DGR-027: Add exact llama.cpp provenance manifest and fetch workspace #11

Closed
opened 2026-07-16 20:36:02 +00:00 by popov · 1 comment
Owner

DGR-027: Add exact llama.cpp provenance manifest and fetch workspace

  • Status / triage: completed; passes: true
  • Execution mode: AFK
  • Milestone: M1
  • Dependencies: DGR-017
  • Blocks (derived): DGR-028, DGR-029, DGR-044
  • Labels: area:upstream, area:build, type:provenance, priority:p0, ready-for-agent
  • Evidence class: model-free
  • Hardware: none
  • Model: generic
  • Upstream: yes

Objective / 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.

Acceptance criteria

  • 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.

Shared quality gates

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

Evidence handoff

Verified evidence: .scratch/distributed-gguf-runtime/evidence/DGR-027/README.md. Legacy evidence remains provenance only and grants no implementation completion credit.

<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. --> # DGR-027: Add exact llama.cpp provenance manifest and fetch workspace - **Status / triage:** completed; `passes: true` - **Execution mode:** `AFK` - **Milestone:** `M1` - **Dependencies:** `DGR-017` - **Blocks (derived):** `DGR-028`, `DGR-029`, `DGR-044` - **Labels:** `area:upstream`, `area:build`, `type:provenance`, `priority:p0`, `ready-for-agent` - **Evidence class:** `model-free` - **Hardware:** `none` - **Model:** `generic` - **Upstream:** `yes` ## Objective / 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. ## Acceptance criteria - [x] Manifest records upstream URL, exact commit, expected source archive/tree hash, license, and retrieval method. - [x] Fetch tooling verifies identity before use and refuses an unpinned branch/tag. - [x] Source is fetched into an ignored build workspace; no submodule, vendored source tree, or permanent fork is introduced. - [x] Offline reuse is supported only after the cached tree’s exact identity is verified. - [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff. ## Shared quality gates - Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`. - `git diff --check` passes. - Default tests are model-download-free, API-credit-free, and GPU-free. - Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit. ## Evidence handoff Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-027/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit. <!-- ralph-story-id: DGR-027 -->
popov added this to the M1 milestone 2026-07-16 20:36:02 +00:00
deploy added status:in-progress and removed status:ready labels 2026-07-17 12:42:30 +00:00
Collaborator

Completed and independently reviewed in commit f83cf33 ([verified] feat: harden llama.cpp provenance workspace), pushed to ralph/dgr-small-terra and fast-forwarded into ralph/distributed-gguf-runtime. Controller gates: 7 focused tests passed; real exact detached-cache fetch/reuse passed; all 3,156 tracked blobs verified; POSIX mode/index-flag regressions passed; compileall, PRD validation (55 stories), and git diff --check passed. Evidence: .scratch/distributed-gguf-runtime/evidence/DGR-027/README.md. Closing as completed.

Completed and independently reviewed in commit `f83cf33` (`[verified] feat: harden llama.cpp provenance workspace`), pushed to `ralph/dgr-small-terra` and fast-forwarded into `ralph/distributed-gguf-runtime`. Controller gates: 7 focused tests passed; real exact detached-cache fetch/reuse passed; all 3,156 tracked blobs verified; POSIX mode/index-flag regressions passed; `compileall`, PRD validation (55 stories), and `git diff --check` passed. Evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-027/README.md`. Closing as completed.
deploy added status:completed and removed status:in-progressready-for-agent labels 2026-07-17 13:26:01 +00:00
popov added the ready-for-agent label 2026-07-21 18:54:12 +00:00
Sign in to join this conversation.
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: popov/neuron-tai#11