": 39, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:scheduler", - "area:batching", - "type:performance", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-055/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-038", - "DGR-040", - "DGR-054" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/055-implement-compatible-continuous-decode-batching.md`, and evidence READMEs for dependencies (DGR-038, DGR-040, DGR-054) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Batch compatible active sessions without violating route, recipe, position, or architecture state.", - "acceptanceCriteria": [ - "Batch only sessions with compatible engine, recipe, phase, boundary schema, and state layout.", - "Preserve per-session positions, sequence IDs, outputs, cancellation, and accounting.", - "Decode receives bounded service while prefill remains schedulable.", - "Deterministic 1/2/4/8 concurrency tests show no cross-session corruption.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/055-implement-compatible-continuous-decode-batching.md; prd.json is authoritative.", - "blocks": [ - "DGR-056", - "DGR-057" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-056", - "title": "Enforce bounded admission, queues, and backpressure", - "priority": 40, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:scheduler", - "area:backpressure", - "type:performance", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-056/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-055" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/056-enforce-bounded-admission-queues-and-backpressure.md`, and evidence READMEs for dependencies (DGR-055) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prevent weight, KV, state, scratch, and stream buffers from exceeding admitted capacity.", - "acceptanceCriteria": [ - "Admission accounts separately for weights, KV/state, scratch, in-flight fragments, and queue slots.", - "Queue and stream limits produce structured retryable or terminal responses.", - "Prefill cannot starve decode and one route session cannot monopolize queue capacity.", - "Telemetry reports active sessions, queue depth/time, batch occupancy, memory pressure, and rejects.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/056-enforce-bounded-admission-queues-and-backpressure.md; prd.json is authoritative.", - "blocks": [ - "DGR-057", - "DGR-058", - "DGR-060" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-057", - "title": "Benchmark batching saturation and fairness", - "priority": 41, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:performance", - "area:batching", - "type:benchmark", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "real-hardware", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-057/README.md", - "hardware": "required", - "model": "dense-llama+deepseek-v4", - "upstream": "no", - "dependsOn": [ - "DGR-055", - "DGR-056" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/057-benchmark-batching-saturation-and-fairness.md`, and evidence READMEs for dependencies (DGR-055, DGR-056) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Identify useful concurrency and saturation points without assuming one global batch size.", - "acceptanceCriteria": [ - "Run controlled concurrency 1/2/4/8 and record aggregate throughput, per-request p50/p95, TTFT, queue time, occupancy, and memory.", - "Measure dense and V4 lanes separately where hardware permits.", - "Verify bounded fairness and no prefill/decode starvation.", - "Produce machine-readable saturation recommendations consumed by capability reporting, not hardcoded constants.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/057-benchmark-batching-saturation-and-fairness.md; prd.json is authoritative.", - "blocks": [ - "DGR-061", - "DGR-063", - "DGR-070" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-058", - "title": "Harden worker and stream failure semantics", - "priority": 42, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:reliability", - "area:failure", - "type:hardening", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-058/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-040", - "DGR-042", - "DGR-056" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/058-harden-worker-and-stream-failure-semantics.md`, and evidence READMEs for dependencies (DGR-040, DGR-042, DGR-056) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Ensure malformed input, process death, transport reset, and cancellation terminate cleanly.", - "acceptanceCriteria": [ - "Test worker death, stream reset, malformed bundle, checksum failure, deadline, cache miss, stale epoch, and partial fragment loss.", - "Cancellation propagates across all stages and releases KV/state, queue entries, and fragment buffers.", - "Duplicate steps are idempotent; uncertain mutations are never silently replayed.", - "Billing/work outcomes distinguish completed, cancelled, failed, and unverified work.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/058-harden-worker-and-stream-failure-semantics.md; prd.json is authoritative.", - "blocks": [ - "DGR-059", - "DGR-060", - "DGR-061" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-059", - "title": "Implement alpha-safe route recovery", - "priority": 43, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:recovery", - "area:routing", - "type:hardening", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-059/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-043", - "DGR-058" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/059-implement-alpha-safe-route-recovery.md`, and evidence READMEs for dependencies (DGR-043, DGR-058) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Recover from route loss without importing or continuing unverified state.", - "acceptanceCriteria": [ - "On route loss or local-state cache miss, restart from token zero or re-prefill on a newly compatible route according to the locked alpha contract.", - "Never import KV, CSA, HCA, SWA, indexer, compressor, recurrent, or MTP cache/state across workers.", - "Keep exact same-route duplicate delivery idempotent while cross-route continuation fails closed.", - "Test direct/relay loss, cache miss, replacement selection, client cancellation, and billing reconciliation.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/059-implement-alpha-safe-route-recovery.md; prd.json is authoritative.", - "blocks": [ - "DGR-070" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-060", - "title": "Certify V4 long-context state correctness", - "priority": 44, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:long-context", - "type:certification", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "real-hardware", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-060/README.md", - "hardware": "required", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-051", - "DGR-056", - "DGR-058" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/060-certify-v4-long-context-state-correctness.md`, and evidence READMEs for dependencies (DGR-051, DGR-056, DGR-058) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove V4’s KV and auxiliary state remain correct and bounded at long contexts.", - "acceptanceCriteria": [ - "Exercise pre-locked context lengths covering multiple prefill chunks and sustained decode.", - "Validate KV plus CSA/HCA/SWA/indexer/compressor state positions across every stage.", - "Measure memory growth, fragment sizes, TTFT, decode degradation, cancellation latency, and cleanup.", - "Cache mismatch, truncation, and context-limit behavior fail deterministically.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/060-certify-v4-long-context-state-correctness.md; prd.json is authoritative.", - "blocks": [ - "DGR-062", - "DGR-064", - "DGR-065", - "DGR-066", - "DGR-070" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-061", - "title": "Certify existing routing with 10+ GGUF stage candidates", - "priority": 45, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:tracker", - "area:scale", - "type:simulation", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-061/README.md", - "hardware": "none", - "model": "generic", - "upstream": "no", - "dependsOn": [ - "DGR-043", - "DGR-057", - "DGR-058" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/061-certify-existing-routing-with-10-gguf-stage-candidates.md`, and evidence READMEs for dependencies (DGR-043, DGR-057, DGR-058) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Certify that existing backend-agnostic routing consumes GGUF compatibility and measured-cost inputs for a 10+ candidate scenario without algorithm or policy redesign.", - "acceptanceCriteria": [ - "Generate deterministic pools with 10+ compatible GGUF stage candidates plus slower, overloaded, unhealthy, and incompatible alternatives.", - "Run the existing routing implementation unchanged and verify complete coverage, compatibility, acyclicity, and use of measured inputs.", - "Regression-test that no stage count, quant, fixed split, architecture, or backend sequence is encoded in production routing policy.", - "Verify existing route recomputation reacts to measured load/failure while tracker, load-balancing, billing, relay, and provider semantics remain unchanged.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/061-certify-existing-routing-with-10-gguf-stage-candidates.md; prd.json is authoritative.", - "blocks": [ - "DGR-062", - "DGR-063" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-062", - "title": "Certify a dynamic real 10+ stage V4 scenario", - "priority": 46, - "milestone": "M4", - "executionMode": "HITL", - "labels": [ - "area:deepseek-v4", - "area:scale", - "area:hardware", - "type:certification", - "priority:p1", - "gate:hitl", - "ready-for-human" - ], - "evidenceClass": "real-hardware", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-062/README.md", - "hardware": "required", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-053", - "DGR-060", - "DGR-061" - ], - "triage": "ready-for-human", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/062-certify-a-dynamic-real-10-stage-v4-scenario.md`, and evidence READMEs for dependencies (DGR-053, DGR-060, DGR-061) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Demonstrate that a large real route can be dynamically selected and usefully execute V4.", - "acceptanceCriteria": [ - "Run one real 10+-stage V4 certification scenario; stage count, quant, and split remain scenario metadata only.", - "Every selected stage proves real work, exact compatible identity, local state ownership, and bounded resources.", - "Record end-to-end and per-stage TTFT, prefill/decode, seam cost, queueing, memory, failures, and cleanup.", - "Inject at least one incompatible or degraded candidate and verify dynamic exclusion/reselection.", - "The scenario must meet its pre-locked usefulness threshold or remain failed evidence.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/062-certify-a-dynamic-real-10-stage-v4-scenario.md; prd.json is authoritative.", - "blocks": [ - "DGR-067", - "DGR-070" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-063", - "title": "Profile and optimize the critical seam", - "priority": 47, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:performance", - "type:optimization", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "real-hardware", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-063/README.md", - "hardware": "required", - "model": "generic", - "upstream": "conditional", - "dependsOn": [ - "DGR-057", - "DGR-061" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/063-profile-and-optimize-the-critical-seam.md`, and evidence READMEs for dependencies (DGR-057, DGR-061) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Optimize only the measured dominant compute, serialization, copy, or transport bottleneck.", - "acceptanceCriteria": [ - "Profile worker compute, tensor conversion, copies, protobuf framing, compression, relay/direct transport, queueing, and synchronization.", - "Select one dominant bottleneck from evidence and lock its before/after benchmark.", - "Implement one bounded optimization without weakening correctness or protocol identity.", - "Report whether the optimization changes TTFT, prefill, decode, throughput, or memory and preserve raw data.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/063-profile-and-optimize-the-critical-seam.md; prd.json is authoritative.", - "blocks": [ - "DGR-064" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-064", - "title": "Add negotiated activation compression", - "priority": 48, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:protocol", - "area:compression", - "type:optimization", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "real-hardware", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-064/README.md", - "hardware": "required", - "model": "deepseek-v4-flash", - "upstream": "no", - "dependsOn": [ - "DGR-060", - "DGR-063" - ], - "triage": "ready-for-agent", - "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.", - "acceptanceCriteria": [ - "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." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/064-add-negotiated-activation-compression.md; prd.json is authoritative.", - "blocks": [ - "DGR-066", - "DGR-070" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-065", - "title": "Define V4 MTP ownership and distributed state contract", - "priority": 49, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:mtp", - "type:contract", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "fixture", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-065/README.md", - "hardware": "none", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-051", - "DGR-054", - "DGR-060" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/065-define-v4-mtp-ownership-and-distributed-state-contract.md`, and evidence READMEs for dependencies (DGR-051, DGR-054, DGR-060) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Lock MTP tensor, execution, boundary, acceptance/rejection, and session-state ownership before implementation while keeping MTP disabled for alpha.", - "acceptanceCriteria": [ - "Derive exact MTP tensor and execution ownership from the pinned V4 target and upstream llama.cpp graph, distinguishing main-layer, tail, and MTP responsibilities.", - "Define typed MTP inputs/outputs plus accepted-token, rejection, rollback/truncation, position, cache, and session/epoch lifecycle semantics.", - "Specify which MTP state remains shard-local and which typed boundary values cross a seam; prohibit WAN migration of KV or V4 auxiliary caches.", - "Keep every MTP recipe disabled and unroutable for alpha, with fail-closed capability negotiation and deterministic contract fixtures.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/065-define-v4-mtp-ownership-and-distributed-state-contract.md; prd.json is authoritative.", - "blocks": [ - "DGR-066" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-066", - "title": "Implement and benchmark V4 MTP", - "priority": 50, - "milestone": "M4", - "executionMode": "AFK", - "labels": [ - "area:deepseek-v4", - "area:mtp", - "type:runtime", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "real-hardware", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-066/README.md", - "hardware": "required", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-054", - "DGR-060", - "DGR-064", - "DGR-065" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/066-implement-and-benchmark-v4-mtp.md`, and evidence READMEs for dependencies (DGR-054, DGR-060, DGR-064, DGR-065) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Implement the locked MTP contract around upstream llama.cpp before beta, without making MTP an alpha prerequisite.", - "acceptanceCriteria": [ - "Implement the exact DGR-065 MTP ownership and typed state contract against the pinned upstream V4 graph while preserving shard-local caches.", - "Pass whole-model versus ranged MTP correctness, accepted-token, rejection, rollback/truncation, and session-isolation tests.", - "Benchmark MTP-off versus MTP-on quality, accepted-token rate, TTFT, decode speed, seam bytes, and memory on the locked lane.", - "Distinguish implemented, certified, disabled, and unsupported MTP recipes in fail-closed capability advertisement.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/066-implement-and-benchmark-v4-mtp.md; prd.json is authoritative.", - "blocks": [ - "DGR-067", - "DGR-070" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-067", - "title": "Certify the backend capability matrix", - "priority": 51, - "milestone": "M4", - "executionMode": "HITL", - "labels": [ - "area:hardware", - "area:admission", - "type:certification", - "priority:p1", - "gate:hitl", - "ready-for-human" - ], - "evidenceClass": "real-hardware", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-067/README.md", - "hardware": "required", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-030", - "DGR-053", - "DGR-062", - "DGR-066" - ], - "triage": "ready-for-human", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/067-certify-the-backend-capability-matrix.md`, and evidence READMEs for dependencies (DGR-030, DGR-053, DGR-062, DGR-066) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Publish only backend/model/recipe lanes proven on actual CPU, CUDA, ROCm, Vulkan, or Metal hardware.", - "acceptanceCriteria": [ - "Maintain independent build and certification status for CPU, CUDA, ROCm, Vulkan, and Metal.", - "Each advertised lane includes real hardware/driver/runtime/model evidence for parity, concurrency, cancellation, cleanup, and useful speed.", - "Build success alone never makes a lane routable; unavailable hardware remains explicitly dark.", - "Tracker admission consumes signed/versioned certification records rather than backend-name allowlists.", - "Mixed-backend routes require exact compatibility evidence and fail closed otherwise.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/067-certify-the-backend-capability-matrix.md; prd.json is authoritative.", - "blocks": [ - "DGR-068", - "DGR-070" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-068", - "title": "Package reproducible native worker releases", - "priority": 52, - "milestone": "M5", - "executionMode": "AFK", - "labels": [ - "area:packaging", - "area:release", - "type:delivery", - "priority:p1", - "ready-for-agent" - ], - "evidenceClass": "release", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-068/README.md", - "hardware": "optional", - "model": "generic", - "upstream": "yes", - "dependsOn": [ - "DGR-030", - "DGR-054", - "DGR-067" - ], - "triage": "ready-for-agent", - "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.", - "acceptanceCriteria": [ - "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." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/068-package-reproducible-native-worker-releases.md; prd.json is authoritative.", - "blocks": [ - "DGR-070" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-069", - "title": "Prepare narrow upstream llama.cpp collaboration patches", - "priority": 53, - "milestone": "M5", - "executionMode": "HITL", - "labels": [ - "area:upstream", - "area:patches", - "type:collaboration", - "priority:p2", - "gate:hitl", - "ready-for-human" - ], - "evidenceClass": "release", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-069/README.md", - "hardware": "none", - "model": "generic+deepseek-v4", - "upstream": "yes", - "dependsOn": [ - "DGR-028", - "DGR-035", - "DGR-038", - "DGR-051" - ], - "triage": "ready-for-human", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/069-prepare-narrow-upstream-llama-cpp-collaboration-patches.md`, and evidence READMEs for dependencies (DGR-028, DGR-035, DGR-038, DGR-051) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Reduce long-term patch burden through generic upstreamable hooks without asking llama.cpp to own Meshnet.", - "acceptanceCriteria": [ - "Separate generic range loading, boundary I/O, and filtered state hooks from project worker/protocol code.", - "Provide one scoped patch, focused test, and minimal reproducer per concern against the exact upstream pin.", - "Compare the proposal with prior-art evidence and current upstream V4 support/maturity.", - "Prepare human-ready design/outreach text; actual issue/PR submission remains a human action.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/069-prepare-narrow-upstream-llama-cpp-collaboration-patches.md; prd.json is authoritative.", - "blocks": [ - "DGR-071" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-070", - "title": "Enforce the DeepSeek V4 Flash beta gate", - "priority": 54, - "milestone": "M5", - "executionMode": "HITL", - "labels": [ - "area:deepseek-v4", - "area:release", - "milestone:beta", - "priority:p0", - "gate:hitl", - "ready-for-human" - ], - "evidenceClass": "release", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-070/README.md", - "hardware": "required", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-057", - "DGR-059", - "DGR-060", - "DGR-062", - "DGR-064", - "DGR-066", - "DGR-067", - "DGR-068" - ], - "triage": "ready-for-human", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/070-enforce-the-deepseek-v4-flash-beta-gate.md`, and evidence READMEs for dependencies (DGR-057, DGR-059, DGR-060, DGR-062, DGR-064, DGR-066, DGR-067, DGR-068) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Promote beta only after concurrency, resilience, long-context, MTP, scale, packaging, and speed gates pass.", - "acceptanceCriteria": [ - "Evaluate all beta metrics against DGF-004 without changing thresholds after observing results.", - "Require V4 parity, batching/fairness, bounded backpressure, failure recovery, long-context correctness, MTP evidence, and dynamic 10+ stage evidence.", - "Publish the exact certified hardware/backend/recipe matrix; all other lanes remain dark.", - "Decision is `beta`, `targeted optimization`, or `stop/rollback`, with unresolved failures listed explicitly.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/070-enforce-the-deepseek-v4-flash-beta-gate.md; prd.json is authoritative.", - "blocks": [ - "DGR-071" - ], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - }, - { - "id": "DGR-071", - "title": "Establish upstream pin, patch, and certification maintenance", - "priority": 55, - "milestone": "M5", - "executionMode": "AFK", - "labels": [ - "area:maintenance", - "area:upstream", - "area:certification", - "type:operations", - "priority:p2", - "ready-for-agent" - ], - "evidenceClass": "release", - "evidencePath": ".scratch/distributed-gguf-runtime/evidence/DGR-071/README.md", - "hardware": "optional", - "model": "deepseek-v4-flash", - "upstream": "yes", - "dependsOn": [ - "DGR-069", - "DGR-070" - ], - "triage": "ready-for-agent", - "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/071-establish-upstream-pin-patch-and-certification-maintenance.md`, and evidence READMEs for dependencies (DGR-069, DGR-070) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Keep beta reproducible and detect upstream/model/hardware drift before it reaches routable nodes.", - "acceptanceCriteria": [ - "Add a documented update procedure for llama.cpp pin, numbered patches, protocol/engine versions, V4 target revision, and certification records.", - "A candidate pin update must apply/build/test in isolation and cannot replace the production pin automatically.", - "Any changed graph, tensor inventory, boundary, cache/state layout, backend behavior, or performance invalidates affected certification.", - "Add scheduled model-free checks plus opt-in real-hardware recertification instructions and rollback procedure.", - "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff." - ], - "passes": true, - "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/071-establish-upstream-pin-patch-and-certification-maintenance.md; prd.json is authoritative.", - "blocks": [], - "completionNotes": "Ephemeral controller masking; canonical PRD remains authoritative." - } - ], - "metadata": { - "updatedAt": "2026-07-25T19:38:00.109Z", - "controller_ephemeral": true, - "controller_story": "DGR-033" - } -} \ No newline at end of file