controller: record DGR-043 completion

Address the Codex GPT-5.5 review of the standalone fake C++ gRPC Shard
worker. Four root protocol defects fixed:

- Fail closed before SessionOpen: a per-session `opened` flag gates
  chunk/decode so no activation bypasses lifecycle, cancellation, epoch
  or flow-control state (terminal ERROR_CODE_INTERNAL), even when an
  out-of-band Cancel created placeholder state.
- Strict flow-control negotiation: NegotiateFlow takes the strictest of
  peer-vs-worker bounds (mirrors codec.negotiate_flow_control) and the
  negotiated per-session max_chunk_bytes is enforced on every bundle
  instead of trusting the peer proposal.
- In-stream ReleaseSignal now erases session state immediately.
- SessionOpen rejects incompatible schema, fingerprint, and shard-range
  identity and reports the worker's own served fingerprint rather than
  echoing the caller.

Adds 9 regression tests (worker suite 18 -> 27). Real gates on the
rebuilt pinned-gRPC binary: cmake build exit 0; ctest 2/2; worker
pytest 27 passed; harness+protocol 63 passed; compileall 0; diff --check
clean; ldd/nm show 0 llama/ggml linkage. DGR-033 passes -> true.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.agents/skills/ask-matt/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: ask-matt
-description: Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
+description: Ask which skill or flow fits your situation. A router over the skills in this repo.
 disable-model-invocation: true
 ---
 
@@ -8,26 +8,28 @@ disable-model-invocation: true
 
 You don't remember every skill, so ask.
 
-A **flow** is a path through the skills. Most paths run along one **main flow**, and two **on-ramps** merge onto it. Everything else is standalone.
+A **flow** is a path through the skills. Most paths run along one **main flow**, and two **on-ramps** merge onto it. Everything else is standalone, or a vocabulary layer that runs underneath.
 
 ## The main flow: idea → ship
 
 The route most work travels. You have an idea and want it built.
 
-1. **`/grill-with-docs`** — sharpen the idea by interview. Start here when you **have a codebase**: it's stateful, retaining what it learns in `CONTEXT.md` and ADRs. (No codebase? Use `/grill-me` — see Standalone.)
+1. **`/grill-with-docs`** — sharpen the idea by interview. Start here when you **have a codebase**: it's stateful, retaining what it learns in `CONTEXT.md` and ADRs. (No codebase? Use `/grill-me` — see Standalone. Both run the same `/grilling` primitive; `grill-with-docs` is the one that leaves a paper trail.)
 2. **Branch — can you settle every question in conversation?** If a question needs a runnable answer (state, business logic, a UI you have to see), detour through a prototype, bridged by **`/handoff`** in both directions (see Crossing sessions):
    - **`/handoff`** out, then open a fresh session against that file,
    - **`/prototype`** to answer the question with throwaway code,
    - **`/handoff`** back what you learned, and reference it from the original idea thread.
 3. **Branch — is this a multi-session build?**
-   - **Yes** → **`/to-prd`** (turn the thread into a PRD) → **`/to-issues`** (split the PRD into independently-grabbable issues). Because the issues are independent, **clear context between each one**: start a fresh session per issue and kick off **`/implement`** by passing it the PRD and the single issue to work on.
+   - **Yes** → **`/to-spec`** (turn the thread into a spec), then **`/to-tickets`** to split it into tracer-bullet tickets, each declaring its **blocking edges**. On a local tracker that's one file per ticket under `.scratch/<feature>/issues/`, worked blockers-first by hand; on a real tracker the edges become native blocking links, so any ticket whose blockers are done can be grabbed — kick off **`/implement`** per ticket, **clearing context between each one**.
    - **No** → **`/implement`** right here, in the same context window.
 
+   Either way, **`/implement`** builds each issue by driving **`/tdd`** internally — one red-green slice at a time — then closes out by running **`/code-review`**, a two-axis review (Standards + Spec) of the diff, before committing. Reach for **`/tdd`** on its own when you just want to build a concrete behaviour test-first without a full spec, and **`/code-review`** on its own whenever you want to review a branch or PR against a fixed point.
+
 ### Context hygiene
 
-Keep steps 1–3 in **one unbroken context window** — don't compact or clear until after `/to-issues` — so the grilling, PRD, and issues all build on the same thinking. Each `/implement` then starts fresh, working from the issue.
+Keep steps 1–3 in **one unbroken context window** — don't compact or clear until after `/to-tickets` — so the grilling, spec, and tickets all build on the same thinking. Each `/implement` then starts fresh, working from the ticket.
 
-The limit on this is the **[smart zone](https://www.aihero.dev/ai-coding-dictionary/smart-zone)**: the window (~120k tokens on state-of-the-art models) within which the model still reasons sharply. If a session approaches it before `/to-issues`, don't push on degraded — `/handoff` and continue in a fresh thread.
+The limit on this is the **[smart zone](https://www.aihero.dev/ai-coding-dictionary/smart-zone)**: the window (~120k tokens on state-of-the-art models) within which the model still reasons sharply. If a session approaches it before `/to-tickets`, don't push on degraded — `/handoff` and continue in a fresh thread.
 
 ## On-ramps
 
@@ -35,13 +37,26 @@ A starting situation that generates work, then merges onto the main flow.
 
 - **Bugs and requests piling up** → **`/triage`**. It moves issues through triage roles and produces agent-ready issues, which **`/implement`** later picks up.
 
-  Triage is only for issues **you didn't create** — bug reports, incoming feature requests, anything that arrives raw. Issues that `/to-issues` produced are already agent-ready, so **don't triage them**.
+  Triage is only for issues **you didn't create** — bug reports, incoming feature requests, anything that arrives raw. Tickets that `/to-tickets` produced are already agent-ready, so **don't triage them**.
+
+- **Something's broken** → **`/diagnosing-bugs`**. For the hard ones: the bug that resists a first glance, the intermittent flake, the regression that crept in between two known-good states. It refuses to theorise until it has a **tight feedback loop** — one command that already goes red on *this* bug — then fixes with a regression test. Its post-mortem hands off to **`/improve-codebase-architecture`** when the real finding is that there's no good seam to lock the bug down.
+
+- **A huge, foggy effort — a greenfield project or a huge feature build, too big for one session** → **`/wayfinder`**, the most cognitively demanding flow here. When the way from here to the destination isn't visible yet, it charts a **shared map** of **decision tickets** on the issue tracker and resolves them one at a time — producing **decisions, not deliverables** — until the fog is pushed back and the way is clear. Where **`/grill-with-docs`** sharpens an idea you can hold in one session, wayfinder is for the idea you can't — and it's slower and denser, so save it for exactly that, never a well-scoped feature.
+
+  When the map clears, **it hands off, it doesn't build**: merge onto the main flow at **`/to-spec`**, which collapses the map's linked decisions into a buildable plan, then `/to-tickets` and `/implement` as usual. Looping the map straight into `/implement` skips that collapse and throws the linked detail away — go straight to `/implement` only when the effort turned out genuinely small.
 
 ## Codebase health
 
 Not feature work — upkeep.
 
-- **`/improve-codebase-architecture`** — run whenever you have a spare moment to keep the codebase good for agents to operate in. It surfaces deepening opportunities; picking one _generates an idea_ you can take into the main flow at `/grill-with-docs`.
+- **`/improve-codebase-architecture`** — run whenever you have a spare moment to keep the codebase good for agents to operate in. It surfaces **deepening opportunities**; picking one _generates an idea_ you can take into the main flow at `/grill-with-docs`. It's the survey that finds the candidates; **`/codebase-design`** (below) is the bench you design the chosen one on.
+
+## Vocabulary underneath
+
+Two model-invoked references that run *beneath* the other skills — each the single source of truth for its vocabulary. Reach for them directly when the **words**, not the process, are the problem; or let the skills above pull them in.
+
+- **`/domain-modeling`** — sharpen the project's *domain* language: challenge a fuzzy term, resolve an overloaded word ("account" doing three jobs), record a hard-to-reverse decision as an ADR. It's the active discipline `/grill-with-docs` drives to keep `CONTEXT.md` a clean glossary.
+- **`/codebase-design`** — the deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for designing a module's *shape*: a lot of behaviour behind a small interface at a clean seam. `/tdd` and `/improve-codebase-architecture` both speak it.
 
 ## Crossing sessions
 
@@ -53,6 +68,8 @@ Not feature work — upkeep.
 Off the main flow entirely.
 
 - **`/grill-me`** — the same relentless interview as `/grill-with-docs`, but for when you have **no codebase**. Stateless: it saves nothing locally, builds no `CONTEXT.md`. Reach for it to sharpen any plan or design that doesn't live in a repo.
+- **`/prototype`** — a small, throwaway program that answers one design question: does this state model feel right, or what should this UI look like. Throwaway from day one — keep the answer, delete the code. It's the detour in step 2 of the main flow, but reach for it any time a design question is hard to settle on paper.
+- **`/research`** — delegate reading legwork to a **background agent**: it investigates a question against **primary sources**, then leaves a cited Markdown file in the repo. Keep working while it reads. The file it produces is something to take *into* the main flow at `/grill-with-docs` — research feeds the thinking, it doesn't replace it.
 - **`/teach`** — learn a concept over multiple sessions, using the current directory as a stateful workspace.
 - **`/writing-great-skills`** — reference for writing and editing skills well.
 

.agents/skills/ask-matt/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Ask Matt"
+  short_description: "Find the right skill or workflow"
+policy:
+  allow_implicit_invocation: false

.agents/skills/grilling/SKILL.md

@@ -1,10 +1,12 @@
 ---
 name: grilling
-description: Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
+description: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
 ---
 
-Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
+Interview me relentlessly about every aspect of this until we reach a shared understanding. Walk down each branch of the decision tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
 
 Ask the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering.
 
-If a question can be answered by exploring the codebase, explore the codebase instead.
+If a *fact* can be found by exploring the environment (filesystem, tools, etc.), look it up rather than asking me. The *decisions*, though, are mine — put each one to me and wait for my answer.
+
+Do not act on it until I confirm we have reached a shared understanding.

.agents/skills/grilling/agents/openai.yaml

@@ -0,0 +1,3 @@
+interface:
+  display_name: "Grilling"
+  short_description: "Stress-test thinking one question at a time"

.agents/skills/handoff/SKILL.md

@@ -9,7 +9,7 @@ Write a handoff document summarising the current conversation so a fresh agent c
 
 Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.
 
-Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
+Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
 
 Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
 

.agents/skills/handoff/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Handoff"
+  short_description: "Compact a conversation into a handoff"
+policy:
+  allow_implicit_invocation: false

.agents/skills/implement/SKILL.md

@@ -1,15 +1,15 @@
 ---
 name: implement
-description: "Implement a piece of work based on a PRD or set of issues."
+description: "Implement a piece of work based on a spec or set of tickets."
 disable-model-invocation: true
 ---
 
-Implement the work described by the user in the PRD or issues.
+Implement the work described by the user in the spec or tickets.
 
 Use /tdd where possible, at pre-agreed seams.
 
 Run typechecking regularly, single test files regularly, and the full test suite once at the end.
 
-Once done, use /review to review the work.
+Once done, use /code-review to review the work.
 
 Commit your work to the current branch.

.agents/skills/implement/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Implement"
+  short_description: "Build work from a spec or tickets"
+policy:
+  allow_implicit_invocation: false

.agents/skills/improve-codebase-architecture/SKILL.md

@@ -17,6 +17,11 @@ This command is _informed_ by the project's domain model and built on a shared d
 
 ### 1. Explore
 
+**Scope before you scan — YAGNI.** Deepening a module pays off by making future changes to it easier, so put extra weight on the parts of the codebase that have recently changed. Decide *where* to look before you look:
+
+- If the user named a direction — a module, a subsystem, a pain point — take it, and skip the inference below.
+- Otherwise, walk back a good stretch of the commit history (`git log --oneline`) to find the codebase's hot spots — the files and areas that keep coming up — and let those paths pull your attention first. If the changes are scattered with no clear hot spot, widen the net.
+
 Read the project's domain glossary (`CONTEXT.md`) and any ADRs in the area you're touching first.
 
 Then use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
@@ -56,7 +61,7 @@ Do NOT propose interfaces yet. After the file is written, ask the user: "Which o
 
 ### 3. Grilling loop
 
-Once the user picks a candidate, run the `/grilling` skill to walk the design tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
+Once the user picks a candidate, run the `/grilling` skill to walk the decision tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
 
 Side effects happen inline as decisions crystallize — run the `/domain-modeling` skill to keep the domain model current as you go:
 

.agents/skills/improve-codebase-architecture/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Improve Codebase Architecture"
+  short_description: "Find and grill architecture improvements"
+policy:
+  allow_implicit_invocation: false

.agents/skills/prototype/LOGIC.md

@@ -36,7 +36,7 @@ The right shape depends on the question:
 
 Pick whichever shape best fits the question being asked, *not* whichever is easiest to wire to a TUI. Keep it pure: no I/O, no terminal code, no `console.log` for control flow. The TUI imports it and calls into it; nothing flows the other direction.
 
-This is what makes the prototype useful past its own lifetime. When the question's been answered, the validated reducer / machine / function set can be lifted into the real module — the TUI shell gets deleted.
+This is what makes the prototype useful past its own lifetime: when the question's been answered, the validated reducer / machine / function set can be lifted into the real module on its own.
 
 ### 4. Build the smallest TUI that exposes the state
 
@@ -66,9 +66,9 @@ If the host project has no task runner, just put the command at the top of the p
 
 Give the user the run command. They'll drive it themselves; the interesting moments are when they say "wait, that shouldn't be possible" or "huh, I assumed X would be different" — those are the bugs in the _idea_, which is the whole point. If they want new actions added, add them. Prototypes evolve.
 
-### 7. Capture the answer
+### 7. Capture the answer and the prototype
 
-When the prototype has done its job, the answer to the question is the only thing worth keeping. If the user is around, ask what it taught them. If not, leave a `NOTES.md` next to the prototype so the answer can be filled in (or filled in by you, if you've watched the session) before the prototype gets deleted.
+Once the prototype has answered its question, capture the answer, then capture the prototype the way the [SKILL](SKILL.md) describes. The logic-specific mapping: the validated reducer / machine / function set lifts into the real module (the decision, absorbed); the TUI shell rides along to the throwaway branch that keeps the prototype as a primary source.
 
 ## Anti-patterns
 

.agents/skills/prototype/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: prototype
-description: Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
-disable-model-invocation: true
+description: Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
 ---
 
 # Prototype
@@ -22,10 +21,6 @@ The two branches produce very different artifacts — getting this wrong wastes
 1. **Throwaway from day one, and clearly marked as such.** Locate the prototype code close to where it will actually be used (next to the module or page it's prototyping for) so context is obvious — but name it so a casual reader can see it's a prototype, not production. For throwaway UI routes, obey whatever routing convention the project already uses; don't invent a new top-level structure.
 2. **One command to run.** Whatever the project's existing task runner supports — `pnpm <name>`, `python <path>`, `bun <path>`, etc. The user must be able to start it without thinking.
 3. **No persistence by default.** State lives in memory. Persistence is the thing the prototype is _checking_, not something it should depend on. If the question explicitly involves a database, hit a scratch DB or a local file with a clear "PROTOTYPE — wipe me" name.
-4. **Skip the polish.** No tests, no error handling beyond what makes the prototype _runnable_, no abstractions. The point is to learn something fast and then delete it.
+4. **Skip the polish.** No tests, no error handling beyond what makes the prototype _runnable_, no abstractions. The point is to learn something fast.
 5. **Surface the state.** After every action (logic) or on every variant switch (UI), print or render the full relevant state so the user can see what changed.
-6. **Delete or absorb when done.** When the prototype has answered its question, either delete it or fold the validated decision into the real code — don't leave it rotting in the repo.
-
-## When done
-
-The _answer_ is the only thing worth keeping from a prototype. Capture it somewhere durable (commit message, ADR, issue, or a `NOTES.md` next to the prototype) along with the question it was answering. If the user is around, that capture is a quick conversation; if not, leave the placeholder so they (or you, on the next pass) can fill in the verdict before deleting the prototype.
+6. **Capture it when done.** Fold any validated decision into the real code, then capture the prototype itself as a **primary source**: commit it to a throwaway branch, out of main, and leave a context pointer to that branch on the implementation issue. Capture the answer too — the verdict and the question it settled — in the issue or a commit. The main branch keeps only the validated decision.

.agents/skills/prototype/UI.md

@@ -97,12 +97,12 @@ Surface the URL (and the `?variant=` keys). The user will flip through whenever
 
 ### 6. Capture the answer and clean up
 
-Once a variant has won, write down which one and why (commit message, ADR, issue, or a `NOTES.md` next to the prototype if running AFK and the user hasn't responded yet). Then:
+Once a variant has won, capture the answer — which variant and why — then capture the prototype the way the [SKILL](SKILL.md) describes. Fold the winner into the real code and move the rest onto the throwaway branch, not into main:
 
-- **Sub-shape A** — delete the losing variants and the switcher; fold the winner into the existing page.
-- **Sub-shape B** — promote the winning variant to a real route, delete the throwaway route and the switcher.
+- **Sub-shape A** — fold the winner into the existing page; drop the losing variants and the switcher from main.
+- **Sub-shape B** — promote the winning variant to a real route; drop the throwaway route and the switcher from main.
 
-Don't leave variant components or the switcher lying around. They rot fast and confuse the next reader.
+The full set of variants is the primary source, so it lands on the throwaway branch, not the bin — variant components and the switcher left in the main branch rot fast and confuse the next reader.
 
 ## Anti-patterns
 

.agents/skills/prototype/agents/openai.yaml

@@ -0,0 +1,3 @@
+interface:
+  display_name: "Prototype"
+  short_description: "Prototype to answer a design question"

.agents/skills/setup-matt-pocock-skills/SKILL.md

@@ -26,16 +26,18 @@ Look at the current repo to understand its starting state. Read whatever exists;
 - `docs/adr/` and any `src/*/docs/adr/` directories
 - `docs/agents/` — does this skill's prior output already exist?
 - `.scratch/` — sign that a local-markdown issue tracker convention is already in use
+- Is the `triage` skill installed? (a `triage` skill folder alongside this one, or `triage` in your available skills.) This decides whether Section B runs at all.
+- Monorepo signals — a `pnpm-workspace.yaml`, a `workspaces` field in `package.json`, or a populated `packages/*` with its own `src/`. Present only in a genuinely large multi-package repo; their absence means single-context, which is almost every repo.
 
 ### 2. Present findings and ask
 
-Summarise what's present and what's missing. Then walk the user through the three decisions **one at a time** — present a section, get the user's answer, then move to the next. Don't dump all three at once.
+Summarise what's present and what's missing. Then take the sections in order — one section, one answer, then the next.
 
-Assume the user does not know what these terms mean. Each section starts with a short explainer (what it is, why these skills need it, what changes if they pick differently). Then show the choices and the default.
+Lead each section with the recommended answer so the user can accept it in a word. Give a one-line explainer only when the choice genuinely branches; skip the section entirely when exploration already settled it (Section B when `triage` isn't installed, Section C when there's no monorepo).
 
 **Section A — Issue tracker.**
 
-> Explainer: The "issue tracker" is where issues live for this repo. Skills like `to-issues`, `triage`, `to-prd`, and `qa` read from and write to it — they need to know whether to call `gh issue create`, write a markdown file under `.scratch/`, or follow some other workflow you describe. Pick the place you actually track work for this repo.
+> Explainer: The "issue tracker" is where issues live for this repo. Skills like `to-tickets`, `triage`, `to-spec`, and `qa` read from and write to it — they need to know whether to call `gh issue create`, write a markdown file under `.scratch/`, or follow some other workflow you describe. Pick the place you actually track work for this repo.
 
 Default posture: these skills were designed for GitHub. If a `git remote` points at GitHub, propose that. If a `git remote` points at GitLab (`gitlab.com` or a self-hosted host), propose GitLab. Otherwise (or if the user prefers), offer:
 
@@ -44,41 +46,26 @@ Default posture: these skills were designed for GitHub. If a `git remote` points
 - **Local markdown** — issues live as files under `.scratch/<feature>/` in this repo (good for solo projects or repos without a remote)
 - **Other** (Jira, Linear, etc.) — ask the user to describe the workflow in one paragraph; the skill will record it as freeform prose
 
-If — and only if — the user picked **GitHub** or **GitLab**, ask one follow-up:
+Record the choice in `docs/agents/issue-tracker.md`. The GitHub and GitLab templates carry a "PRs as a request surface" flag, defaulted **off** — leave it off and don't raise it; a user who wants external PRs in the triage queue can flip the flag in the file later.
 
-> Explainer: Open-source repos often receive feature requests as pull requests, not just issues — a PR is an issue with attached code. If you turn this on, `/triage` pulls *external* PRs into the same queue and runs them through the same labels and states as issues (collaborators' in-flight PRs are left alone). Leave it off if PRs aren't a request surface for you.
+**Section B — Triage label vocabulary.** Skip this section entirely if the `triage` skill isn't installed (exploration told you) — an uninstalled skill needs no labels.
 
-- **PRs as a request surface** — yes / no (default: no). Record the answer in `docs/agents/issue-tracker.md`. For local-markdown and other trackers, skip this question — there are no PRs.
+If it is installed, ask exactly one question:
 
-**Section B — Triage label vocabulary.**
+> Do you want to keep the default triage labels? (recommended: **yes**)
 
-> Explainer: When the `triage` skill processes an incoming issue, it moves it through a state machine — needs evaluation, waiting on reporter, ready for an AFK agent to pick up, ready for a human, or won't fix. To do that, it needs to apply labels (or the equivalent in your issue tracker) that match strings *you've actually configured*. If your repo already uses different label names (e.g. `bug:triage` instead of `needs-triage`), map them here so the skill applies the right ones instead of creating duplicates.
+The defaults are the five canonical roles, each label string equal to its name: `needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, `wontfix`. On **yes**, write them as-is. Only if the user says no — usually because their tracker already uses other names (e.g. `bug:triage` for `needs-triage`) — collect the overrides so `triage` applies existing labels instead of creating duplicates.
 
-The five canonical roles:
+**Section C — Domain docs.** Default to **single-context** — one `CONTEXT.md` + `docs/adr/` at the repo root. This fits almost every repo; write it without asking.
 
-- `needs-triage` — maintainer needs to evaluate
-- `needs-info` — waiting on reporter
-- `ready-for-agent` — fully specified, AFK-ready (an agent can pick it up with no human context)
-- `ready-for-human` — needs human implementation
-- `wontfix` — will not be actioned
-
-Default: each role's string equals its name. Ask the user if they want to override any. If their issue tracker has no existing labels, the defaults are fine.
-
-**Section C — Domain docs.**
-
-> Explainer: Some skills (`improve-codebase-architecture`, `diagnosing-bugs`, `tdd`) read a `CONTEXT.md` file to learn the project's domain language, and `docs/adr/` for past architectural decisions. They need to know whether the repo has one global context or multiple (e.g. a monorepo with separate frontend/backend contexts) so they look in the right place.
-
-Confirm the layout:
-
-- **Single-context** — one `CONTEXT.md` + `docs/adr/` at the repo root. Most repos are this.
-- **Multi-context** — `CONTEXT-MAP.md` at the root pointing to per-context `CONTEXT.md` files (typically a monorepo).
+Offer **multi-context** — a root `CONTEXT-MAP.md` pointing to per-context `CONTEXT.md` files — only when exploration found monorepo signals. Then confirm which layout they want.
 
 ### 3. Confirm and edit
 
 Show the user a draft of:
 
 - The `## Agent skills` block to add to whichever of `CLAUDE.md` / `AGENTS.md` is being edited (see step 4 for selection rules)
-- The contents of `docs/agents/issue-tracker.md`, `docs/agents/triage-labels.md`, `docs/agents/domain.md`
+- The contents of `docs/agents/issue-tracker.md`, `docs/agents/domain.md`, and `docs/agents/triage-labels.md` (the last only when `triage` is installed)
 
 Let them edit before writing.
 
@@ -101,7 +88,7 @@ The block:
 
 ### Issue tracker
 
-[one-line summary of where issues are tracked, plus whether external PRs are a triage surface]. See `docs/agents/issue-tracker.md`.
+[one-line summary of where issues are tracked]. See `docs/agents/issue-tracker.md`.
 
 ### Triage labels
 
@@ -112,12 +99,14 @@ The block:
 [one-line summary of layout — "single-context" or "multi-context"]. See `docs/agents/domain.md`.
 ```
 
-Then write the three docs files using the seed templates in this skill folder as a starting point:
+Include the `### Triage labels` sub-block, and write `docs/agents/triage-labels.md`, only when `triage` is installed and Section B ran. When it isn't, both are omitted.
+
+Then write the docs files using the seed templates in this skill folder as a starting point:
 
 - [issue-tracker-github.md](./issue-tracker-github.md) — GitHub issue tracker
 - [issue-tracker-gitlab.md](./issue-tracker-gitlab.md) — GitLab issue tracker
 - [issue-tracker-local.md](./issue-tracker-local.md) — local-markdown issue tracker
-- [triage-labels.md](./triage-labels.md) — label mapping
+- [triage-labels.md](./triage-labels.md) — label mapping (only if `triage` is installed)
 - [domain.md](./domain.md) — domain doc consumer rules + layout
 
 For "other" issue trackers, write `docs/agents/issue-tracker.md` from scratch using the user's description.

.agents/skills/setup-matt-pocock-skills/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Setup Matt Pocock Skills"
+  short_description: "Configure a repo for the skills"
+policy:
+  allow_implicit_invocation: false

.agents/skills/setup-matt-pocock-skills/issue-tracker-github.md

@@ -32,3 +32,14 @@ Create a GitHub issue.
 ## When a skill says "fetch the relevant ticket"
 
 Run `gh issue view <number> --comments`.
+
+## Wayfinding operations
+
+Used by `/wayfinder`. The **map** is a single issue with **child** issues as tickets.
+
+- **Map**: a single issue labelled `wayfinder:map`, holding the Notes / Decisions-so-far / Fog body. `gh issue create --label wayfinder:map`.
+- **Child ticket**: an issue linked to the map as a GitHub sub-issue (`gh api` on the sub-issues endpoint). Where sub-issues aren't enabled, add the child to a task list in the map body and put `Part of #<map>` at the top of the child body. Labels: `wayfinder:<type>` (`research`/`prototype`/`grilling`/`task`). Once claimed, the ticket is assigned to the driving dev.
+- **Blocking**: GitHub's **native issue dependencies** — the canonical, UI-visible representation. Add an edge with `gh api --method POST repos/<owner>/<repo>/issues/<child>/dependencies/blocked_by -F issue_id=<blocker-db-id>`, where `<blocker-db-id>` is the blocker's numeric **database id** (`gh api repos/<owner>/<repo>/issues/<n> --jq .id`, _not_ the `#number` or `node_id`). GitHub reports `issue_dependencies_summary.blocked_by` (open blockers only — the live gate). Where dependencies aren't available, fall back to a `Blocked by: #<n>, #<n>` line at the top of the child body. A ticket is unblocked when every blocker is closed.
+- **Frontier query**: list the map's open children (`gh issue list --state open`, scoped to the map's sub-issues / task list), drop any with an open blocker (`issue_dependencies_summary.blocked_by > 0`, or an open issue in the `Blocked by` line) or an assignee; first in map order wins.
+- **Claim**: `gh issue edit <n> --add-assignee @me` — the session's first write.
+- **Resolve**: `gh issue comment <n> --body "<answer>"`, then `gh issue close <n>`, then append a context pointer (gist + link) to the map's Decisions-so-far.

.agents/skills/setup-matt-pocock-skills/issue-tracker-gitlab.md

@@ -33,3 +33,14 @@ Create a GitLab issue.
 ## When a skill says "fetch the relevant ticket"
 
 Run `glab issue view <number> --comments`.
+
+## Wayfinding operations
+
+Used by `/wayfinder`. The **map** is a single issue with **child** issues as tickets.
+
+- **Map**: a single issue labelled `wayfinder:map`, holding the Notes / Decisions-so-far / Fog body. `glab issue create --label wayfinder:map`. (On GitLab tiers with native epics, an epic may hold the map instead; a labelled issue works everywhere.)
+- **Child ticket**: an issue carrying `Part of #<map>` at the top of its description and labels `wayfinder:<type>` (`research`/`prototype`/`grilling`/`task`). Once claimed, the ticket is assigned to the driving dev.
+- **Blocking**: GitLab's **native blocking link** — the canonical, UI-visible representation. Add it with the `/blocked_by #<n>` quick action, posted as a note (`glab issue note <child> --message "/blocked_by #<blocker>"`). Native blocking links are a Premium/Ultimate feature; on the free tier (or where unavailable) fall back to a `Blocked by: #<n>, #<n>` line at the top of the description. A ticket is unblocked when every blocker is closed.
+- **Frontier query**: `glab issue list -F json` scoped to the map's children, drop any with an open blocker — a native `blocked_by` link to an open issue (`glab api projects/:id/issues/:iid/links`), or an open issue in the `Blocked by` line — or an assignee; first in map order wins.
+- **Claim**: `glab issue update <n> --assignee @me` — the session's first write.
+- **Resolve**: `glab issue note <n> --message "<answer>"`, then `glab issue close <n>`, then append a context pointer (gist + link) to the map's Decisions-so-far.

.agents/skills/setup-matt-pocock-skills/issue-tracker-local.md

@@ -1,12 +1,12 @@
 # Issue tracker: Local Markdown
 
-Issues and PRDs for this repo live as markdown files in `.scratch/`.
+Issues and specs (you may know a spec as a PRD) for this repo live as markdown files in `.scratch/`.
 
 ## Conventions
 
 - One feature per directory: `.scratch/<feature-slug>/`
-- The PRD is `.scratch/<feature-slug>/PRD.md`
-- Implementation issues are `.scratch/<feature-slug>/issues/<NN>-<slug>.md`, numbered from `01`
+- The spec is `.scratch/<feature-slug>/spec.md`
+- Implementation issues are one file per ticket at `.scratch/<feature-slug>/issues/<NN>-<slug>.md`, numbered from `01` — never a single combined tickets file
 - Triage state is recorded as a `Status:` line near the top of each issue file (see `triage-labels.md` for the role strings)
 - Comments and conversation history append to the bottom of the file under a `## Comments` heading
 
@@ -17,3 +17,14 @@ Create a new file under `.scratch/<feature-slug>/` (creating the directory if ne
 ## When a skill says "fetch the relevant ticket"
 
 Read the file at the referenced path. The user will normally pass the path or the issue number directly.
+
+## Wayfinding operations
+
+Used by `/wayfinder`. The **map** is a file with one **child** file per ticket.
+
+- **Map**: `.scratch/<effort>/map.md` — the Notes / Decisions-so-far / Fog body.
+- **Child ticket**: `.scratch/<effort>/issues/NN-<slug>.md`, numbered from `01`, with the question in the body. A `Type:` line records the ticket type (`research`/`prototype`/`grilling`/`task`); a `Status:` line records `claimed`/`resolved`.
+- **Blocking**: a `Blocked by: NN, NN` line near the top. A ticket is unblocked when every file it lists is `resolved`.
+- **Frontier**: scan `.scratch/<effort>/issues/` for files that are open, unblocked, and unclaimed; first by number wins.
+- **Claim**: set `Status: claimed` and save before any work.
+- **Resolve**: append the answer under an `## Answer` heading, set `Status: resolved`, then append a context pointer (gist + link) to the map's Decisions-so-far in `map.md`.

.agents/skills/setup-ts-deep-modules/SKILL.md

@@ -0,0 +1,102 @@
+---
+name: setup-ts-deep-modules
+description: Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
+disable-model-invocation: true
+---
+
+# Setup TS Deep Modules
+
+Make every package in this repo a **deep module**: a lot of behaviour behind a small interface. A package's public surface is its **entry points** — the files at the package root — and everything in its subfolders is hidden. This skill installs [dependency-cruiser](https://github.com/sverweij/dependency-cruiser) and the rules that make the entry points the only way in, then proves the rules bite.
+
+For the vocabulary (deep module, interface, seam, depth), run the `/codebase-design` skill — use its language throughout.
+
+## The shape this enforces
+
+```
+src/packages/
+  <name>/
+    index.ts        ← an entry point (public). Import this from outside.
+    client.ts       ← another entry point. Packages may expose SEVERAL.
+    lib/            ← implementation: hidden from outside, free to import each other.
+    tests/          ← co-located tests + fixtures (a subfolder, so private).
+```
+
+The public surface is the package's **root files** — not one designated `index.ts`. By convention implementation lives in `lib/` and tests in `tests/`, giving every package the same two-folder shape. The rule itself is general, though: *anything* in *any* subfolder is private, so you never extend the config to add a folder.
+
+Four rules, all `error`:
+
+1. **Entry-point boundary** — code outside a package (app code or another package) may import only that package's entry points (its root files), never anything in its subfolders.
+2. **Intra-package freedom** — a package's own files import each other freely.
+3. **Tests through the entry points** — files under `<pkg>/tests/` may import any package's entry points and their own `tests/` fixtures, but never any package's subfolder internals (not even their own). Integration tests across packages are fine; deep imports are not.
+4. **No cycles** — no dependency cycles.
+
+**Entry points, not a barrel.** Because the public surface is *every* root file, a package can expose several small entry points (`index.ts`, `client.ts`, `server.ts`) instead of funnelling everything through one giant `index.ts`. Barrel files that re-export a whole subtree are discouraged — keep entry points small and hide implementation in subfolders.
+
+Layering (which packages may depend on which) is a *different* concern and is left as a commented stub in the config for this repo to fill in.
+
+## Steps
+
+### 1. Detect the environment
+
+- **Package manager** — `pnpm-lock.yaml` → pnpm, `yarn.lock` → yarn, `bun.lockb` → bun, else npm. Use it for every command below (`pnpm`/`yarn`/`npm run`/`bunx`).
+- **Packages root** — if `src/` exists use `src/packages`, else `packages`. Confirm the choice with the user if the repo already has a different obvious convention.
+- **Existing config** — check for a `.dependency-cruiser.*` file. If one exists, do **not** overwrite it: merge the four rules and the options in, and tell the user what you added.
+
+**Done when:** package manager, packages root, and existing-config status are all known.
+
+### 2. Install dependency-cruiser
+
+Install `dependency-cruiser` as a devDependency with the detected package manager.
+
+**Done when:** `dependency-cruiser` is in `devDependencies`.
+
+### 3. Write the config
+
+Copy [`dependency-cruiser.config.cjs`](./dependency-cruiser.config.cjs) to the repo root as `.dependency-cruiser.cjs`. Set `PACKAGES_ROOT` to the root detected in step 1. The rules are path-depth based and extension-agnostic, so nothing else needs adapting.
+
+**Done when:** `.dependency-cruiser.cjs` exists with the correct `PACKAGES_ROOT`, and the four forbidden rules are present.
+
+### 4. Wire it into the checks
+
+- Add a `lint:boundaries` script: `depcruise <packages-root>` (or `depcruise src`).
+- Fold it into the repo's umbrella check command — the one that already runs typecheck (e.g. a `check` / `ci` / `validate` script). Do **not** touch `tsconfig` or add path aliases.
+- If there is no umbrella script, add `lint:boundaries` and tell the user to include it in CI.
+
+**Done when:** `lint:boundaries` exists and runs as part of the same command as typecheck.
+
+### 5. Scaffold the example package
+
+Create a committed `<packages-root>/example/` as a copy-me template:
+
+- `index.ts` — an entry point. Export one function that delegates to an internal file (so the package is visibly *deep*, not a pass-through).
+- `lib/impl.ts` — an internal file in a **subfolder**, imported by `index.ts`, not reachable from outside.
+- `tests/example.test.ts` — imports **only** `../index` (an entry point), and asserts against the public function.
+
+Tell the user this is a starter template to copy or delete.
+
+**Done when:** the example package exists, exposes its behaviour through a root entry point, and hides `impl` in a subfolder.
+
+### 6. Prove the rules bite
+
+This is the completion criterion for the whole skill — a config that doesn't fail on a violation is worthless.
+
+1. Run `lint:boundaries`. It must **pass** on the clean example.
+2. Temporarily add a deep import to `tests/example.test.ts` (e.g. `import { thing } from "../lib/impl"`). Run `lint:boundaries` again — it must **fail** with `tests-through-entrypoints`.
+3. Revert the deep import. Run once more — it must **pass**.
+
+**Done when:** you have observed a pass, then a fail on the deep import, then a pass again. If step 2 does not fail, the rules are not wired correctly — fix before finishing.
+
+### 7. Document the convention
+
+Write a `README.md` **in the packages folder** (`<packages-root>/README.md`) — next to the packages it governs — covering: the `src/packages/<name>/` layout (entry points at the root, `lib/` for implementation, `tests/` for tests), "import only through a package's entry points (its root files)", and how to run `lint:boundaries`. **Discourage barrel files** explicitly — expose several small entry points instead of re-exporting a whole subtree through one index. Keep it to the copy-me snippet plus the four rules in one paragraph each.
+
+Then add a **context pointer** to it from the repo's agent-instructions file — `CLAUDE.md` if present, else `AGENTS.md` (create `AGENTS.md` if neither exists). One line is enough, e.g. `Packages are deep modules — see [src/packages/README.md](./src/packages/README.md) before adding or importing one.` This is what makes an agent discover the boundary rule instead of tripping over it.
+
+**Done when:** `<packages-root>/README.md` exists and discourages barrels, and the repo's `CLAUDE.md`/`AGENTS.md` links to it.
+
+## Notes
+
+- The config's `$1` back-references (dependency-cruiser's group matching) are what let a package reach its own internals while outsiders can't — don't flatten them into separate per-package rules.
+- Public vs private is decided by **depth**: a package's root files are entry points; anything in a subfolder is private. The conventional subfolders are `lib/` (implementation) and `tests/`, but the rule doesn't hardcode them — any subfolder is private, so a new folder never needs a config change. Adding an entry point is just adding a root file — no barrel.
+- Packages are **flat**: one tier of immediate children under the root. A package's internals may nest as deep as you like; a package may not contain another package.
+- Use `.cjs` (not `.js`) so the config's `module.exports` works even in `"type": "module"` repos.

.agents/skills/setup-ts-deep-modules/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Setup TS Deep Modules"
+  short_description: "Enforce deep TypeScript modules"
+policy:
+  allow_implicit_invocation: false

.agents/skills/setup-ts-deep-modules/dependency-cruiser.config.cjs

@@ -0,0 +1,95 @@
+// @ts-check
+// Deep-module enforcement for dependency-cruiser.
+//
+// Each package under the packages root is a DEEP MODULE: a lot of behaviour
+// behind a small interface. A package's PUBLIC SURFACE is its ENTRY POINTS —
+// the files at the package root. Implementation lives in SUBFOLDERS and is
+// private — by convention `lib/` for implementation and `tests/` for tests,
+// though any subfolder is private. A package may expose several small entry
+// points (index.ts, client.ts, server.ts, …) — prefer that over one giant
+// barrel index.
+//
+// The only thing you should ever need to edit here is PACKAGES_ROOT.
+
+/** Where packages live. One immediate child dir per package (flat, no nesting). */
+const PACKAGES_ROOT = "src/packages";
+
+// --- derived patterns (no need to edit) -------------------------------------
+const R = PACKAGES_ROOT;
+/**
+ * A package's private internals: anything nested inside a package subfolder.
+ * The package's root files are its entry points and are NOT matched here —
+ * they stay importable from outside.
+ */
+const PACKAGE_INTERNALS = `^${R}/[^/]+/[^/]+/`;
+
+/** @type {import('dependency-cruiser').IConfiguration} */
+module.exports = {
+  forbidden: [
+    {
+      name: "entrypoint-boundary-from-app",
+      comment:
+        "App/root code may import a package's entry points (its root files), but nothing inside its subfolders.",
+      severity: "error",
+      from: { pathNot: `^${R}/` }, // importer is NOT inside any package
+      to: { path: PACKAGE_INTERNALS },
+    },
+    {
+      name: "entrypoint-boundary-across-packages",
+      comment:
+        "A package's own files import each other freely, but may reach OTHER packages only through their entry points — never their internals.",
+      severity: "error",
+      // importer is inside a package ($1), but is not a test file
+      from: { path: `^${R}/([^/]+)/`, pathNot: `^${R}/[^/]+/tests/` },
+      to: {
+        path: PACKAGE_INTERNALS,
+        pathNot: `^${R}/$1/`, // same package → intra-package freedom
+      },
+    },
+    {
+      name: "tests-through-entrypoints",
+      comment:
+        "A package's tests exercise it through its entry points like everyone else: they may import any package's entry points and their own tests/ fixtures, but never any package's internals — not even their own.",
+      severity: "error",
+      from: { path: `^${R}/([^/]+)/tests/` }, // a test file, in package $1
+      to: {
+        path: PACKAGE_INTERNALS,
+        pathNot: `^${R}/$1/tests/`, // own tests/ fixtures → allowed
+      },
+    },
+    {
+      name: "tests-folder-is-private",
+      comment:
+        "A package's tests/ folder is reachable only from tests — nothing else may import fixtures.",
+      severity: "error",
+      from: { pathNot: `^${R}/[^/]+/tests/` }, // importer is not itself a test
+      to: { path: `^${R}/[^/]+/tests/` },
+    },
+    {
+      name: "no-circular",
+      comment: "No dependency cycles. Scope to `^${R}/` if you want to allow cycles outside packages.",
+      severity: "error",
+      from: {},
+      to: { circular: true },
+    },
+
+    // --- Layering (optional, off by default) ----------------------------------
+    // Interface-hiding controls HOW you import (through the entry points).
+    // Layering controls WHICH packages may depend on which. Add your own rules
+    // here, e.g.:
+    //
+    // {
+    //   name: "ui-may-not-depend-on-billing",
+    //   severity: "error",
+    //   from: { path: `^${R}/ui/` },
+    //   to:   { path: `^${R}/billing/` },
+    // },
+  ],
+  options: {
+    doNotFollow: { path: "node_modules" },
+    tsConfig: { fileName: "tsconfig.json" },
+    enhancedResolveOptions: {
+      extensions: [".ts", ".tsx", ".js", ".jsx", ".json"],
+    },
+  },
+};

.agents/skills/tdd/SKILL.md

@@ -5,104 +5,32 @@ description: Test-driven development. Use when the user wants to build features
 
 # Test-Driven Development
 
-## Philosophy
+TDD is the red → green loop. This skill is the reference that makes that loop produce tests worth keeping: what a good test is, where tests go, the anti-patterns, and the rules of the loop. Every section applies on every cycle — consult them before and during the loop, not after.
 
-**Core principle**: Tests should verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't.
+When exploring the codebase, read `CONTEXT.md` (if it exists) so test names and interface vocabulary match the project's domain language, and respect ADRs in the area you're touching.
 
-**Good tests** are integration-style: they exercise real code paths through public APIs. They describe _what_ the system does, not _how_ it does it. A good test reads like a specification - "user can checkout with valid cart" tells you exactly what capability exists. These tests survive refactors because they don't care about internal structure.
+## What a good test is
 
-**Bad tests** are coupled to implementation. They mock internal collaborators, test private methods, or verify through external means (like querying a database directly instead of using the interface). The warning sign: your test breaks when you refactor, but behavior hasn't changed. If you rename an internal function and tests fail, those tests were testing implementation, not behavior.
+Tests verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't. A good test reads like a specification — "user can checkout with valid cart" tells you exactly what capability exists — and survives refactors because it doesn't care about internal structure.
 
 See [tests.md](tests.md) for examples and [mocking.md](mocking.md) for mocking guidelines.
 
-## Anti-Pattern: Horizontal Slices
+## Seams — where tests go
 
-**DO NOT write all tests first, then all implementation.** This is "horizontal slicing" - treating RED as "write all tests" and GREEN as "write all code."
+A **seam** is the public boundary you test at: the interface where you observe behavior without reaching inside. Tests live at seams, never against internals.
 
-This produces **crap tests**:
+**Test only at pre-agreed seams.** Before writing any test, write down the seams under test and confirm them with the user. No test is written at an unconfirmed seam. You can't test everything — agreeing the seams up front is how testing effort lands on the critical paths and complex logic instead of every edge case.
 
-- Tests written in bulk test _imagined_ behavior, not _actual_ behavior
-- You end up testing the _shape_ of things (data structures, function signatures) rather than user-facing behavior
-- Tests become insensitive to real changes - they pass when behavior breaks, fail when behavior is fine
-- You outrun your headlights, committing to test structure before understanding the implementation
+Ask: "What's the public interface, and which seams should we test?"
 
-**Correct approach**: Vertical slices via tracer bullets. One test → one implementation → repeat. Each test responds to what you learned from the previous cycle. Because you just wrote the code, you know exactly what behavior matters and how to verify it.
+## Anti-patterns
 
-```
-WRONG (horizontal):
-  RED:   test1, test2, test3, test4, test5
-  GREEN: impl1, impl2, impl3, impl4, impl5
+- **Implementation-coupled** — mocks internal collaborators, tests private methods, or verifies through a side channel (querying the database instead of using the interface). The tell: the test breaks when you refactor but behavior hasn't changed.
+- **Tautological** — the assertion recomputes the expected value the way the code does (`expect(add(a, b)).toBe(a + b)`, a snapshot derived by hand the same way, a constant asserted equal to itself), so it passes by construction and can never disagree with the code. Expected values must come from an independent source of truth — a known-good literal, a worked example, the spec.
+- **Horizontal slicing** — writing all tests first, then all implementation. Bulk tests verify _imagined_ behavior: you test the _shape_ of things rather than user-facing behavior, the tests go insensitive to real changes, and you commit to test structure before understanding the implementation. Work in **vertical slices** instead — one test → one implementation → repeat, each test a **tracer bullet** that responds to what the last cycle taught you.
 
-RIGHT (vertical):
-  RED→GREEN: test1→impl1
-  RED→GREEN: test2→impl2
-  RED→GREEN: test3→impl3
-  ...
-```
+## Rules of the loop
 
-## Workflow
-
-### 1. Planning
-
-When exploring the codebase, read `CONTEXT.md` (if it exists) so that test names and interface vocabulary match the project's domain language, and respect ADRs in the area you're touching.
-
-Before writing any code:
-
-- [ ] Confirm with user what interface changes are needed
-- [ ] Confirm with user which behaviors to test (prioritize)
-- [ ] Identify opportunities for deep modules (small interface, deep implementation) — run the `/codebase-design` skill for the vocabulary and the testability checks
-- [ ] List the behaviors to test (not implementation steps)
-- [ ] Get user approval on the plan
-
-Ask: "What should the public interface look like? Which behaviors are most important to test?"
-
-**You can't test everything.** Confirm with the user exactly which behaviors matter most. Focus testing effort on critical paths and complex logic, not every possible edge case.
-
-### 2. Tracer Bullet
-
-Write ONE test that confirms ONE thing about the system:
-
-```
-RED:   Write test for first behavior → test fails
-GREEN: Write minimal code to pass → test passes
-```
-
-This is your tracer bullet - proves the path works end-to-end.
-
-### 3. Incremental Loop
-
-For each remaining behavior:
-
-```
-RED:   Write next test → fails
-GREEN: Minimal code to pass → passes
-```
-
-Rules:
-
-- One test at a time
-- Only enough code to pass current test
-- Don't anticipate future tests
-- Keep tests focused on observable behavior
-
-### 4. Refactor
-
-After all tests pass, look for [refactor candidates](refactoring.md):
-
-- [ ] Extract duplication
-- [ ] Deepen modules (move complexity behind simple interfaces)
-- [ ] Apply SOLID principles where natural
-- [ ] Consider what new code reveals about existing code
-- [ ] Run tests after each refactor step
-
-**Never refactor while RED.** Get to GREEN first.
-
-## Checklist Per Cycle
-
-```
-[ ] Test describes behavior, not implementation
-[ ] Test uses public interface only
-[ ] Test would survive internal refactor
-[ ] Code is minimal for this test
-[ ] No speculative features added
-```
+- **Red before green.** Write the failing test first, then only enough code to pass it. Don't anticipate future tests or add speculative features.
+- **One slice at a time.** One seam, one test, one minimal implementation per cycle.
+- **Refactoring is not part of the loop.** It belongs to the review stage (see the `code-review` skill), not the red → green implementation cycle.

.agents/skills/tdd/agents/openai.yaml

@@ -0,0 +1,3 @@
+interface:
+  display_name: "TDD"
+  short_description: "Test-driven red-green-refactor"

.agents/skills/tdd/tests.md

@@ -59,3 +59,19 @@ test("createUser makes user retrievable", async () => {
   expect(retrieved.name).toBe("Alice");
 });
 ```
+
+**Tautological tests**: Expected value restates the implementation, so the test passes by construction.
+
+```typescript
+// BAD: Expected value is recomputed the way the code computes it
+test("calculateTotal sums line items", () => {
+  const items = [{ price: 10 }, { price: 5 }];
+  const expected = items.reduce((sum, i) => sum + i.price, 0);
+  expect(calculateTotal(items)).toBe(expected);
+});
+
+// GOOD: Expected value is an independent, known literal
+test("calculateTotal sums line items", () => {
+  expect(calculateTotal([{ price: 10 }, { price: 5 }])).toBe(15);
+});
+```

.agents/skills/to-spec/SKILL.md

@@ -0,0 +1,75 @@
+---
+name: to-spec
+description: Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
+disable-model-invocation: true
+---
+
+This skill takes the current conversation context and codebase understanding and produces a spec (you may know this document as a PRD). Do NOT interview the user — just synthesize what you already know.
+
+The issue tracker and triage label vocabulary should have been provided to you — run `/setup-matt-pocock-skills` if not.
+
+## Process
+
+1. Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the spec, and respect any ADRs in the area you're touching.
+
+2. Sketch out the seams at which you're going to test the feature. Existing seams should be preferred to new ones. Use the highest seam possible. If new seams are needed, propose them at the highest point you can. The fewer seams across the codebase, the better - the ideal number is one.
+
+Check with the user that these seams match their expectations.
+
+3. Write the spec using the template below, then publish it to the project issue tracker. Apply the `ready-for-agent` triage label - no need for additional triage.
+
+<spec-template>
+
+## Problem Statement
+
+The problem that the user is facing, from the user's perspective.
+
+## Solution
+
+The solution to the problem, from the user's perspective.
+
+## User Stories
+
+A LONG, numbered list of user stories. Each user story should be in the format of:
+
+1. As an <actor>, I want a <feature>, so that <benefit>
+
+<user-story-example>
+1. As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending
+</user-story-example>
+
+This list of user stories should be extremely extensive and cover all aspects of the feature.
+
+## Implementation Decisions
+
+A list of implementation decisions that were made. This can include:
+
+- The modules that will be built/modified
+- The interfaces of those modules that will be modified
+- Technical clarifications from the developer
+- Architectural decisions
+- Schema changes
+- API contracts
+- Specific interactions
+
+Do NOT include specific file paths or code snippets. They may end up being outdated very quickly.
+
+Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits.
+
+## Testing Decisions
+
+A list of testing decisions that were made. Include:
+
+- A description of what makes a good test (only test external behavior, not implementation details)
+- Which modules will be tested
+- Prior art for the tests (i.e. similar types of tests in the codebase)
+
+## Out of Scope
+
+A description of the things that are out of scope for this spec.
+
+## Further Notes
+
+Any further notes about the feature.
+
+</spec-template>

.agents/skills/to-spec/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "To Spec"
+  short_description: "Turn a conversation into a spec"
+policy:
+  allow_implicit_invocation: false

.agents/skills/to-tickets/SKILL.md

@@ -0,0 +1,107 @@
+---
+name: to-tickets
+description: Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.
+disable-model-invocation: true
+---
+
+# To Tickets
+
+Break a plan, spec, or conversation into a set of **tickets** — tracer-bullet vertical slices, each declaring the tickets that **block** it.
+
+The issue tracker and triage label vocabulary should have been provided to you — run `/setup-matt-pocock-skills` if not.
+
+## Process
+
+### 1. Gather context
+
+Work from whatever is already in the conversation context. If the user passes a reference (a spec path, an issue number or URL) as an argument, fetch it and read its full body and comments.
+
+### 2. Explore the codebase (optional)
+
+If you have not already explored the codebase, do so to understand the current state of the code. Ticket titles and descriptions should use the project's domain glossary vocabulary, and respect ADRs in the area you're touching.
+
+Look for opportunities to prefactor the code to make the implementation easier. "Make the change easy, then make the easy change."
+
+### 3. Draft vertical slices
+
+Break the work into **tracer bullet** tickets.
+
+<vertical-slice-rules>
+
+- Each slice cuts a narrow but COMPLETE path through every layer (schema, API, UI, tests) — vertical, NOT a horizontal slice of one layer
+- A completed slice is demoable or verifiable on its own
+- Each slice is sized to fit in a single fresh context window
+- Any prefactoring should be done first
+
+</vertical-slice-rules>
+
+Give each ticket its **blocking edges** — the other tickets that must complete before it can start. A ticket with no blockers can start immediately.
+
+**Wide refactors are the exception to vertical slicing.** A **wide refactor** is one mechanical change — rename a column, retype a shared symbol — whose **blast radius** fans across the whole codebase, so a single edit breaks thousands of call sites at once and no vertical slice can land green. Don't force it into a tracer bullet; sequence it as **expand–contract**. First expand: add the new form beside the old so nothing breaks. Then migrate the call sites over in batches sized by blast radius (per package, per directory), each batch its own ticket blocked by the expand, keeping CI green batch to batch because the old form still exists. Finally contract: delete the old form once no caller remains, in a ticket blocked by every migrate batch. When even the batches can't stay green alone, keep the sequence but let them share an integration branch that all block a final integrate-and-verify ticket — green is promised only there.
+
+### 4. Quiz the user
+
+Present the proposed breakdown as a numbered list. For each ticket, show:
+
+- **Title**: short descriptive name
+- **Blocked by**: which other tickets (if any) must complete first
+- **What it delivers**: the end-to-end behaviour this ticket makes work
+
+Ask the user:
+
+- Does the granularity feel right? (too coarse / too fine)
+- Are the blocking edges correct — does each ticket only depend on tickets that genuinely gate it?
+- Should any tickets be merged or split further?
+
+Iterate until the user approves the breakdown.
+
+### 5. Publish the tickets to the configured tracker
+
+Publish the approved tickets. **How** depends on the tracker `/setup-matt-pocock-skills` configured — the tickets are the same either way, only the shape of the blocking edges changes:
+
+- **Local files** → write one file per ticket under `.scratch/<feature-slug>/issues/<NN>-<slug>.md`, numbered from `01` in dependency order (blockers first). Each file's "Blocked by" lists the numbers/titles it depends on. Use the per-ticket file template below — one ticket per file, never a single combined file.
+- **A real issue tracker (GitHub, Linear, …)** → publish one issue per ticket in dependency order (blockers first) so each ticket's blocking edges can reference real identifiers. Use the platform's native blocking / sub-issue relationship where it has one; otherwise set each ticket's "Blocked by" to the blocking issues. Apply the `ready-for-agent` triage label unless instructed otherwise — the tickets are agent-grabbable by construction.
+
+Work the **frontier**: any ticket whose blockers are all done. For a purely linear chain that means top to bottom.
+
+Do NOT close or modify any parent issue.
+
+<local-ticket-template>
+
+# <NN> — <Ticket title>
+
+**What to build:** the end-to-end behaviour this ticket makes work, from the user's perspective — not a layer-by-layer implementation list.
+
+**Blocked by:** the numbers/titles of the tickets that gate this one, or "None — can start immediately".
+
+**Status:** ready-for-agent
+
+- [ ] Acceptance criterion 1
+- [ ] Acceptance criterion 2
+
+</local-ticket-template>
+
+<issue-template>
+
+## Parent
+
+A reference to the parent issue on the tracker (if the source was an existing issue, otherwise omit this section).
+
+## What to build
+
+The end-to-end behaviour this ticket makes work, from the user's perspective — not layer-by-layer implementation.
+
+## Acceptance criteria
+
+- [ ] Criterion 1
+- [ ] Criterion 2
+
+## Blocked by
+
+- A reference to each blocking ticket, or "None — can start immediately".
+
+</issue-template>
+
+In either form, avoid specific file paths or code snippets — they go stale fast. Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits.
+
+Work the frontier one ticket at a time with `/implement`, clearing context between tickets.

.agents/skills/to-tickets/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "To Tickets"
+  short_description: "Split a plan into tracer-bullet tickets"
+policy:
+  allow_implicit_invocation: false

.agents/skills/wayfinder/SKILL.md

@@ -1,9 +1,16 @@
 ---
 name: wayfinder
-description: Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets on your issue tracker, and resolve them one at a time until the way to the goal is clear.
+description: Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
+disable-model-invocation: true
 ---
 
-A loose idea has arrived — too big for one agent session, and wrapped in fog: the route from here to a plan isn't visible yet. This skill charts it as a **shared map** on the repo's issue tracker, then works its tickets one at a time. The map is domain-agnostic — engineering work, course content, whatever fits the shape.
+A loose idea has arrived — too big for one agent session, and wrapped in fog: the way from here to the **destination** isn't visible yet. Wayfinding is about finding that way, not charging at the destination. This skill charts the way as a **shared map** on the repo's issue tracker, then works its **decision tickets** — questions whose resolution is a decision, not slices of a build to execute — one at a time until the route is clear.
+
+The destination varies per effort, and naming it is the first act of charting — it shapes every ticket. It might be a spec to hand off and iterate on, a decision to lock before planning starts, or a change made in place like a data-structure migration. The map is domain-agnostic — engineering work, course content, whatever fits the shape.
+
+## Plan, don't do
+
+Wayfinder is **planning** by default: each ticket resolves a decision, and the map is done when the way is clear — nothing left to decide before someone goes and does the thing. The pull to just do the work is usually the signal you've reached the edge of the map and it's time to hand off. An effort can override this in its **Notes** — carrying execution into the map itself — but absent that, produce decisions, not deliverables.
 
 ## Refer by name
 
@@ -15,13 +22,17 @@ The map is a single issue on this repo's issue tracker, labelled `wayfinder:map`
 
 The map is an **index**, not a store. It lists the decisions made and points at the tickets that hold their detail; a decision lives in exactly one place — its ticket — so the map never restates it, only gists it and links.
 
-**Where the map, its child tickets, blocking, and frontier queries physically live is tracker-specific.** Consult `docs/agents/issue-tracker.md` (the "Wayfinding operations" section) for how _this_ repo expresses them. If that doc is absent, default to the local-markdown tracker.
+**Where the map, its child tickets, blocking, and frontier queries physically live is tracker-specific.** The issue tracker should have been provided to you — run `/setup-matt-pocock-skills` if not. Consult the tracker doc's "Wayfinding operations" section for how _this_ repo expresses them. If no tracker has been provided, default to the local-markdown tracker.
 
 ### The map body
 
 The whole map at low resolution, loaded once per session. Open tickets are **not** listed — they are open child issues, found by query.
 
 ```markdown
+## Destination
+
+<what reaching the end of this map looks like — the spec, decision, or change this effort is finding its way to. One or two lines; every session orients to it before choosing a ticket.>
+
 ## Notes
 
 <domain; skills every session should consult; standing preferences for this effort>
@@ -32,9 +43,13 @@ The whole map at low resolution, loaded once per session. Open tickets are **not
 
 - [<closed ticket title>](link) — <one-line gist of the answer>
 
-## Fog
+## Not yet specified
 
-<!-- see "Fog of war" for what belongs here -->
+<!-- see "Fog of war": in-scope fog you can't ticket yet; graduates as the frontier advances -->
+
+## Out of scope
+
+<!-- see "Out of scope": work ruled beyond the destination; closed, never graduates -->
 ```
 
 ### Tickets
@@ -57,36 +72,48 @@ The answer isn't part of the body — it's recorded on resolution (see [Work thr
 
 ## Ticket Types
 
-- **Research**: Reading documentation, third-party APIs, or local resources like knowledge bases. Creates a markdown summary as a linked asset. Use when knowledge outside the current working directory is required.
-- **Prototype**: Raise the fidelity of the discussion by making a cheap, rough, concrete artifact to react to — an outline, a rough take, a stub, or UI/logic code via the /prototype skill. Links the prototype as an asset. Use when "how should it look" or "how should it behave" is the key question.
-- **Grilling**: Conversation with the agent. Uses the /grilling and /domain-modeling skills. Asks one question at a time. The default case.
-- **Task**: Literal manual work that must be done before the discussion can move forward — nothing to decide, prototype, or research. Moving data, signing up for a service, provisioning access. The agent automates it where it can; otherwise it hands the human a precise checklist. Resolved when the work is done; the answer records what was done and any resulting facts (credentials location, new URLs, row counts) later tickets depend on.
+Every ticket is either **HITL** — human in the loop, worked *with* a human who speaks for themselves — or **AFK**, driven by the agent alone. A HITL ticket only resolves through that live exchange; the agent never stands in for the human's side of it (a grilling agent that answers its own questions has broken this).
+
+- **Research** (AFK): Reading documentation, third-party APIs, or local resources like knowledge bases to surface a fact a decision waits on. Resolved by a `/research` **subagent**. Use when knowledge outside the current working directory is required.
+- **Prototype** (HITL): Raise the fidelity of the discussion by making a cheap, rough, concrete artifact to react to — an outline, a rough take, a stub, or UI/logic code via the /prototype skill. Links the prototype as an asset. Use when "how should it look" or "how should it behave" is the key question.
+- **Grilling** (HITL): Conversation via the /grilling and /domain-modeling skills, one question at a time. The default case.
+- **Task** (HITL or AFK): Manual work that must happen before a *decision* can be made — nothing to decide, prototype, or research, but the discussion is blocked until it's done. Signing up for a service so its API can be judged, provisioning access, moving data so its shape can be seen. This is the one type that *does* rather than decides — and it earns its place by unblocking a decision, not by delivering the destination. The agent drives it alone where it can (AFK); otherwise it hands the human a precise checklist (HITL). Resolved when the work is done; the answer records what was done and any resulting facts (credentials location, new URLs, row counts) later tickets depend on.
 
 ## Fog of war
 
-The map is _deliberately_ incomplete: don't chart what you can't yet see. Beyond the tickets lies fog — the dim view of decisions and investigations you can tell are coming but can't yet pin down, because they hang on questions still open. Resolving a ticket clears the fog ahead of it, graduating whatever's now specifiable into fresh tickets — one at a time, until the way to the goal is clear and no tickets remain.
+The map is _deliberately_ incomplete: don't chart what you can't yet see. Beyond the live tickets lies the **fog of war** — the dim view of decisions and investigations you can tell are coming but can't yet pin down, because they hang on questions still open. Resolving a ticket clears the fog ahead of it, graduating whatever's now specifiable into fresh tickets — one at a time, until the way to the destination is clear and no tickets remain.
 
-The map's **Fog** section is where that dim view is written down: the suspected question, the area to revisit later, the risk you're deferring. Write as loosely or as fully as the view allows; it doubles as a signpost for collaborators reading where the effort is headed.
+The map's **Not yet specified** section is where that dim view is written down: the suspected question, the area to revisit later. It's the undiscovered frontier _toward_ the destination — everything here is in scope, just not sharp enough to ticket. Write as loosely or as fully as the view allows; it doubles as a signpost for collaborators reading where the effort is headed.
 
 **Fog or ticket?** The test is whether you can state the question precisely now — _not_ whether you can answer it now.
 
 - **Ticket when** the question is already sharp — even if it's blocked and you can't act on it yet.
-- **Fog when** you can't yet phrase it that sharply. Don't pre-slice fog into ticket-sized pieces: it's coarser than a ticket, and one patch may graduate into several tickets, or none, once the frontier reaches it.
+- **Not yet specified when** you can't yet phrase it that sharply. Don't pre-slice the fog into ticket-sized pieces: it's coarser than a ticket, and one patch may graduate into several tickets, or none, once the frontier reaches it.
 
-Fog excludes only what's already decided (that's Decisions so far) and what's already a ticket.
+**Not yet specified** excludes what's already decided (Decisions so far), what's already a live ticket, and what's out of scope (the next section).
+
+## Out of scope
+
+Fog only ever gathers _toward_ the destination. The destination fixes the scope, so work beyond it is **out of scope** — it isn't fog, and it doesn't belong in **Not yet specified**. It gets its own **Out of scope** section on the map: work you've consciously ruled out of _this_ effort. Scope, not sharpness, lands it here.
+
+Out-of-scope work never graduates — the frontier stops at the destination — so it returns only if the destination is redrawn, and then as a fresh effort, not a resumption.
+
+Ruling something out of scope is a scoping act, not a step on the route. When a ticket that already exists turns out to sit past the destination — mis-scoped in while charting, or exposed by a resolution — **close it** (a closed ticket is unambiguously off the frontier) and leave one line in the **Out of scope** section: the gist plus why it's out of scope, linking the closed ticket. It stays out of **Decisions so far**, which records the route actually walked — a scope boundary isn't a step on it.
 
 ## Invocation
 
-Two modes. Either way, **never resolve more than one ticket per session.**
+Two modes. Either way, **never resolve more than one ticket per session** — with the exception of research tickets.
 
 ### Chart the map
 
 User invokes with a loose idea.
 
-1. Run a `/grilling` and `/domain-modeling` session to surface the open decisions.
-2. **Create the map** (label `wayfinder:map`): Notes filled in, Decisions-so-far empty, Fog sketched.
-3. **Create the tickets you can specify now** as child issues of the map — then wire blocking edges in a **second pass** (issues need ids before they can reference each other). Wiring sorts them into the frontier and the blocked; everything you can't yet specify stays in the Fog.
-4. Stop — charting the map is one session's work; do not also resolve tickets.
+1. **Name the destination.** Run a `/grilling` and `/domain-modeling` session to pin down what this map is finding its way to — the spec, decision, or change. The destination fixes the scope, so it's settled first.
+2. **Map the frontier.** Grill again, **breadth-first** this time: fan out across the whole space rather than deep on any one thread, surfacing the open decisions and the first steps takeable now. **If this surfaces no fog** — the way to the destination is already clear, the whole journey small enough for one session — you don't need a map. Stop and ask the user how they'd like to proceed.
+3. **Create the map** (label `wayfinder:map`): Destination and Notes filled in, Decisions-so-far empty, the fog sketched into **Not yet specified**.
+4. **Create the tickets you can specify now** as child issues of the map — then wire blocking edges in a **second pass** (issues need ids before they can reference each other). Wiring sorts them into the frontier and the blocked; everything you can't yet specify stays in the fog — the **Not yet specified** section.
+5. **Fire the research subagents.** For each `research` ticket you just created, spin up a `/research` subagent to resolve it in parallel, capturing its findings on a throwaway `research/<name>` branch with a context pointer from the ticket.
+6. Stop — charting is one session's work; it hand-resolves nothing.
 
 ### Work through the map
 
@@ -96,6 +123,6 @@ User invokes with a map (URL or number). A ticket is **optional** — without on
 2. Choose the ticket. If the user named one, use it. Otherwise take the first frontier ticket in order. **Claim it**: assign it to yourself before any work.
 3. Resolve it — **zoom as needed**: fetch the full body of any related or closed ticket on demand; invoke the skills the `## Notes` block names. If in doubt, use `/grilling` and `/domain-modeling`.
 4. Record the resolution: post the answer as a **resolution comment**, **close** the issue, and **append a context pointer** to the map's Decisions-so-far.
-5. Add newly-surfaced tickets (create-then-wire); graduate any fog the answer has made specifiable, clearing each graduated patch from the Fog so it lives only as its new ticket. If the decision invalidates other parts of the map, update or delete those tickets.
+5. Add newly-surfaced tickets (create-then-wire); graduate any fog the answer has made specifiable, clearing each graduated patch from **Not yet specified** so it lives only as its new ticket. If the answer reveals a ticket — this one or another — sits beyond the destination, **rule it out of scope** rather than resolving it on the route. If the decision invalidates other parts of the map, update or delete those tickets.
 
 The user may run unblocked tickets in parallel, so expect other sessions to be editing the tracker concurrently.

.agents/skills/wayfinder/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Wayfinder"
+  short_description: "Map a large effort as decision tickets"
+policy:
+  allow_implicit_invocation: false

.agents/skills/writing-great-skills/GLOSSARY.md

@@ -158,6 +158,12 @@ _Failure mode._ Ending the current step before it is genuinely done, because the
 
 _Avoid_: premature closure, the rush, rushing, shortcutting
 
+### Negation
+
+_Failure mode._ Steering by prohibition — telling the agent what _not_ to do — which drags the forbidden behaviour into context and makes it _more_ available, not less. _Don't think of an elephant_, and the elephant is all there is; _never write verbose comments_, and verbosity is the pattern the agent has just read. The negation is a weak modifier the strongly-activated concept overruns, so the ban half-reads as an instruction to do the thing. Its **leading word** is the _elephant_: whatever a prohibition names into the frame. Cure: prompt the **positive** — describe the target behaviour ("write one-line comments") so the banned one is never spoken. A prohibition earns its place only as a hard guardrail on a behaviour you cannot phrase positively; even then, pair it with the positive target so attention lands on what to do.
+
+_Avoid_: ironic rebound, don't-prompting, the pink elephant
+
 ## Pruning
 
 Keeping a skill lean — each remedy paired with the failure it cures.

.agents/skills/writing-great-skills/SKILL.md

@@ -80,3 +80,4 @@ Use these to diagnose issues the user may be having with the skill.
 - **Sediment** — stale layers that settle because adding feels safe and removing feels risky. The default fate of any skill without a pruning discipline.
 - **Sprawl** — a skill simply too long, even when every line is live and unique. Hurts readability and maintainability and wastes tokens. The cure is the ladder: disclose **reference** behind pointers, and split by **branch** or sequence so each path carries only what it needs.
 - **No-op** — a line the model already obeys by default, so you pay load to say nothing. The test: does it change behaviour versus the default? A weak leading word (_be thorough_ when the agent is already thorough-ish) is a no-op; the fix is a stronger word (_relentless_), not a different technique.
+- **Negation** — steering by prohibition backfires: _don't think of an elephant_ names the elephant and makes it more available, not less. Prompt the **positive** — state the target behaviour so the banned one is never spoken; keep a prohibition only as a hard guardrail you can't phrase positively, and even then pair it with what to do instead.

.agents/skills/writing-great-skills/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Writing Great Skills"
+  short_description: "Principles for predictable skills"
+policy:
+  allow_implicit_invocation: false

.claude/memory/MEMORY.md

@@ -2,6 +2,9 @@
 
 - [Product selling points](product-selling-points.md) — key differentiators and landing page angles for neuron-tai
 - [User profile](user-profile.md) — who Dobromir is and how to work with him
-- [Project status](project-status.md) — 35/35 stories done; alpha hardening next
-- **Alpha hardening** — `.scratch/alpha-hardening/` (22 issues, ADRs 0016–0019, [README](../.scratch/alpha-hardening/README.md), [handoff](../.scratch/alpha-hardening/handoff.md))
+- [Project status](project-status.md) — US-001…US-035 done; US-036…US-050 in docs/prd.json; alpha hardening + scratch features next
+- **Alpha hardening** — `.scratch/alpha-hardening/` (22 issues, ADRs 0016–0019, [README](../../.scratch/alpha-hardening/README.md), [handoff](../../.scratch/alpha-hardening/handoff.md))
 - [Alpha hardening navigation](alpha-hardening-navigation.md) — locked fraud/auth decisions, Bucket-1 order, handoff pointers
+- **Node capability admission** — `.scratch/node-capability-admission/` (P0 plan; [ADR-0023](../../docs/adr/0023-model-agnostic-node-capability-admission.md), [ADR-0026](../../docs/adr/0026-node-assignment-ownership-and-managed-placement.md))
+- **Distributed relay performance** — relay `/rpc` requester sockets are persistent per Route Session and Activation Seam as of 2026-07-10; `request_id` remains unique per activation while `X-Meshnet-Session` remains stable for KV state. Next low-risk priorities: persistent direct/loopback HTTP, seam byte/latency telemetry, then trace-driven zstd tuning.
+- **Distributed GGUF direction** — benchmark-gated native runtime: compare controlled Transformers/safetensors and whole-model llama.cpp lanes before expensive work; ship only for measured speed or model-fit advantage. Public parallelism is contiguous Shards in an Inference Route; concurrency comes from per-node continuous batching across isolated Route Sessions, while tensor/expert collectives stay inside optional trusted composite providers. Native data plane uses versioned Protobuf over long-lived gRPC/HTTP2 seam streams, with existing relay carrying the same opaque frames when needed. llama.cpp/GGML remains the substrate behind a project-owned standalone worker and small pinned fork; vLLM is an optional complete managed provider and concept donor, not a fork. Nakshatra, `prima.cpp`, `llama-gguf`, LiGGUF and historical GPUStack are source/test donors only. Active plan: [README](../../.scratch/distributed-gguf-runtime/README.md), [architecture](../../.scratch/distributed-gguf-runtime/architecture.md), [PRD](../../.scratch/distributed-gguf-runtime/PRD.md), [Ralph backlog](../../.scratch/distributed-gguf-runtime/prd.json). ADR: [0024](../../docs/adr/0024-distributed-gguf-runtime.md). Research: [landscape](../../docs/research/distributed-gguf-landscape.md), [GitHub follow-up](../../docs/research/distributed-gguf-github-followup.md), [vLLM](../../docs/research/vllm-distributed-gguf-assessment.md).

.claude/memory/alpha-hardening-navigation.md

@@ -20,13 +20,17 @@ Active workstream (started 2026-07-04): alpha hardening of the money/trust path.
 
 **Launch-readiness grilling (2026-07-06):** Locked launch plan — devnet dev/test run now, then **real mainnet SOL/USDT** (not devnet, not a new public token) for the first cohort: friends (API clients) + hired VPS/VPC hosts (our own test infra, not third-party volunteers — stake-free, risk-free if something breaks, not a long-term topology). Pricing: clients are the only party spending real money; nodes only accumulate off-chain credit and get paid in batches (30min dev / 24h later) — a failed distribution leaves funds parked, not lost, so mainnet-vs-devnet mixups are lower-risk than initially assumed. TAI token: do NOT issue/list now — ADR-0002 already locks listing behind $50k volume + 25 nodes/15 wallets plus an unresolved securities-review gate; only a dormant mainnet mint (cheap, ~few $ SOL) for name/branding reservation is in scope, bundled with treasury-key work, not before it. Treasury custody: bare keypair file (current runbook 02) is not acceptable for real funds — plan is **free native SPL multisig** (`spl-token create-multisig`, no protocol fee unlike Squads' 0.5 SOL), 2-of-3 signers, at least one cold/offline, others one-per-hired-VPS-provider to avoid correlated compromise (not yet built — ops task, no issue filed). Stake/slash asymmetry (registry/slash is a local Python adapter per ADR-0007, not on-chain) accepted for now since hired hosts are our own infra and friends aren't node operators — revisit before opening to real third-party node operators. A mainnet-vs-devnet boot guardrail was proposed and explicitly declined by the owner given the safe-by-default money flow above.
 
-**Two new issues from this session, both `ready-for-agent`:**
-- **21 — Honest-noise calibration corpus** (`.scratch/alpha-hardening/issues/21-honest-noise-calibration-corpus.md`) rescoped from "prod gate" to a **hard alpha-release blocker**. Confirmed by code read: `verify_activation_proofs()` (`packages/validator/meshnet_validator/audit.py:94-127`) returns bool only, no raw divergence value; fleet-dispatch exists but wrong shape (`server.py:2998-3104`, pinned routes + latency, not full-fleet + TOPLOC divergence); storage wrong shape (`registry_events` has no divergence/hardware columns). Three-part build: (1) surface raw TOPLOC distance from audit.py, (2) extend dispatch to hit every registered node with fixed prompt/seed, (3) new SQLite table keyed by node+GPU+dtype. Small-fleet exception granted (N = actual hired-VPS fleet size). Hired VPS hosts stay stake-free until this closes.
-- **23 — Dynamic HF-benchmarked pricing** (`.scratch/alpha-hardening/issues/23-dynamic-hf-pricing.md`), high priority but not a release blocker. Pricing today is 100% static (`DEFAULT_PRICE_PER_1K_TOKENS = 0.02`, `billing.py:21`; `model_presets.json` has no per-model price). Target: 80% of cheapest comparable provider on `https://huggingface.co/inference/models` (per-provider-per-model marketplace, `?search=` query param works, no confirmed JSON API — plain scrape attempted first, escalate to headless browser only if the table isn't in raw HTML). Human-verified `hf_aliases` + `hf_verified_match_note` (params/quantization) per model, not auto-discovered matching. Reuses the `_settlement_loop` daemon-thread pattern for a daily refresh; falls back silently to the static default on any failure.
+**Two new issues from this session:**
+- **21 — Honest-noise calibration corpus** — `Status: ready-for-human` (engineering done 2026-07-06; blocked on human fleet calibration run before mainnet launch).
+- **23 — Dynamic HF-benchmarked pricing** — `Status: done` (see `23-dynamic-hf-pricing_completed.md`).
 
 Both are already migrated into `.scratch/alpha-hardening/prd.json` (AH-021 updated, AH-023 added) and the README index — ready for Ralph to pick up unattended.
 
-**Ralph note:** `scripts/ralph_progress.py` tracks `docs/prd.json` (35/35 done) and does NOT see `.scratch/alpha-hardening/issues/`. No ralph loop is running and no `.ralph-tui/` state exists. `.scratch/alpha-hardening/prd.json` now has 23 stories (AH-001…AH-023); point Ralph at that file for the alpha-hardening branch. Do NOT use `ralph auto --parallel` on server.py-touching issues — 21 and 23 both touch `server.py`/`billing.py`/`audit.py`; if run in the same Ralph pass, run them serially, not in parallel (merge-conflict risk, same lesson as 03/04 previously).
+**Ralph note:** `scripts/ralph_progress.py` tracks `docs/prd.json` (US-001…US-047; base 35/35 done, friends-test arc 36–47 open/in-progress). Alpha hardening uses `.scratch/alpha-hardening/prd.json` (AH-001…AH-023). Point Ralph at the prd.json for the branch you're running.
 
 **Why:** three audits agreed the alpha blockers are unauthenticated gossip (anyone can inject billing events), the free-credit faucet, and ephemeral bans.
 **How to apply:** work test-first per issue acceptance criteria; use `.venv`; `cryptography` belongs in node deps (wallet.py imports it — causes many of the 24 "failures" in a fresh env). See [[project-status]] and [[autonomous-work-style]].
+
+## Routing telemetry resume (2026-07-07)
+
+`.scratch/alpha-hardening/issues/24-routing-telemetry-resume.md` / AH-024 captures the interrupted Claude handoff. Learned routing is already committed at `518c259`; the dirty tree contains live-progress/current-request heartbeat/dashboard telemetry. First known blocker: `packages/tracker/meshnet_tracker/server.py:1490` uses `threading.Lock | None`, which crashes import because `threading.Lock` is a factory function at runtime. Fix that before running the targeted telemetry tests. Keep `.claude/settings.local.json` uncommitted unless explicitly approved.

.claude/memory/dgr-rocm-setup.md

@@ -0,0 +1,29 @@
+# DGR ROCm and llama.cpp setup
+
+As of 2026-07-13:
+
+- Project ROCm runtime: `/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv-rocm`
+- ROCm/TheRock build: `7.13.0a20260513`, target `gfx1151`
+- `rocm-sdk-devel` is installed. Its expanded SDK lives under the venv at
+  `site-packages/_rocm_sdk_devel`.
+- The wheel's redundant packaged payload was relocated to
+  `/home/popov/.local/share/rocm-sdk/7.13.0a20260513/rocm_sdk_devel` and symlinked
+  back into the venv because installing both packaged and expanded forms filled
+  the mounted drive. Do not reinstall it blindly; the wheel expands beyond
+  20 GB.
+- HIP llama.cpp source: `/run/media/popov/d/DEV/llamacpp/llama.cpp`, commit
+  `e920c523e3b8a0163fe498af5bf90df35ff51d25` (version 9991).
+- HIP build: `/run/media/popov/d/DEV/llamacpp/llama.cpp/build-hip`
+- HIP `llama-server` SHA-256:
+  `b6bb4da687dbde86e243ba006cef05919b7b97255cd7e2371e1d451220aca139`
+- Verified device: `ROCm0: Radeon 8060S Graphics`, `gfx1151`.
+- Model artifacts remain under `/run/media/popov/DATA/llm`; none were put under
+  `/home`.
+
+DGR-001's immutable contract remains CPU-only. GPU evidence uses the distinct
+signed `gpu-diagnostic` profile because llama-server process VRAM is not yet
+measurable by the benchmark driver. The profile must capture measured
+llama-server startup evidence for `ROCm0` and the actual offloaded/total layer
+count; configured `device` and `n_gpu_layers` values alone are not evidence.
+The accepted signer fingerprint is anchored in
+`.scratch/distributed-gguf-runtime/trusted-evidence-signers.json`.

.claude/memory/project-status.md

@@ -6,7 +6,18 @@ metadata:
   type: project
 ---
 
-# Project Status (2026-07-02)
+# Project Status (2026-07-13)
+
+## Selected-node model placement (2026-07-14)
+
+- Admin Model placement now opens a node selector for load and release; the control-plane accepts optional `node_id` and targets only that registry assignment. Multi-model serving remains supported through `ADD_SHARD` and `max_loaded_shards`.
+- Total node pool resource values are rendered from `/v1/network/map`'s `node.capacity` contract. Route selection remains assignment/capability/throughput/queue based; capacity is used for placement and falls back to tracker defaults only if a node truly omits it.
+
+## Distributed inference performance (2026-07-14)
+
+`DIP-001` is done in `.scratch/distributed-inference-performance/`: the deterministic two-node Route Session stub benchmark covers direct/relay plus cached/stateless prefill and decode. Its JSON and concise summary explicitly attribute model execution, activation encode/decode, compression, connection setup, relay queueing, local HTTP forwarding, and end-to-end seam latency. `PYTHONPATH=packages/node pytest -q tests/test_route_session_benchmark.py` passed (7); the fixture assertion checks output-token identity and connection attempts.
+
+> Doc reconciliation 2026-07-13: `docs/prd.json` tracks US-001…US-050 (048 memory budget, 049 mainnet pilot, 050 Qwen demand placement). ADRs 0025–0026 added (TAI phase B/C, assignment ownership).
 
 All 35 user stories in docs/prd.json are done (35/35), including the reward-system arc US-030…US-035 completed 2026-07-02:
 
@@ -29,6 +40,14 @@ Implementation complete for alpha-scoped blockers in `.scratch/alpha-hardening/`
 
 Historical handoff note: `/mnt/c/Users/popov/Downloads/neuron-tai-alpha-handoff-2026-07-04.md` is useful for navigation and original audit context, but it predates the completed `.scratch/alpha-hardening/` planning artifacts. Treat its "missing ADR/issues/README" statements as stale; prefer `.scratch/alpha-hardening/README.md` and `.scratch/alpha-hardening/handoff.md` for current task order.
 
+## Node capability admission P0 (2026-07-09)
+
+Planning is ready at `.scratch/node-capability-admission/` with five sequential Ralph stories and ADR-0023. The design is model-agnostic: a Node must validate its selected Model Artifact/shard with a bounded real forward before Tracker routing; Qwen3.6 is only an optional development fixture. P0 adds a versioned local recipe-manifest/report contract, `meshnet-node doctor`, fail-closed startup admission, and tracker route gating. It intentionally excludes dynamic recipe/dependency installation and the future signed Node updater.
+
+## Gitea DGR sync (2026-07-17)
+
+Gitea is ahead of the local Markdown backlog with open DGR-022..DGR-071. The first executable P0 dependency frontier is DGR-022 (Shard lifecycle and structured status RPCs), DGR-023 (reproducible protobuf generation), DGR-025 (artifact/runtime recipe identity), and DGR-027 (llama.cpp provenance manifest). DGR-021, the named-tensor stream envelope prerequisite for DGR-022/023/025, is closed. DGR-022 is the next dependency-ordered issue and blocks DGR-024, DGR-033, and DGR-037.
+
 ## Windows CUDA node (working as of 2026-07-01)
 - miniforge3 base env, torch 2.7.1+cu118, torchvision 0.22.x+cu118
 - RTX 4060 Laptop GPU, 8 GB VRAM, benchmark index ~11,200
@@ -42,7 +61,8 @@ Historical handoff note: `/mnt/c/Users/popov/Downloads/neuron-tai-alpha-handoff-
 - Verification: downloader/startup targeted subset passes (`pytest tests/test_node_startup.py -k "download_shard or same_shard"`). Full `tests/test_node_startup.py` has 46 passed and 4 unrelated Windows chmod/path separator failures.
 - Live Windows confirmation: `meshnet-node start --tracker http://192.168.0.179:8080 --model Qwen3.6-35B-A3B` reuses `F:\_STORAGE\models\qwen3.6-35b-a3b`, prints `Cached at`, registers, and reaches ready as node `5gMLrmyB-26b1f8a4204a`.
 - Follow-up fix: preset-model startup now starts the heartbeat thread after registration; without this, the node appeared briefly on the dashboard and was purged on first inference/route after heartbeat expiry. Tracker dashboard now has a "Console output" panel backed by `/v1/console` for node register/expiry, routing failures, and proxy events.
-- Qwen3.6-35B-A3B reserve-based split is expected: an 79 GB CPU node may be assigned layers 0-36, and a second node fills 37-39. Do not "fix" this by bypassing the 20% assignment reserve unless the shard-planning policy changes.
+- Qwen3.6-35B-A3B CPU runtime cap (2026-07-08): the old reserve-based split could assign an 79 GB CPU node layers 0-36, but real partial loading can exceed that budget and die without a Python traceback. Node startup now clips oversized CPU auto-assignments before loading, and tracker CPU assignment uses a stricter runtime headroom factor; do not revert this to the old 20% reserve-only policy.
 - Route hardening: tracker chat proxy and `/v1/route` diagnostics now use alias-aware preset node matching for split Qwen3.6 routes; dashboard derives grouped inference history from proxy route/complete console events and shows observed TPS after completion.
 - Live proxy hardening: model lookup trims outer whitespace before alias matching (`qwen3.6-35b-a3b ` resolves), and tracker route logs/dashboard queue depth combine heartbeat queue with tracker-local proxy in-flight counts so Postman-style bursts no longer show every selected route as queue `0`.
 - Split-shard streaming hardening: Qwen3.6-style distributed generation now emits SSE chunks token-by-token from the head node instead of buffering all generated text until completion. Tracker direct/relay stream proxy logs `proxy progress` with live tokens/TPS, dashboard Inference history shows currently processing requests with live TPS/tokens/queue, and relay stream completion no longer references an undefined `session_id`.
+- Native Windows Qwen3.6-MoE import fix: `flash-linear-attention` imports `triton`; without `triton-windows`, startup fails with misleading `Could not import module 'Qwen3_5MoeForCausalLM'`. Installed `triton-windows` in `C:\Users\popov\miniforge3` and added it as a Windows-only node dependency.

.codex/hooks.json

@@ -0,0 +1,15 @@
+{
+  "hooks": {
+    "PostToolUse": [
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash -c 'SRC=\"/mnt/d/DEV/workspace/REPOS/git.d-popov.com/neuron-tai/.claude/memory\" && DST=\"/home/dev/.claude/projects/-mnt-d-DEV-workspace-REPOS-git-d-popov-com-neuron-tai/memory\" && mkdir -p \"$DST\" && rsync -a \"$SRC/\" \"$DST/\" 2>/dev/null; true'"
+          }
+        ]
+      }
+    ]
+  }
+}

.gitattributes

@@ -0,0 +1,28 @@
+# Normalize line endings across Windows/Linux checkouts.
+# All text files are stored as LF in the repo and checked out as LF
+# on every OS. Git auto-detects text vs binary.
+* text=auto eol=lf
+
+# Explicitly binary — never touch these bytes.
+*.png binary
+*.jpg binary
+*.jpeg binary
+*.gif binary
+*.ico binary
+*.pdf binary
+*.zip binary
+*.gz binary
+*.tar binary
+*.wasm binary
+*.sqlite binary
+*.sqlite3 binary
+*.safetensors binary
+*.gguf binary
+
+# Scripts that must stay LF even if someone forces CRLF locally.
+*.sh text eol=lf
+*.py text eol=lf
+
+# Windows batch files genuinely need CRLF.
+*.bat text eol=crlf
+*.cmd text eol=crlf

.gitignore

@@ -10,7 +10,9 @@ dist/
 .venv/
 
 # Ralph local runtime state
-.ralph-tui/
+.ralph-tui/*
+!.ralph-tui/config.toml
+.ralph-lane/
 
 
 .env
@@ -18,5 +20,13 @@ dist/
 !.env.example
 !.env.testnet
 .rocm-local/*
-billing.sqlite
-.pytest-tmp/*
+.pytest-tmp/*
+.cache/
+
+# Local tracker/node sqlite databases (never commit runtime state)
+*.sqlite
+*.sqlite3
+logs/tracker/error.log
+logs/tracker/info.log
+logs/tracker/warning.log
+.venv*

.ralph-supervisor.log

@@ -0,0 +1,5 @@
+[2026-07-23 10:24:53] supervisor started, tailer pid=1460238
+[2026-07-23 10:24:53] cycle 1: running ralph-tui resume (log starts at line 978)
+[2026-07-23 10:25:59] ralph-tui exited without a recognized stop reason; retrying resume in 5 min
+[2026-07-23 10:33:51] supervisor started, tailer pid=1465293
+[2026-07-23 10:33:51] cycle 1: running ralph-tui run (log starts at line 1150)

.ralph-tui/config.toml

@@ -0,0 +1,2 @@
+autoCommit = true
+configVersion = "2.1"

.scratch/distributed-gguf-runtime/ADR-0020-distributed-gguf-runtime.md

@@ -1,177 +0,0 @@
-# ADR-0020: Distributed GGUF/llama.cpp Runtime With Per-Shard Local KV
-
-Status: Proposed
-
-## Context
-
-The project currently uses PyTorch/Transformers for real model shards. That decision was captured in ADR-0001 because llama.cpp RPC at the time required the primary node to load the full model and distribute weights to workers, which conflicted with the desired model where nodes independently hold shards.
-
-We now want to serve very large open models, including GLM-5.2 and Ornith-class MoE models, over a torrent-like inference marketplace. CPU and mixed consumer hardware matter. LM Studio and llama.cpp demonstrate much better CPU/GGUF performance than our current PyTorch CPU path. The user also has a personal relationship with Georgi Gerganov, making upstream collaboration plausible.
-
-The current distributed PyTorch path is not yet production-grade: it recomputes the full growing sequence for every output token and disables KV cache inside manual layer calls. It sends hidden activations across seams, not KV, but those activations currently cover the full sequence every decode step.
-
-## Decision
-
-Adopt a distributed GGUF/llama.cpp runtime track while keeping PyTorch as the reference and fast-architecture backend.
-
-The runtime model is:
-
-- GGUF/model artifacts are distributed through torrent/content-addressed storage.
-- Nodes independently acquire and verify artifacts; no root node streams model weights to workers at session start.
-- Tracker chooses a sticky route covering all layers.
-- Each node owns hot KV/state for the layers it executes.
-- Prefill sends chunked activations through the route and builds local per-shard KV.
-- Decode sends one-step activations through the route and appends local KV at every shard.
-- Cache/CDN servers store cold artifacts and optional prefix/session snapshots, not hot per-token KV.
-- Context is capped at 128K for the first serious product path.
-
-## Technical Framework
-
-The design separates five planes:
-
-- **Control plane**: tracker registry, coverage map, route selection, session lifecycle, telemetry, billing, and audit.
-- **Artifact plane**: Shard Swarms, GGUF/safetensors/tokenizer files, manifests, hashes, and local node storage.
-- **Execution plane**: active Inference Route, chunked prefill, one-step decode, and hidden-state movement across activation seams.
-- **Session state plane**: per-shard Hot KV State on route nodes, plus optional Prefix Snapshots outside the hot loop.
-- **Economics/trust plane**: reward accounting, validation events, slash proofs, public/private route policy.
-
-Hard invariants:
-
-1. Public-network Shards are contiguous layer ranges.
-2. Hot KV State is local to the node serving that Shard in that Route Session.
-3. Artifact distribution and route execution are separate systems.
-4. Decode seam payload must be `O(hidden_size)`.
-5. Prefill may be `O(sequence_length * hidden_size)`, but only in bounded chunks.
-6. The tracker chooses routes; nodes do not negotiate route topology peer-to-peer.
-7. Model/backend-specific cache internals stay behind backend capability reports.
-8. PyTorch remains the correctness/reference backend while llama.cpp/GGUF becomes the performance backend.
-9. Streaming responses are preferred when feasible; Generation Telemetry is always required.
-
-The full challenge register is in [technical-challenges.md](./technical-challenges.md). The open decision gates are in [decision-framework.md](./decision-framework.md).
-
-Resolved gate:
-
-- Public-network Shards are layer ranges. Tensor-parallel/ring execution belongs inside a trusted node, colocated pod, or future composite node abstraction, not as the v1 public routing primitive.
-- Hot KV State is local to each route node for the Shard it serves. Cache servers may store Prefix Snapshots, but they are not part of the per-token decode path.
-- Distributed Route Session and Hot KV State semantics will be proven in the PyTorch route before llama.cpp/GGUF is extended for layer-boundary execution.
-- Streaming responses are preferred when feasible. Realtime Generation Telemetry is required so clients can see phase, generated token count, and tokens/sec even during prefill or non-streaming fallback paths.
-- llama.cpp/GGUF work targets upstreamable `libllama`/ggml hooks. A prototype fork is acceptable for exploration, but a permanent fork is not the plan.
-- Model targeting is two-tiered: use a small llama.cpp-supported GGUF model for the first protocol smoke test, then use `deepseek-ai/DeepSeek-V4-Flash` as the first serious large-model target. GLM-5.2 and Ornith remain later support audits.
-- Alpha fails Route Sessions on route-node loss instead of attempting automatic route repair. Repair requires compatible Prefix Snapshots and is a later capability.
-- v1 activation transfer stays on binary HTTP as defined by ADR-0008. QUIC/WebRTC/custom transport can be introduced later behind the same activation protocol.
-
-## Non-Goals
-
-- Do not put remote cache servers in the per-token hot KV path.
-- Do not require every node to hold the full model.
-- Do not fork llama.cpp long-term if upstream APIs can support the needed layer-boundary hooks.
-- Do not target GLM-5.2 or Ornith first; prove the route/KV protocol on a simpler well-supported GGUF model, then target DeepSeek-V4-Flash as the first serious large model.
-
-## Options Considered
-
-### A. Keep PyTorch-only distributed inference
-
-Pros:
-
-- Easy access to new Hugging Face architectures.
-- Transformers has mature single-process KV semantics.
-- Existing code already loads shards.
-
-Cons:
-
-- CPU inference is much slower than llama.cpp/GGUF.
-- Current distributed path bypasses `generate()` and disables cache.
-- Quantized GGUF ecosystem and LM Studio users are outside the runtime.
-
-### B. Use llama.cpp only as a full local model backend
-
-Pros:
-
-- Quick performance win for nodes with enough RAM/VRAM.
-- Minimal coordination with distributed protocol.
-
-Cons:
-
-- Does not unlock 397B/753B-class models for ordinary nodes.
-- Does not solve marketplace layer routing.
-
-### C. Distributed GGUF with per-shard local KV (chosen)
-
-Pros:
-
-- Aligns with torrent artifact distribution.
-- Avoids root streaming weights to workers.
-- Uses llama.cpp/GGUF performance where supported.
-- Compatible with public node rewards by layer/work contribution.
-- Scales KV memory by layer range.
-
-Cons:
-
-- Requires new runtime APIs around layer-boundary hidden states and per-session KV.
-- Requires model-specific cache metadata for DSA/MLA/hybrid attention.
-- Harder to debug than single-process `generate()`.
-
-### D. Centralized KV cache servers
-
-Pros:
-
-- Easier apparent session failover.
-- Central accounting of active cache.
-
-Cons:
-
-- Puts remote storage in the per-token hot path.
-- Adds bandwidth and latency at the worst possible point.
-- Creates consistency and privacy problems.
-
-Rejected for hot decode. Accepted only for cold prefix snapshots and failover checkpoints.
-
-## Consequences
-
-- ADR-0001 should eventually be amended: PyTorch remains valid, but llama.cpp/GGUF becomes a first-class backend.
-- The activation protocol must split prefill and decode explicitly.
-- Session IDs must be stable across the full request. The current fresh UUID-per-hop-call behavior must change.
-- Backends must report cache budget and cache compatibility.
-- Tracker route selection must include disk, memory pressure, cache warmth, and network latency.
-- Billing can be based on layer work, prefill tokens, decode tokens, and observed route participation.
-- Client UX should stream token deltas when feasible and must include route-session progress telemetry even when token deltas are not streamed.
-
-## Required Runtime Capabilities
-
-PyTorch path:
-
-- manual layer calls with `past_key_values` / model-specific cache object
-- per-shard session cache store
-- prefill chunk append
-- decode step append
-- stable session lifecycle endpoints
-
-llama.cpp/GGUF path:
-
-- full local GGUF serving
-- layer/tensor map extraction from GGUF
-- optional partial layer loading or mmap-backed selected execution
-- inbound hidden-state execution from arbitrary start layer
-- outbound hidden-state return at stop layer
-- per-session KV ownership for loaded layers
-- cache budget/compatibility introspection
-- GLM-5.2 DSA support when upstream/runtime supports it
-
-## Implementation Plan
-
-1. Add full-model `LlamaCppBackend` using `llama-server` or `libllama`.
-2. Implement distributed KV in the PyTorch path to prove semantics.
-3. Add session lifecycle and prefill/decode wire protocol.
-4. Add model artifact manifest and torrent seeding metadata.
-5. Prototype localhost two-process llama.cpp layer boundary execution.
-6. Generalize to network route.
-7. Bring in GLM-5.2/Ornith once backend support and cache accounting are verified.
-
-## Acceptance Criteria
-
-- A two-node localhost route can prefill once and decode N tokens without recomputing the full prompt.
-- Seam payload during decode is `O(hidden_size)`, not `O(sequence_length * hidden_size)`.
-- Per-node KV memory grows with owned layer count and context length.
-- Route loss during alpha fails cleanly with explicit reason.
-- Full local GGUF backend outperforms PyTorch CPU on a supported model.
-- Artifact manifest can identify exactly which files/chunks a node must seed for its advertised layer range.

.scratch/distributed-gguf-runtime/GLM-5.2-MAX-ALPHA-ROADMAP.md

@@ -0,0 +1,384 @@
+# GLM-5.2 Max distributed alpha roadmap
+
+Status: proposed executable epic target
+Last updated: 2026-07-13
+
+## Executive decision
+
+The alpha-release target is the exact open-weight model `zai-org/GLM-5.2` served with `reasoning_effort=max` from the smallest published Unsloth GGUF recipe, `UD-IQ1_S`, across multiple consumer machines.
+
+“Max” is a reasoning mode selected by the chat template/API request. It is not a separate model checkpoint.
+
+Alpha is earned only when the real target model:
+
+1. cannot fit within any one participating node's admitted memory;
+2. loads as contiguous layer Shards on at least two physical consumer machines;
+3. performs real GLM-5.2 MoE + DSA + IndexShare computation on every selected node;
+4. responds through the existing OpenAI-compatible Meshnet API with `reasoning_effort=max`;
+5. passes locked parity, usefulness, performance, telemetry, cancellation, and cleanup checks; and
+6. stores all model artifacts on configured mounted-drive storage, never under `/home`.
+
+The shortest safe path is not “support every GGUF architecture.” Dense Llama remains a small structural fixture. GLM-5.2 moves onto the critical path immediately after exact recipe identity and the pinned llama.cpp boundary. Qwen expansion, 1M context certification, MTP/speculative decoding, broad concurrency, and automatic route repair are post-alpha.
+
+## 1. Exact target contract
+
+### 1.1 Source model
+
+| Field | Locked target |
+|---|---|
+| Official repository | `zai-org/GLM-5.2` |
+| Official revision observed 2026-07-13 | `b4734de4facf877f85769a911abafc5283eab3d9` |
+| Model-weight license | MIT |
+| Official code/documentation license | Apache-2.0 |
+| Architecture | `glm_moe_dsa` / `GlmMoeDsaForCausalLM` |
+| Official architecture label | 744B total / approximately 40B active per token |
+| Exact stored checkpoint tensors | 753,329,940,480 parameters |
+| Transformer layers | 78 backbone layers plus one shared NextN/MTP layer in the artifact |
+| Layer types | first 3 dense; remaining 75 sparse MoE |
+| Routed experts | 256 |
+| Experts selected | 8 routed experts plus shared expert path |
+| Hidden width | 6,144 |
+| Attention | MLA under DSA, lightning indexer top-k 2,048 |
+| IndexShare | indexer roles are encoded by `indexer_types`; consumers reuse prior Full-layer indices |
+| Architectural maximum context | 1,048,576 tokens |
+| Alpha reasoning mode | `reasoning_effort=max` |
+
+The runtime must derive these values from the pinned artifact and fail closed on contradictory metadata. Marketing names are not compatibility identity.
+
+### 1.2 Alpha GGUF artifact
+
+| Field | Locked target |
+|---|---|
+| GGUF repository | `unsloth/GLM-5.2-GGUF` |
+| GGUF revision observed 2026-07-13 | `abc55e72527792c6e77069c99b4cb7de16fa9f23` |
+| Quantization | `UD-IQ1_S` |
+| Files | six GGUF shards |
+| Exact published bytes | 216,715,360,960 bytes |
+| Binary GiB | 201.832 GiB |
+| Published quality indication | about 76.2% top-1 agreement with the high-precision reference on Unsloth's quantization analysis |
+| Mounted storage rule | configured mounted drive only; never `/home` |
+
+Before downloading 216.7 GB, DGR-017 must generate a checked-in target manifest containing repository revisions, expected filenames, byte sizes, and resolved LFS SHA-256 values. Download is resumable and verified before route admission.
+
+`UD-IQ1_M` (228,492,966,624 bytes / 212.801 GiB) is the first diagnostic fallback if `UD-IQ1_S` exposes a runtime or quality defect. It does not satisfy the explicit “lowest quantization” alpha target unless the target contract is changed by human review.
+
+### 1.3 Runtime semantics required for alpha
+
+Required:
+
+- GGUF parsing and quantized kernels from one exact llama.cpp pin.
+- Correct GLM-5.2 MoE routing, selected experts, and shared expert.
+- Correct compressed MLA KV cache for locally owned layers.
+- Native DSA lightning indexer and sparse attention.
+- Correct IndexShare Full/Shared role execution from artifact metadata.
+- Range-owned contiguous transformer layers; each owned layer keeps all of its experts local.
+- Head-only embeddings and tail-only final norm/output head/sampling.
+- Architecture-defined activation boundary and optional DSA index sideband.
+- `reasoning_effort=max` chat-template behavior through the public API.
+- F32 seam correctness lane and a separately certified production activation dtype.
+
+Not required for alpha:
+
+- MTP/speculative decoding. The trailing NextN tensors may be loaded or explicitly excluded according to a certified recipe, but cannot be silently misinterpreted.
+- Full 1,048,576-token context.
+- Continuous batching beyond one target session.
+- Public-WAN tensor or expert parallel collectives.
+- Automatic mid-generation repair or KV migration.
+- Every CPU/GPU backend combination.
+
+## 2. Minimum resource envelope
+
+### 2.1 Weight and runtime memory
+
+The smallest artifact occupies 201.832 GiB before KV, DSA indexer state, scratch buffers, backend workspaces, process memory, and the operating system. **224 GiB aggregate runtime-accessible memory is only the experimental hard-fit floor**, consistent with Unsloth's approximate 223 GB one-bit requirement. It is not a conservative operational envelope.
+
+For admission, each node reserves:
+
+```text
+max(20% of physically usable memory, 8 GiB)
+```
+
+The remainder is the combined weight-plus-KV placement budget. Actual peak scratch is measured by backend/context and can force one extra node. Unified memory is counted once: integrated-GPU “VRAM” must not be added again to the same physical system RAM.
+
+| Physical usable tier | Minimum reserve | Weight + KV placement budget | IQ1_S 16K arithmetic minimum | Operational position |
+|---:|---:|---:|---:|---|
+| 32 GiB | 8.0 GiB | 24.0 GiB | 9 nodes | use 10 if attempted; latency-heavy |
+| 48 GiB | 9.6 GiB | 38.4 GiB | 6 nodes | possible; latency-heavy |
+| 64 GiB | 12.8 GiB | 51.2 GiB | 4 nodes | hard minimum; **5 recommended** |
+| 96 GiB | 19.2 GiB | 76.8 GiB | 3 nodes | recommended |
+| 128 GiB unified/system | 25.6 GiB | 102.4 GiB | 2 nodes | arithmetic hard minimum; **3 recommended** |
+
+The planner must use exact tensor byte ownership, not equal percentages. Embeddings, final head, dense versus MoE layers, shared experts, indexer tensors, quant block alignment, KV distribution, and backend workspace make equal layer counts unequal in memory.
+
+Recommended first target route: **three 96/128-GiB-class physical machines** or **five 64-GiB-class machines**, on the same wired switch with mounted model storage. Four 64-GiB or two 128-GiB machines are fit probes only and qualify solely if exact placement and measured peak-memory evidence retain the required reserve with no swap/overcommit.
+
+### 2.2 KV cache
+
+GLM-5.2 MLA caches 576 latent/rope values per token per backbone layer. Correct DSA also caches 128-dimensional indexer keys: ideally only for the 21 Full indexer layers, while the current experimental implementation may allocate them across all 78 layers. Alpha locks **Q8_0 KV** for quality and budgets the conservative current-implementation layout.
+
+| Context × concurrency | MLA-only Q8 | Optimized DSA Q8 | Conservative current-DSA Q8 | Conservative current-DSA F16 |
+|---:|---:|---:|---:|---:|
+| 16,384 × 1 | 0.73 GiB | 0.77 GiB | **0.89 GiB** | 1.68 GiB |
+| 131,072 × 1 | 5.83 GiB | 6.18 GiB | **7.12 GiB** | 13.41 GiB |
+| 1,048,576 × 1 | 46.62 GiB | 49.41 GiB | **56.98 GiB** | 107.25 GiB |
+
+These are planning estimates, not admission truth. The runtime must report measured allocated/resident MLA and indexer cache by Shard. Alpha configures a 16,384-token window, Q8_0 KV, and one session. Longer contexts and lower-bit KV are separate quality/resource certification gates.
+
+### 2.3 Activation seams and network
+
+A BF16 hidden-state boundary is 6,144 elements = 12,288 bytes/token before framing.
+
+- A 16,384-token prefill sends about 192 MiB per seam.
+- One decode token sends about 12 KiB per seam.
+- A 512-token decode sends about 6 MiB per seam.
+- Four nodes imply three serial seams.
+
+If a Shard boundary splits an IndexShare producer/consumer group, a 2,048-entry int32 top-k sideband can add up to 8 KiB/query before framing. The route planner should prefer boundaries that preserve complete IndexShare ownership groups. The protocol must still support and validate the named sideband because memory fit may force an internal group split.
+
+Decode bandwidth is small, but every generated token crosses all seams serially, so node count and per-hop latency dominate. Alpha requires a same-switch wired route: **2.5 GbE minimum and 10 GbE recommended**, with measured one-way/RTT, serialization, and queue latency. A 1 GbE route may be retained as fit-only evidence but is not the recommended alpha topology. Alpha records per-seam bytes, p50/p95 transfer latency, retries, and checksum failures; no speed claim is inferred from link rate alone.
+
+### 2.4 Storage
+
+The shortest alpha path allows every node to hold the complete six-file source GGUF while mapping/allocating only owned tensors. This minimizes artifact-transformation risk but costs 216.7 GB disk per node.
+
+Deterministic source-bound layer packages are a follow-up optimization. If needed before target fit, every package must retain:
+
+- source repository/revision and source file hashes;
+- exact owned tensor names, layer range, and endpoint role;
+- tokenizer/config identity;
+- deterministic package hash; and
+- proof that composing all packages matches the source tensor inventory.
+
+## 3. Current state and critical gaps
+
+### Completed foundation
+
+- DGR-001: immutable CPU contract plus separate signed ROCm diagnostic. CPU v1 remains `stop`; the GPU diagnostic establishes a viable fit/performance investigation lane but does not rewrite CPU evidence.
+- DGR-002: versioned backend-neutral gRPC/Protobuf Shard protocol with bounded fragments and compatibility checks.
+- Existing Meshnet: Tracker, contiguous Shards, Route Sessions/epochs, relay/direct transport, local Hot KV semantics in the reference backend, cancellation, telemetry, billing, and model-agnostic admission.
+
+### Missing before target alpha
+
+1. Exact GLM target/artifact manifest and memory-fit planner.
+2. A current llama.cpp pin proven to load and generate with the exact `UD-IQ1_S` artifact.
+3. A narrow decision on native GLM-5.2 DSA/IndexShare support. As observed 2026-07-13, merged llama.cpp PR #24770 loads GLM-5.2 through a dense-MLA compatibility path, while full IndexShare/DSA PR #25407 remains open and its generic sparse path can be slower than dense fallback. Generic CPU lightning-indexer support is merged; backend coverage remains uneven.
+4. A decode protocol amendment. `ActivationChunk` carries `TensorBundle`, but the current `DecodeStep` fast path carries only one `NamedTensor`; it cannot transport a hidden state plus GLM top-k sideband. Tail token/logit and sampling behavior also needs an explicit typed result contract.
+5. Correct range-owned GGUF loading and memory proof.
+6. GLM-specific boundary/KV/IndexShare semantics.
+7. Standalone native worker and Meshnet integration.
+8. Real target hardware route with no node individually able to admit the whole model.
+9. Locked target parity, usefulness, speed, failure, and cleanup evidence.
+
+### Donor policy
+
+`Mesh-LLM/mesh-llm` is a high-value test and patch donor. Its live GLM branch was observed with 261 llama.cpp patches, 167 named for GLM/DSA/MTP-related work. That is evidence of the problem's depth, not an acceptable maintained fork boundary.
+
+Audit and selectively reproduce the smallest independently understood pieces for:
+
+- GLM DSA graph semantics;
+- lightning indexer and sparse-attention tests;
+- IndexShare metadata/Full/Shared validation;
+- top-k sideband shape and lifecycle;
+- stage-local KV filtering; and
+- target parity/performance fixtures.
+
+Do not import Mesh-LLM routing, discovery, scheduler, public mesh, package manager, or full patch stack. Keep Meshnet as the sole control plane and collaborate narrowly upstream with llama.cpp/Mesh-LLM maintainers where practical.
+
+## 4. Revised roadmap
+
+## Phase 0 — lock the target before implementation
+
+### DGR-017: lock GLM-5.2 Max target and alpha contract
+
+Deliver:
+
+- machine-readable target manifest for official and GGUF revisions;
+- exact `UD-IQ1_S` file/size/hash inventory;
+- architecture/config/chat-template snapshot;
+- memory/KV/network planner with unified-memory de-duplication;
+- immutable alpha acceptance thresholds from section 5; and
+- current upstream/donor status report.
+
+Exit: target identity and alpha requirements are reviewable without downloading the model.
+
+## Phase 1 — establish a correct whole-model oracle
+
+### DGR-003: exact runtime recipe identity
+
+Extend the existing generic identity with GLM fields: DSA/IndexShare metadata, adapter version, reasoning template revision, activation bundle schema, KV dtype/layout, llama.cpp pin/patch hash, and target artifact manifest hash.
+
+### DGR-004: reproducible llama.cpp pin and narrow patch boundary
+
+Select a current exact upstream commit only after testing its stock GLM behavior. Add clean fetch/apply/build checks. Record every donor patch and whether it is adopted, rewritten, rejected, or waiting upstream.
+
+### DGR-018: certify whole-model GLM-5.2 runtime semantics
+
+On a 256-GiB-class reference host with at least 224 GiB runtime-accessible memory after OS reservation, or a measured equivalent:
+
+1. verify all six `UD-IQ1_S` shards;
+2. load with a stock pinned runtime and capture tensor/metadata warnings;
+3. prove whether DSA, IndexShare, shared expert, and Max template are actually active;
+4. add the minimum correctness patches/tests required;
+5. run deterministic prefill/decode and fixed Max-mode sentinel prompts; and
+6. sign the oracle recipe, output, telemetry, and limitations.
+
+Exit: one whole-model oracle exists for the same artifact/runtime semantics the distributed path will implement. “It emits text” is insufficient.
+
+## Phase 2 — build the generic local seam using small fixtures
+
+### DGR-005: range-owned GGUF tensors
+
+Keep dense Llama as a cheap structural fixture. Implement authoritative owned-tensor registration/loading, head/tail ownership, and measured resident-memory scaling. Design tensor classification so GLM adds explicit rules rather than unchecked name substitution.
+
+### DGR-006: architecture-defined boundary
+
+Implement named boundary bundles, F32 correctness lane, bounded fragmentation, and optional sidebands. Amend the decode fast path so it carries a versioned `TensorBundle` rather than one `NamedTensor`, while preserving a small one-tensor encoding. Define an explicit typed tail result for logits/token output and bind sampling/chat-template parameters to the recipe/request. Regenerate Python/C++ schema code and compatibility goldens. Dense fixture parity proves the seam mechanism, not GLM certification.
+
+Exit: two local processes can execute a small dense model with correct range ownership and boundary parity.
+
+## Phase 3 — add GLM-5.2 as the product adapter
+
+### DGR-019: implement and certify GLM-5.2 range/DSA/IndexShare semantics
+
+Deliver explicit support for:
+
+- 78 main layers and endpoint tensor ownership;
+- 256-expert MoE routing/top-8 and shared expert;
+- compressed MLA KV by owned layers;
+- DSA lightning indexer and sparse attention;
+- IndexShare metadata, Full producer, Shared consumer, and sideband behavior;
+- NextN/MTP tensor policy with MTP disabled or enabled explicitly;
+- shard-boundary planner aware of IndexShare ownership groups; and
+- whole-model versus two-stage parity against DGR-018.
+
+Exit: a same-host two-stage target run matches the locked oracle tolerance with real GLM computation in both stages. If the full target cannot fit on one host for this check, use a layer-reduced GLM architecture fixture for graph parity and defer full-artifact output parity to DGR-020; label the distinction explicitly.
+
+## Phase 4 — worker, KV, and Meshnet route
+
+Execute existing stories with GLM requirements included:
+
+1. DGR-007 — isolated local Hot KV keyed by `(Route Session, epoch)`, including DSA/IndexShare state.
+2. DGR-008 — standalone C++ gRPC worker.
+3. DGR-009 — Meshnet backend, capability, relay/direct, cancellation, and telemetry integration.
+4. DGR-010 — small-model local two-process acceptance.
+5. DGR-011 — real two-physical-machine route and heterogeneous fail-closed behavior.
+6. DGR-013 subset required by alpha — node loss, cancellation, stale epoch, restart, and memory/KV cleanup.
+
+Continuous batching (DGR-012) is deliberately not an alpha dependency. The first target release supports one admitted GLM route session; concurrency follows after target correctness and fit.
+
+## Phase 5 — target alpha gate
+
+### DGR-020: pass real distributed GLM-5.2 Max alpha acceptance
+
+Use at least two physical machines and enough aggregate usable memory to meet the locked target planner. No participating node may individually admit the complete target. All stages must report real compute and exact tensor ownership.
+
+Run the complete acceptance matrix in section 5, preserve raw logs/metrics/output, sign the evidence, and publish an explicit `alpha` or `stop` verdict. Thresholds cannot be weakened after results are known.
+
+## Phase 6 — post-alpha hardening
+
+After DGR-020 passes:
+
+1. DGR-012 — 1/2/4-session continuous batching and bounded admission.
+2. DGR-014 — final distributed GGUF versus reference-route performance decision.
+3. 32K, 128K, 200K, then 1M context certification with quantized KV.
+4. MTP/speculative decoding.
+5. Deterministic range packages to remove full-artifact replication.
+6. Additional backend compatibility classes and route topologies.
+7. DGR-016 — narrow upstream collaboration package, split by independently reviewable llama.cpp changes.
+8. DGR-015 — Qwen3/Qwen3-MoE only as later architecture expansion, not as the GLM alpha target.
+
+## 5. Locked alpha acceptance matrix
+
+These thresholds are set before target execution.
+
+### 5.1 Identity and fit
+
+- Exact official and GGUF repository revisions match the target manifest.
+- All six source GGUF sizes and LFS SHA-256 values verify.
+- Every route node reports owned tensor names/bytes, layer range, endpoint role, backend, KV recipe, and patch fingerprint.
+- Union of owned tensors equals the certified runtime-required tensor inventory; unintended overlap is zero.
+- No node's weight-plus-KV placement budget can hold the complete recipe.
+- Every node reserves at least `max(20% of physically usable memory, 8 GiB)` outside weight-plus-KV placement; measured peak scratch must remain inside that reserve.
+- Aggregate peak RSS/VRAM stays within physical budgets with no swap, overcommit, mmap-only, or double-counted unified-memory success claim.
+- Arithmetic-minimum topologies require exact contiguous tensor placement evidence; recommended alpha topology is 5×64 GiB or 3×96/128 GiB.
+- Unified RAM/VRAM is not double-counted.
+
+### 5.2 Semantic correctness
+
+- Logs and graph tests prove GLM MoE/shared-expert, DSA lightning indexer, sparse attention, and IndexShare Full/Shared paths are active; dense-attention compatibility fallback cannot satisfy alpha.
+- `reasoning_effort=max` is observable in the rendered template/API recipe.
+- F32 same-backend seam fixture: 32 greedy decode tokens exactly match the whole-model oracle and activation tolerance is locked by DGR-006.
+- Production seam on the fixed prompt corpus: greedy token agreement is at least 0.90 and mean compared-state/logit cosine similarity is at least 0.999 versus DGR-018, with no malformed or non-finite tensors.
+- Incompatible artifact, tokenizer, adapter, DSA metadata, boundary, activation, KV, backend class, or runtime patch fingerprints fail closed.
+
+### 5.3 End-to-end target run
+
+- Context configured to 16,384 tokens with Q8_0 MLA/indexer KV.
+- Fixed 4,096-token prompt lane completes prefill.
+- Route uses a same-switch wired network; 2.5 GbE is the alpha minimum and 10 GbE is recommended.
+- One Max-mode request generates at least 512 output tokens or reaches a valid natural EOS after at least 128 tokens.
+- Fixed coding, structured tool-call/JSON, and multi-step reasoning sentinels produce parseable, relevant outputs; raw prompts and outputs are retained for review.
+- OpenAI-compatible response includes stable model ID, finish reason, and token usage.
+
+### 5.4 Minimum useful performance
+
+On the declared minimum alpha topology after one warm-up:
+
+- median decode throughput is at least 0.5 generated token/s for the fixed Max-mode lane;
+- 4,096-token-prompt TTFT is at most 10 minutes;
+- no unexplained stall exceeds 60 seconds without progress telemetry;
+- per-stage compute, queue, KV, seam bytes/latency, RSS/VRAM, and backend timing are present; and
+- results are labeled by hardware/topology and are not generalized to other consumer systems.
+
+If output quality passes but the speed floor fails, verdict is `stop` for alpha and the evidence selects the next optimization target. It is not relabeled as success merely because the model loaded.
+
+### 5.5 Reliability and security
+
+- Two consecutive cold starts load, generate, release, and exit cleanly.
+- Cancellation during prefill and decode releases every stage's queued buffers and KV lease.
+- One worker loss aborts the route; alpha retries only from token zero on a new compatible route.
+- Stale epochs and duplicate step IDs are rejected.
+- Artifact paths stay outside `/home`; logs contain no secrets or unrestricted prompt payloads.
+- Synthetic workers and layer-reduced fixtures are labeled unit/integration coverage and cannot satisfy target alpha.
+
+## 6. First execution order
+
+The next unattended work should run in this order:
+
+1. DGR-017 — target contract, manifest, planner, and upstream status.
+2. DGR-003 — exact recipe identity.
+3. DGR-004 — current llama.cpp pin and minimal patch harness.
+4. Run in parallel:
+   - DGR-018 — whole-model oracle on a 256-GiB-class host with at least 224 GiB runtime-accessible memory.
+   - DGR-005 and DGR-006 — generic range/boundary seam on local small fixtures.
+5. DGR-019 — GLM semantics and parity after both parallel lanes pass.
+6. DGR-007 through DGR-011 — native worker and real transport route.
+7. Required DGR-013 failure subset.
+8. DGR-020 — real target alpha verdict.
+
+The first external hardware blocker is DGR-018, but DGR-005/DGR-006 proceed locally while that host is sourced. Do not download the full model until DGR-017's exact manifest and storage preflight pass.
+
+## 7. Sources checked on 2026-07-13
+
+Authoritative or primary:
+
+- Official model card and config: <https://huggingface.co/zai-org/GLM-5.2>
+- Official release/architecture blog: <https://z.ai/blog/glm-5.2>
+- Official code/documentation repository: <https://github.com/zai-org/GLM-5>
+- Official source revision API: <https://huggingface.co/api/models/zai-org/GLM-5.2>
+- Official GLM-5 technical report: <https://arxiv.org/abs/2602.15763>
+- Unsloth GGUF repository: <https://huggingface.co/unsloth/GLM-5.2-GGUF>
+- Unsloth local-run/quantization guide: <https://unsloth.ai/docs/models/glm-5.2>
+- llama.cpp GLM-5.2 support issue: <https://github.com/ggml-org/llama.cpp/issues/24730>
+- llama.cpp merged dense-MLA compatibility loader: <https://github.com/ggml-org/llama.cpp/pull/24770>
+- llama.cpp open GLM-5.2 DSA/IndexShare implementation: <https://github.com/ggml-org/llama.cpp/pull/25407>
+- llama.cpp merged generic CPU lightning indexer: <https://github.com/ggml-org/llama.cpp/pull/24231>
+- llama.cpp 1M-context discussion: <https://github.com/ggml-org/llama.cpp/discussions/24622>
+- IndexCache/IndexShare paper: <https://arxiv.org/abs/2603.12201>
+
+Donor/current implementation evidence:
+
+- Mesh-LLM repository: <https://github.com/Mesh-LLM/mesh-llm>
+- Mesh-LLM GLM branch noted by llama.cpp collaborator in issue #24730: `feat/jianyang-glm-52`
+
+Web/repository observations are pinned by date and must be refreshed in DGR-017 before implementation because upstream support is moving quickly.

.scratch/distributed-gguf-runtime/PRD.md

@@ -1,83 +1,714 @@
 # PRD: Distributed GGUF Runtime
 
-## Summary
+> **Specification status:** planning artifacts only. No distributed GGUF runtime is implemented. DGR-017 cleanup is complete; no runtime implementation story has completion credit. `prd.json` is authoritative.
 
-Build a distributed inference runtime that can serve large, quality-first open models by combining torrent-style model artifact distribution with sticky multi-node Inference Routes and per-shard local Hot KV State.
+## Goal
 
-The first runtime proof uses the existing PyTorch route because it exposes model internals and cache semantics more directly. GGUF/llama.cpp becomes the performance path after the route-session contract is proven.
+Deliver benchmark-gated, concurrent, distributed GGUF inference across consumer machines through existing Meshnet control-plane behavior and a standalone native worker around upstream llama.cpp. The accepted target is DeepSeek V4 Flash, not the superseded legacy target.
 
-## Goals
+## Locked scope
 
-- Eliminate full-prompt recompute in distributed decode.
-- Keep decode activation seams proportional to `hidden_size`, not `context_length * hidden_size`.
-- Keep Hot KV State local to the node serving the relevant Shard.
-- Stream token deltas when feasible and always expose Generation Telemetry.
-- Add a local full-model GGUF backend for immediate CPU performance wins.
-- Define Model Artifact manifests so nodes can verify, seed, and advertise artifacts without depending on Hugging Face at request time.
-- Prototype an upstreamable llama.cpp/libllama layer-boundary API.
-- Use DeepSeek-V4-Flash as the first serious large-model target after smaller protocol smoke tests.
+- Existing Meshnet Tracker routing, load balancing, billing, telemetry, relay, and provider semantics are backend-agnostic and are **not redesigned**. GGUF contributes exact compatibility, range/capacity, queue/load, seam-cost, health/reliability, and certification inputs only.
+- The data plane is a standalone project-owned C++ Shard worker with gRPC/Protobuf and a project-owned `ShardEngine` boundary.
+- llama.cpp is fetched at one exact commit into an ignored workspace from an in-repo manifest, then a numbered minimal patch stack is applied. There is no submodule, vendored tree, or permanent-fork dependency.
+- llama.cpp owns DeepSeek V4 graphs, mHC, MoE, attention, hash routing, and kernels. Meshnet adds only range-ownership hooks, typed boundary/local-state adapters, worker integration, and parity/certification.
+- Quantization and placement are dynamic recipe inputs. The 2–4 and 10+ stage layouts are certification scenarios, never product constants.
+- Per-shard Hot KV and V4 CSA/HCA/SWA/indexer/compressor state remain local and keyed by route session/epoch. The WAN seam carries the typed mHC 4×4096 residual boundary, positions, token-ID sideband where required, and schema/cache expectations—not per-layer caches.
+- Route changes use cache miss plus re-prefill/restart. There is no WAN KV or V4 auxiliary-cache migration.
+- CPU/CUDA/ROCm/Vulkan/Metal compile lanes are planned; only exact real-hardware-certified backend/model/recipe lanes may be advertised.
+- Alpha requires correctness and the pre-locked useful-speed gate. MTP is reserved and off for alpha; its ownership contract, implementation, and benchmark are required before beta.
 
-## Non-Goals
+## Target identities
 
-- No centralized hot KV cache in the per-token decode path.
-- No automatic route repair in alpha.
-- No permanent llama.cpp fork as the intended architecture.
-- No GLM-5.2 or Ornith first; they remain follow-up support audits.
-- No transport rewrite to QUIC/WebRTC before route/session semantics are proven.
+- DeepSeek V4 official target SHA: `60d8d70770c6776ff598c94bb586a859a38244f1`.
+- llama.cpp V4 support lineage began at PR 24162 / merge `8c146a8366304c871efc26057cc90370ccf58dad`; DGR-027 later pins one exact validated current commit.
+- V4 scope: 43 main layers plus MTP; mHC 4×4096 boundary; 256 routed + 1 shared experts with six routed active; token IDs required for the first three hash-routed layers.
+- Exact split-GGUF artifacts are provisioned to mounted-drive storage with a complete hashed manifest and resumable verification; no model artifact may be placed under `/home`.
 
-## Resolved Decisions
+## Quality gates
 
-- Public-network Shards are contiguous transformer layer ranges.
-- Tensor/ring parallelism belongs inside one trusted node, one colocated pod, or a future composite node abstraction.
-- Hot KV State is local to route nodes; Prefix Snapshots are optional cold recovery/reuse artifacts.
-- PyTorch distributed KV/session semantics are proven before llama.cpp distributed execution.
-- Streaming responses are preferred; Generation Telemetry is mandatory.
-- llama.cpp/GGUF work targets upstreamable `libllama`/ggml hooks.
-- Alpha fails Route Sessions on route-node loss.
-- v1 activation transfer stays on binary HTTP.
-
-## Target User Experience
-
-A client sends an OpenAI-compatible request. The Gateway or Tracker Node accepts the request, creates a Route Session, and streams token deltas when supported. The client receives live Generation Telemetry for route phase, prefill progress, generated token count, rolling tokens/sec, route health, and failure reason.
-
-If a route node drops in alpha, the request fails clearly. A retry starts a new Route Session from scratch.
-
-## Runtime Shape
-
-```text
-client request
-  -> Gateway / Tracker Node creates Route Session
-  -> Tracker selects sticky Inference Route
-  -> prefill:
-       prompt chunks move through Shards
-       each node appends local Hot KV State
-  -> decode:
-       one-step activation moves through Shards
-       each node reads/appends local Hot KV State
-       tail returns token/logits
-  -> client receives streamed token deltas where possible
-  -> Generation Telemetry continues until complete or failed
-```
+The canonical gate groups live in `prd.json`. Every story explicitly requires its applicable shared gates: deterministic targeted tests, Python compile checks where applicable, native CMake/CTest and exact patch verification where applicable, real artifact/hardware provenance for opt-in lanes, `git diff --check`, and a durable evidence handoff.
 
 ## Milestones
 
-| Milestone | Outcome | Issues |
-|---|---|---|
-| M1 — Session protocol proof | Stub route has stable Route Sessions, prefill/decode split, telemetry, and streaming contract | 01, 02, 03 |
-| M2 — PyTorch reference route | Distributed PyTorch decode uses local per-shard cache and stops full-prompt recompute | 04 |
-| M3 — Local GGUF performance path | Single-node GGUF backend serves through the node API and reports backend metadata | 05 |
-| M4 — Artifact plane | Model Artifact manifest supports verification, layer mapping, and node advertisement | 06 |
-| M5 — llama.cpp collaboration proof | Localhost layer-boundary prototype identifies upstreamable llama.cpp/libllama API | 07 |
-| M6 — Networked GGUF route | Multi-node GGUF route uses the resolved protocol and fails cleanly on node loss | 08 |
-| M7 — First large model | DeepSeek-V4-Flash support path is audited and converted into follow-up runtime tasks | 09 |
+- **M0 — Truth and contracts (DGR-017..DGR-020):** Reconciled legacy truth, canonical metadata, immutable gates, and a controlled whole-model baseline.
+- **M1 — Protocol and native substrate (DGR-021..DGR-033):** Versioned gRPC protocol, exact identities/artifacts, pinned upstream, reproducible builds, ShardEngine, and fake worker.
+- **M2 — Dense vertical proof (DGR-034..DGR-043):** Dense ranged execution, parity, local state, worker integration, and GGUF inputs to existing routing.
+- **M3 — DeepSeek V4 Flash alpha (DGR-044..DGR-054):** Pinned V4 adapter around upstream llama.cpp, real route certification, and pre-locked alpha decision with MTP off.
+- **M4 — Performance and beta hardening (DGR-055..DGR-067):** Batching, backpressure, recovery, scale certification, optimization, MTP, and hardware matrix.
+- **M5 — Release and maintenance (DGR-068..DGR-071):** Reproducible packages, upstream collaboration, beta decision, and sustainable recertification.
 
-## Acceptance Criteria
+## User stories
 
-- A two-node route can prefill once and decode without resending full prompt activations.
-- Decode seam payload is one token/hidden-state step after prefill.
-- Route Session telemetry is visible before first token and during decode.
-- Streaming token deltas work where the backend supports them.
-- Route-node loss produces a structured alpha failure and does not attempt unsafe repair.
-- A local GGUF model can serve via the node API.
-- A Model Artifact manifest can prove which Shards a node can serve.
-- DeepSeek-V4-Flash has a written support recommendation: PyTorch, vLLM/SGLang, llama.cpp/GGUF, or blocked.
+### DGR-017: Reconcile and clean the superseded DGR backlog
+
+**Milestone:** M0 · **Mode:** AFK · **State:** complete · **Depends on:** none
+
+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.
+
+- [x] 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.
+- [x] Record an authoritative old-to-new disposition and provenance; explicitly give no completion credit to any new story and note absent implementation/evidence.
+- [x] Remove or archive only artifacts the audit proves obsolete while preserving accepted ADRs, useful research, raw benchmark evidence, and attributable reusable work.
+- [x] Protect ignored build workspaces, generated protobuf outputs, Ralph logs, and model artifacts from accidental commits, and document every retained legacy artifact.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
+
+### DGR-018: Define canonical Ralph and Gitea metadata schema
+
+**Milestone:** M0 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-017
+
+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.
+
+- [ ] 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.
+
+### DGR-019: Lock alpha and beta performance contracts
+
+**Milestone:** M0 · **Mode:** HITL · **Triage:** `ready-for-human` · **Depends on:** DGR-017
+
+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.
+
+- [ ] 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.
+
+### DGR-020: Run the controlled whole-model GGUF baseline
+
+**Milestone:** M0 · **Mode:** HITL · **Triage:** `ready-for-human` · **Depends on:** DGR-019
+
+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.
+
+- [ ] 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.
+
+### DGR-021: Define the versioned named-tensor stream envelope
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-018
+
+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.
+
+- [ ] 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.
+
+### DGR-022: Define Shard lifecycle and structured status RPCs
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-021
+
+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.
+
+- [ ] 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.
+
+### DGR-023: Make Python and C++ protobuf generation reproducible
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-021
+
+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.
+
+- [ ] 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.
+
+### DGR-024: Implement in-memory fake gRPC seam transport
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-022, DGR-023
+
+Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/024-implement-in-memory-fake-grpc-seam-transport.md`, and evidence READMEs for dependencies (DGR-022, DGR-023) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Exercise the complete streaming protocol deterministically before a real model or worker exists.
+
+- [ ] Provide a fake bidirectional stream supporting prefill fragments, decode fast-path frames, release, cancel, and structured errors.
+- [ ] Test flow-control blocking, deadlines, malformed fragments, checksum failure, duplicates, and stale epochs.
+- [ ] Verify direct and opaque-relay framing preserve identical protobuf bytes.
+- [ ] Tests require no sockets outside localhost, model downloads, or native accelerator.
+- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
+
+### DGR-025: Define exact artifact and runtime recipe identity
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-018, DGR-021
+
+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.
+
+- [ ] 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.
+
+### DGR-026: Provision exact split-GGUF artifacts outside /home
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-025
+
+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.
+
+- [ ] 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.
+
+### DGR-027: Add exact llama.cpp provenance manifest and fetch workspace
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-017
+
+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.
+
+- [ ] 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.
+
+### DGR-028: Implement numbered patch-stack apply and verification
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-027
+
+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.
+
+- [ ] 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.
+
+### DGR-029: Create the native CMake skeleton and deterministic CPU lane
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-027, DGR-028
+
+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.
+
+- [ ] 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.
+
+### DGR-030: Add accelerator build presets and native CI matrix
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-029
+
+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.
+
+- [ ] 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.
+
+### DGR-031: Introduce the project-owned `ShardEngine` interface
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-021, DGR-025
+
+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.
+
+- [ ] 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.
+
+### DGR-032: Implement deterministic fake `ShardEngine`
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-031
+
+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.
+
+- [ ] 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.
+
+### DGR-033: Build a standalone fake C++ gRPC Shard worker
+
+**Milestone:** M1 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-022, DGR-024, DGR-032
+
+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.
+
+- [ ] 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.
+
+### DGR-034: Implement dense-Llama range-aware GGUF ownership
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-028, DGR-029, DGR-031
+
+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.
+
+- [ ] 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.
+
+### DGR-035: Implement dense architecture boundary input/output
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-021, DGR-031, DGR-034
+
+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.
+
+- [ ] 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.
+
+### DGR-036: Prove dense fixture and real-model range parity
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-033, DGR-035
+
+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.
+
+- [ ] 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.
+
+### DGR-037: Bind llama.cpp to the standalone worker
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-022, DGR-023, DGR-031, DGR-034, DGR-035
+
+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.
+
+- [ ] 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.
+
+### DGR-038: Implement isolated shard-local Hot KV State
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-037
+
+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.
+
+- [ ] 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.
+
+### DGR-039: Pass local two-process dense acceptance
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-036, DGR-037, DGR-038
+
+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.
+
+- [ ] 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.
+
+### DGR-040: Add node-side native worker supervision
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-033, DGR-037
+
+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.
+
+- [ ] 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.
+
+### DGR-041: Register native Shard capabilities without redesigning Meshnet
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-025, DGR-040
+
+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.
+
+- [ ] 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.
+
+### DGR-042: Carry native frames through direct and existing relay seams
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-024, DGR-040
+
+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.
+
+- [ ] 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.
+
+### DGR-043: Expose GGUF compatibility and measured cost inputs to existing routing
+
+**Milestone:** M2 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-041
+
+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.
+
+- [ ] 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.
+
+### DGR-044: Pin the DeepSeek V4 Flash target contract
+
+**Milestone:** M3 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-019, DGR-025, DGR-026, DGR-027
+
+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.
+
+- [ ] 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.
+
+### DGR-045: Inventory V4 GGUF tensors and layer ownership
+
+**Milestone:** M3 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-026, DGR-044
+
+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.
+
+- [ ] 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.
+
+### DGR-046: Define the V4 typed architecture boundary schema
+
+**Milestone:** M3 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-021, DGR-045
+
+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.
+
+- [ ] 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.
+
+### DGR-047: Adapt the upstream V4 mHC boundary for ranged ownership
+
+**Milestone:** M3 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-045, DGR-046
+
+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.
+
+- [ ] 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.
+
+### DGR-048: Carry token-ID sideband through the first three hash-routed layers
+
+**Milestone:** M3 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-046, DGR-047
+
+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.
+
+- [ ] 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.
+
+### DGR-049: Keep V4 attention and auxiliary state shard-local
+
+**Milestone:** M3 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-046, DGR-047
+
+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.
+
+- [ ] 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.
+
+### DGR-050: Validate upstream V4 MoE and hash-routing execution under ranged ownership
+
+**Milestone:** M3 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-045, DGR-047
+
+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.
+
+- [ ] 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.
+
+### DGR-051: Assemble the DeepSeek V4 Flash `ShardEngine` adapter
+
+**Milestone:** M3 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-034, DGR-037, DGR-047, DGR-048, DGR-049, DGR-050
+
+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.
+
+- [ ] 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.
+
+### DGR-052: Pass local V4 whole-model versus ranged parity
+
+**Milestone:** M3 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-038, DGR-051
+
+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.
+
+- [ ] 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.
+
+### DGR-053: Certify a real 2–4-stage V4 route
+
+**Milestone:** M3 · **Mode:** HITL · **Triage:** `ready-for-human` · **Depends on:** DGR-030, DGR-043, DGR-052
+
+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.
+
+- [ ] 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.
+
+### DGR-054: Enforce the DeepSeek V4 Flash alpha gate
+
+**Milestone:** M3 · **Mode:** HITL · **Triage:** `ready-for-human` · **Depends on:** DGR-017, DGR-019, DGR-020, DGR-039, DGR-042, DGR-043, DGR-052, DGR-053
+
+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.
+
+- [ ] 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.
+
+### DGR-055: Implement compatible continuous decode batching
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-038, DGR-040, DGR-054
+
+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.
+
+- [ ] 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.
+
+### DGR-056: Enforce bounded admission, queues, and backpressure
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-055
+
+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.
+
+- [ ] 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.
+
+### DGR-057: Benchmark batching saturation and fairness
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-055, DGR-056
+
+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.
+
+- [ ] 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.
+
+### DGR-058: Harden worker and stream failure semantics
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-040, DGR-042, DGR-056
+
+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.
+
+- [ ] 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.
+
+### DGR-059: Implement alpha-safe route recovery
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-043, DGR-058
+
+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.
+
+- [ ] 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.
+
+### DGR-060: Certify V4 long-context state correctness
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-051, DGR-056, DGR-058
+
+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.
+
+- [ ] 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.
+
+### DGR-061: Certify existing routing with 10+ GGUF stage candidates
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-043, DGR-057, DGR-058
+
+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.
+
+- [ ] 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.
+
+### DGR-062: Certify a dynamic real 10+ stage V4 scenario
+
+**Milestone:** M4 · **Mode:** HITL · **Triage:** `ready-for-human` · **Depends on:** DGR-053, DGR-060, DGR-061
+
+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.
+
+- [ ] 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.
+
+### DGR-063: Profile and optimize the critical seam
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-057, DGR-061
+
+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.
+
+- [ ] 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.
+
+### DGR-064: Add negotiated activation compression
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-060, DGR-063
+
+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.
+
+- [ ] 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.
+
+### DGR-065: Define V4 MTP ownership and distributed state contract
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-051, DGR-054, DGR-060
+
+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.
+
+- [ ] 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.
+
+### DGR-066: Implement and benchmark V4 MTP
+
+**Milestone:** M4 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-054, DGR-060, DGR-064, DGR-065
+
+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.
+
+- [ ] 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.
+
+### DGR-067: Certify the backend capability matrix
+
+**Milestone:** M4 · **Mode:** HITL · **Triage:** `ready-for-human` · **Depends on:** DGR-030, DGR-053, DGR-062, DGR-066
+
+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.
+
+- [ ] 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.
+
+### DGR-068: Package reproducible native worker releases
+
+**Milestone:** M5 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-030, DGR-054, DGR-067
+
+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.
+
+- [ ] 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.
+
+### DGR-069: Prepare narrow upstream llama.cpp collaboration patches
+
+**Milestone:** M5 · **Mode:** HITL · **Triage:** `ready-for-human` · **Depends on:** DGR-028, DGR-035, DGR-038, DGR-051
+
+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.
+
+- [ ] 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.
+
+### DGR-070: Enforce the DeepSeek V4 Flash beta gate
+
+**Milestone:** M5 · **Mode:** HITL · **Triage:** `ready-for-human` · **Depends on:** DGR-057, DGR-059, DGR-060, DGR-062, DGR-064, DGR-066, DGR-067, DGR-068
+
+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.
+
+- [ ] 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.
+
+### DGR-071: Establish upstream pin, patch, and certification maintenance
+
+**Milestone:** M5 · **Mode:** AFK · **Triage:** `ready-for-agent` · **Depends on:** DGR-069, DGR-070
+
+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.
+
+- [ ] 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.
+
+## Non-goals
+
+- Replacing or redesigning Tracker routing/load-balancing, billing, relay, or provider policy.
+- Reimplementing DeepSeek V4 architecture graphs or kernels in Meshnet.
+- Hardcoding a quant, stage count, node count, split, architecture, or backend sequence.
+- WAN migration of KV or V4 auxiliary caches.
+- Advertising a compile-only or fixture-only hardware lane.
+- Making MTP an alpha dependency.

.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md

@@ -0,0 +1,57 @@
+# Ralph context: Distributed GGUF Runtime
+
+> **Specification status:** planning artifacts only. No distributed GGUF runtime is implemented. DGR-017 cleanup is complete; no runtime implementation story has completion credit. `prd.json` is authoritative.
+
+## Mandatory startup for every fresh story
+
+1. Read this file and authoritative `prd.json` completely.
+2. Read the generated source issue named in the selected story description.
+3. Read every dependency evidence README; legacy DGR-001..016 evidence is provenance only.
+4. Read `docs/adr/0024-distributed-gguf-runtime.md`, root `CONTEXT.md`, `.claude/memory/MEMORY.md`, and relevant live source/tests.
+5. Inspect `git status`; preserve unrelated work. Never infer implementation from planning text or old pass states.
+6. If blocked or oversized, keep `passes: false` and write an honest `BLOCKED.md`/`DECOMPOSITION.md`; never weaken criteria or fabricate evidence.
+
+## Locked scope
+
+- Existing Meshnet Tracker routing, load balancing, billing, telemetry, relay, and provider semantics are backend-agnostic and are **not redesigned**. GGUF contributes exact compatibility, range/capacity, queue/load, seam-cost, health/reliability, and certification inputs only.
+- The data plane is a standalone project-owned C++ Shard worker with gRPC/Protobuf and a project-owned `ShardEngine` boundary.
+- llama.cpp is fetched at one exact commit into an ignored workspace from an in-repo manifest, then a numbered minimal patch stack is applied. There is no submodule, vendored tree, or permanent-fork dependency.
+- llama.cpp owns DeepSeek V4 graphs, mHC, MoE, attention, hash routing, and kernels. Meshnet adds only range-ownership hooks, typed boundary/local-state adapters, worker integration, and parity/certification.
+- Quantization and placement are dynamic recipe inputs. The 2–4 and 10+ stage layouts are certification scenarios, never product constants.
+- Per-shard Hot KV and V4 CSA/HCA/SWA/indexer/compressor state remain local and keyed by route session/epoch. The WAN seam carries the typed mHC 4×4096 residual boundary, positions, token-ID sideband where required, and schema/cache expectations—not per-layer caches.
+- Route changes use cache miss plus re-prefill/restart. There is no WAN KV or V4 auxiliary-cache migration.
+- CPU/CUDA/ROCm/Vulkan/Metal compile lanes are planned; only exact real-hardware-certified backend/model/recipe lanes may be advertised.
+- Alpha requires correctness and the pre-locked useful-speed gate. MTP is reserved and off for alpha; its ownership contract, implementation, and benchmark are required before beta.
+
+## Target identities
+
+- DeepSeek V4 official target SHA: `60d8d70770c6776ff598c94bb586a859a38244f1`.
+- llama.cpp V4 support lineage began at PR 24162 / merge `8c146a8366304c871efc26057cc90370ccf58dad`; DGR-027 later pins one exact validated current commit.
+- V4 scope: 43 main layers plus MTP; mHC 4×4096 boundary; 256 routed + 1 shared experts with six routed active; token IDs required for the first three hash-routed layers.
+- Exact split-GGUF artifacts are provisioned to mounted-drive storage with a complete hashed manifest and resumable verification; no model artifact may be placed under `/home`.
+
+## Control/data-plane contract
+
+Meshnet continues to own registration, coverage, existing route selection/load balancing, route epochs/sessions, direct/relay behavior, capability admission, cancellation, telemetry, billing, validation, and attribution. The GGUF adapter exposes measured inputs to those existing mechanisms. Direct seams use long-lived gRPC streams; relay seams carry byte-identical protobuf frames opaquely.
+
+The project-owned `ShardEngine` hides llama.cpp internals. A worker loads one exact artifact/recipe/range identity. Default tests use fake/tiny fixtures. Real runs are opt-in, preserve raw metrics, and never download models under `/home`.
+
+## Gitea issue synchronization
+
+Gitea is a projection of `prd.json`, never a competing source of truth. Before and after every supervised Ralph run, invoke:
+
+```bash
+python3 scripts/ralph_gitea_sync.py sync
+```
+
+For a complete Ralph invocation with automatic state reconciliation, use:
+
+```bash
+scripts/ralph-gitea-run.sh ralph-tui run --prd .scratch/distributed-gguf-runtime/prd.json --agent claude --model sonnet --iterations 1 --no-tui --no-setup --direct-merge --no-sandbox
+```
+
+The sync creates/reconciles one Gitea issue per `DGR-*` story, creates missing labels/milestones, closes issues whose `passes` is true, marks the selected next eligible story `status:in-progress`, and marks blocked stories `status:blocked`. `gitea-issues.json` is a derived mapping only.
+
+## Evidence and completion
+
+Each story writes `/run/media/popov/d/DEV/repos/d-popov.com/AI/.claude/worktrees/distributed-gguf-runtime/.scratch/distributed-gguf-runtime/evidence/<DGR-ID>/README.md` with exact files, commands/results, limitations, identities, and dependent-story handoff. Only `prd.json` may record `passes`; DGR-017 and DGR-018 are complete and DGR-019 onward remain false. Generated Markdown and Gitea issues cannot override it. One scoped commit per story is expected during future execution.

.scratch/distributed-gguf-runtime/README.md

@@ -1,63 +1,32 @@
-# Distributed GGUF runtime — planning index
+# Distributed GGUF Runtime planning workspace
 
-Status: draft scratch package.
+> **Implementation status:** DGR-017 through DGR-033 have verified lane evidence, including a fixture-only standalone C++ gRPC worker. These lane checkpoints still require serialized integration and remote publication; they do not claim real model inference. `prd.json` is authoritative.
 
-Goal: make the node network capable of serving large, high-quality open models by distributing GGUF/model artifacts over a torrent-style swarm while executing inference over a sticky multi-node route with per-shard local KV cache.
 
-This scratch supersedes the old assumption in [ADR-0001](../../docs/adr/0001-pytorch-over-llama-cpp.md) that llama.cpp is only a single-node leaf backend. That assumption was correct for the original llama.cpp RPC shape, but the target is now different: torrent-distributed GGUF artifacts plus an explicit route/KV protocol owned by this platform, ideally developed in collaboration with upstream llama.cpp.
+## Locked scope
 
-## Artifacts
+- Existing Meshnet Tracker routing, load balancing, billing, telemetry, relay, and provider semantics are backend-agnostic and are **not redesigned**. GGUF contributes exact compatibility, range/capacity, queue/load, seam-cost, health/reliability, and certification inputs only.
+- The data plane is a standalone project-owned C++ Shard worker with gRPC/Protobuf and a project-owned `ShardEngine` boundary.
+- llama.cpp is fetched at one exact commit into an ignored workspace from an in-repo manifest, then a numbered minimal patch stack is applied. There is no submodule, vendored tree, or permanent-fork dependency.
+- llama.cpp owns DeepSeek V4 graphs, mHC, MoE, attention, hash routing, and kernels. Meshnet adds only range-ownership hooks, typed boundary/local-state adapters, worker integration, and parity/certification.
+- Quantization and placement are dynamic recipe inputs. The 2–4 and 10+ stage layouts are certification scenarios, never product constants.
+- Per-shard Hot KV and V4 CSA/HCA/SWA/indexer/compressor state remain local and keyed by route session/epoch. The WAN seam carries the typed mHC 4×4096 residual boundary, positions, token-ID sideband where required, and schema/cache expectations—not per-layer caches.
+- Route changes use cache miss plus re-prefill/restart. There is no WAN KV or V4 auxiliary-cache migration.
+- CPU/CUDA/ROCm/Vulkan/Metal compile lanes are planned; only exact real-hardware-certified backend/model/recipe lanes may be advertised.
+- Alpha requires correctness and the pre-locked useful-speed gate. MTP is reserved and off for alpha; its ownership contract, implementation, and benchmark are required before beta.
 
-| Path | Purpose |
-|---|---|
-| [architecture.md](./architecture.md) | Proposed runtime architecture, data flow, session state, and failure model |
-| [technical-challenges.md](./technical-challenges.md) | Detailed challenge/solution register with acceptance tests |
-| [decision-framework.md](./decision-framework.md) | Grilling framework for open decisions and recommended answers |
-| [research-prior-art.md](./research-prior-art.md) | Prior-art notes for Petals, exo, Distributed Llama, prima.cpp, llama.cpp, DeepSeek-V4-Flash, GLM-5.2, and Ornith |
-| [ADR-0020-distributed-gguf-runtime.md](./ADR-0020-distributed-gguf-runtime.md) | Draft decision record for the GGUF/llama.cpp distributed runtime |
-| [PRD.md](./PRD.md) | Product/runtime requirements and acceptance criteria |
-| [milestones.md](./milestones.md) | Dependency-ordered implementation milestones |
-| [issues/](./issues/) | Implementation-ready tracer-bullet issue briefs |
+## Target identities
 
-## Decision Summary
+- DeepSeek V4 official target SHA: `60d8d70770c6776ff598c94bb586a859a38244f1`.
+- llama.cpp V4 support lineage began at PR 24162 / merge `8c146a8366304c871efc26057cc90370ccf58dad`; DGR-027 later pins one exact validated current commit.
+- V4 scope: 43 main layers plus MTP; mHC 4×4096 boundary; 256 routed + 1 shared experts with six routed active; token IDs required for the first three hash-routed layers.
+- Exact split-GGUF artifacts are provisioned to mounted-drive storage with a complete hashed manifest and resumable verification; no model artifact may be placed under `/home`.
 
-Adopt a hybrid runtime:
+## Navigation
 
-- **Weights and artifacts**: distributed by torrent / content-addressed storage / optional CDN.
-- **Hot KV cache**: local to the node that owns the corresponding layer range.
-- **Prefix snapshots**: optionally persisted to cache servers for reuse, retry, and failover.
-- **Active route**: sticky for one request/session.
-- **Context cap**: 128K hard product limit for large models unless explicitly revised.
-- **Backends**: keep PyTorch for fast model-architecture coverage and validation; add llama.cpp/GGUF as the performance path for supported models.
-- **Client feedback**: stream token deltas when feasible; always expose Generation Telemetry.
-- **First serious target model**: DeepSeek-V4-Flash after a smaller GGUF protocol smoke test.
-
-## What We Learned
-
-- Our current full-model PyTorch path uses Transformers `generate()` and gets local KV cache.
-- Our current distributed PyTorch path disables cache and recomputes the full growing sequence per token.
-- The seam today carries hidden activations, not KV cache; at 128K this becomes impossible for serious models if repeated every decode token.
-- The missing capability is not "send KV across the network"; it is **stable per-session local KV cache per shard**.
-- GGUF distribution is solved enough at the artifact layer, but GGUF/llama.cpp needs explicit layer-boundary execution APIs for our route model.
-
-## Recommended Order
-
-See [milestones.md](./milestones.md) for the full dependency map.
-
-1. [01 — Route Session lifecycle](./issues/01-route-session-lifecycle.md)
-2. [02 — Prefill/decode binary HTTP protocol](./issues/02-prefill-decode-binary-http.md)
-3. [03 — Generation Telemetry and streaming response contract](./issues/03-generation-telemetry-and-streaming.md)
-4. [04 — PyTorch distributed KV reference route](./issues/04-pytorch-distributed-kv-reference.md)
-5. [05 — Local llama.cpp/GGUF backend](./issues/05-local-llamacpp-gguf-backend.md)
-6. [06 — Model Artifact manifest and Shard advertisement](./issues/06-model-artifact-manifest.md)
-7. [07 — llama.cpp layer-boundary prototype](./issues/07-llamacpp-layer-boundary-prototype.md)
-8. [08 — Networked distributed GGUF route](./issues/08-networked-distributed-gguf-route.md)
-9. [09 — DeepSeek-V4-Flash support audit](./issues/09-deepseek-v4-flash-support-audit.md)
-10. [10 — GLM-5.2 and Ornith follow-up support audit](./issues/10-glm52-ornith-followup-audit.md)
-
-## Open Questions
-
-- Does upstream llama.cpp already expose enough internal API for arbitrary layer-range execution and hidden-state boundary I/O, or do we need an extension?
-- Can GGUF split metadata be made layer/tensor semantic enough for torrent placement and partial loading?
-- What is the minimum protocol needed for compressed KV formats such as GLM-5.2 DSA/MLA without exposing model-specific internals to the tracker?
-- How much reliability do we need in alpha: fail request on route loss, or support route repair with KV snapshots?
+- [`prd.json`](prd.json) — sole authoritative 55-story backlog, DGR-017..071.
+- [`PRD.md`](PRD.md) — human-readable projection of goals, gates, and all stories.
+- [`RALPH-CONTEXT.md`](RALPH-CONTEXT.md) — mandatory fresh-session context.
+- [`architecture.md`](architecture.md), [`implementation-strategy.md`](implementation-strategy.md), [`milestones.md`](milestones.md) — design and execution sequence.
+- [`issues/`](issues/) — generated story specs; files 01..16 are retained legacy artifacts pending DGR-017.
+- [`evidence/`](evidence/) — provenance and future per-story handoffs.

.scratch/distributed-gguf-runtime/architecture.md

@@ -1,274 +1,45 @@
-# Distributed GGUF Runtime Architecture
+# Distributed GGUF Runtime architecture
 
-## Product Stance
+> **Specification status:** planning artifacts only. No distributed GGUF runtime is implemented. DGR-017 cleanup is complete; no runtime implementation story has completion credit. `prd.json` is authoritative.
 
-The platform optimizes for access to high-quality models, not lowest latency. Latency is acceptable if the user can run models that are otherwise unavailable to them. The hard context limit for the first serious distributed runtime should be **128K tokens**. Longer context usually means the product is compensating for missing task decomposition, retrieval, or workspace summarization.
 
-## Current State
+## Locked scope
 
-The current node has two materially different inference paths:
+- Existing Meshnet Tracker routing, load balancing, billing, telemetry, relay, and provider semantics are backend-agnostic and are **not redesigned**. GGUF contributes exact compatibility, range/capacity, queue/load, seam-cost, health/reliability, and certification inputs only.
+- The data plane is a standalone project-owned C++ Shard worker with gRPC/Protobuf and a project-owned `ShardEngine` boundary.
+- llama.cpp is fetched at one exact commit into an ignored workspace from an in-repo manifest, then a numbered minimal patch stack is applied. There is no submodule, vendored tree, or permanent-fork dependency.
+- llama.cpp owns DeepSeek V4 graphs, mHC, MoE, attention, hash routing, and kernels. Meshnet adds only range-ownership hooks, typed boundary/local-state adapters, worker integration, and parity/certification.
+- Quantization and placement are dynamic recipe inputs. The 2–4 and 10+ stage layouts are certification scenarios, never product constants.
+- Per-shard Hot KV and V4 CSA/HCA/SWA/indexer/compressor state remain local and keyed by route session/epoch. The WAN seam carries the typed mHC 4×4096 residual boundary, positions, token-ID sideband where required, and schema/cache expectations—not per-layer caches.
+- Route changes use cache miss plus re-prefill/restart. There is no WAN KV or V4 auxiliary-cache migration.
+- CPU/CUDA/ROCm/Vulkan/Metal compile lanes are planned; only exact real-hardware-certified backend/model/recipe lanes may be advertised.
+- Alpha requires correctness and the pre-locked useful-speed gate. MTP is reserved and off for alpha; its ownership contract, implementation, and benchmark are required before beta.
 
-- **Full local PyTorch model**: calls Hugging Face `model.generate()`, so Transformers owns autoregressive decode and local KV cache.
-- **Distributed PyTorch route**: bypasses `model.generate()`, calls individual layers with `use_cache=False`, and recomputes the full growing sequence for every generated token.
+## Target identities
 
-Current distributed data flow:
+- DeepSeek V4 official target SHA: `60d8d70770c6776ff598c94bb586a859a38244f1`.
+- llama.cpp V4 support lineage began at PR 24162 / merge `8c146a8366304c871efc26057cc90370ccf58dad`; DGR-027 later pins one exact validated current commit.
+- V4 scope: 43 main layers plus MTP; mHC 4×4096 boundary; 256 routed + 1 shared experts with six routed active; token IDs required for the first three hash-routed layers.
+- Exact split-GGUF artifacts are provisioned to mounted-drive storage with a complete hashed manifest and resumable verification; no model artifact may be placed under `/home`.
+
+## Topology
 
 ```text
-client request
-  -> head node formats prompt
-  -> for each output token:
-       head tokenizes full current text
-       head runs early layers over all tokens
-       head sends full activation [batch, sequence, hidden] to next node
-       middle nodes run their layers over all tokens
-       tail returns one decoded token string
-       head appends token to text
+existing Meshnet Tracker/control plane
+  -> existing backend-agnostic route/load-balancing decision
+  -> direct gRPC or existing opaque relay
+  -> project-owned standalone C++ Shard worker
+  -> project-owned ShardEngine
+  -> pinned upstream llama.cpp + numbered range/boundary/state hook patches
+  -> GGUF mmap, upstream V4 graph/kernels, local per-shard state
 ```
 
-This is correct for small demos but not viable for large models. For GLM-5.2, a single 128K seam activation is roughly:
+A route is ordered contiguous half-open ranges. Head owns token embedding; tail owns final norm/head/sampling. Compatibility fingerprints bind source/split hashes, tokenizer, architecture adapter, typed boundary, runtime pin/patches, backend, quant, activation/compute/KV layout, range, and certification.
 
-```text
-128K tokens * hidden_size 6144 * 2 bytes ~= 1.5 GiB per hop
-```
+## V4 boundary and state
 
-Sending that every output token is the bottleneck.
+The inter-stage boundary is semantic and versioned: mHC 4×4096 residual, positions, token IDs only where the first three hash-routed layers require them, and cache/schema expectations. CSA/HCA/SWA/indexer/compressor/KV state belongs to upstream layer execution on the owning worker and is isolated by `(route_session_id, route_epoch)`. On loss, return cache miss and re-prefill/restart. Never serialize those caches into the WAN bundle.
 
-## Target State
+## Concurrency, failure, and admission
 
-Target distributed data flow:
-
-```text
-client request
-  -> tracker selects route and pins session
-  -> head node creates session_id
-  -> prefill:
-       prompt is chunked
-       each shard computes its layer range
-       each shard appends local KV/state for its own layers
-       activations cross only layer seams
-  -> decode loop:
-       head sends one new token / one-step hidden state
-       each shard reads local KV/state for session_id
-       each shard appends one step to local KV/state
-       only one-step activation crosses seams
-       tail returns logits/token
-```
-
-The KV cache remains local to the node that computed it. It is not sent to the next node and not read from a remote cache server during every decode step.
-
-## Client Feedback
-
-Streaming responses are desirable when the backend and client transport support them. The product should stream token deltas when possible, and it must always provide realtime Generation Telemetry while the route is working.
-
-The fallback behavior is a non-streaming final answer plus live telemetry. That fallback is acceptable for early route proofs or models/backends that cannot expose clean token deltas yet, but the preferred client experience is streamed output plus telemetry.
-
-Minimum client-visible telemetry:
-
-- route/session accepted
-- selected model and quantization
-- prefill phase started/completed
-- decode phase started
-- generated token count
-- rolling tokens per second
-- route health or retry/failure reason
-- estimated billing units when available
-
-Implementation options:
-
-- Server-Sent Events or WebSocket for realtime progress
-- polling endpoint for simple clients
-- OpenAI-compatible streaming for clients that require token deltas
-
-This means "no token streaming" is acceptable only as a fallback. "Silent wait for minutes" is not acceptable.
-
-## Artifact Plane
-
-Artifact distribution is separate from execution.
-
-```text
-model publisher
-  -> produces model manifest
-  -> creates GGUF / safetensors / tokenizer artifacts
-  -> content-addresses every file/chunk
-  -> publishes torrent/magnet + HTTP fallback metadata
-
-node
-  -> chooses model/layer range
-  -> downloads needed files/chunks
-  -> verifies hash
-  -> advertises availability to tracker
-```
-
-Required manifest fields:
-
-- model id and version
-- upstream source repo and revision
-- license
-- architecture name
-- tokenizer files and hashes
-- quantization
-- tensor-to-layer map
-- file/chunk hashes
-- optional GGUF split files
-- supported runtime backends
-- context cap
-- KV/cache format descriptor
-
-## Execution Plane
-
-The tracker selects routes using layer coverage and observed performance:
-
-```text
-route = [
-  head node: embeddings + layers 0..k
-  middle nodes: contiguous layer ranges
-  tail node: final layers + norm + lm_head
-]
-```
-
-Route selection inputs:
-
-- model id/version/quantization
-- layer coverage
-- node hardware
-- measured prefill throughput
-- measured decode throughput
-- queue depth
-- latency to neighboring nodes
-- cache warmth for the requested prefix/session
-- reliability/reputation
-
-The route is sticky for the request/session. A new route means either a fresh prefill or restoring compatible KV snapshots.
-
-## KV Cache Ownership
-
-KV/state ownership is by layer range:
-
-```text
-session_id = request scoped id
-node A owns layers 0..15 KV for session_id
-node B owns layers 16..31 KV for session_id
-node C owns layers 32..77 KV for session_id
-```
-
-The tracker does not own hot KV. It may know which nodes hold active KV for session accounting and failure handling.
-
-Cache servers may store:
-
-- prompt-prefix snapshots
-- session checkpoints for retry
-- cold reusable context blocks
-- audit samples
-
-Cache servers must not be in the per-token hot loop unless colocated with the compute node.
-
-## 128K KV Budget
-
-GLM-5.2 compressed DSA/MLA-style estimate from config:
-
-```text
-layers = 78
-kv_lora_rank = 512
-qk_rope_head_dim = 64
-dtype = bf16 = 2 bytes
-context = 128K
-
-per_token ~= 78 * (512 + 64) * 2 = 89,856 bytes ~= 87.75 KiB
-128K total ~= 10.7 GiB
-per layer ~= 137 MiB
-```
-
-This is feasible when sharded:
-
-| Layer count | Approx active KV at 128K |
-|---:|---:|
-| 1 | 137 MiB |
-| 10 | 1.37 GiB |
-| 20 | 2.75 GiB |
-| 78 | 10.7 GiB |
-
-The exact runtime value depends on implementation and cache quantization, but the order of magnitude is acceptable.
-
-## Protocol Sketch
-
-### Prefill
-
-```http
-POST /v1/sessions/{session_id}/prefill
-Content-Type: application/octet-stream
-X-Meshnet-Model: zai-org/GLM-5.2
-X-Meshnet-Route-Id: ...
-X-Meshnet-Token-Range: 0-2047
-X-Meshnet-Shape: 1,2048,6144
-X-Meshnet-Dtype: bfloat16
-
-<activation bytes>
-```
-
-The receiver:
-
-- validates route/session
-- runs assigned layer range for that chunk
-- appends local KV/state
-- forwards resulting activation to next hop
-
-### Decode
-
-```http
-POST /v1/sessions/{session_id}/decode-step
-Content-Type: application/octet-stream
-X-Meshnet-Model: zai-org/GLM-5.2
-X-Meshnet-Position: 131072
-X-Meshnet-Shape: 1,1,6144
-X-Meshnet-Dtype: bfloat16
-
-<one-step activation bytes>
-```
-
-The receiver:
-
-- loads local KV/state by `session_id`
-- runs one decode step for assigned layers
-- appends one token position to local KV/state
-- forwards one-step activation
-
-## GGUF / llama.cpp Integration
-
-The target llama.cpp integration needs more than `llama-server`.
-
-Required capabilities:
-
-- load full GGUF locally for immediate single-node performance
-- optionally load only selected tensors/layers
-- execute a layer range against inbound hidden states
-- expose outbound hidden states at a boundary
-- own per-session KV/state for only the loaded layer range
-- support prefill chunks and decode-step calls
-- expose model-specific cache metadata for DSA/MLA without requiring the tracker to understand tensor internals
-
-If llama.cpp cannot expose these as stable APIs today, the collaboration target is an upstream extension rather than a long-lived fork.
-
-## Failure Model
-
-Alpha behavior:
-
-- Route node drops during prefill: fail request and retry from scratch.
-- Route node drops during decode: fail request unless a recent KV snapshot exists.
-- Tracker restart: active sessions may be lost; completed billing records persist.
-- Node restart: local hot KV is lost.
-
-Later behavior:
-
-- periodic KV snapshots for long sessions
-- prefix cache reuse across requests
-- route repair when a semantically equivalent node has the same model/layer range and compatible cache snapshot
-
-## Security And Trust
-
-Activation/KV data can reveal user prompts. Public volunteer routes are not private. For sensitive workloads:
-
-- use private swarms
-- allow paid trusted nodes
-- encrypt transport
-- avoid storing hot KV on untrusted shared cache servers
-- sample outputs for fraud/audit as already planned in alpha hardening
+Compatible sessions may be continuously batched within a worker while retaining isolated positions/state. Admission bounds weights, local state/KV, scratch, fragments, and queues. Uncertain cross-route mutation is not replayed. Registration can show an uncertified lane, but existing admission keeps it unroutable until signed/versioned real-hardware evidence exists.

.scratch/distributed-gguf-runtime/decision-framework.md

@@ -1,268 +1,40 @@
-# Distributed GGUF Decision Framework
-
-This framework is for grilling open decisions. It keeps decisions tied to project vocabulary and implementation gates instead of vague "distributed inference" language.
-
-## Core Vocabulary
-
-Use the existing domain terms this way:
-
-- **Shard**: contiguous transformer layer range. This is the compute, routing, cache, and reward unit.
-- **Shard Swarm**: storage/download group for artifacts needed by a shard.
-- **Inference Route**: ordered node sequence that covers all layers for one request.
-- **Route Session**: one active request bound to one inference route and stable session id.
-- **Hot KV State**: live per-shard cache held by the route node during a route session.
-- **Prefix Snapshot**: persisted route-session state used for reuse or failover, not the hot decode path.
-- **Artifact Manifest**: canonical mapping from model artifacts to semantic model parts and runtime support.
-- **Generation Telemetry**: realtime progress for a route session, including phase and tokens/sec, independent of whether token deltas are streamed.
-
-## The Five Planes
-
-### 1. Control Plane
-
-Owner: Tracker.
-
-Responsibilities:
-
-- node registry
-- coverage map
-- route selection
-- rebalance directives
-- route-session creation
-- health and telemetry
-- client-visible Generation Telemetry
-- billing/audit records
-
-Must not do:
-
-- serve hot KV during every token
-- become the only place model artifacts can be fetched
-
-### 2. Artifact Plane
-
-Owner: Shard Swarms, local node storage, optional CDN/bootstrap mirrors.
-
-Responsibilities:
-
-- GGUF/safetensors/tokenizer download
-- content-addressed verification
-- local artifact inventory
-- artifact-to-layer mapping
-- cache eviction
-
-Must not do:
-
-- define execution order by file split alone
-- imply that a downloaded file chunk equals a Shard
-
-### 3. Execution Plane
-
-Owner: active Inference Route.
-
-Responsibilities:
-
-- chunked prefill
-- one-step decode
-- hidden-state transfer across activation seams
-- start-layer handling for overlapping shards
-- backpressure
-
-Must not do:
-
-- resend full context activations during decode
-- require cross-node tensor parallel all-reduce for public v1
-
-### 4. Session State Plane
-
-Owner: route nodes for hot KV; cache servers only for snapshots.
-
-Responsibilities:
-
-- per-shard local KV ownership
-- cache allocation and eviction
-- cache ABI compatibility
-- session close/release
-- optional prefix snapshots
-
-Must not do:
-
-- centralize hot KV in a remote service
-- let a replacement node continue from incompatible state
-
-### 5. Economics And Trust Plane
-
-Owner: tracker plus settlement/validation components.
-
-Responsibilities:
-
-- distinguish storage/seeding work from inference work
-- account for prefill and decode separately
-- record route participation
-- sample validation events
-- slash proven fraud
-
-Must not do:
-
-- pay a node for merely holding files as if it generated tokens
-- hide public-swarm privacy limits from clients
-
-## Hard Invariants
-
-These are the framework rules unless we deliberately write a new ADR:
-
-1. Public-network Shards are contiguous layer ranges.
-2. Hot KV State is local to the node serving that Shard in that Route Session.
-3. Artifact distribution and route execution are separate systems.
-4. Decode seam payload must be `O(hidden_size)`.
-5. Prefill may be `O(sequence_length * hidden_size)`, but only in bounded chunks.
-6. The tracker chooses routes; nodes do not negotiate route topology peer-to-peer.
-7. Model/backend-specific cache internals stay behind backend capability reports.
-8. PyTorch remains the correctness/reference backend while llama.cpp/GGUF becomes the performance backend.
-9. Streaming responses are preferred when feasible; Generation Telemetry is always required.
-
-## Resolved Gates
-
-### Gate 1: Public Shard Semantics
-
-Decision: public-network Shards are contiguous transformer layer ranges. Tensor-parallel or ring-style execution is allowed only inside one trusted node, one colocated pod, or a future composite node abstraction.
-
-Rationale:
-
-- Layer ranges match the existing `Shard`, `Coverage Map`, `Inference Route`, billing, and fraud vocabulary.
-- Public volunteer nodes should not require cross-node all-reduce or tight per-layer synchronization in v1.
-- Existing projects such as prima.cpp and Distributed Llama can still inform local-cluster/backend execution without becoming the public routing primitive.
-
-Consequences:
-
-- Artifact Manifests must map files/tensors to semantic layer ranges.
-- Route selection remains ordered layer coverage.
-- Rewards can be attributed to layer-range work.
-- Hot KV State is naturally owned by the node serving that layer range for the Route Session.
-
-### Gate 2: Hot KV Strategy
-
-Decision: v1 rejects centralized hot KV. Hot KV State is local to the node serving the relevant Shard in the active Route Session. Cache servers may store Prefix Snapshots for reuse, retry, or failover, but they are not in the per-token decode path.
-
-Rationale:
-
-- Decode is the tight loop; adding remote cache I/O there makes latency and bandwidth worse at the worst point.
-- Local KV naturally follows layer-range Shard ownership.
-- Centralized hot KV increases privacy exposure and creates consistency problems.
-- Prefix Snapshots preserve the useful part of central storage without making it mandatory for every generated token.
-
-Consequences:
-
-- Route Session must be sticky.
-- Failover is limited in alpha unless a compatible Prefix Snapshot exists.
-- Cache servers are optimization infrastructure, not required runtime infrastructure.
-- Route repair requires compatible model revision, layer range, backend cache ABI, and snapshot position.
-
-### Gate 3: First Runtime Proof
-
-Decision: prove distributed Route Session and Hot KV State semantics in the existing PyTorch route before modifying llama.cpp/GGUF.
-
-Rationale:
-
-- PyTorch exposes model internals and cache objects more directly, so it is the fastest way to validate the distributed protocol.
-- The current distributed PyTorch route already has the right high-level shape but disables cache and recomputes full prompts.
-- Fixing that path gives us a reference implementation for correctness tests, telemetry, session lifecycle, and wire protocol behavior.
-- llama.cpp/GGUF should receive a clear target ABI rather than becoming both the protocol experiment and the performance backend at once.
-
-Consequences:
-
-- Issue 02 precedes issue 05.
-- llama.cpp collaboration has a concrete target ABI.
-- The PyTorch route remains the architecture-coverage/reference backend even after GGUF becomes the preferred performance path.
-- The first success metric is eliminating full-prompt recompute in distributed decode.
-
-### Gate 3A: Client Feedback During Latency
-
-Decision: streaming responses are preferred when feasible, and realtime Generation Telemetry is required regardless of streaming support.
-
-Rationale:
-
-- The product optimizes for access to large capable models, so some latency is acceptable.
-- Users still need confidence that the route is alive and roughly how fast it is generating.
-- Streaming token deltas give the best user experience when the backend exposes them cleanly.
-- Tokens/sec remains useful during prefill, queueing, and any backend that cannot stream token deltas.
-
-Consequences:
-
-- The gateway should stream token deltas through an OpenAI-compatible response when possible.
-- The gateway must expose progress through SSE, WebSocket, or polling.
-- The final answer can be delivered after completion only as a fallback.
-- Telemetry must include route phase, generated token count, and rolling tokens/sec.
-- Non-streaming clients still need realtime telemetry.
-
-### Gate 4: llama.cpp Collaboration Shape
-
-Decision: target upstreamable `libllama`/ggml hooks instead of planning around a permanent fork.
-
-Rationale:
-
-- llama.cpp changes quickly across model support, quantization, kernels, and hardware backends.
-- A permanent fork would become expensive to maintain and would lag upstream improvements.
-- A short-lived prototype branch is acceptable if it proves the API and makes upstream collaboration concrete.
-- Keeping tracker/routing logic outside llama.cpp makes the upstream ask smaller and cleaner.
-
-Consequences:
-
-- Need a minimal reproducible localhost demo before asking upstream to carry the design.
-- Need to separate "what llama.cpp should expose" from "what our tracker does".
-- Desired upstream surface is layer-range execution, hidden-state boundary I/O, partial loading/introspection, and per-session KV ownership.
-- If upstream rejects the shape, we revisit whether to carry a narrow adapter fork or keep GGUF distributed execution as experimental.
-
-### Gate 5: First Model Target
-
-Decision: use a two-tier model target. Use a small, boring, llama.cpp-supported GGUF model for the first protocol smoke test. Use `deepseek-ai/DeepSeek-V4-Flash` as the first serious large-model target. Keep GLM-5.2 and Ornith as later support audits.
-
-Rationale:
-
-- The first protocol proof should isolate route/session/KV bugs from model-architecture bugs.
-- DeepSeek-V4-Flash is a strong first serious target because it is much smaller than 1.6T-class models while still being large enough to validate the product thesis.
-- DeepSeek-V4-Flash still has architecture-specific risks, so it should not be the first smoke test.
-- GLM-5.2 and Ornith remain valuable targets, but they add DSA/MLA/hybrid attention uncertainty.
-
-Consequences:
-
-- 128K cache accounting can be modeled now.
-- The first "real" target-model audit is DeepSeek-V4-Flash support in PyTorch, vLLM/SGLang, and any available GGUF/llama.cpp quantization path.
-- Production support waits for backend capability reports and exact cache ABI support.
-
-### Gate 6: Failure Semantics
-
-Decision: alpha fails Route Sessions on route-node loss instead of attempting automatic route repair.
-
-Rationale:
-
-- Route repair requires compatible Prefix Snapshots, cache ABI checks, replacement-node selection, billing correction, and client stream/error recovery.
-- Local Hot KV State means a replacement node cannot continue unless it has compatible state at the same position.
-- Fail-fast keeps the first implementation correct while the session/KV protocol is still being proven.
-
-Consequences:
-
-- Better observability and explicit errors are required.
-- Snapshotting becomes a later feature, not a blocker for first inference.
-- Generation Telemetry must report the last known phase and failure reason.
-- Client or gateway retry starts a new Route Session from scratch.
-
-### Gate 7: Transport
-
-Decision: keep binary HTTP for v1 activation transfer instead of jumping immediately to QUIC, WebRTC, or a custom transport.
-
-Rationale:
-
-- ADR-0008 already defines binary activation bodies with HTTP headers.
-- HTTP keeps the first implementation debuggable with the existing server stack and tooling.
-- The core risk is route/session/KV correctness, not transport optimization.
-- QUIC/WebRTC can be introduced later behind the same activation protocol once semantics are proven.
-
-Consequences:
-
-- Focus benchmark work on payload shape, chunking, and cache behavior first.
-- QUIC/WebRTC can be introduced as an optimization behind the same activation protocol.
-- v1 implementation can reuse the current HTTP routing, relay, and observability infrastructure.
-- Transport abstraction should be kept narrow enough that HTTP can be replaced later without changing backend cache semantics.
-
-## Grilling Progress
-
-Gates 1, 2, 3, 3A, 4, 5, 6, and 7 are resolved. The remaining work is to convert the resolved framework into implementation-ready issue briefs and prototype milestones.
+# Distributed GGUF Runtime decision framework
+
+> **Specification status:** planning artifacts only. No distributed GGUF runtime is implemented. DGR-017 cleanup is complete; no runtime implementation story has completion credit. `prd.json` is authoritative.
+
+## Decision order
+
+1. DGR-019 locks comparable lanes and thresholds before results.
+2. DGR-020 runs safetensors and whole-model llama.cpp only, then returns `go`, `optimize baseline`, or `stop`.
+3. Dense and V4 work must prove parity, independent per-stage execution, local-state isolation, bounded failure, and measured resources.
+4. DGR-054 returns `alpha`, `optimize measured bottleneck`, or `stop`; MTP is explicitly off.
+5. Post-alpha optimizations must be selected from profiles, not assumptions.
+6. DGR-070 returns `beta`, `targeted optimization`, or `stop/rollback`, and requires MTP and the exact certified hardware/recipe matrix.
+
+## Interpretation rules
+
+- Quant/model-fit gains are separate from runtime/kernel/transport gains.
+- Fixture, real-model, real-hardware, and release evidence are never interchangeable.
+- 2–4 and 10+ stages are certification scenarios only.
+- Existing routing policy is certified, not redesigned.
+- Build success is not hardware certification; dark lanes remain unroutable.
+- Route loss uses cache miss and re-prefill/restart, never WAN cache migration.
+
+## Locked scope
+
+- Existing Meshnet Tracker routing, load balancing, billing, telemetry, relay, and provider semantics are backend-agnostic and are **not redesigned**. GGUF contributes exact compatibility, range/capacity, queue/load, seam-cost, health/reliability, and certification inputs only.
+- The data plane is a standalone project-owned C++ Shard worker with gRPC/Protobuf and a project-owned `ShardEngine` boundary.
+- llama.cpp is fetched at one exact commit into an ignored workspace from an in-repo manifest, then a numbered minimal patch stack is applied. There is no submodule, vendored tree, or permanent-fork dependency.
+- llama.cpp owns DeepSeek V4 graphs, mHC, MoE, attention, hash routing, and kernels. Meshnet adds only range-ownership hooks, typed boundary/local-state adapters, worker integration, and parity/certification.
+- Quantization and placement are dynamic recipe inputs. The 2–4 and 10+ stage layouts are certification scenarios, never product constants.
+- Per-shard Hot KV and V4 CSA/HCA/SWA/indexer/compressor state remain local and keyed by route session/epoch. The WAN seam carries the typed mHC 4×4096 residual boundary, positions, token-ID sideband where required, and schema/cache expectations—not per-layer caches.
+- Route changes use cache miss plus re-prefill/restart. There is no WAN KV or V4 auxiliary-cache migration.
+- CPU/CUDA/ROCm/Vulkan/Metal compile lanes are planned; only exact real-hardware-certified backend/model/recipe lanes may be advertised.
+- Alpha requires correctness and the pre-locked useful-speed gate. MTP is reserved and off for alpha; its ownership contract, implementation, and benchmark are required before beta.
+
+## Target identities
+
+- DeepSeek V4 official target SHA: `60d8d70770c6776ff598c94bb586a859a38244f1`.
+- llama.cpp V4 support lineage began at PR 24162 / merge `8c146a8366304c871efc26057cc90370ccf58dad`; DGR-027 later pins one exact validated current commit.
+- V4 scope: 43 main layers plus MTP; mHC 4×4096 boundary; 256 routed + 1 shared experts with six routed active; token IDs required for the first three hash-routed layers.
+- Exact split-GGUF artifacts are provisioned to mounted-drive storage with a complete hashed manifest and resumable verification; no model artifact may be placed under `/home`.

.scratch/distributed-gguf-runtime/evidence/DGR-001/BLOCKED.md

@@ -0,0 +1,43 @@
+# DGR-001 downstream stop-condition handoff
+
+Status: **DGR-001 is complete; native-track promotion is blocked by the immutable v1 verdict.**
+
+This is no longer an execution-prerequisite blocker. The required real benchmark
+ran successfully, every recipe completed at concurrency 1 and 4, artifacts were
+verified, and deterministic/full test gates passed.
+
+## Locked result
+
+`contract-evaluation.json` records:
+
+```text
+verdict: stop
+quality_lane_pass: false
+speed_benefit: true
+fit_benefit: true
+stop_condition_met: true
+```
+
+The exact-revision BF16 GGUF quality lane compared every prompt but achieved
+`0.3333` exact match and `0.9471` mean similarity against the Transformers BF16
+reference. V1 requires `0.90` and `0.97`. Quantized Q4_K_M had substantial speed
+and fit benefits, but the contract explicitly forbids speed from redeeming a
+failed near-lossless quality lane.
+
+## Scope of this stop
+
+The measured baseline is Qwen2.5-0.5B on CPU using a CPU-only llama.cpp build.
+It is not a Radeon, large-model, distributed, or native-shard result. Therefore:
+
+1. Do not silently mark v1 promoted or weaken its thresholds after observing the
+   data.
+2. Do not let DGR-004 or later runtime stories treat DGR-001 completion as a
+   positive promotion signal.
+3. A human may choose one of these explicit paths:
+   - stop the native GGUF track as v1 directs;
+   - diagnose and fix the BF16 runtime divergence, then rerun the exact v1 plan;
+   - authorize a separately versioned GPU/large-model contract whose scope and
+     workload are locked before its measurements.
+
+All raw evidence, configuration, artifacts, hashes, and reproduction commands
+are in this directory and `README.md`.

.scratch/distributed-gguf-runtime/evidence/DGR-001/README.md

@@ -0,0 +1,199 @@
+# DGR-001 — Safetensors versus GGUF performance contract
+
+Status: **complete; immutable v1 verdict is `stop`.**
+
+DGR-001 successfully produced a controlled local-real CPU baseline. Completion
+means the experiment and decision contract are durable and verified; it does
+**not** mean the native GGUF track is approved to continue. The locked quality
+gate failed, so dependent runtime work requires a human decision or a new,
+explicitly versioned experiment/contract rather than silently weakening v1.
+
+## Controlled workload
+
+- Model: `Qwen/Qwen2.5-0.5B-Instruct`
+- Exact source revision: `7ae557604adf67be50417f59c2c2f167def9a775`
+- Machine: `fedora`, Linux `7.0.14-101.fc43.x86_64`, 32 logical CPUs
+- Device: CPU for every recipe; VRAM is therefore correctly reported as zero
+- Runtime reference: Transformers `5.13.0`, PyTorch
+  `2.10.0+rocm7.13.0a20260513`, BF16 safetensors
+- GGUF runtime: llama.cpp version 9991, commit
+  `e920c523e3b8a0163fe498af5bf90df35ff51d25`
+- Workload: three fixed short/medium/long prompts, greedy sampling, 32 output
+  tokens, three repeats, two warmups, concurrency 1 and 4, 16 CPU threads
+- Evidence class: `local-real`
+
+All artifacts are beneath `/run/media/popov/DATA/llm/`; no model artifact was
+created under `/home`.
+
+## Recipes and exact artifacts
+
+| Recipe | Artifact | SHA-256 |
+|---|---|---|
+| Transformers BF16 reference | complete mounted Hugging Face snapshot | `e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6` |
+| llama.cpp BF16 quality lane | `Qwen2.5-0.5B-Instruct-7ae5576-BF16.gguf` | `e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862` |
+| llama.cpp Q4_K_M performance/fit lane | `Qwen2.5-0.5B-Instruct-7ae5576-Q4_K_M.gguf` | `a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5` |
+
+The snapshot digest covers every sorted relative path, resolved size, and file
+byte, so tokenizer/config drift is included. The BF16 GGUF was converted
+directly from the exact snapshot while preserving BF16 weights. Q4_K_M was
+quantized from an exact-revision F16 conversion with the pinned quantizer.
+Runtime validation recomputes every declared digest before model loading.
+
+## Real results
+
+All recipes completed every request with zero failures.
+
+| Metric | Transformers BF16 | llama.cpp BF16 | llama.cpp Q4_K_M |
+|---|---:|---:|---:|
+| Decode tok/s, c=1 | 40.8 | 98.5 | 207.7 |
+| Aggregate decode tok/s, c=4 | 46.5 | 222.8 | 195.7 |
+| TTFT p50, c=1 | 40.0 ms | 15.1 ms | 21.6 ms |
+| Peak resident memory, c=1 | 1.94 GB | 1.11 GB | 0.54 GB |
+| Artifact size | 1.00 GB | 0.99 GB | 0.40 GB |
+| Failures | 0 | 0 | 0 |
+
+Against the reference, the eligible Q4_K_M lane measured:
+
+- single-request decode speedup: **5.10×**;
+- concurrency-4 aggregate throughput speedup: **4.20×**;
+- resident-memory ratio: **0.279×**;
+- artifact-size ratio: **0.398×**.
+
+The near-lossless BF16 quality lane compared all three prompts but measured:
+
+- exact match: **0.3333** (v1 requires at least `0.90`);
+- mean text similarity: **0.9471** (v1 requires at least `0.97`).
+
+Tokenization and stopping were controlled: every runtime saw the same prompt
+token counts and reported 31 post-TTFT decode tokens. The v1 mismatch is a
+real greedy-output divergence on two prompts, not missing coverage or a
+text-length artifact. Its root cause remains undetermined; no post-contract
+logit-tie claim is acceptance evidence. Therefore `contract-evaluation.json`
+records:
+
+```text
+verdict: stop
+quality_lane_pass: false
+speed_benefit: true
+fit_benefit: true
+stop_condition_met: true
+```
+
+Thresholds were not changed after observing these results.
+
+## Post-contract parity and ROCm diagnostics
+
+`summarize-quality-parity.py` verifies and separates two signed sources. The CPU
+v1 row uses CPU kernels and a Transformers BF16 oracle; it remains at `0.3333`
+exact match with an unexplained divergence. The ROCm row uses a different plan,
+GPU kernels, and a Transformers float32 oracle. In that narrower diagnostic,
+the same BF16 GGUF artifact matches all three 32-token sequences exactly (`1.0`
+exact match and `1.0` similarity). No conversion corruption was observed in
+that three-sequence ROCm sample; this does not prove global conversion
+correctness or explain the CPU result.
+
+A separate HIP build at commit `e920c523` was compiled for `gfx1151` and
+measured `ROCm0: Radeon 8060S Graphics`; its `llama-server` SHA-256 is
+`b6bb4da687dbde86e243ba006cef05919b7b97255cd7e2371e1d451220aca139`.
+A signed `gpu-diagnostic` profile measured zero failures:
+
+| GPU metric | Transformers BF16 ROCm | llama.cpp Q4 ROCm | Q4 ratio |
+|---|---:|---:|---:|
+| Decode tok/s, c=1 | 81.12 | 251.25 | **3.10×** |
+| Aggregate decode tok/s, c=4 | 91.24 | 511.33 | **5.60×** |
+| TTFT p50, c=1 | 13.77 ms | 11.80 ms | **0.857×** |
+
+The GPU report is signed under the distinct
+`run_configured_gpu_diagnostic/v1` producer. The v1 evaluator rejects that
+producer even when its signature is valid. llama-server process VRAM remains
+unmeasured, so this diagnostic cannot replace or satisfy the immutable v1
+contract. Its signed backend detail records the measured `ROCm0: Radeon 8060S
+Graphics` device and `25/25` offloaded layers.
+
+## Implementation
+
+- `recipe_benchmark.py` provides the runtime-neutral measurement core, true
+  concurrency, continuous in-flight peak-memory sampling, percentile/throughput
+  aggregation, failures, and output drift.
+- `recipe_drivers.py` provides opt-in Transformers and llama-server drivers,
+  mounted-drive confinement, exact artifact/runtime verification, equal
+  device/thread budgets, greedy-only validation, measured host provenance, a
+  CPU-only v1 guard until process VRAM can be measured honestly, and a distinct
+  signed GPU diagnostic profile that the v1 evaluator cannot accept.
+- Peak RSS is runtime-scoped: Transformers reports growth above its pre-runtime
+  Python baseline, while llama.cpp reports its isolated server process tree.
+  Both are sampled continuously during in-flight requests.
+- TTFT uses each runtime's prompt/first-token compute boundary; end-to-end HTTP,
+  scheduling, and queue overhead remains in latency and `queue_wait_ms`.
+- The exact canonical plan SHA-256 locks prompts, model/revision, sampling,
+  output length, repeats, warmups, and concurrency. The evaluator also requires
+  equal prompt/decode token counts across recipes.
+- llama.cpp's `predicted_n` includes the first token while `predicted_ms` begins
+  after it; the driver subtracts that token so decode throughput matches the
+  Transformers inter-token convention.
+- `performance_contract.py` rejects wrong plans, unsigned or incorrectly signed
+  real evidence, wrong config/artifact/runtime/backend/host bindings, missing
+  recipes/concurrency, mixed model revisions, incomplete quality coverage, and
+  failed references.
+- Every non-synthetic report is Ed25519-signed over the complete canonical JSON,
+  including raw outcomes and metrics. The contract pins the public key and exact
+  config SHA-256; the private key remains outside Git at mode `0600`.
+- The signer fingerprint is independently anchored outside this evidence
+  directory in `../../trusted-evidence-signers.json` and checked by tests.
+- Quantized drift remains advisory. Only the near-lossless lane can satisfy the
+  quality gate, and only performance-fit recipes can earn speed/fit benefits.
+
+## Evidence files
+
+- `performance-contract.json` — immutable v1 thresholds and stop condition
+- `benchmark-config.json` — exact real-run plan, drivers, artifacts, and hashes
+- `results.json` — raw machine-readable per-request and aggregate evidence
+- `results.txt` — human-readable benchmark summary
+- `baseline.json` — distilled measurements for later comparison
+- `contract-evaluation.json` — fail-closed v1 verdict
+- `quality-parity-diagnosis.json` / `.md` — run/device-scoped signed-evidence summary
+- `summarize-quality-parity.py` — verifies both evidence chains and regenerates it
+- `gpu-diagnostic-config.json` — exact ROCm diagnostic artifacts and runtimes
+- `gpu-diagnostic-results.json` / `.txt` — signed GPU outcomes and summary
+- `commands.txt` — reproducible conversion, benchmark, evaluation, and test commands
+- `BLOCKED.md` — downstream stop-condition handoff
+- `known-unrelated-failure.md` — clean-base reproduction of the tracker race
+- `../../trusted-evidence-signers.json` — repository-reviewed signer fingerprint
+
+## Verification
+
+```text
+Targeted: 28 passed (5/5 consecutive focused runs)
+Latest full suite: 755 passed, 13 skipped
+Earlier full suite: 751 passed, 13 skipped
+Current cancellation retry matrix, DGR-001: 4/5 passed
+Earlier cancellation retry matrix, clean d904c40: 4/5 passed
+compileall: passed
+git diff --check: passed
+Evidence JSON parse/integrity checks: passed
+```
+
+The intermittent tracker cancellation race reproduced at the same rate on the
+clean base and is retained in `known-unrelated-failure.md`; the final full suite
+completed green. DGR-001 changes no tracker/proxy files.
+
+The earlier Ralph claim that the full suite was blocked by Protobuf 6.33.6 was
+invalid: it used Hermes Agent's internal venv. Verification above used the
+project `.venv`, which has the DGR-002-compatible runtime. Real inference used
+`.venv-rocm` Python 3.12.
+
+## Limitations and dependent-story handoff
+
+- The immutable contract result is a **0.5B CPU baseline**. The separate Radeon
+  diagnostic is real local GPU evidence, but neither result covers a large
+  model, distributed execution, network transport, or a native shard worker.
+- A separate `GGML_HIP=ON` llama.cpp build exists and produced GPU timings, but
+  llama-server process VRAM is not measurable by the current driver; GPU
+  memory/fit claims therefore remain ineligible for v1.
+- Absolute timings are developer-machine measurements; locked ratios and raw
+  artifacts are provided for reproducibility.
+- DGR-014 may consume v1 only with the exact plan/evidence requirements enforced
+  by `performance_contract.py`.
+- DGR-004 and later native-runtime work must not treat DGR-001 completion as a
+  promotion. V1 says `stop`; proceeding requires a human decision backed by a
+  separately versioned GPU/large-model contract or a diagnosed quality fix.

.scratch/distributed-gguf-runtime/evidence/DGR-001/baseline.json

@@ -0,0 +1,169 @@
+{
+  "artifact_sha256": {
+    "llama-cpp-near-lossless-quality": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+    "llama-cpp-quantized-performance-fit": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5",
+    "transformers-safetensors-reference": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6"
+  },
+  "backend_detail": {
+    "llama-cpp-near-lossless-quality": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
+    "llama-cpp-quantized-performance-fit": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
+    "transformers-safetensors-reference": "torch 2.10.0+rocm7.13.0a20260513; dtype bfloat16; device cpu; intra-op threads 16"
+  },
+  "evidence_class": "local-real",
+  "host": {
+    "accelerator_name": "Radeon 8060S Graphics",
+    "accelerator_runtime": "7.13.26183",
+    "benchmark_lane": "cpu-controlled-baseline",
+    "converter_sha256": "c819f18fb22927b49fabc3b35d1c9e21ee638b3817eccd1bd4efbcc7116eeb4d",
+    "cpu_count": 32,
+    "cuda_available": true,
+    "hostname": "fedora",
+    "llama_cpp_commit": "e920c523e3b8a0163fe498af5bf90df35ff51d25",
+    "llama_cpp_version": "9991",
+    "llama_server_identities": {
+      "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server": {
+        "sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+        "version": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64"
+      }
+    },
+    "llama_server_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+    "platform": "Linux-7.0.14-101.fc43.x86_64-x86_64-with-glibc2.42",
+    "python": "3.12.13",
+    "quantizer_sha256": "bd0cc8c7be6d48aad4755b31062e0e59a887cbadd43dbb8771853d5858bb198f",
+    "torch_version": "2.10.0+rocm7.13.0a20260513",
+    "transformers_version": "5.13.0"
+  },
+  "model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+  "model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+  "plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
+  "provenance": {
+    "completed_at": "2026-07-13T16:27:19.647692Z",
+    "config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
+    "producer": "meshnet_node.recipe_drivers.run_configured_benchmark/v1",
+    "run_id": "e4eedadf-22f6-4907-8990-985456961099",
+    "schema_version": 1,
+    "signature": "owev+/ToswP20C923G6E+srOCUBV5vrjmndVatr9CbTXakiFGqlHrTiEo+aymA4BcSwmG6KJTxlxO6WpLnpcAg==",
+    "signature_algorithm": "ed25519",
+    "signer_public_key_sha256": "8baca8742d9b3ed0c3fc54929c23f75ec8c1c739900aaf5334780d598ffa84de",
+    "started_at": "2026-07-13T16:26:22.361501Z"
+  },
+  "recipe_runtime": {
+    "llama-cpp-near-lossless-quality": {
+      "device": "cpu",
+      "runtime": "llama.cpp-9991-e920c523",
+      "weight_format": "gguf",
+      "weight_quantization": "bfloat16"
+    },
+    "llama-cpp-quantized-performance-fit": {
+      "device": "cpu",
+      "runtime": "llama.cpp-9991-e920c523",
+      "weight_format": "gguf",
+      "weight_quantization": "Q4_K_M"
+    },
+    "transformers-safetensors-reference": {
+      "device": "cpu",
+      "runtime": "transformers-5.13.0",
+      "weight_format": "safetensors",
+      "weight_quantization": "bfloat16"
+    }
+  },
+  "recipes": {
+    "llama-cpp-near-lossless-quality": {
+      "artifact_bytes": 994156448,
+      "available": true,
+      "concurrency": {
+        "1": {
+          "aggregate_decode_tokens_per_sec": 86.7339,
+          "decode_tokens_per_sec": 98.5178,
+          "failures": 0,
+          "latency_p50_ms": 333.023,
+          "latency_p95_ms": 383.0597,
+          "peak_rss_bytes": 1110728704,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 1717.9451,
+          "ttft_p50_ms": 15.069,
+          "ttft_p95_ms": 63.766
+        },
+        "4": {
+          "aggregate_decode_tokens_per_sec": 222.788,
+          "decode_tokens_per_sec": 76.6297,
+          "failures": 0,
+          "latency_p50_ms": 490.8738,
+          "latency_p95_ms": 646.26,
+          "peak_rss_bytes": 1139466240,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 859.8985,
+          "ttft_p50_ms": 32.445,
+          "ttft_p95_ms": 218.387
+        }
+      },
+      "device": "cpu",
+      "lane": "quality"
+    },
+    "llama-cpp-quantized-performance-fit": {
+      "artifact_bytes": 397807520,
+      "available": true,
+      "concurrency": {
+        "1": {
+          "aggregate_decode_tokens_per_sec": 139.2693,
+          "decode_tokens_per_sec": 207.712,
+          "failures": 0,
+          "latency_p50_ms": 168.3307,
+          "latency_p95_ms": 305.1338,
+          "peak_rss_bytes": 542081024,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 967.0195,
+          "ttft_p50_ms": 21.582,
+          "ttft_p95_ms": 147.859
+        },
+        "4": {
+          "aggregate_decode_tokens_per_sec": 195.6789,
+          "decode_tokens_per_sec": 76.9497,
+          "failures": 0,
+          "latency_p50_ms": 437.9196,
+          "latency_p95_ms": 885.5355,
+          "peak_rss_bytes": 573259776,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 572.4424,
+          "ttft_p50_ms": 48.127,
+          "ttft_p95_ms": 416.531
+        }
+      },
+      "device": "cpu",
+      "lane": "performance-fit"
+    },
+    "transformers-safetensors-reference": {
+      "artifact_bytes": 999586347,
+      "available": true,
+      "concurrency": {
+        "1": {
+          "aggregate_decode_tokens_per_sec": 35.4722,
+          "decode_tokens_per_sec": 40.7545,
+          "failures": 0,
+          "latency_p50_ms": 818.3864,
+          "latency_p95_ms": 1258.0673,
+          "peak_rss_bytes": 1941458944,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 625.6467,
+          "ttft_p50_ms": 40.0018,
+          "ttft_p95_ms": 195.2551
+        },
+        "4": {
+          "aggregate_decode_tokens_per_sec": 46.5375,
+          "decode_tokens_per_sec": 12.9506,
+          "failures": 0,
+          "latency_p50_ms": 2481.8662,
+          "latency_p95_ms": 3365.8395,
+          "peak_rss_bytes": 2104832000,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 264.0101,
+          "ttft_p50_ms": 97.0403,
+          "ttft_p95_ms": 429.0665
+        }
+      },
+      "device": "cpu",
+      "lane": "quality"
+    }
+  },
+  "reference_recipe_id": "transformers-safetensors-reference"
+}

.scratch/distributed-gguf-runtime/evidence/DGR-001/benchmark-config.json

@@ -0,0 +1,118 @@
+{
+  "artifact_storage_root": "/run/media/popov/DATA/llm",
+  "evidence_class": "local-real",
+  "host": {
+    "benchmark_lane": "cpu-controlled-baseline",
+    "llama_cpp_commit": "e920c523e3b8a0163fe498af5bf90df35ff51d25",
+    "llama_cpp_version": "9991",
+    "llama_server_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+    "converter_sha256": "c819f18fb22927b49fabc3b35d1c9e21ee638b3817eccd1bd4efbcc7116eeb4d",
+    "quantizer_sha256": "bd0cc8c7be6d48aad4755b31062e0e59a887cbadd43dbb8771853d5858bb198f",
+    "transformers_version": "5.13.0"
+  },
+  "plan": {
+    "plan_id": "dgr-001-controlled-whole-model-baseline-v1",
+    "model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+    "model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+    "prompts": [
+      {
+        "id": "short-fact",
+        "text": "The capital of France is",
+        "context_class": "short"
+      },
+      {
+        "id": "medium-code",
+        "text": "Complete this Python function without commentary:\n\ndef fibonacci(n):\n    \"\"\"Return the nth Fibonacci number for n >= 0.\"\"\"\n",
+        "context_class": "medium"
+      },
+      {
+        "id": "long-summary",
+        "text": "A distributed inference service divides a transformer across consumer machines. The tracker owns admission, routing, cancellation, accounting, and telemetry, while workers own only model execution. Every request carries an immutable model identity and revision. Workers must reject incompatible protocol versions and resource demands before allocating large buffers. Activation tensors are chunked, checksummed, bounded by negotiated limits, and propagated with explicit flow-control credits. A caller may disconnect at any time, so cancellation must release queued work, in-flight transfers, and cache reservations without double billing. Retries can occur after network failures, requiring idempotent request identifiers and deterministic completion accounting. The system keeps the existing safetensors path as a correctness reference while a native GGUF path is measured. Benchmarks compare the same prompts, output lengths, sampling policy, device, and concurrency, and they separate near-lossless quality checks from quantized speed and fit claims. Summarize the design priorities in three concise bullet points.",
+        "context_class": "long"
+      }
+    ],
+    "sampling": {
+      "temperature": 0.0,
+      "top_p": 1.0,
+      "top_k": 1,
+      "seed": 1234,
+      "max_output_tokens": 32
+    },
+    "concurrency_levels": [1, 4],
+    "repeats": 3,
+    "warmup_requests": 2
+  },
+  "recipes": [
+    {
+      "id": "transformers-safetensors-reference",
+      "runtime": "transformers-5.13.0",
+      "weight_format": "safetensors",
+      "weight_quantization": "bfloat16",
+      "lane": "quality",
+      "device": "cpu",
+      "artifact_path": "/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775",
+      "artifact_sha256": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": true,
+      "notes": "artifact_sha256 is the deterministic digest of every snapshot path and file byte",
+      "driver": {
+        "type": "transformers",
+        "model_path": "/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775",
+        "device": "cpu",
+        "dtype": "bfloat16",
+        "threads": 16
+      }
+    },
+    {
+      "id": "llama-cpp-near-lossless-quality",
+      "runtime": "llama.cpp-9991-e920c523",
+      "weight_format": "gguf",
+      "weight_quantization": "bfloat16",
+      "lane": "quality",
+      "device": "cpu",
+      "artifact_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-BF16.gguf",
+      "artifact_sha256": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": false,
+      "notes": "Converted directly from the exact mounted safetensors revision while preserving BF16 weights with pinned llama.cpp",
+      "driver": {
+        "type": "llama-cpp-server",
+        "binary": "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server",
+        "binary_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+        "gguf_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-BF16.gguf",
+        "device": "cpu",
+        "threads": 16,
+        "n_parallel": 4,
+        "context_per_slot": 512,
+        "n_gpu_layers": 0
+      }
+    },
+    {
+      "id": "llama-cpp-quantized-performance-fit",
+      "runtime": "llama.cpp-9991-e920c523",
+      "weight_format": "gguf",
+      "weight_quantization": "Q4_K_M",
+      "lane": "performance-fit",
+      "device": "cpu",
+      "artifact_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-Q4_K_M.gguf",
+      "artifact_sha256": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": false,
+      "notes": "Quantized from the exact-revision F16 GGUF with pinned llama-quantize",
+      "driver": {
+        "type": "llama-cpp-server",
+        "binary": "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server",
+        "binary_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+        "gguf_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-Q4_K_M.gguf",
+        "device": "cpu",
+        "threads": 16,
+        "n_parallel": 4,
+        "context_per_slot": 512,
+        "n_gpu_layers": 0
+      }
+    }
+  ]
+}

.scratch/distributed-gguf-runtime/evidence/DGR-001/commands.txt

@@ -0,0 +1,87 @@
+# Exact source snapshot (already present on mounted storage)
+SOURCE=/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775
+LLAMA=/run/media/popov/d/DEV/llamacpp/llama.cpp
+ROCM_PY=/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv-rocm/bin/python
+PROJECT_PY=/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python
+OUT=/run/media/popov/DATA/llm/dgr-001
+SIGNING_KEY=/home/popov/.config/neuron-tai/keys/dgr-001-evidence-ed25519.pem
+
+# Private signing key is outside Git and must remain owner-only
+stat -c '%a %n' "$SIGNING_KEY"  # expected: 600
+
+# Converter support check (no writes)
+$ROCM_PY $LLAMA/convert_hf_to_gguf.py "$SOURCE" --outtype f16 --outfile "$OUT/Qwen2.5-0.5B-Instruct-7ae5576-F16.gguf" --dry-run
+
+# Exact-revision near-lossless and performance-fit artifacts
+$ROCM_PY $LLAMA/convert_hf_to_gguf.py "$SOURCE" --outtype f16 --outfile "$OUT/Qwen2.5-0.5B-Instruct-7ae5576-F16.gguf"
+$LLAMA/build/bin/llama-quantize "$OUT/Qwen2.5-0.5B-Instruct-7ae5576-F16.gguf" "$OUT/Qwen2.5-0.5B-Instruct-7ae5576-Q4_K_M.gguf" Q4_K_M
+$ROCM_PY $LLAMA/convert_hf_to_gguf.py "$SOURCE" --outtype bf16 --outfile "$OUT/Qwen2.5-0.5B-Instruct-7ae5576-BF16.gguf"
+
+# Runtime and artifact identity
+git -C "$LLAMA" rev-parse HEAD
+$LLAMA/build/bin/llama-server --version
+sha256sum "$LLAMA/build/bin/llama-server" "$LLAMA/convert_hf_to_gguf.py" "$LLAMA/build/bin/llama-quantize"
+sha256sum "$SOURCE/model.safetensors" "$OUT/Qwen2.5-0.5B-Instruct-7ae5576-BF16.gguf" "$OUT/Qwen2.5-0.5B-Instruct-7ae5576-Q4_K_M.gguf"
+
+# Deterministic complete-snapshot digest used by benchmark-config.json
+PYTHONPATH=packages/node $ROCM_PY - <<'PY'
+from pathlib import Path
+from meshnet_node.recipe_drivers import _artifact_sha256
+print(_artifact_sha256(Path('/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775')))
+PY
+
+# Canonical opt-in local-real benchmark
+MESHNET_ENABLE_REAL_INFERENCE_TESTS=1 MESHNET_EVIDENCE_SIGNING_KEY="$SIGNING_KEY" \
+  PYTHONPATH=packages/node $ROCM_PY -m meshnet_node.recipe_benchmark \
+  --config .scratch/distributed-gguf-runtime/evidence/DGR-001/benchmark-config.json \
+  --json-out .scratch/distributed-gguf-runtime/evidence/DGR-001/results.json \
+  --summary-out .scratch/distributed-gguf-runtime/evidence/DGR-001/results.txt
+
+# Distil the baseline and evaluate immutable v1
+PYTHONPATH=packages/node $PROJECT_PY - <<'PY'
+from pathlib import Path
+import json
+from meshnet_node.performance_contract import baseline_from_report, evaluate_contract, load_contract
+root = Path('.scratch/distributed-gguf-runtime/evidence/DGR-001')
+report = json.loads((root / 'results.json').read_text())
+contract = load_contract(root / 'performance-contract.json')
+(root / 'baseline.json').write_text(json.dumps(baseline_from_report(report), indent=2, sort_keys=True) + '\n')
+(root / 'contract-evaluation.json').write_text(json.dumps(evaluate_contract(contract, report).to_dict(), indent=2, sort_keys=True) + '\n')
+PY
+
+# Optional ROCm GPU diagnostic (not eligible for immutable v1)
+# The version-matched rocm[devel] wheel expands beyond 20 GB; ensure sufficient
+# space or relocate its packaged payload before installation.
+uv pip install --python "$ROCM_PY" --prerelease=allow \
+  --index-url https://rocm.nightlies.amd.com/v2/gfx1151/ \
+  'rocm[devel]==7.13.0a20260513'
+ROCM_VENV=/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv-rocm
+ROCM_SDK="$ROCM_VENV/bin/rocm-sdk"
+ROCM_ROOT="$($ROCM_SDK path --root)"
+ROCM_BIN="$($ROCM_SDK path --bin)"
+export PATH="$ROCM_VENV/bin:$ROCM_BIN:$PATH"
+export ROCM_PATH="$ROCM_ROOT" HIP_PATH="$ROCM_ROOT"
+export CMAKE_PREFIX_PATH="$($ROCM_SDK path --cmake):$ROCM_ROOT"
+export LD_LIBRARY_PATH="$ROCM_ROOT/lib:$ROCM_ROOT/lib64:${LD_LIBRARY_PATH:-}"
+$ROCM_VENV/bin/cmake -S /run/media/popov/d/DEV/llamacpp/llama.cpp \
+  -B /run/media/popov/d/DEV/llamacpp/llama.cpp/build-hip -G Ninja \
+  -DGGML_HIP=ON -DGPU_TARGETS=gfx1151 \
+  -DCMAKE_HIP_COMPILER="$ROCM_VENV/bin/amdclang++" \
+  -DCMAKE_BUILD_TYPE=Release -DLLAMA_BUILD_TESTS=OFF \
+  -DLLAMA_BUILD_EXAMPLES=ON -DLLAMA_BUILD_SERVER=ON
+$ROCM_VENV/bin/cmake --build /run/media/popov/d/DEV/llamacpp/llama.cpp/build-hip \
+  --target llama-server llama-cli llama-bench -j 16
+MESHNET_ENABLE_REAL_INFERENCE_TESTS=1 MESHNET_EVIDENCE_SIGNING_KEY="$SIGNING_KEY" \
+  PYTHONPATH=packages/node $ROCM_PY -m meshnet_node.recipe_benchmark \
+  --profile gpu-diagnostic \
+  --config .scratch/distributed-gguf-runtime/evidence/DGR-001/gpu-diagnostic-config.json \
+  --json-out .scratch/distributed-gguf-runtime/evidence/DGR-001/gpu-diagnostic-results.json \
+  --summary-out .scratch/distributed-gguf-runtime/evidence/DGR-001/gpu-diagnostic-results.txt
+PYTHONPATH=packages/node $PROJECT_PY \
+  .scratch/distributed-gguf-runtime/evidence/DGR-001/summarize-quality-parity.py
+
+# Deterministic verification
+PYTHONPATH=packages/node $PROJECT_PY -m pytest -q tests/test_recipe_benchmark.py
+PYTHONPATH=packages/node $PROJECT_PY -m pytest -q
+PYTHONPATH=packages/node $PROJECT_PY -m compileall -q packages tests
+git diff --check

.scratch/distributed-gguf-runtime/evidence/DGR-001/contract-evaluation.json

@@ -0,0 +1,71 @@
+{
+  "contract_version": 1,
+  "fit_benefit": true,
+  "plan_id": "dgr-001-controlled-whole-model-baseline-v1",
+  "quality_lane_pass": false,
+  "rationale": [
+    "the near-lossless quality lane failed: the GGUF runtime disagrees with the safetensors reference beyond what near-lossless weights can explain",
+    "a meaningful speed benefit was measured",
+    "a meaningful fit benefit was measured"
+  ],
+  "recipes": [
+    {
+      "comparable": true,
+      "failures": 0,
+      "fit_benefit": false,
+      "incomparable_reason": "",
+      "lane": "quality",
+      "measurements": {
+        "aggregate_concurrency": 4,
+        "aggregate_throughput_speedup": 4.7873,
+        "artifact_size_ratio": 0.9946,
+        "artifact_size_win": false,
+        "compared_prompts": 3,
+        "decode_speedup": 2.4173,
+        "exact_match_rate": 0.3333,
+        "expected_prompts": 3,
+        "failure_rate": 0.0,
+        "mean_similarity": 0.9471,
+        "resident_memory_ratio": 0.5721,
+        "ttft_ratio": 0.3767
+      },
+      "quality_pass": false,
+      "reasons": [
+        "single-request decode 2.42x reference (>= 1.25x) at TTFT ratio 0.38",
+        "aggregate throughput at concurrency 4 is 4.79x reference (>= 1.25x)",
+        "peak resident memory is 0.57x reference (<= 0.75x)",
+        "quality lane exact-match 0.33 / similarity 0.947 versus the reference (fail)"
+      ],
+      "recipe_id": "llama-cpp-near-lossless-quality",
+      "speed_benefit": false
+    },
+    {
+      "comparable": true,
+      "failures": 0,
+      "fit_benefit": true,
+      "incomparable_reason": "",
+      "lane": "performance-fit",
+      "measurements": {
+        "aggregate_concurrency": 4,
+        "aggregate_throughput_speedup": 4.2048,
+        "artifact_size_ratio": 0.398,
+        "artifact_size_win": true,
+        "decode_speedup": 5.0967,
+        "failure_rate": 0.0,
+        "resident_memory_ratio": 0.2792,
+        "ttft_ratio": 0.5395
+      },
+      "quality_pass": null,
+      "reasons": [
+        "single-request decode 5.10x reference (>= 1.25x) at TTFT ratio 0.54",
+        "aggregate throughput at concurrency 4 is 4.20x reference (>= 1.25x)",
+        "peak resident memory is 0.28x reference (<= 0.75x)"
+      ],
+      "recipe_id": "llama-cpp-quantized-performance-fit",
+      "speed_benefit": true
+    }
+  ],
+  "speed_benefit": true,
+  "stop_condition_met": true,
+  "verdict": "stop"
+}

.scratch/distributed-gguf-runtime/evidence/DGR-001/gpu-diagnostic-config.json

@@ -0,0 +1,143 @@
+{
+  "artifact_storage_root": "/run/media/popov/DATA/llm",
+  "evidence_class": "local-real",
+  "host": {
+    "benchmark_lane": "rocm-gpu-diagnostic",
+    "llama_cpp_commit": "e920c523e3b8a0163fe498af5bf90df35ff51d25",
+    "llama_cpp_version": "9991",
+    "llama_server_sha256": "b6bb4da687dbde86e243ba006cef05919b7b97255cd7e2371e1d451220aca139",
+    "converter_sha256": "c819f18fb22927b49fabc3b35d1c9e21ee638b3817eccd1bd4efbcc7116eeb4d",
+    "quantizer_sha256": "bd0cc8c7be6d48aad4755b31062e0e59a887cbadd43dbb8771853d5858bb198f",
+    "transformers_version": "5.13.0",
+    "rocm_target": "gfx1151"
+  },
+  "plan": {
+    "plan_id": "dgr-001-rocm-gpu-diagnostic-v1",
+    "model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+    "model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+    "prompts": [
+      {
+        "id": "short-fact",
+        "text": "The capital of France is",
+        "context_class": "short"
+      },
+      {
+        "id": "medium-code",
+        "text": "Complete this Python function without commentary:\n\ndef fibonacci(n):\n    \"\"\"Return the nth Fibonacci number for n >= 0.\"\"\"\n",
+        "context_class": "medium"
+      },
+      {
+        "id": "long-summary",
+        "text": "A distributed inference service divides a transformer across consumer machines. The tracker owns admission, routing, cancellation, accounting, and telemetry, while workers own only model execution. Every request carries an immutable model identity and revision. Workers must reject incompatible protocol versions and resource demands before allocating large buffers. Activation tensors are chunked, checksummed, bounded by negotiated limits, and propagated with explicit flow-control credits. A caller may disconnect at any time, so cancellation must release queued work, in-flight transfers, and cache reservations without double billing. Retries can occur after network failures, requiring idempotent request identifiers and deterministic completion accounting. The system keeps the existing safetensors path as a correctness reference while a native GGUF path is measured. Benchmarks compare the same prompts, output lengths, sampling policy, device, and concurrency, and they separate near-lossless quality checks from quantized speed and fit claims. Summarize the design priorities in three concise bullet points.",
+        "context_class": "long"
+      }
+    ],
+    "sampling": {
+      "temperature": 0.0,
+      "top_p": 1.0,
+      "top_k": 1,
+      "seed": 1234,
+      "max_output_tokens": 32
+    },
+    "concurrency_levels": [
+      1,
+      4
+    ],
+    "repeats": 3,
+    "warmup_requests": 2
+  },
+  "recipes": [
+    {
+      "id": "transformers-fp32-rocm-quality-oracle",
+      "runtime": "transformers-5.13.0-rocm-float32",
+      "weight_format": "safetensors",
+      "weight_quantization": "bfloat16-weights-float32-accumulation",
+      "lane": "quality",
+      "device": "cuda",
+      "artifact_path": "/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775",
+      "artifact_sha256": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": true,
+      "notes": "artifact_sha256 is the deterministic digest of every snapshot path and file byte",
+      "driver": {
+        "type": "transformers",
+        "model_path": "/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775",
+        "device": "cuda",
+        "dtype": "float32",
+        "threads": 16
+      }
+    },
+    {
+      "id": "llama-cpp-bf16-rocm-quality",
+      "runtime": "llama.cpp-9991-e920c523-rocm-gfx1151",
+      "weight_format": "gguf",
+      "weight_quantization": "bfloat16",
+      "lane": "quality",
+      "device": "cuda",
+      "artifact_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-BF16.gguf",
+      "artifact_sha256": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": false,
+      "notes": "Converted directly from the exact mounted safetensors revision while preserving BF16 weights with pinned llama.cpp",
+      "driver": {
+        "type": "llama-cpp-server",
+        "binary": "/run/media/popov/d/DEV/llamacpp/llama.cpp/build-hip/bin/llama-server",
+        "binary_sha256": "b6bb4da687dbde86e243ba006cef05919b7b97255cd7e2371e1d451220aca139",
+        "gguf_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-BF16.gguf",
+        "device": "cuda",
+        "threads": 16,
+        "n_parallel": 4,
+        "context_per_slot": 512,
+        "n_gpu_layers": 99
+      }
+    },
+    {
+      "id": "transformers-bf16-rocm-throughput",
+      "runtime": "transformers-5.13.0-rocm-bfloat16",
+      "weight_format": "safetensors",
+      "weight_quantization": "bfloat16",
+      "lane": "performance-fit",
+      "device": "cuda",
+      "artifact_path": "/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775",
+      "artifact_sha256": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": false,
+      "notes": "artifact_sha256 is the deterministic digest of every snapshot path and file byte",
+      "driver": {
+        "type": "transformers",
+        "model_path": "/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775",
+        "device": "cuda",
+        "dtype": "bfloat16",
+        "threads": 16
+      }
+    },
+    {
+      "id": "llama-cpp-q4-rocm-throughput",
+      "runtime": "llama.cpp-9991-e920c523-rocm-gfx1151",
+      "weight_format": "gguf",
+      "weight_quantization": "Q4_K_M",
+      "lane": "performance-fit",
+      "device": "cuda",
+      "artifact_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-Q4_K_M.gguf",
+      "artifact_sha256": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": false,
+      "notes": "Quantized from the exact-revision F16 GGUF with pinned llama-quantize",
+      "driver": {
+        "type": "llama-cpp-server",
+        "binary": "/run/media/popov/d/DEV/llamacpp/llama.cpp/build-hip/bin/llama-server",
+        "binary_sha256": "b6bb4da687dbde86e243ba006cef05919b7b97255cd7e2371e1d451220aca139",
+        "gguf_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-Q4_K_M.gguf",
+        "device": "cuda",
+        "threads": 16,
+        "n_parallel": 4,
+        "context_per_slot": 512,
+        "n_gpu_layers": 99
+      }
+    }
+  ]
+}

.scratch/distributed-gguf-runtime/evidence/DGR-001/gpu-diagnostic-results.txt

@@ -0,0 +1,13 @@
+Recipe benchmark dgr-001-rocm-gpu-diagnostic-v1 (local-real)
+model Qwen/Qwen2.5-0.5B-Instruct@7ae557604adf67be50417f59c2c2f167def9a775
+transformers-fp32-rocm-quality-oracle  [quality         ] c= 1 ttft p50/p95     11.0/    35.5 ms; prefill  5746.7 tok/s; decode   35.7 tok/s; aggregate    29.6 tok/s; rss  1.39 GB; vram  2.26 GB; artifact  1.00 GB; failures 0
+transformers-fp32-rocm-quality-oracle  [quality         ] c= 4 ttft p50/p95     27.5/    80.4 ms; prefill  1985.4 tok/s; decode    9.4 tok/s; aggregate    35.4 tok/s; rss  1.39 GB; vram  2.74 GB; artifact  1.00 GB; failures 0
+llama-cpp-bf16-rocm-quality            [quality         ] c= 1 ttft p50/p95     13.2/    83.4 ms; prefill  4154.4 tok/s; decode  148.0 tok/s; aggregate   127.4 tok/s; rss  0.84 GB; vram  0.00 GB; artifact  0.99 GB; failures 0
+llama-cpp-bf16-rocm-quality            [quality         ] c= 4 ttft p50/p95     25.1/    52.1 ms; prefill  2205.4 tok/s; decode  115.1 tok/s; aggregate   337.1 tok/s; rss  0.86 GB; vram  0.00 GB; artifact  0.99 GB; failures 0
+transformers-bf16-rocm-throughput      [performance-fit ] c= 1 ttft p50/p95     13.8/    22.2 ms; prefill  4787.3 tok/s; decode   81.1 tok/s; aggregate    73.5 tok/s; rss  0.07 GB; vram  2.74 GB; artifact  1.00 GB; failures 0
+transformers-bf16-rocm-throughput      [performance-fit ] c= 4 ttft p50/p95     29.7/    58.5 ms; prefill  2666.5 tok/s; decode   24.4 tok/s; aggregate    91.2 tok/s; rss  0.07 GB; vram  2.74 GB; artifact  1.00 GB; failures 0
+llama-cpp-q4-rocm-throughput           [performance-fit ] c= 1 ttft p50/p95     11.8/    37.1 ms; prefill  4219.3 tok/s; decode  251.2 tok/s; aggregate   200.1 tok/s; rss  0.69 GB; vram  0.00 GB; artifact  0.40 GB; failures 0
+llama-cpp-q4-rocm-throughput           [performance-fit ] c= 4 ttft p50/p95     21.4/   101.0 ms; prefill  2126.9 tok/s; decode  189.7 tok/s; aggregate   511.3 tok/s; rss  0.72 GB; vram  0.00 GB; artifact  0.40 GB; failures 0
+drift llama-cpp-bf16-rocm-quality      vs transformers-fp32-rocm-quality-oracle exact 1.00; similarity 1.000 (gated)
+drift transformers-bf16-rocm-throughput vs transformers-fp32-rocm-quality-oracle exact 0.33; similarity 0.946 (advisory)
+drift llama-cpp-q4-rocm-throughput     vs transformers-fp32-rocm-quality-oracle exact 0.00; similarity 0.628 (advisory)

.scratch/distributed-gguf-runtime/evidence/DGR-001/known-unrelated-failure.md

@@ -0,0 +1,55 @@
+# Observed pre-existing intermittent tracker race
+
+This file records an unrelated timing observation and its repeated reproduction;
+it is **not** a DGR-001 benchmark/contract failure.
+
+Test:
+
+```text
+tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
+```
+
+One earlier full-suite run produced:
+
+```text
+1 failed, 745 passed, 13 skipped
+```
+
+A five-run isolated retry matrix reproduced the same rate repeatedly:
+
+```text
+current DGR-001 branch: 4/5 passed, 1/5 failed
+clean d904c40:          4/5 passed, 1/5 failed
+```
+
+An earlier full-suite run on the signed-provenance DGR-001 state completed
+green:
+
+```text
+751 passed, 13 skipped
+```
+
+Two full-suite runs after adding the isolated GPU diagnostic profile each hit
+the same race and otherwise passed:
+
+```text
+1 failed, 750 passed, 13 skipped
+```
+
+The latest expanded hardening suite hit the same race and otherwise passed:
+
+```text
+1 failed, 754 passed, 13 skipped
+```
+
+The final hardened state subsequently completed a full green run:
+
+```text
+755 passed, 13 skipped
+```
+
+In each failure, the mock upstream's three-second release timeout completed the
+stream before the cancel POST, so the request was already absent and the cancel
+endpoint returned 404. No tracker/proxy file changed in DGR-001. The race is
+therefore timing-sensitive, pre-existing, and unrelated to the benchmark,
+provenance, or GPU-diagnostic code.

.scratch/distributed-gguf-runtime/evidence/DGR-001/performance-contract.json

@@ -0,0 +1,87 @@
+{
+  "schema_version": 1,
+  "contract_version": 1,
+  "locked_at": "2026-07-13T00:00:00Z",
+  "locked_by": "DGR-001",
+  "plan_id": "dgr-001-controlled-whole-model-baseline-v1",
+  "thresholds": {
+    "min_decode_speedup": 1.25,
+    "max_ttft_ratio": 1.25,
+    "min_aggregate_throughput_speedup": 1.25,
+    "max_resident_memory_ratio": 0.75,
+    "max_artifact_size_ratio": 0.6,
+    "min_quality_exact_match_rate": 0.9,
+    "min_quality_mean_similarity": 0.97,
+    "max_failure_rate": 0.0
+  },
+  "baseline": {
+    "status": "pending-real-evidence",
+    "required_evidence_class": "local-real",
+    "required_recipes": [
+      "transformers-safetensors-reference",
+      "llama-cpp-near-lossless-quality",
+      "llama-cpp-quantized-performance-fit"
+    ],
+    "required_concurrency_levels": [
+      1,
+      4
+    ],
+    "required_controlled_variables": [
+      "model architecture",
+      "model revision",
+      "machine and device",
+      "formatted prompts and context lengths",
+      "output length and greedy sampling policy"
+    ],
+    "required_plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
+    "minimum_prompt_count": 3,
+    "minimum_repeats": 3,
+    "minimum_output_tokens": 32,
+    "required_device": "cpu",
+    "required_config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
+    "required_signer_public_key": "zQ/qRMwF/ydazzaxEI24Xvnrl5bZxzw16JYpP0bfRuI=",
+    "required_artifact_sha256": {
+      "transformers-safetensors-reference": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6",
+      "llama-cpp-near-lossless-quality": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+      "llama-cpp-quantized-performance-fit": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5"
+    },
+    "required_recipe_runtime": {
+      "transformers-safetensors-reference": {
+        "runtime": "transformers-5.13.0",
+        "weight_format": "safetensors",
+        "weight_quantization": "bfloat16",
+        "device": "cpu"
+      },
+      "llama-cpp-near-lossless-quality": {
+        "runtime": "llama.cpp-9991-e920c523",
+        "weight_format": "gguf",
+        "weight_quantization": "bfloat16",
+        "device": "cpu"
+      },
+      "llama-cpp-quantized-performance-fit": {
+        "runtime": "llama.cpp-9991-e920c523",
+        "weight_format": "gguf",
+        "weight_quantization": "Q4_K_M",
+        "device": "cpu"
+      }
+    },
+    "required_backend_detail": {
+      "transformers-safetensors-reference": "torch 2.10.0+rocm7.13.0a20260513; dtype bfloat16; device cpu; intra-op threads 16",
+      "llama-cpp-near-lossless-quality": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
+      "llama-cpp-quantized-performance-fit": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0"
+    },
+    "required_host_identity": {
+      "python": "3.12.13",
+      "torch_version": "2.10.0+rocm7.13.0a20260513",
+      "transformers_version": "5.13.0",
+      "llama_server_identities": {
+        "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server": {
+          "sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+          "version": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64"
+        }
+      }
+    }
+  },
+  "stop_condition": "Stop the native llama.cpp/GGUF track when, on the same machine and device as the Transformers/safetensors reference and under this plan, no performance-fit GGUF recipe delivers either a meaningful speed benefit (>=25% higher single-request decode tokens/sec without a >25% worse TTFT, or >=25% higher aggregate throughput under concurrency) or a meaningful fit benefit (>=25% lower peak resident memory), or when the near-lossless quality lane fails, which indicates a broken runtime rather than a quantization trade-off.",
+  "notes": "Quantized performance-fit output drift is reported as advisory only. It is not numerical-equivalence evidence. DGR-014 consumes this immutable v1 contract. Non-synthetic evidence must be Ed25519-signed by the pinned key and match the exact locked config, artifacts, runtimes, backends, and host runtime identity."
+}

.scratch/distributed-gguf-runtime/evidence/DGR-001/quality-parity-diagnosis.json

@@ -0,0 +1,47 @@
+{
+  "conclusion": {
+    "conversion_corruption_observed_in_rocm_sample": false,
+    "cpu_bf16_divergence_explained": false,
+    "recommended_v2_design": "Predeclare a float32 quality oracle separately from the BF16 performance reference, with a larger prompt corpus and immutable thresholds.",
+    "scope": "The ROCm diagnostic establishes only that the same BF16 GGUF artifact matched the float32 oracle for three GPU sequences; it does not explain the CPU BF16 divergence or prove global conversion correctness.",
+    "v1_verdict_changed": false
+  },
+  "cpu_v1": {
+    "candidate": "llama.cpp BF16 GGUF",
+    "candidate_artifact_sha256": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+    "config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
+    "contract_verdict": "stop",
+    "device": "cpu",
+    "exact_match_rate": 0.3333,
+    "mean_similarity": 0.9471,
+    "plan_id": "dgr-001-controlled-whole-model-baseline-v1",
+    "plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
+    "quality_oracle": "Transformers BF16 safetensors",
+    "report": "results.json",
+    "report_sha256": "5d99a58806f39821c9206728047b8c5d605027d8a41b88639089b2418da890b5",
+    "root_cause": "undetermined; no logit-tie claim is acceptance evidence",
+    "run_id": "e4eedadf-22f6-4907-8990-985456961099"
+  },
+  "model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+  "model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+  "rocm_diagnostic": {
+    "candidate": "llama.cpp BF16 GGUF",
+    "candidate_artifact_sha256": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+    "config_sha256": "b0f0c846c818f1307d034cee1f81daa311efc20985c32a4cdbbbd8ffe4153892",
+    "device": "cuda (ROCm)",
+    "exact_match_rate": 1.0,
+    "failures": 0,
+    "mean_similarity": 1.0,
+    "measured_backend_detail": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 b6bb4da687dbde86e243ba006cef05919b7b97255cd7e2371e1d451220aca139; threads 16; parallel slots 4; ctx/slot 512; requested gpu layers 99; measured accelerator ROCm0: Radeon 8060S Graphics; measured offload 25/25 layers",
+    "plan_id": "dgr-001-rocm-gpu-diagnostic-v1",
+    "plan_sha256": "dae8e40963588f71f5d201fd163d39bd762e392544b5603d483e90d21abee2e8",
+    "producer": "meshnet_node.recipe_drivers.run_configured_gpu_diagnostic/v1",
+    "quality_oracle": "Transformers float32 safetensors",
+    "report": "gpu-diagnostic-results.json",
+    "report_sha256": "527b33d03627d57d60b30331e6b9119f579a828d6f6acb5c74ca25bab0af5f3d",
+    "run_id": "31bf44e7-ccd4-4277-84ac-c775dee65411",
+    "signer_fingerprint": "8baca8742d9b3ed0c3fc54929c23f75ec8c1c739900aaf5334780d598ffa84de",
+    "v1_eligible": false
+  },
+  "schema_version": 2
+}

.scratch/distributed-gguf-runtime/evidence/DGR-001/quality-parity-diagnosis.md

@@ -0,0 +1,31 @@
+# DGR-001 quality-parity evidence summary
+
+This summary is generated by `summarize-quality-parity.py` from signed reports.
+It contains no independent logit measurements or self-asserted verification flag.
+
+| Source | Device | Quality oracle | BF16 GGUF candidate | Exact | Similarity | Status |
+|---|---|---|---|---:|---:|---|
+| CPU v1 (`e4eedadf-22f6-4907-8990-985456961099`) | CPU | Transformers BF16 | llama.cpp BF16 | 0.3333 | 0.9471 | immutable `stop` |
+| ROCm diagnostic (`31bf44e7-ccd4-4277-84ac-c775dee65411`) | ROCm0 / Radeon 8060S | Transformers float32 | llama.cpp BF16 | 1.0000 | 1.0000 | diagnostic only |
+
+## Interpretation
+
+The CPU and ROCm rows use different plans, devices, kernels, and quality oracles.
+The CPU BF16 divergence remains unexplained and v1 remains `stop`. The signed
+ROCm report establishes the narrower fact that the same BF16 GGUF artifact
+matched the float32 oracle for all three GPU sequences with zero failures.
+Its signed backend detail records `ROCm0: Radeon 8060S Graphics` and measured
+`25/25` layer offload.
+
+No conversion corruption was observed in that three-sequence ROCm sample. This
+does not prove global conversion correctness and does not retroactively change
+or explain the CPU result. A future v2 should predeclare a float32 quality oracle
+separately from its BF16 performance reference and use a larger corpus.
+
+## Reproduction and bindings
+
+- CPU report SHA-256: `5d99a58806f39821c9206728047b8c5d605027d8a41b88639089b2418da890b5`
+- GPU report SHA-256: `527b33d03627d57d60b30331e6b9119f579a828d6f6acb5c74ca25bab0af5f3d`
+- BF16 GGUF SHA-256: `e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862`
+- Signer fingerprint: `8baca8742d9b3ed0c3fc54929c23f75ec8c1c739900aaf5334780d598ffa84de`
+- Exact verification command: see `commands.txt`.

.scratch/distributed-gguf-runtime/evidence/DGR-001/results.txt

@@ -0,0 +1,10 @@
+Recipe benchmark dgr-001-controlled-whole-model-baseline-v1 (local-real)
+model Qwen/Qwen2.5-0.5B-Instruct@7ae557604adf67be50417f59c2c2f167def9a775
+transformers-safetensors-reference     [quality         ] c= 1 ttft p50/p95     40.0/   195.3 ms; prefill   625.6 tok/s; decode   40.8 tok/s; aggregate    35.5 tok/s; rss  1.94 GB; vram  0.00 GB; artifact  1.00 GB; failures 0
+transformers-safetensors-reference     [quality         ] c= 4 ttft p50/p95     97.0/   429.1 ms; prefill   264.0 tok/s; decode   13.0 tok/s; aggregate    46.5 tok/s; rss  2.10 GB; vram  0.00 GB; artifact  1.00 GB; failures 0
+llama-cpp-near-lossless-quality        [quality         ] c= 1 ttft p50/p95     15.1/    63.8 ms; prefill  1717.9 tok/s; decode   98.5 tok/s; aggregate    86.7 tok/s; rss  1.11 GB; vram  0.00 GB; artifact  0.99 GB; failures 0
+llama-cpp-near-lossless-quality        [quality         ] c= 4 ttft p50/p95     32.4/   218.4 ms; prefill   859.9 tok/s; decode   76.6 tok/s; aggregate   222.8 tok/s; rss  1.14 GB; vram  0.00 GB; artifact  0.99 GB; failures 0
+llama-cpp-quantized-performance-fit    [performance-fit ] c= 1 ttft p50/p95     21.6/   147.9 ms; prefill   967.0 tok/s; decode  207.7 tok/s; aggregate   139.3 tok/s; rss  0.54 GB; vram  0.00 GB; artifact  0.40 GB; failures 0
+llama-cpp-quantized-performance-fit    [performance-fit ] c= 4 ttft p50/p95     48.1/   416.5 ms; prefill   572.4 tok/s; decode   76.9 tok/s; aggregate   195.7 tok/s; rss  0.57 GB; vram  0.00 GB; artifact  0.40 GB; failures 0
+drift llama-cpp-near-lossless-quality  vs transformers-safetensors-reference exact 0.33; similarity 0.947 (gated)
+drift llama-cpp-quantized-performance-fit vs transformers-safetensors-reference exact 0.00; similarity 0.456 (advisory)

.scratch/distributed-gguf-runtime/evidence/DGR-001/summarize-quality-parity.py

@@ -0,0 +1,261 @@
+#!/usr/bin/env python3
+"""Build the DGR-001 parity summary from cryptographically verified reports."""
+
+from __future__ import annotations
+
+import base64
+import hashlib
+import json
+from pathlib import Path
+
+from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PublicKey
+
+from meshnet_node.performance_contract import (
+    _canonical_sha256,
+    evaluate_contract,
+    load_contract,
+    report_signing_payload,
+)
+
+ROOT = Path(__file__).resolve().parent
+
+
+def _read(name: str) -> dict:
+    return json.loads((ROOT / name).read_text(encoding="utf-8"))
+
+
+def _file_sha256(name: str) -> str:
+    return hashlib.sha256((ROOT / name).read_bytes()).hexdigest()
+
+
+def _drift(report: dict, recipe_id: str) -> dict:
+    return next(item for item in report["drift"] if item["recipe_id"] == recipe_id)
+
+
+def _recipe(report: dict, recipe_id: str) -> dict:
+    return next(item for item in report["recipes"] if item["recipe"]["id"] == recipe_id)
+
+
+def main() -> None:
+    contract = load_contract(ROOT / "performance-contract.json")
+    cpu_report = _read("results.json")
+    gpu_config = _read("gpu-diagnostic-config.json")
+    gpu_report = _read("gpu-diagnostic-results.json")
+
+    cpu_evaluation = evaluate_contract(contract, cpu_report)
+    if cpu_evaluation.verdict != "stop":
+        raise RuntimeError("immutable CPU v1 evidence no longer evaluates to stop")
+
+    public_key_bytes = base64.b64decode(contract.baseline["required_signer_public_key"])
+    public_key = Ed25519PublicKey.from_public_bytes(public_key_bytes)
+    public_key.verify(
+        base64.b64decode(gpu_report["provenance"]["signature"]),
+        report_signing_payload(gpu_report),
+    )
+    signer_fingerprint = hashlib.sha256(public_key_bytes).hexdigest()
+    if gpu_report["provenance"]["signer_public_key_sha256"] != signer_fingerprint:
+        raise RuntimeError("GPU report signer fingerprint does not match the contract trust key")
+    if gpu_report["provenance"]["config_sha256"] != _canonical_sha256(gpu_config):
+        raise RuntimeError("GPU report is not bound to gpu-diagnostic-config.json")
+
+    if gpu_report.get("schema_version") != 1 or gpu_report.get("evidence_class") != "local-real":
+        raise RuntimeError("GPU report must be schema-v1 local-real evidence")
+    expected_producer = "meshnet_node.recipe_drivers.run_configured_gpu_diagnostic/v1"
+    if gpu_report["provenance"].get("producer") != expected_producer:
+        raise RuntimeError("GPU report was not emitted by the canonical diagnostic producer")
+    if gpu_report.get("reference_recipe_id") != "transformers-fp32-rocm-quality-oracle":
+        raise RuntimeError("GPU report uses the wrong quality reference")
+    if gpu_report.get("host", {}).get("benchmark_lane") != "rocm-gpu-diagnostic":
+        raise RuntimeError("GPU report lacks the diagnostic host marker")
+
+    trusted = json.loads(
+        (ROOT.parents[1] / "trusted-evidence-signers.json").read_text(encoding="utf-8")
+    )
+    if not any(
+        signer.get("algorithm") == "ed25519"
+        and signer.get("fingerprint_sha256") == signer_fingerprint
+        and signer.get("status") == "active"
+        for signer in trusted.get("signers", ())
+    ):
+        raise RuntimeError("GPU signer is not active in the trusted-signers registry")
+
+    for field in ("model_id", "model_revision"):
+        if gpu_report["plan"].get(field) != cpu_report["plan"].get(field):
+            raise RuntimeError(f"CPU and GPU reports do not share {field}")
+        if gpu_config["plan"].get(field) != gpu_report["plan"].get(field):
+            raise RuntimeError(f"GPU config and report do not share {field}")
+
+    expected_recipes = {
+        "transformers-fp32-rocm-quality-oracle": ("quality", "cuda"),
+        "llama-cpp-bf16-rocm-quality": ("quality", "cuda"),
+        "transformers-bf16-rocm-throughput": ("performance-fit", "cuda"),
+        "llama-cpp-q4-rocm-throughput": ("performance-fit", "cuda"),
+    }
+    actual_recipes = {
+        entry["recipe"]["id"]: (entry["recipe"]["lane"], entry["recipe"]["device"])
+        for entry in gpu_report["recipes"]
+    }
+    if actual_recipes != expected_recipes:
+        raise RuntimeError("GPU report recipe identities, lanes, or devices changed")
+
+    gpu_prompt_ids = {prompt["id"] for prompt in gpu_report["plan"]["prompts"]}
+    levels = {int(level) for level in gpu_report["plan"]["concurrency_levels"]}
+    repeats = int(gpu_report["plan"]["repeats"])
+    expected_outcomes = len(gpu_prompt_ids) * repeats * sum(levels)
+    for entry in gpu_report["recipes"]:
+        recipe_id = entry["recipe"]["id"]
+        if not entry.get("available") or len(entry.get("outcomes", ())) != expected_outcomes:
+            raise RuntimeError(f"GPU recipe {recipe_id!r} lacks complete outcomes")
+        if any(
+            not outcome.get("ok")
+            or outcome.get("recipe_id") != recipe_id
+            or outcome.get("prompt_id") not in gpu_prompt_ids
+            or int(outcome.get("concurrency", 0)) not in levels
+            or not 0 <= int(outcome.get("repeat", -1)) < repeats
+            for outcome in entry["outcomes"]
+        ):
+            raise RuntimeError(f"GPU recipe {recipe_id!r} contains failed or invalid outcomes")
+        if {int(level) for level in entry["concurrency"]} != levels:
+            raise RuntimeError(f"GPU recipe {recipe_id!r} has wrong concurrency cells")
+        for prompt_id in gpu_prompt_ids:
+            for level in levels:
+                for repeat in range(repeats):
+                    count = sum(
+                        outcome["prompt_id"] == prompt_id
+                        and int(outcome["concurrency"]) == level
+                        and int(outcome["repeat"]) == repeat
+                        for outcome in entry["outcomes"]
+                    )
+                    if count != level:
+                        raise RuntimeError(
+                            f"GPU recipe {recipe_id!r} lacks complete request coverage"
+                        )
+        if any(
+            int(cell.get("failures", -1)) != 0
+            or int(cell.get("requests", -1))
+            != len(
+                [
+                    outcome
+                    for outcome in entry["outcomes"]
+                    if int(outcome["concurrency"]) == int(level)
+                ]
+            )
+            for level, cell in entry["concurrency"].items()
+        ):
+            raise RuntimeError(f"GPU recipe {recipe_id!r} aggregates do not match outcomes")
+
+    cpu_quality = _drift(cpu_report, "llama-cpp-near-lossless-quality")
+    gpu_quality = _drift(gpu_report, "llama-cpp-bf16-rocm-quality")
+    cpu_recipe = _recipe(cpu_report, "llama-cpp-near-lossless-quality")
+    gpu_recipe = _recipe(gpu_report, "llama-cpp-bf16-rocm-quality")
+    gpu_backend = gpu_recipe["load"]["backend_detail"]
+    if "measured accelerator ROCm0: Radeon 8060S Graphics" not in gpu_backend:
+        raise RuntimeError("GPU report lacks measured ROCm device evidence")
+    if "measured offload 25/25 layers" not in gpu_backend:
+        raise RuntimeError("GPU report lacks measured layer-offload evidence")
+    if cpu_recipe["recipe"]["artifact_sha256"] != gpu_recipe["recipe"]["artifact_sha256"]:
+        raise RuntimeError("CPU and GPU diagnostics use different BF16 GGUF artifacts")
+    if gpu_quality.get("compared_prompts") != len(gpu_prompt_ids):
+        raise RuntimeError("GPU quality drift lacks complete prompt coverage")
+    if {item["prompt_id"] for item in gpu_quality.get("per_prompt", ())} != gpu_prompt_ids:
+        raise RuntimeError("GPU quality drift prompt identities do not match the plan")
+
+    summary = {
+        "schema_version": 2,
+        "model_id": cpu_report["plan"]["model_id"],
+        "model_revision": cpu_report["plan"]["model_revision"],
+        "cpu_v1": {
+            "report": "results.json",
+            "report_sha256": _file_sha256("results.json"),
+            "run_id": cpu_report["provenance"]["run_id"],
+            "plan_id": cpu_report["plan"]["plan_id"],
+            "plan_sha256": _canonical_sha256(cpu_report["plan"]),
+            "config_sha256": cpu_report["provenance"]["config_sha256"],
+            "device": "cpu",
+            "quality_oracle": "Transformers BF16 safetensors",
+            "candidate": "llama.cpp BF16 GGUF",
+            "candidate_artifact_sha256": cpu_recipe["recipe"]["artifact_sha256"],
+            "exact_match_rate": cpu_quality["exact_match_rate"],
+            "mean_similarity": cpu_quality["mean_similarity"],
+            "contract_verdict": cpu_evaluation.verdict,
+            "root_cause": "undetermined; no logit-tie claim is acceptance evidence",
+        },
+        "rocm_diagnostic": {
+            "report": "gpu-diagnostic-results.json",
+            "report_sha256": _file_sha256("gpu-diagnostic-results.json"),
+            "run_id": gpu_report["provenance"]["run_id"],
+            "producer": gpu_report["provenance"]["producer"],
+            "signer_fingerprint": signer_fingerprint,
+            "plan_id": gpu_report["plan"]["plan_id"],
+            "plan_sha256": _canonical_sha256(gpu_report["plan"]),
+            "config_sha256": gpu_report["provenance"]["config_sha256"],
+            "device": "cuda (ROCm)",
+            "quality_oracle": "Transformers float32 safetensors",
+            "candidate": "llama.cpp BF16 GGUF",
+            "candidate_artifact_sha256": gpu_recipe["recipe"]["artifact_sha256"],
+            "measured_backend_detail": gpu_backend,
+            "exact_match_rate": gpu_quality["exact_match_rate"],
+            "mean_similarity": gpu_quality["mean_similarity"],
+            "failures": sum(
+                metrics["failures"]
+                for entry in gpu_report["recipes"]
+                for metrics in entry["concurrency"].values()
+            ),
+            "v1_eligible": False,
+        },
+        "conclusion": {
+            "v1_verdict_changed": False,
+            "cpu_bf16_divergence_explained": False,
+            "conversion_corruption_observed_in_rocm_sample": False,
+            "scope": (
+                "The ROCm diagnostic establishes only that the same BF16 GGUF artifact "
+                "matched the float32 oracle for three GPU sequences; it does not explain "
+                "the CPU BF16 divergence or prove global conversion correctness."
+            ),
+            "recommended_v2_design": (
+                "Predeclare a float32 quality oracle separately from the BF16 performance "
+                "reference, with a larger prompt corpus and immutable thresholds."
+            ),
+        },
+    }
+
+    (ROOT / "quality-parity-diagnosis.json").write_text(
+        json.dumps(summary, indent=2, sort_keys=True) + "\n", encoding="utf-8"
+    )
+    md = f"""# DGR-001 quality-parity evidence summary
+
+This summary is generated by `summarize-quality-parity.py` from signed reports.
+It contains no independent logit measurements or self-asserted verification flag.
+
+| Source | Device | Quality oracle | BF16 GGUF candidate | Exact | Similarity | Status |
+|---|---|---|---|---:|---:|---|
+| CPU v1 (`{summary['cpu_v1']['run_id']}`) | CPU | Transformers BF16 | llama.cpp BF16 | {summary['cpu_v1']['exact_match_rate']:.4f} | {summary['cpu_v1']['mean_similarity']:.4f} | immutable `stop` |
+| ROCm diagnostic (`{summary['rocm_diagnostic']['run_id']}`) | ROCm0 / Radeon 8060S | Transformers float32 | llama.cpp BF16 | {summary['rocm_diagnostic']['exact_match_rate']:.4f} | {summary['rocm_diagnostic']['mean_similarity']:.4f} | diagnostic only |
+
+## Interpretation
+
+The CPU and ROCm rows use different plans, devices, kernels, and quality oracles.
+The CPU BF16 divergence remains unexplained and v1 remains `stop`. The signed
+ROCm report establishes the narrower fact that the same BF16 GGUF artifact
+matched the float32 oracle for all three GPU sequences with zero failures.
+Its signed backend detail records `ROCm0: Radeon 8060S Graphics` and measured
+`25/25` layer offload.
+
+No conversion corruption was observed in that three-sequence ROCm sample. This
+does not prove global conversion correctness and does not retroactively change
+or explain the CPU result. A future v2 should predeclare a float32 quality oracle
+separately from its BF16 performance reference and use a larger corpus.
+
+## Reproduction and bindings
+
+- CPU report SHA-256: `{summary['cpu_v1']['report_sha256']}`
+- GPU report SHA-256: `{summary['rocm_diagnostic']['report_sha256']}`
+- BF16 GGUF SHA-256: `{summary['rocm_diagnostic']['candidate_artifact_sha256']}`
+- Signer fingerprint: `{signer_fingerprint}`
+- Exact verification command: see `commands.txt`.
+"""
+    (ROOT / "quality-parity-diagnosis.md").write_text(md, encoding="utf-8")
+
+
+if __name__ == "__main__":
+    main()

.scratch/distributed-gguf-runtime/evidence/DGR-002/README.md

@@ -0,0 +1,242 @@
+# DGR-002 — Adopt the versioned gRPC Shard protocol
+
+Status: **done**. Every acceptance criterion is met with real command output.
+Evidence class: **synthetic/unit** — this story defines a schema and proves both
+languages agree on it. No model, GPU, network peer or benchmark is involved, and
+none is claimed.
+
+## 1. Summary
+
+`packages/node/native/proto/shard_runtime.proto` is now the semantic contract for
+the native Shard data plane: Protocol Buffers over gRPC/HTTP2 (ADR-0020). Python
+and C++ both generate from it, and a shared committed conformance vector proves
+they encode it identically — byte for byte.
+
+Design decisions worth carrying forward:
+
+- **Everything gRPC gives you is *also* in the schema.** Deadline, cancellation,
+  identity and flow control are carried as fields, not left to HTTP/2 metadata,
+  because the existing relay carries these frames as **opaque binary**. A relayed
+  frame has no HTTP/2 context to inherit a deadline or a channel identity from.
+  If it is not in the schema, it does not survive the relay.
+- **Cancellation is both in-band and out-of-band.** `CancelSignal` rides the
+  stream; `Cancel` is also a unary RPC. A cancel that can only travel down a
+  stream that flow control has wedged is not a cancel.
+- **Checksums cover the uncompressed payload.** Compression is a per-hop
+  transport decision (reusing the existing `activation_compression` policies), so
+  a checksum over the compressed frame would be invalidated by a hop that merely
+  chose differently.
+- **Application-level flow-control credits, not just HTTP/2 windows.** HTTP/2
+  bounds *bytes in flight*; it does not bound how much *work* a worker has queued,
+  and a relayed frame gets no window at all. Credits bound queue occupancy and KV
+  pressure, and negotiation takes the strictest bound of either peer so a sender
+  cannot talk a worker into unbounded queues.
+
+## 2. Files changed
+
+New:
+
+| Path | What |
+|---|---|
+| `packages/node/native/proto/shard_runtime.proto` | The schema (sha256 `9e211660…`, see `protocol.json`) |
+| `packages/node/native/CMakeLists.txt` | C++ generation + build wiring + ctest |
+| `packages/node/native/tests/test_shard_protocol_conformance.cpp` | C++ conformance test |
+| `packages/node/native/testdata/*.binpb` | Committed cross-language vectors |
+| `packages/node/native/README.md` | How to regenerate and build |
+| `packages/node/meshnet_node/native_protocol/__init__.py` | Public Python surface |
+| `packages/node/meshnet_node/native_protocol/codec.py` | Bundle encode/decode, fragmentation, CRC32C, chunking, FC negotiation |
+| `packages/node/meshnet_node/native_protocol/conformance.py` | Canonical vectors shared by both languages |
+| `packages/node/meshnet_node/native_protocol/generated/` | Generated Python stubs (committed) |
+| `scripts/generate_native_protocol.py` | Python generation, with `--check` |
+| `scripts/generate_protocol_goldens.py` | Vector generation, with `--check` |
+| `scripts/bootstrap_native_toolchain.sh` | Builds protobuf C++ from source |
+| `tests/test_native_shard_protocol.py` | 45 Python tests |
+
+Modified:
+
+- `packages/node/pyproject.toml` — added runtime floors `grpcio>=1.82.1` and
+  `protobuf>=7.35.0`, matching the committed generated-code requirements; new
+  `proto` extra pinning `grpcio-tools==1.82.1`.
+- `packages/node/meshnet_node/activation_compression.py` — optional bounded zstd
+  output for untrusted protocol frames; existing callers remain compatible.
+- `packages/node/meshnet_node/native_protocol/__init__.py` — exports negotiated
+  bound constants and whole-session-message validation.
+
+The canonical PRD marks only DGR-002 passed. `git status` before this story was clean.
+
+## 3. Commands and real results
+
+See `commands.txt` for the exact ordered list. Results:
+
+```
+python scripts/generate_native_protocol.py --check    -> generated stubs are up to date
+python scripts/generate_protocol_goldens.py --check   -> conformance vectors are up to date
+
+cmake -S packages/node/native -B build/native -DCMAKE_PREFIX_PATH=/tmp/pbsrc/install
+  -- gRPC C++ not found: building message types only (sufficient for the conformance test)
+cmake --build build/native -j                         -> Built target shard_protocol_conformance
+ctest --test-dir build/native --output-on-failure     -> 1/1 Test #1: shard_protocol_conformance ... Passed
+                                                          100% tests passed out of 1
+
+cmp build/native/cpp_roundtrip.binpb \
+    packages/node/native/testdata/session_request_golden.binpb   -> identical (exit 0)
+
+pytest -q tests/test_native_shard_protocol.py         -> 45 passed
+pytest -q tests/test_native_shard_protocol.py \
+  tests/test_activation_compression.py                -> 51 passed
+pytest -q  (final full suite)                         -> 728 passed, 12 skipped
+pytest -q tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
+  (after an earlier flaky full-suite failure)          -> 1 passed, 1 passed, 1 passed
+clean minimum-runtime import + codec smoke test        -> passed
+  grpcio==1.82.1, protobuf==7.35.0
+compileall -q packages tests                          -> OK (exit 0)
+git diff --check                                      -> clean (exit 0)
+```
+
+The C++ lane was rebuilt from scratch by Ralph (`rm -rf build/native`) using only
+the documented commands, and reproduced the same result. During controller
+review the user explicitly chose not to repeat the destructive build-directory
+cleanup, so the independent controller relied on the recorded CMake/CTest run
+while reproducing every Python/generation/full-suite gate.
+
+### Controller review corrections
+
+Independent controller review found and fixed two classes of issue before
+integration:
+
+1. Generated stubs required gRPC 1.82.1 and Protobuf 7.35.0, while the initial
+   package metadata allowed much older runtimes that could fail at import time.
+2. Flow-control bounds were described but not enforced by the reference decoder.
+   Tensor declarations, shape rank/dimensions, fragment/tensor counts, fragments,
+   wire bodies, whole bundles, complete session messages (including envelope
+   overhead), and zstd window/output expansion are now fail-closed against the
+   negotiated/default bounds. Unspecified bundle versions, compression and
+   checksums are rejected rather than interpreted as valid data.
+3. Negotiated initial credits could exceed `max_inflight_chunks`; credits are now
+   capped by the settled in-flight limit.
+
+Controller results: protocol tests `45 passed`; protocol plus shared compression
+tests `51 passed`; final full suite `728 passed, 12 skipped`. A clean environment
+at the declared minimum gRPC/Protobuf runtime versions imported both generated
+stub modules and round-tripped the codec. Generation checks, `compileall`, static
+secret scan, and `git diff --check` all passed.
+
+### Full-suite note — a pre-existing flaky test
+
+`tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy`
+is **flaky on a clean tree, independent of this story**. Reproduction, run
+*before any DGR-002 file existed* (working tree clean, `git status` empty):
+
+```
+pytest -q                                       -> 1 failed, 682 passed, 12 skipped
+  FAILED tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
+
+# same test, three consecutive isolated runs on the same clean tree:
+pytest -q tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
+  -> 1 passed in 1.76s
+  -> 1 failed in 4.39s
+  -> 1 passed in 1.10s
+```
+
+It is a timing race in proxy cancellation (a 3-second in-flight generation raced
+against the cancel assertion), not a deterministic failure, and it touches no code
+this story changes. One controller full-suite run reported exactly that one failure
+(`1 failed, 719 passed, 12 skipped`); three immediate isolated retries all passed
+in 1.11 seconds, and the final exact-code full suite was green (`728 passed,
+12 skipped`). It is flagged for whoever owns the tracker cancel path and is **not**
+fixed here, since silently touching another story's code is out of scope.
+
+## 4. Acceptance criteria
+
+| Criterion | Where it is proven |
+|---|---|
+| Schema for capability, health, session stream, release, cancellation | `shard_runtime.proto` `service ShardRuntime`; `test_service_exposes_capability_health_session_release_and_cancel` |
+| One long-lived bidi stream per Activation Seam, with deadlines, cancellation, flow control, structured errors | `rpc Session (stream) returns (stream)`; `test_session_is_one_long_lived_bidirectional_stream`; `Envelope.deadline_unix_nanos`, `CancelSignal` + unary `Cancel`, `FlowControl`, `ShardError` |
+| Bounded chunking for prefill; small decode fast path | `ChunkInfo` + `plan_prefill_chunks` (128-token bound, ADR-0008); `DecodeStep`; `test_prefill_is_split_into_bounded_token_aligned_chunks`, `test_decode_fast_path_is_much_smaller_than_a_full_envelope_chunk` |
+| Envelope carries schema version, work id, session id, epoch, fingerprint, range/effective start, phase, position, idempotency step, cache expectation, compression, checksum | `Envelope` + `NamedTensor`; `test_envelope_carries_every_field_the_protocol_promises` asserts against the **descriptor**, so deleting a field from the `.proto` fails the test |
+| Versioned named-tensor bundle: name, shape, dtype, byte order, fragments | `TensorBundle`/`NamedTensor`/`TensorFragment`; `test_named_tensor_bundle_is_versioned_and_fully_described`, `test_bundle_round_trips_multiple_named_tensors` |
+| Round-trip + compatibility tests in Python and C++ | 45 Python tests; C++ `ctest` 1/1; cross-language byte equality |
+| Targeted pytest passes | 45 passed |
+| `compileall packages tests` | exit 0 |
+| `git diff --check` | exit 0 |
+| Default tests deterministic, download-free, credit-free, GPU-free | Pure in-memory protobuf; no model, no network, no GPU |
+| Full deterministic pytest passes, or pre-existing failure recorded | Final exact-code run: 728 passed, 12 skipped; earlier sole flaky failure documented with clean-tree reproduction and 3/3 passing retries |
+
+## 5. How the cross-language claim is actually earned
+
+Two codecs that each round-trip their own output prove only that each is
+self-consistent. Instead:
+
+1. Python builds the canonical `SessionRequest` and commits its bytes.
+2. The C++ test parses **those** bytes, asserts every field, recomputes the CRC32C
+   **from the polynomial in independent C++ code**, reassembles the multi-fragment
+   tensor, and re-serializes to `cpp_roundtrip.binpb`.
+3. `test_cpp_and_python_agree_byte_for_byte` asserts that file equals the golden.
+
+Compatibility is tested in both languages: an unknown field from a newer peer
+survives a parse/serialize hop (a Shard forwards activations — silently stripping
+fields would corrupt a route it is merely a waypoint on), and a sparse message
+from an older peer parses to proto3 defaults.
+
+## 6. Limitations and deferred work
+
+- **gRPC C++ was not built or linked.** The C++ lane verifies the *schema* (message
+  types), not a running gRPC C++ server, because this machine has no gRPC C++ stack
+  and building it is a large dependency the conformance test does not need.
+  `CMakeLists.txt` already generates and exports `shard_runtime_grpc` when
+  `find_package(gRPC)` succeeds. **DGR-008 must install gRPC C++ and extend
+  `scripts/bootstrap_native_toolchain.sh`.**
+- **No wire is exercised.** No client, server, or stream lifecycle exists yet — no
+  deadline actually fires, no credit is actually consumed. This story defines and
+  proves the contract; DGR-008/DGR-009 implement it.
+- The protobuf C++ toolchain used here was installed to `/tmp/pbsrc/install` (ephemeral).
+  `scripts/bootstrap_native_toolchain.sh` reproduces it; prefer a durable prefix such
+  as `build/native-toolchain`.
+- `crc32c` has a pure-Python fallback (used here) and picks up `google_crc32c` when
+  present. The fallback is byte-exact but slow; a worker on the hot path should install
+  the native package. Not a correctness limitation.
+- Compression on the wire is zstd-or-none only, matching the existing seam.
+
+## 7. Compatibility and migration notes
+
+- **This does not change the existing HTTP activation wire.** `X-Meshnet-Wire` stays
+  at `2` and the legacy `/forward` path is untouched. The native protocol is a
+  *separate* contract with its own `SchemaVersion`, starting at 1. Nothing in this
+  story is on any live request path — it is additive.
+- Semantics are deliberately preserved from the existing ADRs so the two transports
+  mean the same thing: `effective_start_layer` (ADR-0012), `CacheMode`/`expected_past_len`
+  and `ERROR_CODE_CACHE_MISS` mapping to today's HTTP 409 `cache_miss` (ADR-0022),
+  bfloat16 boundary dtype and 128-token prefill chunks (ADR-0008), fingerprint/recipe
+  identity mirroring the capability report (ADR-0023).
+- `TensorFragment` field 5 (`uncompressed_size`) is **reserved**: it was removed
+  because `NamedTensor.total_bytes` is the single source of truth. Never recycle it —
+  a recycled field number is the one schema change peers cannot detect, because the
+  bytes still parse.
+- Committed Python stubs are guarded by `--check` in the test suite, so they cannot
+  drift from the schema unnoticed.
+
+## 8. Handoff to dependent stories
+
+- **DGR-003 (runtime recipe/fingerprint):** populate `Fingerprint`
+  (`model_artifact_digest`, `runtime_recipe_digest`, `recipe_id`, `recipe_version`,
+  `catalogue_version`). The mismatch outcome is already specified:
+  `ERROR_CODE_FINGERPRINT_MISMATCH`. Do not invent a second identity struct.
+- **DGR-005/006 (range loading, architecture boundary):** the boundary payload is a
+  **named bundle**, not a bare tensor — a boundary needing more than one tensor is
+  already representable. Execute `[effective_start_layer, end_layer)`, never from
+  `start_layer`.
+- **DGR-007 (concurrent sessions/KV):** isolate on `(route_session_id, route_epoch)`.
+  `CacheExpectation`/`CacheResult` and `ERROR_CODE_CACHE_MISS` are the contract; a
+  decode step whose `expected_past_len` does not match **must** miss, never fall back
+  to a silent stateless forward. `idempotency_step` means a retried step is
+  acknowledged (`Ack.duplicate`), not re-applied — re-applying advances the KV cache
+  twice and desynchronises the route.
+- **DGR-008 (C++ worker):** link `shard_runtime_grpc` from `CMakeLists.txt`; you must
+  first install gRPC C++ (see limitations). Honour `FlowControl` credits and the
+  `max_chunk_bytes` bound. Use `packages/node/meshnet_node/native_protocol/codec.py`
+  as the reference for fragment reassembly and checksum validation.
+- **DGR-009 (Meshnet integration):** the relay may carry these serialized frames as
+  opaque binary — that is exactly why deadline/cancel/identity are in-band. Do not add
+  a second control plane.
+- **Anyone editing the schema:** run both `--check` scripts; if a vector legitimately
+  changes, regenerate it and say so, because the C++ test asserts those exact bytes.

.scratch/distributed-gguf-runtime/evidence/DGR-002/commands.txt

@@ -0,0 +1,45 @@
+# DGR-002 — exact commands, in order. Run from the repository root.
+# Interpreter: <repo>/.venv/bin/python (CPython 3.14.6). Deterministic, GPU-free,
+# no model download, no API credits.
+
+# --- toolchain (this machine had no protoc, no cmake, no protobuf C++ headers)
+.venv/bin/python -m pip install grpcio-tools==1.82.1 grpcio==1.82.1 cmake==4.4.0
+scripts/bootstrap_native_toolchain.sh /tmp/pbsrc/install   # protobuf C++ 33.1 + abseil 20250814.1
+
+# --- schema generation (Python stubs; committed)
+.venv/bin/python scripts/generate_native_protocol.py
+.venv/bin/python scripts/generate_native_protocol.py --check     # -> "generated stubs are up to date"
+
+# --- cross-language conformance vectors (committed)
+.venv/bin/python scripts/generate_protocol_goldens.py
+.venv/bin/python scripts/generate_protocol_goldens.py --check    # -> "conformance vectors are up to date"
+
+# --- C++ generation, build and conformance test
+cmake -S packages/node/native -B build/native -DCMAKE_PREFIX_PATH=/tmp/pbsrc/install
+cmake --build build/native -j"$(nproc)"
+ctest --test-dir build/native --output-on-failure                # -> 1/1 Passed
+cmp build/native/cpp_roundtrip.binpb packages/node/native/testdata/session_request_golden.binpb
+
+# --- Python tests
+.venv/bin/python -m pytest -q tests/test_native_shard_protocol.py   # -> 29 passed
+.venv/bin/python -m pytest -q                                        # full suite
+
+# --- repository gates
+.venv/bin/python -m compileall -q packages tests
+git diff --check
+
+# --- independent controller review after Ralph
+PYTHONPATH=packages/node .venv/bin/python -m pytest -q tests/test_native_shard_protocol.py
+# -> 45 passed
+PYTHONPATH=packages/node .venv/bin/python -m pytest -q \
+  tests/test_native_shard_protocol.py tests/test_activation_compression.py
+# -> 51 passed
+PYTHONPATH=packages/node .venv/bin/python -m pytest -q
+# -> final exact-code run: 728 passed, 12 skipped
+for i in 1 2 3; do PYTHONPATH=packages/node .venv/bin/python -m pytest -q \
+  tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy; done
+# -> 1 passed, 1 passed, 1 passed
+# clean minimum-runtime venv: protobuf==7.35.0 grpcio==1.82.1
+# generated pb2 + pb2_grpc imports and one-byte codec round trip -> passed
+# The user chose to rely on Ralph's recorded successful C++ CMake/CTest run
+# rather than repeat deletion of an isolated generated build directory.

.scratch/distributed-gguf-runtime/evidence/DGR-002/protocol.json

@@ -0,0 +1,95 @@
+{
+  "schema_version": "SCHEMA_VERSION_1",
+  "bundle_version": 1,
+  "proto_path": "packages/node/native/proto/shard_runtime.proto",
+  "proto_sha256": "9e211660b3fcefc88bcdf3851c3571088c00349aacb5adc5ef45083c83d0cce2",
+  "protoc": "grpc_tools 1.82.1 (python) / protobuf 33.1 (C++)",
+  "service": {
+    "GetCapability": {
+      "client_streaming": false,
+      "server_streaming": false
+    },
+    "Health": {
+      "client_streaming": false,
+      "server_streaming": false
+    },
+    "Session": {
+      "client_streaming": true,
+      "server_streaming": true
+    },
+    "Release": {
+      "client_streaming": false,
+      "server_streaming": false
+    },
+    "Cancel": {
+      "client_streaming": false,
+      "server_streaming": false
+    }
+  },
+  "envelope_fields": [
+    "cache_expectation",
+    "chunk",
+    "deadline_unix_nanos",
+    "fingerprint",
+    "idempotency_step",
+    "phase",
+    "position",
+    "route_epoch",
+    "route_session_id",
+    "schema_version",
+    "shard_range",
+    "work_id"
+  ],
+  "named_tensor_fields": [
+    "byte_order",
+    "checksum",
+    "compression",
+    "dtype",
+    "fragments",
+    "name",
+    "shape",
+    "total_bytes"
+  ],
+  "phases": [
+    "PHASE_UNSPECIFIED",
+    "PHASE_PREFILL",
+    "PHASE_DECODE",
+    "PHASE_RELEASE",
+    "PHASE_CANCEL"
+  ],
+  "error_codes": [
+    "ERROR_CODE_UNSPECIFIED",
+    "ERROR_CODE_SCHEMA_UNSUPPORTED",
+    "ERROR_CODE_FINGERPRINT_MISMATCH",
+    "ERROR_CODE_EPOCH_STALE",
+    "ERROR_CODE_SHARD_RANGE_MISMATCH",
+    "ERROR_CODE_CACHE_MISS",
+    "ERROR_CODE_RESOURCE_EXHAUSTED",
+    "ERROR_CODE_PAYLOAD_CORRUPT",
+    "ERROR_CODE_CANCELLED",
+    "ERROR_CODE_DEADLINE_EXCEEDED",
+    "ERROR_CODE_FLOW_CONTROL_VIOLATION",
+    "ERROR_CODE_INTERNAL"
+  ],
+  "bounds": {
+    "max_prefill_chunk_tokens": 128,
+    "max_chunk_bytes": 4194304,
+    "max_fragment_bytes": 1048576,
+    "max_inflight_chunks": 8,
+    "max_fragments_per_tensor": 64,
+    "max_tensors_per_bundle": 64,
+    "max_tensor_rank": 8,
+    "max_tensor_dimension": 2147483647,
+    "whole_session_message_enforced": true
+  },
+  "golden_vectors": {
+    "session_request_golden.binpb": "c2c3df8a717ddeae7bd99624d2c7f34c09a518988de990237fe313b75cff0817",
+    "capability_report_golden.binpb": "71ac5f150775f398515b43a63596a5cbe8d2ad607e7e4de56bd44fbe7987080c"
+  },
+  "verification": {
+    "python_protocol_tests": "45 passed",
+    "python_protocol_and_compression_tests": "51 passed",
+    "full_suite": "728 passed, 12 skipped",
+    "minimum_runtime": "grpcio 1.82.1 / protobuf 7.35.0 passed import and codec smoke"
+  }
+}

.scratch/distributed-gguf-runtime/evidence/DGR-003/README.md

@@ -0,0 +1,186 @@
+# DGR-003 — exact Artifact and runtime recipe identity
+
+Evidence class: deterministic offline/unit. No model payload, GPU, external API,
+network node, or API credit is required or claimed.
+
+## Result — delayed-review repair, 2026-07-14
+
+DGR-003 defines and tests an exact, model-agnostic compatibility identity and
+connects it to DGR-002's gRPC `Fingerprint` plus tracker parsing, admission,
+route partitioning, and certification. It is **not complete**: the existing
+production doctor/backend path still emits the legacy capability report without
+constructing a `ShardIdentity` from authoritative loaded artifact/runtime state.
+No exact recipe is therefore claimed live or routable from that path; supplied
+exact identities remain dark until tracker-owned certification.
+
+A matching digest proves canonical consistency, **not node authenticity or real
+execution**. Tracker-owned certification of a fingerprint by a non-synthetic,
+complete, multi-node distributed forward is the execution trust boundary.
+
+## Implementation
+
+- `ArtifactIdentity` binds artifact ID/revision, exact content digest,
+  architecture/config digest, layer count, and optional derivative binding.
+- `DerivativeBinding` binds a split artifact to the exact source artifact digest
+  and its end-exclusive layer range. A Shard cannot advertise outside that range.
+- `RuntimeRecipe` keeps these canonical axes separate rather than hiding them in
+  a backend label:
+  - weight quantization;
+  - activation and compute dtypes;
+  - KV dtype and layout;
+  - tokenizer revision;
+  - architecture adapter;
+  - backend and runtime version;
+  - boundary and protocol schema versions;
+  - recipe ID/version and catalogue version.
+- `CompatibilityFingerprint` populates the existing DGR-002 Protobuf
+  `Fingerprint`; `check_session_open()` fails closed on schema, fingerprint,
+  advertised/effective range, non-empty route session, positive route epoch,
+  and (when supplied) exact tracker route-session/epoch assignment.
+- Node and tracker implementations independently canonicalize the declaration.
+  This is intentional: the tracker must not trust a digest copied from a node,
+  and future native/C++ workers also need an independent implementation. Their
+  behavior is pinned by `tests/data/recipe_fingerprint_vectors.json`.
+- Tracker admission cross-checks the exact identity against the capability
+  proof's model, range, recipe labels, backend, and weight quantization. Any
+  disagreement fails closed.
+- `TrackerServer` owns the sole live certification ledger and passes it through
+  direct and replicated registration paths. A known exact recipe is
+  `uncertified` and dark for user traffic until the same exact fingerprint is
+  certified. Restart fails closed; durable/cluster-wide certification events
+  require the later real-forward control path and are not claimed here.
+- Certification evidence is bound to the promoted fingerprint, requires at
+  least two distinct nodes, complete layer coverage, generated tokens, and
+  `synthetic=false`. Unknown or mismatched fingerprints cannot be promoted.
+
+## Files changed
+
+- `packages/node/meshnet_node/runtime_recipe.py`
+- `packages/tracker/meshnet_tracker/recipe.py`
+- `packages/tracker/meshnet_tracker/capability.py`
+- `packages/tracker/meshnet_tracker/server.py`
+- `tests/data/recipe_fingerprint_vectors.json`
+- `tests/test_runtime_recipe_identity.py`
+- this evidence directory, issue state, and DGR-003 PRD state
+
+A late review of dependency DGR-017 also found and fixed two genuine contract
+continuity defects during delayed DGR-003 review: v1 now has an independently
+trusted digest and recursively immutable parsed state. Those changes and tests
+are recorded in DGR-017 evidence rather than claimed as DGR-003 functionality.
+
+## Verification
+
+Exact commands and outcomes are in `commands.txt`.
+
+Observed final results:
+
+- DGR-003 identity + node/tracker capability suites: **126 passed**.
+- DGR-017 focused dependency repair suite: **99 passed**.
+- Tracker routing suite: **93 passed**.
+- First delayed-review integrated run: **898 passed, 13 skipped, 1 failed** on
+  the pre-existing tracker-cancellation race.
+- Final delayed-review integrated rerun: **899 passed, 13 skipped** in
+  **253.64s**; Hermes controller acceptance rerun: **899 passed, 13 skipped**
+  in **252.66s**.
+- `python -m compileall -q packages tests`: pass.
+- `git diff --check`: pass.
+- Ruff on the changed identity, capability, contract, and test modules: pass.
+- `server.py` has 8 pre-existing Ruff findings at both pushed baseline and the
+  current tree; DGR-003 added no finding.
+
+The first integrated full-suite run produced **871 passed, 13 skipped, 1 failed**
+on the known unrelated
+`test_tracker_dashboard_can_cancel_inflight_proxy` timing race. Its fixture
+completed after three seconds just before cancellation, so the cancel endpoint
+returned 404. In this delayed repair it again produced a 404 after the stream
+finished (first integrated run: **898 passed, 13 skipped, 1 failed**); three
+immediate isolated repeats passed before a fourth reproduced the same race.
+No cancellation-test code was changed. The final complete integrated rerun
+passed **899/899** tests.
+
+## Limitations
+
+- Certification state is process-local in this story. The same running tracker
+  reuses it across registrations, but durable/cluster-wide certification-event
+  persistence belongs with the later real distributed-forward control path.
+  Restart or failover therefore returns exact recipes to the safe dark state;
+  it never makes an unsupported recipe routable.
+- The node module has no certification ledger or admission policy; it holds only
+  identity construction and handshake validation. The Tracker is the sole
+  promotion authority.
+- **Completion blocker:** `doctor._validate_recipe()` calls
+  `build_capability_report()` without `identity=`, because the legacy
+  Transformers backend does not expose an immutable artifact-content pin and
+  full runtime recipe axes authoritative enough to build one. Adding a guessed
+  identity would weaken this contract. Production emission must be added with
+  the authoritative native worker/backend loading seam; until then the issue and
+  PRD deliberately remain incomplete.
+- This story proves identity and admission behavior with deterministic fixtures.
+  It does not claim a real GLM forward or hardware certification.
+
+## Compatibility
+
+- Capability report identity is additive. Legacy reports without the new block
+  retain ADR-0023's explicit compatibility-policy behavior.
+- Reports that opt into exact identity are held to it and fail closed on malformed,
+  inconsistent, unknown, dark, or mismatched declarations.
+- No new wire identity was invented; DGR-002's `Fingerprint` remains the gRPC
+  representation.
+
+## Handoff
+
+DGR-004 and native workers must build `ShardIdentity` from the actual immutable
+artifact pin, patch/runtime pin, tokenizer, numerical recipe, cache layout,
+schema versions, and owned range. At `SessionOpen`, compare its
+`CompatibilityFingerprint` and return DGR-002's
+`ERROR_CODE_FINGERPRINT_MISMATCH` on any mismatch.
+
+A digest match is not certification. Only tracker-recorded evidence from the
+same exact fingerprint and a real complete distributed forward can move that
+recipe out of dark status.
+
+## Native emission closure — 2026-07-14
+
+Status: **done**. DGR-004/DGR-005's native loaded-artifact seam now reaches the
+production capability-report path through `NativeWorkerBackendAdapter`.
+
+### Files changed
+
+- `packages/node/meshnet_node/native_backend.py` — immutable loaded-GGUF report,
+  immutable artifact and numerical pins, exact identity derivation, and the
+  SessionOpen boundary.
+- `packages/node/meshnet_node/doctor.py` — includes exact identity only for the
+  native adapter and derives all matching capability-proof fields from it.
+- `tests/test_native_identity_emission.py` — deterministic native report,
+  immutable-pin, SessionOpen, capability emission, legacy-dark, and
+  tracker-uncertified tests.
+- This issue, `prd.json`, and this evidence directory.
+
+### Correctness and trust boundary
+
+The native report carries the end-exclusive owned range, mapped/resident/
+registered bytes, GGUF architecture metadata digest, and layer count. The
+adapter constructs `ShardIdentity` only from that report plus immutable artifact
+pin, tokenizer revision, and numerical recipe inputs. It does not accept a
+caller-supplied shard range.
+
+`on_session_open()` calls `check_session_open()` before returning
+`SessionAccepted`, preserving fingerprint, schema, range, tracker-session, and
+epoch fail-closed behavior. The legacy Transformers backend is deliberately not
+an adapter and its doctor report remains identity-free.
+
+The tracker evaluates a self-consistent native report as `uncertified`: digest
+equality is canonical consistency, not node authenticity. Only its owned
+certification ledger can promote a real distributed forward.
+
+### Verification
+
+- Focused/adversarial DGR-003, node/tracker capability, doctor, and native
+  dependency suites: **171 passed, 1 skipped**.
+- Native protocol CMake configure/build plus CTest: **1/1 passed**.
+- `compileall`, Ruff, and `git diff --check`: pass.
+- Full deterministic suite: **902 passed, 13 skipped** (255.01s).
+
+No model payload, GPU, external API, network node, or real distributed forward
+was run or claimed. The standalone gRPC process remains DGR-008 work; this
+story supplies its exact native identity and fail-closed SessionOpen contract.

.scratch/distributed-gguf-runtime/evidence/DGR-003/commands.txt

@@ -0,0 +1,108 @@
+# DGR-003 final verification — 2026-07-14
+
+# Native emission closure — 2026-07-14
+PYTHONPATH=packages/node:packages/tracker:packages/contracts /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_native_identity_emission.py tests/test_runtime_recipe_identity.py tests/test_node_capability.py tests/test_tracker_capability_admission.py tests/test_node_doctor.py tests/test_llama_cpp_dependency.py
+# result: 171 passed, 1 skipped in 7.07s
+
+ruff check packages/node/meshnet_node/native_backend.py packages/node/meshnet_node/doctor.py tests/test_native_identity_emission.py
+# result: All checks passed
+
+git diff --check
+# result: pass
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m compileall packages tests
+# result: pass
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/cmake -S packages/node/native -B build/dgr-003-native-protocol -DCMAKE_PREFIX_PATH=/tmp/pbsrc/install
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/cmake --build build/dgr-003-native-protocol -j2
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/ctest --test-dir build/dgr-003-native-protocol --output-on-failure
+# result: configured and built shard_protocol_conformance; 1/1 CTest passed
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q
+# result: 902 passed, 13 skipped in 255.01s
+
+PYTHONPATH=packages/node:packages/tracker:packages/contracts /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_runtime_recipe_identity.py tests/test_node_capability.py tests/test_tracker_capability_admission.py
+# result: 99 passed in 4.76s
+
+PYTHONPATH=packages/node /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_glm_alpha_target.py
+# result: 99 passed in 0.15s
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q
+# first integrated result: 871 passed, 13 skipped, 1 failed in 258.18s
+# sole failure: tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
+# fixture completed at ~3s before cancellation; cancel endpoint returned 404
+
+for i in 1 2 3 4 5; do
+  /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
+done
+# result: 5/5 passed (1.14s, 1.14s, 1.26s, 1.14s, 1.64s)
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q
+# final integrated result: 872 passed, 13 skipped in 253.46s
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m compileall -q packages tests
+# result: pass
+
+git diff --check
+# result: pass
+
+ruff check packages/node/meshnet_node/glm_alpha/contract.py packages/node/meshnet_node/runtime_recipe.py packages/tracker/meshnet_tracker/recipe.py packages/tracker/meshnet_tracker/capability.py tests/test_glm_alpha_target.py tests/test_runtime_recipe_identity.py
+# result: All checks passed!
+
+git show e7c780a:packages/tracker/meshnet_tracker/server.py > /tmp/dgr003-server-base.py
+ruff check /tmp/dgr003-server-base.py
+ruff check packages/tracker/meshnet_tracker/server.py
+# result: both baseline and current server.py report the same 8 pre-existing findings
+
+# ---------------------------------------------------------------------------
+# Delayed-review repair continuation — 2026-07-14
+# No model payload, GPU, external API, or real inference was run.
+# ---------------------------------------------------------------------------
+
+PYTHONPATH=packages/node:packages/tracker:packages/contracts /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_runtime_recipe_identity.py tests/test_node_capability.py tests/test_tracker_capability_admission.py
+# result: 126 passed in 4.77s
+# includes adversarial certification binding, unknown participant, mutation-atomicity,
+# report/identity revision+config, route partition, golden-vector, and SessionOpen tests
+
+PYTHONPATH=packages/node:packages/tracker /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python scripts/gen_recipe_fingerprint_vectors.py --check
+# result: tests/data/recipe_fingerprint_vectors.json matches the identity implementation
+
+PYTHONPATH=packages/node /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_glm_alpha_target.py
+# result: 99 passed in 0.11s
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_tracker_routing.py
+# result: 93 passed in 46.83s
+# there is no separate tests/test_tracker_server.py in this repository
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m compileall -q packages tests
+# result: pass
+
+ruff check packages/node/meshnet_node/runtime_recipe.py packages/tracker/meshnet_tracker/recipe.py packages/tracker/meshnet_tracker/capability.py tests/test_runtime_recipe_identity.py scripts/gen_recipe_fingerprint_vectors.py
+# result: All checks passed!
+
+git show e7c780a:packages/tracker/meshnet_tracker/server.py > /tmp/dgr003-server-base.py
+ruff check /tmp/dgr003-server-base.py
+ruff check packages/tracker/meshnet_tracker/server.py
+# result: baseline has 8 pre-existing findings; current has 7 because DGR-003 now
+# uses the previously unused STATE_ADMITTED import. No new server.py finding.
+
+git diff --check
+# result: pass
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q
+# result: 898 passed, 13 skipped, 1 failed in 255.43s
+# sole failure: tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
+# the fixture completed its three-second stream before the cancel request, so cancel returned 404
+
+for i in 1 2 3 4 5; do
+  /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy || exit 1
+done
+# result: first 3 passed (1.16s, 1.65s, 1.64s); attempt 4 reproduced the same 404 race.
+# The test was not modified because it is outside the current DGR-003 P1 repair.
+
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q
+# result: 899 passed, 13 skipped in 253.64s (0:04:13)
+
+# Hermes controller acceptance rerun after agent completion
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q
+# result: 899 passed, 13 skipped in 252.66s (0:04:12)

.scratch/distributed-gguf-runtime/evidence/DGR-004/BLOCKED.md

@@ -0,0 +1,42 @@
+# DGR-004 verification blocker — 2026-07-14
+
+## Verified state
+
+The pre-existing DGR-004 boundary is present and its lock data is internally
+consistent:
+
+- `scripts/llama_cpp_dependency.py inspect` reports pin
+  `e920c523e3b8a0163fe498af5bf90df35ff51d25`, one patch, no model downloads,
+  and no semantic certification.
+- The existing clean cached checkout at `build/dgr-004-final/source` is at the
+  locked commit/tree and contains only the expected staged patch changes.
+- The existing `llama-gguf-hash --help` smoke binary runs successfully.
+- `python -m compileall -q packages tests`, Ruff on the DGR-004 Python files,
+  and `git diff --check` pass.
+
+## Blocker
+
+The verification environment no longer contains the `.venv` recorded in
+`commands.txt`, nor a `cmake` executable on `PATH`. The available global
+pytest environment cannot import the native protocol because its protobuf
+runtime is 6.33.6 while the checked-in generated code requires 7.35.0. This
+causes both `tests/test_llama_cpp_dependency.py` and the native protocol suite
+to fail during the repository-wide autouse fixture setup, before their tests
+run.
+
+This prevents the required fresh focused test and native CTest verification.
+No DGR-004 completion state, commit, or push is claimed from this worktree.
+
+## Continuation
+
+1. Restore the project test environment used by the prior evidence (including
+   protobuf >= 7.35.0 and CMake), without changing DGR-004 source files.
+2. Run the exact focused test command from `commands.txt` and the clean
+   `reproduce` command using the local llama.cpp object cache.
+3. Re-run compileall, Ruff, diff check, and the deterministic full suite.
+4. Only then apply the supervising engine's commit policy and unblock DGR-005.
+
+## Dependency graph
+
+`DGR-004 verification -> DGR-005 range-aware GGUF ownership -> DGR-003 live
+ShardIdentity emission`. DGR-005 and DGR-003-emission were not modified.

.scratch/distributed-gguf-runtime/evidence/DGR-004/README.md

@@ -0,0 +1,31 @@
+# DGR-004 — Reproducible pinned llama.cpp patch stack
+
+Status: **done**. This is reproducible native-build infrastructure evidence, not model execution evidence.
+
+## Delivered boundary
+
+- Pin: `ggml-org/llama.cpp` at `e920c523e3b8a0163fe498af5bf90df35ff51d25` (tree `6c91a11407a3a3fb160f5dac705f9c59718f54f1`).
+- Ordered patch: `0001-cmake-reserve-meshnet-patch-stack-abi-marker.patch`, SHA-256 `1454216c019c1cb7f78d1d836fe4054164fff1d498391013bcaf13cc2d328c75`.
+- The sole patch adds an interface-library CMake marker. It adds no model execution/loading, networking, Tracker, relay, gRPC, billing, or authentication code.
+- `scripts/llama_cpp_dependency.py` makes a fresh checkout, validates commit/tree/baseline blob, validates patch order/digests/context, applies the series, and verifies the exact resulting Git index tree. It rejects stale destinations, upstream drift, changed patches, untracked files, and local edits.
+
+## Build and smoke result
+
+The clean build cloned only the already-present exact Git object cache as a read-only source and did not trust its worktree. CMake 4.4.0 and GCC 15.2.1 built `llama-gguf-hash` with the locked Release/CPU flags in `UPSTREAM_LOCK.json`; `llama-gguf-hash --help` passed with no model download or load.
+
+llama.cpp tests are intentionally off for this small no-model smoke target, so no upstream CTest applies. Meshnet's focused native protocol suite passed independently. Exact results are in `commands.txt` and `results.json`.
+
+## License, compatibility, and handoff
+
+llama.cpp is MIT licensed. The materializer requires upstream `LICENSE`, preserves all upstream notices, and `THIRD_PARTY_NOTICES.md` requires including them in redistribution. No Mesh-LLM code or patch was adopted.
+
+The lock records the patched upstream blob and resulting patched tree. Pin updates must intentionally revise those values, the patch digest/order, toolchain metadata, and evidence.
+
+This stock/native build is **infrastructure evidence only**: not a standalone Meshnet worker (DGR-008), GLM semantic acceptance, DSA/IndexShare proof, numerical equivalence, performance success, model-fit evidence, or route certification. The stock dense-MLA fallback remains explicitly uncertified. DGR-001 CPU v1 remains `stop`; DGR-017 is a separate target contract. DGR-005 may consume this dense-Llama structural boundary; DGR-018/DGR-019 must prove GLM semantics.
+
+## Files changed
+
+- `packages/node/native/llama/*`
+- `scripts/llama_cpp_dependency.py`
+- `tests/test_llama_cpp_dependency.py`
+- this evidence directory, the DGR-004 issue, and `prd.json`

.scratch/distributed-gguf-runtime/evidence/DGR-004/commands.txt

@@ -0,0 +1,28 @@
+# DGR-004 commands and real results — 2026-07-14
+
+```text
+$ .venv/bin/python -m pytest -q tests/test_llama_cpp_dependency.py tests/test_native_shard_protocol.py
+47 passed, 1 skipped in 0.59s
+
+$ .venv/bin/python scripts/llama_cpp_dependency.py reproduce --work-dir build/dgr-004-smoke --source-repository /run/media/popov/d/DEV/llamacpp/llama.cpp
+llama-gguf-hash --help -> exit 0; output contains "Hash a GGUF file"
+
+$ touch build/dgr-004-drift/source/DGR-004-local-edit
+$ .venv/bin/python scripts/llama_cpp_dependency.py apply --source-dir build/dgr-004-drift/source
+DGR-004 dependency error: local edits detected in materialized llama.cpp checkout
+exit 2
+
+$ .venv/bin/python -m compileall -q packages tests
+exit 0
+
+$ ruff check scripts/llama_cpp_dependency.py tests/test_llama_cpp_dependency.py
+All checks passed!
+
+$ git diff --check
+exit 0
+
+$ .venv/bin/python -m pytest -q --cache-clear
+902 passed, 13 skipped in 255.01s (0:04:15)
+```
+
+The source-cache command avoids transient network availability only. The script defaults to the public upstream URL and verifies the exact object/tree, not external worktree state.

.scratch/distributed-gguf-runtime/evidence/DGR-004/results.json

@@ -0,0 +1,18 @@
+{
+  "evidence_class": "native build infrastructure",
+  "llama_cpp": {
+    "upstream": "https://github.com/ggml-org/llama.cpp.git",
+    "commit": "e920c523e3b8a0163fe498af5bf90df35ff51d25",
+    "commit_tree": "6c91a11407a3a3fb160f5dac705f9c59718f54f1",
+    "patched_tree": "4a37c06fac668834435b803caa59ba272bdace5c",
+    "patch_sha256": "1454216c019c1cb7f78d1d836fe4054164fff1d498391013bcaf13cc2d328c75"
+  },
+  "toolchain": {"cmake": "4.4.0", "cxx": "GCC 15.2.1", "generator": "Unix Makefiles", "target": "llama-gguf-hash", "configure_flags": ["-DCMAKE_BUILD_TYPE=Release", "-DLLAMA_BUILD_TESTS=OFF", "-DLLAMA_BUILD_EXAMPLES=ON", "-DLLAMA_BUILD_SERVER=OFF", "-DLLAMA_BUILD_TOOLS=OFF", "-DLLAMA_BUILD_APP=OFF", "-DLLAMA_CURL=OFF"]},
+  "checks": {"clean_materialize_apply_build_smoke": "passed", "local_edit_detection": "passed (exit 2)", "focused_pytest": "47 passed, 1 skipped", "compileall": "passed", "ruff": "passed", "git_diff_check": "passed", "full_pytest": "902 passed, 13 skipped"},
+  "model_downloads": false,
+  "model_loaded": false,
+  "inference_run": false,
+  "glm_semantic_certification": false,
+  "performance_certification": false,
+  "route_certification": false
+}

.scratch/distributed-gguf-runtime/evidence/DGR-005/DECOMPOSITION.md

@@ -0,0 +1,63 @@
+# DGR-005 decomposition — 2026-07-14
+
+## Verified starting point
+
+- The mandated environment is present: project Python 3.14.6, CMake 4.4.0,
+  and protobuf 7.35.1.
+- DGR-003's focused identity/capability tests and DGR-004's dependency tests
+  pass together: `95 passed`.
+- The DGR-004 materialized source at the pinned commit is available for source
+  inspection. It contains only the DGR-004 CMake-marker patch.
+
+## Why this chain cannot safely claim DGR-005 yet
+
+At the locked llama.cpp revision, `llama_model_base::load_tensors()`:
+
+1. sizes `layers` to `hparams.n_layer_all`;
+2. calls every architecture loader, which registers each architecture's layer
+   tensors; and
+3. runs a generic optional-scale pass over the full layer count before creating
+   mmap/backend buffers.
+
+Filtering names after this point does not meet the ownership contract: it
+leaves full-model model/graph assumptions and can make a middle Shard silently
+look valid while it lacks the endpoint and boundary semantics needed by the
+next story. A generic `blk.N.*` filter alone is also not an architecture
+adapter, which violates ADR-0020's fail-closed dense-Llama-first rule.
+
+## Required child slices
+
+1. **DGR-005A — native dense-Llama ownership API and loader**
+   - Add an explicit end-exclusive owned range to the project-owned native
+     interface and validate it against immutable GGUF layer metadata.
+   - Restrict registration, optional scales, allocation and mmap ranges to the
+     owned `blk.N.*` tensors.
+   - Record authoritative loaded start/end and mapped/resident byte counters
+     from the instantiated model, not command-line input.
+   - Add a deterministic synthetic dense-Llama GGUF fixture plus native tests
+     for head, middle and tail ranges.
+
+2. **DGR-005B — endpoint ownership and graph guard**
+   - Load token embeddings only for the head, and final norm/output head only
+     for the tail, including tied embeddings.
+   - Make the dense-Llama graph fail closed when an endpoint-required tensor is
+     absent; do not infer endpoint ownership from an empty pointer.
+   - Prove that split ranges map fewer bytes than the whole-model fixture and
+     that the loaded range report matches actual registered tensors.
+
+3. **DGR-003-emission follow-up**
+   - Expose the resulting immutable native loaded-artifact report to a native
+     worker/backend adapter.
+   - Construct `ShardIdentity` only from that report plus the immutable
+     artifact, tokenizer and numerical-recipe inputs. The legacy Transformers
+     doctor path must remain identity-free rather than fabricate a pin.
+   - Wire `check_session_open()` at the worker SessionOpen boundary; current
+     unit coverage already verifies its fail-closed fingerprint, range,
+     session and epoch behavior.
+
+## Handoff and non-claims
+
+No DGR-005 source patch, identity-emission code, issue status, or `prd.json`
+pass state was changed. No model was loaded, downloaded, benchmarked, or
+certified. This document is a supervised-review handoff, not DGR-005 evidence
+of completion.

.scratch/distributed-gguf-runtime/evidence/DGR-005/README.md

@@ -0,0 +1,79 @@
+# DGR-005 — dense-Llama range-aware GGUF ownership
+
+Evidence class: deterministic offline/unit (synthetic fixture) plus
+real-model integration (TinyLlama 1.1B, opt-in via MESHNET_ENABLE_REAL_INFERENCE_TESTS=1).
+
+## Result
+
+All six acceptance criteria pass:
+
+1. **Range-aware tensor ownership**: native C++ patch (`0002-dense-llama-owned-range-loader.patch`,
+   169 lines as merged — DGR-005A's original 365-line version was slimmed by DGR-005B)
+   adds `llama_model_params.meshnet_owned_layer_start/end`, `llama_meshnet_range_report`,
+   and restricts `blk.N.*` registration to the owned range.
+2. **Head/tail embedding loading**: head loads `token_embd.weight`; tail loads `output_norm`/`output`
+   (with tied-embedding dedup). Middle shards load zero endpoint tensors.
+3. **Mapped/resident memory scales with owned tensors**: proven with TinyLlama 1.1B Q4_K_M.
+4. **Targeted pytest tests**: `tests/test_llama_cpp_dependency.py` (3 tests — lock/patch
+   manifest consistency, offline dependency report, control-plane-code scan; re-verified
+   2026-07-14: `3 passed, 6 skipped` together with the opt-in integration file), native CTest
+   (`test-meshnet-range-ownership` synthetic fixture, added by the 0002 patch).
+5. **compileall, ruff, git diff --check, full pytest**: all pass.
+6. **Integration test**: `tests/test_gguf_distributed_load.py` (6/6, opt-in real model).
+
+## Files changed (vs HEAD at DGR-004)
+
+- `packages/node/native/llama/patches/0002-dense-llama-owned-range-loader.patch` — 169-line native patch (as merged)
+- `packages/node/native/llama/patches/SHA256SUMS` — updated hash
+- `packages/node/native/llama/patches/series` — added patch to series
+- `packages/node/native/llama/UPSTREAM_LOCK.json` — updated patched_tree, serial number
+- `scripts/llama_cpp_dependency.py` — `inspect` report for 2-patch stack
+- `tests/test_llama_cpp_dependency.py` — patch_count 2
+- `packages/node/native/llama/meshnet-range-loader.cpp` — C CLI wrapper
+- `tests/test_gguf_distributed_load.py` — real-model integration test
+
+## Commands
+
+```text
+# Build patched llama.cpp + range loader
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/cmake \
+  -S build/dgr-004-final/source -B build/dgr-004-final/build \
+  -DCMAKE_BUILD_TYPE=Release -DLLAMA_BUILD_EXAMPLES=ON \
+  -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_SERVER=OFF \
+  -DLLAMA_BUILD_TOOLS=ON -DLLAMA_CURL=OFF
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/cmake \
+  --build build/dgr-004-final/build --target llama-simple -j$(nproc)
+g++ -std=c++17 -Ibuild/dgr-004-final/source -Ibuild/dgr-004-final/source/include \
+  -Ibuild/dgr-004-final/source/ggml/include -Lbuild/dgr-004-final/build/bin \
+  packages/node/native/llama/meshnet-range-loader.cpp -lllama \
+  -Wl,-rpath,build/dgr-004-final/build/bin \
+  -o build/dgr-004-final/build/bin/meshnet-range-loader
+
+# Focused tests (no model download)
+PYTHONPATH=packages/node:packages/tracker:packages/contracts
+/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python \
+  -m pytest -q tests/test_llama_cpp_dependency.py
+
+# Real-model integration test (opt-in, downloads ~670 MB)
+MESHNET_ENABLE_REAL_INFERENCE_TESTS=1 PYTHONPATH=... \
+  /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python \
+  -m pytest -q tests/test_gguf_distributed_load.py
+```
+
+## Limitations
+
+- Dense-Llama architecture only (LLM_ARCH_LLAMA). GLM/MoE/MLA is DGR-006+.
+- Graph-level endpoint assertions (`has_token_embeddings`, `has_output_head`) were
+  simplified to only `start_layer`/`end_layer`/`mapped_bytes`/`resident_bytes` in
+  the patch as merged. Full endpoint tracking is available via the integration test
+  by observing which tensors are registered per shard.
+- Loading the full `llama-simple` CLI requires reconfiguring with `-DLLAMA_BUILD_EXAMPLES=ON`.
+  The smoke-only build (`llama-gguf-hash`) is sufficient for patch verification.
+- TinyLlama 1.1B is a baseline dense-Llama architecture only.
+
+## Commits
+
+- `252d131` feat: DGR-005A dense Llama owned range loader
+- `f844ae6` feat: DGR-005B endpoint ownership and graph guard
+- `31065c0` feat: distributed GGUF shard load integration test with TinyLlama 1.1B
+- `d6b808d` chore: mark DGR-005 passes:true in PRD

.scratch/distributed-gguf-runtime/evidence/DGR-006/README.md

@@ -0,0 +1,71 @@
+# DGR-006 — architecture-defined boundary input/output
+
+Status: complete deterministic/offline contract and dense-fixture evidence.
+
+## Result
+
+The native protocol now carries a versioned `TensorBundle` on the decode fast
+path. It includes explicit architecture and boundary-point metadata. Its legacy
+`NamedTensor` field remains a compact one-tensor encoding for certified dense
+boundaries; the writer deliberately selects it only for a one-tensor bundle and
+new readers wrap that representation into a bundle. The bundle is authoritative
+when present, allowing MoE/MLA sidebands without a second transport contract.
+
+`architecture_boundary.py` is the fail-closed adapter boundary. Dense head
+Shards accept token IDs and own embedding. Middle/tail Shards accept only a
+validated bundle. Dense, MoE, and MLA route through explicit adapters; unknown
+architectures are rejected. The dense F32 fixture proves whole-model versus
+two-range boundary parity without model downloads or real inference.
+
+Tail output is explicit in the schema: `TailResult` contains either logits or a
+sampled token and binds sampling parameters plus request ID, runtime recipe,
+chat template/version, reasoning mode, and architecture identity. The adapter
+builds and validates the serialized protobuf result before returning it.
+
+## Files changed
+
+- `packages/node/native/proto/shard_runtime.proto`
+- `packages/node/meshnet_node/native_protocol/{codec.py,__init__.py,conformance.py,generated/*}`
+- `packages/node/native/testdata/decode_step_golden.binpb`
+- `packages/node/native/tests/test_shard_protocol_conformance.cpp`
+- `packages/node/meshnet_node/architecture_boundary.py`
+- `tests/test_architecture_boundary.py`
+- `tests/test_native_shard_protocol.py`
+- `packages/node/native/README.md`
+
+## Commands and results
+
+All Python commands used `/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python`.
+All native commands used `/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/cmake`.
+
+```text
+python scripts/generate_native_protocol.py --check       -> passed
+python scripts/generate_protocol_goldens.py --check      -> passed
+pytest -q tests/test_architecture_boundary.py \
+  tests/test_native_shard_protocol.py tests/test_llama_cpp_dependency.py
+                                                    -> 59 passed
+cmake -S packages/node/native -B build/native \
+  -DCMAKE_PREFIX_PATH=/tmp/pbsrc/install                -> configured
+cmake --build build/native -j$(nproc)                   -> built shard_protocol_conformance
+ctest --test-dir build/native --output-on-failure       -> 1/1 passed
+python -m compileall -q packages tests                  -> passed
+git diff --check                                        -> passed
+pytest -q                                               -> 917 passed, 18 skipped
+```
+
+## Compatibility and limitations
+
+- Existing Nodes that send `DecodeStep.tensor` are accepted. New multi-tensor
+  Nodes require the versioned bundle and older Nodes safely preserve it as an
+  unknown field rather than interpreting it as a single tensor.
+- The committed C++ conformance vector covers the multi-tensor decode path.
+- The dense parity result is a deterministic F32 structural fixture, not real
+  GGUF inference or GLM certification. No real inference was run.
+- MoE and MLA adapters define and validate their sideband contracts but are not
+  architecture certifications. DGR-019 owns GLM MoE/MLA/DSA/IndexShare semantics.
+
+## Handoff
+
+DGR-007 can key its Hot KV state to the validated decoded bundle. DGR-008 can
+translate the generated `TailResult` and decode bundle over gRPC. DGR-019 must
+replace the generic MoE/MLA sideband names with exact certified GLM semantics.

.scratch/distributed-gguf-runtime/evidence/DGR-017/README.md

@@ -0,0 +1,114 @@
+# DGR-017 evidence — superseded backlog cleanup
+
+**Completed:** 2026-07-16
+**Branch:** `ralph/distributed-gguf-runtime`
+**Planning checkpoint before cleanup:** `81b1fa6`
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json`
+
+## Outcome
+
+The old DGR-001…016 completion claims and active artifacts were reconciled against the live branch. No old pass state transferred to the new implementation roadmap.
+
+The active `packages/` and `tests/` trees were restored exactly to `origin/master`. The branch therefore no longer exposes a nominal GGUF startup path backed by unimplemented transport methods, a protobuf-only native scaffold, or isolated synthetic scheduler/cache/failure modules as if they were a working distributed GGUF runtime.
+
+## Classification and disposition
+
+### Retained
+
+- Accepted ADRs and repository research, including `docs/research/colibri-implementation-audit.md`.
+- The authoritative 55-story roadmap `DGR-017…071` and its generated issue specifications.
+- The real public-relay smoke benchmark, moved with provenance to `legacy-public-relay-smoke-benchmark.json`.
+- Git history containing the complete superseded implementation/reference work.
+
+### Removed from the active tree
+
+- Legacy issue specifications DGR-001…016 and their stale/blocked/synthetic evidence directories.
+- The nonfunctional `gguf_backend` startup path whose gRPC execution methods raised not-implemented errors.
+- Synthetic/reference-only boundary, Hot KV, scheduler, failure, recipe, ownership, and native-protocol modules that were not a real llama.cpp Shard runtime.
+- The protobuf round-trip-only native scaffold, placeholder llama.cpp patch, generated bindings/build workspace, and associated tests.
+- Tracker/admission/source modifications coupled to that superseded scaffold.
+
+### Confirmed absent and still required
+
+- Real standalone C++ gRPC Shard worker.
+- Exact pinned llama.cpp manifest and verified patch stack.
+- Range-aware GGUF tensor ownership and real ranged execution.
+- Real Shard-local llama.cpp KV/V4 auxiliary state.
+- DeepSeek V4 boundary adapter and ranged parity.
+- Real multi-machine DeepSeek V4 alpha or beta acceptance.
+
+These remain `passes: false` in DGR-018…071.
+
+## Before-cleanup baseline
+
+Command:
+
+```bash
+.venv-rocm/bin/python -m pytest -q \
+  tests/test_performance_contract.py tests/test_native_shard_protocol.py \
+  tests/test_gguf_ownership.py tests/test_boundary_adapter.py \
+  tests/test_hot_kv_state.py tests/test_gguf_backend.py \
+  tests/test_batch_scheduler.py tests/test_failure_semantics.py \
+  tests/test_llama_worker_build.py tests/test_node_admission.py \
+  tests/test_node_capability.py tests/test_tracker_capability_admission.py
+```
+
+Result:
+
+```text
+216 passed, 2 skipped, 1 failed, 1 warning
+```
+
+The failure was a synthetic capability-test helper `KeyError: 'compatibility_fingerprint'`. The warning was a pre-existing heartbeat-thread `SystemExit` warning.
+
+## Cleanup verification
+
+### Source equality
+
+Command:
+
+```bash
+git diff --quiet origin/master -- packages tests
+```
+
+Result:
+
+```text
+packages_tests_match_origin_master=yes
+```
+
+The staged cleanup removes approximately 15.3k obsolete source/test/evidence lines from the active branch.
+
+### Cleanup-relevant regression suite
+
+Command:
+
+```bash
+.venv-rocm/bin/python -m pytest -q \
+  tests/test_node_admission.py tests/test_node_capability.py \
+  tests/test_tracker_capability_admission.py \
+  tests/test_kv_cache_distributed.py tests/test_real_distributed_inference.py
+```
+
+Result:
+
+```text
+119 passed, 2 skipped, 1 warning in 15.90s
+```
+
+The warning is the same pre-existing heartbeat-thread `SystemExit` warning.
+
+### Known `origin/master` limitations
+
+The wider routing run produced `210 passed, 2 skipped, 4 failed, 1 warning`. Each failure reproduced individually while `packages/` and `tests/` matched `origin/master` exactly:
+
+- `test_tracker_models_endpoint_lists_registered_hf_repo_and_short_name_alias`
+- `test_torch_node_applies_tracker_load_shard_directive`
+- `test_shard_heal_cycle_surviving_node_covers_dead_peers_gap`
+- `test_a_node_with_an_unusable_precision_covers_no_layers`
+
+They are recorded as pre-existing baseline defects and were not repaired or hidden by this cleanup story.
+
+## Dependency handoff
+
+DGR-018 and later stories must start from the cleaned upstream-equivalent runtime tree. Reuse concepts from superseded commits only by explicitly porting the smallest verified slice under the new story’s contracts, tests, and evidence gates. Git history is provenance, not completion evidence.

.scratch/distributed-gguf-runtime/evidence/DGR-017/commands.txt

@@ -0,0 +1,115 @@
+# DGR-017 — exact commands and real results (2026-07-13)
+# Project venv is used explicitly. NOTE: bare `pytest` on this machine resolves to
+# Hermes Agent's internal venv (/home/popov/.hermes/...), which DGR-001 already
+# recorded as the cause of a bogus "suite is blocked" claim. Always use $VP.
+VP=/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python   # Python 3.14.6
+
+# ---------------------------------------------------------------------------
+# 1. Resolve the target from upstream metadata ONLY. No weight payload downloaded.
+#    Sizes and SHA-256 come from the HF LFS pointer metadata (paths-info), not the blobs.
+# ---------------------------------------------------------------------------
+curl -sS "https://huggingface.co/api/models/zai-org/GLM-5.2"
+  -> sha b4734de4facf877f85769a911abafc5283eab3d9  (matches the roadmap pin)
+  -> license mit, lastModified 2026-07-02T08:08:14.000Z
+
+curl -sS "https://huggingface.co/api/models/unsloth/GLM-5.2-GGUF"
+  -> sha abc55e72527792c6e77069c99b4cb7de16fa9f23  (matches the roadmap pin)
+  -> license mit, lastModified 2026-06-23T15:18:23.000Z
+  -> six UD-IQ1_S shards present
+
+curl -sS -X POST -d '{"paths": [<6 UD-IQ1_S shards>]}' \
+  "https://huggingface.co/api/models/unsloth/GLM-5.2-GGUF/paths-info/abc55e7..."
+  -> all six shards resolved with exact size + LFS oid (sha256)
+  -> sum = 216,715,360,960 bytes = 201.832 GiB = 216.715 GB
+  -> matches the roadmap's published byte total EXACTLY
+  -> UD-IQ1_M fallback = 228,492,966,624 bytes = 212.801 GiB (also matches)
+
+curl -sS ".../resolve/b4734de4.../{config.json,chat_template.jinja,
+          generation_config.json,tokenizer_config.json}"
+  -> config.json           3732 B  sha256 185f93ee6d12548e16a847e279dc0c3c90b1524c970b0866b42fb545747d859a
+  -> chat_template.jinja   5076 B  sha256 172dc74a35e1752df75ecfb2b2cf9326d2852bb1379868ebeec9571654489679
+  -> generation_config.json 194 B  sha256 ac76b43d8683d3b930126870fc8be73d8679308fe752fa1f381096d8354f6a55
+  -> tokenizer_config.json  761 B  sha256 98b1271574f41abf89427ae2dda030d94dc9478f0edc5a8bd240db213c6fd5fc
+
+# ---------------------------------------------------------------------------
+# 2. Verify the checked-in pins still match live upstream (reproducible, no weights)
+# ---------------------------------------------------------------------------
+$VP scripts/refresh_glm_target_manifest.py --check
+  -> "target manifest and architecture snapshot match upstream"
+  -> exit 0
+
+# ---------------------------------------------------------------------------
+# 3. Upstream llama.cpp / donor status refresh (GitHub REST API, read-only)
+# ---------------------------------------------------------------------------
+curl -sS "https://api.github.com/repos/ggml-org/llama.cpp/issues/{24730,24770,25407,24231}"
+  -> #24730 issue  OPEN    "Feature Request: Support for GLM 5.2"
+  -> #24770 PR     MERGED  2026-06-20  dense-MLA compatibility loader (DSA tensors optional)
+  -> #24231 PR     MERGED  2026-07-11  generic GGML_OP_LIGHTNING_INDEXER  [CHANGED since roadmap]
+  -> #25407 PR     OPEN    updated 2026-07-13, non-draft, 12 files, +414/-7  GLM 5.2 Indexer support
+curl -sS "https://api.github.com/repos/Mesh-LLM/mesh-llm{,/branches/feat%2Fjianyang-glm-52}"
+  -> Apache-2.0, 2048 stars, branch head 9bd18f1509dff7fac21578635084035b3ba90a38 (2026-07-12)
+  -> recorded as donor only; nothing forked, nothing adopted
+
+# ---------------------------------------------------------------------------
+# 4. Seal the alpha contract (digest over its own canonical content)
+# ---------------------------------------------------------------------------
+$VP -c "seal_contract(...)"  -> contract_sha256 aab23220280c053a3c14ff559df3cb5c9e1bf7f0f7188c6519e2e9d9ad036ed9
+
+# ---------------------------------------------------------------------------
+# 5. Generate the machine-readable resource plan from the pinned artifact
+# ---------------------------------------------------------------------------
+PYTHONPATH=packages/node $VP <generate resource-plan.json>
+  -> manifest_sha256            0b6aed04479d204902bb64c0203f1a46cab26a47b378ecccf85237b63f6c1962
+  -> architecture_sha256        253fbd94b06b42acc4724ec2c7f33914e2d4cc43f54a36dff6af19a80ae6ceb1
+  -> alpha_contract_sha256      aab23220280c053a3c14ff559df3cb5c9e1bf7f0f7188c6519e2e9d9ad036ed9
+  -> tier arithmetic minimum    32:9  48:6  64:4  96:3  128:2   (reproduces the roadmap table)
+  -> tier recommended           32:10 48:6  64:5  96:3  128:3   (reproduces the roadmap table)
+  -> 5x64 GiB unified           fits, +53.28 GiB headroom
+  -> 3x96 GiB unified           fits, +27.68 GiB headroom
+  -> 2x128 / 4x64 (fit probes)  fit with only +2.08 GiB headroom across the WHOLE route
+  -> 2x112 GiB (= 224 GiB, the hard-fit floor)  DOES NOT FIT: -23.52 GiB
+  -> 3x64 GiB                   does not fit: -49.12 GiB
+
+# ---------------------------------------------------------------------------
+# 6. Quality gates (project .venv, deterministic, offline, GPU-free)
+# ---------------------------------------------------------------------------
+$VP -m pytest -q tests/test_glm_alpha_target.py
+  -> 97 passed in 0.12s
+  -> includes coordinated shard/config substitution, malformed telemetry, and
+     contract-ID reseal rejection tests added during controller review
+
+$VP -m pip wheel --no-deps packages/node -w /tmp/dgr017-wheel
+$VP -m pip install --no-deps --target /tmp/dgr017-install /tmp/dgr017-wheel/*.whl
+$VP -I -c "... from meshnet_node.glm_alpha import load_locked_target ..."
+  -> INSTALLED_WHEEL_PASS
+  -> packaged alpha-contract.json, target-manifest.json, and architecture-snapshot.json
+     load and cross-bind successfully outside the source tree
+
+$VP -m compileall -q packages tests
+  -> exit 0
+
+git diff --check
+  -> exit 0
+
+$VP -m pytest -q            # full deterministic suite
+  -> first final run: 1 failed, 851 passed, 13 skipped; only the tracker cancellation
+     race already documented by DGR-001/DGR-002 failed
+$VP -m pytest -q tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
+  -> 1 passed, repeated 5/5 in isolation
+$VP -m pytest -q            # integrated rerun
+  -> 852 passed, 13 skipped in 253.30s (0:04:13)
+
+# ---------------------------------------------------------------------------
+# 7. Late independent-review repair (2026-07-14)
+# ---------------------------------------------------------------------------
+PYTHONPATH=packages/node $VP -m pytest -q tests/test_glm_alpha_target.py
+  -> 99 passed in 0.15s
+  -> adds trusted-v1-digest rejection after coordinated mutation + reseal
+  -> adds nested parsed-state immutability and isolated to_dict() coverage
+
+$VP -m pytest -q            # after DGR-003 integration and DGR-017 repair
+  -> first run: 871 passed, 13 skipped, 1 known cancellation-race failure
+$VP -m pytest -q tests/test_tracker_routing.py::test_tracker_dashboard_can_cancel_inflight_proxy
+  -> 5/5 passed in isolation
+$VP -m pytest -q            # integrated rerun
+  -> 872 passed, 13 skipped in 253.46s (0:04:13)

.scratch/distributed-gguf-runtime/evidence/DGR-017/legacy-public-relay-smoke-benchmark.json

@@ -0,0 +1,83 @@
+{
+  "schema_version": 1,
+  "executed_at_utc": "2026-07-15T10:41:14Z",
+  "test_kind": "public-relay-single-node-streaming-smoke-benchmark",
+  "target": {
+    "public_chat_endpoint": "https://meshnet.2.d-popov.com/v1/chat/completions",
+    "relay_url": "wss://meshnet.2.d-popov.com/ws",
+    "model": "qwen2.5-0.5b-instruct",
+    "quantization": "bfloat16"
+  },
+  "recovery": {
+    "problem": "The local node's capability proof had expired and its port-7000 HTTP server had wedged with CLOSE-WAIT sockets.",
+    "action": "Gracefully restarted the local public-tracker meshnet-node process on port 7000.",
+    "startup_validation": {
+      "device": "cuda",
+      "capability_proof_ms": 336,
+      "node_id": "7j77FsPY-b32476219492",
+      "relay_addr": "wss://meshnet.2.d-popov.com/rpc/7j77FsPY1evV8tuf-7000"
+    }
+  },
+  "tracker_admission_after_recovery": {
+    "node_id": "7j77FsPY-b32476219492",
+    "alive": true,
+    "status": "ready",
+    "capability_state": "admitted",
+    "routable": true,
+    "route_hops": 1
+  },
+  "client_measurements": {
+    "warmup": {
+      "http_status": 200,
+      "ttft_ms": 420.8,
+      "elapsed_ms": 610.23,
+      "response_text": "MeshNet Relay Benchmark Passed"
+    },
+    "runs": [
+      {
+        "run": 1,
+        "ttft_ms": 376.04,
+        "elapsed_ms": 458.65,
+        "response_text": "relay benchmark pass"
+      },
+      {
+        "run": 2,
+        "ttft_ms": 258.33,
+        "elapsed_ms": 336.71,
+        "response_text": "relay benchmark pass"
+      },
+      {
+        "run": 3,
+        "ttft_ms": 288.26,
+        "elapsed_ms": 363.2,
+        "response_text": "relay benchmark pass"
+      }
+    ],
+    "p50_ttft_ms": 288.26,
+    "p50_elapsed_ms": 363.2
+  },
+  "tracker_relay_evidence": [
+    {
+      "status": 200,
+      "relay": true,
+      "node_id": "7j77FsPY-b32476219492",
+      "tokens": 11,
+      "elapsed_seconds": 0.1686,
+      "tokens_per_sec": 65.2541
+    },
+    {
+      "status": 200,
+      "relay": true,
+      "node_id": "7j77FsPY-b32476219492",
+      "tokens": 11,
+      "elapsed_seconds": 0.1891,
+      "tokens_per_sec": 58.1799
+    }
+  ],
+  "scope_and_remaining_work": {
+    "validated": "Public HTTPS chat endpoint routed a streaming request through the tracker relay to the local CUDA node and completed with HTTP 200.",
+    "not_validated": "Two-node shard routing was not run because the remote node 5gMLrmyB-88f5cba044d0 still had an expired capability proof and was not routable.",
+    "next_gate": "Refresh the remote node capability proof, then load a multi-node-compatible assignment and repeat the benchmark through the public tracker relay."
+  },
+  "reproduction": "Use a valid bearer API key with the public /v1/chat/completions endpoint and stream a short qwen2.5-0.5b-instruct request. Do not connect directly to private node HTTP endpoints; the tracker relay is the required path."
+}

.scratch/distributed-gguf-runtime/evidence/DGR-017/resource-plan.json

@@ -0,0 +1,255 @@
+{
+  "generated_by": "DGR-017 meshnet_node.glm_alpha.planner",
+  "target": {
+    "gguf_repo_id": "unsloth/GLM-5.2-GGUF",
+    "gguf_revision": "abc55e72527792c6e77069c99b4cb7de16fa9f23",
+    "quantization": "UD-IQ1_S",
+    "total_bytes": 216715360960,
+    "total_gib": 201.832,
+    "total_gb": 216.715
+  },
+  "manifest_sha256": "0b6aed04479d204902bb64c0203f1a46cab26a47b378ecccf85237b63f6c1962",
+  "architecture_snapshot_sha256": "253fbd94b06b42acc4724ec2c7f33914e2d4cc43f54a36dff6af19a80ae6ceb1",
+  "alpha_contract_sha256": "aab23220280c053a3c14ff559df3cb5c9e1bf7f0f7188c6519e2e9d9ad036ed9",
+  "kv_assumptions": {
+    "dtype": "Q8_0",
+    "bytes_per_value": 1.0625,
+    "context_tokens": 16384,
+    "concurrency": 1,
+    "indexer_layout": "conservative",
+    "mla_values_per_token_per_layer": 576,
+    "backbone_layers": 78,
+    "indexer_full_layers": 21,
+    "note": "Alpha budgets indexer keys across all 78 layers (current experimental DSA layout), not only the 21 Full layers."
+  },
+  "kv_table_gib": {
+    "16384": {
+      "mla_only_q8_gib": 0.73,
+      "optimized_dsa_q8_gib": 0.77,
+      "conservative_dsa_q8_gib": 0.89,
+      "conservative_dsa_f16_gib": 1.68
+    },
+    "131072": {
+      "mla_only_q8_gib": 5.83,
+      "optimized_dsa_q8_gib": 6.18,
+      "conservative_dsa_q8_gib": 7.12,
+      "conservative_dsa_f16_gib": 13.41
+    },
+    "1048576": {
+      "mla_only_q8_gib": 46.62,
+      "optimized_dsa_q8_gib": 49.41,
+      "conservative_dsa_q8_gib": 56.98,
+      "conservative_dsa_f16_gib": 107.25
+    }
+  },
+  "aggregate_hard_fit_floor_gib": 224.0,
+  "aggregate_floor_class": "experimental_hard_fit_floor",
+  "placement_imbalance_factor": 1.1,
+  "tier_table": {
+    "32": {
+      "physical_usable_gib": 32.0,
+      "reserve_gib": 8.0,
+      "placement_budget_gib": 24.0,
+      "weight_gib": 201.832,
+      "kv_gib": 0.89,
+      "total_placement_gib": 202.722,
+      "arithmetic_minimum_nodes": 9,
+      "recommended_nodes": 10,
+      "imbalance_factor": 1.1
+    },
+    "48": {
+      "physical_usable_gib": 48.0,
+      "reserve_gib": 9.6,
+      "placement_budget_gib": 38.4,
+      "weight_gib": 201.832,
+      "kv_gib": 0.89,
+      "total_placement_gib": 202.722,
+      "arithmetic_minimum_nodes": 6,
+      "recommended_nodes": 6,
+      "imbalance_factor": 1.1
+    },
+    "64": {
+      "physical_usable_gib": 64.0,
+      "reserve_gib": 12.8,
+      "placement_budget_gib": 51.2,
+      "weight_gib": 201.832,
+      "kv_gib": 0.89,
+      "total_placement_gib": 202.722,
+      "arithmetic_minimum_nodes": 4,
+      "recommended_nodes": 5,
+      "imbalance_factor": 1.1
+    },
+    "96": {
+      "physical_usable_gib": 96.0,
+      "reserve_gib": 19.2,
+      "placement_budget_gib": 76.8,
+      "weight_gib": 201.832,
+      "kv_gib": 0.89,
+      "total_placement_gib": 202.722,
+      "arithmetic_minimum_nodes": 3,
+      "recommended_nodes": 3,
+      "imbalance_factor": 1.1
+    },
+    "128": {
+      "physical_usable_gib": 128.0,
+      "reserve_gib": 25.6,
+      "placement_budget_gib": 102.4,
+      "weight_gib": 201.832,
+      "kv_gib": 0.89,
+      "total_placement_gib": 202.722,
+      "arithmetic_minimum_nodes": 2,
+      "recommended_nodes": 3,
+      "imbalance_factor": 1.1
+    }
+  },
+  "routes": {
+    "recommended_5x64_unified": {
+      "node_count": 5,
+      "aggregate_usable_gib": 320.0,
+      "aggregate_placement_budget_gib": 256.0,
+      "required_placement_gib": 202.722,
+      "fits": true,
+      "meets_hard_fit_floor": true,
+      "no_single_node_can_admit_target": true,
+      "headroom_gib": 53.278,
+      "reasons": []
+    },
+    "recommended_3x96_unified": {
+      "node_count": 3,
+      "aggregate_usable_gib": 288.0,
+      "aggregate_placement_budget_gib": 230.4,
+      "required_placement_gib": 202.722,
+      "fits": true,
+      "meets_hard_fit_floor": true,
+      "no_single_node_can_admit_target": true,
+      "headroom_gib": 27.678,
+      "reasons": []
+    },
+    "recommended_3x128_unified": {
+      "node_count": 3,
+      "aggregate_usable_gib": 384.0,
+      "aggregate_placement_budget_gib": 307.2,
+      "required_placement_gib": 202.722,
+      "fits": true,
+      "meets_hard_fit_floor": true,
+      "no_single_node_can_admit_target": true,
+      "headroom_gib": 104.478,
+      "reasons": []
+    },
+    "fit_probe_2x128_unified": {
+      "node_count": 2,
+      "aggregate_usable_gib": 256.0,
+      "aggregate_placement_budget_gib": 204.8,
+      "required_placement_gib": 202.722,
+      "fits": true,
+      "meets_hard_fit_floor": true,
+      "no_single_node_can_admit_target": true,
+      "headroom_gib": 2.078,
+      "reasons": []
+    },
+    "fit_probe_4x64_unified": {
+      "node_count": 4,
+      "aggregate_usable_gib": 256.0,
+      "aggregate_placement_budget_gib": 204.8,
+      "required_placement_gib": 202.722,
+      "fits": true,
+      "meets_hard_fit_floor": true,
+      "no_single_node_can_admit_target": true,
+      "headroom_gib": 2.078,
+      "reasons": []
+    },
+    "hard_fit_floor_2x112_unified": {
+      "node_count": 2,
+      "aggregate_usable_gib": 224.0,
+      "aggregate_placement_budget_gib": 179.2,
+      "required_placement_gib": 202.722,
+      "fits": false,
+      "meets_hard_fit_floor": true,
+      "no_single_node_can_admit_target": true,
+      "headroom_gib": -23.522,
+      "reasons": [
+        "aggregate placement budget 179.2 GiB is below the 202.7 GiB the target needs after each node's reserve"
+      ]
+    },
+    "insufficient_3x64_unified": {
+      "node_count": 3,
+      "aggregate_usable_gib": 192.0,
+      "aggregate_placement_budget_gib": 153.6,
+      "required_placement_gib": 202.722,
+      "fits": false,
+      "meets_hard_fit_floor": false,
+      "no_single_node_can_admit_target": true,
+      "headroom_gib": -49.122,
+      "reasons": [
+        "aggregate placement budget 153.6 GiB is below the 202.7 GiB the target needs after each node's reserve",
+        "aggregate usable memory 192.0 GiB is below the 224 GiB experimental hard-fit floor"
+      ]
+    }
+  },
+  "seams": {
+    "3_nodes_2.5gbe": {
+      "node_count": 3,
+      "seam_count": 2,
+      "hidden_size": 6144,
+      "bytes_per_token_per_seam": 12288,
+      "prefill_bytes_per_seam": 201326592,
+      "decode_bytes_per_seam_per_token": 12288,
+      "dsa_sideband_bytes_per_query": 8192,
+      "link_rate_gbps": 2.5,
+      "meets_alpha_minimum": true,
+      "is_recommended_link": false,
+      "decode_serialization_ms_per_token": 0.0786,
+      "decode_latency_ms_per_token": 1.0,
+      "decode_bandwidth_share_ms_per_token": 0.0786,
+      "prefill_serialization_ms": 1288.49
+    },
+    "3_nodes_10.0gbe": {
+      "node_count": 3,
+      "seam_count": 2,
+      "hidden_size": 6144,
+      "bytes_per_token_per_seam": 12288,
+      "prefill_bytes_per_seam": 201326592,
+      "decode_bytes_per_seam_per_token": 12288,
+      "dsa_sideband_bytes_per_query": 8192,
+      "link_rate_gbps": 10.0,
+      "meets_alpha_minimum": true,
+      "is_recommended_link": true,
+      "decode_serialization_ms_per_token": 0.0197,
+      "decode_latency_ms_per_token": 1.0,
+      "decode_bandwidth_share_ms_per_token": 0.0197,
+      "prefill_serialization_ms": 322.123
+    },
+    "5_nodes_2.5gbe": {
+      "node_count": 5,
+      "seam_count": 4,
+      "hidden_size": 6144,
+      "bytes_per_token_per_seam": 12288,
+      "prefill_bytes_per_seam": 201326592,
+      "decode_bytes_per_seam_per_token": 12288,
+      "dsa_sideband_bytes_per_query": 8192,
+      "link_rate_gbps": 2.5,
+      "meets_alpha_minimum": true,
+      "is_recommended_link": false,
+      "decode_serialization_ms_per_token": 0.1573,
+      "decode_latency_ms_per_token": 2.0,
+      "decode_bandwidth_share_ms_per_token": 0.1573,
+      "prefill_serialization_ms": 2576.98
+    },
+    "5_nodes_10.0gbe": {
+      "node_count": 5,
+      "seam_count": 4,
+      "hidden_size": 6144,
+      "bytes_per_token_per_seam": 12288,
+      "prefill_bytes_per_seam": 201326592,
+      "decode_bytes_per_seam_per_token": 12288,
+      "dsa_sideband_bytes_per_query": 8192,
+      "link_rate_gbps": 10.0,
+      "meets_alpha_minimum": true,
+      "is_recommended_link": true,
+      "decode_serialization_ms_per_token": 0.0393,
+      "decode_latency_ms_per_token": 2.0,
+      "decode_bandwidth_share_ms_per_token": 0.0393,
+      "prefill_serialization_ms": 644.245
+    }
+  }
+}

.scratch/distributed-gguf-runtime/evidence/DGR-017/upstream-status.json

@@ -0,0 +1,89 @@
+{
+  "observed_at": "2026-07-13",
+  "observed_by": "DGR-017",
+  "method": "GitHub REST API (api.github.com), read-only; no fork, no clone, no patch adopted",
+  "refresh_note": "The roadmap's 2026-07-13 observations were re-verified against live upstream. One item changed: PR #24231 is now MERGED (2026-07-11), which the roadmap already anticipated as 'generic CPU lightning-indexer support is merged'.",
+  "llama_cpp": {
+    "repo": "ggml-org/llama.cpp",
+    "items": [
+      {
+        "ref": "issue #24730",
+        "url": "https://github.com/ggml-org/llama.cpp/issues/24730",
+        "title": "Feature Request: Support for GLM 5.2",
+        "type": "issue",
+        "state": "open",
+        "updated_at": "2026-07-03T22:02:15Z",
+        "meaning": "The umbrella GLM-5.2 support request is still open. GLM-5.2 is not fully supported upstream."
+      },
+      {
+        "ref": "PR #24770",
+        "url": "https://github.com/ggml-org/llama.cpp/pull/24770",
+        "title": "model : glm-dsa load DSA indexer tensors as optional",
+        "type": "pull_request",
+        "state": "closed",
+        "merged_at": "2026-06-20T10:48:24Z",
+        "meaning": "MERGED. GLM-5.2 loads, but through a dense-MLA compatibility path with DSA indexer tensors treated as optional. This is the fallback the alpha contract explicitly refuses: it can produce text without performing DSA/IndexShare computation."
+      },
+      {
+        "ref": "PR #24231",
+        "url": "https://github.com/ggml-org/llama.cpp/pull/24231",
+        "title": "New GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer",
+        "type": "pull_request",
+        "state": "closed",
+        "merged_at": "2026-07-11T09:39:07Z",
+        "meaning": "MERGED since the roadmap was written. A generic lightning-indexer op now exists in GGML. Backend coverage beyond CPU remains uneven and must be verified per backend by DGR-018, not assumed."
+      },
+      {
+        "ref": "PR #25407",
+        "url": "https://github.com/ggml-org/llama.cpp/pull/25407",
+        "title": "GLM 5.2 Indexer support",
+        "type": "pull_request",
+        "state": "open",
+        "draft": false,
+        "mergeable_state": "unstable",
+        "head_sha": "8dedd06415f36f10fc6091241a39b23c1bf0ee11",
+        "base": "master",
+        "commits": 6,
+        "changed_files": 12,
+        "additions": 414,
+        "deletions": 7,
+        "updated_at": "2026-07-13T15:28:51Z",
+        "meaning": "OPEN and actively moving (updated today). This is the real DSA/IndexShare implementation alpha needs. It is narrow — 12 files, +414/-7 — which is the single most important finding for donor policy: the semantics alpha requires are reviewable and trackable upstream, not a 261-patch fork."
+      }
+    ]
+  },
+  "capability_status_for_alpha": {
+    "gguf_load_of_UD-IQ1_S": "expected via merged #24770, unverified by this project; DGR-018 must prove it against the exact pinned artifact",
+    "moe_routing_and_shared_expert": "expected supported; unverified here",
+    "compressed_mla_kv": "supported via the dense-MLA compatibility path",
+    "dsa_lightning_indexer": "generic GGML op merged (#24231); GLM-5.2 wiring still open (#25407)",
+    "indexshare_full_shared_roles": "NOT upstream; only in open PR #25407",
+    "mtp_nextn": "not required for alpha; NextN tensors must be explicitly loaded or excluded, never silently reinterpreted",
+    "conclusion": "As of 2026-07-13 no released upstream llama.cpp performs native GLM-5.2 DSA + IndexShare. A stock pin today would satisfy 'it emits text' via the dense fallback and would FAIL the alpha semantic-correctness contract. This is the gating technical risk for DGR-004 and DGR-018."
+  },
+  "donor": {
+    "repo": "Mesh-LLM/mesh-llm",
+    "url": "https://github.com/Mesh-LLM/mesh-llm",
+    "license": "Apache-2.0",
+    "stars_observed": 2048,
+    "pushed_at": "2026-07-13T06:45:51Z",
+    "glm_branch": "feat/jianyang-glm-52",
+    "glm_branch_head": "9bd18f1509dff7fac21578635084035b3ba90a38",
+    "glm_branch_head_date": "2026-07-12T06:37:43Z",
+    "policy": "TEST AND PATCH DONOR ONLY. Do not adopt the fork, its scheduler, discovery, routing, public mesh, or package manager. Meshnet remains the sole control plane (RALPH-CONTEXT runtime decision, ADR-0020).",
+    "focused_candidates": [
+      "GLM DSA graph semantics",
+      "lightning indexer and sparse-attention tests",
+      "IndexShare metadata and Full/Shared role validation",
+      "top-k sideband shape and lifecycle",
+      "stage-local KV filtering",
+      "target parity and performance fixtures"
+    ],
+    "adoption_state": "none adopted in DGR-017. This story reads and records upstream state; it takes no patch and forks nothing."
+  },
+  "recommendation_for_dgr_004_and_dgr_018": [
+    "Track upstream PR #25407 rather than forking Mesh-LLM. At 12 files and +414/-7 it is small enough to review, reproduce, and carry as a numbered patch in the project's own pinned stack.",
+    "Any pin chosen before #25407 merges will load GLM-5.2 through the dense-MLA compatibility path. DGR-018 must therefore prove DSA/IndexShare are ACTIVE, not merely that the model emits text — the alpha contract already forbids the fallback.",
+    "Verify lightning-indexer backend coverage (#24231) on the specific backend the route will use. CPU support being merged says nothing about ROCm/HIP."
+  ]
+}

.scratch/distributed-gguf-runtime/evidence/DGR-018/BLOCKED.md

@@ -0,0 +1,53 @@
+# DGR-018 — BLOCKED: no 256-GiB-class oracle host
+
+Recorded: 2026-07-14 (MAINT-003). Preflight scripts preserved at commit
+`a0f28b5` ("chore: preserve DGR-018 preflight scripts (postponed)").
+
+## Blocker
+
+DGR-018 requires a 256-GiB-class host with at least **224 GiB
+runtime-accessible memory** (the DGR-017 experimental hard-fit floor for the
+whole-model `UD-IQ1_S` oracle) and **250 GB free storage** on one filesystem
+outside `/home` (216.715 GB artifact plus resume/temp headroom). The available
+development host fails both gates, so the whole-model oracle cannot be
+established. Per the issue's finish contract, no smaller model may be
+substituted.
+
+DGR-019 (needs the DGR-018 oracle for parity certification) and DGR-020
+(needs DGR-018 and DGR-019, plus enough physical consumer nodes that no single
+node admits the whole recipe) are blocked transitively.
+
+## Exact preflight output
+
+Command (offline; resolves everything from the pinned target manifest and
+never contacts the network):
+
+```
+$ python scripts/glm_whole_model_preflight.py
+target: UD-IQ1_S 216.715 GB, 6 shards @ abc55e725277
+[FAIL] storage: need >= 250 GB free on one filesystem outside ['/home']; observed no eligible filesystem
+[FAIL] memory: need >= 224 GiB runtime-accessible memory (DGR-017 experimental hard-fit floor); observed 124.9 GiB MemTotal
+destination: NONE — no filesystem outside ['/home'] has 250 GB free
+  - /run/media/popov/DATA (ext4): 74.2 GB free
+  - / (ext4): 51.1 GB free
+  - /run/media/popov/Windows (fuseblk): 26.0 GB free
+  - /run/media/popov/d (fuseblk): 5.1 GB free
+verdict: fail
+$ echo $?
+1
+```
+
+Host: Linux 7.0.14-101.fc43.x86_64 x86_64, `MemTotal: 130997376 kB`
+(124.9 GiB). The full machine-readable report (including the ordered
+download/verify plan against revision `abc55e72527792c6e77069c99b4cb7de16fa9f23`,
+manifest SHA-256 `0b6aed04479d204902bb64c0203f1a46cab26a47b378ecccf85237b63f6c1962`)
+is in [preflight.json](preflight.json).
+
+## How to resume
+
+1. On a qualifying host, run `python scripts/glm_whole_model_preflight.py`
+   (optionally `--dest DIR`); it must exit 0 with `verdict: pass`.
+2. Download shards in the preflight's ordered plan; verify each with
+   `python scripts/verify_glm_shards.py` before the next transfer starts.
+3. Proceed with the DGR-018 issue
+   (`.scratch/distributed-gguf-runtime/issues/18-certify-whole-model-glm-5-2-runtime-semantics.md`).

.scratch/distributed-gguf-runtime/evidence/DGR-018/README.md

@@ -0,0 +1,204 @@
+# DGR-018 evidence — canonical Ralph and Gitea metadata schema
+
+**Completed:** 2026-07-16
+**Branch:** `ralph/distributed-gguf-runtime`
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json`
+**Dependency:** DGR-017 (`evidence/DGR-017/README.md`) — cleaned backlog reconciled to `origin/master`; no old pass state transferred.
+
+## Objective
+
+Make `prd.json` the validated source from which Markdown (and, later, Gitea) issues
+can be generated losslessly, per
+`.scratch/distributed-gguf-runtime/issues/018-define-canonical-ralph-and-gitea-metadata-schema.md`.
+
+## Pre-existing state found (not caused by this story)
+
+Before any change in this session, `git status` showed `.scratch/distributed-gguf-runtime/prd.json`
+already modified in the working tree relative to `HEAD` (commit `369b207`), with no corresponding
+progress-log entry. Diffing against `HEAD` showed the working copy had **dropped** prd.json's
+top-level `sourceOfTruth`, `qualityGates`, `metadataSchema`, `milestones`, and `supersededStories`
+objects, while `userStories` itself was byte-identical to `HEAD`. This looked like an abandoned,
+uncommitted partial edit from a prior session, not intentional current work — those fields are
+exactly the schema/quality-gate/audit-provenance content this story depends on, and their loss
+wasn't explained by any acceptance criterion. They were restored (see "Changes" below) rather than
+silently accepted or discarded, per the instruction to investigate unexplained working-tree state
+before building on top of it.
+
+## Changes
+
+### `scripts/ralph_prd_schema.py` (new)
+
+Single module providing:
+
+- **Parse:** `load_prd(path)` — JSON load with clear `PrdValidationError`s for missing file /
+  invalid JSON / non-object document.
+- **Canonical schema registry:** `STORY_FIELDS` (name → required/type), `EXECUTION_MODES`,
+  `EVIDENCE_CLASSES`, `HARDWARE_FLAGS`, `UPSTREAM_FLAGS`, `TRIAGE_VALUES`. Covers every field named
+  in the acceptance criteria: stable `id`/`title`, `labels`, `milestone`, derived `type`
+  (`derive_type`), `dependsOn`, derived `blocks`, `triage`, `evidenceClass`, and
+  `hardware`/`model`/`upstream` flags.
+- **Structural validation:** `validate_schema(data)` — required fields, types, enum membership,
+  ID convention, `type:`/`priority:` label cardinality, non-empty `acceptanceCriteria`.
+- **Semantic validation:** `validate_semantics(data)` — unique IDs, unique titles, `dependsOn`
+  resolves to known stories (no self-dependency), dependency graph is acyclic (with a reported
+  cycle path on failure), `blocks` matches the dependency graph exactly (sorted set equality, not
+  superset), and `evidencePath` matches the per-story convention.
+- **Fresh vs. in-progress backlog:** `validate_fresh_backlog(data)` additionally requires every
+  story to start `passes: false` (for a backlog that hasn't started execution yet);
+  `validate_backlog(data)` is the composed check for a real, in-flight backlog where some stories
+  have legitimately completed.
+- **Self-consistency check:** `validate_metadata_schema_consistency(data)` — when prd.json declares
+  its own `metadataSchema`/`qualityGates` (as this one now does), verifies that self-documentation
+  hasn't drifted from what the validator actually enforces (enum sets, required/optional field
+  lists, presence of `qualityGates` and `generatedArtifactDisclaimer`). This is a no-op for minimal
+  fixture PRDs that don't carry that documentation.
+- **Generation (one-directional, prd.json → artifact):** `render_issue_markdown(story, data)`
+  renders the exact Markdown convention already used by
+  `.scratch/distributed-gguf-runtime/issues/*.md`, sourcing the "Shared quality gates" bullets from
+  `data["qualityGates"]` and the leading disclaimer from
+  `data["metadataSchema"]["generatedArtifactDisclaimer"]` (falling back to a module default only
+  when `data` omits them) — not from a duplicated Python string literal.
+  `to_gitea_issue_payload(story, data)` wraps the same body into a Gitea create-issue-shaped payload
+  (`title`, `body`, `labels`, `milestone`).
+- **Authority guard:** `check_generated_markdown_authority(text, disclaimer=...)` rejects generated
+  Markdown that's missing the disclaimer or that contains a conflicting authority claim (e.g. "this
+  file is authoritative"). There is deliberately no Markdown → prd.json parser, so a generated
+  artifact structurally cannot feed `passes` (or anything else) back into the authoritative source.
+- CLI: `python scripts/ralph_prd_schema.py validate <prd.json> [--fresh]` and
+  `... render <prd.json> <STORY-ID>`.
+
+### `.scratch/distributed-gguf-runtime/prd.json`
+
+- Restored the top-level `sourceOfTruth`, `qualityGates`, `milestones`, and `supersededStories`
+  objects to their `HEAD` content (see "Pre-existing state" above); `userStories` was already
+  identical to `HEAD` and is unchanged in content.
+- Extended `metadataSchema` (previously incomplete for this story's own acceptance criteria) with:
+  `requiredStoryFields` now also lists `notes` and `blocks` (present on all 55 stories); new
+  `optionalStoryFields: ["completionNotes"]`; new `hardwareValues`/`upstreamValues` enums (`model`
+  is documented as an open convention, not a closed enum, since quantization/model targets are
+  dynamic recipe inputs per `RALPH-CONTEXT.md`); new `typeDerivation` and `labelConventions`
+  (reserved prefixes, cardinality); new `generatedArtifactDisclaimer` (the exact string generated
+  artifacts must start with); extended `dependencyRules`/`authorityRule` prose to match what the
+  validator enforces.
+- Reworded `sourceOfTruth`'s stale "All stories are unimplemented ... passes=false" clause, which
+  was no longer accurate once DGR-017 completed.
+- Marked `DGR-018.passes = true` with `completionNotes` recording this story's outcome.
+
+### `.scratch/distributed-gguf-runtime/issues/018-define-canonical-ralph-and-gitea-metadata-schema.md`
+
+Regenerated via `render_issue_markdown` to reflect `passes: true` (checked acceptance criteria,
+"completed" status line, "Verified evidence" handoff line) — matching the same convention DGR-017's
+issue file already used for a completed story.
+
+### `tests/test_ralph_prd_schema.py` (new)
+
+108 deterministic, model-download-free, GPU-free tests:
+
+- **Parse** (4 tests): real backlog parses to 55 stories; missing file, invalid JSON, and
+  non-object documents raise `PrdValidationError`.
+- **Structural/semantic validation against the real backlog** (7 tests): passes `validate_schema`,
+  `validate_semantics`, and the composed `validate_backlog`; unique IDs/titles; all `dependsOn`
+  resolve; `blocks` matches the derived dependency graph for all 55 stories; no cycle; every
+  `passes: true` story carries `completionNotes` and an existing evidence README (a durable
+  invariant, not a hardcoded list of which stories have completed — that list will keep growing).
+- **Structural/semantic failure-mode fixtures** (13 tests): missing required field, bad enum, wrong
+  type, empty `acceptanceCriteria`, multiple `type:` labels, duplicate ID, duplicate title, unknown
+  dependency, self-dependency, dependency cycle, mismatched `blocks`, bad `evidencePath`.
+- **Fresh-backlog invariant** (3 tests): accepts all-`false`, rejects a premature `passes: true`,
+  and confirms `validate_backlog` (the in-progress variant) permits completed stories.
+- **prd.json-as-source-of-truth for boilerplate** (9 tests): `qualityGates`/`metadataSchema`
+  self-consistency checks (no-op without them, catches a drifted enum, catches a missing
+  `qualityGates`), `quality_gate_bullets` flattening order, `authority_disclaimer` precedence and
+  fallback, and 3 tests asserting the real backlog's declared schema matches the code, its 7
+  quality-gate bullets are intact, and its disclaimer matches the module default.
+- **`derive_type`** (4 tests): label-derived type, release-gate synthetic type for HITL gate
+  stories, `None` when absent, and confirmation that the real backlog's two release-gate stories
+  (`DGR-054`, `DGR-070`) derive `release-gate`.
+- **Markdown generation round trips** (55 parametrized + 6 tests): `render_issue_markdown` for
+  every story `DGR-017`..`DGR-071` is byte-for-byte identical to the corresponding file already in
+  `.scratch/distributed-gguf-runtime/issues/`; determinism; leading disclaimer; `Blocks (derived)`
+  rendering (`None` vs. listed); checkbox reflects `passes`; filename convention.
+- **Authority-claim rejection** (4 tests): accepts real generated text, rejects a missing
+  disclaimer, rejects an overriding claim, and confirms every committed issue file in
+  `.scratch/distributed-gguf-runtime/issues/` passes the check.
+- **Gitea payload generation** (3 tests): payload shape, body carries no information beyond what's
+  in prd.json, and every real story's payload is well-formed and authority-clean.
+
+## Commands and results
+
+```bash
+python3 -m pytest -q tests/test_ralph_prd_schema.py
+```
+```text
+108 passed in 0.16s
+```
+
+```bash
+python3 -m compileall -q packages tests
+```
+Exit code 0, no output (all files compile).
+
+```bash
+git diff --check
+```
+Exit code 0 (no whitespace errors).
+
+```bash
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json
+```
+```text
+OK: 55 stories validated.
+```
+
+```bash
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json --fresh
+```
+```text
+ERROR: DGR-017: fresh backlog requires passes=false, got True
+ERROR: DGR-018: fresh backlog requires passes=false, got True
+2 validation error(s).
+```
+Expected: `--fresh` is the invariant for a backlog that hasn't started execution; this backlog has
+legitimately completed two stories, so it correctly fails that stricter check while passing the
+plain (in-progress) `validate` command above.
+
+### Baseline: full repository suite (ad hoc `python3`, not a project venv)
+
+```bash
+python3 -m pytest -q
+```
+```text
+20 failed, 776 passed, 13 skipped, 2 warnings in 244.17s (0:04:04)
+```
+None of the failures touch `scripts/ralph_prd_schema.py` or `tests/test_ralph_prd_schema.py`
+(neither file existed before this story; this story adds no changes to `packages/`). Four of the
+20 failures reproduce exactly the pre-existing baseline defects DGR-017's evidence already recorded
+(`test_tracker_models_endpoint_lists_registered_hf_repo_and_short_name_alias`,
+`test_torch_node_applies_tracker_load_shard_directive`,
+`test_shard_heal_cycle_surviving_node_covers_dead_peers_gap`,
+`test_a_node_with_an_unusable_precision_covers_no_layers`). The remaining 16 (activation
+compression, dynamic routing, gossip/relay, manual route benchmark, openai gateway, TOPLoC
+calibration dispatch, tracker control plane) include a `ModuleNotFoundError: langchain` failure,
+indicating this ad hoc `python3` lacks the project's `dev` extras (`langchain-openai`, etc.) rather
+than a real regression; this environment has no project virtualenv (e.g. no `.venv-rocm`) to run
+against instead. Not investigated further as out of scope for this story.
+
+## Limitations
+
+- No real Gitea instance or API integration exists; `to_gitea_issue_payload` defines the payload
+  shape (title/body/labels/milestone) only. Creating issues against a live Gitea server is future
+  work, not claimed here.
+- `model` is intentionally validated as an open string, not a closed enum, per
+  `RALPH-CONTEXT.md`'s "Quantization and placement are dynamic recipe inputs" constraint; the schema
+  documents (`metadataSchema.modelConvention`) but does not restrict its value set.
+- Validation and generation were exercised only against this feature's `prd.json`
+  (`.scratch/distributed-gguf-runtime/prd.json`); `docs/prd.json` and other `.scratch/*/prd.json`
+  files in this repo use a materially different (simpler) shape and are out of scope.
+
+## Dependency handoff
+
+DGR-021 and DGR-025 (this story's derived `blocks`) may treat `prd.json`'s `metadataSchema`,
+`qualityGates`, and this validator/generator as stable. Any future field addition to a story shape
+must extend `STORY_FIELDS` in `scripts/ralph_prd_schema.py` and the corresponding
+`metadataSchema.requiredStoryFields`/`optionalStoryFields` in `prd.json` together —
+`validate_metadata_schema_consistency` fails closed if they drift apart.

.scratch/distributed-gguf-runtime/evidence/DGR-018/preflight.json

@@ -0,0 +1,140 @@
+{
+  "generated_by": "scripts/glm_whole_model_preflight.py",
+  "target": {
+    "gguf_repo_id": "unsloth/GLM-5.2-GGUF",
+    "gguf_revision": "abc55e72527792c6e77069c99b4cb7de16fa9f23",
+    "quantization": "UD-IQ1_S",
+    "shard_count": 6,
+    "total_bytes": 216715360960,
+    "total_gb": 216.715,
+    "manifest_sha256": "0b6aed04479d204902bb64c0203f1a46cab26a47b378ecccf85237b63f6c1962"
+  },
+  "forbidden_path_prefixes": [
+    "/home"
+  ],
+  "mounts": [
+    {
+      "mountpoint": "/run/media/popov/DATA",
+      "fstype": "ext4",
+      "total_gb": 1208.8,
+      "free_gb": 74.2,
+      "free_bytes": 74201321472,
+      "forbidden": false,
+      "eligible": false
+    },
+    {
+      "mountpoint": "/",
+      "fstype": "ext4",
+      "total_gb": 217.7,
+      "free_gb": 51.1,
+      "free_bytes": 51073683456,
+      "forbidden": false,
+      "eligible": false
+    },
+    {
+      "mountpoint": "/run/media/popov/Windows",
+      "fstype": "fuseblk",
+      "total_gb": 434.9,
+      "free_gb": 26.0,
+      "free_bytes": 25964466176,
+      "forbidden": false,
+      "eligible": false
+    },
+    {
+      "mountpoint": "/run/media/popov/d",
+      "fstype": "fuseblk",
+      "total_gb": 161.1,
+      "free_gb": 5.1,
+      "free_bytes": 5148332032,
+      "forbidden": false,
+      "eligible": false
+    }
+  ],
+  "chosen_destination": null,
+  "checks": [
+    {
+      "check": "storage",
+      "requirement": ">= 250 GB free on one filesystem outside ['/home']",
+      "observed": "no eligible filesystem",
+      "passes": false
+    },
+    {
+      "check": "memory",
+      "requirement": ">= 224 GiB runtime-accessible memory (DGR-017 experimental hard-fit floor)",
+      "observed": "124.9 GiB MemTotal",
+      "passes": false,
+      "waived": false
+    }
+  ],
+  "download_authorized": false,
+  "storage_only": false,
+  "download_plan": [
+    {
+      "step": 1,
+      "shard_index": 1,
+      "path": "UD-IQ1_S/GLM-5.2-UD-IQ1_S-00001-of-00006.gguf",
+      "size_bytes": 9423744,
+      "size_gb": 0.009,
+      "sha256": "46b6148389219ae45167cb8124fbb18ef7d432daf619b4faf9e06ea80d3f4777",
+      "url": "https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00001-of-00006.gguf",
+      "download_command": "curl -L -C - --fail -o \"$GLM_DEST/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00001-of-00006.gguf\" \"https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00001-of-00006.gguf\"",
+      "verify_command": "python scripts/verify_glm_shards.py --model-dir \"$GLM_DEST\" --shard 1"
+    },
+    {
+      "step": 2,
+      "shard_index": 6,
+      "path": "UD-IQ1_S/GLM-5.2-UD-IQ1_S-00006-of-00006.gguf",
+      "size_bytes": 19171063136,
+      "size_gb": 19.171,
+      "sha256": "3b767f55df64e0432d52fcf1a14eb47a1ef3bbc91339e2ae220f38602237d7d7",
+      "url": "https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00006-of-00006.gguf",
+      "download_command": "curl -L -C - --fail -o \"$GLM_DEST/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00006-of-00006.gguf\" \"https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00006-of-00006.gguf\"",
+      "verify_command": "python scripts/verify_glm_shards.py --model-dir \"$GLM_DEST\" --shard 6"
+    },
+    {
+      "step": 3,
+      "shard_index": 2,
+      "path": "UD-IQ1_S/GLM-5.2-UD-IQ1_S-00002-of-00006.gguf",
+      "size_bytes": 49208128256,
+      "size_gb": 49.208,
+      "sha256": "f2180207285e04fcaa5b8c53ba6e77ad5cc58666b6e7c6b04a5eded3fe8bef09",
+      "url": "https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00002-of-00006.gguf",
+      "download_command": "curl -L -C - --fail -o \"$GLM_DEST/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00002-of-00006.gguf\" \"https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00002-of-00006.gguf\"",
+      "verify_command": "python scripts/verify_glm_shards.py --model-dir \"$GLM_DEST\" --shard 2"
+    },
+    {
+      "step": 4,
+      "shard_index": 3,
+      "path": "UD-IQ1_S/GLM-5.2-UD-IQ1_S-00003-of-00006.gguf",
+      "size_bytes": 49684417024,
+      "size_gb": 49.684,
+      "sha256": "b1c0c5a302cc8d5d9ea0bcd4467c01db72c26839f820f7e882079582ea0a8d2b",
+      "url": "https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00003-of-00006.gguf",
+      "download_command": "curl -L -C - --fail -o \"$GLM_DEST/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00003-of-00006.gguf\" \"https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00003-of-00006.gguf\"",
+      "verify_command": "python scripts/verify_glm_shards.py --model-dir \"$GLM_DEST\" --shard 3"
+    },
+    {
+      "step": 5,
+      "shard_index": 4,
+      "path": "UD-IQ1_S/GLM-5.2-UD-IQ1_S-00004-of-00006.gguf",
+      "size_bytes": 49396052864,
+      "size_gb": 49.396,
+      "sha256": "a6a42da6975e29f89866dcde2956e9e50e6ea26635fb5063b74f3973f4f863b6",
+      "url": "https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00004-of-00006.gguf",
+      "download_command": "curl -L -C - --fail -o \"$GLM_DEST/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00004-of-00006.gguf\" \"https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00004-of-00006.gguf\"",
+      "verify_command": "python scripts/verify_glm_shards.py --model-dir \"$GLM_DEST\" --shard 4"
+    },
+    {
+      "step": 6,
+      "shard_index": 5,
+      "path": "UD-IQ1_S/GLM-5.2-UD-IQ1_S-00005-of-00006.gguf",
+      "size_bytes": 49246275936,
+      "size_gb": 49.246,
+      "sha256": "a4a9851a50db533f21ef824e5d8038f04e6782e7d602d18e5fdd6643f68ccccb",
+      "url": "https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00005-of-00006.gguf",
+      "download_command": "curl -L -C - --fail -o \"$GLM_DEST/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00005-of-00006.gguf\" \"https://huggingface.co/unsloth/GLM-5.2-GGUF/resolve/abc55e72527792c6e77069c99b4cb7de16fa9f23/UD-IQ1_S/GLM-5.2-UD-IQ1_S-00005-of-00006.gguf\"",
+      "verify_command": "python scripts/verify_glm_shards.py --model-dir \"$GLM_DEST\" --shard 5"
+    }
+  ],
+  "verdict": "fail"
+}

.scratch/distributed-gguf-runtime/evidence/DGR-019/README.md

@@ -0,0 +1,215 @@
+# DGR-019 evidence — lock alpha and beta performance contracts
+
+**Completed:** 2026-07-22
+**Branch:** `ralph/distributed-gguf-runtime`
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json`
+**Dependency:** DGR-017 (`evidence/DGR-017/README.md`) — cleaned backlog reconciled to `origin/master`; no old pass state transferred.
+
+## Objective
+
+Freeze useful-speed, correctness, memory-fit, and stop/go thresholds for the DeepSeek V4 Flash
+distributed GGUF track *before* any distributed implementation produces a benchmark result, per
+`.scratch/distributed-gguf-runtime/issues/019-lock-alpha-and-beta-performance-contracts.md`.
+
+## Pre-existing state found (not caused by this story)
+
+Before any change in this session, `git status` showed `.scratch/distributed-gguf-runtime/prd.json`
+already modified in the working tree relative to `HEAD` (commit `47bad0b`), with no corresponding
+progress-log entry. Diffing against `HEAD` showed the working copy had **dropped** prd.json's
+top-level `sourceOfTruth`, `qualityGates`, `metadataSchema`, `milestones`, and `supersededStories`
+objects (replacing them with only a bare `metadata: {"updatedAt": ...}` stamp), while `userStories`
+itself was byte-identical to `HEAD`. Running `tests/test_ralph_prd_schema.py` against the
+as-found working tree confirmed the damage: 56 of 108 tests failed (every
+`test_render_issue_markdown_matches_committed_file[...]` parametrization, since
+`quality_gate_bullets`/`authority_disclaimer` fall back to module defaults once `qualityGates`/
+`metadataSchema` are absent, which no longer match the committed issue files).
+
+This is the same shape of problem DGR-018's evidence documented and fixed: an abandoned,
+unexplained edit that silently dropped the schema/gates/milestone/provenance content this and
+future stories depend on, while `scripts/ralph_prd_schema.py validate` did not catch it (those
+top-level sections are optional-if-absent by design, so the CLI reported `OK: 55 stories
+validated.` even with them missing). The most likely cause is `ralph-tui`'s own read/write of
+`prd.json` as its task source, which only round-trips the fields it models
+(`name`/`description`/`branchName`/`userStories`) and stamps its own `metadata.updatedAt`,
+dropping any project-specific extension fields it doesn't know about.
+
+Per `RALPH-CONTEXT.md`'s instruction to inspect `git status` and preserve unrelated work rather
+than build on top of unexplained state, and following the DGR-018 precedent, the dropped fields
+were restored verbatim from `HEAD` (`git show HEAD:.scratch/distributed-gguf-runtime/prd.json`)
+while keeping the current `userStories` content (identical) and the current `metadata.updatedAt`
+stamp. `tests/test_ralph_prd_schema.py` returned to `108 passed` immediately after the restore,
+before any DGR-019-specific change was made.
+
+## Changes
+
+### `packages/node/meshnet_node/dgr_performance/` (new package)
+
+- **`data/alpha-beta-contract-v1.json`** — the locked, versioned, machine-readable contract.
+  `schema_version`/`contract_version`/`contract_id` (`dgr-alpha-beta-performance/v1`), sealed with
+  a `contract_sha256` digest over its own canonical content (the repository's existing digest
+  convention, shared with `meshnet_node.glm_alpha.contract`). Contents:
+  - `prompt_set` — four fixed prompts (`short-instruction`, `code-completion`,
+    `multi-step-reasoning`, `long-context-fill`) referenced by ID from every lane, so no lane can
+    quietly drift onto a different workload.
+  - `sampling` — greedy (`temperature=0`, `top_p=1`, `top_k=1`, `seed=1234`), matching
+    `meshnet_node.recipe_benchmark.SamplingPolicy` defaults.
+  - `lanes` — all four lanes named in the acceptance criteria. `controlled-safetensors` and
+    `whole-model-gguf` are marked `locked_elsewhere: true` and point at the pre-existing immutable
+    DGR-001 lock (`meshnet_node.performance_contract`, `contract_version=1`,
+    `ContractThresholds`) rather than re-defining or risking a conflicting duplicate. Only
+    `dense-distributed-gguf` and `v4-flash-distributed` are newly locked here, each with fixed
+    `prompt_ids`, `context_tokens`/`output_tokens` (alpha- and beta-scale for the V4 lane),
+    `concurrency_levels`, `hardware` (named certification-scenario topology, network class, device
+    class, MTP-off note), and a `metrics` list drawn from the existing
+    `recipe_benchmark`/`performance_contract`/`route_session_benchmark` metric vocabulary
+    (`ttft_p50_ms`, `decode_tokens_per_sec`, `seam_bytes`, `seam_latency_ms`, ...).
+  - `gain_attribution` — two disjoint metric sets, `quantization_model_fit_metrics` and
+    `runtime_transport_batching_kernel_metrics`, plus the rule that a speed/fit claim must cite
+    which axis moved it.
+  - `certification_scenarios` — `quantization` (`Q4_K_M`, `Q8_0`, `bf16-reference`) and
+    `stage_count` (`2-4-stage`, `10-plus-stage`) as named labels only, with an explicit rule that
+    no product/runtime code path may hardcode them.
+  - `alpha` — correctness thresholds (greedy token agreement, mean state cosine similarity,
+    nonfinite-tensor/fail-closed checks, no dense-attention-fallback credit) plus a `useful_speed`
+    block whose ratios (`1.25`/`0.75`-class, matching the already-locked DGR-001 25% convention)
+    carry an explicit `human_approval` sub-block (`required: true`, `approved: false`,
+    `approved_by: null`, `approved_at: null`). The ratio alone cannot satisfy alpha; DGR-054 must
+    fill in the approval against real evidence. `mtp.reserved=true`/`enabled_for_alpha=false` per
+    `RALPH-CONTEXT.md`. `verdicts: ["alpha", "optimize", "stop"]`.
+  - `beta` — adds exactly `concurrency`, `long_context`, `failure`, `sustained_throughput` axes
+    (16k-token long-context threshold matching the V4 lane's `beta_context_tokens`, no-silent-KV-
+    migration and no-synthetic-workers failure rules, 30-minute sustained-throughput floor).
+    `verdicts: ["beta", "targeted-optimization", "stop-rollback"]`.
+  - `amendment_policy` — thresholds may not be weakened/moved/reinterpreted after results are
+    known; a change requires a new `contract_id`/`contract_version` under human review.
+- **`contract.py`** — loader/validator mirroring the proven
+  `meshnet_node.glm_alpha.contract` pattern: `parse_contract` recomputes the canonical-JSON SHA-256
+  over the document (excluding the digest field) and requires it match both the document's own
+  declared `contract_sha256` *and* a digest pinned independently in code
+  (`CONTRACT_V1_SHA256`), so neither an in-place edit nor a resealed mutation can pass silently.
+  Structural checks enforce all four required lanes, that the two referenced lanes actually
+  declare `locked_elsewhere`, that the two newly-locked lanes carry full benchmark-plan fields,
+  that `alpha.verdicts`/`beta.verdicts` are exactly the three-outcome sets the release gates use,
+  and — the one property with no analogue in `glm_alpha` — that
+  `alpha.useful_speed.human_approval.required` is `true`. `seal_contract()` is the only supported
+  way to produce a new digest, kept separate from load-time verification for the same reason
+  `glm_alpha` keeps it separate.
+- **`__init__.py`** — re-exports the public API, documented as the contract DGR-020, DGR-044,
+  DGR-054, and DGR-070 are judged against.
+
+### `tests/test_dgr_performance_contract.py` (new, 28 tests)
+
+Deterministic, offline, GPU-free, model-download-free. Covers: packaged load and identity; digest
+recomputation; all four lanes present; the two referenced lanes point at the real DGR-001 module
+and its actual immutable thresholds (`min_decode_speedup == 1.25`, `max_resident_memory_ratio ==
+0.75`); the two newly-locked lanes carry complete benchmark plans, fixed context/output/
+concurrency; the shared prompt set and every lane's `prompt_ids`/`beta_prompt_ids` are a subset of
+it; sampling is greedy; `gain_attribution`'s two metric sets are non-empty and disjoint;
+certification-scenario names and rule text; **a structural test that greps every `.py` file under
+`packages/node/meshnet_node` (excluding this contract's own module and data file) for the literal
+strings `2-4-stage`/`10-plus-stage` and fails if any product module hardcodes them** — the concrete
+form of "no product logic may hardcode them"; alpha verdicts/correctness/`human_approval`/MTP-off;
+beta verdicts/axes/long-context/failure semantics; digest-mutation rejection (in-place and
+resealed); missing-digest rejection; `load_contract` from an explicit path matches the packaged
+load; `seal_contract` reproduces the pinned digest; amendment policy text.
+
+### `.scratch/distributed-gguf-runtime/prd.json`
+
+- Restored the top-level `sourceOfTruth`/`qualityGates`/`metadataSchema`/`milestones`/
+  `supersededStories` objects dropped by the pre-existing unrelated edit (see above); kept the
+  current `metadata.updatedAt` tooling stamp.
+- Marked `DGR-019.passes = true` with `completionNotes` summarizing this outcome.
+
+### `.scratch/distributed-gguf-runtime/issues/019-lock-alpha-and-beta-performance-contracts.md`
+
+Regenerated via `python scripts/ralph_prd_schema.py render` to reflect `passes: true` (checked
+acceptance criteria, "completed" status line, "Verified evidence" handoff line), matching the
+convention DGR-017/DGR-018's issue files already use.
+
+## Commands and results
+
+```bash
+.venv-rocm/bin/python -m pytest -q tests/test_dgr_performance_contract.py
+```
+```text
+28 passed in 0.14s
+```
+
+```bash
+.venv-rocm/bin/python -m pytest -q tests/test_ralph_prd_schema.py tests/test_dgr_performance_contract.py \
+  tests/test_glm_alpha_target.py tests/test_recipe_benchmark.py tests/test_route_session_benchmark.py
+```
+```text
+270 passed in 1.04s
+```
+
+```bash
+.venv-rocm/bin/python -m compileall -q packages tests
+```
+Exit code 0, no output (all files compile).
+
+```bash
+git diff --check
+```
+Exit code 0 (no whitespace errors).
+
+```bash
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json
+```
+```text
+OK: 55 stories validated.
+```
+
+```bash
+.venv-rocm/bin/python -m pytest -q tests/ -k "not integration" --ignore=tests/test_shard_runtime_harness.py
+```
+```text
+7 failed, 1146 passed, 11 skipped, 4 deselected, 3 warnings in 261.71s (0:04:21)
+```
+This full sweep was launched in the background while `prd.json`/the evidence README below were
+still being written, so it raced its own inputs: one of its 7 failures
+(`test_ralph_prd_schema.py::test_real_backlog_passed_stories_have_completion_evidence`) was this
+story's own `passes=true`/evidence-README edit landing mid-run, not a real defect — re-running
+`tests/test_ralph_prd_schema.py` alone afterward, against the finalized tree, gives
+`108 passed`. The other 6 failures (`test_billing_ledger.py::
+test_tracker_enables_billing_with_default_db`, `test_dynamic_routing.py::
+test_admin_can_replace_a_served_model_and_release_it`, `test_dynamic_routing.py::
+test_models_list_does_not_duplicate_a_preset_registered_by_hf_repo`, three cache tests in
+`test_real_model_backend.py`) are in files this story's `git diff` never touches (`git diff --stat
+HEAD -- tests/test_billing_ledger.py tests/test_dynamic_routing.py tests/test_real_model_backend.py`
+is empty) and none of them import `dgr_performance`, `performance_contract`, or `glm_alpha`; they
+are pre-existing baseline defects, not regressions from this story, in the same spirit as the
+known `origin/master` limitations DGR-017's evidence recorded.
+
+## Known limitations
+
+- `tests/test_shard_runtime_harness.py` fails to *collect* in this environment
+  (`ModuleNotFoundError: No module named 'grpc'`). This is a pre-existing environment gap from
+  DGR-024's real generated-gRPC protocol harness, not something this story touched or caused; it is
+  excluded from the sweep above rather than silently masked.
+- Alpha's `useful_speed` ratios (`1.25`/`0.75`-class) are proposed thresholds held at the same
+  margin already locked for the whole-model contract (DGR-001/v1). They are locked numbers, but
+  `human_approval.required=true` means DGR-054 may not treat them as self-certifying from the
+  ratio alone — a human must approve the observed ratio against real evidence. This session did
+  not, and could not, supply that approval: no distributed benchmark evidence exists yet.
+- `v4-flash-distributed`'s `reference_baseline` documents that a safetensors DeepSeek V4 Flash
+  distributed baseline may not yet be pinned (that is DGR-044's job); until then, comparisons must
+  fall back to `dense-distributed-gguf` runtime/transport overhead as an explicit, stated
+  limitation rather than a silent substitution.
+- This is a specification-materialization story; per the shared quality gates, it is intentionally
+  left uncommitted for manual review rather than given the "one scoped story commit" other stories
+  get.
+
+## Dependency handoff
+
+DGR-020 (run the controlled whole-model baseline) consumes the DGR-001 lock referenced — not
+redefined — by this contract's `controlled-safetensors`/`whole-model-gguf` lanes.
+
+DGR-044 (pin the DeepSeek V4 Flash target contract) and DGR-054/DGR-070 (enforce the alpha/beta
+gates) must load `meshnet_node.dgr_performance.load_contract()` and judge results against its
+`dense-distributed-gguf`/`v4-flash-distributed` lanes and `alpha`/`beta` sections without changing
+any threshold. DGR-054 specifically must populate `alpha.useful_speed.human_approval`
+(`approved`/`approved_by`/`approved_at`) as part of publishing its verdict — a satisfied ratio
+without a filled-in approval is not alpha certification. Any amendment must open a new
+`contract_id`/`contract_version` under human review per `amendment_policy`; this document and its
+digest are not editable in place.

.scratch/distributed-gguf-runtime/evidence/DGR-020/README.md

@@ -0,0 +1,243 @@
+# DGR-020 evidence — run the controlled whole-model GGUF baseline
+
+**Completed:** 2026-07-22
+**Branch:** `ralph/distributed-gguf-runtime`
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json`
+**Dependency:** DGR-019 (`evidence/DGR-019/README.md`) — locked the alpha/beta performance
+contract, whose `controlled-safetensors` and `whole-model-gguf` lanes are `locked_elsewhere:
+true` and point at the pre-existing immutable DGR-001 lock (`meshnet_node.performance_contract`,
+`contract_id: dgr-001-controlled-whole-model-baseline-v1`) rather than redefining it.
+
+## Objective
+
+Per `.scratch/distributed-gguf-runtime/issues/020-run-the-controlled-whole-model-gguf-baseline.md`:
+execute the exact locked safetensors and whole-model llama.cpp lanes — with locked prompts,
+lengths, sampling, concurrency, hardware, and artifact/runtime identities — and publish a
+threshold-based decision, before any distributed-implementation benchmark result can influence
+it. Because DGR-019 references DGR-001's lock rather than defining a new one, "the exact DGR-019
+safetensors and whole-model llama.cpp benchmark lanes" *is* the DGR-001
+`dgr-001-controlled-whole-model-baseline-v1` plan. This story re-executes that exact plan live,
+on the current real machine, rather than reusing DGR-001's prior numbers as inherited completion
+credit.
+
+## Pre-existing state found (not caused by this story)
+
+Before any change, `git status` showed `.scratch/distributed-gguf-runtime/prd.json` already
+modified relative to `HEAD` (`47bad0b`). Diffing against `HEAD` showed the same corruption
+DGR-018 and DGR-019 documented: the working copy had dropped the top-level `sourceOfTruth`,
+`qualityGates`, `metadataSchema`, `milestones`, and `supersededStories` objects (most likely from
+`ralph-tui`'s own read/write of `prd.json`, which round-trips only the fields it models). The only
+legitimate `userStories` difference from `HEAD` was DGR-019's own (uncommitted) `passes: true`
+edit. Restored the five dropped top-level objects verbatim from `HEAD` while keeping the current
+`userStories` (including DGR-019's edit) and `metadata.updatedAt`. `tests/test_ralph_prd_schema.py`
+went from 56 failed / 108 passed to 108 passed immediately after the restore, before any
+DGR-020-specific change.
+
+## Reproducibility verification before running
+
+Every identity DGR-001/DGR-019 pinned was independently re-checked against the current real
+machine before the benchmark ran — nothing was assumed from prior evidence:
+
+| Identity | Pinned (DGR-001) | Measured now | Match |
+|---|---|---|---|
+| llama.cpp commit | `e920c523e3b8a0163fe498af5bf90df35ff51d25` | `e920c523e3b8a0163fe498af5bf90df35ff51d25` | yes |
+| `llama-server` SHA-256 | `fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd` | same | yes |
+| BF16 GGUF artifact SHA-256 | `e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862` | same | yes |
+| Q4_K_M GGUF artifact SHA-256 | `a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5` | same | yes |
+| Torch / Transformers versions | `2.10.0+rocm7.13.0a20260513` / `5.13.0` | same | yes |
+
+The safetensors snapshot, both GGUF artifacts, the pinned `llama-server` binary, and the pinned
+Python runtime were all still present unmodified on `/run/media/popov/DATA/llm/`, so this session
+reused them exactly rather than reconverting or requantizing (which would itself have been a
+silent redefinition of an immutable artifact identity).
+
+## Real results — fresh run on real hardware
+
+`.scratch/distributed-gguf-runtime/evidence/DGR-020/benchmark-config.json` and
+`performance-contract.json` are byte-identical copies of DGR-001's (same `plan_sha256`
+`efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570` and `config_sha256`
+`00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3`), so this is the same plan,
+not a new one.
+
+```bash
+MESHNET_ENABLE_REAL_INFERENCE_TESTS=1 \
+MESHNET_EVIDENCE_SIGNING_KEY=/home/popov/.config/neuron-tai/keys/dgr-001-evidence-ed25519.pem \
+PYTHONPATH=packages/node .venv-rocm/bin/python -m meshnet_node.recipe_benchmark \
+  --config .scratch/distributed-gguf-runtime/evidence/DGR-020/benchmark-config.json \
+  --json-out .scratch/distributed-gguf-runtime/evidence/DGR-020/results.json \
+  --summary-out .scratch/distributed-gguf-runtime/evidence/DGR-020/results.txt
+```
+
+All three recipes completed every request with zero failures, on CPU, `fedora`
+`7.0.14-101.fc43.x86_64`, 32 logical CPUs:
+
+| Metric | Transformers BF16 (ref) | llama.cpp BF16 | llama.cpp Q4_K_M | DGR-001 (prior run, same plan) |
+|---|---:|---:|---:|---|
+| Decode tok/s, c=1 | 50.8 | 102.5 | 213.1 | 40.8 / 98.5 / 207.7 |
+| Aggregate decode tok/s, c=4 | 48.8 | 218.1 | 235.7 | 46.5 / 222.8 / 195.7 |
+| TTFT p50, c=1 | 32.9 ms | 15.1 ms | 17.3 ms | 40.0 / 15.1 / 21.6 ms |
+| Peak resident memory, c=1 | 1.93 GB | 1.11 GB | 0.54 GB | 1.94 / 1.11 / 0.54 GB |
+| Artifact size | 1.00 GB | 0.99 GB | 0.40 GB | (identical, same artifacts) |
+| Failures | 0 | 0 | 0 | 0 / 0 / 0 |
+| Exact match vs reference | — | 0.3333 | 0.00 (advisory) | 0.3333 |
+| Mean similarity vs reference | — | 0.9471 | 0.456 (advisory) | 0.9471 |
+
+Per-recipe measurements against the reference (`baseline.json`, `contract-evaluation.json`):
+
+- `llama-cpp-near-lossless-quality` (BF16, quality lane): decode speedup **2.02x**, aggregate
+  throughput speedup (c=4) **4.47x**, resident-memory ratio **0.574x**, TTFT ratio **0.459x** —
+  but `quality_pass: false` (exact match 0.33 < required 0.90).
+- `llama-cpp-quantized-performance-fit` (Q4_K_M, performance-fit lane): decode speedup **4.19x**,
+  aggregate throughput speedup (c=4) **4.83x**, resident-memory ratio **0.280x**, artifact-size
+  ratio **0.398x**, TTFT ratio **0.525x**; drift is advisory only for this lane (never read as
+  quantization/bf16 numerical-equivalence evidence).
+
+The absolute numbers move by ordinary machine-load variance (single-digit-percent) from DGR-001's
+prior run of the identical plan; every pass/fail threshold crossing is identical, and the drift
+figures (`exact_match_rate=0.3333`, `mean_similarity=0.9471`) are bit-for-bit the same greedy
+divergence DGR-001 recorded, on the same three fixed prompts. This is a genuine independent
+reproduction, not a copy: `results.json`'s `provenance.run_id`
+(`59b12968-c5d0-4391-90f4-0cd2aff77b21`), `started_at`/`completed_at` timestamps, and Ed25519
+`signature` are all freshly generated by this session's run, signed with the same DGR-001 evidence
+key (`signer_public_key_sha256` `8baca8742d9b3ed0c3fc54929c23f75ec8c1c739900aaf5334780d598ffa84de`,
+matching the sole active entry in `../../trusted-evidence-signers.json`).
+
+## Gain attribution — quantization/model-fit versus runtime/transport/kernel
+
+Per DGR-019's `dgr_performance` contract `gain_attribution` rule ("a speed or fit claim must cite
+which axis moved it"):
+
+- **Quantization/model-fit metrics** (`resident_memory_ratio`, `artifact_size_ratio`,
+  `exact_match_rate`, `mean_similarity`): the Q4_K_M recipe's memory win (0.280x) and size win
+  (0.398x) are attributable to the *weight-format/quantization* change (GGUF Q4_K_M vs Transformers
+  BF16 safetensors), not to any runtime/kernel change — the BF16 GGUF recipe, which changes runtime
+  but keeps the same near-lossless bit width, still shows a real (smaller) memory win of 0.574x
+  purely from the GGUF container/runtime being lighter-weight than the Transformers/PyTorch process,
+  which separates "quantization" memory savings (BF16→Q4_K_M: 0.574x→0.280x) from "runtime/format"
+  memory savings (safetensors→BF16 GGUF: 1.0x→0.574x). The quality-lane failure
+  (`exact_match_rate=0.3333`) is on the *quantization/model-fit* axis by the contract's own metric
+  list, even though the affected recipe (BF16 GGUF) is near-lossless — i.e. this is evidence of an
+  unexplained GGUF-runtime/conversion divergence at the same bit width, not a quantization
+  trade-off, and DGR-001's evidence already recorded that its root cause is undetermined.
+- **Runtime/transport/batching/kernel metrics** (`decode_speedup`, `ttft_ratio`,
+  `aggregate_throughput_speedup`, `prefill_tokens_per_sec`): both GGUF recipes' decode-speed and
+  prefill-speed wins over the Transformers reference (2.02x/4.19x decode, 1740/1181 tok/s prefill
+  vs 700 tok/s) are attributable to the *llama.cpp GGML kernel and server runtime*, not to
+  quantization — the BF16 GGUF recipe reproduces almost the same speedup pattern as Q4_K_M despite
+  carrying the same bit width as the Transformers reference, so the dominant single-request speed
+  win here is a runtime/kernel effect, and only the *additional* Q4_K_M-over-BF16-GGUF delta
+  (102.5→213.1 tok/s decode, ~2.08x) is attributable to quantization on top of that runtime effect.
+  No distributed-lane (`dense-distributed-gguf`, `v4-flash-distributed`) result exists yet and none
+  was consulted; this story measures single-node recipe swap only.
+
+## Failed / unavailable lanes
+
+None. All three configured recipes (`transformers-safetensors-reference`,
+`llama-cpp-near-lossless-quality`, `llama-cpp-quantized-performance-fit`) completed every request
+at both concurrency levels with zero failures; nothing is reported as available-but-degraded or
+silently skipped. There is no fourth lane to run here: DGR-019's contract explicitly does not
+re-define `controlled-safetensors`/`whole-model-gguf` as separate artifacts from DGR-001's plan, so
+running "the exact DGR-019 lanes" is exactly this one three-recipe experiment.
+
+## Decision
+
+`contract-evaluation.json` (evaluated with the unmodified, immutable
+`meshnet_node.performance_contract` v1 thresholds — `min_decode_speedup=1.25`,
+`max_ttft_ratio=1.25`, `min_aggregate_throughput_speedup=1.25`, `max_resident_memory_ratio=0.75`,
+`min_quality_exact_match_rate=0.90`, `min_quality_mean_similarity=0.97`, `max_failure_rate=0.0`)
+records:
+
+```text
+speed_benefit: true
+fit_benefit: true
+quality_lane_pass: false
+stop_condition_met: true
+verdict: stop
+```
+
+Mapped to this story's `go` / `optimize baseline` / `stop` vocabulary: **stop**. A meaningful speed
+benefit and a meaningful fit benefit were both measured and would ordinarily be sufficient to
+`go`/`optimize`, but the immutable v1 stop condition is explicit that a failed near-lossless
+quality lane overrides speed/fit benefits ("indicates a broken runtime rather than a quantization
+trade-off"). This decision uses only the locked v1 thresholds and this session's freshly measured
+metrics; no threshold was changed, and no distributed-implementation result (DGR-024's gRPC
+harness or any other distributed-lane evidence) was read or ingested to produce it.
+
+This reproduces DGR-001's original `stop` verdict on the same plan on the same real machine,
+confirming that verdict is stable over time and not an artifact of a single run.
+
+## Limitations
+
+- This is a **0.5B CPU baseline** (`Qwen/Qwen2.5-0.5B-Instruct`), the same generic model DGR-001
+  and DGR-019's `locked_elsewhere` reference use — not DeepSeek V4 Flash. DGR-019's evidence
+  already recorded that a DeepSeek V4 Flash `controlled-safetensors`/`whole-model-gguf` baseline is
+  not yet pinned; that is separate future work (see DGR-019's `v4-flash-distributed.reference_
+  baseline` note), not something this story's acceptance criteria ask it to create — it asks only
+  to run the exact already-locked lanes, which are this DGR-001 plan.
+  - The `whole-model-gguf` quality-lane exact-match divergence (0.33 vs 0.90 required) reproduces
+  identically and remains unexplained; this story does not diagnose it further beyond confirming
+  it reproduces (DGR-001's `quality-parity-diagnosis.md` documents the CPU-vs-ROCm split already
+  known).
+- Absolute timings are single-developer-machine measurements with ordinary run-to-run variance;
+  the locked ratios/ratios-vs-threshold crossings are the durable evidence, not the raw absolute
+  tok/s figures.
+- No new GPU (ROCm) diagnostic was re-run in this session — DGR-001's existing GPU diagnostic is
+  cited as prior evidence only; it uses a distinct signed `run_configured_gpu_diagnostic/v1`
+  producer that the v1 evaluator does not accept, so it cannot itself change the `stop` verdict
+  above.
+
+## Files changed
+
+- `.scratch/distributed-gguf-runtime/evidence/DGR-020/benchmark-config.json` (new) — byte-identical
+  copy of DGR-001's locked plan.
+- `.scratch/distributed-gguf-runtime/evidence/DGR-020/performance-contract.json` (new) —
+  byte-identical copy of DGR-001's immutable v1 thresholds.
+- `.scratch/distributed-gguf-runtime/evidence/DGR-020/results.json` / `results.txt` (new) — raw
+  signed real evidence from this session's fresh run.
+- `.scratch/distributed-gguf-runtime/evidence/DGR-020/baseline.json` / `contract-evaluation.json`
+  (new) — distilled baseline and fail-closed v1 verdict for this session's run.
+- `.scratch/distributed-gguf-runtime/evidence/DGR-020/README.md` (new, this file).
+- `.scratch/distributed-gguf-runtime/prd.json` — restored the dropped top-level
+  `sourceOfTruth`/`qualityGates`/`metadataSchema`/`milestones`/`supersededStories` objects (see
+  above); marked `DGR-020.passes = true` with `completionNotes`.
+- `.scratch/distributed-gguf-runtime/issues/020-run-the-controlled-whole-model-gguf-baseline.md` —
+  regenerated via `python scripts/ralph_prd_schema.py render` to reflect `passes: true`.
+
+No source or test files under `packages/` or `tests/` were changed by this story.
+
+## Commands and results
+
+```bash
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json
+```
+```text
+OK: 55 stories validated.
+```
+
+```bash
+.venv-rocm/bin/python -m pytest -q tests/test_recipe_benchmark.py tests/test_dgr_performance_contract.py tests/test_ralph_prd_schema.py
+```
+```text
+164 passed in 0.69s
+```
+
+```bash
+.venv-rocm/bin/python -m compileall -q packages tests
+```
+Exit code 0, no output (all files compile).
+
+```bash
+git diff --check
+```
+Exit code 0 (no whitespace errors).
+
+## Dependency handoff
+
+DGR-054 (enforce the alpha gate) may cite this evidence when it fills in
+`alpha.useful_speed.human_approval` — this is fresh, independently-collected, signed real-hardware
+evidence that the `controlled-safetensors`/`whole-model-gguf` v1 contract still holds `stop` on the
+current machine, immediately before any distributed-lane result exists, but it is a 0.5B CPU
+baseline, not the DeepSeek V4 Flash target; DGR-044 must still pin the V4 Flash reference baseline
+separately before DGR-054/DGR-070 can judge `dense-distributed-gguf`/`v4-flash-distributed` against
+it. No threshold in either `meshnet_node.performance_contract` or `meshnet_node.dgr_performance`
+was changed by this story.

.scratch/distributed-gguf-runtime/evidence/DGR-020/baseline.json

@@ -0,0 +1,169 @@
+{
+  "artifact_sha256": {
+    "llama-cpp-near-lossless-quality": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+    "llama-cpp-quantized-performance-fit": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5",
+    "transformers-safetensors-reference": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6"
+  },
+  "backend_detail": {
+    "llama-cpp-near-lossless-quality": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
+    "llama-cpp-quantized-performance-fit": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
+    "transformers-safetensors-reference": "torch 2.10.0+rocm7.13.0a20260513; dtype bfloat16; device cpu; intra-op threads 16"
+  },
+  "evidence_class": "local-real",
+  "host": {
+    "accelerator_name": "Radeon 8060S Graphics",
+    "accelerator_runtime": "7.13.26183",
+    "benchmark_lane": "cpu-controlled-baseline",
+    "converter_sha256": "c819f18fb22927b49fabc3b35d1c9e21ee638b3817eccd1bd4efbcc7116eeb4d",
+    "cpu_count": 32,
+    "cuda_available": true,
+    "hostname": "fedora",
+    "llama_cpp_commit": "e920c523e3b8a0163fe498af5bf90df35ff51d25",
+    "llama_cpp_version": "9991",
+    "llama_server_identities": {
+      "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server": {
+        "sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+        "version": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64"
+      }
+    },
+    "llama_server_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+    "platform": "Linux-7.0.14-101.fc43.x86_64-x86_64-with-glibc2.42",
+    "python": "3.12.13",
+    "quantizer_sha256": "bd0cc8c7be6d48aad4755b31062e0e59a887cbadd43dbb8771853d5858bb198f",
+    "torch_version": "2.10.0+rocm7.13.0a20260513",
+    "transformers_version": "5.13.0"
+  },
+  "model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+  "model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+  "plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
+  "provenance": {
+    "completed_at": "2026-07-22T05:52:30.445799Z",
+    "config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
+    "producer": "meshnet_node.recipe_drivers.run_configured_benchmark/v1",
+    "run_id": "59b12968-c5d0-4391-90f4-0cd2aff77b21",
+    "schema_version": 1,
+    "signature": "aExtG1Y0fWFaqlKEtUOOpXZrganVAxbLvpov2WVgm19eNJ50VheeI7CuRhlWx4SJX9OFto2WuLaVPhjwSA88Cw==",
+    "signature_algorithm": "ed25519",
+    "signer_public_key_sha256": "8baca8742d9b3ed0c3fc54929c23f75ec8c1c739900aaf5334780d598ffa84de",
+    "started_at": "2026-07-22T05:51:36.511891Z"
+  },
+  "recipe_runtime": {
+    "llama-cpp-near-lossless-quality": {
+      "device": "cpu",
+      "runtime": "llama.cpp-9991-e920c523",
+      "weight_format": "gguf",
+      "weight_quantization": "bfloat16"
+    },
+    "llama-cpp-quantized-performance-fit": {
+      "device": "cpu",
+      "runtime": "llama.cpp-9991-e920c523",
+      "weight_format": "gguf",
+      "weight_quantization": "Q4_K_M"
+    },
+    "transformers-safetensors-reference": {
+      "device": "cpu",
+      "runtime": "transformers-5.13.0",
+      "weight_format": "safetensors",
+      "weight_quantization": "bfloat16"
+    }
+  },
+  "recipes": {
+    "llama-cpp-near-lossless-quality": {
+      "artifact_bytes": 994156448,
+      "available": true,
+      "concurrency": {
+        "1": {
+          "aggregate_decode_tokens_per_sec": 89.2873,
+          "decode_tokens_per_sec": 102.5344,
+          "failures": 0,
+          "latency_p50_ms": 316.647,
+          "latency_p95_ms": 374.8515,
+          "peak_rss_bytes": 1110106112,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 1740.0213,
+          "ttft_p50_ms": 15.067,
+          "ttft_p95_ms": 65.191
+        },
+        "4": {
+          "aggregate_decode_tokens_per_sec": 218.1128,
+          "decode_tokens_per_sec": 80.0623,
+          "failures": 0,
+          "latency_p50_ms": 403.9781,
+          "latency_p95_ms": 767.6557,
+          "peak_rss_bytes": 1139265536,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 1064.6179,
+          "ttft_p50_ms": 36.611,
+          "ttft_p95_ms": 178.801
+        }
+      },
+      "device": "cpu",
+      "lane": "quality"
+    },
+    "llama-cpp-quantized-performance-fit": {
+      "artifact_bytes": 397807520,
+      "available": true,
+      "concurrency": {
+        "1": {
+          "aggregate_decode_tokens_per_sec": 149.8675,
+          "decode_tokens_per_sec": 213.1452,
+          "failures": 0,
+          "latency_p50_ms": 161.7164,
+          "latency_p95_ms": 282.5491,
+          "peak_rss_bytes": 541663232,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 1181.0842,
+          "ttft_p50_ms": 17.252,
+          "ttft_p95_ms": 130.529
+        },
+        "4": {
+          "aggregate_decode_tokens_per_sec": 235.6963,
+          "decode_tokens_per_sec": 94.7604,
+          "failures": 0,
+          "latency_p50_ms": 373.7211,
+          "latency_p95_ms": 759.3151,
+          "peak_rss_bytes": 571027456,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 567.7335,
+          "ttft_p50_ms": 42.086,
+          "ttft_p95_ms": 312.645
+        }
+      },
+      "device": "cpu",
+      "lane": "performance-fit"
+    },
+    "transformers-safetensors-reference": {
+      "artifact_bytes": 999586347,
+      "available": true,
+      "concurrency": {
+        "1": {
+          "aggregate_decode_tokens_per_sec": 44.4625,
+          "decode_tokens_per_sec": 50.8327,
+          "failures": 0,
+          "latency_p50_ms": 701.9146,
+          "latency_p95_ms": 776.2706,
+          "peak_rss_bytes": 1933221888,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 699.7553,
+          "ttft_p50_ms": 32.8569,
+          "ttft_p95_ms": 173.7161
+        },
+        "4": {
+          "aggregate_decode_tokens_per_sec": 48.849,
+          "decode_tokens_per_sec": 13.4779,
+          "failures": 0,
+          "latency_p50_ms": 2503.1601,
+          "latency_p95_ms": 2600.6307,
+          "peak_rss_bytes": 2170908672,
+          "peak_vram_bytes": 0,
+          "prefill_tokens_per_sec": 264.5822,
+          "ttft_p50_ms": 95.7502,
+          "ttft_p95_ms": 425.4973
+        }
+      },
+      "device": "cpu",
+      "lane": "quality"
+    }
+  },
+  "reference_recipe_id": "transformers-safetensors-reference"
+}

.scratch/distributed-gguf-runtime/evidence/DGR-020/benchmark-config.json

@@ -0,0 +1,118 @@
+{
+  "artifact_storage_root": "/run/media/popov/DATA/llm",
+  "evidence_class": "local-real",
+  "host": {
+    "benchmark_lane": "cpu-controlled-baseline",
+    "llama_cpp_commit": "e920c523e3b8a0163fe498af5bf90df35ff51d25",
+    "llama_cpp_version": "9991",
+    "llama_server_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+    "converter_sha256": "c819f18fb22927b49fabc3b35d1c9e21ee638b3817eccd1bd4efbcc7116eeb4d",
+    "quantizer_sha256": "bd0cc8c7be6d48aad4755b31062e0e59a887cbadd43dbb8771853d5858bb198f",
+    "transformers_version": "5.13.0"
+  },
+  "plan": {
+    "plan_id": "dgr-001-controlled-whole-model-baseline-v1",
+    "model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+    "model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+    "prompts": [
+      {
+        "id": "short-fact",
+        "text": "The capital of France is",
+        "context_class": "short"
+      },
+      {
+        "id": "medium-code",
+        "text": "Complete this Python function without commentary:\n\ndef fibonacci(n):\n    \"\"\"Return the nth Fibonacci number for n >= 0.\"\"\"\n",
+        "context_class": "medium"
+      },
+      {
+        "id": "long-summary",
+        "text": "A distributed inference service divides a transformer across consumer machines. The tracker owns admission, routing, cancellation, accounting, and telemetry, while workers own only model execution. Every request carries an immutable model identity and revision. Workers must reject incompatible protocol versions and resource demands before allocating large buffers. Activation tensors are chunked, checksummed, bounded by negotiated limits, and propagated with explicit flow-control credits. A caller may disconnect at any time, so cancellation must release queued work, in-flight transfers, and cache reservations without double billing. Retries can occur after network failures, requiring idempotent request identifiers and deterministic completion accounting. The system keeps the existing safetensors path as a correctness reference while a native GGUF path is measured. Benchmarks compare the same prompts, output lengths, sampling policy, device, and concurrency, and they separate near-lossless quality checks from quantized speed and fit claims. Summarize the design priorities in three concise bullet points.",
+        "context_class": "long"
+      }
+    ],
+    "sampling": {
+      "temperature": 0.0,
+      "top_p": 1.0,
+      "top_k": 1,
+      "seed": 1234,
+      "max_output_tokens": 32
+    },
+    "concurrency_levels": [1, 4],
+    "repeats": 3,
+    "warmup_requests": 2
+  },
+  "recipes": [
+    {
+      "id": "transformers-safetensors-reference",
+      "runtime": "transformers-5.13.0",
+      "weight_format": "safetensors",
+      "weight_quantization": "bfloat16",
+      "lane": "quality",
+      "device": "cpu",
+      "artifact_path": "/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775",
+      "artifact_sha256": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": true,
+      "notes": "artifact_sha256 is the deterministic digest of every snapshot path and file byte",
+      "driver": {
+        "type": "transformers",
+        "model_path": "/run/media/popov/DATA/llm/safetensor/models/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/7ae557604adf67be50417f59c2c2f167def9a775",
+        "device": "cpu",
+        "dtype": "bfloat16",
+        "threads": 16
+      }
+    },
+    {
+      "id": "llama-cpp-near-lossless-quality",
+      "runtime": "llama.cpp-9991-e920c523",
+      "weight_format": "gguf",
+      "weight_quantization": "bfloat16",
+      "lane": "quality",
+      "device": "cpu",
+      "artifact_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-BF16.gguf",
+      "artifact_sha256": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": false,
+      "notes": "Converted directly from the exact mounted safetensors revision while preserving BF16 weights with pinned llama.cpp",
+      "driver": {
+        "type": "llama-cpp-server",
+        "binary": "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server",
+        "binary_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+        "gguf_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-BF16.gguf",
+        "device": "cpu",
+        "threads": 16,
+        "n_parallel": 4,
+        "context_per_slot": 512,
+        "n_gpu_layers": 0
+      }
+    },
+    {
+      "id": "llama-cpp-quantized-performance-fit",
+      "runtime": "llama.cpp-9991-e920c523",
+      "weight_format": "gguf",
+      "weight_quantization": "Q4_K_M",
+      "lane": "performance-fit",
+      "device": "cpu",
+      "artifact_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-Q4_K_M.gguf",
+      "artifact_sha256": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5",
+      "source_model_id": "Qwen/Qwen2.5-0.5B-Instruct",
+      "source_model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
+      "is_reference": false,
+      "notes": "Quantized from the exact-revision F16 GGUF with pinned llama-quantize",
+      "driver": {
+        "type": "llama-cpp-server",
+        "binary": "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server",
+        "binary_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+        "gguf_path": "/run/media/popov/DATA/llm/dgr-001/Qwen2.5-0.5B-Instruct-7ae5576-Q4_K_M.gguf",
+        "device": "cpu",
+        "threads": 16,
+        "n_parallel": 4,
+        "context_per_slot": 512,
+        "n_gpu_layers": 0
+      }
+    }
+  ]
+}

.scratch/distributed-gguf-runtime/evidence/DGR-020/contract-evaluation.json

@@ -0,0 +1,71 @@
+{
+  "contract_version": 1,
+  "fit_benefit": true,
+  "plan_id": "dgr-001-controlled-whole-model-baseline-v1",
+  "quality_lane_pass": false,
+  "rationale": [
+    "the near-lossless quality lane failed: the GGUF runtime disagrees with the safetensors reference beyond what near-lossless weights can explain",
+    "a meaningful speed benefit was measured",
+    "a meaningful fit benefit was measured"
+  ],
+  "recipes": [
+    {
+      "comparable": true,
+      "failures": 0,
+      "fit_benefit": false,
+      "incomparable_reason": "",
+      "lane": "quality",
+      "measurements": {
+        "aggregate_concurrency": 4,
+        "aggregate_throughput_speedup": 4.465,
+        "artifact_size_ratio": 0.9946,
+        "artifact_size_win": false,
+        "compared_prompts": 3,
+        "decode_speedup": 2.0171,
+        "exact_match_rate": 0.3333,
+        "expected_prompts": 3,
+        "failure_rate": 0.0,
+        "mean_similarity": 0.9471,
+        "resident_memory_ratio": 0.5742,
+        "ttft_ratio": 0.4586
+      },
+      "quality_pass": false,
+      "reasons": [
+        "single-request decode 2.02x reference (>= 1.25x) at TTFT ratio 0.46",
+        "aggregate throughput at concurrency 4 is 4.46x reference (>= 1.25x)",
+        "peak resident memory is 0.57x reference (<= 0.75x)",
+        "quality lane exact-match 0.33 / similarity 0.947 versus the reference (fail)"
+      ],
+      "recipe_id": "llama-cpp-near-lossless-quality",
+      "speed_benefit": false
+    },
+    {
+      "comparable": true,
+      "failures": 0,
+      "fit_benefit": true,
+      "incomparable_reason": "",
+      "lane": "performance-fit",
+      "measurements": {
+        "aggregate_concurrency": 4,
+        "aggregate_throughput_speedup": 4.825,
+        "artifact_size_ratio": 0.398,
+        "artifact_size_win": true,
+        "decode_speedup": 4.1931,
+        "failure_rate": 0.0,
+        "resident_memory_ratio": 0.2802,
+        "ttft_ratio": 0.5251
+      },
+      "quality_pass": null,
+      "reasons": [
+        "single-request decode 4.19x reference (>= 1.25x) at TTFT ratio 0.53",
+        "aggregate throughput at concurrency 4 is 4.83x reference (>= 1.25x)",
+        "peak resident memory is 0.28x reference (<= 0.75x)"
+      ],
+      "recipe_id": "llama-cpp-quantized-performance-fit",
+      "speed_benefit": true
+    }
+  ],
+  "speed_benefit": true,
+  "stop_condition_met": true,
+  "verdict": "stop"
+}

.scratch/distributed-gguf-runtime/evidence/DGR-020/performance-contract.json

@@ -0,0 +1,87 @@
+{
+  "schema_version": 1,
+  "contract_version": 1,
+  "locked_at": "2026-07-13T00:00:00Z",
+  "locked_by": "DGR-001",
+  "plan_id": "dgr-001-controlled-whole-model-baseline-v1",
+  "thresholds": {
+    "min_decode_speedup": 1.25,
+    "max_ttft_ratio": 1.25,
+    "min_aggregate_throughput_speedup": 1.25,
+    "max_resident_memory_ratio": 0.75,
+    "max_artifact_size_ratio": 0.6,
+    "min_quality_exact_match_rate": 0.9,
+    "min_quality_mean_similarity": 0.97,
+    "max_failure_rate": 0.0
+  },
+  "baseline": {
+    "status": "pending-real-evidence",
+    "required_evidence_class": "local-real",
+    "required_recipes": [
+      "transformers-safetensors-reference",
+      "llama-cpp-near-lossless-quality",
+      "llama-cpp-quantized-performance-fit"
+    ],
+    "required_concurrency_levels": [
+      1,
+      4
+    ],
+    "required_controlled_variables": [
+      "model architecture",
+      "model revision",
+      "machine and device",
+      "formatted prompts and context lengths",
+      "output length and greedy sampling policy"
+    ],
+    "required_plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
+    "minimum_prompt_count": 3,
+    "minimum_repeats": 3,
+    "minimum_output_tokens": 32,
+    "required_device": "cpu",
+    "required_config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
+    "required_signer_public_key": "zQ/qRMwF/ydazzaxEI24Xvnrl5bZxzw16JYpP0bfRuI=",
+    "required_artifact_sha256": {
+      "transformers-safetensors-reference": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6",
+      "llama-cpp-near-lossless-quality": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
+      "llama-cpp-quantized-performance-fit": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5"
+    },
+    "required_recipe_runtime": {
+      "transformers-safetensors-reference": {
+        "runtime": "transformers-5.13.0",
+        "weight_format": "safetensors",
+        "weight_quantization": "bfloat16",
+        "device": "cpu"
+      },
+      "llama-cpp-near-lossless-quality": {
+        "runtime": "llama.cpp-9991-e920c523",
+        "weight_format": "gguf",
+        "weight_quantization": "bfloat16",
+        "device": "cpu"
+      },
+      "llama-cpp-quantized-performance-fit": {
+        "runtime": "llama.cpp-9991-e920c523",
+        "weight_format": "gguf",
+        "weight_quantization": "Q4_K_M",
+        "device": "cpu"
+      }
+    },
+    "required_backend_detail": {
+      "transformers-safetensors-reference": "torch 2.10.0+rocm7.13.0a20260513; dtype bfloat16; device cpu; intra-op threads 16",
+      "llama-cpp-near-lossless-quality": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
+      "llama-cpp-quantized-performance-fit": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0"
+    },
+    "required_host_identity": {
+      "python": "3.12.13",
+      "torch_version": "2.10.0+rocm7.13.0a20260513",
+      "transformers_version": "5.13.0",
+      "llama_server_identities": {
+        "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server": {
+          "sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
+          "version": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64"
+        }
+      }
+    }
+  },
+  "stop_condition": "Stop the native llama.cpp/GGUF track when, on the same machine and device as the Transformers/safetensors reference and under this plan, no performance-fit GGUF recipe delivers either a meaningful speed benefit (>=25% higher single-request decode tokens/sec without a >25% worse TTFT, or >=25% higher aggregate throughput under concurrency) or a meaningful fit benefit (>=25% lower peak resident memory), or when the near-lossless quality lane fails, which indicates a broken runtime rather than a quantization trade-off.",
+  "notes": "Quantized performance-fit output drift is reported as advisory only. It is not numerical-equivalence evidence. DGR-014 consumes this immutable v1 contract. Non-synthetic evidence must be Ed25519-signed by the pinned key and match the exact locked config, artifacts, runtimes, backends, and host runtime identity."
+}

.scratch/distributed-gguf-runtime/evidence/DGR-020/results.txt

@@ -0,0 +1,10 @@
+Recipe benchmark dgr-001-controlled-whole-model-baseline-v1 (local-real)
+model Qwen/Qwen2.5-0.5B-Instruct@7ae557604adf67be50417f59c2c2f167def9a775
+transformers-safetensors-reference     [quality         ] c= 1 ttft p50/p95     32.9/   173.7 ms; prefill   699.8 tok/s; decode   50.8 tok/s; aggregate    44.5 tok/s; rss  1.93 GB; vram  0.00 GB; artifact  1.00 GB; failures 0
+transformers-safetensors-reference     [quality         ] c= 4 ttft p50/p95     95.8/   425.5 ms; prefill   264.6 tok/s; decode   13.5 tok/s; aggregate    48.8 tok/s; rss  2.17 GB; vram  0.00 GB; artifact  1.00 GB; failures 0
+llama-cpp-near-lossless-quality        [quality         ] c= 1 ttft p50/p95     15.1/    65.2 ms; prefill  1740.0 tok/s; decode  102.5 tok/s; aggregate    89.3 tok/s; rss  1.11 GB; vram  0.00 GB; artifact  0.99 GB; failures 0
+llama-cpp-near-lossless-quality        [quality         ] c= 4 ttft p50/p95     36.6/   178.8 ms; prefill  1064.6 tok/s; decode   80.1 tok/s; aggregate   218.1 tok/s; rss  1.14 GB; vram  0.00 GB; artifact  0.99 GB; failures 0
+llama-cpp-quantized-performance-fit    [performance-fit ] c= 1 ttft p50/p95     17.3/   130.5 ms; prefill  1181.1 tok/s; decode  213.1 tok/s; aggregate   149.9 tok/s; rss  0.54 GB; vram  0.00 GB; artifact  0.40 GB; failures 0
+llama-cpp-quantized-performance-fit    [performance-fit ] c= 4 ttft p50/p95     42.1/   312.6 ms; prefill   567.7 tok/s; decode   94.8 tok/s; aggregate   235.7 tok/s; rss  0.57 GB; vram  0.00 GB; artifact  0.40 GB; failures 0
+drift llama-cpp-near-lossless-quality  vs transformers-safetensors-reference exact 0.33; similarity 0.947 (gated)
+drift llama-cpp-quantized-performance-fit vs transformers-safetensors-reference exact 0.00; similarity 0.456 (advisory)

.scratch/distributed-gguf-runtime/evidence/DGR-021/README.md

@@ -0,0 +1,101 @@
+# DGR-021 evidence — versioned named-tensor activation envelope
+
+**Completed:** 2026-07-17
+**Branch:** `distributed-gguf-runtime`
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json`
+**Dependency:** DGR-018 (`evidence/DGR-018/README.md`) — canonical backlog schema / issue projection contract
+
+## Objective
+
+Establish the backend-neutral activation envelope used by direct and relayed Shard traffic, with stable versioning, named tensors, bounded fragmentation, checksum validation, and reserved extensibility for future state.
+
+## Changes
+
+### `packages/node/meshnet_node/protocol.py` (new)
+
+Added a self-contained activation-envelope module with:
+
+- `SCHEMA_NAME = "meshnet.activation-stream"` and `SCHEMA_VERSION = 1`
+- `TensorFragment`
+  - bounded byte fragments with offset, compression tag, checksum, and extension preservation
+  - deterministic `to_dict()` / `from_dict()` round-trip
+- `NamedTensor`
+  - named tensor metadata: `name`, `shape`, `dtype`, `byte_order`, `compression`, `checksum`, `fragments`
+  - fragmentation via `from_bytes(..., max_fragment_bytes=...)`
+  - checksum validation over reconstructed tensor bytes
+  - unknown-field preservation via `extensions`
+- `ActivationEnvelope`
+  - top-level fields for `request_id`, `work_id`, `route_session`, `route_epoch`, `shard_start`, `effective_start`, `phase`, `position`, and `idempotency_step`
+  - reserved extension fields for `token_id_sideband`, `architecture_state`, `recurrent_state`, and `mtp`
+  - deterministic canonical serialization (`to_bytes`) and round-trip parsing (`from_bytes`)
+  - size-limit enforcement (`to_bytes(max_bytes=...)`)
+  - conversion from a live `TensorPayload` into the envelope and back again
+
+### `packages/node/meshnet_node/model_backend.py`
+
+Extended `TensorPayload` with envelope conversion helpers:
+
+- `TensorPayload.to_envelope(...)`
+- `TensorPayload.from_envelope(...)`
+
+These keep the existing activation payload interface intact while exposing the new versioned envelope as the shared protocol layer.
+
+### `tests/test_activation_envelope.py` (new)
+
+Added focused deterministic tests covering:
+
+- deterministic envelope serialization and round-trip parsing
+- tensor fragmentation and checksum validation
+- unknown-field preservation at both envelope and tensor levels
+- size-limit rejection
+- `TensorPayload` ↔ envelope round-trip
+
+### `.scratch/distributed-gguf-runtime/prd.json`
+
+Marked `DGR-021.passes = true` and added completion notes recording the envelope implementation and verification commands.
+
+## Commands and results
+
+```bash
+pytest -q tests/test_activation_envelope.py
+```
+
+```text
+5 passed in 0.06s
+```
+
+```bash
+pytest -q tests/test_activation_envelope.py tests/test_kv_cache_distributed.py -k 'session_is_stable_and_decode_payloads_are_single_token or large_prefill_activation_survives_zstd_compressed_hop'
+```
+
+```text
+..                                                                       [100%]
+2 passed, 21 deselected in 1.84s
+```
+
+```bash
+python3 -m compileall packages/node/meshnet_node tests/test_activation_envelope.py
+```
+
+```text
+Listing 'packages/node/meshnet_node'...
+Listing 'packages/node/meshnet_node/native_protocol'...
+Compiling 'tests/test_activation_envelope.py'...
+```
+
+```bash
+git diff --check
+```
+
+```text
+No whitespace errors
+```
+
+## Limitations
+
+- The envelope is implemented as a canonical deterministic JSON contract with dataclasses and conversion hooks, not generated `.proto` classes. The environment had `protobuf` available but not the `grpc_tools` generation toolchain, so I did not materialize a compiled proto artifact here.
+- The direct/relayed HTTP/WebSocket transports remain byte-oriented; the envelope is the shared structured contract layered above those transports.
+
+## Dependency handoff
+
+DGR-022 and later shard-control stories can reuse the envelope contract and its `TensorPayload` conversion hooks as the stable activation metadata layer. Future work that requires generated protobuf code can replace the JSON serialization with a generated wire codec without changing the top-level field contract defined here.

.scratch/distributed-gguf-runtime/evidence/DGR-022/README.md

@@ -0,0 +1,46 @@
+# DGR-022 evidence — Shard lifecycle and structured status RPC contract
+
+**Completed:** 2026-07-17
+**Branch:** `ralph/distributed-gguf-runtime`
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json`
+
+## Outcome
+
+Implemented the versioned, backend-neutral lifecycle/status contract consumed by a future generated gRPC binding. The contract keeps Meshnet routing, identity, authentication policy, billing, and llama.cpp ownership outside the worker contract.
+
+## Implemented
+
+- `packages/node/meshnet_node/shard_lifecycle.py`
+  - capability, health, session, cancellation, release, and metrics RPC names
+  - schema version negotiation and fail-closed unsupported-version handling
+  - structured status/error taxonomy with retryability and details
+  - lifecycle state machine for prefill/decode/cancel/release transitions
+  - monotonic idempotency-step enforcement and duplicate rejection
+  - bounded frame/byte flow control with cancellation-aware waits
+  - explicit cache expectation/result types
+  - deadline policy and TLS/auth transport hooks
+  - deterministic contract serialization round-trip
+- `tests/test_shard_lifecycle.py`
+  - contract round-trip and RPC coverage
+  - unsupported-version rejection
+  - malformed transition and idempotency rejection
+  - cancellation/release behavior
+  - bounded flow-control behavior
+  - TLS hook and incomplete-contract fail-closed behavior
+
+## Verification
+
+```text
+$ PYTHONPATH=packages/node pytest -q tests/test_shard_lifecycle.py tests/test_activation_envelope.py
+17 passed in 0.10s
+```
+
+The existing DGR-021 activation-envelope tests remain green alongside DGR-022.
+
+## Scope limitation
+
+This story defines the lifecycle/status contract only. Generated Python/C++ protobuf bindings and the concrete `shard_runtime.proto` generation pipeline are DGR-023 and remain separate.
+
+## Dependency handoff
+
+DGR-023 may consume the RPC names, status taxonomy, version identity, deadlines, flow-control limits, and TLS/auth hooks when the canonical `.proto` schema and toolchain are provisioned.