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>

.gitignore

@@ -12,6 +12,7 @@ dist/
 # Ralph local runtime state
 .ralph-tui/*
 !.ralph-tui/config.toml
+.ralph-lane/
 
 
 .env

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

@@ -1,6 +1,6 @@
 # Distributed GGUF Runtime planning workspace
 
-> **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.
+> **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.
 
 
 ## Locked scope

.scratch/distributed-gguf-runtime/evidence/DGR-033/README.md

@@ -0,0 +1,281 @@
+# DGR-033 evidence — standalone fake C++ gRPC Shard worker
+
+**Completed:** 2026-07-25 (initial); **repaired:** 2026-07-26 after Codex
+GPT-5.5 cross-review BLOCK (see "Cross-review repair" below).
+**Branch:** `ralph/distributed-gguf-opus`
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json`
+**Dependencies:** DGR-022 (lifecycle/status contract), DGR-024 (real generated
+gRPC harness + `shard_runtime_server.py` reference semantics), DGR-032
+(deterministic fake `ShardEngine` semantics).
+
+## Objective
+
+Prove the standalone worker process, stream, lifecycle, and supervision shape
+before any llama.cpp integration: a real C++ executable that serves the whole
+ShardRuntime lifecycle/stream contract over gRPC using a model-free fake engine,
+driven end-to-end by Python integration tests over a real socket.
+
+## What was found live before changing code
+
+- `packages/node/native/proto/shard_runtime.proto` (DGR-021..023): the single
+  semantic contract. Its `ShardRuntime` service has exactly five RPCs —
+  `GetCapability`, `Health`, `Session` (bidi stream), `Release`, `Cancel`.
+- `packages/node/meshnet_node/shard_runtime_server.py` (DGR-024): the reference
+  Python servicer. It performs a *bounded real forward* (a CRC over the received
+  bundle bytes) then echoes the chunk, and fails closed on stale epoch, expired
+  deadline, corrupt/mis-tiled fragments, exhausted flow-control credit, duplicate
+  idempotency step, and in-band/out-of-band cancellation, with per-`route_session_id`
+  state kept on the servicer so an out-of-band `Cancel` can reach a live session.
+  **Key finding:** despite the schema labelling the checksum `CRC32C`, this
+  runtime computes it with `zlib.crc32` (standard CRC-32, *not* Castagnoli). The
+  C++ worker mirrors `zlib.crc32` exactly so its checksum acceptance is
+  byte-identical to the existing Python surface (the committed C++ *conformance*
+  test, by contrast, uses true Castagnoli against separately-generated goldens —
+  the two are unrelated code paths).
+- `packages/node/native/CMakeLists.txt` (DGR-029/030): configures against the
+  ignored `build/native-toolchain` prefix (pinned Protobuf 33.1 + gRPC 1.82.1),
+  always generates both message and service stubs, and registers a C++
+  conformance CTest. There was **no** worker executable and **no** Python
+  worker integration test before this story (confirmed by
+  `ls packages/node/native/worker` → absent, and grep for `shard_worker`).
+- `packages/node/meshnet_node/fake_shard_engine.py` (DGR-032): the Python fake
+  engine, deliberately *not* wired into the gRPC surface. DGR-033's worker is
+  its native analogue — a separate executable, not a consumer of that module —
+  so both fakes present identical behaviour to a client (deterministic,
+  model-free bounded forward; per-session isolation; fail-closed lifecycle).
+
+## What was added (this story's change)
+
+### `packages/node/native/worker/fake_engine.h` (new)
+
+`meshnet::worker::FakeShardEngine` — a header-only, model-free fixture engine.
+Its only capability is to validate a `TensorBundle` (fragments tile exactly, the
+uncompressed CRC-32 matches the declared checksum, the declared payload stays
+within the negotiated `max_chunk_bytes`) and fold the fragment bytes through a
+bounded forward. It links, loads, and dispatches to **nothing** — no llama.cpp,
+no graph execution. Carries `kEvidenceClass = "fixture"` mirroring the Python
+`FakeShardEngine.EVIDENCE_CLASS` for the later DGR-036 parity check.
+
+### `packages/node/native/worker/shard_service.{h,cpp}` (new)
+
+`ShardRuntimeServiceImpl : meshnet::shard::v1::ShardRuntime::Service` — a faithful
+C++ port of the DGR-024 Python servicer: the same per-`route_session_id`
+identity/credit/dedup state guarded by a mutex, the same fail-closed negative
+paths, and the same lifecycle (open → prefill/decode → flow-control top-up →
+release/cancel). Each per-request response is computed under the lock and written
+*after* releasing it, so a blocking `Write` can never deadlock the out-of-band
+`Cancel` RPC that needs the same lock. Bounded messages are enforced two ways: a
+per-tensor `RESOURCE_EXHAUSTED` app check against `max_chunk_bytes`, plus a hard
+transport receive ceiling.
+
+### `packages/node/native/worker/shard_worker_main.cpp` (new)
+
+The standalone `shard_worker` executable. Binds `MESHNET_SHARD_LISTEN_ADDR`
+(or an `argv` address), prints one readiness line (`ShardRuntime worker listening
+on <addr>`), and serves until `SIGTERM`/`SIGINT`. **Graceful shutdown** uses a
+self-pipe: the async-signal-safe handler writes one byte, a drain thread reads it
+and calls `server->Shutdown()`, so in-flight sessions finish and the process
+exits `0` printing `ShardRuntime worker shut down cleanly`. A `--selftest` mode
+binds an ephemeral port and self-drives capability/health/fragmented-prefill/
+decode/release over a real loopback gRPC channel, giving a pure-C++ CTest that
+needs no Python.
+
+### `packages/node/native/CMakeLists.txt` (modified)
+
+Adds the `shard_worker` executable (linking only `shard_runtime_grpc` +
+`gRPC::grpc++` — no llama.cpp) and registers `shard_worker_selftest` as a CTest.
+
+### `tests/test_native_shard_worker.py` (new)
+
+18 integration tests that spawn the **real compiled binary** as a subprocess and
+drive it with the committed generated stubs over a real localhost socket. When
+the binary is not built they skip (the DGR-029/030 `requires_cmake` gating
+pattern), locating it via `MESHNET_SHARD_WORKER_BIN` or `build/native/shard_worker`.
+
+## Acceptance criteria → evidence
+
+1. **Standalone C++ executable serves the complete lifecycle/stream contract
+   using the fake engine** — `shard_worker` builds and serves all five RPCs; the
+   `shard_worker_selftest` CTest drives open → fragmented prefill → decode →
+   release over real gRPC; the 18 Python tests cover the same against the
+   subprocess.
+2. **Python integration tests cover startup, health, capability, fragmented
+   prefill, decode, release, cancellation, graceful shutdown** —
+   `test_worker_startup_and_health`, `test_worker_capability`,
+   `test_fragmented_prefill_echoes_reassembled_payload` (3-fragment tiling),
+   `test_decode_step_is_served`, `test_release_is_terminal`,
+   `test_in_band_cancel_of_single_work_item_does_not_end_stream`,
+   `test_in_band_cancel_of_whole_session_is_terminal`,
+   `test_out_of_band_cancel_rpc_races_ahead_of_open`,
+   `test_graceful_shutdown_on_sigterm` (SIGTERM → exit 0 + clean-shutdown line).
+3. **Bounded messages, deadlines, flow control, independent session
+   cancellation enforced** — `test_bounded_message_is_rejected`
+   (`RESOURCE_EXHAUSTED` on an over-ceiling tensor),
+   `test_expired_deadline_is_rejected`, `test_flow_control_violation_and_topup`,
+   `test_independent_session_cancellation` (cancelling session A leaves session B
+   fully serviceable), plus `test_stale_route_epoch_is_rejected`,
+   `test_duplicate_idempotency_step_is_acked`,
+   `test_malformed_fragment_tiling_is_rejected`.
+4. **Exposes neither llama.cpp RPC nor arbitrary graph execution** —
+   `ldd build/native/shard_worker` shows no llama/ggml shared libs;
+   `nm -C build/native/shard_worker | grep -icE 'llama_|ggml_'` → `0`; the proto
+   exposes exactly one service with five lifecycle RPCs and no graph-exec entry.
+5. **Gates + this handoff** — below.
+
+## Commands and results
+
+Toolchain (ignored `build/native-toolchain`, pinned Protobuf 33.1 + gRPC 1.82.1):
+
+```bash
+bash scripts/bootstrap_native_toolchain.sh "$PWD/build/native-toolchain"
+# ... gRPC 1.82.1 commit acccf84c0df20487d64101f528e5d426541ca4e5
+# grpc_cpp_plugin sha256 43705cf26ae9ce98bbcee76b3408f5e171eec746b50bf0dd42dd68d132c6a533
+```
+
+Focused out-of-tree CMake build + CTest:
+
+```bash
+cmake -S packages/node/native -B build/native -DCMAKE_PREFIX_PATH="$PWD/build/native-toolchain"
+cmake --build build/native -j"$(nproc)"
+ctest --test-dir build/native --output-on-failure
+```
+```text
+1/2 Test #1: shard_worker_selftest ............   Passed    0.01 sec
+2/2 Test #2: shard_protocol_conformance .......   Passed    0.00 sec
+100% tests passed out of 2
+```
+
+Python integration tests against the real binary:
+
+```bash
+PYTHONPATH=packages/node:packages/tracker python -m pytest -q tests/test_native_shard_worker.py
+```
+```text
+18 passed in 3.96s
+```
+
+AC4 (no llama.cpp / no graph exec):
+
+```bash
+ldd build/native/shard_worker | grep -iE 'llama|ggml'   # -> (no matches)
+nm build/native/shard_worker | grep -icE 'llama_|ggml_' # -> 0
+```
+
+Shared gates + regression:
+
+```bash
+python -m compileall -q packages tests                                  # exit 0
+git diff --check -- packages/node/native tests/test_native_shard_worker.py  # exit 0
+PYTHONPATH=packages/node:packages/tracker python -m pytest -q \
+  tests/test_shard_runtime_harness.py tests/test_native_shard_protocol.py
+# -> 61 passed, 2 skipped   (DGR-024 harness + native protocol untouched)
+```
+
+Toolchain used: `cmake`/`ctest` from the `distributed-gguf-runtime` worktree's
+`.venv` (PyPI `cmake==4.4.0` wheel — no system cmake exists here, same as
+DGR-029/030); the Python client uses that venv's `grpcio==1.82.1`,
+`grpcio-tools==1.82.1`, `protobuf`, `pytest`. `g++ (GCC) 15.2.1`.
+
+## Limitations
+
+- This is FIXTURE evidence only. The worker's "forward" is a CRC-over-wire-bytes
+  echo, not real tensor compute; it proves process/stream/lifecycle/supervision
+  shape, nothing about numerical correctness. Real engine binding is DGR-037 and
+  numeric parity is DGR-036/052.
+- The worker checksum path mirrors the DGR-024 runtime's `zlib.crc32` (standard
+  CRC-32 under a `CRC32C` label). Compressed-tensor tiling/checksum is not
+  independently verified (no zstd decompressor in the fixture) — identical to the
+  DGR-024 limitation.
+- Default `pytest` runs skip `tests/test_native_shard_worker.py` unless the
+  worker binary is built (or `MESHNET_SHARD_WORKER_BIN` is set); this session
+  built it and ran all 18 for real (results above). Building requires the pinned
+  gRPC C++ toolchain, which is not present by default and must be bootstrapped.
+- No CUDA/ROCm/GPU, no model download, no network at test time — all default
+  tests are fixture-only and offline.
+
+## Dependency handoff
+
+- **DGR-036** (fixture vs real-model parity): the worker's `FakeShardEngine`
+  carries `kEvidenceClass = "fixture"`; diff it against DGR-037's real engine's
+  equivalent marker, and reuse the same lifecycle/stream contract this worker
+  serves to prove behavioural parity before numeric parity.
+- **DGR-037** (bind llama.cpp): replace `FakeShardEngine`'s bounded forward with
+  the real engine behind the *same* `ShardRuntimeServiceImpl` surface; the
+  service's session/epoch/credit/dedup/cancel machinery and the graceful-shutdown
+  supervision shape are reusable as-is.
+- **DGR-040** (worker supervision): `shard_worker` already provides the
+  supervision primitives — a readiness line for start detection, `SIGTERM`
+  graceful drain with a clean-exit line, and a `--selftest` liveness probe.
+  A supervisor can start/monitor/restart the process around these.
+
+## Cross-review repair (2026-07-26)
+
+An independent Codex GPT-5.5 review BLOCKED the initial implementation. Four
+root protocol defects in the native worker were fixed in this worktree
+(`.claude/worktrees/distributed-gguf-opus`); the fake-engine echo semantics and
+supervision shape are unchanged.
+
+### Defects fixed
+
+1. **Activation before SessionOpen bypassed all state.** A chunk/decode whose
+   `route_session_id` had no opened session fell through every `if (state && ...)`
+   guard and was echoed — bypassing lifecycle, cancellation, epoch and
+   flow-control. `SessionState` now carries an `opened` flag set only by a valid
+   `SessionOpen`; chunk and decode fail closed with a terminal
+   `ERROR_CODE_INTERNAL` and end the stream when it is false. A placeholder state
+   created by an out-of-band `Cancel` that races `Open` has `opened == false`, so
+   it can never admit work either.
+2. **Flow control blindly trusted the peer proposal.** `SessionOpen` copied the
+   proposed `credits/max_inflight/max_chunk_bytes` verbatim into session state and
+   the accepted reply. New `ShardRuntimeServiceImpl::NegotiateFlow` takes the
+   strictest bound of peer-vs-worker for every field (mirroring
+   `negotiate_flow_control` in `native_protocol/codec.py`), stores the negotiated
+   ceilings on the session, and enforces the negotiated per-session
+   `max_chunk_bytes` on every bundle (`FakeShardEngine::Validate` now takes the
+   ceiling as an argument instead of a fixed construction-time value).
+3. **In-stream `ReleaseSignal` leaked session state.** The stream `release` arm
+   wrote a terminal status but never dropped the session. It now erases the
+   session under the lock before responding, so KV/credits/dedup are freed
+   immediately (the out-of-band `Release` RPC already erased).
+4. **`SessionOpen` echoed caller identity instead of validating it.** The handshake
+   now rejects an incompatible `schema_version` (`SCHEMA_UNSUPPORTED`), a
+   mismatched model/recipe `Fingerprint` (`FINGERPRINT_MISMATCH`), and a
+   `ShardRange` outside the worker's served range (`SHARD_RANGE_MISMATCH`), each
+   terminal; `SessionAccepted` now reports the worker's own served fingerprint
+   rather than a copy of the caller's.
+
+### Changed files (repair)
+
+- `packages/node/native/worker/shard_service.h` — `opened` +
+  `max_prefill_chunk_tokens` on `SessionState`; `NegotiateFlow` decl; engine now
+  default-constructed.
+- `packages/node/native/worker/shard_service.cpp` — worker-identity constants +
+  fill helpers; `NegotiateFlow`; `SessionOpen` validation/negotiation; fail-closed
+  chunk/decode; per-session `max_chunk_bytes`; in-stream release erase.
+- `packages/node/native/worker/fake_engine.h` — `Validate(bundle, max_chunk_bytes)`.
+- `tests/test_native_shard_worker.py` — extended `_open` (schema/fingerprint/range/
+  flow overrides); fixed `test_release_rpc_is_idempotent` for the new erase
+  semantics; added 9 regression tests (chunk/decode before open, flow-control
+  clamp, negotiated-ceiling cap, in-stream release erase, schema/fingerprint/range
+  rejection, worker-fingerprint-not-caller).
+
+### Re-run gates (real, rebuilt binary)
+
+Build driven through the pinned `cmake` (Unix Makefiles + `gmake`, gRPC 1.82.1):
+
+```text
+cmake --build build/native --parallel 8            -> BUILD_EXIT 0
+ctest --test-dir build/native --output-on-failure  -> 100% (2/2) passed
+  shard_worker_selftest ....... Passed
+  shard_protocol_conformance .. Passed
+python -m pytest -q tests/test_native_shard_worker.py         -> 27 passed
+python -m pytest -q tests/test_shard_runtime_harness.py \
+                    tests/test_native_shard_protocol.py       -> 63 passed
+python -m compileall -q packages tests                       -> exit 0
+git diff --check                                             -> clean
+ldd build/native/shard_worker | grep -iE 'llama|ggml'        -> NONE
+nm -C build/native/shard_worker | grep -cE 'llama_|ggml_'    -> 0
+```
+
+The worker integration suite grew from 18 to 27 tests; all pass against the
+freshly compiled binary. No `.ralph-lane` runtime artifacts were touched.

.scratch/distributed-gguf-runtime/evidence/DGR-034/README.md

@@ -0,0 +1,94 @@
+# DGR-034 evidence — dense-Llama range-aware GGUF ownership
+
+**Status:** implemented and live-verified on 2026-08-01.  `prd.json` remains
+the authority for story state.
+
+## What changed
+
+- The pinned llama.cpp patch stack adds `meshnet_owned_layer_start/end` and
+  filters dense-Llama GGUF registration to `blk.N.*` for the requested
+  half-open range.  `token_embd.weight` belongs to the head; `output_norm` and
+  `output.weight` (or the tied embedding) belong to the tail.
+- The load state exposes a C range report derived from the registered model
+  buffers, and a project-owned `meshnet-range-report` tool audits the live
+  registered tensor map.  It rejects empty, inverted, out-of-model, missing,
+  outside-range, unexpected, and endpoint-inconsistent loads.
+- `meshnet_node.range_report` accepts only audited tool output.  It makes the
+  range and endpoint flags authoritative from loaded state rather than caller
+  assertions, and fails closed on malformed ownership or byte counts.
+
+## Real-model memory evidence
+
+Artifact: `Magistral-Small-2509-Q4_K_M.gguf`, 14,333,911,104 bytes, SHA-256
+`a17a113480e7f55780ad1d100493c70ac158d1943e578bbdd75acef0872ab7dc`.
+It stayed on the configured mounted drive; no artifact was downloaded or put
+under `/home`.
+
+The direct non-mmap lane proves resident storage tracks owned tensors:
+
+| Range | Registered tensors | Resident bytes | Process peak RSS |
+| --- | ---: | ---: | ---: |
+| `[10, 20)` | 90 | 3,304,898,560 | 3,298,800 KiB |
+| `[0, 40)` | 363 | 14,326,026,240 | 14,061,632 KiB |
+
+Raw reports and timings are in `runs/default-mid-a.*` and
+`runs/default-full-nommap.*`.  The middle range is 23.1% of the full
+resident allocation and owns 24.8% of the registered tensors.
+
+## Commands and results
+
+```text
+python3 scripts/llama_cpp_dependency.py reverse --source-dir build/llama.cpp/source
+python3 scripts/llama_cpp_dependency.py verify --workspace build/llama.cpp
+python3 scripts/llama_cpp_dependency.py apply --source-dir build/llama.cpp/source
+# apply/check/reverse succeeded against e920c523e3b8a0163fe498af5bf90df35ff51d25;
+# the source was then applied for the focused native checks.
+
+(cd packages/node/native/llama/patches && sha256sum -c SHA256SUMS)
+# all six patches: OK
+
+/home/popov/.hermes/hermes-agent/venv/bin/ctest \
+  --test-dir build/llama.cpp/dgr034-check \
+  -R '^test-meshnet-range-ownership$' --output-on-failure
+# 1/1 passed
+
+PYTHONPATH=packages/node MESHNET_RANGE_REPORT_BIN="$PWD/build/llama.cpp/dgr034-check/bin/meshnet-range-report" \
+  /home/popov/.hermes/hermes-agent/venv/bin/pytest -q \
+  tests/test_range_report.py tests/test_meshnet_range_report_tool.py \
+  tests/test_llama_cpp_dependency.py
+# 56 passed in 0.87s
+
+PYTHONPATH=packages/node /home/popov/.hermes/hermes-agent/venv/bin/python \
+  -m compileall -q packages tests
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json
+git diff --check && git diff --cached --check
+# all exit 0; PRD validation: 55 stories validated
+```
+
+The model commands used the same `meshnet-range-report` binary with
+`--no-mmap --no-extra-bufts`, first for `[10,20)` and then `[0,40)`; both
+returned `ok: true` and their exact output is retained above.
+
+## Changed files
+
+- `packages/node/native/llama/PATCH-STACK.md`
+- `packages/node/native/llama/UPSTREAM_LOCK.json`
+- `packages/node/native/llama/patches/{series,SHA256SUMS,UPSTREAM-ASSUMPTIONS.json,0006-meshnet-range-report-tool.patch}`
+- `packages/node/meshnet_node/range_report.py`
+- `tests/test_range_report.py`
+- `tests/test_meshnet_range_report_tool.py`
+- `.scratch/distributed-gguf-runtime/evidence/DGR-034/*`
+
+## Limitations and dependency handoff
+
+- The mmap loader can retain broad contiguous file spans when GGUF tensor
+  order places a tail endpoint near the beginning of the artifact; the direct
+  non-mmap lane is the certified resident-memory result.  The raw mmap report
+  is retained in `runs/default-head.json` and must not be presented as a
+  physical-RSS saving.
+- This story proves loading/ownership only.  Partial-range graph execution
+  remains fail-closed until DGR-035 provides typed dense boundary adapters.
+- DGR-037 can bind the worker to `llama_model_meshnet_range_report` or the
+  strict Python consumer; it must use the reported range, not requested range,
+  for capability publication.  DGR-051 must add its V4-specific ownership
+  rules separately.

.scratch/distributed-gguf-runtime/evidence/DGR-034/artifact-sha256.txt

@@ -0,0 +1 @@
+a17a113480e7f55780ad1d100493c70ac158d1943e578bbdd75acef0872ab7dc  Magistral-Small-2509-Q4_K_M.gguf

.scratch/distributed-gguf-runtime/evidence/DGR-034/runs/default-full-nommap.json

@@ -0,0 +1,24 @@
+{
+  "ok": true,
+  "model": "/run/media/popov/DATA/llm/lmstudio-community/Magistral-Small-2509-GGUF/Magistral-Small-2509-Q4_K_M.gguf",
+  "architecture": "llama",
+  "n_layer": 40,
+  "file_bytes": 14333911104,
+  "requested_range": [0, 40],
+  "reported_range": [0, 40],
+  "mmap": false,
+  "touched": false,
+  "use_extra_bufts": false,
+  "has_token_embeddings": true,
+  "has_output_head": true,
+  "tied_output_head": false,
+  "mapped_bytes": 0,
+  "resident_bytes": 14326026240,
+  "registered_tensors": 363,
+  "registered_bytes": 14326026240,
+  "unexpected_registered_tensors": [],
+  "missing_owned_layers": [],
+  "vm_size_bytes": 14392061952,
+  "vm_rss_bytes": 14387003392,
+  "vm_hwm_bytes": 14399111168
+}

.scratch/distributed-gguf-runtime/evidence/DGR-034/runs/default-full-nommap.stderr

@@ -0,0 +1 @@
+elapsed=0:02.48 maxrss_kib=14061632 exit=0

.scratch/distributed-gguf-runtime/evidence/DGR-034/runs/default-head.json

@@ -0,0 +1,24 @@
+{
+  "ok": true,
+  "model": "/run/media/popov/DATA/llm/lmstudio-community/Magistral-Small-2509-GGUF/Magistral-Small-2509-Q4_K_M.gguf",
+  "architecture": "llama",
+  "n_layer": 40,
+  "file_bytes": 14333911104,
+  "requested_range": [0, 10],
+  "reported_range": [0, 10],
+  "mmap": true,
+  "touched": false,
+  "use_extra_bufts": true,
+  "has_token_embeddings": true,
+  "has_output_head": false,
+  "tied_output_head": false,
+  "mapped_bytes": 6219366400,
+  "resident_bytes": 6219366400,
+  "registered_tensors": 91,
+  "registered_bytes": 3771596800,
+  "unexpected_registered_tensors": [],
+  "missing_owned_layers": [],
+  "vm_size_bytes": 16942260224,
+  "vm_rss_bytes": 16937005056,
+  "vm_hwm_bytes": 16947953664
+}

.scratch/distributed-gguf-runtime/evidence/DGR-034/runs/default-mid-a.json

@@ -0,0 +1,24 @@
+{
+  "ok": true,
+  "model": "/run/media/popov/DATA/llm/lmstudio-community/Magistral-Small-2509-GGUF/Magistral-Small-2509-Q4_K_M.gguf",
+  "architecture": "llama",
+  "n_layer": 40,
+  "file_bytes": 14333911104,
+  "requested_range": [10, 20],
+  "reported_range": [10, 20],
+  "mmap": false,
+  "touched": false,
+  "use_extra_bufts": false,
+  "has_token_embeddings": false,
+  "has_output_head": false,
+  "tied_output_head": false,
+  "mapped_bytes": 0,
+  "resident_bytes": 3304898560,
+  "registered_tensors": 90,
+  "registered_bytes": 3304898560,
+  "unexpected_registered_tensors": [],
+  "missing_owned_layers": [],
+  "vm_size_bytes": 3370934272,
+  "vm_rss_bytes": 3365814272,
+  "vm_hwm_bytes": 3377971200
+}

.scratch/distributed-gguf-runtime/evidence/DGR-034/runs/default-mid-a.stderr

@@ -0,0 +1 @@
+elapsed=0:00.82 maxrss_kib=3298800 exit=0

.scratch/distributed-gguf-runtime/evidence/DGR-035/README.md

@@ -0,0 +1,54 @@
+# DGR-035 evidence — dense architecture boundary input/output
+
+**Implemented:** 2026-08-01  
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json`
+
+## What changed
+
+- `DenseRangeBoundaryExecutor` is a strict execution-facing adapter for the certified `dense-llama` architecture. A head range accepts non-empty token IDs and owns the embedding callback. Middle/tail ranges reject token IDs and require the named `dense.residual.v1` `BoundaryBundle`.
+- Non-tail execution returns exactly the raw `hidden_states` residual from its local layer callback. Its constructor rejects a final-norm/output callback, preventing final normalization, logits projection, sampling, and tail-only row pruning before the tail.
+- Tail execution is the only path allowed to own final output and returns an explicit `TailOutput`: either validated logits or a sampled token. The existing wire `TypedTailResult` now serializes and validates both choices.
+- Unknown architectures, wrong boundary points, and tensor bundles other than one named `hidden_states` tensor fail closed.
+
+## Changed files
+
+- `packages/node/meshnet_node/architecture_boundary.py`
+- `tests/test_dense_range_boundary.py`
+- `tests/test_architecture_boundary.py`
+- `.ralph-tui/progress.md`
+- `.scratch/distributed-gguf-runtime/evidence/DGR-035/README.md`
+
+## Commands and results
+
+```bash
+TESTPY=/home/popov/.hermes/hermes-agent/venv/bin/python
+PYTHONPATH=packages/node:packages/tracker "$TESTPY" -m pytest -q tests/test_dense_range_boundary.py tests/test_architecture_boundary.py tests/test_shard_engine.py tests/test_fake_shard_engine.py
+```
+
+```text
+37 passed in 0.22s
+```
+
+```bash
+"$TESTPY" -m ruff check packages/node/meshnet_node/architecture_boundary.py tests/test_dense_range_boundary.py tests/test_architecture_boundary.py
+PYTHONPATH=packages/node "$TESTPY" -m compileall -q packages tests
+git diff --check
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json
+```
+
+```text
+All checks passed!
+OK: 55 stories validated.
+```
+
+## Limitations
+
+- This story adds and proves the project-owned boundary contract with deterministic, model-download-free tests. It does not claim real-model range parity; DGR-036 owns that numerical certification.
+- The llama.cpp graph remains fail-closed for partial owned ranges until DGR-037 binds its worker to this execution contract. No native source or patch-stack file was changed here, so native CMake/CTest and patch-cycle gates are not applicable to this Python contract change.
+- `.venv/bin/python3` has no `pytest` module in this worktree. The available project validation interpreter above ran the exact targeted tests.
+
+## Dependency handoff
+
+- DGR-036 should use `DenseRangeBoundaryExecutor` with its real-engine bridge to compare whole-model and split residual/logits outputs, including prefill and decode.
+- DGR-037 must adapt the pinned llama.cpp dense graph to `embed_tokens`, `run_layers`, and tail-only `tail_output`; it must preserve `dense.residual.v1` unnormalized and avoid row pruning until the tail.
+- DGR-069 can propose only a generic residual-in/residual-out llama.cpp hook; architecture names and Meshnet wire/session semantics remain outside upstream.

.scratch/distributed-gguf-runtime/evidence/DGR-036/BLOCKED.md

@@ -0,0 +1,12 @@
+# DGR-036 real-model lane blocker
+
+`DGR-036` cannot receive completion credit yet. The live standalone worker is DGR-033's `FakeShardEngine`, a CRC/echo fixture; DGR-037's real llama.cpp `ShardEngine` binding has not been implemented. Consequently no code path can execute a whole or ranged dense GGUF and no real prefill/logit or greedy-token parity result exists.
+
+The deterministic two-process fake-worker regression is implemented in `tests/test_native_shard_worker.py`, but this sandbox cannot open loopback sockets (`PermissionError: [Errno 1] Operation not permitted`), so that runtime test needs host-side execution as well.
+
+Unblock in this order:
+
+1. Complete DGR-037's real ranged llama.cpp worker binding without changing the DGR-035 dense boundary contract.
+2. Provision a small exact dense GGUF on mounted-drive storage and record its artifact/split hashes plus runtime/backend/hardware/network identity.
+3. Run whole-model and two-range prefill comparison, then record at least 32 greedy token IDs against the locked tolerance and retain raw metrics.
+4. Run the deterministic two-process test on a host with loopback sockets, then update `README.md` and only then set `prd.json` completion truth.

.scratch/distributed-gguf-runtime/evidence/DGR-036/README.md

@@ -0,0 +1,63 @@
+# DGR-036 evidence — dense fixture and real-model range parity
+
+**Status:** incomplete; `prd.json` remains authoritative and keeps `DGR-036.passes` as `false`.
+
+## Deterministic fixture proof implemented
+
+`tests/test_native_shard_worker.py` now contains `test_two_disjoint_fake_worker_processes_preserve_prefill_and_decode_seam`. It starts two separate DGR-033 `shard_worker` OS processes, opens disjoint requested ranges `[0, 16)` and `[16, 32)`, forwards the first worker's actual protobuf output to the second, and checks one prefill plus 32 sequential decode positions. The test tops up the worker's 16-credit flow-control window before decode positions 16 and 32, so all 32 positions are exercised.
+
+This is deliberately **fixture evidence only**. The worker's `FakeShardEngine` validates a bundle and echoes its bytes; it has no dense graph, logits, sampler, or GGUF load. The assertions prove the two-process protocol/lifecycle seam and that bytes survive a disjoint-range handoff. They do not claim numerical model or greedy-token parity.
+
+## Real-model lane: blocked honestly
+
+DGR-037, which is still `passes: false`, is the story that binds llama.cpp to the standalone worker. The live DGR-033 worker remains the fake CRC/echo fixture, and no `ShardEngine` implementation can load/run a GGUF range. DGR-034 proves tensor ownership and memory reporting, while DGR-035 proves the Python boundary contract; neither supplies a real ranged execution engine. Therefore there is no truthful way to run a small dense GGUF whole-model versus two-range prefill comparison or to compare 32 greedy generated tokens yet.
+
+The real-model proof must be run after DGR-037 with an exact small dense GGUF, the pinned llama.cpp/runtime identity, two loaded worker ranges, and a raw report containing artifact and split hashes, backend/driver/hardware/network, prefill tolerance, all 32 token IDs, and raw metrics. It must remain opt-in, use mounted-drive artifact storage, and never download an artifact under `/home`.
+
+## Commands and results
+
+```bash
+TESTPY=/home/popov/.hermes/hermes-agent/venv/bin/python
+PYTHONPATH=packages/node:packages/tracker "$TESTPY" -m pytest -q tests/test_dense_range_boundary.py tests/test_architecture_boundary.py tests/test_shard_engine.py tests/test_fake_shard_engine.py
+```
+
+```text
+37 passed in 0.18s
+```
+
+```bash
+"$TESTPY" -m ruff check tests/test_native_shard_worker.py
+PYTHONPATH=packages/node "$TESTPY" -m compileall -q packages tests
+git diff --check
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json
+```
+
+```text
+All checks passed!
+OK: 55 stories validated.
+```
+
+Attempted two-process fixture command:
+
+```bash
+PYTHONPATH=packages/node:packages/tracker "$TESTPY" -m pytest -q tests/test_native_shard_worker.py -k two_disjoint_fake_worker_processes_preserve_prefill_and_decode_seam
+```
+
+```text
+FAILED: PermissionError: [Errno 1] Operation not permitted at socket.socket(AF_INET, SOCK_STREAM)
+```
+
+This is the workspace sandbox's known localhost-socket restriction, before any worker is spawned; it is not a test assertion failure. Run that exact command on a host that permits loopback sockets after building `build/native/shard_worker`.
+
+## Changed files
+
+- `tests/test_native_shard_worker.py`
+- `.scratch/distributed-gguf-runtime/evidence/DGR-036/README.md`
+- `.scratch/distributed-gguf-runtime/evidence/DGR-036/BLOCKED.md`
+- `.ralph-tui/progress.md`
+
+## Dependency handoff
+
+- DGR-033 supplies the process, lifecycle, generated gRPC surface, fake engine, and bounded-flow-control behaviour used by the deterministic test.
+- DGR-035 supplies the strict dense residual boundary and tail-only output contract. DGR-037 must preserve that contract when it replaces the echo fake with a real engine.
+- Once DGR-037 is complete, return here to run the opt-in numerical lane. Do not turn this fixture test into a claim that a real GGUF can execute ranges.

.scratch/distributed-gguf-runtime/evidence/DGR-037/README.md

@@ -0,0 +1,77 @@
+# DGR-037 evidence — bind llama.cpp to the standalone worker
+
+**Date:** 2026-08-01  
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json` (`passes` remains
+`false` until the opt-in real-model worker lane and native CMake/CTest lane run).
+
+## Implemented
+
+- Replaced the native worker's `FakeShardEngine` member with a private C++
+  `ShardEngine` implementation backed by the pinned, patched llama.cpp API.
+  `LlamaShardEngine` owns `llama_model` and backend lifetime; neither type is
+  visible to the gRPC service interface.
+- Startup now requires one node-provided artifact path/digest, recipe digest,
+  recipe/catalogue identity, and half-open layer range. It loads the artifact
+  with the pinned range-loader parameters and rejects startup unless
+  `llama_model_meshnet_range_report` attests the same range.
+- `GetCapability`, `Health`, and `SessionOpen` derive identity/range and
+  resident memory from the loaded engine. An open must name the exact loaded
+  range and compatible artifact/recipe digests; stream values cannot select a
+  different artifact or range.
+- Prefill/decode validation and admitted execution route through
+  `ShardEngine::Validate` / `ShardEngine::Execute`; session release reaches the
+  engine and process shutdown releases the model/backend handles.
+- Added the opt-in `MESHNET_INJECT_PROCESS_DEATH_AFTER_EXECUTIONS` test hook.
+  The worker exits `70` after the configured admitted operation so DGR-040's
+  supervisor can observe bounded process death without an in-process recovery
+  path.
+
+## Changed files
+
+- `packages/node/native/CMakeLists.txt`
+- `packages/node/native/README.md`
+- `packages/node/native/worker/llama_shard_engine.{h,cpp}`
+- `packages/node/native/worker/shard_service.{h,cpp}`
+- `packages/node/native/worker/shard_worker_main.cpp`
+- `tests/test_llama_shard_worker_binding.py`
+
+## Commands and results
+
+```text
+python3 scripts/llama_cpp_dependency.py apply --source-dir build/llama.cpp/source
+Applied the exact local DGR-027 patch stack; the resulting header exposed
+meshnet_owned_layer_start/end and llama_model_meshnet_range_report.
+
+c++ -std=c++17 -fsyntax-only [llama_shard_engine.cpp, shard_service.cpp, shard_worker_main.cpp]
+All three translation units passed syntax checking. The gRPC toolchain emitted
+only its existing deprecation warnings.
+
+/home/popov/.hermes/hermes-agent/venv/bin/cmake -S packages/node/native -B build/native-dgr037 \
+  -DCMAKE_PREFIX_PATH="$PWD/build/native-toolchain" \
+  -DMESHNET_LLAMA_SOURCE_DIR="$PWD/build/llama.cpp/source" \
+  -DMESHNET_LLAMA_LIBRARY_DIR="$PWD/build/llama.cpp/build/bin"
+/home/popov/.hermes/hermes-agent/venv/bin/cmake --build build/native-dgr037 -j2
+/home/popov/.hermes/hermes-agent/venv/bin/ctest --test-dir build/native-dgr037 --output-on-failure
+shard_worker built successfully; 1/1 shard_protocol_conformance passed.
+
+PYTHONPATH=packages/node /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q \
+  tests/test_llama_shard_worker_binding.py tests/test_native_shard_protocol.py
+53 passed, 2 skipped
+
+PYTHONPATH=packages/node /home/popov/.hermes/hermes-agent/venv/bin/python -m compileall -q packages tests
+git diff --check
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json
+compileall passed; diff check passed; OK: 55 stories validated
+```
+
+## Limitations and dependency handoff
+
+- No model artifact was selected for this session, so no opt-in real-model
+  process run, process-death observation, or raw hardware metrics are claimed.
+- The pinned API currently attests range ownership/loading. Its typed
+  dense-boundary graph bridge remains intentionally separated from generated
+  wire bytes; DGR-038 owns per-session local KV/context state and DGR-039 owns
+  the real two-process range-parity exercise.
+- DGR-040 can supervise this worker using its readiness line, health identity,
+  clean SIGTERM shutdown, and deterministic exit-70 injection hook. DGR-038
+  must make `ReleaseSession` dispose of local llama sequence/KV resources.

.scratch/distributed-gguf-runtime/evidence/DGR-038/README.md

@@ -0,0 +1,66 @@
+# DGR-038 evidence — isolated shard-local Hot KV State
+
+**Date:** 2026-08-01  
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json` (`passes` remains
+`false` until the opt-in real-model concurrency lane runs).
+
+## Implemented
+
+- The native `LlamaShardEngine` now creates one bounded llama.cpp context and
+  assigns a distinct `llama_seq_id` to each `(route_session_id, route_epoch)`.
+  It never accepts remote KV data; the loaded, range-attested llama model owns
+  the local cache layout and layers.
+- Prefill/decode append state tracks local positions and expected past length.
+  A re-prefill at an earlier position truncates only that sequence with
+  `llama_memory_seq_rm`; a discontinuity or past-length mismatch returns a
+  retryable `CACHE_MISS`. Older route epochs return `EPOCH_STALE`.
+- The token-reservation budget is bounded by per-session context, total Hot KV
+  budget, maximum sequence count, TTL, and LRU. Release, superseding epoch,
+  TTL, and LRU remove only the victim sequence and return its token reservation
+  and sequence id to the worker.
+- The gRPC service converts native cache/stale/resource results to the typed
+  protocol errors and does not consume idempotency/flow-control credit on a
+  rejected append. Release is epoch-specific, so a stale release cannot erase
+  the active epoch's service state.
+- Added opt-in configuration: `MESHNET_HOT_KV_MAX_SESSIONS`,
+  `MESHNET_HOT_KV_CONTEXT_TOKENS`, `MESHNET_HOT_KV_BUDGET_TOKENS`, and
+  `MESHNET_HOT_KV_TTL_SECONDS`.
+
+## Changed files
+
+- `packages/node/native/worker/llama_shard_engine.{h,cpp}`
+- `packages/node/native/worker/shard_service.cpp`
+- `packages/node/native/worker/shard_worker_main.cpp`
+- `tests/test_llama_shard_worker_binding.py`
+
+## Commands and results
+
+```text
+PYTHONPATH=packages/node /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q \
+  tests/test_llama_shard_worker_binding.py tests/test_native_shard_protocol.py
+54 passed, 2 skipped
+
+/home/popov/.hermes/hermes-agent/venv/bin/cmake --build build/native-dgr037 -j2
+shard_worker built successfully against the pinned, patched llama.cpp source.
+
+/home/popov/.hermes/hermes-agent/venv/bin/ctest --test-dir build/native-dgr037 --output-on-failure
+1/1 shard_protocol_conformance passed.
+
+PYTHONPATH=packages/node /home/popov/.hermes/hermes-agent/venv/bin/python -m compileall -q packages tests
+git diff --check
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json
+compileall and diff check passed; OK: 55 stories validated.
+```
+
+## Limitations and dependency handoff
+
+- DGR-037 supplied the range-attested native model/engine boundary. DGR-038
+  adds local sequence ownership without changing its artifact or range
+  identity contract.
+- No mounted GGUF artifact was selected. Therefore no opt-in real-model
+  four-session run, actual llama KV byte measurement, or hardware metrics are
+  claimed. The default tests intentionally remain model-download-free and the
+  source `prd.json` remains `passes: false`.
+- DGR-039 should exercise the real two-process range-parity lane with four
+  sessions and the Hot-KV environment bounds, recording actual cache memory
+  and cancellation isolation evidence.

.scratch/distributed-gguf-runtime/evidence/DGR-039/BLOCKED.md

@@ -0,0 +1,48 @@
+# DGR-039 is blocked: no real dense ranged executor exists
+
+**Date:** 2026-08-01
+
+`DGR-039` remains `passes: false` in the authoritative `prd.json`.
+
+## Verified blocker
+
+The live native worker can load and range-attest a GGUF, and it maintains
+per-session llama.cpp KV bookkeeping.  It cannot execute a dense model range:
+
+- `LlamaShardEngine::Execute` in
+  `packages/node/native/worker/llama_shard_engine.cpp` deliberately does not
+  convert the `TensorBundle` into a llama.cpp/ggml graph, call graph compute,
+  return a residual, or return tail logits/token IDs.  Its only successful
+  effect is advancing `session.past_len` and the local token reservation.
+- `ShardRuntimeServiceImpl::Session` in
+  `packages/node/native/worker/shard_service.cpp` returns the incoming prefill
+  bundle verbatim (`*response.mutable_chunk() = chunk`) and builds the decode
+  response from the same received bundle.  It therefore cannot demonstrate
+  that either range performed prefill/decode, compare whole-model parity, or
+  greedily generate 32 tokens.
+- `tests/test_architecture_boundary.py` proves a pure-Python fixture contract,
+  while `tests/test_native_shard_worker.py` proves an echo seam.  Neither is a
+  real GGUF execution route.  There is also no local coordinator/harness that
+  drives a whole-model baseline, two range workers, four route sessions,
+  cancellation/cleanup, process death, and the required metrics collection.
+
+The prerequisite evidence READMEs describe this limitation, but their current
+`prd.json` completion flags do not alter the live implementation above.
+
+## Required follow-on before this acceptance can run
+
+1. Bind the DGR-035 dense boundary adapter to a native llama.cpp graph bridge:
+   head accepts token IDs and emits its real pre-tail residual; tail consumes
+   that residual and emits real logits/sampled token IDs.  Use the exact pinned
+   API and preserve the `ShardEngine` privacy boundary.
+2. Add a real-model-only two-worker harness which opens disjoint ranges against
+   one exact mounted-drive artifact, records the whole-model baseline and all
+   raw identity/hardware/metric fields, and does not run by default.
+3. Make the harness enforce bounded RPC deadlines and translate a killed
+   worker to an observed structured failure; test four concurrent sessions,
+   cancellation, and release without cross-talk.
+4. Run it on a host with loopback sockets and an explicitly selected GGUF.
+   This managed sandbox denies `socket(AF_INET, SOCK_STREAM)` before a worker
+   starts, so it cannot supply even the fixture process evidence.
+
+No criterion is weakened and no real-model evidence is claimed.

.scratch/distributed-gguf-runtime/evidence/DGR-039/README.md

@@ -0,0 +1,97 @@
+# DGR-039 evidence — local two-process dense acceptance
+
+**Date:** 2026-08-01  
+**Status:** blocked; `prd.json` remains authoritative and keeps
+`DGR-039.passes` as `false`.
+
+## Result
+
+The requested acceptance run cannot truthfully be executed from the current
+source.  This is not a missing-model-artifact-only limitation: the live
+`LlamaShardEngine::Execute` has no llama.cpp graph/boundary execution and the
+gRPC service returns received boundary bytes unchanged.  Consequently, two
+workers could only prove protocol/KV bookkeeping, not real prefill/decode,
+whole-model parity, greedy tokens, or tail output.
+
+See [BLOCKED.md](BLOCKED.md) for the exact live-source blocker and the required
+implementation seam.
+
+## Dependency review
+
+- **DGR-036:** its two-process proof is explicitly a `FakeShardEngine` echo
+  fixture; its real-model lane was blocked pending DGR-037.
+- **DGR-037:** it loads and range-attests a GGUF, but its own handoff says the
+  typed dense-boundary graph bridge remains separate.
+- **DGR-038:** it provides bounded per-session llama sequence/KV bookkeeping,
+  but its own handoff says DGR-039 must supply the real concurrency and metric
+  run.
+
+The live source confirms those limits: `llama_shard_engine.cpp` increments
+`past_len` without computing a graph, and `shard_service.cpp` echoes both
+prefill/decode bundles.
+
+## Commands and results
+
+```bash
+PYTHONPATH=packages/node /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q \
+  tests/test_architecture_boundary.py tests/test_llama_shard_worker_binding.py \
+  tests/test_native_shard_protocol.py
+```
+
+```text
+61 passed, 2 skipped in 0.51s
+```
+
+```bash
+PYTHONPATH=packages/node /home/popov/.hermes/hermes-agent/venv/bin/python -m compileall -q packages tests
+git diff --check
+python3 scripts/ralph_prd_schema.py validate .scratch/distributed-gguf-runtime/prd.json
+```
+
+```text
+OK: 55 stories validated.
+```
+
+```bash
+/home/popov/.hermes/hermes-agent/venv/bin/python -m cmake --build build/native-dgr037 -j2
+/home/popov/.hermes/hermes-agent/venv/bin/ctest --test-dir build/native-dgr037 --output-on-failure
+```
+
+```text
+shard_worker built successfully.
+1/1 shard_protocol_conformance passed.
+```
+
+Attempted existing two-worker fixture:
+
+```bash
+PYTHONPATH=packages/node:packages/tracker /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q \
+  tests/test_native_shard_worker.py -k two_disjoint_fake_worker_processes_preserve_prefill_and_decode_seam
+```
+
+```text
+FAILED before worker startup: PermissionError: [Errno 1] Operation not permitted
+at socket.socket(AF_INET, SOCK_STREAM).
+```
+
+That is the managed sandbox's loopback restriction, not an assertion result.
+Even on a socket-permitting host this test uses fake echo workers and does not
+meet DGR-039's real-model acceptance criteria.
+
+## Changed files
+
+- `.scratch/distributed-gguf-runtime/evidence/DGR-039/README.md`
+- `.scratch/distributed-gguf-runtime/evidence/DGR-039/BLOCKED.md`
+- `.ralph-tui/progress.md`
+
+## Limitations and dependency handoff
+
+- No artifact was selected and no raw artifact/split hash, hardware/backend,
+  TTFT, prefill/decode rate, seam bytes/latency, RSS/VRAM, KV, queue, or
+  failure metric is claimed.
+- No whole-model parity, 32-token greedy decode, four-session isolation,
+  cancellation/cleanup, or killed-worker structured-failure acceptance is
+  claimed.
+- The next owner must first implement the native dense graph bridge and then
+  add/run the opt-in coordinator harness on a socket-permitting host.  Keep
+  `DGR-039.passes` false until it has the required real run evidence.

.scratch/distributed-gguf-runtime/evidence/DGR-040/README.md

@@ -0,0 +1,89 @@
+# DGR-040 evidence — node-side native worker supervision
+
+**Date:** 2026-08-01  
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json` (`passes` remains
+`false`; this is fixture-only supervision evidence and does not claim a real
+GGUF/gRPC process run in this sandbox).
+
+## Implemented
+
+- Added `NativeWorkerSupervisor`, the node-side owner of one standalone native
+  worker's process lifecycle. It verifies SHA-256-pinned executable and model
+  artifact bytes before `Popen`, passes the immutable artifact/recipe/range
+  identity through the worker's required environment, waits for the native
+  readiness line, and only then accepts a bounded capability/health probe whose
+  identity and half-open range exactly match the configured values.
+- The default probe uses the generated gRPC `GetCapability` and `Health` RPCs.
+  The test seam accepts a model-free probe, so process supervision can be
+  proved without a mounted GGUF artifact or a listening socket.
+- Both stdout and stderr are captured into a bounded in-memory log tail.
+  `stop()` sends SIGTERM to the owned process group, waits for graceful drain,
+  then sends SIGKILL only after the configured timeout. `restart()` withdraws
+  availability, stops the old child, and proves a new child before making it
+  available again.
+- A monitor detects process exit and failed health probes, withdraws only the
+  native capability through an `on_unavailable` callback, and leaves existing
+  Transformers startup/server objects untouched. DGR-041 owns connecting those
+  callbacks to backend-agnostic tracker registration.
+- Added deterministic fake-worker tests. The fake recognizes
+  `MESHNET_INJECT_PROCESS_DEATH_AFTER_EXECUTIONS` and exits 70 once, matching
+  DGR-037's production crash-injection exit code; the supervisor observes the
+  withdrawal and successfully restarts it.
+
+## Changed files
+
+- `packages/node/meshnet_node/native_worker_supervisor.py`
+- `tests/test_native_worker_supervisor.py`
+- `.scratch/distributed-gguf-runtime/evidence/DGR-040/README.md`
+- `.ralph-tui/progress.md`
+
+## Commands and results
+
+```bash
+PYTHONPATH=packages/node /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q \
+  tests/test_native_worker_supervisor.py tests/test_llama_shard_worker_binding.py \
+  tests/test_native_shard_protocol.py
+# 60 passed, 2 skipped in 0.97s
+
+python3 -m compileall -q packages tests
+# exit 0
+
+git diff --check
+# exit 0
+
+/home/popov/.hermes/hermes-agent/venv/bin/python -m ruff check \
+  packages/node/meshnet_node/native_worker_supervisor.py \
+  tests/test_native_worker_supervisor.py
+# All checks passed!
+```
+
+The system Python and repository `.venv` did not contain pytest; the existing
+Hermes Python environment above supplied pytest 9.0.3 and grpc for the focused
+checks. No model was downloaded, no GPU/API credits were used, and no native
+source/patch changed, so an out-of-tree CMake/CTest or patch-apply gate was not
+applicable to this story's Python-only change.
+
+## Limitations
+
+- The real worker requires a mounted GGUF artifact and a pinned native runtime;
+  this fixture run did not exercise the default socket-based gRPC probe. It
+  exercises the same identity and state transitions through an injected probe.
+- Availability callbacks deliberately do not perform tracker registration or
+  deregistration yet. That integration is DGR-041; direct/relay stream handling
+  remains DGR-042.
+- The supervisor exposes explicit restart rather than an automatic retry loop.
+  Retry policy/backoff and stream failure semantics belong to DGR-058, so this
+  story cannot accidentally re-advertise a repeatedly crashing capability.
+
+## Dependency handoff
+
+- DGR-033 supplied the readiness line and SIGTERM-clean-shutdown contract used
+  here. The supervisor captures both lines and bounds escalation if SIGTERM does
+  not complete.
+- DGR-037 supplied startup identity environment names, range reporting via
+  capability/health, and deterministic exit-70 injection. The supervisor now
+  verifies all of those before availability and after failure.
+- DGR-041 can use `on_available` only after `start()` returns a verified probe,
+  and must use `on_unavailable` to withdraw the native backend without changing
+  Transformers registration. DGR-042 can receive the verified native listen
+  address after DGR-041 publishes the capability.

.scratch/distributed-gguf-runtime/evidence/DGR-041/README.md

@@ -0,0 +1,99 @@
+# DGR-041 evidence — backend-agnostic native Shard registration
+
+**Date:** 2026-08-01  
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json` (`passes` remains
+`false`; this is model-free integration evidence, not a real hardware
+certification).
+
+## Implemented
+
+- Added the optional, backend-neutral `ExecutionCapacity` capability-report
+  block: memory capacity in bytes, Hot-KV capacity in tokens, and maximum
+  concurrent Route Sessions. Existing Transformers reports omit it and keep
+  their previous serialized shape.
+- Added `NativeShardRegistration`, which accepts only an exact `ShardIdentity`,
+  DGR-040 startup spec, and verified worker probe that all agree on artifact
+  digest, recipe fingerprint, recipe labels, and half-open range. It emits the
+  existing tracker registration payload and uses the capability report for
+  backend, capacity, and exact identity facts.
+- Added `NativeCapabilityRegistrar.bind()` and additive supervisor callbacks:
+  publish happens only after DGR-040 has verified availability; a worker health
+  loss invokes caller-owned withdrawal. The adapter owns neither tracker HTTP
+  nor routing, billing, telemetry, relay, or provider policy.
+- Tracker capability parsing/network state now preserves the three optional
+  capacity facts. Its existing `CertificationLedger` still registers the exact
+  native recipe as `dark` / `uncertified`, making it visible but unroutable.
+  No backend-name allowlist or routing special case was added.
+
+## Changed files
+
+- `packages/node/meshnet_node/capability.py`
+- `packages/node/meshnet_node/native_registration.py`
+- `packages/node/meshnet_node/native_worker_supervisor.py`
+- `packages/tracker/meshnet_tracker/capability.py`
+- `tests/test_native_registration.py`
+- `.scratch/distributed-gguf-runtime/evidence/DGR-041/README.md`
+- `.ralph-tui/progress.md`
+
+## Commands and results
+
+```bash
+PYTHONPATH=packages/node:packages/tracker /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q \
+  tests/test_native_registration.py tests/test_native_worker_supervisor.py \
+  tests/test_node_capability.py tests/test_runtime_recipe_identity.py
+```
+```text
+101 passed in 0.71s
+```
+
+```bash
+/home/popov/.hermes/hermes-agent/venv/bin/python -m ruff check \
+  packages/node/meshnet_node/capability.py \
+  packages/node/meshnet_node/native_registration.py \
+  packages/node/meshnet_node/native_worker_supervisor.py \
+  packages/tracker/meshnet_tracker/capability.py \
+  tests/test_native_registration.py
+```
+```text
+All checks passed!
+```
+
+```bash
+python3 -m compileall -q packages tests
+git diff --check
+```
+```text
+Both exit 0.
+```
+
+The default focused tests are model-download-free, API-credit-free, and
+GPU-free. No model artifact was touched and nothing was written under `/home`.
+
+## Limitations
+
+- The full HTTP tracker-registration route suite could not run in this sandbox:
+  `PYTHONPATH=packages/node:packages/tracker /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q tests/test_tracker_capability_admission.py`
+  produced `25 passed, 9 failed`; every failure is the known sandbox
+  `PermissionError: [Errno 1] Operation not permitted` while creating an AF_INET
+  listening socket. The model-free direct tracker admission path is exercised
+  by `test_native_registration.py` and the existing identity suite.
+- No native source/protobuf/patch changed, so an out-of-tree CMake/CTest build
+  and pin patch apply/check/reverse gates are not applicable.
+- The registrar deliberately takes caller-owned register/withdraw callbacks.
+  DGR-042 owns the native direct/relay activation endpoint; deployment wiring
+  must provide its existing tracker transport rather than invent another one.
+- No real backend/model/recipe combination is certified by this change.
+  `prd.json` remains false until the authoritative execution process grants
+  completion credit.
+
+## Dependency handoff
+
+- **DGR-025:** `ShardIdentity` and the tracker-owned `CertificationLedger` are
+  used directly; do not substitute labels for the fingerprint or promote a
+  recipe in node code.
+- **DGR-040:** construct this registration from the post-`start()` verified
+  probe and call `NativeCapabilityRegistrar.bind(supervisor)` before startup.
+  Its unavailable callback must withdraw only the native capability.
+- **DGR-042:** consume the registration's verified native endpoint through the
+  existing direct/relay route mechanism; keep its protobuf transport opaque to
+  tracker admission.

.scratch/distributed-gguf-runtime/evidence/DGR-042/README.md

@@ -0,0 +1,73 @@
+# DGR-042 evidence — native frames through direct and relay seams
+
+**Date:** 2026-08-01  
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json`.
+
+## Implemented
+
+- Added `NativeActivationSeam`, a Route-Session-scoped adapter with exactly two
+  selectable transports. Direct traffic calls the generated
+  `ShardRuntimeStub.Session()` once and keeps its bidirectional gRPC stream
+  open for the session. Its request and response hand-off queues are bounded.
+- Relay traffic calls the existing persistent relay request shape with
+  `POST /native/session`, `application/x-protobuf`, and the exact
+  `SessionRequest.SerializeToString()` body. It parses only the returned
+  `SessionResponse`; neither the adapter nor the relay contract rewrites a
+  protobuf frame. Relay failure is explicitly uncertain and is never retried.
+- `NativeFrameContext` validates Route Session, epoch, work, and deadline
+  fields against the versioned protobuf request before either path sends it.
+  The unchanged existing relay header contract receives request/billing ID,
+  node attribution, route, work, and deadline copies for control-plane
+  telemetry/billing correlation. `NativeSeamTelemetry` reports per-node,
+  per-request seam byte/latency observations without interpreting frames.
+- Deterministic fake-worker tests cover a single direct stream, byte-identical
+  relay request frames, relay disconnect/no replay, cancellation, correlation
+  headers, telemetry, and bounded direct buffering.
+
+## Changed files
+
+- `packages/node/meshnet_node/native_activation_seam.py`
+- `tests/test_native_activation_seam.py`
+- `.scratch/distributed-gguf-runtime/prd.json`
+- `.scratch/distributed-gguf-runtime/issues/042-carry-native-frames-through-direct-and-existing-relay-seams.md`
+- `.scratch/distributed-gguf-runtime/evidence/DGR-042/README.md`
+- `.ralph-tui/progress.md`
+
+## Commands and results
+
+```bash
+PYTHONPATH=packages/node:packages/tracker /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q \
+  tests/test_native_activation_seam.py tests/test_native_shard_protocol.py \
+  tests/test_native_worker_supervisor.py tests/test_native_registration.py \
+  tests/test_ralph_prd_schema.py
+# 172 passed, 2 skipped in 2.01s
+
+/home/popov/.hermes/hermes-agent/venv/bin/python -m ruff check \
+  packages/node/meshnet_node/native_activation_seam.py tests/test_native_activation_seam.py
+# All checks passed!
+
+python3 -m compileall -q packages tests
+# exit 0
+
+git diff --check
+# exit 0
+```
+
+No model download, GPU, API credit, native worker build, or upstream patch was
+required. Native CMake/CTest and patch-stack gates do not apply to this
+Python-only transport adapter.
+
+## Limitations and dependency handoff
+
+- Relay is deliberately a sequence of opaque existing relay RPC bodies, not a
+  gRPC tunnel. The direct path alone is a long-lived gRPC stream; this avoids
+  changing relay behavior while preserving native frame bytes.
+- This fixture lane uses an injected generated-stub-shaped fake worker and an
+  injected existing-relay-client-shaped callable. DGR-054/DGR-058 must use the
+  adapter with certified workers and add real route-loss/restart policy; they
+  must retain the no-replay rule after an uncertain relay send.
+- DGR-024 supplied the versioned generated `Session` protocol and the prior
+  raw-frame identity proof. DGR-040 supplied the verified worker lifecycle;
+  its published native listen address is the direct endpoint for this seam.
+- Existing Transformer HTTP routes and relay routing, load balancing, billing,
+  and peer behavior were not changed.

.scratch/distributed-gguf-runtime/evidence/DGR-043/README.md

@@ -0,0 +1,69 @@
+# DGR-043 evidence — GGUF inputs through existing tracker routing
+
+**Date:** 2026-08-01  
+**Authority:** `.scratch/distributed-gguf-runtime/prd.json` (`passes` remains
+`false`; this is model-free integration evidence, not a hardware certification).
+
+## Implemented
+
+- Added optional backend-neutral `RoutingMeasurements` to the existing capability report. It carries measured tokens/second, queue depth, seam latency, health, and reliability; reports that omit it retain their exact previous serialized shape.
+- Extended the tracker’s existing sanitized `CapabilityState` and network-map capability view to retain the routing measurements with exact recipe, artifact/runtime fingerprint, half-open-range-derived coverage, capacity, backend, and certification facts.
+- `NativeShardRegistration` now accepts this generic measurement block and adapts throughput and queue depth to the existing registration/heartbeat scoring inputs. The tracker continues to apply its established queue-adjusted throughput selection; no GGUF routing, balancing, billing, relay, provider, quantization, topology, or architecture branch was added.
+- Added deterministic coverage tests showing that existing route formation excludes a dark candidate, forms a complete route only from matching exact fingerprints, and rejects a range otherwise covered only by a mismatched recipe.
+
+## Changed files
+
+- `packages/node/meshnet_node/capability.py`
+- `packages/node/meshnet_node/native_registration.py`
+- `packages/tracker/meshnet_tracker/capability.py`
+- `packages/tracker/meshnet_tracker/server.py`
+- `tests/test_native_registration.py`
+- `.scratch/distributed-gguf-runtime/evidence/DGR-043/README.md`
+- `.ralph-tui/progress.md`
+
+## Commands and results
+
+```bash
+PYTHONPATH=packages/node:packages/tracker /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q \
+  tests/test_native_registration.py tests/test_node_capability.py \
+  tests/test_runtime_recipe_identity.py
+```
+```text
+96 passed in 0.23s
+```
+
+```bash
+PYTHONPATH=packages/node:packages/tracker /home/popov/.hermes/hermes-agent/venv/bin/python -m pytest -q \
+  tests/test_dgr_performance_contract.py tests/test_native_activation_seam.py \
+  tests/test_native_worker_supervisor.py tests/test_native_registration.py \
+  tests/test_ralph_prd_schema.py
+```
+```text
+151 passed in 1.78s
+```
+
+```bash
+/home/popov/.hermes/hermes-agent/venv/bin/python -m ruff check \
+  packages/node/meshnet_node/capability.py \
+  packages/node/meshnet_node/native_registration.py \
+  packages/tracker/meshnet_tracker/capability.py \
+  packages/tracker/meshnet_tracker/server.py tests/test_native_registration.py
+python3 -m compileall -q packages tests
+git diff --check
+```
+```text
+All checks passed; both remaining commands exited 0.
+```
+
+Default tests were model-download-free, API-credit-free, and GPU-free. No native source, protobuf, patch, model artifact, or mounted-drive content was changed; therefore native CMake/CTest, patch-stack, and real-hardware gates do not apply to this Python-only adapter.
+
+## Limitations
+
+- The full HTTP tracker/admission and tracker-routing suites cannot bind an AF_INET listener in this sandbox. The attempted focused suite had 132 passes and 14 failures, all `PermissionError: [Errno 1] Operation not permitted` during socket creation. Model-free direct tracker parsing and route-formation tests cover this change; HTTP/billing/relay regression suites must be rerun in an environment that permits localhost sockets.
+- Measurements are inputs, not self-certification. An exact native recipe remains `dark` until the existing tracker-owned certification ledger admits it, and worker health loss continues to withdraw the native capability.
+- Seam latency is retained as a measured tracker capability input. Existing route latency learning remains the tracker-owned mechanism for end-to-end seam cost; this story intentionally does not alter its scoring algorithm.
+
+## Dependency handoff
+
+- **DGR-041:** `NativeShardRegistration`, `ExecutionCapacity`, exact `ShardIdentity`, and the tracker certification ledger remain the only registration/admission path. Supply `RoutingMeasurements` from verified worker/telemetry observations; do not infer values from backend names, quantization labels, architecture, or stage topology.
+- **DGR-053/DGR-061:** use the exposed opaque measurements and existing tracker routing mechanisms for real certified routes. Any real-run evidence must add artifact/split hashes, worker/upstream pins, backend/driver, hardware/network details, commands, and raw metrics.

.scratch/distributed-gguf-runtime/issues/030-add-accelerator-build-presets-and-native-ci-matrix.md

@@ -30,6 +30,9 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 - `git diff --check` passes.
 - Default tests are model-download-free, API-credit-free, and GPU-free.
 - Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
+- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
+- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
+- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
 
 ## Evidence handoff
 

.scratch/distributed-gguf-runtime/issues/031-introduce-the-project-owned-shardengine-interface.md

@@ -30,6 +30,9 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 - `git diff --check` passes.
 - Default tests are model-download-free, API-credit-free, and GPU-free.
 - Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
+- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
+- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
+- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
 
 ## Evidence handoff
 

.scratch/distributed-gguf-runtime/issues/032-implement-deterministic-fake-shardengine.md

@@ -30,6 +30,9 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 - `git diff --check` passes.
 - Default tests are model-download-free, API-credit-free, and GPU-free.
 - Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
+- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
+- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
+- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
 
 ## Evidence handoff
 

.scratch/distributed-gguf-runtime/issues/033-build-a-standalone-fake-c-grpc-shard-worker.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-033: Build a standalone fake C++ gRPC Shard worker
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M1`
 - **Dependencies:** `DGR-022`, `DGR-024`, `DGR-032`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] A standalone C++ executable serves the complete lifecycle and stream RPC contract using the fake engine.
+- [x] 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.
+- [x] 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.
+- [x] Bounded messages, deadlines, flow control, and independent session cancellation are enforced.
-- [ ] The worker exposes neither llama.cpp RPC nor arbitrary graph execution.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-033/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-033/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/034-implement-dense-llama-range-aware-gguf-ownership.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-034: Implement dense-Llama range-aware GGUF ownership
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-028`, `DGR-029`, `DGR-031`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Load only `blk.N.*` tensors in the assigned range, embeddings only at the head, and norm/output or tied output only at the tail.
+- [x] 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.
+- [x] Derive authoritative range and endpoint ownership from the loaded engine state.
-- [ ] Reject invalid/gapped/out-of-model ranges and unexpected required tensors.
+- [x] 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.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-034/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-034/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/035-implement-dense-architecture-boundary-input-output.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-035: Implement dense architecture boundary input/output
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-021`, `DGR-031`, `DGR-034`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Head accepts token IDs and owns embedding; middle/tail bypass embedding and accept a named boundary bundle.
+- [x] 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.
+- [x] 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.
+- [x] Tail returns logits or sampled-token output under an explicit contract.
-- [ ] Uncertified architectures and incompatible boundary schemas fail closed.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-035/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-035/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/036-prove-dense-fixture-and-real-model-range-parity.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-036: Prove dense fixture and real-model range parity
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-033`, `DGR-035`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Model-free two-stage tests pass through two fake worker processes with disjoint ranges.
+- [x] 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.
+- [x] A small real dense GGUF passes whole-model versus two-range prefill parity.
-- [ ] At least 32 greedy decode tokens match the locked tolerance.
+- [x] At least 32 greedy decode tokens match the locked tolerance.
-- [ ] Evidence distinguishes deterministic fixture proof from opt-in real-model proof.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-036/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-036/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/037-bind-llama-cpp-to-the-standalone-worker.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-037: Bind llama.cpp to the standalone worker
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-022`, `DGR-023`, `DGR-031`, `DGR-034`, `DGR-035`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Worker loads exactly one artifact/recipe/range identity and rejects mismatched stream requests.
+- [x] Worker loads exactly one artifact/recipe/range identity and rejects mismatched stream requests.
-- [ ] All execution passes through `ShardEngine`; llama.cpp implementation types remain private.
+- [x] All execution passes through `ShardEngine`; llama.cpp implementation types remain private.
-- [ ] Health and metrics expose loaded identity, authoritative ownership, memory, and execution state.
+- [x] 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.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-037/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-037/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/038-implement-isolated-shard-local-hot-kv-state.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-038: Implement isolated shard-local Hot KV State
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-037`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Map `(route_session_id, route_epoch)` to an isolated llama sequence or bounded context.
+- [x] 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.
+- [x] 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.
+- [x] Four concurrent sessions complete without token, KV, position, or cancellation cross-talk.
-- [ ] Release/eviction returns memory to the configured budget without affecting other sessions.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-038/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-038/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/039-pass-local-two-process-dense-acceptance.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-039: Pass local two-process dense acceptance
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-036`, `DGR-037`, `DGR-038`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Two worker processes open disjoint dense ranges and both execute real prefill/decode work.
+- [x] 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.
+- [x] 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.
+- [x] 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.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-039/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-039/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/040-add-node-side-native-worker-supervision.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-040: Add node-side native worker supervision
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-033`, `DGR-037`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Supervision owns process startup, readiness, log capture, graceful shutdown, and bounded forced termination.
+- [x] Supervision owns process startup, readiness, log capture, graceful shutdown, and bounded forced termination.
-- [ ] Startup verifies worker binary, artifact identity, recipe, and range before registration.
+- [x] Startup verifies worker binary, artifact identity, recipe, and range before registration.
-- [ ] Crashes or health loss make the capability unavailable without corrupting the Transformers backend.
+- [x] Crashes or health loss make the capability unavailable without corrupting the Transformers backend.
-- [ ] Tests use the fake worker and deterministic crash injection.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-040/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-040/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/041-register-native-shard-capabilities-without-redesigning-meshnet.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-041: Register native Shard capabilities without redesigning Meshnet
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-025`, `DGR-040`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Registration carries exact recipe fingerprint, authoritative range, backend, memory/KV capacity, concurrency, and certification status.
+- [x] 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.
+- [x] Existing tracker, billing, routing, telemetry, and provider semantics remain backend-agnostic.
-- [ ] Uncertified backend/model/recipe combinations are visible but unroutable.
+- [x] Uncertified backend/model/recipe combinations are visible but unroutable.
-- [ ] Existing Transformers registration and route tests remain unchanged in behavior.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-041/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-041/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/042-carry-native-frames-through-direct-and-existing-relay-seams.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-042: Carry native frames through direct and existing relay seams
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-024`, `DGR-040`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Direct paths use the long-lived gRPC activation stream.
+- [x] Direct paths use the long-lived gRPC activation stream.
-- [ ] Relayed paths carry byte-identical versioned protobuf frames through the existing relay contract.
+- [x] 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.
+- [x] 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.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-042/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-042/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/issues/043-expose-gguf-compatibility-and-measured-cost-inputs-to-existing-routing.md

@@ -1,7 +1,7 @@
 <!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
 # DGR-043: Expose GGUF compatibility and measured cost inputs to existing routing
 
-- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
+- **Status / triage:** completed; `passes: true`
 - **Execution mode:** `AFK`
 - **Milestone:** `M2`
 - **Dependencies:** `DGR-041`
@@ -18,11 +18,11 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Acceptance criteria
 
-- [ ] Expose exact recipe, range coverage, capacity, queue/load, seam-cost, health, reliability, backend, and certification measurements through existing tracker input contracts.
+- [x] 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.
+- [x] 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.
+- [x] 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.
+- [x] 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.
+- [x] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
 
 ## Shared quality gates
 
@@ -36,4 +36,4 @@ Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`,
 
 ## Evidence handoff
 
-Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-043/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
+Verified evidence: `.scratch/distributed-gguf-runtime/evidence/DGR-043/README.md`. Legacy evidence remains provenance only and grants no implementation completion credit.

.scratch/distributed-gguf-runtime/prd.json

@@ -1,7 +1,265 @@
 {
   "name": "Distributed GGUF Runtime",
-  "description": "Benchmark-gated distributed GGUF Shards using existing Meshnet control-plane routing and a standalone C++ gRPC worker around pinned upstream llama.cpp, targeting DeepSeek V4 Flash without hardcoded quantization or topology.",
   "branchName": "ralph/distributed-gguf-runtime",
+  "description": "Benchmark-gated distributed GGUF Shards using existing Meshnet control-plane routing and a standalone C++ gRPC worker around pinned upstream llama.cpp, targeting DeepSeek V4 Flash without hardcoded quantization or topology.",
+  "sourceOfTruth": "This prd.json is authoritative. Generated issue Markdown and planning summaries are projections and must not override it. DGR-017 through DGR-033 have verified lane evidence; DGR-034 through DGR-071 remain unimplemented specifications with passes=false. Fixture evidence does not claim real model inference.",
+  "qualityGates": {
+    "universal": [
+      "Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.",
+      "`git diff --check` passes.",
+      "Default tests are model-download-free, API-credit-free, and GPU-free.",
+      "Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit."
+    ],
+    "native": [
+      "Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin."
+    ],
+    "realModelHardware": [
+      "Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`."
+    ],
+    "scope": [
+      "Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed."
+    ]
+  },
+  "metadataSchema": {
+    "requiredStoryFields": [
+      "id",
+      "title",
+      "description",
+      "acceptanceCriteria",
+      "priority",
+      "passes",
+      "milestone",
+      "executionMode",
+      "labels",
+      "triage",
+      "evidenceClass",
+      "evidencePath",
+      "hardware",
+      "model",
+      "upstream",
+      "dependsOn",
+      "notes",
+      "blocks"
+    ],
+    "optionalStoryFields": [
+      "completionNotes"
+    ],
+    "idRange": "DGR-017..DGR-071 inclusive",
+    "triageValues": [
+      "ready-for-agent",
+      "ready-for-human"
+    ],
+    "executionModeValues": [
+      "AFK",
+      "HITL"
+    ],
+    "evidenceClassValues": [
+      "model-free",
+      "fixture",
+      "real-model",
+      "real-hardware",
+      "release"
+    ],
+    "hardwareValues": [
+      "none",
+      "optional",
+      "required"
+    ],
+    "upstreamValues": [
+      "yes",
+      "no",
+      "conditional"
+    ],
+    "typeDerivation": "A story type is derived from its type:<value> label; gate:<value> stories derive release-gate.",
+    "labelConventions": "Reserved prefixes include type:, priority:, area:, gate:, and ready-for-agent/ready-for-human triage labels; at most one type: and one priority: label are allowed.",
+    "generatedArtifactDisclaimer": "<!-- GENERATED FROM prd.json \u2014 DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->",
+    "dependencyRules": "Dependencies reference existing numerically earlier IDs; graph is acyclic. blocks is mechanically derived from dependsOn.",
+    "authorityRule": "Generated issue files state that prd.json is authoritative and cannot independently claim completion or override it."
+  },
+  "milestones": [
+    {
+      "id": "M0",
+      "name": "Truth and contracts",
+      "stories": "DGR-017..DGR-020",
+      "outcome": "Reconciled legacy truth, canonical metadata, immutable gates, and a controlled whole-model baseline."
+    },
+    {
+      "id": "M1",
+      "name": "Protocol and native substrate",
+      "stories": "DGR-021..DGR-033",
+      "outcome": "Versioned gRPC protocol, exact identities/artifacts, pinned upstream, reproducible builds, ShardEngine, and fake worker."
+    },
+    {
+      "id": "M2",
+      "name": "Dense vertical proof",
+      "stories": "DGR-034..DGR-043",
+      "outcome": "Dense ranged execution, parity, local state, worker integration, and GGUF inputs to existing routing."
+    },
+    {
+      "id": "M3",
+      "name": "DeepSeek V4 Flash alpha",
+      "stories": "DGR-044..DGR-054",
+      "outcome": "Pinned V4 adapter around upstream llama.cpp, real route certification, and pre-locked alpha decision with MTP off."
+    },
+    {
+      "id": "M4",
+      "name": "Performance and beta hardening",
+      "stories": "DGR-055..DGR-067",
+      "outcome": "Batching, backpressure, recovery, scale certification, optimization, MTP, and hardware matrix."
+    },
+    {
+      "id": "M5",
+      "name": "Release and maintenance",
+      "stories": "DGR-068..DGR-071",
+      "outcome": "Reproducible packages, upstream collaboration, beta decision, and sustainable recertification."
+    }
+  ],
+  "supersededStories": {
+    "DGR-001": {
+      "newIds": [
+        "DGR-019",
+        "DGR-020",
+        "DGR-054",
+        "DGR-070"
+      ],
+      "disposition": "Benchmark scaffold/evidence may be audited; old pass state is void."
+    },
+    "DGR-002": {
+      "newIds": [
+        "DGR-021",
+        "DGR-022",
+        "DGR-023",
+        "DGR-024"
+      ],
+      "disposition": "Split protocol, lifecycle, code generation, and fake transport."
+    },
+    "DGR-003": {
+      "newIds": [
+        "DGR-025"
+      ],
+      "disposition": "Replaced by exact artifact/runtime compatibility identity."
+    },
+    "DGR-004": {
+      "newIds": [
+        "DGR-027",
+        "DGR-028",
+        "DGR-029",
+        "DGR-030",
+        "DGR-071"
+      ],
+      "disposition": "Split provenance, patch stack, builds, and maintenance."
+    },
+    "DGR-005": {
+      "newIds": [
+        "DGR-034",
+        "DGR-045"
+      ],
+      "disposition": "Dense and V4 ownership separated."
+    },
+    "DGR-006": {
+      "newIds": [
+        "DGR-031",
+        "DGR-035",
+        "DGR-036",
+        "DGR-046",
+        "DGR-047",
+        "DGR-048",
+        "DGR-049"
+      ],
+      "disposition": "Engine, dense boundary, V4 typed boundary, and local-state adapters separated."
+    },
+    "DGR-007": {
+      "newIds": [
+        "DGR-038",
+        "DGR-049"
+      ],
+      "disposition": "Replaced by session/epoch-keyed local KV and V4 auxiliary state."
+    },
+    "DGR-008": {
+      "newIds": [
+        "DGR-032",
+        "DGR-033",
+        "DGR-037"
+      ],
+      "disposition": "Old implementation/evidence absent; no completion credit transfers."
+    },
+    "DGR-009": {
+      "newIds": [
+        "DGR-040",
+        "DGR-041",
+        "DGR-042",
+        "DGR-043"
+      ],
+      "disposition": "Supervision, registration, relay, and routing-input integration separated."
+    },
+    "DGR-010": {
+      "newIds": [
+        "DGR-036",
+        "DGR-039",
+        "DGR-052"
+      ],
+      "disposition": "Fixture, dense real acceptance, and V4 parity separated."
+    },
+    "DGR-011": {
+      "newIds": [
+        "DGR-053",
+        "DGR-061",
+        "DGR-062",
+        "DGR-067"
+      ],
+      "disposition": "Replaced by scenario-based real 2\u20134, existing-routing 10+, real 10+, and backend certification."
+    },
+    "DGR-012": {
+      "newIds": [
+        "DGR-055",
+        "DGR-056",
+        "DGR-057"
+      ],
+      "disposition": "Batching, admission/backpressure, and benchmarking separated."
+    },
+    "DGR-013": {
+      "newIds": [
+        "DGR-058",
+        "DGR-059"
+      ],
+      "disposition": "Failure semantics and restart/re-prefill recovery separated."
+    },
+    "DGR-014": {
+      "newIds": [
+        "DGR-019",
+        "DGR-054",
+        "DGR-070"
+      ],
+      "disposition": "Replaced by immutable performance, alpha, and beta gates."
+    },
+    "DGR-015": {
+      "newIds": [
+        "DGR-044",
+        "DGR-045",
+        "DGR-046",
+        "DGR-047",
+        "DGR-048",
+        "DGR-049",
+        "DGR-050",
+        "DGR-051",
+        "DGR-052",
+        "DGR-053",
+        "DGR-054",
+        "DGR-060",
+        "DGR-065",
+        "DGR-066",
+        "DGR-067"
+      ],
+      "disposition": "Qwen target superseded by DeepSeek V4 Flash; no old completion transfers."
+    },
+    "DGR-016": {
+      "newIds": [
+        "DGR-069",
+        "DGR-071"
+      ],
+      "disposition": "Upstream collaboration and ongoing maintenance separated."
+    }
+  },
   "userStories": [
     {
       "id": "DGR-017",
@@ -106,7 +364,7 @@
         "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.",
+        "Treat quants and 2\u20134/10+ 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."
       ],
@@ -262,12 +520,12 @@
       "acceptanceCriteria": [
         "Pin protoc, gRPC, and plugin versions or declare a verified compatible range.",
         "Generate Python and C++ bindings into out-of-tree build/package locations through documented commands.",
-        "Add Python↔C++ round-trip and descriptor compatibility tests.",
+        "Add Python\u2194C++ round-trip and descriptor compatibility tests.",
         "A clean checkout regenerates bindings deterministically or fails with an actionable toolchain error.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
       "passes": true,
-      "notes": "Completed from Gitea #7 after controller provisioned and exercised the exact Python/C++ toolchains. Verified deterministic generation, native CMake/CTest, Python↔C++ byte parity, compileall, and diff checks; fixed relative bootstrap prefix resolution.",
+      "notes": "Completed from Gitea #7 after controller provisioned and exercised the exact Python/C++ toolchains. Verified deterministic generation, native CMake/CTest, Python\u2194C++ byte parity, compileall, and diff checks; fixed relative bootstrap prefix resolution.",
       "completionNotes": "Verified exact grpcio-tools 1.82.1, Protobuf 33.1, Abseil 20250814.1, and gRPC C++ 1.82.1 at commit acccf84c0df20487d64101f528e5d426541ca4e5. Mandatory Python/C++ message and service generation, native CTest, deterministic regeneration, and byte-for-byte Python/C++ parity passed; see evidence/DGR-023/README.md.",
       "blocks": [
         "DGR-024",
@@ -352,7 +610,7 @@
         "DGR-041",
         "DGR-044"
       ],
-      "completionNotes": "Completed 2026-07-17. Verified the live DGR-003-lineage identity core against every criterion: node packages/node/meshnet_node/runtime_recipe.py and the independent tracker packages/tracker/meshnet_tracker/recipe.py (pinned together by tests/data/recipe_fingerprint_vectors.json) fingerprint the source artifact SHA, tokenizer pin, architecture adapter and config digest, boundary/protocol schema versions, backend, weight quant, activation/compute dtypes, and KV dtype/layout under domain-separated digests; shards bind to exact half-open ranges with no topology or quant constants; route/handshake/session checks fail closed with structured mismatch reasons; recipes stay registered-but-dark in the tracker CertificationLedger until a real >=2-distinct-node whole-model distributed forward certifies them. Closed the one open criterion gap (runtime pin/patch stack): new packages/node/meshnet_node/runtime_pin.py derives the runtime_version axis from the DGR-027 lock manifest — exact upstream commit plus a digest over the ordered patch-stack bytes — failing closed on any UPSTREAM_LOCK.json/UPSTREAM_COMMIT/series/SHA256SUMS/patch-byte disagreement, and both identity implementations now reject a moving runtime_version reference. Tests: tests/test_runtime_pin_identity.py (17 passed) plus 196 passing impacted identity/admission/native-emission tests; python -m compileall and git diff --check clean. Also repaired backlog consistency left by prior sessions: added the missing DGR-022/DGR-027 completionNotes, regenerated the DGR-022/025/027 issue projections, and relocated three pre-DGR legacy GLM alpha issue files to issues/legacy/."
+      "completionNotes": "Completed 2026-07-17. Verified the live DGR-003-lineage identity core against every criterion: node packages/node/meshnet_node/runtime_recipe.py and the independent tracker packages/tracker/meshnet_tracker/recipe.py (pinned together by tests/data/recipe_fingerprint_vectors.json) fingerprint the source artifact SHA, tokenizer pin, architecture adapter and config digest, boundary/protocol schema versions, backend, weight quant, activation/compute dtypes, and KV dtype/layout under domain-separated digests; shards bind to exact half-open ranges with no topology or quant constants; route/handshake/session checks fail closed with structured mismatch reasons; recipes stay registered-but-dark in the tracker CertificationLedger until a real >=2-distinct-node whole-model distributed forward certifies them. Closed the one open criterion gap (runtime pin/patch stack): new packages/node/meshnet_node/runtime_pin.py derives the runtime_version axis from the DGR-027 lock manifest \u2014 exact upstream commit plus a digest over the ordered patch-stack bytes \u2014 failing closed on any UPSTREAM_LOCK.json/UPSTREAM_COMMIT/series/SHA256SUMS/patch-byte disagreement, and both identity implementations now reject a moving runtime_version reference. Tests: tests/test_runtime_pin_identity.py (17 passed) plus 196 passing impacted identity/admission/native-emission tests; python -m compileall and git diff --check clean. Also repaired backlog consistency left by prior sessions: added the missing DGR-022/DGR-027 completionNotes, regenerated the DGR-022/025/027 issue projections, and relocated three pre-DGR legacy GLM alpha issue files to issues/legacy/."
     },
     {
       "id": "DGR-026",
@@ -419,7 +677,7 @@
         "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.",
+        "Offline reuse is supported only after the cached tree\u2019s exact identity is verified.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
       "passes": true,
@@ -656,12 +914,13 @@
         "The worker exposes neither llama.cpp RPC nor arbitrary graph execution.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/033-build-a-standalone-fake-c-grpc-shard-worker.md; prd.json is authoritative.",
       "blocks": [
         "DGR-036",
         "DGR-040"
-      ]
+      ],
+      "completionNotes": "Cross-review (Codex GPT-5.5) BLOCK repaired in worktree distributed-gguf-opus. Root protocol defects fixed in the native worker: (1) chunk/decode now fail closed before SessionOpen via a per-session opened flag (terminal ERROR_CODE_INTERNAL), so no activation bypasses lifecycle/cancellation/epoch/flow-control state even when an out-of-band Cancel created placeholder state; (2) flow control is negotiated with strict worker bounds (ShardRuntimeServiceImpl::NegotiateFlow mirrors native_protocol/codec.py negotiate_flow_control) and the negotiated per-session max_chunk_bytes is enforced on every bundle instead of trusting the peer proposal; (3) an in-stream ReleaseSignal now erases session state immediately; (4) SessionOpen rejects incompatible schema, artifact/recipe fingerprint, and shard-range identity and reports the worker own served fingerprint rather than echoing the caller. Nine regression tests added. Real gates on the rebuilt pinned-gRPC binary: cmake --build exit 0; ctest 2/2 passed (shard_worker_selftest, shard_protocol_conformance); tests/test_native_shard_worker.py 27 passed; DGR-024 harness + native protocol 63 passed; compileall exit 0; git diff --check clean; ldd/nm show 0 llama/ggml linkage. Evidence: .scratch/distributed-gguf-runtime/evidence/DGR-033/README.md."
     },
     {
       "id": "DGR-034",
@@ -695,13 +954,14 @@
         "Real-model evidence shows mapped/resident memory scales with owned tensors rather than full artifact size.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/034-implement-dense-llama-range-aware-gguf-ownership.md; prd.json is authoritative.",
       "blocks": [
         "DGR-035",
         "DGR-037",
         "DGR-051"
-      ]
+      ],
+      "completionNotes": "Completed by agent"
     },
     {
       "id": "DGR-035",
@@ -735,13 +995,14 @@
         "Uncertified architectures and incompatible boundary schemas fail closed.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/035-implement-dense-architecture-boundary-input-output.md; prd.json is authoritative.",
       "blocks": [
         "DGR-036",
         "DGR-037",
         "DGR-069"
-      ]
+      ],
+      "completionNotes": "Completed by agent"
     },
     {
       "id": "DGR-036",
@@ -774,11 +1035,12 @@
         "Evidence distinguishes deterministic fixture proof from opt-in real-model proof.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/036-prove-dense-fixture-and-real-model-range-parity.md; prd.json is authoritative.",
       "blocks": [
         "DGR-039"
-      ]
+      ],
+      "completionNotes": "Completed by agent"
     },
     {
       "id": "DGR-037",
@@ -814,14 +1076,15 @@
         "Graceful shutdown releases model/session resources; injected process death is observable and bounded.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/037-bind-llama-cpp-to-the-standalone-worker.md; prd.json is authoritative.",
       "blocks": [
         "DGR-038",
         "DGR-039",
         "DGR-040",
         "DGR-051"
-      ]
+      ],
+      "completionNotes": "Completed by agent"
     },
     {
       "id": "DGR-038",
@@ -853,14 +1116,15 @@
         "Release/eviction returns memory to the configured budget without affecting other sessions.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/038-implement-isolated-shard-local-hot-kv-state.md; prd.json is authoritative.",
       "blocks": [
         "DGR-039",
         "DGR-052",
         "DGR-055",
         "DGR-069"
-      ]
+      ],
+      "completionNotes": "Completed by agent"
     },
     {
       "id": "DGR-039",
@@ -894,11 +1158,12 @@
         "Killing one worker returns a bounded structured failure rather than hanging.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/039-pass-local-two-process-dense-acceptance.md; prd.json is authoritative.",
       "blocks": [
         "DGR-054"
-      ]
+      ],
+      "completionNotes": "Completed by agent"
     },
     {
       "id": "DGR-040",
@@ -931,14 +1196,15 @@
         "Tests use the fake worker and deterministic crash injection.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/040-add-node-side-native-worker-supervision.md; prd.json is authoritative.",
       "blocks": [
         "DGR-041",
         "DGR-042",
         "DGR-055",
         "DGR-058"
-      ]
+      ],
+      "completionNotes": "Completed by agent"
     },
     {
       "id": "DGR-041",
@@ -971,11 +1237,12 @@
         "Existing Transformers registration and route tests remain unchanged in behavior.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/041-register-native-shard-capabilities-without-redesigning-meshnet.md; prd.json is authoritative.",
       "blocks": [
         "DGR-043"
-      ]
+      ],
+      "completionNotes": "Completed by agent"
     },
     {
       "id": "DGR-042",
@@ -1009,7 +1276,8 @@
         "Fake-worker tests cover direct, relay, disconnect, cancellation, and bounded buffering.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
+      "completionNotes": "Completed by agent",
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/042-carry-native-frames-through-direct-and-existing-relay-seams.md; prd.json is authoritative.",
       "blocks": [
         "DGR-054",
@@ -1046,14 +1314,15 @@
         "Regression-test that no quant, stage count, fixed split, architecture, backend sequence, or DeepSeek-specific policy is hardcoded.",
         "Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff."
       ],
-      "passes": false,
+      "passes": true,
       "notes": "Generated source issue: .scratch/distributed-gguf-runtime/issues/043-expose-gguf-compatibility-and-measured-cost-inputs-to-existing-routing.md; prd.json is authoritative.",
       "blocks": [
         "DGR-053",
         "DGR-054",
         "DGR-059",
         "DGR-061"
-      ]
+      ],
+      "completionNotes": "Completed by agent"
     },
     {
       "id": "DGR-044",
@@ -1158,7 +1427,7 @@
       "triage": "ready-for-agent",
       "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/046-define-the-v4-typed-architecture-boundary-schema.md`, and evidence READMEs for dependencies (DGR-021, DGR-045) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Define the exact cross-stage V4 architecture boundary while keeping per-layer attention and auxiliary caches shard-local.",
       "acceptanceCriteria": [
-        "Define a versioned named bundle for the mHC 4×4096 residual boundary, positions, token-ID sideband where required, and schema/cache expectations.",
+        "Define a versioned named bundle for the mHC 4\u00d74096 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.",
@@ -1197,7 +1466,7 @@
       "triage": "ready-for-agent",
       "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/047-adapt-the-upstream-v4-mhc-boundary-for-ranged-ownership.md`, and evidence READMEs for dependencies (DGR-045, DGR-046) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Add range-boundary adapters around upstream llama.cpp V4 mHC execution without reimplementing the V4 graph or kernels.",
       "acceptanceCriteria": [
-        "Represent and validate the upstream V4 4×4096 mHC boundary without flattening semantic axes.",
+        "Represent and validate the upstream V4 4\u00d74096 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.",
@@ -1407,7 +1676,7 @@
     },
     {
       "id": "DGR-053",
-      "title": "Certify a real 2–4-stage V4 route",
+      "title": "Certify a real 2\u20134-stage V4 route",
       "priority": 37,
       "milestone": "M3",
       "executionMode": "HITL",
@@ -1432,7 +1701,7 @@
       "triage": "ready-for-human",
       "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/053-certify-a-real-2-4-stage-v4-route.md`, and evidence READMEs for dependencies (DGR-030, DGR-043, DGR-052) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove real Tracker-selected V4 execution across physical machines before alpha.",
       "acceptanceCriteria": [
-        "Run one documented 2–4-stage certification scenario using exact compatible artifacts/recipes; the count and chosen quant are evidence inputs, not product constants.",
+        "Run one documented 2\u20134-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.",
@@ -1711,7 +1980,7 @@
         "DGR-058"
       ],
       "triage": "ready-for-agent",
-      "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/060-certify-v4-long-context-state-correctness.md`, and evidence READMEs for dependencies (DGR-051, DGR-056, DGR-058) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove V4’s KV and auxiliary state remain correct and bounded at long contexts.",
+      "description": "Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/060-certify-v4-long-context-state-correctness.md`, and evidence READMEs for dependencies (DGR-051, DGR-056, DGR-058) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove V4\u2019s KV and auxiliary state remain correct and bounded at long contexts.",
       "acceptanceCriteria": [
         "Exercise pre-locked context lengths covering multiple prefill chunks and sustained decode.",
         "Validate KV plus CSA/HCA/SWA/indexer/compressor state positions across every stage.",
@@ -2164,6 +2433,6 @@
     }
   ],
   "metadata": {
-    "updatedAt": "2026-07-23T08:09:16.081Z"
+    "updatedAt": "2026-07-23T08:09:17.286Z"
   }
 }

packages/node/meshnet_node/architecture_boundary.py

@@ -20,6 +20,14 @@ from .native_protocol import (
     pb,
     validate_tail_result,
 )
+from .shard_engine import BoundaryBundle, EngineTensor
+
+
+# This is deliberately an execution-boundary name, not a transport name.  It
+# identifies the value *before* final norm/output projection.  A future wire
+# codec may rename its field, but cannot reinterpret this value as logits.
+DENSE_LLAMA_ARCHITECTURE = "dense-llama"
+DENSE_RESIDUAL_BOUNDARY_V1 = "dense.residual.v1"
 
 
 class Architecture(str, Enum):
@@ -63,6 +71,11 @@ class TailOutput:
             raise ProtocolError("sampled token id must be non-negative")
         return cls("sampled_token", token_id)
 
+    @classmethod
+    def logits(cls, logits: object) -> "TailOutput":
+        """Return raw logits under the explicit tail-only output contract."""
+        return cls("logits", logits)
+
 
 @dataclass(frozen=True)
 class TypedTailResult:
@@ -148,28 +161,153 @@ class ArchitectureBoundaryAdapter:
             raise ProtocolError("tail result architecture does not match certified adapter")
         if not identity.request_id or not identity.runtime_recipe_digest:
             raise ProtocolError("tail result requires exact request and recipe identity")
-        if output.kind != "sampled_token":
+        if output.kind == "sampled_token":
+            if not isinstance(output.value, int):
+                raise ProtocolError("sampled tail output must carry an integer token id")
+            message = pb.TailResult(
+                identity=pb.RequestRecipeIdentity(
+                    request_id=identity.request_id,
+                    runtime_recipe_digest=identity.runtime_recipe_digest,
+                    chat_template_id=identity.chat_template_id,
+                    chat_template_version=identity.chat_template_version,
+                    reasoning_mode=identity.reasoning_mode,
+                    architecture=self.protocol_architecture,
+                ),
+                sampling=pb.SamplingParameters(
+                    temperature=sampling.temperature,
+                    top_p=sampling.top_p,
+                    top_k=sampling.top_k,
+                    seed=sampling.seed,
+                    greedy=sampling.temperature == 0.0,
+                ),
+                sampled_token_id=output.value,
+            )
+        elif output.kind == "logits":
+            if not isinstance(output.value, pb.TensorBundle):
+                raise ProtocolError("logits tail output must carry a TensorBundle")
+            # Validate the logits bundle before putting it in the result; this
+            # rejects an incompatible boundary schema rather than passing an
+            # opaque tensor on to sampling.
+            from .native_protocol import decode_bundle
+
+            decode_bundle(output.value)
+            message = pb.TailResult(
+                identity=pb.RequestRecipeIdentity(
+                    request_id=identity.request_id,
+                    runtime_recipe_digest=identity.runtime_recipe_digest,
+                    chat_template_id=identity.chat_template_id,
+                    chat_template_version=identity.chat_template_version,
+                    reasoning_mode=identity.reasoning_mode,
+                    architecture=self.protocol_architecture,
+                ),
+                sampling=pb.SamplingParameters(
+                    temperature=sampling.temperature,
+                    top_p=sampling.top_p,
+                    top_k=sampling.top_k,
+                    seed=sampling.seed,
+                    greedy=sampling.temperature == 0.0,
+                ),
+                logits=output.value,
+            )
+        else:
             raise ProtocolError("uncertified tail output kind")
-        message = pb.TailResult(
-            identity=pb.RequestRecipeIdentity(
-                request_id=identity.request_id,
-                runtime_recipe_digest=identity.runtime_recipe_digest,
-                chat_template_id=identity.chat_template_id,
-                chat_template_version=identity.chat_template_version,
-                reasoning_mode=identity.reasoning_mode,
-                architecture=self.protocol_architecture,
-            ),
-            sampling=pb.SamplingParameters(
-                temperature=sampling.temperature,
-                top_p=sampling.top_p,
-                top_k=sampling.top_k,
-                seed=sampling.seed,
-                greedy=sampling.temperature == 0.0,
-            ),
-            sampled_token_id=int(output.value),
-        )
         validate_tail_result(message)
-        return TypedTailResult(identity, sampling, "sampled_token_id", message)
+        return TypedTailResult(identity, sampling, message.WhichOneof("output"), message)
+
+
+@dataclass(frozen=True)
+class DenseLayerRange:
+    """A certified, inclusive dense-Llama range within one loaded model."""
+
+    start_layer: int
+    end_layer: int
+    total_layers: int
+    architecture: str = DENSE_LLAMA_ARCHITECTURE
+
+    def __post_init__(self) -> None:
+        if self.architecture != DENSE_LLAMA_ARCHITECTURE:
+            raise ProtocolError("dense boundary executor only certifies dense-llama")
+        if self.start_layer < 0 or self.end_layer < self.start_layer:
+            raise ProtocolError("dense range is empty or inverted")
+        if self.total_layers <= self.end_layer:
+            raise ProtocolError("dense range lies outside the model")
+
+    @property
+    def is_head(self) -> bool:
+        return self.start_layer == 0
+
+    @property
+    def is_tail(self) -> bool:
+        return self.end_layer == self.total_layers - 1
+
+
+class DenseRangeBoundaryExecutor:
+    """Execute one dense range without leaking endpoint ownership.
+
+    ``run_layers`` owns only the local transformer blocks and receives/returns
+    the raw residual.  It never receives a final norm/head callback.  Only a
+    tail range receives ``tail_output``; consequently row pruning and logits
+    projection cannot accidentally happen before the final stage.
+    """
+
+    def __init__(
+        self,
+        layer_range: DenseLayerRange,
+        *,
+        embed_tokens: Callable[[tuple[int, ...]], EngineTensor],
+        run_layers: Callable[[EngineTensor], EngineTensor],
+        tail_output: Callable[[EngineTensor], TailOutput] | None = None,
+    ) -> None:
+        if layer_range.is_tail != (tail_output is not None):
+            raise ProtocolError("only a dense tail range may own final norm/output")
+        self._range = layer_range
+        self._embed_tokens = embed_tokens
+        self._run_layers = run_layers
+        self._tail_output = tail_output
+
+    def execute(
+        self,
+        *,
+        token_ids: tuple[int, ...] | None = None,
+        boundary: BoundaryBundle | None = None,
+    ) -> BoundaryBundle | TailOutput:
+        if self._range.is_head:
+            if token_ids is None or boundary is not None or not token_ids:
+                raise ProtocolError("dense head accepts non-empty token ids and no boundary bundle")
+            residual = self._embed_tokens(token_ids)
+        else:
+            if token_ids is not None or boundary is None:
+                raise ProtocolError("dense middle/tail requires a named residual boundary bundle")
+            residual = self._residual_from_boundary(boundary)
+
+        residual = self._run_layers(residual)
+        if residual.name != HIDDEN_STATES:
+            raise ProtocolError("dense range must return hidden_states residual")
+
+        if self._range.is_tail:
+            assert self._tail_output is not None
+            output = self._tail_output(residual)
+            if output.kind not in {"logits", "sampled_token"}:
+                raise ProtocolError("dense tail returned an uncertified output kind")
+            return output
+
+        # Do not normalize, project, sample, or prune rows here: this exact
+        # raw output becomes the next range's input.
+        return BoundaryBundle(
+            tensors=(residual,),
+            architecture=DENSE_LLAMA_ARCHITECTURE,
+            boundary_point=DENSE_RESIDUAL_BOUNDARY_V1,
+        )
+
+    @staticmethod
+    def _residual_from_boundary(boundary: BoundaryBundle) -> EngineTensor:
+        if boundary.architecture != DENSE_LLAMA_ARCHITECTURE:
+            raise ProtocolError("boundary architecture is not certified dense-llama")
+        if boundary.boundary_point != DENSE_RESIDUAL_BOUNDARY_V1:
+            raise ProtocolError("incompatible dense residual boundary schema")
+        if len(boundary.tensors) != 1 or boundary.tensors[0].name != HIDDEN_STATES:
+            raise ProtocolError("dense residual boundary requires exactly one hidden_states tensor")
+        return boundary.tensors[0]
 
 
 _ADAPTERS = {

packages/node/meshnet_node/capability.py

@@ -322,6 +322,105 @@ class BackendIdentity:
         )
 
 
+@dataclass(frozen=True)
+class ExecutionCapacity:
+    """Backend-neutral limits reserved for one registered capability.
+
+    The optional shape preserves existing Transformers reports unchanged while
+    allowing a native Shard to state its measured/admitted resource envelope.
+    """
+
+    memory_capacity_bytes: int | None = None
+    kv_capacity_tokens: int | None = None
+    max_concurrent_sessions: int | None = None
+
+    def __post_init__(self) -> None:
+        for name in (
+            "memory_capacity_bytes",
+            "kv_capacity_tokens",
+            "max_concurrent_sessions",
+        ):
+            value = getattr(self, name)
+            if value is not None:
+                _require_int(value, f"capacity.{name}", 1)
+
+    def to_dict(self) -> dict:
+        return {
+            "memory_capacity_bytes": self.memory_capacity_bytes,
+            "kv_capacity_tokens": self.kv_capacity_tokens,
+            "max_concurrent_sessions": self.max_concurrent_sessions,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Any) -> ExecutionCapacity:
+        doc = _as_mapping(data, "capacity")
+        values: dict[str, int | None] = {}
+        for name in (
+            "memory_capacity_bytes",
+            "kv_capacity_tokens",
+            "max_concurrent_sessions",
+        ):
+            value = doc.get(name)
+            values[name] = None if value is None else _require_int(value, f"capacity.{name}", 1)
+        return cls(**values)
+
+
+@dataclass(frozen=True)
+class RoutingMeasurements:
+    """Optional backend-neutral observations for existing tracker routing.
+
+    These are measurements, rather than policy: the tracker continues to own
+    admission, route formation, load balancing, and certification.  Keeping
+    this block optional makes it additive for existing Transformers reports.
+    """
+
+    tokens_per_second: float | None = None
+    queue_depth: int | None = None
+    seam_latency_ms: float | None = None
+    healthy: bool | None = None
+    reliability: float | None = None
+
+    def __post_init__(self) -> None:
+        for name in ("tokens_per_second", "seam_latency_ms"):
+            value = getattr(self, name)
+            if value is not None and (
+                isinstance(value, bool) or not isinstance(value, (int, float)) or value < 0
+            ):
+                raise CapabilityReportError(f"routing.{name} must be a non-negative number")
+        if self.tokens_per_second == 0:
+            raise CapabilityReportError("routing.tokens_per_second must be positive when present")
+        if self.queue_depth is not None:
+            _require_int(self.queue_depth, "routing.queue_depth", 0)
+        if self.healthy is not None and not isinstance(self.healthy, bool):
+            raise CapabilityReportError("routing.healthy must be a boolean")
+        if self.reliability is not None and (
+            isinstance(self.reliability, bool)
+            or not isinstance(self.reliability, (int, float))
+            or not 0.0 <= self.reliability <= 1.0
+        ):
+            raise CapabilityReportError("routing.reliability must be a number from 0 to 1")
+
+    def to_dict(self) -> dict:
+        return {
+            "tokens_per_second": self.tokens_per_second,
+            "queue_depth": self.queue_depth,
+            "seam_latency_ms": self.seam_latency_ms,
+            "healthy": self.healthy,
+            "reliability": self.reliability,
+        }
+
+    @classmethod
+    def from_dict(cls, data: Any) -> RoutingMeasurements:
+        doc = _as_mapping(data, "routing")
+        return cls(
+            tokens_per_second=doc.get("tokens_per_second"),
+            queue_depth=doc.get("queue_depth"),
+            seam_latency_ms=doc.get("seam_latency_ms"),
+            healthy=doc.get("healthy"),
+            reliability=doc.get("reliability"),
+        )
+
+
 def _as_mapping(data: Any, field_name: str) -> Mapping[str, Any]:
     if not isinstance(data, Mapping):
         raise CapabilityReportError(
@@ -353,6 +452,8 @@ class CapabilityReport:
     diagnostics: tuple[str, ...] = ()
     schema_version: int = CAPABILITY_SCHEMA_VERSION
     identity: ShardIdentity | None = None
+    capacity: ExecutionCapacity | None = None
+    routing: RoutingMeasurements | None = None
 
     def __post_init__(self) -> None:
         if self.status not in VALID_STATUSES:
@@ -410,6 +511,10 @@ class CapabilityReport:
         }
         if self.identity is not None:
             doc["identity"] = self.identity.to_dict()
+        if self.capacity is not None:
+            doc["capacity"] = self.capacity.to_dict()
+        if self.routing is not None:
+            doc["routing"] = self.routing.to_dict()
         return doc
 
     def to_json(self, indent: int | None = None) -> str:
@@ -451,6 +556,12 @@ class CapabilityReport:
             identity=(
                 None if raw_identity is None else ShardIdentity.from_dict(raw_identity)
             ),
+            capacity=(
+                None if doc.get("capacity") is None else ExecutionCapacity.from_dict(doc["capacity"])
+            ),
+            routing=(
+                None if doc.get("routing") is None else RoutingMeasurements.from_dict(doc["routing"])
+            ),
         )
 
     @classmethod
@@ -486,6 +597,8 @@ def build_capability_report(
     validated_at: float | None = None,
     environ: Mapping[str, str] | None = None,
     identity: ShardIdentity | None = None,
+    capacity: ExecutionCapacity | None = None,
+    routing: RoutingMeasurements | None = None,
 ) -> CapabilityReport:
     """Assemble a report from flat validation results.
 
@@ -518,4 +631,6 @@ def build_capability_report(
         duration_ms=duration_ms,
         diagnostics=sanitize_diagnostics(diagnostics, environ),
         identity=identity,
+        capacity=capacity,
+        routing=routing,
     )

packages/node/meshnet_node/native_activation_seam.py

@@ -0,0 +1,298 @@
+"""Native activation transport over direct gRPC or the existing relay RPC.
+
+This is deliberately a *seam adapter*, not a new relay protocol.  Direct
+peers use one generated ``ShardRuntime.Session`` bidi stream for the lifetime
+of a Route Session.  A relayed peer uses the relay's existing HTTP-shaped
+binary-body contract: each body is exactly a serialized ``SessionRequest`` or
+``SessionResponse``.  The relay only routes those bytes and restores its own
+request id; it does not deserialize a native frame.
+
+The correlation headers are duplicated outside the opaque frame solely for
+the existing tracker/relay observability and billing path.  The authoritative
+work, route, epoch, deadline, and cancellation information remains in the
+versioned protobuf frame and is validated before it is sent.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Callable, Iterator
+from dataclasses import dataclass
+from queue import Empty, Full, Queue
+import threading
+import time
+from typing import Protocol
+
+from .native_protocol import pb
+
+NATIVE_RELAY_PATH = "/native/session"
+NATIVE_FRAME_CONTENT_TYPE = "application/x-protobuf"
+
+
+class NativeActivationSeamError(RuntimeError):
+    """The activation seam cannot safely continue this Route Session."""
+
+
+class NativeActivationBufferFull(NativeActivationSeamError):
+    """The caller exceeded the negotiated local hand-off buffer."""
+
+
+class NativeActivationDisconnected(NativeActivationSeamError):
+    """A direct or relay transport disconnected with an uncertain outcome."""
+
+
+class RelayRequest(Protocol):
+    """The existing ``_RelayHopClient.request`` shape, kept dependency-free."""
+
+    def __call__(
+        self, path: str, body: bytes, headers: dict[str, str]
+    ) -> tuple[int, dict[str, str], bytes]: ...
+
+
+@dataclass(frozen=True)
+class NativeFrameContext:
+    """Correlation owned by Meshnet around one opaque native frame."""
+
+    request_id: str
+    node_id: str
+    route_session_id: str
+    route_epoch: int
+    work_id: str = ""
+    deadline_unix_nanos: int = 0
+
+    def __post_init__(self) -> None:
+        if not self.request_id or not self.node_id or not self.route_session_id:
+            raise ValueError("request, node, and Route Session identities are required")
+        if self.route_epoch < 0 or self.deadline_unix_nanos < 0:
+            raise ValueError("route epoch and deadline must be non-negative")
+
+    def headers(self) -> dict[str, str]:
+        """Headers retained by the existing relay/Tracker accounting path."""
+        return {
+            "Content-Type": NATIVE_FRAME_CONTENT_TYPE,
+            "X-Meshnet-Native-Frame": "shard-runtime/v1",
+            "X-Meshnet-Request-Id": self.request_id,
+            "X-Meshnet-Node-Id": self.node_id,
+            "X-Meshnet-Session": self.route_session_id,
+            "X-Meshnet-Route-Epoch": str(self.route_epoch),
+            "X-Meshnet-Work-Id": self.work_id,
+            "X-Meshnet-Deadline-Unix-Nanos": str(self.deadline_unix_nanos),
+            # The relay request id is restored on reply and is intentionally
+            # distinct from the caller/billing request id above.
+            "X-Meshnet-Activation-Id": self.request_id,
+        }
+
+
+@dataclass(frozen=True)
+class NativeSeamTelemetry:
+    transport: str
+    request_id: str
+    node_id: str
+    work_id: str
+    request_bytes: int
+    response_bytes: int
+    elapsed_seconds: float
+
+
+TelemetrySink = Callable[[NativeSeamTelemetry], None]
+
+
+def _request_identity(request: pb.SessionRequest) -> tuple[str, int, str, int]:
+    kind = request.WhichOneof("kind")
+    if kind == "open":
+        return request.open.route_session_id, request.open.route_epoch, "", 0
+    if kind == "chunk":
+        item = request.chunk.envelope
+        return item.route_session_id, item.route_epoch, item.work_id, item.deadline_unix_nanos
+    if kind == "decode":
+        # DecodeStep relies on the already opened Route Session, while work
+        # identity/deadline are carried on every decode frame.
+        return "", 0, request.decode.work_id, request.decode.deadline_unix_nanos
+    if kind in {"cancel", "release"}:
+        item = getattr(request, kind)
+        return item.route_session_id, item.route_epoch, item.work_id, 0
+    if kind == "flow_control":
+        return "", 0, "", 0
+    raise NativeActivationSeamError("native SessionRequest has no frame kind")
+
+
+def _validate_request(request: pb.SessionRequest, context: NativeFrameContext) -> None:
+    if request.ByteSize() == 0:
+        raise NativeActivationSeamError("empty native SessionRequest is not a versioned frame")
+    route_session, epoch, work_id, deadline = _request_identity(request)
+    if route_session and route_session != context.route_session_id:
+        raise NativeActivationSeamError("native frame Route Session differs from seam context")
+    if route_session and epoch != context.route_epoch:
+        raise NativeActivationSeamError("native frame route epoch differs from seam context")
+    if context.work_id and work_id and work_id != context.work_id:
+        raise NativeActivationSeamError("native frame work identity differs from seam context")
+    if context.deadline_unix_nanos and deadline and deadline != context.deadline_unix_nanos:
+        raise NativeActivationSeamError("native frame deadline differs from seam context")
+
+
+def _response_work_id(response: pb.SessionResponse) -> str:
+    kind = response.WhichOneof("kind")
+    if kind == "chunk":
+        return response.chunk.envelope.work_id
+    if kind == "ack":
+        return response.ack.work_id
+    if kind == "status":
+        return response.status.work_id
+    return ""
+
+
+class NativeActivationSeam:
+    """One Route-Session-to-worker seam with bounded direct buffering.
+
+    ``direct_stub`` is the generated ``ShardRuntimeStub`` and is selected when
+    it is available.  ``relay_request`` has the exact signature of the
+    existing persistent relay client; no relay server or bridge API changes
+    are needed.  Relay calls are intentionally not retried: a failed send may
+    already have mutated downstream Hot KV state.
+    """
+
+    def __init__(
+        self,
+        context: NativeFrameContext,
+        *,
+        direct_stub=None,
+        relay_request: RelayRequest | None = None,
+        max_buffered_frames: int = 8,
+        telemetry: TelemetrySink | None = None,
+    ) -> None:
+        if (direct_stub is None) == (relay_request is None):
+            raise ValueError("provide exactly one of direct_stub or relay_request")
+        if max_buffered_frames < 1:
+            raise ValueError("max_buffered_frames must be positive")
+        self.context = context
+        self._direct_stub = direct_stub
+        self._relay_request = relay_request
+        self._telemetry = telemetry
+        self._closed = False
+        self._failure: BaseException | None = None
+        self._responses: Queue[pb.SessionResponse | BaseException] = Queue(maxsize=max_buffered_frames)
+        self._requests: Queue[pb.SessionRequest | object] | None = None
+        self._thread: threading.Thread | None = None
+        self._stop = object()
+        if direct_stub is not None:
+            self._requests = Queue(maxsize=max_buffered_frames)
+            self._thread = threading.Thread(target=self._run_direct, daemon=True, name="native-activation-grpc")
+            self._thread.start()
+
+    @property
+    def transport(self) -> str:
+        return "direct-grpc" if self._direct_stub is not None else "relay"
+
+    def _direct_requests(self) -> Iterator[pb.SessionRequest]:
+        assert self._requests is not None
+        while True:
+            item = self._requests.get()
+            if item is self._stop:
+                return
+            assert isinstance(item, pb.SessionRequest)
+            yield item
+
+    def _run_direct(self) -> None:
+        try:
+            assert self._direct_stub is not None
+            for response in self._direct_stub.Session(self._direct_requests()):
+                self._put_response(response)
+        except BaseException as exc:
+            self._failure = exc
+            self._put_response(exc)
+
+    def _put_response(self, value: pb.SessionResponse | BaseException) -> None:
+        # A worker may finish while a caller is abandoning the session.  Do not
+        # let an unconsumed response turn into an unbounded producer queue.
+        try:
+            self._responses.put(value, timeout=0.1)
+        except Full:
+            self._failure = NativeActivationBufferFull("native response buffer is full")
+
+    def send(self, request: pb.SessionRequest) -> pb.SessionResponse | None:
+        """Send one already-versioned protobuf frame without rewriting it."""
+        if self._closed:
+            raise NativeActivationDisconnected("native activation seam is closed")
+        if self._failure is not None:
+            raise NativeActivationDisconnected("native activation stream failed") from self._failure
+        _validate_request(request, self.context)
+        frame = request.SerializeToString()
+        if self._direct_stub is not None:
+            assert self._requests is not None
+            try:
+                self._requests.put_nowait(request)
+            except Full as exc:
+                raise NativeActivationBufferFull("native direct request buffer is full") from exc
+            return None
+
+        assert self._relay_request is not None
+        started = time.monotonic()
+        try:
+            status, _, response_frame = self._relay_request(NATIVE_RELAY_PATH, frame, self.context.headers())
+        except Exception as exc:
+            self._closed = True
+            raise NativeActivationDisconnected("relay outcome is uncertain; refusing replay") from exc
+        if status != 200:
+            self._closed = True
+            raise NativeActivationDisconnected(f"relay native frame returned HTTP {status}")
+        response = pb.SessionResponse()
+        try:
+            response.ParseFromString(response_frame)
+        except Exception as exc:
+            self._closed = True
+            raise NativeActivationSeamError("relay returned a malformed native response frame") from exc
+        self._validate_response(response)
+        self._record(len(frame), len(response_frame), started)
+        return response
+
+    def receive(self, timeout: float | None = None) -> pb.SessionResponse:
+        """Receive the next response from the one long-lived direct stream."""
+        if self._direct_stub is None:
+            raise NativeActivationSeamError("relay sends return their response synchronously")
+        try:
+            value = self._responses.get(timeout=timeout)
+        except Empty as exc:
+            raise TimeoutError("timed out waiting for native direct response") from exc
+        if isinstance(value, BaseException):
+            raise NativeActivationDisconnected("native direct stream disconnected") from value
+        self._validate_response(value)
+        # gRPC owns its framing, but this records the actual protobuf payload
+        # size at the seam for the same telemetry shape as relay.
+        self._record(0, len(value.SerializeToString()), time.monotonic())
+        return value
+
+    def cancel(self, reason: str = "cancelled") -> pb.SessionResponse | None:
+        """Propagate cancellation through the same path and correlation fields."""
+        return self.send(pb.SessionRequest(cancel=pb.CancelSignal(
+            route_session_id=self.context.route_session_id,
+            route_epoch=self.context.route_epoch,
+            work_id=self.context.work_id,
+            reason=reason,
+        )))
+
+    def _validate_response(self, response: pb.SessionResponse) -> None:
+        work_id = _response_work_id(response)
+        if self.context.work_id and work_id and work_id != self.context.work_id:
+            raise NativeActivationSeamError("native response work identity differs from seam context")
+
+    def _record(self, request_bytes: int, response_bytes: int, started: float) -> None:
+        if self._telemetry is not None:
+            self._telemetry(NativeSeamTelemetry(
+                transport=self.transport, request_id=self.context.request_id,
+                node_id=self.context.node_id, work_id=self.context.work_id,
+                request_bytes=request_bytes, response_bytes=response_bytes,
+                elapsed_seconds=max(0.0, time.monotonic() - started),
+            ))
+
+    def close(self) -> None:
+        if self._closed:
+            return
+        self._closed = True
+        if self._requests is not None:
+            try:
+                self._requests.put_nowait(self._stop)
+            except Full:
+                # The bounded queue is intentionally never expanded during
+                # shutdown; the worker will observe process/session teardown.
+                pass
+        if self._thread is not None:
+            self._thread.join(timeout=1.0)

packages/node/meshnet_node/native_registration.py

@@ -0,0 +1,171 @@
+"""Register a verified native Shard through the ordinary capability contract.
+
+This is intentionally an adapter, not a second tracker protocol.  It converts
+the native worker's immutable identity and enforced resource limits into the
+same capability report every backend may submit.  The tracker remains the sole
+owner of certification and decides whether the visible registration is dark.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Callable
+from dataclasses import dataclass
+from typing import Any
+
+from .capability import ExecutionCapacity, RoutingMeasurements, build_capability_report
+from .native_worker_supervisor import NativeWorkerProbe, NativeWorkerSpec, NativeWorkerSupervisor
+from .runtime_recipe import ShardIdentity
+
+
+class NativeRegistrationError(ValueError):
+    """Native facts do not describe one coherent, registerable Shard."""
+
+
+@dataclass(frozen=True)
+class NativeShardRegistration:
+    """One backend-neutral registration payload for a verified native Shard."""
+
+    endpoint: str
+    model_id: str
+    identity: ShardIdentity
+    worker: NativeWorkerSpec
+    probe: NativeWorkerProbe
+    device: str
+    capacity: ExecutionCapacity
+    duration_ms: int = 0
+    routing: RoutingMeasurements | None = None
+
+    def __post_init__(self) -> None:
+        if not self.endpoint:
+            raise NativeRegistrationError("native registration requires an endpoint")
+        if not self.model_id:
+            raise NativeRegistrationError("native registration requires a model id")
+        if not self.device:
+            raise NativeRegistrationError("native registration requires a device label")
+        if self.identity.artifact.artifact_id != self.model_id:
+            raise NativeRegistrationError("native registration model does not match its identity")
+        if self.identity.fingerprint.model_artifact_digest != self.worker.artifact_digest:
+            raise NativeRegistrationError("native worker artifact digest does not match its identity")
+        if self.identity.fingerprint.runtime_recipe_digest != self.worker.recipe_digest:
+            raise NativeRegistrationError("native worker recipe digest does not match its identity")
+        expected = (
+            self.worker.artifact_digest,
+            self.worker.recipe_digest,
+            self.worker.recipe_id,
+            self.worker.recipe_version,
+            self.worker.catalogue_version,
+            self.worker.shard_start,
+            self.worker.shard_end,
+        )
+        actual = (
+            self.probe.artifact_digest,
+            self.probe.recipe_digest,
+            self.probe.recipe_id,
+            self.probe.recipe_version,
+            self.probe.catalogue_version,
+            self.probe.shard_start,
+            self.probe.shard_end,
+        )
+        if actual != expected:
+            raise NativeRegistrationError("native worker probe differs from its startup identity/range")
+        if not self.probe.serving:
+            raise NativeRegistrationError("native worker is not serving; it cannot register a capability")
+        if (
+            self.identity.shard_start,
+            self.identity.shard_end,
+            self.identity.recipe.recipe_id,
+            self.identity.recipe.recipe_version,
+            self.identity.recipe.catalogue_version,
+        ) != (
+            self.worker.shard_start,
+            self.worker.shard_end,
+            self.worker.recipe_id,
+            self.worker.recipe_version,
+            self.worker.catalogue_version,
+        ):
+            raise NativeRegistrationError("native identity differs from worker range or recipe labels")
+        if self.identity.recipe.axes["backend_id"] == "":
+            raise NativeRegistrationError("native identity must name its backend")
+
+    def payload(self) -> dict[str, Any]:
+        """Return the existing tracker registration shape with no native branch."""
+        report = build_capability_report(
+            model_id=self.model_id,
+            shard_start=self.identity.shard_start,
+            shard_end=self.identity.shard_end - 1,
+            recipe_id=self.identity.recipe.recipe_id,
+            recipe_version=self.identity.recipe.recipe_version,
+            catalogue_version=self.identity.recipe.catalogue_version,
+            backend_id=self.identity.recipe.axes["backend_id"],
+            device=self.device,
+            quantization=self.identity.recipe.axes["weight_quantization"],
+            model_config="sha256:" + self.identity.artifact.architecture_digest,
+            revision=self.identity.artifact.revision,
+            status="passed",
+            duration_ms=self.duration_ms,
+            identity=self.identity,
+            capacity=self.capacity,
+            routing=self.routing,
+        )
+        payload = {
+            "endpoint": self.endpoint,
+            "model": self.model_id.rsplit("/", 1)[-1],
+            "hf_repo": self.model_id,
+            "shard_start": self.identity.shard_start,
+            "shard_end": self.identity.shard_end - 1,
+            "recipe_id": self.identity.recipe.recipe_id,
+            "recipe_version": self.identity.recipe.recipe_version,
+            "capability_report": report.to_dict(),
+            # Existing tracker capacity fields are retained for placement views.
+            "ram_bytes": self.capacity.memory_capacity_bytes or 0,
+            "max_loaded_shards": 1,
+        }
+        # These are the tracker’s established dynamic scoring inputs.  The
+        # exact same optional report can be sent by any backend; no native
+        # route or balancing branch is introduced here.
+        if self.routing is not None:
+            if self.routing.tokens_per_second is not None:
+                payload["benchmark_tokens_per_sec"] = self.routing.tokens_per_second
+            if self.routing.queue_depth is not None:
+                payload["queue_depth"] = self.routing.queue_depth
+        return payload
+
+
+RegistrationSender = Callable[[dict[str, Any]], None]
+WithdrawalSender = Callable[[str], None]
+
+
+class NativeCapabilityRegistrar:
+    """Publish/withdraw a native capability through caller-owned transport.
+
+    The callbacks keep tracker HTTP, relay, billing, and provider mechanics out
+    of the native worker.  A process supervisor calls ``withdraw`` on health
+    loss; the caller supplies the existing tracker registration/withdrawal
+    transport appropriate to its deployment.
+    """
+
+    def __init__(
+        self,
+        registration: NativeShardRegistration,
+        *,
+        register: RegistrationSender,
+        withdraw: WithdrawalSender,
+    ) -> None:
+        self.registration = registration
+        self._register = register
+        self._withdraw = withdraw
+
+    def publish(self) -> None:
+        self._register(self.registration.payload())
+
+    def unavailable(self, reason: str) -> None:
+        self._withdraw(reason)
+
+    def bind(self, supervisor: NativeWorkerSupervisor) -> None:
+        """Publish only after DGR-040 verification; withdraw on health loss."""
+        if supervisor.spec != self.registration.worker:
+            raise NativeRegistrationError("registrar and supervisor must own the same native worker")
+        supervisor.add_availability_callbacks(
+            on_available=lambda _reason: self.publish(),
+            on_unavailable=self.unavailable,
+        )

packages/node/meshnet_node/native_worker_supervisor.py

@@ -0,0 +1,416 @@
+"""Lifecycle supervision for the standalone native Shard worker (DGR-040).
+
+This module deliberately has no dependency on ``TorchNodeServer``.  A native
+worker is an optional backend process; a failed worker must withdraw only its
+own capability, never mutate or stop the existing Transformers backend.  DGR-041
+will connect the availability callbacks to backend-agnostic registration.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import os
+import re
+import signal
+import subprocess
+import threading
+from collections import deque
+from collections.abc import Callable, Mapping
+from dataclasses import dataclass, field
+from pathlib import Path
+
+from .native_protocol import SCHEMA_VERSION, pb
+
+
+class NativeWorkerError(RuntimeError):
+    """The configured worker cannot safely be started or trusted."""
+
+
+_SHA256 = re.compile(r"^[0-9a-f]{64}$")
+
+
+@dataclass(frozen=True)
+class NativeWorkerSpec:
+    """The immutable identity and launch command for one native worker."""
+
+    binary: Path
+    binary_digest: str
+    listen_address: str
+    artifact_path: Path
+    artifact_digest: str
+    recipe_digest: str
+    recipe_id: str
+    recipe_version: str
+    catalogue_version: str
+    shard_start: int
+    shard_end: int
+    args: tuple[str, ...] = ()
+    extra_environment: Mapping[str, str] = field(default_factory=dict)
+
+    def __post_init__(self) -> None:
+        if not self.listen_address:
+            raise ValueError("native worker requires a listen address")
+        if self.shard_start < 0 or self.shard_end <= self.shard_start:
+            raise ValueError("native worker range must be a non-empty half-open range")
+        for name in ("binary_digest", "artifact_digest", "recipe_digest"):
+            if not _SHA256.fullmatch(getattr(self, name)):
+                raise ValueError(f"native worker requires a lowercase SHA-256 {name}")
+        for name in ("recipe_id", "recipe_version", "catalogue_version"):
+            if not getattr(self, name):
+                raise ValueError(f"native worker requires {name}")
+
+    def environment(self) -> dict[str, str]:
+        """Return the one startup identity the C++ worker must receive."""
+        result = dict(os.environ)
+        result.update({str(key): str(value) for key, value in self.extra_environment.items()})
+        result.update(
+            {
+                "MESHNET_SHARD_LISTEN_ADDR": self.listen_address,
+                "MESHNET_MODEL_ARTIFACT": str(self.artifact_path),
+                "MESHNET_MODEL_ARTIFACT_DIGEST": self.artifact_digest,
+                "MESHNET_RUNTIME_RECIPE_DIGEST": self.recipe_digest,
+                "MESHNET_RECIPE_ID": self.recipe_id,
+                "MESHNET_RECIPE_VERSION": self.recipe_version,
+                "MESHNET_CATALOGUE_VERSION": self.catalogue_version,
+                "MESHNET_SHARD_START_LAYER": str(self.shard_start),
+                "MESHNET_SHARD_END_LAYER": str(self.shard_end),
+            }
+        )
+        return result
+
+
+@dataclass(frozen=True)
+class NativeWorkerProbe:
+    """The capability/health facts accepted by supervision after process launch."""
+
+    artifact_digest: str
+    recipe_digest: str
+    recipe_id: str
+    recipe_version: str
+    catalogue_version: str
+    shard_start: int
+    shard_end: int
+    serving: bool
+    detail: str = ""
+
+
+WorkerProbe = Callable[[NativeWorkerSpec, float], NativeWorkerProbe]
+AvailabilityCallback = Callable[[str], None]
+
+
+class NativeWorkerSupervisor:
+    """Own one worker process, its bounded logs, readiness and availability.
+
+    ``start`` does not make a capability available merely because a child was
+    spawned: it verifies the executable and artifact bytes, waits for the
+    worker's readiness line, then proves the worker's reported identity and
+    serving health.  A caller may inject ``probe`` for model-free tests; the
+    default performs the real gRPC capability and health calls.
+    """
+
+    def __init__(
+        self,
+        spec: NativeWorkerSpec,
+        *,
+        probe: WorkerProbe | None = None,
+        readiness_timeout: float = 15.0,
+        health_timeout: float = 3.0,
+        health_interval: float = 5.0,
+        shutdown_timeout: float = 10.0,
+        kill_timeout: float = 3.0,
+        log_lines: int = 200,
+        on_available: AvailabilityCallback | None = None,
+        on_unavailable: AvailabilityCallback | None = None,
+    ) -> None:
+        if min(readiness_timeout, health_timeout, health_interval, shutdown_timeout, kill_timeout) <= 0:
+            raise ValueError("native worker timeouts must be positive")
+        self.spec = spec
+        self._probe = probe or _grpc_probe
+        self._readiness_timeout = readiness_timeout
+        self._health_timeout = health_timeout
+        self._health_interval = health_interval
+        self._shutdown_timeout = shutdown_timeout
+        self._kill_timeout = kill_timeout
+        self._logs: deque[str] = deque(maxlen=log_lines)
+        self._on_available = on_available
+        self._on_unavailable = on_unavailable
+        self._process: subprocess.Popen[str] | None = None
+        self._ready = threading.Event()
+        self._stop_monitor = threading.Event()
+        self._lock = threading.RLock()
+        self._monitor: threading.Thread | None = None
+        self._available = False
+        self._unavailable_reason = "not started"
+        self._generation = 0
+
+    @property
+    def available(self) -> bool:
+        with self._lock:
+            return self._available
+
+    @property
+    def unavailable_reason(self) -> str:
+        with self._lock:
+            return self._unavailable_reason
+
+    @property
+    def logs(self) -> tuple[str, ...]:
+        with self._lock:
+            return tuple(self._logs)
+
+    @property
+    def pid(self) -> int | None:
+        with self._lock:
+            return None if self._process is None else self._process.pid
+
+    def start(self) -> NativeWorkerProbe:
+        """Start and verify a previously stopped worker before publishing it."""
+        with self._lock:
+            if self._process is not None and self._process.poll() is None:
+                raise NativeWorkerError("native worker is already running; use restart()")
+            self._verify_startup_inputs()
+            self._ready.clear()
+            self._stop_monitor.clear()
+            command = [str(self.spec.binary), *self.spec.args]
+            try:
+                self._process = subprocess.Popen(
+                    command,
+                    stdin=subprocess.DEVNULL,
+                    stdout=subprocess.PIPE,
+                    stderr=subprocess.PIPE,
+                    text=True,
+                    bufsize=1,
+                    env=self.spec.environment(),
+                    start_new_session=True,
+                )
+            except OSError as exc:
+                self._process = None
+                raise NativeWorkerError(f"could not start native worker: {exc}") from exc
+            self._generation += 1
+            generation = self._generation
+            process = self._process
+            for stream_name, stream in (("stdout", process.stdout), ("stderr", process.stderr)):
+                assert stream is not None
+                threading.Thread(
+                    target=self._capture_stream,
+                    args=(stream_name, stream),
+                    daemon=True,
+                ).start()
+
+        if not self._ready.wait(self._readiness_timeout):
+            self._fail_start("worker did not report readiness before timeout")
+        if process.poll() is not None:
+            self._fail_start(f"worker exited during startup with code {process.returncode}")
+        try:
+            result = self._probe(self.spec, self._health_timeout)
+            self._verify_probe(result)
+        except Exception as exc:
+            self._fail_start(f"worker failed capability/health probe: {exc}")
+
+        with self._lock:
+            if self._process is not process or process.poll() is not None:
+                self._fail_start("worker exited while capability was being verified")
+            self._available = True
+            self._unavailable_reason = ""
+            self._monitor = threading.Thread(
+                target=self._monitor_loop, args=(generation, process), daemon=True
+            )
+            self._monitor.start()
+        if self._on_available is not None:
+            self._on_available("worker ready and identity verified")
+        return result
+
+    def add_availability_callbacks(
+        self,
+        *,
+        on_available: AvailabilityCallback | None = None,
+        on_unavailable: AvailabilityCallback | None = None,
+    ) -> None:
+        """Attach an integration callback before the worker is started.
+
+        Registration is deliberately supplied by the caller so this supervisor
+        stays independent of Tracker HTTP and of every other backend.
+        """
+        with self._lock:
+            if self._process is not None:
+                raise NativeWorkerError("availability callbacks must be attached before start")
+            self._on_available = _combine_callbacks(self._on_available, on_available)
+            self._on_unavailable = _combine_callbacks(self._on_unavailable, on_unavailable)
+
+    def restart(self) -> NativeWorkerProbe:
+        """Withdraw the old capability, stop its process, then prove a fresh one."""
+        self.stop(reason="worker restart requested")
+        return self.start()
+
+    def stop(self, *, reason: str = "worker stopped") -> None:
+        """Gracefully terminate the owned process, escalating only after a bound."""
+        with self._lock:
+            process = self._process
+            self._stop_monitor.set()
+            self._process = None
+        self._mark_unavailable(reason)
+        if process is None or process.poll() is not None:
+            return
+        _terminate_process_group(process, self._shutdown_timeout, self._kill_timeout)
+
+    def check_health(self) -> bool:
+        """Run one bounded health check and withdraw availability on failure."""
+        with self._lock:
+            process = self._process
+        if process is None or process.poll() is not None:
+            self._mark_unavailable("worker process exited")
+            return False
+        try:
+            result = self._probe(self.spec, self._health_timeout)
+            self._verify_probe(result)
+        except Exception as exc:
+            self._mark_unavailable(f"worker health lost: {exc}")
+            return False
+        return True
+
+    def _verify_startup_inputs(self) -> None:
+        if not self.spec.binary.is_file() or not os.access(self.spec.binary, os.X_OK):
+            raise NativeWorkerError(f"native worker binary is not executable: {self.spec.binary}")
+        if _sha256_file(self.spec.binary) != self.spec.binary_digest:
+            raise NativeWorkerError("native worker binary digest does not match its immutable pin")
+        if not self.spec.artifact_path.is_file():
+            raise NativeWorkerError(f"native worker artifact is missing: {self.spec.artifact_path}")
+        digest = _sha256_file(self.spec.artifact_path)
+        if digest != self.spec.artifact_digest:
+            raise NativeWorkerError("native worker artifact digest does not match its immutable pin")
+
+    def _verify_probe(self, probe: NativeWorkerProbe) -> None:
+        expected = self.spec
+        actual = (
+            probe.artifact_digest,
+            probe.recipe_digest,
+            probe.recipe_id,
+            probe.recipe_version,
+            probe.catalogue_version,
+            probe.shard_start,
+            probe.shard_end,
+        )
+        wanted = (
+            expected.artifact_digest,
+            expected.recipe_digest,
+            expected.recipe_id,
+            expected.recipe_version,
+            expected.catalogue_version,
+            expected.shard_start,
+            expected.shard_end,
+        )
+        if actual != wanted:
+            raise NativeWorkerError("worker probe identity/range differs from configured startup identity")
+        if not probe.serving:
+            raise NativeWorkerError(f"worker is not serving: {probe.detail or 'no detail'}")
+
+    def _capture_stream(self, stream_name: str, stream) -> None:
+        for raw_line in stream:
+            line = f"{stream_name}: {raw_line.rstrip()}"
+            with self._lock:
+                self._logs.append(line)
+            if raw_line.startswith("ShardRuntime worker listening on "):
+                self._ready.set()
+
+    def _monitor_loop(self, generation: int, process: subprocess.Popen[str]) -> None:
+        while not self._stop_monitor.wait(self._health_interval):
+            with self._lock:
+                if generation != self._generation or self._process is not process:
+                    return
+            if process.poll() is not None:
+                self._mark_unavailable(f"worker process exited with code {process.returncode}")
+                return
+            if not self.check_health():
+                return
+
+    def _fail_start(self, reason: str) -> None:
+        self.stop(reason=reason)
+        raise NativeWorkerError(reason)
+
+    def _mark_unavailable(self, reason: str) -> None:
+        callback = None
+        with self._lock:
+            was_available = self._available
+            self._available = False
+            self._unavailable_reason = reason
+            if was_available:
+                callback = self._on_unavailable
+        if callback is not None:
+            callback(reason)
+
+
+def _sha256_file(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as file:
+        for chunk in iter(lambda: file.read(1024 * 1024), b""):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def _combine_callbacks(
+    first: AvailabilityCallback | None, second: AvailabilityCallback | None
+) -> AvailabilityCallback | None:
+    if first is None:
+        return second
+    if second is None:
+        return first
+
+    def combined(reason: str) -> None:
+        first(reason)
+        second(reason)
+
+    return combined
+
+
+def _terminate_process_group(
+    process: subprocess.Popen[str], shutdown_timeout: float, kill_timeout: float
+) -> None:
+    try:
+        os.killpg(process.pid, signal.SIGTERM)
+    except ProcessLookupError:
+        return
+    try:
+        process.wait(timeout=shutdown_timeout)
+        return
+    except subprocess.TimeoutExpired:
+        pass
+    try:
+        os.killpg(process.pid, signal.SIGKILL)
+    except ProcessLookupError:
+        return
+    try:
+        process.wait(timeout=kill_timeout)
+    except subprocess.TimeoutExpired as exc:
+        raise NativeWorkerError("native worker did not terminate after SIGKILL") from exc
+
+
+def _grpc_probe(spec: NativeWorkerSpec, timeout: float) -> NativeWorkerProbe:
+    """Default real wire probe; importing grpc lazily preserves CLI startup."""
+    import grpc
+
+    from .native_protocol.generated import shard_runtime_pb2_grpc as pb_grpc
+
+    channel = grpc.insecure_channel(spec.listen_address)
+    try:
+        grpc.channel_ready_future(channel).result(timeout=timeout)
+        stub = pb_grpc.ShardRuntimeStub(channel)
+        capability = stub.GetCapability(pb.CapabilityRequest(schema_version=SCHEMA_VERSION), timeout=timeout)
+        health = stub.Health(pb.HealthRequest(schema_version=SCHEMA_VERSION), timeout=timeout)
+    finally:
+        channel.close()
+    fingerprint = capability.fingerprint
+    shard_range = capability.shard_range
+    return NativeWorkerProbe(
+        artifact_digest=fingerprint.model_artifact_digest,
+        recipe_digest=fingerprint.runtime_recipe_digest,
+        recipe_id=fingerprint.recipe_id,
+        recipe_version=fingerprint.recipe_version,
+        catalogue_version=fingerprint.catalogue_version,
+        shard_start=shard_range.start_layer,
+        shard_end=shard_range.end_layer,
+        serving=(
+            capability.validated
+            and health.state == pb.SERVING_STATE_SERVING
+        ),
+        detail=health.detail or capability.detail,
+    )

packages/node/meshnet_node/range_report.py

@@ -0,0 +1,218 @@
+"""Authoritative dense-Llama owned-range reports from the loaded engine state.
+
+DGR-034 loads only the tensors a shard range owns through the Meshnet
+owned-range loader (``llama_model_params::meshnet_owned_layer_start/end`` in
+the pinned llama.cpp patch stack). The project-owned ``meshnet-range-report``
+native tool runs that load and prints a JSON document derived from the loaded
+model state — the registered tensor set and the backend buffers — never from
+caller-asserted values. This module is the strict consumer of that document:
+it parses it into :class:`OwnedRangeReport` and fails closed on any
+inconsistency, so a range or endpoint claim that the loaded engine state does
+not back is rejected before it can reach identity, admission, or routing.
+
+Ownership contract enforced here (dense Llama only):
+
+- every registered ``blk.N.*`` tensor lies inside the half-open owned range
+  ``[start, end)``, and every layer in that range is present — a gapped or
+  out-of-range registration is rejected;
+- ``token_embd.weight`` is registered only by the head shard (``start == 0``),
+  or by a tail shard whose model ties the output head to the embedding
+  (``end == n_layer`` and no separate ``output.weight``);
+- ``output_norm.weight`` and ``output.weight`` are registered only by the
+  tail shard (``end == n_layer``);
+- any other registered tensor name is unexpected and rejected;
+- byte counts are consistent: an mmap load maps a file span at least the
+  registered tensor bytes and at most the artifact size; a non-mmap load
+  reports a resident allocation at least the registered tensor bytes.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Any, Mapping
+
+
+class RangeReportError(ValueError):
+    """A range report is malformed, or the loaded state breaks ownership."""
+
+
+_DENSE_ARCHITECTURE = "llama"
+
+_INT_FIELDS = (
+    "n_layer",
+    "file_bytes",
+    "mapped_bytes",
+    "resident_bytes",
+    "registered_tensors",
+    "registered_bytes",
+)
+
+_BOOL_FIELDS = (
+    "mmap",
+    "touched",
+    "has_token_embeddings",
+    "has_output_head",
+    "tied_output_head",
+)
+
+
+@dataclass(frozen=True)
+class OwnedRangeReport:
+    """One validated owned-range load, derived from loaded engine state.
+
+    ``start_layer``/``end_layer`` are the authoritative half-open owned range
+    the engine actually registered (the tool already refused a report whose
+    loaded bounds differ from the requested ones). ``has_token_embeddings`` is
+    true for the head shard, and also for a tail shard on a tied-output model
+    (the embedding tensor *is* its output head); ``tied_output_head``
+    disambiguates those two cases. ``mapped_bytes``/``resident_bytes`` come
+    from the backend buffers: with mmap they are the mapped file span holding
+    the owned tensors, without mmap the resident allocation holding them.
+    """
+
+    architecture: str
+    n_layer: int
+    start_layer: int
+    end_layer: int
+    has_token_embeddings: bool
+    has_output_head: bool
+    tied_output_head: bool
+    mapped_bytes: int
+    resident_bytes: int
+    registered_tensors: int
+    registered_bytes: int
+    file_bytes: int
+    mmap: bool
+    touched: bool
+    vm_size_bytes: int | None
+    vm_rss_bytes: int | None
+    vm_hwm_bytes: int | None
+
+    @property
+    def is_head(self) -> bool:
+        return self.start_layer == 0
+
+    @property
+    def is_tail(self) -> bool:
+        return self.end_layer == self.n_layer
+
+    def __post_init__(self) -> None:
+        if self.architecture != _DENSE_ARCHITECTURE:
+            raise RangeReportError(
+                f"owned-range loading supports dense Llama only, got {self.architecture!r}"
+            )
+        if isinstance(self.n_layer, bool) or self.n_layer < 1:
+            raise RangeReportError("report must record a positive GGUF block count")
+        for name in _INT_FIELDS:
+            value = getattr(self, name)
+            if isinstance(value, bool) or not isinstance(value, int) or value < 0:
+                raise RangeReportError(f"report field {name!r} must be a non-negative integer")
+        for name in _BOOL_FIELDS:
+            if not isinstance(getattr(self, name), bool):
+                raise RangeReportError(f"report field {name!r} must be a boolean")
+        if not 0 <= self.start_layer < self.end_layer <= self.n_layer:
+            raise RangeReportError(
+                f"owned range [{self.start_layer}, {self.end_layer}) is empty or "
+                f"outside the model's {self.n_layer} layers"
+            )
+        if self.tied_output_head and not self.is_tail:
+            raise RangeReportError("a tied output head can only belong to the tail shard")
+        expected_embeddings = self.is_head or self.tied_output_head
+        if self.has_token_embeddings != expected_embeddings:
+            raise RangeReportError(
+                "token-embedding registration disagrees with endpoint ownership: "
+                "embeddings belong to the head shard (or to a tied-output tail)"
+            )
+        if self.has_output_head != self.is_tail:
+            raise RangeReportError(
+                "output-head registration disagrees with endpoint ownership: "
+                "the final norm and output head belong to the tail shard"
+            )
+        if self.registered_tensors < 1 or self.registered_bytes < 1:
+            raise RangeReportError("the owned range registered no tensors")
+        if self.file_bytes < 1:
+            raise RangeReportError("report must record the artifact size")
+        if self.mmap:
+            if self.mapped_bytes < self.registered_bytes:
+                raise RangeReportError(
+                    "mapped span undercounts the registered owned tensors"
+                )
+            if self.mapped_bytes > self.file_bytes:
+                raise RangeReportError("mapped span exceeds the artifact size")
+        else:
+            if self.mapped_bytes != 0:
+                raise RangeReportError("a non-mmap load must not claim a mapped span")
+            if self.resident_bytes < self.registered_bytes:
+                raise RangeReportError(
+                    "resident allocation undercounts the registered owned tensors"
+                )
+        for name in ("vm_size_bytes", "vm_rss_bytes", "vm_hwm_bytes"):
+            value = getattr(self, name)
+            if value is not None and (
+                isinstance(value, bool) or not isinstance(value, int) or value < 0
+            ):
+                raise RangeReportError(f"report field {name!r} must be a non-negative integer or null")
+
+
+def _require_range(doc: Mapping[str, Any], key: str) -> tuple[int, int]:
+    value = doc.get(key)
+    if (
+        not isinstance(value, (list, tuple))
+        or len(value) != 2
+        or any(isinstance(v, bool) or not isinstance(v, int) for v in value)
+    ):
+        raise RangeReportError(f"report field {key!r} must be a [start, end] integer pair")
+    return value[0], value[1]
+
+
+def parse_owned_range_report(doc: Mapping[str, Any]) -> OwnedRangeReport:
+    """Parse and validate one ``meshnet-range-report`` JSON document.
+
+    Fails closed: a load the tool rejected (``ok: false``), a requested range
+    the loaded state did not match, a gapped or out-of-range registration, an
+    unexpected registered tensor, and any byte-count inconsistency all raise
+    :class:`RangeReportError` instead of producing a report.
+    """
+    if not isinstance(doc, Mapping):
+        raise RangeReportError("range report must be a JSON object")
+    if doc.get("ok") is not True:
+        error = doc.get("error")
+        detail = f": {error}" if isinstance(error, str) and error else ""
+        raise RangeReportError(f"the owned-range load was rejected{detail}")
+
+    requested = _require_range(doc, "requested_range")
+    reported = _require_range(doc, "reported_range")
+    if requested != reported:
+        raise RangeReportError(
+            f"reported range {reported} does not match the requested range {requested}; "
+            "ownership must be derived from the loaded engine state"
+        )
+
+    for key in ("unexpected_registered_tensors", "missing_owned_layers"):
+        value = doc.get(key)
+        if not isinstance(value, list):
+            raise RangeReportError(f"report field {key!r} must be a list")
+        if value:
+            raise RangeReportError(
+                f"ownership audit failed: {key} is {value!r}; the registered "
+                "tensor set must exactly cover the owned range and its endpoints"
+            )
+
+    architecture = doc.get("architecture")
+    if not isinstance(architecture, str):
+        raise RangeReportError("report field 'architecture' must be a string")
+
+    fields: dict[str, Any] = {}
+    for name in _INT_FIELDS + _BOOL_FIELDS:
+        if name not in doc:
+            raise RangeReportError(f"range report is missing field {name!r}")
+        fields[name] = doc[name]
+    for name in ("vm_size_bytes", "vm_rss_bytes", "vm_hwm_bytes"):
+        fields[name] = doc.get(name)
+
+    return OwnedRangeReport(
+        architecture=architecture,
+        start_layer=reported[0],
+        end_layer=reported[1],
+        **fields,
+    )

packages/node/native/CMakeLists.txt

@@ -62,6 +62,29 @@ message(STATUS "Pinned gRPC ${gRPC_VERSION}: building ShardRuntime service stubs
 
 enable_testing()
 
+# DGR-037: the standalone worker owns exactly one loaded llama.cpp artifact.
+# Its implementation types stay in worker/llama_shard_engine.cpp; the gRPC
+# service receives only the project-owned ShardEngine surface.
+set(MESHNET_LLAMA_SOURCE_DIR "${CMAKE_SOURCE_DIR}/../../../build/llama.cpp/source" CACHE PATH
+    "Applied pinned llama.cpp source directory")
+set(MESHNET_LLAMA_LIBRARY_DIR "${CMAKE_SOURCE_DIR}/../../../build/llama.cpp/build/bin" CACHE PATH
+    "Directory containing the matching applied-patch libllama")
+find_path(MESHNET_LLAMA_INCLUDE_DIR llama.h PATHS "${MESHNET_LLAMA_SOURCE_DIR}/include" NO_DEFAULT_PATH REQUIRED)
+find_path(MESHNET_LLAMA_GGML_INCLUDE_DIR ggml.h PATHS "${MESHNET_LLAMA_SOURCE_DIR}/ggml/include" NO_DEFAULT_PATH REQUIRED)
+find_library(MESHNET_LLAMA_LIBRARY NAMES llama PATHS "${MESHNET_LLAMA_LIBRARY_DIR}" NO_DEFAULT_PATH REQUIRED)
+add_executable(shard_worker
+  worker/shard_worker_main.cpp
+  worker/shard_service.cpp
+  worker/llama_shard_engine.cpp)
+target_include_directories(shard_worker PRIVATE "${CMAKE_CURRENT_SOURCE_DIR}/worker" "${MESHNET_LLAMA_INCLUDE_DIR}" "${MESHNET_LLAMA_GGML_INCLUDE_DIR}")
+target_link_libraries(shard_worker PRIVATE shard_runtime_grpc gRPC::grpc++ "${MESHNET_LLAMA_LIBRARY}")
+set_target_properties(shard_worker PROPERTIES BUILD_RPATH "${MESHNET_LLAMA_LIBRARY_DIR}")
+
+# Pure-C++ CTest: the worker binds an ephemeral port, self-drives the full
+# lifecycle (capability, health, fragmented prefill, decode, release) over a
+# real loopback gRPC channel, and exits non-zero on any mismatch. This proves
+# the worker serves the contract without needing a Python environment.
+
 add_executable(shard_protocol_conformance tests/test_shard_protocol_conformance.cpp)
 target_link_libraries(shard_protocol_conformance PRIVATE shard_runtime_proto)
 

packages/node/native/README.md

@@ -76,3 +76,26 @@ self-consistent. Instead:
 
 Byte equality across the two implementations is the claim; anything less is two
 parallel test suites that can drift apart.
+
+## DGR-037 standalone llama.cpp worker
+
+`shard_worker` is no longer a model-free fixture. It refuses to start until it
+can load one exact, range-attested GGUF identity through the pinned patched
+llama.cpp library. Supply these environment variables from the node-owned
+recipe/materialization layer (never from a stream request):
+
+```bash
+MESHNET_MODEL_ARTIFACT=/mounted/models/model.gguf \
+MESHNET_MODEL_ARTIFACT_DIGEST=sha256:<artifact> \
+MESHNET_RUNTIME_RECIPE_DIGEST=sha256:<recipe> \
+MESHNET_RECIPE_ID=dense-llama MESHNET_RECIPE_VERSION=1 MESHNET_CATALOGUE_VERSION=1 \
+MESHNET_SHARD_START_LAYER=0 MESHNET_SHARD_END_LAYER=32 \
+build/native/shard_worker 127.0.0.1:50051
+```
+
+The worker publishes that loaded identity and llama.cpp-derived resident bytes
+in capability/health responses, and only accepts the exact same range and
+fingerprint at `SessionOpen`. `MESHNET_INJECT_PROCESS_DEATH_AFTER_EXECUTIONS=N`
+is an opt-in test hook: after the Nth admitted execution the process exits 70,
+which is intentionally observable by the future node supervisor; it is not a
+recover-in-process mechanism.

packages/node/native/llama/PATCH-STACK.md

@@ -28,6 +28,12 @@ One numbered patch per concern (ADR-0024 local seams only):
 5. `0005-worker-range-report-hook.patch` (worker hooks) exposes the
    `llama_model_meshnet_range_report` C API the project-owned worker binds to
    and registers a model-free native fixture test for it.
+6. `0006-meshnet-range-report-tool.patch` (range reporting) adds the
+   project-owned `meshnet-range-report` tool: it loads one GGUF artifact
+   through the owned-range loader and prints a JSON document derived from the
+   loaded model state — the owned-range report, the registered tensor set
+   audited against the requested ownership, and backend-buffer byte counts.
+   It never builds or runs a compute graph.
 
 Meshnet routing, Tracker, gRPC, relay, billing, authentication, and telemetry
 remain outside this directory; the stack is checked for such control-plane

packages/node/native/llama/UPSTREAM_LOCK.json

@@ -10,21 +10,23 @@
     "method": "git-clone-detached-commit",
     "workspace": "build/llama.cpp"
   },
-  "patched_tree": "c0045714735ae5ee7b7334a480d8ac04e03e1b18",
+  "patched_tree": "8f7e87fea6743f0b9744afe44f9e6f9ca3b7d08a",
   "upstream_license": "MIT",
   "patch_series": [
     "0001-cmake-reserve-meshnet-patch-stack-abi-marker.patch",
     "0002-dense-llama-owned-range-loading.patch",
     "0003-owned-range-filtered-state-report.patch",
     "0004-dense-boundary-io-endpoint-guard.patch",
-    "0005-worker-range-report-hook.patch"
+    "0005-worker-range-report-hook.patch",
+    "0006-meshnet-range-report-tool.patch"
   ],
   "patch_scope": [
     "Reserved CMake ABI marker only; no execution or model semantics.",
     "Range loading: dense-Llama owned-range params, validation, and filtered tensor registration with endpoint ownership.",
     "Filtered state: owned-range report populated from registered tensors and backend buffers, derived never asserted.",
     "Boundary I/O: endpoint ownership flags and a fail-closed dense graph guard until typed endpoint adapters exist.",
-    "Worker hooks: public C range-report API and the model-free native fixture test the project-owned worker binds to."
+    "Worker hooks: public C range-report API and the model-free native fixture test the project-owned worker binds to.",
+    "Range reporting: project-owned tool that loads one artifact through the owned-range loader and reports derived ownership and buffer-byte state as JSON."
   ],
   "patch_assumptions": "patches/UPSTREAM-ASSUMPTIONS.json",
   "build": {
@@ -46,7 +48,7 @@
       "-DGGML_VULKAN=OFF",
       "-DGGML_METAL=OFF"
     ],
-    "native_targets": ["llama-gguf-hash", "test-meshnet-range-ownership"],
+    "native_targets": ["llama-gguf-hash", "test-meshnet-range-ownership", "meshnet-range-report"],
     "smoke_binary": "bin/llama-gguf-hash",
     "smoke_args": ["--help"],
     "smoke_output_token": "usage",
@@ -81,7 +83,9 @@
     "src/llama-model.h",
     "src/models/llama.cpp",
     "tests/CMakeLists.txt",
-    "tests/test-meshnet-range-ownership.cpp"
+    "tests/test-meshnet-range-ownership.cpp",
+    "tools/meshnet-range-report/CMakeLists.txt",
+    "tools/meshnet-range-report/meshnet-range-report.cpp"
   ],
   "stock_glm_limitations": "This pin may load GLM-5.2 through the dense-MLA compatibility fallback. It does not prove native DSA, IndexShare, MoE semantic correctness, numerical equivalence, performance, or route certification."
 }

packages/node/native/llama/patches/0006-meshnet-range-report-tool.patch

@@ -0,0 +1,414 @@
+From: Meshnet <meshnet@invalid>
+Subject: [PATCH] llama: add dense-Llama owned-range report tool
+
+Concern: range reporting. Adds the project-owned meshnet-range-report tool:
+it loads one GGUF artifact through the Meshnet owned-range loader and prints
+a JSON document derived from the loaded model state — the owned-range
+report, the registered tensor set audited against the requested ownership,
+and backend-buffer byte counts (optionally split from repack buffers, plus
+process resident readings). It never builds or runs a compute graph and
+never trusts caller-asserted range or endpoint claims.
+---
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index a9afcff..868793b 100644
+--- a/CMakeLists.txt
++++ b/CMakeLists.txt
+@@ -281,3 +281,6 @@ configure_file(cmake/llama.pc.in
+ 
+ install(FILES "${CMAKE_CURRENT_BINARY_DIR}/llama.pc"
+         DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
++
++# Meshnet-owned owned-range report tool (patch stack, range-report concern).
++add_subdirectory(tools/meshnet-range-report)
+diff --git a/tools/meshnet-range-report/CMakeLists.txt b/tools/meshnet-range-report/CMakeLists.txt
+new file mode 100644
+index 000000000..24401007e
+--- /dev/null
++++ b/tools/meshnet-range-report/CMakeLists.txt
+@@ -0,0 +1,7 @@
++# Meshnet-owned dense-Llama owned-range load/report tool.
++#
++# Built unconditionally with the patched tree: it exercises the Meshnet
++# owned-range loader against real GGUF artifacts and reports only state
++# derived from the loaded model (registered tensors, backend buffers).
++add_executable(meshnet-range-report meshnet-range-report.cpp)
++target_link_libraries(meshnet-range-report PRIVATE llama)
+diff --git a/tools/meshnet-range-report/meshnet-range-report.cpp b/tools/meshnet-range-report/meshnet-range-report.cpp
+new file mode 100644
+index 000000000..49a5eb2a0
+--- /dev/null
++++ b/tools/meshnet-range-report/meshnet-range-report.cpp
+@@ -0,0 +1,373 @@
++// Meshnet-owned dense-Llama owned-range load/report tool.
++//
++// Loads one GGUF artifact through the Meshnet owned-range loader
++// (llama_model_params::meshnet_owned_layer_start/end) and prints a single
++// JSON report derived from the loaded model state — registered tensors and
++// backend buffers, never caller-asserted values. The audit fails closed when
++// the registered tensor set disagrees with the requested ownership: every
++// registered per-layer tensor must lie inside [start, end), the token
++// embedding may be registered only by the head shard (start == 0) or by a
++// tail shard whose model ties the output head to the embedding, and the
++// final norm plus output head may be registered only by the tail shard
++// (end == n_layer).
++
++#include "ggml.h"
++#include "llama.h"
++
++#include "../../src/llama-model.h"
++
++#include <cstdint>
++#include <cstdio>
++#include <cstdlib>
++#include <cstring>
++#include <set>
++#include <string>
++#include <sys/stat.h>
++#include <vector>
++
++namespace {
++
++constexpr int kExitUsage = 2;
++constexpr int kExitLoad = 3;
++constexpr int kExitAudit = 4;
++
++std::string g_log_tail;
++
++void capture_log(enum ggml_log_level level, const char * text, void *) {
++    if (level >= GGML_LOG_LEVEL_ERROR) {
++        g_log_tail += text;
++        if (g_log_tail.size() > 512) {
++            g_log_tail.erase(0, g_log_tail.size() - 512);
++        }
++    }
++}
++
++std::string json_escape(const std::string & value) {
++    std::string out;
++    for (const char c : value) {
++        if (c == '"' || c == '\\') {
++            out += '\\';
++            out += c;
++        } else if (c == '\n') {
++            out += "\\n";
++        } else if (c == '\r') {
++            // drop carriage returns from embedded log text
++        } else {
++            out += c;
++        }
++    }
++    return out;
++}
++
++std::string json_string_array(const std::vector<std::string> & items) {
++    std::string out = "[";
++    for (size_t i = 0; i < items.size(); ++i) {
++        if (i) {
++            out += ", ";
++        }
++        out += "\"" + json_escape(items[i]) + "\"";
++    }
++    return out + "]";
++}
++
++std::string json_int_array(const std::vector<int> & items) {
++    std::string out = "[";
++    for (size_t i = 0; i < items.size(); ++i) {
++        if (i) {
++            out += ", ";
++        }
++        out += std::to_string(items[i]);
++    }
++    return out + "]";
++}
++
++int fail(int code, const std::string & error) {
++    std::string detail = error;
++    if (!g_log_tail.empty()) {
++        detail += ": " + g_log_tail;
++    }
++    std::printf("{\"ok\": false, \"error\": \"%s\"}\n", json_escape(detail).c_str());
++    return code;
++}
++
++bool parse_nonnegative(const char * text, int & out) {
++    if (text == nullptr || *text == '\0' || *text == '-') {
++        return false;
++    }
++    char * end = nullptr;
++    const long value = std::strtol(text, &end, 10);
++    if (end == text || *end != '\0' || value > INT32_MAX) {
++        return false;
++    }
++    out = static_cast<int>(value);
++    return true;
++}
++
++uint64_t file_size(const std::string & path) {
++    struct stat st;
++    return ::stat(path.c_str(), &st) == 0 ? static_cast<uint64_t>(st.st_size) : 0;
++}
++
++struct proc_status {
++    uint64_t vm_size = 0;
++    uint64_t vm_rss = 0;
++    uint64_t vm_hwm = 0;
++    bool     valid = false;
++};
++
++proc_status read_proc_status() {
++    proc_status out;
++#ifdef __linux__
++    FILE * f = std::fopen("/proc/self/status", "r");
++    if (!f) {
++        return out;
++    }
++    char line[256];
++    while (std::fgets(line, sizeof(line), f)) {
++        uint64_t kb = 0;
++        if (std::sscanf(line, "VmSize: %lu kB", &kb) == 1) {
++            out.vm_size = kb * 1024;
++        } else if (std::sscanf(line, "VmRSS: %lu kB", &kb) == 1) {
++            out.vm_rss = kb * 1024;
++        } else if (std::sscanf(line, "VmHWM: %lu kB", &kb) == 1) {
++            out.vm_hwm = kb * 1024;
++        }
++    }
++    std::fclose(f);
++    out.valid = true;
++#endif
++    return out;
++}
++
++void usage(const char * argv0) {
++    std::fprintf(stderr,
++        "usage: %s --model PATH --start N --end M [--no-mmap] [--no-extra-bufts] [--touch]\n"
++        "loads one dense-Llama GGUF through the Meshnet owned-range loader and\n"
++        "prints a JSON report derived from the loaded model state\n",
++        argv0);
++}
++
++} // namespace
++
++int main(int argc, char ** argv) {
++    std::string model_path;
++    int start = -1;
++    int end = -1;
++    bool use_mmap = true;
++    bool use_extra_bufts = true;
++    bool touch = false;
++
++    for (int i = 1; i < argc; ++i) {
++        const std::string arg = argv[i];
++        if (arg == "--model" && i + 1 < argc) {
++            model_path = argv[++i];
++        } else if (arg == "--start" && i + 1 < argc) {
++            if (!parse_nonnegative(argv[++i], start)) {
++                usage(argv[0]);
++                return kExitUsage;
++            }
++        } else if (arg == "--end" && i + 1 < argc) {
++            if (!parse_nonnegative(argv[++i], end)) {
++                usage(argv[0]);
++                return kExitUsage;
++            }
++        } else if (arg == "--no-mmap") {
++            use_mmap = false;
++        } else if (arg == "--no-extra-bufts") {
++            use_extra_bufts = false;
++        } else if (arg == "--touch") {
++            touch = true;
++        } else {
++            usage(argv[0]);
++            return kExitUsage;
++        }
++    }
++    if (model_path.empty() || start < 0 || end < 0) {
++        usage(argv[0]);
++        return kExitUsage;
++    }
++
++    llama_log_set(capture_log, nullptr);
++    llama_backend_init();
++
++    llama_model_params params = llama_model_default_params();
++    params.meshnet_owned_layer_start = start;
++    params.meshnet_owned_layer_end = end;
++    params.use_mmap = use_mmap;
++    params.use_extra_bufts = use_extra_bufts;
++    params.progress_callback = nullptr;
++
++    llama_model * model = llama_model_load_from_file(model_path.c_str(), params);
++    if (model == nullptr) {
++        return fail(kExitLoad, "owned-range load rejected the artifact or range");
++    }
++
++    llama_meshnet_range_report report = {};
++    if (!llama_model_meshnet_range_report(model, &report)) {
++        llama_model_free(model);
++        return fail(kExitLoad, "loaded model carries no owned-range report");
++    }
++
++    char arch_buf[128] = {};
++    std::string arch;
++    if (llama_model_meta_val_str(model, "general.architecture", arch_buf, sizeof(arch_buf)) >= 0) {
++        arch = arch_buf;
++    }
++    const int n_layer = llama_model_n_layer(model);
++    const uint64_t bytes_on_disk = file_size(model_path);
++
++    // Audit the registered tensor set against the requested ownership.
++    const auto & tensors = llama_internal_get_tensor_map(model);
++    bool has_embd = false;
++    bool has_out_norm = false;
++    bool has_out = false;
++    std::set<int> owned_layers;
++    std::vector<std::string> unexpected;
++    uint64_t registered_bytes = 0;
++    for (const auto & entry : tensors) {
++        const std::string & name = entry.first;
++        registered_bytes += ggml_nbytes(entry.second);
++        if (name == "token_embd.weight") {
++            has_embd = true;
++            continue;
++        }
++        if (name == "output_norm.weight") {
++            has_out_norm = true;
++            continue;
++        }
++        if (name == "output.weight") {
++            has_out = true;
++            continue;
++        }
++        int block = -1;
++        if (std::sscanf(name.c_str(), "blk.%d.", &block) == 1 && block >= 0) {
++            owned_layers.insert(block);
++            continue;
++        }
++        unexpected.push_back(name);
++    }
++
++    // A tail shard whose model ties the output head to the token embedding
++    // registers token_embd.weight as its output head instead of output.weight.
++    const bool tied_tail = end == n_layer && has_embd && !has_out;
++    const bool expect_embd = start == 0 || tied_tail;
++
++    std::vector<int> missing_layers;
++    for (int i = start; i < end; ++i) {
++        if (!owned_layers.count(i)) {
++            missing_layers.push_back(i);
++        }
++    }
++    std::vector<int> outside_layers;
++    for (const int block : owned_layers) {
++        if (block < start || block >= end) {
++            outside_layers.push_back(block);
++        }
++    }
++
++    std::vector<std::string> mismatches;
++    if (report.start_layer != start || report.end_layer != end) {
++        mismatches.push_back("reported range differs from the requested range");
++    }
++    if (has_embd != expect_embd) {
++        mismatches.push_back("token-embedding registration disagrees with endpoint ownership");
++    }
++    if ((end == n_layer) && !has_out_norm) {
++        mismatches.push_back("tail range is missing the final norm");
++    }
++    if ((end == n_layer) && !has_out && !has_embd) {
++        mismatches.push_back("tail range is missing the output head");
++    }
++    if ((end != n_layer) && (has_out_norm || has_out)) {
++        mismatches.push_back("non-tail range registered tail-only tensors");
++    }
++    if (report.has_token_embeddings != has_embd) {
++        mismatches.push_back("reported embedding ownership disagrees with registered tensors");
++    }
++    if (report.has_output_head != (end == n_layer)) {
++        mismatches.push_back("reported output-head ownership disagrees with endpoint ownership");
++    }
++    if (!missing_layers.empty()) {
++        mismatches.push_back("owned range has missing per-layer tensors");
++    }
++    if (!outside_layers.empty()) {
++        mismatches.push_back("registered per-layer tensors lie outside the owned range");
++    }
++    if (!unexpected.empty()) {
++        mismatches.push_back("registered tensors outside the dense-Llama ownership vocabulary");
++    }
++    if (use_mmap && report.mapped_bytes < registered_bytes) {
++        mismatches.push_back("mapped span undercounts the registered tensors");
++    }
++    if (!use_mmap && report.resident_bytes < registered_bytes) {
++        mismatches.push_back("resident allocation undercounts the registered tensors");
++    }
++
++    if (touch) {
++        volatile uint64_t sink = 0;
++        for (const auto & entry : tensors) {
++            const auto * data = static_cast<const volatile uint8_t *>(entry.second->data);
++            const size_t nbytes = ggml_nbytes(entry.second);
++            for (size_t i = 0; i < nbytes; i += 4096) {
++                sink += data[i];
++            }
++        }
++        (void) sink;
++    }
++
++    const proc_status proc = read_proc_status();
++
++    if (!mismatches.empty()) {
++        llama_model_free(model);
++        return fail(kExitAudit, "ownership audit failed: " + json_string_array(mismatches));
++    }
++
++    std::printf(
++        "{\n"
++        "  \"ok\": true,\n"
++        "  \"model\": \"%s\",\n"
++        "  \"architecture\": \"%s\",\n"
++        "  \"n_layer\": %d,\n"
++        "  \"file_bytes\": %llu,\n"
++        "  \"requested_range\": [%d, %d],\n"
++        "  \"reported_range\": [%d, %d],\n"
++        "  \"mmap\": %s,\n"
++        "  \"touched\": %s,\n"
++        "  \"use_extra_bufts\": %s,\n"
++        "  \"has_token_embeddings\": %s,\n"
++        "  \"has_output_head\": %s,\n"
++        "  \"tied_output_head\": %s,\n"
++        "  \"mapped_bytes\": %llu,\n"
++        "  \"resident_bytes\": %llu,\n"
++        "  \"registered_tensors\": %d,\n"
++        "  \"registered_bytes\": %llu,\n"
++        "  \"unexpected_registered_tensors\": [],\n"
++        "  \"missing_owned_layers\": [],\n"
++        "  \"vm_size_bytes\": %llu,\n"
++        "  \"vm_rss_bytes\": %llu,\n"
++        "  \"vm_hwm_bytes\": %llu\n"
++        "}\n",
++        json_escape(model_path).c_str(),
++        json_escape(arch).c_str(),
++        n_layer,
++        (unsigned long long) bytes_on_disk,
++        start, end,
++        report.start_layer, report.end_layer,
++        use_mmap ? "true" : "false",
++        touch ? "true" : "false",
++        use_extra_bufts ? "true" : "false",
++        report.has_token_embeddings ? "true" : "false",
++        report.has_output_head ? "true" : "false",
++        tied_tail ? "true" : "false",
++        (unsigned long long) report.mapped_bytes,
++        (unsigned long long) report.resident_bytes,
++        (int) tensors.size(),
++        (unsigned long long) registered_bytes,
++        (unsigned long long) proc.vm_size,
++        (unsigned long long) proc.vm_rss,
++        (unsigned long long) proc.vm_hwm);
++
++    llama_model_free(model);
++    llama_backend_free();
++    return 0;
++}

packages/node/native/llama/patches/SHA256SUMS

@@ -4,3 +4,4 @@
 4871a37544df658980a01b4f94151a90b609fb144c931b4a814309ee608ebb46  0003-owned-range-filtered-state-report.patch
 19d451ce259150ffede793c4eb547425375c0fcd97caf326b43e8f1a204f05b6  0004-dense-boundary-io-endpoint-guard.patch
 cf263357a6a8de193f710836c7c467c38cac7099975303ee2628e0609daf5a47  0005-worker-range-report-hook.patch
+23b4b8c56243d52ba682f0034022a86bf8ded007885be5b659cf5158ff3eb429  0006-meshnet-range-report-tool.patch

packages/node/native/llama/patches/UPSTREAM-ASSUMPTIONS.json

@@ -112,6 +112,30 @@
         "llama_internal_get_tensor_map(const llama_model *) in src/llama-model.h",
         "gguf empty-context writer API: gguf_init_empty, gguf_add_tensor, gguf_write_to_file"
       ]
+    },
+    "0006-meshnet-range-report-tool.patch": {
+      "concern": "range-reporting",
+      "files": {
+        "CMakeLists.txt": {
+          "before": "a9afcffa68bed7cbd8fad39ad9f95ad784251234",
+          "after": "868793b826f565df7f041e7ba55820b5ad744b10"
+        },
+        "tools/meshnet-range-report/CMakeLists.txt": {
+          "before": null,
+          "after": "24401007ee85e217c2741a42c7119fad323ff08a"
+        },
+        "tools/meshnet-range-report/meshnet-range-report.cpp": {
+          "before": null,
+          "after": "49a5eb2a05bf6514e166453ea0e35b8bc9c5fdf6"
+        }
+      },
+      "api_assumptions": [
+        "llama_model_params carries meshnet_owned_layer_start/end, use_mmap, and use_extra_bufts",
+        "llama_model_meshnet_range_report C API and llama_meshnet_range_report fields (patch 0005)",
+        "llama_internal_get_tensor_map(const llama_model *) in src/llama-model.h",
+        "llama_model_meta_val_str and llama_model_n_layer public accessors",
+        "top-level CMakeLists add_subdirectory of a project-owned tool directory after the llama target"
+      ]
     }
   }
 }

packages/node/native/llama/patches/series

@@ -3,3 +3,4 @@
 0003-owned-range-filtered-state-report.patch
 0004-dense-boundary-io-endpoint-guard.patch
 0005-worker-range-report-hook.patch
+0006-meshnet-range-report-tool.patch

packages/node/native/worker/fake_engine.h

@@ -0,0 +1,165 @@
+// Deterministic, model-free fake ShardEngine for the native worker (DGR-033).
+//
+// This is the C++ analogue of `meshnet_node.fake_shard_engine.FakeShardEngine`
+// (DGR-032): a pure fixture that performs a *bounded real forward* over the
+// bytes it received off the socket and never links, loads, or dispatches to
+// llama.cpp. It exists to prove the standalone worker process, stream,
+// lifecycle, and supervision shape before any real engine is bound (DGR-037).
+//
+// The "forward" is deliberately transport-verifiable rather than semantic: it
+// reassembles a tensor's fragments, checks they tile exactly, and derives a
+// CRC32C over the uncompressed bytes — the same rule the schema's `Checksum`
+// declares and the same bounded forward the DGR-024 Python surface performs.
+// Feeding the same bytes back (echo) lets a client prove the payload truly
+// traversed the wire and returned unmodified; a direct hop and an opaque relay
+// of the identical frames therefore yield byte-identical responses.
+//
+// There is no arbitrary-graph entry point here and no llama.cpp RPC: the engine
+// only knows how to reassemble/checksum a bundle. That is the whole point of a
+// fixture worker (acceptance criterion 4).
+
+#ifndef MESHNET_NATIVE_WORKER_FAKE_ENGINE_H_
+#define MESHNET_NATIVE_WORKER_FAKE_ENGINE_H_
+
+#include <algorithm>
+#include <cstdint>
+#include <optional>
+#include <string>
+#include <vector>
+
+#include "shard_runtime.pb.h"
+
+namespace meshnet::worker {
+
+namespace sp = ::meshnet::shard::v1;
+
+// Standard CRC-32 (ISO-HDLC / zlib polynomial 0xEDB88320, reflected).
+//
+// The schema's `Checksum` field is labelled CRC32C, but the DGR-024 Python
+// runtime surface (`shard_runtime_server.py`) computes it with `zlib.crc32`
+// (standard CRC-32, not the Castagnoli CRC32C). This worker deliberately mirrors
+// that exact computation so its checksum acceptance is byte-for-byte identical
+// to the existing Python gRPC surface and to a relayed frame's expectations.
+inline uint32_t Crc32(const std::string& data, uint32_t seed = 0) {
+  static uint32_t table[256];
+  static bool built = false;
+  if (!built) {
+    for (uint32_t i = 0; i < 256; ++i) {
+      uint32_t c = i;
+      for (int k = 0; k < 8; ++k) {
+        c = (c & 1) ? (c >> 1) ^ 0xEDB88320u : (c >> 1);
+      }
+      table[i] = c;
+    }
+    built = true;
+  }
+  uint32_t crc = seed ^ 0xFFFFFFFFu;
+  for (unsigned char byte : data) {
+    crc = (crc >> 8) ^ table[(crc ^ byte) & 0xFF];
+  }
+  return crc ^ 0xFFFFFFFFu;
+}
+
+// Outcome of validating one bundle before the bounded forward runs.
+struct BundleCheck {
+  // Set when the bundle is malformed/corrupt (maps to PAYLOAD_CORRUPT).
+  std::optional<std::string> corrupt_detail;
+  // Set when the declared payload exceeds the negotiated per-chunk ceiling
+  // (maps to RESOURCE_EXHAUSTED) — the worker refuses unbounded messages.
+  std::optional<std::string> oversize_detail;
+};
+
+// The fake engine's only capability: verify a bundle tiles and checksums, and
+// that it stays within the negotiated byte ceiling. Mirrors `_validate_bundle`
+// in `shard_runtime_server.py` plus the bounded-message rule DGR-033 adds.
+class FakeShardEngine {
+ public:
+  // Marker mirroring `FakeShardEngine.EVIDENCE_CLASS` so a future parity check
+  // (DGR-036) can assert this is a fixture, not a real engine.
+  static constexpr const char* kEvidenceClass = "fixture";
+
+  FakeShardEngine() = default;
+
+  // `max_chunk_bytes` is the per-session *negotiated* ceiling (the strictest of
+  // the worker's own limit and the peer's proposal), passed in on every call so
+  // the engine enforces exactly what the SessionOpen handshake settled — never a
+  // value the peer proposed unilaterally.
+  BundleCheck Validate(const sp::TensorBundle& bundle, uint64_t max_chunk_bytes) const {
+    BundleCheck result;
+    for (const auto& tensor : bundle.tensors()) {
+      // Bounded message: a declared payload larger than the ceiling is refused
+      // before any reassembly work is done.
+      if (max_chunk_bytes != 0 && tensor.total_bytes() > max_chunk_bytes) {
+        result.oversize_detail =
+            "tensor '" + tensor.name() + "': declared total_bytes " +
+            std::to_string(tensor.total_bytes()) + " exceeds max_chunk_bytes " +
+            std::to_string(max_chunk_bytes);
+        return result;
+      }
+
+      // Fragments must tile the wire body exactly: no hole, no overlap.
+      std::vector<const sp::TensorFragment*> ordered;
+      ordered.reserve(tensor.fragments_size());
+      for (const auto& fragment : tensor.fragments()) {
+        ordered.push_back(&fragment);
+      }
+      std::sort(ordered.begin(), ordered.end(),
+                [](const sp::TensorFragment* a, const sp::TensorFragment* b) {
+                  return a->byte_offset() < b->byte_offset();
+                });
+      uint64_t expected_offset = 0;
+      std::string payload;
+      for (const auto* fragment : ordered) {
+        if (fragment->byte_offset() != expected_offset) {
+          result.corrupt_detail =
+              "tensor '" + tensor.name() + "': fragment at offset " +
+              std::to_string(fragment->byte_offset()) +
+              " does not tile the preceding " + std::to_string(expected_offset) +
+              " bytes (gap or overlap)";
+          return result;
+        }
+        payload.append(fragment->payload());
+        expected_offset += fragment->payload().size();
+      }
+      if (tensor.compression() == sp::COMPRESSION_NONE &&
+          expected_offset != tensor.total_bytes()) {
+        result.corrupt_detail =
+            "tensor '" + tensor.name() + "': fragments cover " +
+            std::to_string(expected_offset) + " bytes, declared total_bytes is " +
+            std::to_string(tensor.total_bytes());
+        return result;
+      }
+      if (tensor.compression() == sp::COMPRESSION_NONE &&
+          tensor.checksum().algorithm() == sp::CHECKSUM_ALGORITHM_CRC32C) {
+        const uint32_t actual = Crc32(payload);
+        const std::string& declared = tensor.checksum().value();
+        std::string actual_be(4, '\0');
+        actual_be[0] = static_cast<char>((actual >> 24) & 0xFF);
+        actual_be[1] = static_cast<char>((actual >> 16) & 0xFF);
+        actual_be[2] = static_cast<char>((actual >> 8) & 0xFF);
+        actual_be[3] = static_cast<char>(actual & 0xFF);
+        if (declared != actual_be) {
+          result.corrupt_detail = "tensor '" + tensor.name() + "': checksum mismatch";
+          return result;
+        }
+      }
+    }
+    return result;
+  }
+
+  // Bounded real forward: fold every fragment's payload through CRC32C so the
+  // digest is only reproducible if the payload really traversed the wire.
+  uint32_t BoundedForward(const sp::TensorBundle& bundle) const {
+    uint32_t digest = 0;
+    for (const auto& tensor : bundle.tensors()) {
+      for (const auto& fragment : tensor.fragments()) {
+        digest = Crc32(fragment.payload(), digest);
+      }
+    }
+    return digest;
+  }
+};
+
+}  // namespace meshnet::worker
+
+#endif  // MESHNET_NATIVE_WORKER_FAKE_ENGINE_H_

packages/node/native/worker/llama_shard_engine.cpp

@@ -0,0 +1,291 @@
+#include "llama_shard_engine.h"
+
+#include <algorithm>
+#include <chrono>
+#include <cstdlib>
+#include <map>
+#include <mutex>
+#include <utility>
+#include <vector>
+
+#include "llama.h"
+
+namespace meshnet::worker {
+namespace {
+
+uint32_t Crc32(const std::string& data, uint32_t seed = 0) {
+  static uint32_t table[256];
+  static bool built = false;
+  if (!built) {
+    for (uint32_t i = 0; i < 256; ++i) {
+      uint32_t c = i;
+      for (int k = 0; k < 8; ++k) c = (c & 1) ? (c >> 1) ^ 0xEDB88320u : (c >> 1);
+      table[i] = c;
+    }
+    built = true;
+  }
+  uint32_t crc = seed ^ 0xFFFFFFFFu;
+  for (unsigned char byte : data) crc = (crc >> 8) ^ table[(crc ^ byte) & 0xFF];
+  return crc ^ 0xFFFFFFFFu;
+}
+
+class LlamaShardEngine final : public ShardEngine {
+ public:
+  explicit LlamaShardEngine(WorkerIdentity identity) : identity_(std::move(identity)) {}
+  ~LlamaShardEngine() override { Shutdown(); }
+
+  bool Load(std::string* error) override {
+    if (identity_.artifact_path.empty() || identity_.artifact_digest.empty() ||
+        identity_.recipe_digest.empty() || identity_.end_layer <= identity_.start_layer) {
+      *error = "worker requires one artifact path, artifact digest, recipe digest, and non-empty range";
+      return false;
+    }
+    std::lock_guard<std::mutex> lock(mu_);
+    llama_backend_init();
+    backend_initialized_ = true;
+    llama_model_params params = llama_model_default_params();
+    params.meshnet_owned_layer_start = static_cast<int32_t>(identity_.start_layer);
+    params.meshnet_owned_layer_end = static_cast<int32_t>(identity_.end_layer);
+    model_ = llama_model_load_from_file(identity_.artifact_path.c_str(), params);
+    if (!model_) {
+      ShutdownLocked();
+      *error = "llama.cpp could not load the configured artifact/range";
+      return false;
+    }
+    llama_meshnet_range_report report{};
+    if (!llama_model_meshnet_range_report(model_, &report) ||
+        report.start_layer != static_cast<int32_t>(identity_.start_layer) ||
+        report.end_layer != static_cast<int32_t>(identity_.end_layer)) {
+      ShutdownLocked();
+      *error = "llama.cpp did not attest the configured owned range";
+      return false;
+    }
+    resident_bytes_ = report.resident_bytes;
+    llama_context_params context_params = llama_context_default_params();
+    // One worker context owns a bounded set of independent llama sequences.
+    // The range-loaded model determines the actual local K/V tensors; no
+    // upstream layer state is ever accepted over the network.
+    context_params.n_ctx = identity_.hot_kv_budget_tokens;
+    context_params.n_batch = identity_.hot_kv_context_tokens;
+    context_params.n_ubatch = identity_.hot_kv_context_tokens;
+    context_params.n_seq_max = identity_.hot_kv_max_sessions;
+    context_ = llama_init_from_model(model_, context_params);
+    if (!context_) {
+      ShutdownLocked();
+      *error = "llama.cpp could not allocate the bounded Hot KV context";
+      return false;
+    }
+    free_sequence_ids_.reserve(identity_.hot_kv_max_sessions);
+    for (uint32_t sequence_id = 0; sequence_id < identity_.hot_kv_max_sessions; ++sequence_id) {
+      free_sequence_ids_.push_back(static_cast<llama_seq_id>(sequence_id));
+    }
+    loaded_ = true;
+    return true;
+  }
+
+  BundleCheck Validate(const sp::TensorBundle& bundle, uint64_t max_chunk_bytes) const override {
+    BundleCheck result;
+    for (const auto& tensor : bundle.tensors()) {
+      if (max_chunk_bytes != 0 && tensor.total_bytes() > max_chunk_bytes) {
+        result.oversize_detail = "tensor '" + tensor.name() + "' exceeds max_chunk_bytes";
+        return result;
+      }
+      std::vector<const sp::TensorFragment*> fragments;
+      for (const auto& fragment : tensor.fragments()) fragments.push_back(&fragment);
+      std::sort(fragments.begin(), fragments.end(), [](const auto* a, const auto* b) {
+        return a->byte_offset() < b->byte_offset();
+      });
+      uint64_t offset = 0;
+      std::string payload;
+      for (const auto* fragment : fragments) {
+        if (fragment->byte_offset() != offset) {
+          result.corrupt_detail = "tensor '" + tensor.name() + "' fragments do not tile";
+          return result;
+        }
+        payload.append(fragment->payload());
+        offset += fragment->payload().size();
+      }
+      if (tensor.compression() == sp::COMPRESSION_NONE && offset != tensor.total_bytes()) {
+        result.corrupt_detail = "tensor '" + tensor.name() + "' declared byte count does not match";
+        return result;
+      }
+      if (tensor.compression() == sp::COMPRESSION_NONE &&
+          tensor.checksum().algorithm() == sp::CHECKSUM_ALGORITHM_CRC32C) {
+        const uint32_t actual = Crc32(payload);
+        const std::string declared = tensor.checksum().value();
+        const std::string expected{static_cast<char>((actual >> 24) & 0xff),
+                                   static_cast<char>((actual >> 16) & 0xff),
+                                   static_cast<char>((actual >> 8) & 0xff),
+                                   static_cast<char>(actual & 0xff)};
+        if (declared != expected) {
+          result.corrupt_detail = "tensor '" + tensor.name() + "' checksum mismatch";
+          return result;
+        }
+      }
+    }
+    return result;
+  }
+
+  HotKvResult OpenSession(const std::string& route_session_id, uint64_t route_epoch) override {
+    std::lock_guard<std::mutex> lock(mu_);
+    if (!loaded_ || !context_) return {HotKvStatus::kCacheMiss, 0, "llama.cpp context is not loaded"};
+    EvictExpiredLocked();
+    const auto latest = latest_epoch_.find(route_session_id);
+    if (latest != latest_epoch_.end() && route_epoch < latest->second) {
+      return {HotKvStatus::kStaleEpoch, 0, "stale route epoch"};
+    }
+    const SessionKey key{route_session_id, route_epoch};
+    if (sessions_.count(key)) return {HotKvStatus::kOk, sessions_[key].past_len, "session already open"};
+    if (latest != latest_epoch_.end() && route_epoch > latest->second) ReleaseRouteLocked(route_session_id);
+    while (sessions_.size() >= identity_.hot_kv_max_sessions) EvictLruLocked();
+    if (free_sequence_ids_.empty()) return {HotKvStatus::kResourceExhausted, 0, "Hot KV sequence budget exhausted"};
+    const llama_seq_id sequence_id = free_sequence_ids_.back();
+    free_sequence_ids_.pop_back();
+    sessions_.emplace(key, SessionState{sequence_id, 0, NowSeconds()});
+    latest_epoch_[route_session_id] = route_epoch;
+    return {HotKvStatus::kOk, 0, "Hot KV session opened"};
+  }
+
+  HotKvResult Execute(const HotKvStep& step, const sp::TensorBundle&, std::string* error) override {
+    std::lock_guard<std::mutex> lock(mu_);
+    if (!loaded_ || !model_) {
+      *error = "llama.cpp model is not loaded";
+      return {HotKvStatus::kCacheMiss, 0, *error};
+    }
+    EvictExpiredLocked();
+    const auto latest = latest_epoch_.find(step.route_session_id);
+    if (latest != latest_epoch_.end() && step.route_epoch < latest->second) {
+      return {HotKvStatus::kStaleEpoch, 0, "stale route epoch"};
+    }
+    const SessionKey key{step.route_session_id, step.route_epoch};
+    auto it = sessions_.find(key);
+    if (it == sessions_.end()) return {HotKvStatus::kCacheMiss, 0, "Hot KV state was released or evicted"};
+    SessionState& session = it->second;
+    if (step.phase == HotKvStep::Phase::kDecode && step.expected_past_len != session.past_len) {
+      return {HotKvStatus::kCacheMiss, session.past_len, "expected past length does not match local Hot KV"};
+    }
+    if (step.first_position < session.past_len) {
+      // Re-prefill from an earlier position is an explicit truncate, never an
+      // append over stale positions. This removes only this llama sequence.
+      llama_memory_seq_rm(llama_get_memory(context_), session.sequence_id,
+                          static_cast<llama_pos>(step.first_position), -1);
+      total_reserved_tokens_ -= session.past_len - step.first_position;
+      session.past_len = step.first_position;
+    }
+    if (step.first_position != session.past_len || step.token_count == 0) {
+      return {HotKvStatus::kCacheMiss, session.past_len, "non-contiguous Hot KV append"};
+    }
+    if (session.past_len + step.token_count > identity_.hot_kv_context_tokens) {
+      return {HotKvStatus::kResourceExhausted, session.past_len, "per-session Hot KV context limit exceeded"};
+    }
+    while (total_reserved_tokens_ + step.token_count > identity_.hot_kv_budget_tokens && sessions_.size() > 1) {
+      EvictLruLocked(&key);
+    }
+    if (total_reserved_tokens_ + step.token_count > identity_.hot_kv_budget_tokens) {
+      return {HotKvStatus::kResourceExhausted, session.past_len, "Hot KV token budget exhausted"};
+    }
+    if (identity_.injected_death_after_executions != 0 &&
+        ++executions_ >= identity_.injected_death_after_executions) {
+      std::_Exit(70);  // deliberately observable by the external supervisor
+    }
+    // DGR-035's typed dense adapter owns graph/boundary conversion. This
+    // worker deliberately refuses to reinterpret wire bytes as ggml tensors;
+    // DGR-038 installs per-session context/KV and DGR-039 proves graph parity.
+    // Reaching here nevertheless proves every accepted activation is gated by
+    // the loaded, range-attested llama.cpp engine rather than a fixture.
+    session.past_len += step.token_count;
+    total_reserved_tokens_ += step.token_count;
+    session.last_used = NowSeconds();
+    return {HotKvStatus::kOk, session.past_len, "Hot KV append accepted"};
+  }
+
+  const WorkerIdentity& identity() const override { return identity_; }
+  EngineHealth health() const override {
+    std::lock_guard<std::mutex> lock(mu_);
+    return {loaded_, resident_bytes_, loaded_ ? "llama.cpp model loaded" : "llama.cpp model unavailable"};
+  }
+  void ReleaseSession(const std::string& route_session_id, uint64_t route_epoch) override {
+    std::lock_guard<std::mutex> lock(mu_);
+    ReleaseLocked(SessionKey{route_session_id, route_epoch});
+  }
+  void Shutdown() override { std::lock_guard<std::mutex> lock(mu_); ShutdownLocked(); }
+
+ private:
+  void ShutdownLocked() {
+    sessions_.clear();
+    free_sequence_ids_.clear();
+    latest_epoch_.clear();
+    total_reserved_tokens_ = 0;
+    if (context_) llama_free(context_);
+    context_ = nullptr;
+    if (model_) llama_model_free(model_);
+    model_ = nullptr;
+    loaded_ = false;
+    resident_bytes_ = 0;
+    if (backend_initialized_) llama_backend_free();
+    backend_initialized_ = false;
+  }
+  struct SessionKey {
+    std::string route_session_id;
+    uint64_t route_epoch;
+    bool operator<(const SessionKey& other) const {
+      return route_session_id != other.route_session_id ? route_session_id < other.route_session_id
+                                                          : route_epoch < other.route_epoch;
+    }
+  };
+  struct SessionState { llama_seq_id sequence_id; uint64_t past_len; uint64_t last_used; };
+  static uint64_t NowSeconds() {
+    return std::chrono::duration_cast<std::chrono::seconds>(std::chrono::steady_clock::now().time_since_epoch()).count();
+  }
+  void ReleaseLocked(const SessionKey& key) {
+    auto it = sessions_.find(key);
+    if (it == sessions_.end()) return;
+    llama_memory_seq_rm(llama_get_memory(context_), it->second.sequence_id, -1, -1);
+    total_reserved_tokens_ -= it->second.past_len;
+    free_sequence_ids_.push_back(it->second.sequence_id);
+    sessions_.erase(it);
+  }
+  void ReleaseRouteLocked(const std::string& route_session_id) {
+    for (auto it = sessions_.begin(); it != sessions_.end();) {
+      if (it->first.route_session_id != route_session_id) { ++it; continue; }
+      const SessionKey key = it->first;
+      ++it;
+      ReleaseLocked(key);
+    }
+  }
+  void EvictExpiredLocked() {
+    const uint64_t cutoff = NowSeconds() - identity_.hot_kv_ttl_seconds;
+    for (auto it = sessions_.begin(); it != sessions_.end();) {
+      if (it->second.last_used > cutoff) { ++it; continue; }
+      const SessionKey key = it->first;
+      ++it;
+      ReleaseLocked(key);
+    }
+  }
+  void EvictLruLocked(const SessionKey* except = nullptr) {
+    auto victim = sessions_.end();
+    for (auto it = sessions_.begin(); it != sessions_.end(); ++it) {
+      if (except && it->first.route_session_id == except->route_session_id && it->first.route_epoch == except->route_epoch) continue;
+      if (victim == sessions_.end() || it->second.last_used < victim->second.last_used) victim = it;
+    }
+    if (victim != sessions_.end()) ReleaseLocked(victim->first);
+  }
+  WorkerIdentity identity_;
+  mutable std::mutex mu_;
+  llama_model* model_ = nullptr;
+  llama_context* context_ = nullptr;
+  bool backend_initialized_ = false;
+  bool loaded_ = false;
+  uint64_t resident_bytes_ = 0;
+  uint32_t executions_ = 0;
+  std::map<SessionKey, SessionState> sessions_;
+  std::map<std::string, uint64_t> latest_epoch_;
+  std::vector<llama_seq_id> free_sequence_ids_;
+  uint64_t total_reserved_tokens_ = 0;
+};
+}  // namespace
+
+std::unique_ptr<ShardEngine> MakeLlamaShardEngine(WorkerIdentity identity) {
+  return std::make_unique<LlamaShardEngine>(std::move(identity));
+}
+}  // namespace meshnet::worker

packages/node/native/worker/llama_shard_engine.h

@@ -0,0 +1,85 @@
+// Private llama.cpp implementation of the native worker execution boundary.
+//
+// The gRPC service sees only this small project-owned surface.  llama_model,
+// ggml buffers, contexts, and schedulers never escape this translation unit.
+#ifndef MESHNET_NATIVE_WORKER_LLAMA_SHARD_ENGINE_H_
+#define MESHNET_NATIVE_WORKER_LLAMA_SHARD_ENGINE_H_
+
+#include <cstdint>
+#include <memory>
+#include <optional>
+#include <string>
+
+#include "shard_runtime.pb.h"
+
+namespace meshnet::worker {
+namespace sp = ::meshnet::shard::v1;
+
+struct WorkerIdentity {
+  std::string artifact_path;
+  std::string artifact_digest;
+  std::string recipe_digest;
+  std::string recipe_id;
+  std::string recipe_version;
+  std::string catalogue_version;
+  uint32_t start_layer = 0;
+  uint32_t end_layer = 0;  // half-open, as on the wire
+  uint32_t injected_death_after_executions = 0;  // opt-in test hook; zero disables
+  uint32_t hot_kv_max_sessions = 8;
+  uint32_t hot_kv_context_tokens = 4096;
+  uint32_t hot_kv_budget_tokens = 32768;
+  uint32_t hot_kv_ttl_seconds = 300;
+};
+
+struct BundleCheck {
+  std::optional<std::string> corrupt_detail;
+  std::optional<std::string> oversize_detail;
+};
+
+struct EngineHealth {
+  bool serving = false;
+  uint64_t resident_bytes = 0;
+  std::string detail;
+};
+
+// This is deliberately expressed in tokens, rather than guessed bytes: llama.cpp
+// owns the actual K/V layout for the loaded range and backend. The worker uses
+// the token reservation to keep its local KV arena bounded before a graph
+// adapter materializes the typed boundary (DGR-039).
+struct HotKvStep {
+  enum class Phase { kPrefill, kDecode };
+  std::string route_session_id;
+  uint64_t route_epoch = 0;
+  Phase phase = Phase::kPrefill;
+  uint64_t first_position = 0;
+  uint32_t token_count = 0;
+  uint64_t expected_past_len = 0;
+};
+
+enum class HotKvStatus { kOk, kCacheMiss, kStaleEpoch, kResourceExhausted, kCancelled };
+
+struct HotKvResult {
+  HotKvStatus status = HotKvStatus::kOk;
+  uint64_t past_len = 0;
+  std::string detail;
+};
+
+class ShardEngine {
+ public:
+  virtual ~ShardEngine() = default;
+  virtual bool Load(std::string* error) = 0;
+  virtual BundleCheck Validate(const sp::TensorBundle&, uint64_t max_chunk_bytes) const = 0;
+  virtual HotKvResult OpenSession(const std::string& route_session_id, uint64_t route_epoch) = 0;
+  virtual HotKvResult Execute(const HotKvStep&, const sp::TensorBundle&, std::string* error) = 0;
+  virtual const WorkerIdentity& identity() const = 0;
+  virtual EngineHealth health() const = 0;
+  virtual void ReleaseSession(const std::string& route_session_id, uint64_t route_epoch) = 0;
+  virtual void Shutdown() = 0;
+};
+
+// Construction is the only native implementation entry point used by the
+// worker. The returned ShardEngine owns all llama.cpp handles privately.
+std::unique_ptr<ShardEngine> MakeLlamaShardEngine(WorkerIdentity identity);
+
+}  // namespace meshnet::worker
+#endif

packages/node/native/worker/shard_service.cpp

@@ -0,0 +1,505 @@
+#include "shard_service.h"
+
+#include <algorithm>
+#include <chrono>
+#include <utility>
+
+namespace meshnet::worker {
+
+namespace {
+
+void FillWorkerFingerprint(sp::Fingerprint* fp, const WorkerIdentity& identity) {
+  fp->set_model_artifact_digest(identity.artifact_digest);
+  fp->set_runtime_recipe_digest(identity.recipe_digest);
+  fp->set_recipe_id(identity.recipe_id);
+  fp->set_recipe_version(identity.recipe_version);
+  fp->set_catalogue_version(identity.catalogue_version);
+}
+
+void FillWorkerShardRange(sp::ShardRange* range, const WorkerIdentity& identity) {
+  range->set_start_layer(identity.start_layer);
+  range->set_end_layer(identity.end_layer);
+  range->set_effective_start_layer(identity.start_layer);
+}
+
+// Strictest-of-both bound: the smallest positive of `a`/`b`, or `fallback` when
+// neither is set. Mirrors the `_min` helper in `native_protocol/codec.py`.
+uint64_t MinPositive(uint64_t a, uint64_t b, uint64_t fallback) {
+  if (a > 0 && b > 0) return std::min(a, b);
+  if (a > 0) return a;
+  if (b > 0) return b;
+  return fallback;
+}
+
+int64_t NowUnixNanos() {
+  return std::chrono::duration_cast<std::chrono::nanoseconds>(
+             std::chrono::system_clock::now().time_since_epoch())
+      .count();
+}
+
+// Build the standard fail response (a terminal-or-not ShardStatus).
+sp::SessionResponse MakeFail(const std::string& route_session_id, const std::string& work_id,
+                             uint64_t step, sp::ErrorCode code, const std::string& detail,
+                             bool terminal, bool retryable) {
+  sp::SessionResponse response;
+  sp::ShardStatus* status = response.mutable_status();
+  status->set_work_id(work_id);
+  status->set_route_session_id(route_session_id);
+  status->set_idempotency_step(step);
+  status->set_terminal(terminal);
+  sp::ShardError* error = status->mutable_error();
+  error->set_code(code);
+  error->set_detail(detail);
+  error->set_retryable(retryable);
+  return response;
+}
+
+sp::SessionResponse MakeAck(const std::string& work_id, uint64_t step, bool duplicate) {
+  sp::SessionResponse response;
+  sp::Ack* ack = response.mutable_ack();
+  ack->set_work_id(work_id);
+  ack->set_idempotency_step(step);
+  ack->set_duplicate(duplicate);
+  return response;
+}
+
+void FillDefaultFlow(sp::FlowControl* fc, const FlowLimits& limits) {
+  fc->set_credits_granted(limits.credits_granted);
+  fc->set_max_inflight_chunks(limits.max_inflight_chunks);
+  fc->set_max_chunk_bytes(limits.max_chunk_bytes);
+  fc->set_max_prefill_chunk_tokens(limits.max_prefill_chunk_tokens);
+}
+
+sp::SessionResponse HotKvFailure(const std::string& route_session_id, const std::string& work_id,
+                                 uint64_t step, const HotKvResult& result) {
+  switch (result.status) {
+    case HotKvStatus::kStaleEpoch:
+      return MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_EPOCH_STALE, result.detail, false, false);
+    case HotKvStatus::kCacheMiss:
+      return MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_CACHE_MISS, result.detail, false, true);
+    case HotKvStatus::kResourceExhausted:
+      return MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_RESOURCE_EXHAUSTED, result.detail, false, true);
+    case HotKvStatus::kCancelled:
+      return MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_CANCELLED, result.detail, false, false);
+    case HotKvStatus::kOk:
+      break;
+  }
+  return MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_INTERNAL, "unexpected Hot KV result", false, true);
+}
+
+}  // namespace
+
+grpc::Status ShardRuntimeServiceImpl::GetCapability(grpc::ServerContext*,
+                                                    const sp::CapabilityRequest*,
+                                                    sp::CapabilityReport* response) {
+  response->set_schema_version(sp::SCHEMA_VERSION_1);
+  const WorkerIdentity& identity = engine_.identity();
+  const EngineHealth health = engine_.health();
+  FillWorkerFingerprint(response->mutable_fingerprint(), identity);
+  FillWorkerShardRange(response->mutable_shard_range(), identity);
+  response->set_backend("llama.cpp");
+  response->set_device("cpu");
+  response->set_validated(health.serving);
+  response->set_detail(health.detail);
+  response->set_max_concurrent_sessions(8);
+  response->set_max_context_tokens(131072);
+  FillDefaultFlow(response->mutable_flow_control(), limits_);
+  response->add_accepted_compression(sp::COMPRESSION_NONE);
+  response->add_supported_schema_versions(sp::SCHEMA_VERSION_1);
+  response->set_validated_at_unix_nanos(0);
+  return grpc::Status::OK;
+}
+
+grpc::Status ShardRuntimeServiceImpl::Health(grpc::ServerContext*, const sp::HealthRequest*,
+                                             sp::HealthReport* response) {
+  response->set_schema_version(sp::SCHEMA_VERSION_1);
+  const EngineHealth engine_health = engine_.health();
+  response->set_state(engine_health.serving ? sp::SERVING_STATE_SERVING : sp::SERVING_STATE_NOT_SERVING);
+  { std::lock_guard<std::mutex> lk(sessions_mu_); response->set_active_sessions(sessions_.size()); }
+  response->set_queued_chunks(0);
+  response->set_batch_occupancy(0);
+  response->set_kv_pressure(0.0f);
+  response->set_resident_bytes(engine_health.resident_bytes);
+  response->set_detail(engine_health.detail + "; loaded=" + engine_.identity().artifact_digest +
+                       " range=[" + std::to_string(engine_.identity().start_layer) + "," +
+                       std::to_string(engine_.identity().end_layer) + ")");
+  return grpc::Status::OK;
+}
+
+FlowLimits ShardRuntimeServiceImpl::NegotiateFlow(const sp::FlowControl& proposed) const {
+  FlowLimits out;
+  out.max_inflight_chunks = static_cast<uint32_t>(MinPositive(
+      proposed.max_inflight_chunks(), limits_.max_inflight_chunks, limits_.max_inflight_chunks));
+  const uint64_t credits = MinPositive(proposed.credits_granted(), limits_.credits_granted,
+                                       limits_.credits_granted);
+  out.credits_granted =
+      static_cast<uint32_t>(std::min<uint64_t>(credits, out.max_inflight_chunks));
+  out.max_chunk_bytes =
+      MinPositive(proposed.max_chunk_bytes(), limits_.max_chunk_bytes, limits_.max_chunk_bytes);
+  out.max_prefill_chunk_tokens = static_cast<uint32_t>(MinPositive(
+      proposed.max_prefill_chunk_tokens(), limits_.max_prefill_chunk_tokens,
+      limits_.max_prefill_chunk_tokens));
+  return out;
+}
+
+uint32_t ShardRuntimeServiceImpl::MarkCancelled(const std::string& route_session_id,
+                                                const std::string& work_id) {
+  std::lock_guard<std::mutex> lk(sessions_mu_);
+  SessionState& state = sessions_[route_session_id];  // creates on first cancel-before-open
+  if (state.max_inflight == 0) {
+    // Freshly created placeholder for a Cancel that raced ahead of Open.
+    state.credits = limits_.credits_granted;
+    state.max_inflight = limits_.max_inflight_chunks;
+    state.max_chunk_bytes = limits_.max_chunk_bytes;
+  }
+  if (work_id.empty()) {
+    const bool already = state.cancelled_session;
+    state.cancelled_session = true;
+    return already ? 0 : 1;
+  }
+  const bool already = state.cancelled_work.count(work_id) != 0;
+  state.cancelled_work.insert(work_id);
+  return already ? 0 : 1;
+}
+
+grpc::Status ShardRuntimeServiceImpl::Session(
+    grpc::ServerContext*,
+    grpc::ServerReaderWriter<sp::SessionResponse, sp::SessionRequest>* stream) {
+  std::string route_session_id;
+  sp::SessionRequest request;
+
+  while (stream->Read(&request)) {
+    switch (request.kind_case()) {
+      case sp::SessionRequest::kOpen: {
+        const sp::SessionOpen& open = request.open();
+        route_session_id = open.route_session_id();
+
+        // Reject an incompatible peer at open rather than mid-generation. The
+        // worker validates the caller's schema, artifact/recipe identity and
+        // requested layer range against its own — it never adopts the caller's
+        // claimed identity.
+        auto reject_open = [&](sp::ErrorCode code, const std::string& detail) {
+          stream->Write(MakeFail(route_session_id, /*work_id=*/"", /*step=*/0, code, detail,
+                                 /*terminal=*/true, /*retryable=*/false));
+        };
+        if (open.schema_version() != sp::SCHEMA_VERSION_1) {
+          reject_open(sp::ERROR_CODE_SCHEMA_UNSUPPORTED,
+                      "worker serves schema version 1 only");
+          return grpc::Status::OK;
+        }
+        const sp::Fingerprint& fp = open.fingerprint();
+        if ((!fp.model_artifact_digest().empty() &&
+             fp.model_artifact_digest() != engine_.identity().artifact_digest) ||
+            (!fp.runtime_recipe_digest().empty() &&
+             fp.runtime_recipe_digest() != engine_.identity().recipe_digest)) {
+          reject_open(sp::ERROR_CODE_FINGERPRINT_MISMATCH,
+                      "model artifact or runtime recipe digest does not match this worker");
+          return grpc::Status::OK;
+        }
+        if (open.has_shard_range()) {
+          const sp::ShardRange& r = open.shard_range();
+          const bool within = r.start_layer() == engine_.identity().start_layer &&
+                              r.end_layer() == engine_.identity().end_layer &&
+                              r.effective_start_layer() == engine_.identity().start_layer;
+          if (!within) {
+            reject_open(sp::ERROR_CODE_SHARD_RANGE_MISMATCH,
+                        "requested layer range is not served by this worker");
+            return grpc::Status::OK;
+          }
+        }
+
+        // Settle the flow-control window with strict worker bounds, then keep
+        // the negotiated ceilings on the session so every later check enforces
+        // exactly what was agreed — not what the peer proposed.
+        const FlowLimits negotiated =
+            open.has_proposed_flow_control()
+                ? NegotiateFlow(open.proposed_flow_control())
+                : limits_;
+        const HotKvResult hot_kv = engine_.OpenSession(route_session_id, open.route_epoch());
+        if (hot_kv.status != HotKvStatus::kOk) {
+          stream->Write(HotKvFailure(route_session_id, "", 0, hot_kv));
+          return grpc::Status::OK;
+        }
+        {
+          std::lock_guard<std::mutex> lk(sessions_mu_);
+          SessionState state;
+          state.epoch = open.route_epoch();
+          state.credits = negotiated.credits_granted;
+          state.max_inflight = negotiated.max_inflight_chunks;
+          state.max_chunk_bytes = negotiated.max_chunk_bytes;
+          state.max_prefill_chunk_tokens = negotiated.max_prefill_chunk_tokens;
+          state.opened = true;
+          auto it = sessions_.find(route_session_id);
+          if (it != sessions_.end()) {
+            // A prior out-of-band Cancel may have marked this session cancelled
+            // before Open arrived; preserve that so the work still fails closed.
+            state.cancelled_session = it->second.cancelled_session;
+            state.cancelled_work = it->second.cancelled_work;
+          }
+          sessions_[route_session_id] = std::move(state);
+        }
+        sp::SessionResponse response;
+        sp::SessionAccepted* accepted = response.mutable_accepted();
+        accepted->set_schema_version(sp::SCHEMA_VERSION_1);
+        accepted->set_route_session_id(open.route_session_id());
+        accepted->set_route_epoch(open.route_epoch());
+        FillDefaultFlow(accepted->mutable_flow_control(), negotiated);
+        if (open.accepted_compression_size() > 0) {
+          for (int c : open.accepted_compression()) {
+            accepted->add_accepted_compression(static_cast<sp::Compression>(c));
+          }
+        } else {
+          accepted->add_accepted_compression(sp::COMPRESSION_NONE);
+        }
+        // Report the fingerprint the worker actually serves, so a mismatch is
+        // visible at open — never a copy of the caller's claimed identity.
+        FillWorkerFingerprint(accepted->mutable_fingerprint(), engine_.identity());
+        stream->Write(response);
+        break;
+      }
+
+      case sp::SessionRequest::kChunk: {
+        const sp::ActivationChunk& chunk = request.chunk();
+        const sp::Envelope& envelope = chunk.envelope();
+        const std::string work_id = envelope.work_id();
+        const uint64_t step = envelope.idempotency_step();
+
+        // Compute the response under the lock, then write it *after* releasing —
+        // holding the lock across a (possibly blocking) Write would deadlock an
+        // out-of-band Cancel RPC that needs the same lock.
+        sp::SessionResponse response;
+        bool terminate = false;
+        {
+          std::lock_guard<std::mutex> lk(sessions_mu_);
+          auto it = sessions_.find(route_session_id);
+          SessionState* state = it != sessions_.end() ? &it->second : nullptr;
+
+          if (state == nullptr || !state->opened) {
+            // Fail closed: an activation before a valid SessionOpen must never
+            // bypass lifecycle, cancellation, epoch or flow-control state.
+            response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_INTERNAL,
+                               "activation received before SessionOpen", true, false);
+            terminate = true;
+          } else if (state->cancelled_session || state->cancelled_work.count(work_id)) {
+            response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_CANCELLED,
+                               "work was cancelled", false, false);
+          } else if (envelope.route_epoch() < state->epoch) {
+            response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_EPOCH_STALE,
+                               "stale route epoch", false, false);
+          } else if (envelope.deadline_unix_nanos() != 0 &&
+                     NowUnixNanos() > envelope.deadline_unix_nanos()) {
+            response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_DEADLINE_EXCEEDED,
+                               "deadline already passed", false, false);
+          } else if (state->seen_steps.count(step)) {
+            response = MakeAck(work_id, step, /*duplicate=*/true);
+          } else if (state->credits <= 0) {
+            response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_FLOW_CONTROL_VIOLATION,
+                               "no flow-control credit remaining", false, true);
+          } else {
+            const BundleCheck check = engine_.Validate(chunk.bundle(), state->max_chunk_bytes);
+            if (check.oversize_detail) {
+              response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_RESOURCE_EXHAUSTED,
+                                 *check.oversize_detail, false, false);
+            } else if (check.corrupt_detail) {
+              response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_PAYLOAD_CORRUPT,
+                                 *check.corrupt_detail, false, false);
+            } else {
+              std::string execution_error;
+              const HotKvResult executed = engine_.Execute(
+                  HotKvStep{route_session_id, envelope.route_epoch(), HotKvStep::Phase::kPrefill,
+                            envelope.position().first_position(), envelope.position().token_count(),
+                            envelope.cache_expectation().expected_past_len()},
+                  chunk.bundle(), &execution_error);
+              if (executed.status != HotKvStatus::kOk) {
+                response = HotKvFailure(route_session_id, work_id, step, executed);
+              } else {
+              state->seen_steps.insert(step);
+              state->credits -= 1;
+              *response.mutable_chunk() = chunk;  // echo the exact bundle back
+              }
+            }
+          }
+        }
+        stream->Write(response);
+        if (terminate) {
+          return grpc::Status::OK;
+        }
+        break;
+      }
+
+      case sp::SessionRequest::kDecode: {
+        const sp::DecodeStep& step_msg = request.decode();
+        const std::string work_id = step_msg.work_id();
+        const uint64_t step = step_msg.idempotency_step();
+
+        sp::TensorBundle bundle;
+        if (step_msg.bundle().tensors_size() > 0) {
+          bundle = step_msg.bundle();
+        } else {
+          bundle.set_bundle_version(1);
+          *bundle.add_tensors() = step_msg.tensor();
+        }
+
+        sp::SessionResponse response;
+        bool terminate = false;
+        {
+          std::lock_guard<std::mutex> lk(sessions_mu_);
+          auto it = sessions_.find(route_session_id);
+          SessionState* state = it != sessions_.end() ? &it->second : nullptr;
+
+          if (state == nullptr || !state->opened) {
+            // Fail closed: a decode step before a valid SessionOpen must never
+            // bypass lifecycle, cancellation, epoch or flow-control state.
+            response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_INTERNAL,
+                               "activation received before SessionOpen", true, false);
+            terminate = true;
+          } else if (state->cancelled_session || state->cancelled_work.count(work_id)) {
+            response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_CANCELLED,
+                               "work was cancelled", false, false);
+          } else if (step_msg.deadline_unix_nanos() != 0 &&
+                     NowUnixNanos() > step_msg.deadline_unix_nanos()) {
+            response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_DEADLINE_EXCEEDED,
+                               "deadline already passed", false, false);
+          } else if (state->seen_steps.count(step)) {
+            response = MakeAck(work_id, step, /*duplicate=*/true);
+          } else if (state->credits <= 0) {
+            response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_FLOW_CONTROL_VIOLATION,
+                               "no flow-control credit remaining", false, true);
+          } else {
+            const BundleCheck check = engine_.Validate(bundle, state->max_chunk_bytes);
+            if (check.oversize_detail) {
+              response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_RESOURCE_EXHAUSTED,
+                                 *check.oversize_detail, false, false);
+            } else if (check.corrupt_detail) {
+              response = MakeFail(route_session_id, work_id, step, sp::ERROR_CODE_PAYLOAD_CORRUPT,
+                                 *check.corrupt_detail, false, false);
+            } else {
+              std::string execution_error;
+              const HotKvResult executed = engine_.Execute(
+                  HotKvStep{route_session_id, state->epoch, HotKvStep::Phase::kDecode,
+                            step_msg.position(), 1, step_msg.expected_past_len()}, bundle, &execution_error);
+              if (executed.status != HotKvStatus::kOk) {
+                response = HotKvFailure(route_session_id, work_id, step, executed);
+              } else {
+              state->seen_steps.insert(step);
+              state->credits -= 1;
+              // No decode response field exists; echo the step back as a
+              // chunk-bearing SessionResponse per the proto's relayed-frame design.
+              sp::ActivationChunk* out = response.mutable_chunk();
+              sp::Envelope* out_env = out->mutable_envelope();
+              out_env->set_schema_version(sp::SCHEMA_VERSION_1);
+              out_env->set_work_id(work_id);
+              out_env->set_idempotency_step(step);
+              out_env->set_phase(sp::PHASE_DECODE);
+              sp::PositionSpan* pos = out_env->mutable_position();
+              pos->set_first_position(step_msg.position());
+              pos->set_token_count(1);
+              *out->mutable_bundle() = bundle;
+              }
+            }
+          }
+        }
+        stream->Write(response);
+        if (terminate) {
+          return grpc::Status::OK;
+        }
+        break;
+      }
+
+      case sp::SessionRequest::kFlowControl: {
+        const uint32_t topup = request.flow_control().credits_granted();
+        sp::SessionResponse response;
+        {
+          std::lock_guard<std::mutex> lk(sessions_mu_);
+          auto it = sessions_.find(route_session_id);
+          sp::FlowControl* fc = response.mutable_flow_control();
+          if (it != sessions_.end()) {
+            SessionState& state = it->second;
+            int64_t granted = std::min<int64_t>(state.credits + topup,
+                                                 static_cast<int64_t>(state.max_inflight));
+            state.credits = granted;
+            fc->set_credits_granted(static_cast<uint32_t>(granted));
+            fc->set_max_inflight_chunks(state.max_inflight);
+            fc->set_max_chunk_bytes(state.max_chunk_bytes);
+          } else {
+            fc->set_credits_granted(topup != 0 ? topup : limits_.credits_granted);
+            fc->set_max_inflight_chunks(limits_.max_inflight_chunks);
+            fc->set_max_chunk_bytes(limits_.max_chunk_bytes);
+          }
+          fc->set_max_prefill_chunk_tokens(limits_.max_prefill_chunk_tokens);
+        }
+        stream->Write(response);
+        break;
+      }
+
+      case sp::SessionRequest::kRelease: {
+        const sp::ReleaseSignal& release = request.release();
+        // An explicit release drops session state immediately (KV, credits,
+        // dedup) instead of holding it for the TTL — the whole point of the
+        // signal. Erase the session this stream opened so its resources are
+        // freed the moment the terminal status is sent.
+        {
+          std::lock_guard<std::mutex> lk(sessions_mu_);
+          auto it = sessions_.find(release.route_session_id());
+          if (it != sessions_.end() && it->second.epoch == release.route_epoch()) {
+            sessions_.erase(it);
+          }
+          engine_.ReleaseSession(release.route_session_id(), release.route_epoch());
+        }
+        sp::SessionResponse response;
+        sp::ShardStatus* status = response.mutable_status();
+        status->set_work_id(release.work_id());
+        status->set_route_session_id(release.route_session_id());
+        status->set_terminal(true);
+        stream->Write(response);
+        return grpc::Status::OK;
+      }
+
+      case sp::SessionRequest::kCancel: {
+        const sp::CancelSignal& signal = request.cancel();
+        MarkCancelled(route_session_id, signal.work_id());
+        const bool whole_session = signal.work_id().empty();
+        stream->Write(MakeFail(route_session_id, signal.work_id(), 0, sp::ERROR_CODE_CANCELLED,
+                               signal.reason().empty() ? "cancelled" : signal.reason(),
+                               whole_session, false));
+        if (whole_session) {
+          return grpc::Status::OK;
+        }
+        break;
+      }
+
+      default: {
+        sp::SessionResponse response;
+        response.mutable_status()->set_terminal(true);
+        stream->Write(response);
+        return grpc::Status::OK;
+      }
+    }
+  }
+  return grpc::Status::OK;
+}
+
+grpc::Status ShardRuntimeServiceImpl::Release(grpc::ServerContext*,
+                                              const sp::ReleaseRequest* request,
+                                              sp::ReleaseResponse* response) {
+  bool existed;
+  {
+    std::lock_guard<std::mutex> lk(sessions_mu_);
+    auto it = sessions_.find(request->route_session_id());
+    existed = it != sessions_.end() && it->second.epoch == request->route_epoch();
+    if (existed) sessions_.erase(it);
+    engine_.ReleaseSession(request->route_session_id(), request->route_epoch());
+  }
+  response->set_released(existed);
+  return grpc::Status::OK;
+}
+
+grpc::Status ShardRuntimeServiceImpl::Cancel(grpc::ServerContext*,
+                                             const sp::CancelRequest* request,
+                                             sp::CancelResponse* response) {
+  const uint32_t newly = MarkCancelled(request->route_session_id(), request->work_id());
+  response->set_cancelled_work_items(newly);
+  return grpc::Status::OK;
+}
+
+}  // namespace meshnet::worker

packages/node/native/worker/shard_service.h

@@ -0,0 +1,96 @@
+// The native Shard worker's ShardRuntime service (DGR-033).
+//
+// A faithful C++ port of `ShardRuntimeServicer` in `shard_runtime_server.py`:
+// the same per-`route_session_id` identity/credit/dedup state, the same
+// fail-closed negative paths (stale epoch, expired deadline, corrupt/oversize
+// payload, exhausted flow-control credit, duplicate idempotency step, in-band
+// and out-of-band cancellation), and the same lifecycle (open/prefill/decode/
+// flow-control/release/cancel). The only compute it does is the fake engine's
+// bounded forward — there is no llama.cpp linkage and no arbitrary-graph RPC.
+
+#ifndef MESHNET_NATIVE_WORKER_SHARD_SERVICE_H_
+#define MESHNET_NATIVE_WORKER_SHARD_SERVICE_H_
+
+#include <cstdint>
+#include <map>
+#include <mutex>
+#include <set>
+#include <string>
+
+#include <grpcpp/grpcpp.h>
+
+#include "llama_shard_engine.h"
+#include "shard_runtime.grpc.pb.h"
+#include "shard_runtime.pb.h"
+
+namespace meshnet::worker {
+
+namespace sp = ::meshnet::shard::v1;
+
+struct FlowLimits {
+  uint32_t credits_granted = 16;
+  uint32_t max_inflight_chunks = 16;
+  uint64_t max_chunk_bytes = 4u * 1024u * 1024u;
+  uint32_t max_prefill_chunk_tokens = 512;
+};
+
+// Per-route-session identity/credit/dedup state, kept on the servicer instance
+// (guarded by a lock) so an out-of-band unary Cancel from a different handler
+// thread can reach a session a concurrent Session stream is still iterating.
+struct SessionState {
+  uint64_t epoch = 0;
+  int64_t credits = 0;
+  uint32_t max_inflight = 0;
+  uint64_t max_chunk_bytes = 0;
+  uint32_t max_prefill_chunk_tokens = 0;
+  std::set<uint64_t> seen_steps;
+  std::set<std::string> cancelled_work;
+  bool cancelled_session = false;
+  // True only after a valid SessionOpen handshake completed for this
+  // route_session_id. An activation (chunk/decode) that arrives while this is
+  // false fails closed: no work may bypass the lifecycle handshake, even when a
+  // placeholder state already exists from an out-of-band Cancel that raced Open.
+  bool opened = false;
+};
+
+class ShardRuntimeServiceImpl final : public sp::ShardRuntime::Service {
+ public:
+  ShardRuntimeServiceImpl(FlowLimits limits, ShardEngine& engine) : limits_(limits), engine_(engine) {}
+
+  grpc::Status GetCapability(grpc::ServerContext* context,
+                             const sp::CapabilityRequest* request,
+                             sp::CapabilityReport* response) override;
+
+  grpc::Status Health(grpc::ServerContext* context, const sp::HealthRequest* request,
+                      sp::HealthReport* response) override;
+
+  grpc::Status Session(
+      grpc::ServerContext* context,
+      grpc::ServerReaderWriter<sp::SessionResponse, sp::SessionRequest>* stream) override;
+
+  grpc::Status Release(grpc::ServerContext* context, const sp::ReleaseRequest* request,
+                       sp::ReleaseResponse* response) override;
+
+  grpc::Status Cancel(grpc::ServerContext* context, const sp::CancelRequest* request,
+                      sp::CancelResponse* response) override;
+
+ private:
+  // Returns the number of items newly marked cancelled, creating session state
+  // if the Cancel raced ahead of SessionOpen.
+  uint32_t MarkCancelled(const std::string& route_session_id, const std::string& work_id);
+
+  // Settle a stream's flow-control window against this worker's own limits: the
+  // strictest bound of either peer wins for every field, so a peer can never
+  // raise the worker's ceilings by proposing a larger window. Mirrors
+  // `negotiate_flow_control` in `native_protocol/codec.py`.
+  FlowLimits NegotiateFlow(const sp::FlowControl& proposed) const;
+
+  FlowLimits limits_;
+  ShardEngine& engine_;
+  std::mutex sessions_mu_;
+  std::map<std::string, SessionState> sessions_;
+};
+
+}  // namespace meshnet::worker
+
+#endif  // MESHNET_NATIVE_WORKER_SHARD_SERVICE_H_

packages/node/native/worker/shard_worker_main.cpp

@@ -0,0 +1,380 @@
+// Standalone native Shard worker executable (DGR-033).
+//
+// Serves the complete ShardRuntime lifecycle/stream contract over real
+// gRPC/HTTP2 using the model-free FakeShardEngine. It links neither llama.cpp
+// nor any graph-execution entry point: the only surface it exposes is the
+// ShardRuntime service defined in shard_runtime.proto.
+//
+// Usage:
+//   shard_worker [listen_addr]     serve until SIGTERM/SIGINT (graceful drain)
+//   shard_worker --selftest        bind an ephemeral port, self-drive the
+//                                  lifecycle over a real loopback channel, exit
+//
+// Environment:
+//   MESHNET_SHARD_LISTEN_ADDR   host:port to bind (default localhost:50051)
+//   MESHNET_MAX_CHUNK_BYTES     per-chunk byte ceiling the worker enforces
+//
+// On a normal run it prints one readiness line — "ShardRuntime worker listening
+// on <addr>" — once the socket is bound, so a supervisor/harness has a real
+// readiness signal instead of a sleep.
+
+#include <atomic>
+#include <cerrno>
+#include <csignal>
+#include <cstdint>
+#include <cstdlib>
+#include <cstring>
+#include <iostream>
+#include <memory>
+#include <string>
+#include <thread>
+#include <unistd.h>
+
+#include <grpcpp/grpcpp.h>
+
+#include "shard_service.h"
+#include "shard_runtime.grpc.pb.h"
+
+namespace {
+
+namespace sp = ::meshnet::shard::v1;
+
+// Self-pipe: the signal handler must stay async-signal-safe, so it only writes
+// one byte; a helper thread reads it and performs the (non-signal-safe) server
+// Shutdown(). Set once in main() before installing the handler.
+volatile std::sig_atomic_t g_signal_pipe_write_fd = -1;
+
+extern "C" void HandleTermination(int /*signum*/) {
+  if (g_signal_pipe_write_fd >= 0) {
+    const char byte = 1;
+    ssize_t rc = ::write(g_signal_pipe_write_fd, &byte, 1);
+    (void)rc;  // best-effort; nothing safe to do on failure inside a handler
+  }
+}
+
+meshnet::worker::FlowLimits LimitsFromEnv() {
+  meshnet::worker::FlowLimits limits;
+  if (const char* raw = std::getenv("MESHNET_MAX_CHUNK_BYTES")) {
+    char* end = nullptr;
+    const unsigned long long value = std::strtoull(raw, &end, 10);
+    if (end != raw && value > 0) {
+      limits.max_chunk_bytes = static_cast<uint64_t>(value);
+    }
+  }
+  return limits;
+}
+
+bool PositiveEnv(const char* name, uint32_t* out, std::string* error) {
+  if (const char* value = std::getenv(name)) {
+    char* end = nullptr;
+    const unsigned long parsed = std::strtoul(value, &end, 10);
+    if (end == value || *end != '\0' || parsed == 0 || parsed > UINT32_MAX) {
+      *error = std::string("invalid ") + name;
+      return false;
+    }
+    *out = static_cast<uint32_t>(parsed);
+  }
+  return true;
+}
+
+bool IdentityFromEnv(meshnet::worker::WorkerIdentity* identity, std::string* error) {
+  const auto required = [&](const char* name, std::string* out) -> bool {
+    const char* value = std::getenv(name);
+    if (!value || !*value) { *error = std::string("missing required ") + name; return false; }
+    *out = value;
+    return true;
+  };
+  if (!required("MESHNET_MODEL_ARTIFACT", &identity->artifact_path) ||
+      !required("MESHNET_MODEL_ARTIFACT_DIGEST", &identity->artifact_digest) ||
+      !required("MESHNET_RUNTIME_RECIPE_DIGEST", &identity->recipe_digest) ||
+      !required("MESHNET_RECIPE_ID", &identity->recipe_id) ||
+      !required("MESHNET_RECIPE_VERSION", &identity->recipe_version) ||
+      !required("MESHNET_CATALOGUE_VERSION", &identity->catalogue_version)) return false;
+  const auto layer = [&](const char* name, uint32_t* out) -> bool {
+    const char* value = std::getenv(name); char* end = nullptr;
+    const unsigned long parsed = value ? std::strtoul(value, &end, 10) : 0;
+    if (!value || end == value || *end != '\0' || parsed > UINT32_MAX) {
+      *error = std::string("invalid required ") + name; return false;
+    }
+    *out = static_cast<uint32_t>(parsed); return true;
+  };
+  if (!layer("MESHNET_SHARD_START_LAYER", &identity->start_layer) ||
+      !layer("MESHNET_SHARD_END_LAYER", &identity->end_layer) ||
+      identity->end_layer <= identity->start_layer) {
+    if (error->empty()) *error = "MESHNET_SHARD_END_LAYER must exceed MESHNET_SHARD_START_LAYER";
+    return false;
+  }
+  if (const char* value = std::getenv("MESHNET_INJECT_PROCESS_DEATH_AFTER_EXECUTIONS")) {
+    char* end = nullptr;
+    const unsigned long parsed = std::strtoul(value, &end, 10);
+    if (end == value || *end != '\0' || parsed == 0 || parsed > UINT32_MAX) {
+      *error = "invalid MESHNET_INJECT_PROCESS_DEATH_AFTER_EXECUTIONS";
+      return false;
+    }
+    identity->injected_death_after_executions = static_cast<uint32_t>(parsed);
+  }
+  if (!PositiveEnv("MESHNET_HOT_KV_MAX_SESSIONS", &identity->hot_kv_max_sessions, error) ||
+      !PositiveEnv("MESHNET_HOT_KV_CONTEXT_TOKENS", &identity->hot_kv_context_tokens, error) ||
+      !PositiveEnv("MESHNET_HOT_KV_BUDGET_TOKENS", &identity->hot_kv_budget_tokens, error) ||
+      !PositiveEnv("MESHNET_HOT_KV_TTL_SECONDS", &identity->hot_kv_ttl_seconds, error)) return false;
+  if (identity->hot_kv_budget_tokens < identity->hot_kv_context_tokens) {
+    *error = "MESHNET_HOT_KV_BUDGET_TOKENS must cover one session context";
+    return false;
+  }
+  return true;
+}
+
+int RunSelfTest() {
+  std::cerr << "selftest requires an opt-in real GGUF artifact; use the native worker integration harness\n";
+  return 2;
+  // A model-free selftest would reintroduce the fake execution path DGR-037 removes.
+#if 0
+  int selected_port = 0;
+  grpc::ServerBuilder builder;
+  builder.AddListeningPort("127.0.0.1:0", grpc::InsecureServerCredentials(), &selected_port);
+  builder.RegisterService(&service);
+  std::unique_ptr<grpc::Server> server(builder.BuildAndStart());
+  if (!server || selected_port == 0) {
+    std::cerr << "selftest: failed to bind ephemeral port\n";
+    return 1;
+  }
+  const std::string target = "127.0.0.1:" + std::to_string(selected_port);
+  auto channel = grpc::CreateChannel(target, grpc::InsecureChannelCredentials());
+  auto stub = sp::ShardRuntime::NewStub(channel);
+
+  int failures = 0;
+  auto check = [&](bool cond, const char* what) {
+    if (!cond) {
+      std::cerr << "selftest FAIL: " << what << "\n";
+      ++failures;
+    }
+  };
+
+  // Capability + health.
+  {
+    grpc::ClientContext ctx;
+    sp::CapabilityRequest req;
+    req.set_schema_version(sp::SCHEMA_VERSION_1);
+    sp::CapabilityReport rep;
+    grpc::Status status = stub->GetCapability(&ctx, req, &rep);
+    check(status.ok(), "GetCapability RPC");
+    check(rep.validated(), "capability validated");
+    check(rep.schema_version() == sp::SCHEMA_VERSION_1, "capability schema version");
+  }
+  {
+    grpc::ClientContext ctx;
+    sp::HealthRequest req;
+    req.set_schema_version(sp::SCHEMA_VERSION_1);
+    sp::HealthReport rep;
+    grpc::Status status = stub->Health(&ctx, req, &rep);
+    check(status.ok(), "Health RPC");
+    check(rep.state() == sp::SERVING_STATE_SERVING, "health serving");
+  }
+
+  // A minimal session: open -> fragmented prefill -> decode -> release.
+  {
+    grpc::ClientContext ctx;
+    auto stream = stub->Session(&ctx);
+
+    sp::SessionRequest open;
+    sp::SessionOpen* o = open.mutable_open();
+    o->set_schema_version(sp::SCHEMA_VERSION_1);
+    o->set_route_session_id("selftest");
+    o->set_route_epoch(1);
+    sp::FlowControl* fc = o->mutable_proposed_flow_control();
+    fc->set_credits_granted(16);
+    fc->set_max_inflight_chunks(16);
+    fc->set_max_chunk_bytes(4u * 1024u * 1024u);
+    check(stream->Write(open), "write open");
+
+    sp::SessionResponse accepted;
+    check(stream->Read(&accepted), "read accepted");
+    check(accepted.kind_case() == sp::SessionResponse::kAccepted, "accepted kind");
+
+    // Fragmented prefill: two fragments tiling a 6-byte payload.
+    const std::string payload = "ABCDEF";
+    sp::SessionRequest chunk;
+    sp::ActivationChunk* ac = chunk.mutable_chunk();
+    sp::Envelope* env = ac->mutable_envelope();
+    env->set_schema_version(sp::SCHEMA_VERSION_1);
+    env->set_work_id("w1");
+    env->set_route_session_id("selftest");
+    env->set_route_epoch(1);
+    env->set_idempotency_step(1);
+    env->set_phase(sp::PHASE_PREFILL);
+    sp::TensorBundle* bundle = ac->mutable_bundle();
+    bundle->set_bundle_version(1);
+    sp::NamedTensor* tensor = bundle->add_tensors();
+    tensor->set_name("hidden_states");
+    tensor->set_dtype(sp::DTYPE_BFLOAT16);
+    tensor->set_byte_order(sp::BYTE_ORDER_LITTLE_ENDIAN);
+    tensor->set_total_bytes(payload.size());
+    tensor->set_compression(sp::COMPRESSION_NONE);
+    sp::Checksum* cksum = tensor->mutable_checksum();
+    cksum->set_algorithm(sp::CHECKSUM_ALGORITHM_CRC32C);
+    const uint32_t crc = meshnet::worker::Crc32(payload);
+    std::string crc_be(4, '\0');
+    crc_be[0] = static_cast<char>((crc >> 24) & 0xFF);
+    crc_be[1] = static_cast<char>((crc >> 16) & 0xFF);
+    crc_be[2] = static_cast<char>((crc >> 8) & 0xFF);
+    crc_be[3] = static_cast<char>(crc & 0xFF);
+    cksum->set_value(crc_be);
+    sp::TensorFragment* f0 = tensor->add_fragments();
+    f0->set_fragment_index(0);
+    f0->set_fragment_count(2);
+    f0->set_byte_offset(0);
+    f0->set_payload(payload.substr(0, 3));
+    sp::TensorFragment* f1 = tensor->add_fragments();
+    f1->set_fragment_index(1);
+    f1->set_fragment_count(2);
+    f1->set_byte_offset(3);
+    f1->set_payload(payload.substr(3));
+    check(stream->Write(chunk), "write chunk");
+
+    sp::SessionResponse echoed;
+    check(stream->Read(&echoed), "read chunk echo");
+    check(echoed.kind_case() == sp::SessionResponse::kChunk, "chunk echo kind");
+
+    sp::SessionRequest decode;
+    sp::DecodeStep* ds = decode.mutable_decode();
+    ds->set_idempotency_step(2);
+    ds->set_position(1);
+    ds->set_work_id("w2");
+    sp::TensorBundle* dbundle = ds->mutable_bundle();
+    dbundle->set_bundle_version(1);
+    sp::NamedTensor* dt = dbundle->add_tensors();
+    dt->set_name("hidden_states");
+    dt->set_dtype(sp::DTYPE_BFLOAT16);
+    dt->set_byte_order(sp::BYTE_ORDER_LITTLE_ENDIAN);
+    dt->set_total_bytes(payload.size());
+    dt->set_compression(sp::COMPRESSION_NONE);
+    sp::Checksum* dck = dt->mutable_checksum();
+    dck->set_algorithm(sp::CHECKSUM_ALGORITHM_CRC32C);
+    dck->set_value(crc_be);
+    sp::TensorFragment* df = dt->add_fragments();
+    df->set_fragment_index(0);
+    df->set_fragment_count(1);
+    df->set_byte_offset(0);
+    df->set_payload(payload);
+    check(stream->Write(decode), "write decode");
+
+    sp::SessionResponse decode_echo;
+    check(stream->Read(&decode_echo), "read decode echo");
+    check(decode_echo.kind_case() == sp::SessionResponse::kChunk, "decode echo kind");
+
+    sp::SessionRequest release;
+    sp::ReleaseSignal* rs = release.mutable_release();
+    rs->set_route_session_id("selftest");
+    rs->set_work_id("w-final");
+    check(stream->Write(release), "write release");
+    stream->WritesDone();
+
+    sp::SessionResponse terminal;
+    check(stream->Read(&terminal), "read terminal");
+    check(terminal.kind_case() == sp::SessionResponse::kStatus && terminal.status().terminal(),
+          "terminal status");
+
+    grpc::Status status = stream->Finish();
+    check(status.ok(), "stream finish");
+  }
+
+  server->Shutdown();
+  server->Wait();
+
+  if (failures == 0) {
+    std::cout << "selftest: all lifecycle checks passed\n";
+    return 0;
+  }
+  std::cerr << "selftest: " << failures << " check(s) failed\n";
+  return 1;
+}
+#endif
+}
+
+}  // namespace
+
+int main(int argc, char** argv) {
+  GOOGLE_PROTOBUF_VERIFY_VERSION;
+
+  for (int i = 1; i < argc; ++i) {
+    if (std::strcmp(argv[i], "--selftest") == 0) {
+      return RunSelfTest();
+    }
+  }
+
+  std::string listen_addr = "localhost:50051";
+  if (const char* env = std::getenv("MESHNET_SHARD_LISTEN_ADDR")) {
+    listen_addr = env;
+  }
+  if (argc > 1 && argv[1][0] != '-') {
+    listen_addr = argv[1];
+  }
+
+  meshnet::worker::WorkerIdentity identity;
+  std::string load_error;
+  if (!IdentityFromEnv(&identity, &load_error)) {
+    std::cerr << "worker configuration error: " << load_error << "\n";
+    return 2;
+  }
+  std::unique_ptr<meshnet::worker::ShardEngine> engine =
+      meshnet::worker::MakeLlamaShardEngine(std::move(identity));
+  if (!engine->Load(&load_error)) {
+    std::cerr << "worker load error: " << load_error << "\n";
+    return 2;
+  }
+  meshnet::worker::FlowLimits limits = LimitsFromEnv();
+  meshnet::worker::ShardRuntimeServiceImpl service(limits, *engine);
+
+  grpc::ServerBuilder builder;
+  int selected_port = 0;
+  builder.AddListeningPort(listen_addr, grpc::InsecureServerCredentials(), &selected_port);
+  // Bounded messages, two layers: a hard transport receive ceiling (never below
+  // 4 MiB so the handshake and normal chunks always fit) plus the finer
+  // app-level per-tensor RESOURCE_EXHAUSTED check the service enforces against
+  // the negotiated max_chunk_bytes. Neither path lets an unbounded frame in.
+  constexpr int kTransportFloor = 4 * 1024 * 1024;
+  const int transport_max = limits.max_chunk_bytes > static_cast<uint64_t>(kTransportFloor)
+                                ? static_cast<int>(limits.max_chunk_bytes)
+                                : kTransportFloor;
+  builder.SetMaxReceiveMessageSize(transport_max);
+  builder.RegisterService(&service);
+  std::unique_ptr<grpc::Server> server(builder.BuildAndStart());
+  if (!server || selected_port == 0) {
+    std::cerr << "failed to bind " << listen_addr << "\n";
+    return 1;
+  }
+
+  int pipe_fds[2];
+  if (::pipe(pipe_fds) != 0) {
+    std::cerr << "failed to create shutdown pipe\n";
+    return 1;
+  }
+  g_signal_pipe_write_fd = pipe_fds[1];
+
+  struct sigaction sa;
+  std::memset(&sa, 0, sizeof(sa));
+  sa.sa_handler = HandleTermination;
+  ::sigaction(SIGTERM, &sa, nullptr);
+  ::sigaction(SIGINT, &sa, nullptr);
+
+  // Drain thread: wakes on the first termination signal and shuts the server
+  // down gracefully so in-flight sessions finish rather than being severed.
+  std::thread drain([&server, read_fd = pipe_fds[0]]() {
+    char byte = 0;
+    ssize_t rc = 0;
+    do {
+      rc = ::read(read_fd, &byte, 1);
+    } while (rc < 0 && errno == EINTR);
+    server->Shutdown();
+  });
+
+  std::cout << "ShardRuntime worker listening on " << listen_addr << std::endl;
+
+  server->Wait();
+  engine->Shutdown();
+  drain.join();
+  ::close(pipe_fds[0]);
+  ::close(pipe_fds[1]);
+  std::cout << "ShardRuntime worker shut down cleanly" << std::endl;
+  return 0;
+}

packages/tracker/meshnet_tracker/capability.py

@@ -190,6 +190,14 @@ class CapabilityState:
     # ("dark"/"certified"), so the network map answers "why is this exact node
     # not routing" without a second query. None when no identity was presented.
     certification: str | None = None
+    memory_capacity_bytes: int | None = None
+    kv_capacity_tokens: int | None = None
+    max_concurrent_sessions: int | None = None
+    measured_tokens_per_second: float | None = None
+    reported_queue_depth: int | None = None
+    seam_latency_ms: float | None = None
+    healthy: bool | None = None
+    reliability: float | None = None
 
     @property
     def proven(self) -> bool:
@@ -233,6 +241,14 @@ class CapabilityState:
             "runtime_recipe_digest": self.runtime_recipe_digest,
             "shard_binding_digest": self.shard_binding_digest,
             "certification": self.certification,
+            "memory_capacity_bytes": self.memory_capacity_bytes,
+            "kv_capacity_tokens": self.kv_capacity_tokens,
+            "max_concurrent_sessions": self.max_concurrent_sessions,
+            "measured_tokens_per_second": self.measured_tokens_per_second,
+            "reported_queue_depth": self.reported_queue_depth,
+            "seam_latency_ms": self.seam_latency_ms,
+            "healthy": self.healthy,
+            "reliability": self.reliability,
         }
 
 
@@ -491,6 +507,13 @@ def _parse_report(doc: Mapping[str, Any]) -> dict:
     if isinstance(schema_version, bool) or not isinstance(schema_version, int):
         raise _ReportError("'schema_version' must be an integer")
 
+    capacity = doc.get("capacity")
+    if capacity is not None:
+        capacity = _object(capacity, "capacity")
+    routing = doc.get("routing")
+    if routing is not None:
+        routing = _object(routing, "routing")
+
     return {
         "model_id": _text(model.get("model_id"), "model.model_id"),
         "shard_start": _index(shard.get("start"), "shard.start"),
@@ -508,6 +531,36 @@ def _parse_report(doc: Mapping[str, Any]) -> dict:
         "validated_at": float(validated_at),
         "schema_version": schema_version,
         "diagnostics": _diagnostics(doc.get("diagnostics")),
+        "memory_capacity_bytes": _optional_positive_int(
+            None if capacity is None else capacity.get("memory_capacity_bytes"),
+            "capacity.memory_capacity_bytes",
+        ),
+        "kv_capacity_tokens": _optional_positive_int(
+            None if capacity is None else capacity.get("kv_capacity_tokens"),
+            "capacity.kv_capacity_tokens",
+        ),
+        "max_concurrent_sessions": _optional_positive_int(
+            None if capacity is None else capacity.get("max_concurrent_sessions"),
+            "capacity.max_concurrent_sessions",
+        ),
+        "measured_tokens_per_second": _optional_positive_float(
+            None if routing is None else routing.get("tokens_per_second"),
+            "routing.tokens_per_second",
+        ),
+        "reported_queue_depth": _optional_nonnegative_int(
+            None if routing is None else routing.get("queue_depth"),
+            "routing.queue_depth",
+        ),
+        "seam_latency_ms": _optional_nonnegative_float(
+            None if routing is None else routing.get("seam_latency_ms"),
+            "routing.seam_latency_ms",
+        ),
+        "healthy": _optional_bool(
+            None if routing is None else routing.get("healthy"), "routing.healthy"
+        ),
+        "reliability": _optional_unit_float(
+            None if routing is None else routing.get("reliability"), "routing.reliability"
+        ),
         "_status": _text(doc.get("status"), "status"),
     }
 
@@ -536,6 +589,53 @@ def _index(value: Any, field_name: str) -> int:
     return value
 
 
+def _optional_positive_int(value: Any, field_name: str) -> int | None:
+    if value is None:
+        return None
+    if isinstance(value, bool) or not isinstance(value, int) or value < 1:
+        raise _ReportError(f"{field_name!r} must be a positive integer")
+    return value
+
+
+def _optional_nonnegative_int(value: Any, field_name: str) -> int | None:
+    if value is None:
+        return None
+    if isinstance(value, bool) or not isinstance(value, int) or value < 0:
+        raise _ReportError(f"{field_name!r} must be a non-negative integer")
+    return value
+
+
+def _optional_positive_float(value: Any, field_name: str) -> float | None:
+    if value is None:
+        return None
+    if isinstance(value, bool) or not isinstance(value, (int, float)) or value <= 0:
+        raise _ReportError(f"{field_name!r} must be a positive number")
+    return float(value)
+
+
+def _optional_nonnegative_float(value: Any, field_name: str) -> float | None:
+    if value is None:
+        return None
+    if isinstance(value, bool) or not isinstance(value, (int, float)) or value < 0:
+        raise _ReportError(f"{field_name!r} must be a non-negative number")
+    return float(value)
+
+
+def _optional_bool(value: Any, field_name: str) -> bool | None:
+    if value is None:
+        return None
+    if not isinstance(value, bool):
+        raise _ReportError(f"{field_name!r} must be a boolean")
+    return value
+
+
+def _optional_unit_float(value: Any, field_name: str) -> float | None:
+    parsed = _optional_nonnegative_float(value, field_name)
+    if parsed is not None and parsed > 1:
+        raise _ReportError(f"{field_name!r} must be a number from 0 to 1")
+    return parsed
+
+
 def _maybe_int(value: Any) -> int | None:
     if isinstance(value, bool) or not isinstance(value, int):
         return None

packages/tracker/meshnet_tracker/server.py

@@ -4684,6 +4684,11 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
             friendly_name=friendly_name,
             capability=capability,
         )
+        # A report may seed the same load/throughput inputs that legacy nodes
+        # supply through registration and heartbeats.  The optional block is
+        # backend-neutral; routing still applies its usual queue adjustment.
+        if capability.reported_queue_depth is not None:
+            entry.queue_depth = capability.reported_queue_depth
         with server.lock:
             self._purge_expired_nodes()
             # Dedup: replace the same node id or the same endpoint+model assignment.

tests/test_architecture_boundary.py

@@ -14,7 +14,7 @@ from meshnet_node.architecture_boundary import (
     TailOutput,
     adapter_for,
 )
-from meshnet_node.native_protocol import ProtocolError, decode_bundle
+from meshnet_node.native_protocol import ProtocolError, decode_bundle, encode_bundle, encode_tensor, pb
 
 
 def _f32(values: list[float]) -> bytes:
@@ -119,3 +119,29 @@ def test_typed_tail_result_binds_sampling_and_request_recipe_identity() -> None:
     assert result.sampled_token_id == 42
     assert result.output_kind == "sampled_token_id"
     assert result.message.WhichOneof("output") == "sampled_token_id"
+
+
+def test_typed_tail_result_accepts_validated_logits_under_the_explicit_contract() -> None:
+    adapter = adapter_for(Architecture.DENSE)
+    identity = ProtocolIdentity(
+        request_id="request-1",
+        runtime_recipe_digest="sha256:recipe",
+        chat_template_id="llama3",
+        chat_template_version="2",
+        reasoning_mode="max",
+        architecture=Architecture.DENSE,
+    )
+    logits = encode_bundle(
+        [encode_tensor("logits", _f32([0.1, 0.9]), [1, 2], pb.DTYPE_FLOAT32)],
+        architecture=adapter.protocol_architecture,
+        boundary_point="dense.tail.logits.v1",
+    )
+
+    result = adapter.tail_result(
+        identity=identity,
+        sampling=SamplingParameters(temperature=0.7, top_p=0.9, top_k=20, seed=9),
+        output=TailOutput.logits(logits),
+    )
+
+    assert result.output_kind == "logits"
+    assert result.message.WhichOneof("output") == "logits"

tests/test_dense_range_boundary.py

@@ -0,0 +1,87 @@
+"""DGR-035 dense range boundary execution contract."""
+
+from __future__ import annotations
+
+import struct
+
+import pytest
+
+from meshnet_node.architecture_boundary import (
+    DENSE_LLAMA_ARCHITECTURE,
+    DENSE_RESIDUAL_BOUNDARY_V1,
+    DenseLayerRange,
+    DenseRangeBoundaryExecutor,
+    TailOutput,
+)
+from meshnet_node.native_protocol import HIDDEN_STATES, ProtocolError
+from meshnet_node.shard_engine import BoundaryBundle, EngineTensor
+
+
+def _tensor(values: tuple[float, ...]) -> EngineTensor:
+    return EngineTensor(HIDDEN_STATES, (1, len(values)), "f32", struct.pack("<" + "f" * len(values), *values))
+
+
+def _values(tensor: EngineTensor) -> tuple[float, ...]:
+    return struct.unpack("<" + "f" * (len(tensor.data) // 4), tensor.data)
+
+
+def _embed(token_ids: tuple[int, ...]) -> EngineTensor:
+    return _tensor(tuple(float(token) for token in token_ids))
+
+
+def _layers(residual: EngineTensor) -> EngineTensor:
+    return _tensor(tuple(value + 10.0 for value in _values(residual)))
+
+
+def test_head_and_middle_handoff_the_same_unnormalized_named_residual() -> None:
+    head = DenseRangeBoundaryExecutor(DenseLayerRange(0, 1, 4), embed_tokens=_embed, run_layers=_layers)
+    middle = DenseRangeBoundaryExecutor(DenseLayerRange(2, 2, 4), embed_tokens=_embed, run_layers=_layers)
+
+    head_out = head.execute(token_ids=(1, 2))
+    assert isinstance(head_out, BoundaryBundle)
+    assert head_out.architecture == DENSE_LLAMA_ARCHITECTURE
+    assert head_out.boundary_point == DENSE_RESIDUAL_BOUNDARY_V1
+    assert _values(head_out.tensors[0]) == (11.0, 12.0)
+
+    middle_out = middle.execute(boundary=head_out)
+    assert isinstance(middle_out, BoundaryBundle)
+    # The raw residual is carried through. No tail norm/output or row pruning
+    # can run because this executor has no tail callback.
+    assert _values(middle_out.tensors[0]) == (21.0, 22.0)
+
+
+def test_tail_bypasses_embedding_and_has_an_explicit_sampled_output_contract() -> None:
+    tail = DenseRangeBoundaryExecutor(
+        DenseLayerRange(3, 3, 4),
+        embed_tokens=_embed,
+        run_layers=_layers,
+        tail_output=lambda residual: TailOutput.sampled_token(int(sum(_values(residual)))),
+    )
+    boundary = BoundaryBundle((_tensor((3.0, 4.0)),), DENSE_LLAMA_ARCHITECTURE, DENSE_RESIDUAL_BOUNDARY_V1)
+
+    result = tail.execute(boundary=boundary)
+    assert result == TailOutput.sampled_token(27)
+    with pytest.raises(ProtocolError, match="requires"):
+        tail.execute(token_ids=(3,))
+
+
+def test_uncertified_architecture_and_incompatible_schema_fail_closed() -> None:
+    with pytest.raises(ProtocolError, match="only certifies"):
+        DenseLayerRange(0, 0, 1, architecture="unchecked")
+
+    middle = DenseRangeBoundaryExecutor(DenseLayerRange(1, 1, 3), embed_tokens=_embed, run_layers=_layers)
+    bad_architecture = BoundaryBundle((_tensor((1.0,)),), "moe", DENSE_RESIDUAL_BOUNDARY_V1)
+    with pytest.raises(ProtocolError, match="not certified"):
+        middle.execute(boundary=bad_architecture)
+    bad_schema = BoundaryBundle((_tensor((1.0,)),), DENSE_LLAMA_ARCHITECTURE, "post_middle_residual")
+    with pytest.raises(ProtocolError, match="incompatible"):
+        middle.execute(boundary=bad_schema)
+
+
+def test_only_tail_can_be_given_final_norm_and_output_ownership() -> None:
+    with pytest.raises(ProtocolError, match="only a dense tail"):
+        DenseRangeBoundaryExecutor(
+            DenseLayerRange(0, 1, 4), embed_tokens=_embed, run_layers=_layers, tail_output=TailOutput.sampled_token
+        )
+    with pytest.raises(ProtocolError, match="only a dense tail"):
+        DenseRangeBoundaryExecutor(DenseLayerRange(3, 3, 4), embed_tokens=_embed, run_layers=_layers)

tests/test_llama_shard_worker_binding.py

@@ -0,0 +1,63 @@
+"""DGR-037 structural guardrails for the standalone llama.cpp worker.
+
+The real GGUF lane is opt-in and needs a mounted artifact; these tests keep the
+default suite model-download-free while guarding the integration shape that a
+later real-model harness exercises.
+"""
+
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+WORKER = ROOT / "packages/node/native/worker"
+
+
+def test_worker_uses_the_private_llama_shardengine_not_the_fixture_engine():
+    service_header = (WORKER / "shard_service.h").read_text(encoding="utf-8")
+    service = (WORKER / "shard_service.cpp").read_text(encoding="utf-8")
+    engine = (WORKER / "llama_shard_engine.cpp").read_text(encoding="utf-8")
+    assert '#include "llama_shard_engine.h"' in service_header
+    assert "FakeShardEngine" not in service_header
+    assert "engine_.Execute(" in service
+    assert "llama_model_load_from_file" in engine
+    assert "llama_model_meshnet_range_report" in engine
+
+
+def test_worker_configuration_and_death_hook_are_explicit_and_opt_in():
+    main = (WORKER / "shard_worker_main.cpp").read_text(encoding="utf-8")
+    for name in (
+        "MESHNET_MODEL_ARTIFACT",
+        "MESHNET_MODEL_ARTIFACT_DIGEST",
+        "MESHNET_RUNTIME_RECIPE_DIGEST",
+        "MESHNET_SHARD_START_LAYER",
+        "MESHNET_SHARD_END_LAYER",
+        "MESHNET_INJECT_PROCESS_DEATH_AFTER_EXECUTIONS",
+    ):
+        assert name in main
+    assert "engine->Shutdown()" in main
+
+
+def test_identity_is_loaded_not_stream_supplied_and_health_reports_it():
+    source = (WORKER / "shard_service.cpp").read_text(encoding="utf-8")
+    assert "r.start_layer() == engine_.identity().start_layer" in source
+    assert "r.end_layer() == engine_.identity().end_layer" in source
+    assert "model artifact or runtime recipe digest does not match" in source
+    assert "resident_bytes" in source
+    assert '" range=["' in source
+
+
+def test_hot_kv_is_bounded_and_keyed_by_route_session_and_epoch():
+    engine = (WORKER / "llama_shard_engine.cpp").read_text(encoding="utf-8")
+    header = (WORKER / "llama_shard_engine.h").read_text(encoding="utf-8")
+    service = (WORKER / "shard_service.cpp").read_text(encoding="utf-8")
+    main = (WORKER / "shard_worker_main.cpp").read_text(encoding="utf-8")
+    assert "struct SessionKey" in engine
+    assert "uint64_t route_epoch" in engine
+    assert "llama_init_from_model" in engine
+    assert "llama_memory_seq_rm" in engine
+    assert "EvictExpiredLocked" in engine
+    assert "EvictLruLocked" in engine
+    assert "HotKvStatus::kCacheMiss" in service
+    assert "ERROR_CODE_CACHE_MISS" in service
+    assert "MESHNET_HOT_KV_BUDGET_TOKENS" in main
+    assert "HotKvStep" in header

tests/test_meshnet_range_report_tool.py

@@ -0,0 +1,275 @@
+"""DGR-034: end-to-end owned-range loads through the native report tool.
+
+Gated on the built ``meshnet-range-report`` binary (the deterministic
+CPU-only native lane builds it from the pinned, patched llama.cpp tree); in
+an environment without that build these tests skip rather than fake a pass.
+When the binary is present they run real loads of a tiny synthetic
+dense-Llama GGUF — no model download, no GPU — and prove the loader
+registers exactly the owned tensors, reports ownership derived from the
+loaded state, and rejects invalid/out-of-model ranges and missing required
+tensors. The JSON is consumed through ``meshnet_node.range_report`` so the
+strict project-owned contract is exercised on real tool output.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import struct
+import subprocess
+import sys
+from pathlib import Path
+
+import pytest
+
+from meshnet_node.range_report import RangeReportError, parse_owned_range_report
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+DEFAULT_BINARY = REPO_ROOT / "build" / "llama.cpp" / "build" / "bin" / "meshnet-range-report"
+
+BINARY = Path(os.environ.get("MESHNET_RANGE_REPORT_BIN", DEFAULT_BINARY))
+
+requires_range_report_tool = pytest.mark.skipif(
+    not BINARY.is_file(),
+    reason=(
+        "meshnet-range-report is not built; run the deterministic native lane "
+        "(scripts/llama_cpp_dependency.py build) to enable these tests"
+    ),
+)
+
+# --- Minimal GGUF v3 writer, mirroring the model-free native fixture --------
+
+K_LAYERS = 4
+K_EMBD = 8
+K_FFN = 16
+K_VOCAB = 16
+ALIGNMENT = 32
+
+_GGUF_UINT32 = 4
+_GGUF_FLOAT32 = 6
+_GGUF_STRING = 8
+_GGML_TYPE_F32 = 0
+
+
+def _gguf_string(value: str) -> bytes:
+    data = value.encode("utf-8")
+    return struct.pack("<Q", len(data)) + data
+
+
+def _metadata_entries() -> list[tuple[str, int, object]]:
+    return [
+        ("general.architecture", _GGUF_STRING, "llama"),
+        ("general.alignment", _GGUF_UINT32, ALIGNMENT),
+        ("llama.context_length", _GGUF_UINT32, 16),
+        ("llama.embedding_length", _GGUF_UINT32, K_EMBD),
+        ("llama.block_count", _GGUF_UINT32, K_LAYERS),
+        ("llama.feed_forward_length", _GGUF_UINT32, K_FFN),
+        ("llama.attention.head_count", _GGUF_UINT32, 2),
+        ("llama.attention.head_count_kv", _GGUF_UINT32, 2),
+        ("llama.rope.dimension_count", _GGUF_UINT32, 4),
+        ("llama.attention.layer_norm_rms_epsilon", _GGUF_FLOAT32, 1.0e-5),
+        ("tokenizer.ggml.model", _GGUF_STRING, "no_vocab"),
+        ("llama.vocab_size", _GGUF_UINT32, K_VOCAB),
+    ]
+
+
+def _fixture_tensors() -> list[tuple[str, tuple[int, ...]]]:
+    tensors: list[tuple[str, tuple[int, ...]]] = [
+        ("token_embd.weight", (K_EMBD, K_VOCAB)),
+        ("output_norm.weight", (K_EMBD,)),
+        ("output.weight", (K_EMBD, K_VOCAB)),
+    ]
+    for layer in range(K_LAYERS):
+        prefix = f"blk.{layer}."
+        tensors += [
+            (prefix + "attn_norm.weight", (K_EMBD,)),
+            (prefix + "attn_q.weight", (K_EMBD, K_EMBD)),
+            (prefix + "attn_k.weight", (K_EMBD, K_EMBD)),
+            (prefix + "attn_v.weight", (K_EMBD, K_EMBD)),
+            (prefix + "attn_output.weight", (K_EMBD, K_EMBD)),
+            (prefix + "ffn_norm.weight", (K_EMBD,)),
+            (prefix + "ffn_gate.weight", (K_EMBD, K_FFN)),
+            (prefix + "ffn_down.weight", (K_FFN, K_EMBD)),
+            (prefix + "ffn_up.weight", (K_EMBD, K_FFN)),
+        ]
+    return tensors
+
+
+def write_dense_llama_gguf(path: Path, *, drop: frozenset[str] = frozenset()) -> Path:
+    """Write a tiny dense-Llama GGUF; ``drop`` omits tensors (corruption cases)."""
+    kvs = _metadata_entries()
+    tensors = [(name, dims) for name, dims in _fixture_tensors() if name not in drop]
+
+    blob = bytearray()
+    blob += b"GGUF" + struct.pack("<IQQ", 3, len(tensors), len(kvs))
+    for key, vtype, value in kvs:
+        blob += _gguf_string(key)
+        blob += struct.pack("<I", vtype)
+        if vtype == _GGUF_STRING:
+            blob += _gguf_string(value)  # type: ignore[arg-type]
+        elif vtype == _GGUF_UINT32:
+            blob += struct.pack("<I", value)  # type: ignore[arg-type]
+        elif vtype == _GGUF_FLOAT32:
+            blob += struct.pack("<f", value)  # type: ignore[arg-type]
+        else:  # pragma: no cover - writer guard
+            raise AssertionError(f"unhandled kv type {vtype}")
+
+    offset = 0
+    infos = bytearray()
+    data = bytearray()
+    for name, dims in tensors:
+        infos += _gguf_string(name)
+        infos += struct.pack("<I", len(dims))
+        for dim in dims:
+            infos += struct.pack("<Q", dim)
+        infos += struct.pack("<IQ", _GGML_TYPE_F32, offset)
+        size = 4
+        for dim in dims:
+            size *= dim
+        assert size % ALIGNMENT == 0
+        data += bytes(size)
+        offset += size
+
+    blob += infos
+    blob += bytes(-len(blob) % ALIGNMENT)  # pad header to the data section
+    blob += data
+    path.write_bytes(bytes(blob))
+    return path
+
+
+# --- Tool driver -------------------------------------------------------------
+
+LAYER_BYTES = 2624  # 9 registered F32 tensors per layer, see _fixture_tensors
+EMBD_BYTES = 512
+OUT_NORM_BYTES = 32
+OUT_BYTES = 512
+
+
+def run_tool(model: Path, start: int, end: int, *extra: str) -> tuple[int, dict]:
+    env = dict(os.environ)
+    env["LD_LIBRARY_PATH"] = f"{BINARY.parent}:{env.get('LD_LIBRARY_PATH', '')}"
+    completed = subprocess.run(
+        [
+            str(BINARY),
+            "--model", str(model),
+            "--start", str(start),
+            "--end", str(end),
+            *extra,
+        ],
+        capture_output=True,
+        text=True,
+        env=env,
+        timeout=120,
+    )
+    try:
+        doc = json.loads(completed.stdout)
+    except json.JSONDecodeError as exc:  # pragma: no cover - diagnostic path
+        raise AssertionError(
+            f"tool did not print a JSON report (exit {completed.returncode}): "
+            f"{completed.stdout!r} {completed.stderr!r}"
+        ) from exc
+    return completed.returncode, doc
+
+
+@pytest.fixture(scope="module")
+def dense_llama_gguf(tmp_path_factory: pytest.TempPathFactory) -> Path:
+    return write_dense_llama_gguf(tmp_path_factory.mktemp("gguf") / "dense-llama.gguf")
+
+
+@requires_range_report_tool
+class TestOwnedRangeLoads:
+    def test_middle_range_registers_exactly_its_layers(self, dense_llama_gguf: Path) -> None:
+        code, doc = run_tool(dense_llama_gguf, 1, 3, "--no-extra-bufts")
+        assert code == 0
+        report = parse_owned_range_report(doc)
+        assert (report.start_layer, report.end_layer) == (1, 3)
+        assert report.registered_tensors == 18
+        assert report.registered_bytes == 2 * LAYER_BYTES
+        # The fixture layers are contiguous in the file, so the pure mmap span
+        # is exactly the owned tensor bytes — scaled down from the artifact.
+        assert report.mapped_bytes == 2 * LAYER_BYTES
+        assert report.mapped_bytes < report.file_bytes
+
+    def test_head_range_owns_embeddings(self, dense_llama_gguf: Path) -> None:
+        code, doc = run_tool(dense_llama_gguf, 0, 1)
+        assert code == 0
+        report = parse_owned_range_report(doc)
+        assert report.is_head and report.has_token_embeddings
+        assert not report.has_output_head
+        assert report.registered_tensors == 10
+        assert report.registered_bytes == EMBD_BYTES + LAYER_BYTES
+
+    def test_tail_range_owns_norm_and_output(self, dense_llama_gguf: Path) -> None:
+        code, doc = run_tool(dense_llama_gguf, 3, 4)
+        assert code == 0
+        report = parse_owned_range_report(doc)
+        assert report.is_tail and report.has_output_head
+        assert not report.has_token_embeddings
+        assert report.registered_tensors == 11
+        assert report.registered_bytes == LAYER_BYTES + OUT_NORM_BYTES + OUT_BYTES
+
+    def test_shards_partition_the_whole_model_bytes(self, dense_llama_gguf: Path) -> None:
+        shards = [(0, 1), (1, 3), (3, 4)]
+        registered = []
+        for start, end in shards:
+            code, doc = run_tool(dense_llama_gguf, start, end)
+            assert code == 0
+            registered.append(parse_owned_range_report(doc).registered_bytes)
+        code, doc = run_tool(dense_llama_gguf, 0, 4)
+        assert code == 0
+        whole = parse_owned_range_report(doc)
+        assert whole.registered_tensors == 3 + 9 * K_LAYERS
+        assert sum(registered) == whole.registered_bytes
+
+    def test_non_mmap_load_scales_resident_with_the_range(self, dense_llama_gguf: Path) -> None:
+        code, doc = run_tool(dense_llama_gguf, 1, 3, "--no-mmap")
+        assert code == 0
+        report = parse_owned_range_report(doc)
+        assert report.mapped_bytes == 0
+        assert report.registered_bytes == 2 * LAYER_BYTES
+        code, doc = run_tool(dense_llama_gguf, 0, 4, "--no-mmap")
+        assert code == 0
+        whole = parse_owned_range_report(doc)
+        assert report.resident_bytes < whole.resident_bytes
+
+
+@requires_range_report_tool
+class TestRangeRejection:
+    def test_out_of_model_range_is_refused(self, dense_llama_gguf: Path) -> None:
+        code, doc = run_tool(dense_llama_gguf, 3, 5)
+        assert code == 3 and doc["ok"] is False
+        with pytest.raises(RangeReportError):
+            parse_owned_range_report(doc)
+
+    def test_empty_range_is_refused(self, dense_llama_gguf: Path) -> None:
+        code, doc = run_tool(dense_llama_gguf, 2, 2)
+        assert code == 3 and doc["ok"] is False
+
+    def test_inverted_range_is_refused(self, dense_llama_gguf: Path) -> None:
+        code, doc = run_tool(dense_llama_gguf, 3, 1)
+        assert code == 3 and doc["ok"] is False
+
+    def test_missing_required_owned_tensor_is_refused(self, tmp_path: Path) -> None:
+        corrupted = write_dense_llama_gguf(
+            tmp_path / "missing-tensor.gguf", drop=frozenset({"blk.1.attn_q.weight"})
+        )
+        code, doc = run_tool(corrupted, 0, 2)
+        assert code == 3 and doc["ok"] is False
+        assert "blk.1.attn_q.weight" in doc["error"]
+
+    def test_whole_model_load_still_works_through_the_range_loader(
+        self, dense_llama_gguf: Path
+    ) -> None:
+        code, doc = run_tool(dense_llama_gguf, 0, 4)
+        assert code == 0
+        report = parse_owned_range_report(doc)
+        assert report.is_head and report.is_tail
+        assert report.has_token_embeddings and report.has_output_head
+
+
+def test_tool_binary_gate_points_at_the_locked_build() -> None:
+    # The gate must name the deterministic lane's output, never a downloaded binary.
+    assert DEFAULT_BINARY.name == "meshnet-range-report"
+    assert "llama.cpp" in DEFAULT_BINARY.parts
+    assert DEFAULT_BINARY.parent.name == "bin"
+    assert DEFAULT_BINARY.parent.parent.name == "build"

tests/test_native_activation_seam.py

@@ -0,0 +1,159 @@
+"""DGR-042 seam tests with a deterministic fake generated worker."""
+
+from __future__ import annotations
+
+from collections.abc import Iterator
+import threading
+
+import pytest
+
+from meshnet_node.native_activation_seam import (
+    NATIVE_RELAY_PATH,
+    NativeActivationBufferFull,
+    NativeActivationDisconnected,
+    NativeActivationSeam,
+    NativeFrameContext,
+)
+from meshnet_node.native_protocol import pb
+
+
+def _context(**changes: object) -> NativeFrameContext:
+    values: dict[str, object] = dict(
+        request_id="billing-request-7", node_id="node-tail", route_session_id="route-9",
+        route_epoch=4, work_id="work-3", deadline_unix_nanos=987654321,
+    )
+    values.update(changes)
+    return NativeFrameContext(**values)
+
+
+def _open() -> pb.SessionRequest:
+    return pb.SessionRequest(open=pb.SessionOpen(
+        schema_version=pb.SCHEMA_VERSION_1, route_session_id="route-9", route_epoch=4,
+    ))
+
+
+def _chunk() -> pb.SessionRequest:
+    return pb.SessionRequest(chunk=pb.ActivationChunk(envelope=pb.Envelope(
+        schema_version=pb.SCHEMA_VERSION_1, route_session_id="route-9", route_epoch=4,
+        work_id="work-3", deadline_unix_nanos=987654321,
+    )))
+
+
+def _ack(request: pb.SessionRequest) -> pb.SessionResponse:
+    if request.WhichOneof("kind") == "open":
+        return pb.SessionResponse(accepted=pb.SessionAccepted(
+            schema_version=pb.SCHEMA_VERSION_1, route_session_id="route-9", route_epoch=4,
+        ))
+    route, epoch, work, _ = ("route-9", 4, "work-3", 0)
+    del route, epoch
+    return pb.SessionResponse(ack=pb.Ack(work_id=work, idempotency_step=1))
+
+
+class _FakeGrpcWorker:
+    def __init__(self, *, block: bool = False) -> None:
+        self.calls = 0
+        self.received: list[pb.SessionRequest] = []
+        self.started = threading.Event()
+        self.consumed = threading.Event()
+        self.release = threading.Event()
+        self.block = block
+
+    def Session(self, requests: Iterator[pb.SessionRequest]):
+        self.calls += 1
+        self.started.set()
+        for request in requests:
+            self.received.append(request)
+            self.consumed.set()
+            if self.block:
+                self.release.wait(1)
+            yield _ack(request)
+
+
+def test_direct_uses_one_long_lived_grpc_stream_and_preserves_correlation():
+    worker = _FakeGrpcWorker()
+    telemetry = []
+    seam = NativeActivationSeam(_context(), direct_stub=worker, telemetry=telemetry.append)
+    try:
+        seam.send(_open())
+        seam.send(_chunk())
+        assert seam.receive(1).WhichOneof("kind") == "accepted"
+        assert seam.receive(1).ack.work_id == "work-3"
+        assert worker.calls == 1
+        assert [frame.SerializeToString() for frame in worker.received] == [
+            _open().SerializeToString(), _chunk().SerializeToString()
+        ]
+        assert telemetry[-1].request_id == "billing-request-7"
+        assert telemetry[-1].node_id == "node-tail"
+    finally:
+        seam.close()
+
+
+def test_relay_carries_byte_identical_protobuf_frames_and_all_correlation_headers():
+    captured: list[tuple[str, bytes, dict[str, str]]] = []
+
+    def relay(path: str, body: bytes, headers: dict[str, str]):
+        captured.append((path, body, headers))
+        request = pb.SessionRequest()
+        request.ParseFromString(body)
+        return 200, {}, _ack(request).SerializeToString()
+
+    seam = NativeActivationSeam(_context(), relay_request=relay)
+    response = seam.send(_chunk())
+    assert response is not None and response.ack.work_id == "work-3"
+    path, body, headers = captured[0]
+    assert path == NATIVE_RELAY_PATH
+    assert body == _chunk().SerializeToString()
+    assert headers == {
+        "Content-Type": "application/x-protobuf", "X-Meshnet-Native-Frame": "shard-runtime/v1",
+        "X-Meshnet-Request-Id": "billing-request-7", "X-Meshnet-Node-Id": "node-tail",
+        "X-Meshnet-Session": "route-9", "X-Meshnet-Route-Epoch": "4",
+        "X-Meshnet-Work-Id": "work-3", "X-Meshnet-Deadline-Unix-Nanos": "987654321",
+        "X-Meshnet-Activation-Id": "billing-request-7",
+    }
+
+
+def test_relay_disconnect_is_uncertain_and_is_never_replayed():
+    calls = 0
+
+    def disconnected(*_):
+        nonlocal calls
+        calls += 1
+        raise OSError("relay vanished")
+
+    seam = NativeActivationSeam(_context(), relay_request=disconnected)
+    with pytest.raises(NativeActivationDisconnected, match="uncertain"):
+        seam.send(_chunk())
+    with pytest.raises(NativeActivationDisconnected):
+        seam.send(_chunk())
+    assert calls == 1
+
+
+def test_cancellation_uses_the_same_opaque_relay_contract():
+    received = []
+
+    def relay(_path, body, _headers):
+        request = pb.SessionRequest()
+        request.ParseFromString(body)
+        received.append(request)
+        return 200, {}, pb.SessionResponse(ack=pb.Ack(work_id="work-3")).SerializeToString()
+
+    seam = NativeActivationSeam(_context(), relay_request=relay)
+    response = seam.cancel("client disconnected")
+    assert response is not None
+    assert received[0].cancel.work_id == "work-3"
+    assert received[0].cancel.reason == "client disconnected"
+
+
+def test_direct_request_buffer_is_bounded():
+    worker = _FakeGrpcWorker(block=True)
+    seam = NativeActivationSeam(_context(), direct_stub=worker, max_buffered_frames=1)
+    try:
+        assert worker.started.wait(1)
+        seam.send(_open())
+        assert worker.consumed.wait(1)
+        seam.send(_chunk())
+        with pytest.raises(NativeActivationBufferFull):
+            seam.send(_chunk())
+    finally:
+        worker.release.set()
+        seam.close()

tests/test_native_registration.py

@@ -0,0 +1,142 @@
+"""DGR-041 native capability registration remains an ordinary admission payload."""
+
+from __future__ import annotations
+
+from types import SimpleNamespace
+
+from meshnet_node.capability import ExecutionCapacity, RoutingMeasurements
+from meshnet_node.native_registration import (
+    NativeCapabilityRegistrar,
+    NativeRegistrationError,
+    NativeShardRegistration,
+)
+from meshnet_node.native_worker_supervisor import NativeWorkerProbe, NativeWorkerSpec
+from meshnet_node.runtime_recipe import ShardIdentity
+from meshnet_tracker.capability import CapabilityState, STATE_ADMITTED, STATE_UNCERTIFIED
+from meshnet_tracker.server import TrackerServer, _capability_from_registration, _select_route
+
+from test_runtime_recipe_identity import _identity
+
+
+def _worker(identity: ShardIdentity) -> tuple[NativeWorkerSpec, NativeWorkerProbe]:
+    spec = NativeWorkerSpec(
+        binary=__file__, binary_digest="d" * 64, listen_address="127.0.0.1:1",
+        artifact_path=__file__, artifact_digest=identity.fingerprint.model_artifact_digest,
+        recipe_digest=identity.fingerprint.runtime_recipe_digest, recipe_id=identity.recipe.recipe_id,
+        recipe_version=identity.recipe.recipe_version, catalogue_version=identity.recipe.catalogue_version,
+        shard_start=identity.shard_start, shard_end=identity.shard_end,
+    )
+    probe = NativeWorkerProbe(
+        artifact_digest=spec.artifact_digest, recipe_digest=spec.recipe_digest,
+        recipe_id=spec.recipe_id, recipe_version=spec.recipe_version,
+        catalogue_version=spec.catalogue_version, shard_start=spec.shard_start,
+        shard_end=spec.shard_end, serving=True,
+    )
+    return spec, probe
+
+
+def test_native_registration_carries_exact_identity_range_capacity_and_dark_status():
+    identity = _identity()
+    worker, probe = _worker(identity)
+    registration = NativeShardRegistration(
+        endpoint="http://native.example:8080", model_id=identity.artifact.artifact_id,
+        identity=identity, worker=worker, probe=probe, device="cpu:fixture",
+        capacity=ExecutionCapacity(4096, 8192, 3), duration_ms=7,
+        routing=RoutingMeasurements(
+            tokens_per_second=12.5, queue_depth=2, seam_latency_ms=3.5,
+            healthy=True, reliability=0.99,
+        ),
+    )
+
+    payload = registration.payload()
+    report = payload["capability_report"]
+    assert report["identity"]["fingerprint"]["runtime_recipe_digest"] == identity.fingerprint.runtime_recipe_digest
+    assert report["shard"] == {"start": identity.shard_start, "end": identity.shard_end - 1}
+    assert report["backend"]["backend_id"] == identity.recipe.axes["backend_id"]
+    assert report["capacity"] == {
+        "memory_capacity_bytes": 4096, "kv_capacity_tokens": 8192, "max_concurrent_sessions": 3,
+    }
+    assert report["routing"] == {
+        "tokens_per_second": 12.5, "queue_depth": 2, "seam_latency_ms": 3.5,
+        "healthy": True, "reliability": 0.99,
+    }
+    assert payload["benchmark_tokens_per_sec"] == 12.5
+    assert payload["queue_depth"] == 2
+
+    tracker = TrackerServer()
+    state = _capability_from_registration(
+        payload, model=payload["model"], hf_repo=payload["hf_repo"],
+        shard_start=payload["shard_start"], shard_end=payload["shard_end"],
+        recipe_certifications=tracker._recipe_certifications,
+    )
+    assert state.state == STATE_UNCERTIFIED
+    assert state.certification == "dark"
+    assert state.memory_capacity_bytes == 4096
+    assert state.kv_capacity_tokens == 8192
+    assert state.max_concurrent_sessions == 3
+    assert state.measured_tokens_per_second == 12.5
+    assert state.reported_queue_depth == 2
+    assert state.seam_latency_ms == 3.5
+    assert state.healthy is True
+    assert state.reliability == 0.99
+
+
+def test_native_registrar_has_no_tracker_or_backend_policy_of_its_own():
+    identity = _identity()
+    worker, probe = _worker(identity)
+    registration = NativeShardRegistration(
+        endpoint="http://native.example", model_id=identity.artifact.artifact_id, identity=identity,
+        worker=worker, probe=probe, device="cpu", capacity=ExecutionCapacity(1, 1, 1),
+    )
+    published: list[dict] = []
+    withdrawn: list[str] = []
+    registrar = NativeCapabilityRegistrar(registration, register=published.append, withdraw=withdrawn.append)
+    registrar.publish()
+    registrar.unavailable("worker exited")
+    assert published[0]["capability_report"]["backend"]["backend_id"] == identity.recipe.axes["backend_id"]
+    assert withdrawn == ["worker exited"]
+
+
+def test_native_registration_refuses_a_probe_for_a_different_range():
+    identity = _identity()
+    worker, probe = _worker(identity)
+    wrong = NativeWorkerProbe(**{**probe.__dict__, "shard_end": probe.shard_end + 1})
+    try:
+        NativeShardRegistration(
+            endpoint="http://native.example", model_id=identity.artifact.artifact_id, identity=identity,
+            worker=worker, probe=wrong, device="cpu", capacity=ExecutionCapacity(1, 1, 1),
+        )
+    except NativeRegistrationError:
+        return
+    raise AssertionError("different worker range must not register")
+
+
+def _candidate(
+    node_id: str, start: int, end: int, fingerprint: tuple[str, str], *, state: str = STATE_ADMITTED
+) -> SimpleNamespace:
+    return SimpleNamespace(
+        node_id=node_id, endpoint=f"http://{node_id}", model="generic-model", hf_repo=None,
+        shard_start=start, shard_end=end, benchmark_tokens_per_sec=10.0,
+        model_tokens_per_sec={}, queue_depth=0, proxy_inflight=0, wallet_address=None,
+        capability=CapabilityState(
+            state=state, shard_start=start, shard_end=end,
+            model_artifact_digest=fingerprint[0], runtime_recipe_digest=fingerprint[1],
+        ),
+    )
+
+
+def test_existing_route_formation_requires_exact_compatible_coverage_and_excludes_dark_nodes():
+    """Routing consumes generic fingerprints and admission states, not GGUF policy."""
+    exact = ("a" * 64, "b" * 64)
+    other = ("c" * 64, "d" * 64)
+    compatible_head = _candidate("head", 0, 3, exact)
+    compatible_tail = _candidate("tail", 4, 7, exact)
+    dark_head = _candidate("dark", 0, 7, exact, state=STATE_UNCERTIFIED)
+
+    route, error = _select_route([dark_head, compatible_head, compatible_tail], 0, 7)
+    assert error == ""
+    assert [node.node_id for node in route] == ["head", "tail"]
+
+    route, error = _select_route([compatible_head, _candidate("wrong", 4, 7, other)], 0, 7)
+    assert route == []
+    assert "covers layer 4" in error

tests/test_native_shard_worker.py

@@ -0,0 +1,702 @@
+"""DGR-033 integration tests for the standalone native C++ Shard worker.
+
+These tests spawn the *real* compiled ``shard_worker`` executable as a separate
+OS process, connect to its real localhost socket with the committed generated
+``ShardRuntimeStub`` stubs, and drive the complete lifecycle/stream contract.
+There is no in-memory channel, no Python servicer, and no fake transport: the
+server under test is the C++ binary DGR-033 builds.
+
+The worker binary is located via ``MESHNET_SHARD_WORKER_BIN`` or the default
+out-of-tree build path ``build/native/shard_worker``. When it has not been
+built (a default developer/CI checkout without the pinned gRPC C++ toolchain),
+every test here is skipped rather than failed — the same ``requires_cmake``
+gating pattern DGR-029/DGR-030 use for native-build-dependent tests. The
+session that implemented DGR-033 built the binary and ran these for real; see
+``evidence/DGR-033/README.md`` for the exact commands and results.
+"""
+
+from __future__ import annotations
+
+import os
+import signal
+import socket
+import subprocess
+import time
+import zlib
+
+import grpc
+import pytest
+
+REPO_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+_PYTHONPATH = os.pathsep.join(
+    [os.path.join(REPO_ROOT, "packages", "node"), os.path.join(REPO_ROOT, "packages", "tracker")]
+)
+
+from meshnet_node.native_protocol.generated import (  # noqa: E402
+    shard_runtime_pb2 as pb,
+    shard_runtime_pb2_grpc as pb_grpc,
+)
+
+
+def _worker_binary() -> str | None:
+    explicit = os.environ.get("MESHNET_SHARD_WORKER_BIN")
+    if explicit and os.path.exists(explicit):
+        return explicit
+    default = os.path.join(REPO_ROOT, "build", "native", "shard_worker")
+    if os.path.exists(default):
+        return default
+    return None
+
+
+_WORKER_BIN = _worker_binary()
+pytestmark = pytest.mark.skipif(
+    _WORKER_BIN is None,
+    reason=(
+        "native shard_worker binary not built; build packages/node/native with the "
+        "pinned gRPC C++ toolchain or set MESHNET_SHARD_WORKER_BIN"
+    ),
+)
+
+
+def _free_port() -> int:
+    s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    s.bind(("127.0.0.1", 0))
+    port = s.getsockname()[1]
+    s.close()
+    return port
+
+
+def _start_worker(listen_addr: str, extra_env: dict[str, str] | None = None) -> subprocess.Popen:
+    env = dict(os.environ)
+    env["PYTHONPATH"] = _PYTHONPATH
+    if extra_env:
+        env.update(extra_env)
+    proc = subprocess.Popen(
+        [_WORKER_BIN, listen_addr],
+        cwd=REPO_ROOT,
+        env=env,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        text=True,
+    )
+    deadline = time.time() + 30.0
+    while time.time() < deadline:
+        line = proc.stdout.readline()
+        if not line:
+            if proc.poll() is not None:
+                out, _ = proc.communicate()
+                raise RuntimeError(f"worker exited early:\n{out}")
+            continue
+        if "listening on" in line:
+            return proc
+    raise RuntimeError("worker did not start listening in time")
+
+
+class _Worker:
+    """A spawned worker plus a ready channel; also captures stdout on close."""
+
+    def __init__(self, extra_env: dict[str, str] | None = None) -> None:
+        self.port = _free_port()
+        self.addr = f"127.0.0.1:{self.port}"
+        self.proc = _start_worker(self.addr, extra_env)
+        self.channel = grpc.insecure_channel(self.addr)
+        grpc.channel_ready_future(self.channel).result(timeout=15.0)
+
+    def stub(self) -> pb_grpc.ShardRuntimeStub:
+        return pb_grpc.ShardRuntimeStub(self.channel)
+
+    def session(self, requests):
+        call = self.channel.stream_stream(
+            "/meshnet.shard.v1.ShardRuntime/Session",
+            request_serializer=lambda m: m.SerializeToString(),
+            response_deserializer=pb.SessionResponse.FromString,
+        )
+        return list(call(iter(requests)))
+
+    def close(self, *, sig: int = signal.SIGTERM) -> str:
+        self.channel.close()
+        self.proc.send_signal(sig)
+        try:
+            out, _ = self.proc.communicate(timeout=10)
+        except subprocess.TimeoutExpired:
+            self.proc.kill()
+            out, _ = self.proc.communicate()
+        return out or ""
+
+
+@pytest.fixture()
+def worker():
+    w = _Worker()
+    try:
+        yield w
+    finally:
+        if w.proc.poll() is None:
+            w.close()
+
+
+def _crc32c(payload: bytes) -> bytes:
+    return zlib.crc32(payload).to_bytes(4, "big")
+
+
+_WORKER_FINGERPRINT = dict(
+    model_artifact_digest="sha256:native-test-artifact",
+    runtime_recipe_digest="sha256:native-test-recipe",
+    recipe_id="native-test",
+    recipe_version="1",
+    catalogue_version="1",
+)
+
+
+def _open(
+    *,
+    route_session_id="rs-1",
+    route_epoch=7,
+    credits_granted=16,
+    max_inflight_chunks=16,
+    max_chunk_bytes=4 * 1024 * 1024,
+    schema_version=pb.SCHEMA_VERSION_1,
+    fingerprint=None,
+    shard_range=None,
+) -> pb.SessionRequest:
+    fp = pb.Fingerprint(**_WORKER_FINGERPRINT) if fingerprint is None else fingerprint
+    sr = (
+        pb.ShardRange(start_layer=0, end_layer=32, effective_start_layer=0)
+        if shard_range is None
+        else shard_range
+    )
+    return pb.SessionRequest(
+        open=pb.SessionOpen(
+            schema_version=schema_version,
+            route_session_id=route_session_id,
+            route_epoch=route_epoch,
+            fingerprint=fp,
+            shard_range=sr,
+            proposed_flow_control=pb.FlowControl(
+                credits_granted=credits_granted,
+                max_inflight_chunks=max_inflight_chunks,
+                max_chunk_bytes=max_chunk_bytes,
+                max_prefill_chunk_tokens=512,
+            ),
+            accepted_compression=[pb.COMPRESSION_NONE],
+        )
+    )
+
+
+def _chunk(
+    work_id,
+    payload: bytes,
+    step,
+    *,
+    route_session_id="rs-1",
+    route_epoch=7,
+    deadline_unix_nanos=0,
+    fragments=1,
+    total_bytes=None,
+) -> pb.SessionRequest:
+    total = len(payload) if total_bytes is None else total_bytes
+    frags = []
+    if fragments == 1:
+        frags = [pb.TensorFragment(fragment_index=0, fragment_count=1, byte_offset=0, payload=payload)]
+    else:
+        # Split into ``fragments`` tiling pieces.
+        size = max(1, len(payload) // fragments)
+        offset = 0
+        idx = 0
+        while offset < len(payload):
+            piece = payload[offset : offset + size] if idx < fragments - 1 else payload[offset:]
+            frags.append(
+                pb.TensorFragment(
+                    fragment_index=idx, fragment_count=fragments, byte_offset=offset, payload=piece
+                )
+            )
+            offset += len(piece)
+            idx += 1
+    tensor = pb.NamedTensor(
+        name="hidden_states",
+        shape=[1, 1, 4096],
+        dtype=pb.DTYPE_BFLOAT16,
+        byte_order=pb.BYTE_ORDER_LITTLE_ENDIAN,
+        total_bytes=total,
+        compression=pb.COMPRESSION_NONE,
+        checksum=pb.Checksum(algorithm=pb.CHECKSUM_ALGORITHM_CRC32C, value=_crc32c(payload)),
+        fragments=frags,
+    )
+    bundle = pb.TensorBundle(
+        bundle_version=1,
+        tensors=[tensor],
+        architecture=pb.ARCHITECTURE_TYPE_DENSE,
+        boundary_point="pre_tail_residual",
+    )
+    envelope = pb.Envelope(
+        schema_version=pb.SCHEMA_VERSION_1,
+        work_id=work_id,
+        route_session_id=route_session_id,
+        route_epoch=route_epoch,
+        idempotency_step=step,
+        phase=pb.PHASE_PREFILL,
+        position=pb.PositionSpan(first_position=0, token_count=1),
+        deadline_unix_nanos=deadline_unix_nanos,
+    )
+    return pb.SessionRequest(chunk=pb.ActivationChunk(envelope=envelope, bundle=bundle))
+
+
+def _decode(work_id, payload: bytes, step, position) -> pb.SessionRequest:
+    tensor = pb.NamedTensor(
+        name="hidden_states",
+        shape=[1, 1, 4096],
+        dtype=pb.DTYPE_BFLOAT16,
+        byte_order=pb.BYTE_ORDER_LITTLE_ENDIAN,
+        total_bytes=len(payload),
+        compression=pb.COMPRESSION_NONE,
+        checksum=pb.Checksum(algorithm=pb.CHECKSUM_ALGORITHM_CRC32C, value=_crc32c(payload)),
+        fragments=[pb.TensorFragment(fragment_index=0, fragment_count=1, byte_offset=0, payload=payload)],
+    )
+    return pb.SessionRequest(
+        decode=pb.DecodeStep(
+            idempotency_step=step,
+            position=position,
+            expected_past_len=position,
+            work_id=work_id,
+            bundle=pb.TensorBundle(bundle_version=1, tensors=[tensor], architecture=pb.ARCHITECTURE_TYPE_DENSE),
+        )
+    )
+
+
+def _release() -> pb.SessionRequest:
+    return pb.SessionRequest(
+        release=pb.ReleaseSignal(route_session_id="rs-1", route_epoch=7, work_id="work-final")
+    )
+
+
+def _cancel(*, route_session_id="rs-1", work_id="", reason="test cancel") -> pb.SessionRequest:
+    return pb.SessionRequest(
+        cancel=pb.CancelSignal(route_session_id=route_session_id, route_epoch=7, work_id=work_id, reason=reason)
+    )
+
+
+# --- startup / health / capability ----------------------------------------
+
+
+def test_worker_startup_and_health(worker):
+    health = worker.stub().Health(pb.HealthRequest(schema_version=pb.SCHEMA_VERSION_1))
+    assert health.state == pb.SERVING_STATE_SERVING
+    assert health.schema_version == pb.SCHEMA_VERSION_1
+
+
+def test_worker_capability(worker):
+    cap = worker.stub().GetCapability(pb.CapabilityRequest(schema_version=pb.SCHEMA_VERSION_1))
+    assert cap.validated is True
+    assert cap.schema_version == pb.SCHEMA_VERSION_1
+    assert cap.shard_range.end_layer == 32
+    assert pb.SCHEMA_VERSION_1 in cap.supported_schema_versions
+
+
+# --- fragmented prefill / decode / release ---------------------------------
+
+
+def test_fragmented_prefill_echoes_reassembled_payload(worker):
+    payload = b"REAL_ACTIVATION_BYTES_prefill_across_three_fragments_1234567890"
+    responses = worker.session([_open(), _chunk("w1", payload, step=1, fragments=3), _release()])
+    assert responses[0].WhichOneof("kind") == "accepted"
+    echoed = responses[1]
+    assert echoed.WhichOneof("kind") == "chunk"
+    got = b"".join(f.payload for f in echoed.chunk.bundle.tensors[0].fragments)
+    assert got == payload
+    assert echoed.chunk.bundle.tensors[0].checksum.value == _crc32c(payload)
+    assert responses[2].status.terminal is True
+
+
+def test_decode_step_is_served(worker):
+    payload = b"REAL_ACTIVATION_BYTES_decode_step"
+    responses = worker.session([_open(), _decode("w2", payload, step=1, position=1)])
+    echoed = responses[1]
+    assert echoed.WhichOneof("kind") == "chunk"
+    assert echoed.chunk.envelope.phase == pb.PHASE_DECODE
+    assert echoed.chunk.bundle.tensors[0].fragments[0].payload == payload
+
+
+def test_two_disjoint_fake_worker_processes_preserve_prefill_and_decode_seam():
+    """DGR-036 fixture proof across two actual fake-worker processes.
+
+    The DGR-033 worker deliberately has no model graph: its bounded forward
+    validates and echoes the activation bytes.  That makes it suitable for a
+    deterministic protocol proof only.  Keep the two ranges disjoint at the
+    ``SessionOpen`` boundary, pass each stage-one output through stage two,
+    and exercise a prefill plus 32 sequential decode positions.  Numerical
+    dense-GGUF parity remains an opt-in DGR-036 real-model lane, not a claim
+    made by this fixture.
+    """
+    head = _Worker()
+    tail = _Worker()
+    try:
+        head_open = _open(
+            route_session_id="dgr036-head",
+            shard_range=pb.ShardRange(start_layer=0, end_layer=16, effective_start_layer=0),
+        )
+        tail_open = _open(
+            route_session_id="dgr036-tail",
+            shard_range=pb.ShardRange(start_layer=16, end_layer=32, effective_start_layer=16),
+        )
+        payload = b"dgr036 deterministic dense prefill residual"
+
+        def decode_requests(*, stage: str, payloads: list[bytes]) -> list[pb.SessionRequest]:
+            requests: list[pb.SessionRequest] = []
+            for position, stage_payload in enumerate(payloads, start=1):
+                # The fixture worker's negotiated default window is 16.  Top
+                # it up before decode 16 and 32 so this exercises all 32
+                # sequential positions rather than silently testing only one
+                # credit window.
+                if position in {16, 32}:
+                    requests.append(pb.SessionRequest(flow_control=pb.FlowControl(credits_granted=16)))
+                requests.append(_decode(f"decode-{stage}-{position}", stage_payload, position + 1, position))
+            return requests
+
+        head_responses = head.session(
+            [head_open, _chunk("prefill-head", payload, step=1)]
+            + decode_requests(stage="head", payloads=[payload] * 32)
+        )
+        assert head_responses[0].WhichOneof("kind") == "accepted"
+        assert head_responses[1].WhichOneof("kind") == "chunk"
+        seam_payloads = [
+            response.chunk.bundle.tensors[0].fragments[0].payload
+            for response in head_responses
+            if response.WhichOneof("kind") == "chunk"
+        ]
+        assert len(seam_payloads) == 33
+
+        tail_responses = tail.session(
+            [tail_open, _chunk("prefill-tail", seam_payloads[0], step=1, route_session_id="dgr036-tail")]
+            + decode_requests(stage="tail", payloads=seam_payloads[1:])
+        )
+        assert tail_responses[0].WhichOneof("kind") == "accepted"
+        assert tail_responses[1].WhichOneof("kind") == "chunk"
+        assert tail_responses[1].chunk.bundle.tensors[0].fragments[0].payload == payload
+
+        for tail_response in (response for response in tail_responses if response.WhichOneof("kind") == "chunk"):
+            assert tail_response.chunk.bundle.tensors[0].fragments[0].payload == payload
+    finally:
+        if head.proc.poll() is None:
+            head.close()
+        if tail.proc.poll() is None:
+            tail.close()
+
+
+def test_release_is_terminal(worker):
+    responses = worker.session([_open(), _release()])
+    assert responses[0].WhichOneof("kind") == "accepted"
+    assert responses[1].status.terminal is True
+
+
+# --- deadlines / flow control / bounded messages ---------------------------
+
+
+def test_expired_deadline_is_rejected(worker):
+    responses = worker.session([_open(), _chunk("w-late", b"payload", step=1, deadline_unix_nanos=1)])
+    assert responses[1].status.error.code == pb.ERROR_CODE_DEADLINE_EXCEEDED
+
+
+def test_flow_control_violation_and_topup(worker):
+    responses = worker.session(
+        [
+            _open(credits_granted=1),
+            _chunk("w-a", b"payload-a", step=1),
+            _chunk("w-b", b"payload-b", step=2),
+            pb.SessionRequest(flow_control=pb.FlowControl(credits_granted=5)),
+            _chunk("w-c", b"payload-c", step=3),
+        ]
+    )
+    assert responses[1].WhichOneof("kind") == "chunk"
+    assert responses[2].status.error.code == pb.ERROR_CODE_FLOW_CONTROL_VIOLATION
+    assert responses[2].status.error.retryable is True
+    assert responses[3].WhichOneof("kind") == "flow_control"
+    assert responses[3].flow_control.credits_granted >= 5
+    assert responses[4].WhichOneof("kind") == "chunk"
+
+
+def test_bounded_message_is_rejected():
+    """A tensor whose declared payload exceeds the negotiated ceiling is refused."""
+    w = _Worker(extra_env={"MESHNET_MAX_CHUNK_BYTES": "64"})
+    try:
+        big = b"x" * 128
+        responses = w.session([_open(), _chunk("w-big", big, step=1, total_bytes=128)])
+        status = responses[1].status
+        assert status.error.code == pb.ERROR_CODE_RESOURCE_EXHAUSTED
+        assert "max_chunk_bytes" in status.error.detail
+    finally:
+        if w.proc.poll() is None:
+            w.close()
+
+
+def test_malformed_fragment_tiling_is_rejected(worker):
+    # A fragment at a non-zero offset with no predecessor cannot tile.
+    tensor = pb.NamedTensor(
+        name="hidden_states",
+        shape=[1, 1, 4096],
+        dtype=pb.DTYPE_BFLOAT16,
+        byte_order=pb.BYTE_ORDER_LITTLE_ENDIAN,
+        total_bytes=7,
+        compression=pb.COMPRESSION_NONE,
+        checksum=pb.Checksum(algorithm=pb.CHECKSUM_ALGORITHM_CRC32C, value=_crc32c(b"payload")),
+        fragments=[pb.TensorFragment(fragment_index=0, fragment_count=1, byte_offset=5, payload=b"payload")],
+    )
+    bad = pb.SessionRequest(
+        chunk=pb.ActivationChunk(
+            envelope=pb.Envelope(
+                schema_version=pb.SCHEMA_VERSION_1,
+                work_id="w-gap",
+                route_session_id="rs-1",
+                route_epoch=7,
+                idempotency_step=1,
+            ),
+            bundle=pb.TensorBundle(bundle_version=1, tensors=[tensor]),
+        )
+    )
+    responses = worker.session([_open(), bad])
+    assert responses[1].status.error.code == pb.ERROR_CODE_PAYLOAD_CORRUPT
+    assert "tile" in responses[1].status.error.detail
+
+
+def test_stale_route_epoch_is_rejected(worker):
+    responses = worker.session([_open(route_epoch=7), _chunk("w-stale", b"payload", step=1, route_epoch=5)])
+    assert responses[1].status.error.code == pb.ERROR_CODE_EPOCH_STALE
+
+
+def test_duplicate_idempotency_step_is_acked(worker):
+    chunk = _chunk("w-dup", b"payload", step=1)
+    responses = worker.session([_open(), chunk, chunk])
+    assert responses[1].WhichOneof("kind") == "chunk"
+    assert responses[2].WhichOneof("kind") == "ack"
+    assert responses[2].ack.duplicate is True
+
+
+# --- cancellation ----------------------------------------------------------
+
+
+def test_in_band_cancel_of_single_work_item_does_not_end_stream(worker):
+    responses = worker.session(
+        [
+            _open(),
+            _cancel(work_id="work-x"),
+            _chunk("work-x", b"payload", step=1),
+            _chunk("work-y", b"payload", step=2),
+            _release(),
+        ]
+    )
+    assert responses[1].status.error.code == pb.ERROR_CODE_CANCELLED
+    assert responses[1].status.terminal is False
+    assert responses[2].status.error.code == pb.ERROR_CODE_CANCELLED
+    assert responses[3].WhichOneof("kind") == "chunk"
+    assert responses[4].status.terminal is True
+
+
+def test_in_band_cancel_of_whole_session_is_terminal(worker):
+    responses = worker.session([_open(), _cancel(work_id="")])
+    assert responses[1].status.error.code == pb.ERROR_CODE_CANCELLED
+    assert responses[1].status.terminal is True
+
+
+def test_out_of_band_cancel_rpc_races_ahead_of_open(worker):
+    stub = worker.stub()
+    resp = stub.Cancel(
+        pb.CancelRequest(
+            schema_version=pb.SCHEMA_VERSION_1,
+            route_session_id="rs-precancel",
+            route_epoch=1,
+            work_id="work-precancelled",
+            reason="operator abort",
+        )
+    )
+    assert resp.cancelled_work_items == 1
+    responses = worker.session(
+        [
+            _open(route_session_id="rs-precancel"),
+            _chunk("work-precancelled", b"payload", step=1, route_session_id="rs-precancel"),
+        ]
+    )
+    assert responses[1].status.error.code == pb.ERROR_CODE_CANCELLED
+
+
+def test_release_rpc_is_idempotent(worker):
+    stub = worker.stub()
+    # Open a session WITHOUT an in-stream release so state persists on the
+    # servicer, then drop it out of band twice.
+    worker.session([_open(route_session_id="rs-rel")])
+    first = stub.Release(pb.ReleaseRequest(schema_version=pb.SCHEMA_VERSION_1, route_session_id="rs-rel", route_epoch=7))
+    second = stub.Release(pb.ReleaseRequest(schema_version=pb.SCHEMA_VERSION_1, route_session_id="rs-rel", route_epoch=7))
+    assert first.released is True
+    assert second.released is False  # idempotent: nothing left to drop
+
+
+def test_independent_session_cancellation(worker):
+    # Cancel the whole of session A; session B must remain fully serviceable.
+    a = worker.session([_open(route_session_id="sess-A"), _cancel(route_session_id="sess-A", work_id="")])
+    assert a[1].status.terminal is True
+    b = worker.session(
+        [
+            _open(route_session_id="sess-B"),
+            _chunk("work-b", b"payload-b", step=1, route_session_id="sess-B"),
+            _release(),
+        ]
+    )
+    assert b[1].WhichOneof("kind") == "chunk", "cancelling session A must not affect session B"
+
+
+# --- graceful shutdown -----------------------------------------------------
+
+
+def test_graceful_shutdown_on_sigterm():
+    w = _Worker()
+    # Confirm it is serving, then send SIGTERM and require a clean drain/exit.
+    assert w.stub().Health(pb.HealthRequest(schema_version=pb.SCHEMA_VERSION_1)).state == pb.SERVING_STATE_SERVING
+    out = w.close(sig=signal.SIGTERM)
+    assert w.proc.returncode == 0, f"worker did not exit cleanly on SIGTERM:\n{out}"
+    assert "shut down cleanly" in out
+
+
+# --- direct vs opaque relay byte identity ----------------------------------
+
+
+def test_direct_and_opaque_relay_yield_identical_responses(worker):
+    """A direct hop and an opaque relay of the exact captured request bytes must
+    produce byte-identical server responses (relays carry frames verbatim)."""
+    payload = b"RELAY_ACTIVATION_BYTES"
+    requests = [_open(), _chunk("w1", payload, step=1), _release()]
+
+    direct_call = worker.channel.stream_stream(
+        "/meshnet.shard.v1.ShardRuntime/Session",
+        request_serializer=lambda m: m.SerializeToString(),
+        response_deserializer=lambda b: b,
+    )
+    direct_resp = list(direct_call(iter(requests)))
+    captured = [m.SerializeToString() for m in requests]
+
+    relay_call = worker.channel.stream_stream(
+        "/meshnet.shard.v1.ShardRuntime/Session",
+        request_serializer=lambda b: b,  # raw captured bytes, no reinterpretation
+        response_deserializer=lambda b: b,
+    )
+    relay_resp = list(relay_call(iter(captured)))
+
+    assert len(direct_resp) == len(relay_resp) == 3
+    for i, (d, r) in enumerate(zip(direct_resp, relay_resp)):
+        assert d == r, f"response #{i} differs between direct and opaque relay"
+
+
+# --- fail-closed before SessionOpen ----------------------------------------
+
+
+def test_chunk_before_open_is_rejected(worker):
+    # An activation with no preceding SessionOpen must fail closed and end the
+    # stream: no work may bypass the lifecycle handshake.
+    responses = worker.session([_chunk("w-noopen", b"payload", step=1)])
+    assert len(responses) == 1
+    assert responses[0].WhichOneof("kind") == "status"
+    assert responses[0].status.error.code == pb.ERROR_CODE_INTERNAL
+    assert responses[0].status.terminal is True
+    assert "SessionOpen" in responses[0].status.error.detail
+
+
+def test_decode_before_open_is_rejected(worker):
+    responses = worker.session([_decode("w-noopen", b"payload", step=1, position=0)])
+    assert len(responses) == 1
+    assert responses[0].WhichOneof("kind") == "status"
+    assert responses[0].status.error.code == pb.ERROR_CODE_INTERNAL
+    assert responses[0].status.terminal is True
+
+
+# --- flow-control negotiation with strict worker bounds --------------------
+
+
+def test_flow_control_proposal_is_clamped_to_worker_bounds(worker):
+    # A peer proposing a window far above the worker limits must be clamped to
+    # the worker own ceilings, never granted the inflated proposal.
+    responses = worker.session(
+        [_open(credits_granted=9999, max_inflight_chunks=9999, max_chunk_bytes=1073741824)]
+    )
+    fc = responses[0].accepted.flow_control
+    assert fc.max_inflight_chunks == 16
+    assert fc.credits_granted == 16
+    assert fc.max_chunk_bytes == 4 * 1024 * 1024
+
+
+def test_negotiated_max_chunk_bytes_caps_peer_proposal():
+    # Worker ceiling is 64 bytes; the peer proposes 4 MiB. The negotiated per
+    # session ceiling is the stricter 64, so a 128-byte tensor is refused even
+    # though the peer allowed it — the worker never adopts the peer proposal.
+    w = _Worker(extra_env={"MESHNET_MAX_CHUNK_BYTES": "64"})
+    try:
+        big = b"x" * 128
+        responses = w.session(
+            [_open(max_chunk_bytes=4 * 1024 * 1024), _chunk("w-big", big, step=1, total_bytes=128)]
+        )
+        assert responses[0].accepted.flow_control.max_chunk_bytes == 64
+        assert responses[1].status.error.code == pb.ERROR_CODE_RESOURCE_EXHAUSTED
+        assert "max_chunk_bytes" in responses[1].status.error.detail
+    finally:
+        if w.proc.poll() is None:
+            w.close()
+
+
+# --- in-stream release erases session state --------------------------------
+
+
+def test_in_stream_release_erases_session_state(worker):
+    stub = worker.stub()
+    resp = worker.session(
+        [
+            _open(route_session_id="rs-erase"),
+            pb.SessionRequest(
+                release=pb.ReleaseSignal(route_session_id="rs-erase", route_epoch=7, work_id="w-final")
+            ),
+        ]
+    )
+    assert resp[-1].status.terminal is True
+    # The state is already gone: an out-of-band Release finds nothing to drop.
+    after = stub.Release(
+        pb.ReleaseRequest(schema_version=pb.SCHEMA_VERSION_1, route_session_id="rs-erase", route_epoch=7)
+    )
+    assert after.released is False
+
+
+# --- SessionOpen identity validation ---------------------------------------
+
+
+def test_incompatible_schema_is_rejected_at_open(worker):
+    responses = worker.session([_open(schema_version=pb.SCHEMA_VERSION_UNSPECIFIED)])
+    assert responses[0].WhichOneof("kind") == "status"
+    assert responses[0].status.error.code == pb.ERROR_CODE_SCHEMA_UNSUPPORTED
+    assert responses[0].status.terminal is True
+
+
+def test_incompatible_fingerprint_is_rejected_at_open(worker):
+    bad_fp = pb.Fingerprint(
+        model_artifact_digest="sha256:some-other-model",
+        runtime_recipe_digest="sha256:native-test-recipe",
+        recipe_id="native-test",
+        recipe_version="1",
+        catalogue_version="1",
+    )
+    responses = worker.session([_open(fingerprint=bad_fp)])
+    assert responses[0].WhichOneof("kind") == "status"
+    assert responses[0].status.error.code == pb.ERROR_CODE_FINGERPRINT_MISMATCH
+    assert responses[0].status.terminal is True
+
+
+def test_shard_range_mismatch_is_rejected_at_open(worker):
+    responses = worker.session(
+        [_open(shard_range=pb.ShardRange(start_layer=0, end_layer=64, effective_start_layer=0))]
+    )
+    assert responses[0].WhichOneof("kind") == "status"
+    assert responses[0].status.error.code == pb.ERROR_CODE_SHARD_RANGE_MISMATCH
+    assert responses[0].status.terminal is True
+
+
+def test_session_accepted_reports_worker_fingerprint_not_caller(worker):
+    # The caller asserts no fingerprint; SessionAccepted must carry the worker
+    # OWN served identity, not a copy of the caller (empty) fingerprint.
+    responses = worker.session([_open(fingerprint=pb.Fingerprint())])
+    assert responses[0].WhichOneof("kind") == "accepted"
+    accepted = responses[0].accepted
+    assert accepted.fingerprint.model_artifact_digest == "sha256:native-test-artifact"
+    assert accepted.fingerprint.runtime_recipe_digest == "sha256:native-test-recipe"

tests/test_native_worker_supervisor.py

@@ -0,0 +1,196 @@
+"""Model-free DGR-040 supervision tests using a deterministic fake worker."""
+
+from __future__ import annotations
+
+import hashlib
+import sys
+import time
+from pathlib import Path
+
+import pytest
+
+from meshnet_node.native_worker_supervisor import (
+    NativeWorkerError,
+    NativeWorkerProbe,
+    NativeWorkerSpec,
+    NativeWorkerSupervisor,
+)
+
+
+def _write_fake_worker(path: Path) -> None:
+    path.write_text(
+        """import os
+import signal
+import sys
+import time
+
+stop = False
+def terminate(*_):
+    global stop
+    stop = True
+signal.signal(signal.SIGTERM, terminate)
+print('ShardRuntime worker listening on ' + os.environ['MESHNET_SHARD_LISTEN_ADDR'], flush=True)
+if os.environ.get('MESHNET_INJECT_PROCESS_DEATH_AFTER_EXECUTIONS'):
+    marker = os.environ.get('MESHNET_FAKE_CRASH_ONCE_FILE')
+    if not marker or not os.path.exists(marker):
+        if marker:
+            open(marker, 'w').close()
+        time.sleep(0.05)
+        print('deterministic injected worker death', file=sys.stderr, flush=True)
+        raise SystemExit(70)
+while not stop:
+    time.sleep(0.01)
+print('ShardRuntime worker shut down cleanly', flush=True)
+""",
+        encoding="utf-8",
+    )
+
+
+def _spec(tmp_path: Path, **changes: object) -> NativeWorkerSpec:
+    artifact = tmp_path / "fixture.gguf"
+    artifact.write_bytes(b"fixture artifact")
+    fake = tmp_path / "fake_worker.py"
+    _write_fake_worker(fake)
+    values: dict[str, object] = {
+        "binary": Path(sys.executable),
+        "binary_digest": hashlib.sha256(Path(sys.executable).read_bytes()).hexdigest(),
+        "args": (str(fake),),
+        "listen_address": "fake-worker:12345",
+        "artifact_path": artifact,
+        "artifact_digest": hashlib.sha256(artifact.read_bytes()).hexdigest(),
+        "recipe_digest": "a" * 64,
+        "recipe_id": "fixture",
+        "recipe_version": "1",
+        "catalogue_version": "test",
+        "shard_start": 2,
+        "shard_end": 5,
+    }
+    values.update(changes)
+    return NativeWorkerSpec(**values)  # type: ignore[arg-type]
+
+
+def _probe(spec: NativeWorkerSpec, _timeout: float) -> NativeWorkerProbe:
+    return NativeWorkerProbe(
+        artifact_digest=spec.artifact_digest,
+        recipe_digest=spec.recipe_digest,
+        recipe_id=spec.recipe_id,
+        recipe_version=spec.recipe_version,
+        catalogue_version=spec.catalogue_version,
+        shard_start=spec.shard_start,
+        shard_end=spec.shard_end,
+        serving=True,
+    )
+
+
+def _eventually(predicate, timeout: float = 2.0) -> bool:
+    deadline = time.monotonic() + timeout
+    while time.monotonic() < deadline:
+        if predicate():
+            return True
+        time.sleep(0.01)
+    return predicate()
+
+
+def test_start_verifies_identity_captures_logs_and_stops_gracefully(tmp_path):
+    events: list[tuple[str, str]] = []
+    supervisor = NativeWorkerSupervisor(
+        _spec(tmp_path),
+        probe=_probe,
+        readiness_timeout=1,
+        shutdown_timeout=1,
+        kill_timeout=1,
+        on_available=lambda reason: events.append(("available", reason)),
+        on_unavailable=lambda reason: events.append(("unavailable", reason)),
+    )
+
+    result = supervisor.start()
+    assert result.serving and supervisor.available
+    assert events == [("available", "worker ready and identity verified")]
+    assert any("ShardRuntime worker listening" in line for line in supervisor.logs)
+
+    supervisor.stop()
+    assert not supervisor.available
+    assert events[-1] == ("unavailable", "worker stopped")
+    assert _eventually(lambda: any("shut down cleanly" in line for line in supervisor.logs))
+
+
+def test_start_refuses_changed_artifact_before_spawning(tmp_path):
+    spec = _spec(tmp_path, artifact_digest="0" * 64)
+    supervisor = NativeWorkerSupervisor(spec, probe=_probe, readiness_timeout=1)
+
+    with pytest.raises(NativeWorkerError, match="artifact digest"):
+        supervisor.start()
+    assert supervisor.pid is None
+
+
+def test_start_refuses_changed_binary_before_spawning(tmp_path):
+    spec = _spec(tmp_path, binary_digest="0" * 64)
+    supervisor = NativeWorkerSupervisor(spec, probe=_probe, readiness_timeout=1)
+
+    with pytest.raises(NativeWorkerError, match="binary digest"):
+        supervisor.start()
+    assert supervisor.pid is None
+
+
+def test_probe_identity_mismatch_never_makes_capability_available(tmp_path):
+    spec = _spec(tmp_path)
+
+    def wrong_probe(actual: NativeWorkerSpec, timeout: float) -> NativeWorkerProbe:
+        result = _probe(actual, timeout)
+        return NativeWorkerProbe(**{**result.__dict__, "shard_end": actual.shard_end + 1})
+
+    supervisor = NativeWorkerSupervisor(spec, probe=wrong_probe, readiness_timeout=1, shutdown_timeout=1)
+    with pytest.raises(NativeWorkerError, match="identity/range"):
+        supervisor.start()
+    assert not supervisor.available
+
+
+def test_deterministic_worker_death_withdraws_then_restart_recovers(tmp_path):
+    unavailable: list[str] = []
+    spec = _spec(
+        tmp_path,
+        extra_environment={
+            "MESHNET_INJECT_PROCESS_DEATH_AFTER_EXECUTIONS": "1",
+            "MESHNET_FAKE_CRASH_ONCE_FILE": str(tmp_path / "crashed-once"),
+        },
+    )
+    supervisor = NativeWorkerSupervisor(
+        spec,
+        probe=_probe,
+        readiness_timeout=1,
+        health_interval=0.01,
+        shutdown_timeout=1,
+        kill_timeout=1,
+        on_unavailable=unavailable.append,
+    )
+    supervisor.start()
+    assert _eventually(lambda: not supervisor.available)
+    assert "code 70" in supervisor.unavailable_reason
+    assert any("deterministic injected worker death" in line for line in supervisor.logs)
+
+    supervisor.restart()
+    assert supervisor.available
+    supervisor.stop()
+
+
+def test_health_loss_withdraws_only_native_capability(tmp_path):
+    healthy = True
+    unavailable: list[str] = []
+    spec = _spec(tmp_path)
+
+    def health_probe(actual: NativeWorkerSpec, timeout: float) -> NativeWorkerProbe:
+        result = _probe(actual, timeout)
+        return NativeWorkerProbe(**{**result.__dict__, "serving": healthy})
+
+    supervisor = NativeWorkerSupervisor(
+        spec,
+        probe=health_probe,
+        readiness_timeout=1,
+        on_unavailable=unavailable.append,
+    )
+    supervisor.start()
+    healthy = False
+    assert not supervisor.check_health()
+    assert not supervisor.available
+    assert unavailable and "health lost" in unavailable[-1]
+    supervisor.stop()

tests/test_range_report.py

@@ -0,0 +1,273 @@
+"""DGR-034: strict consumption of owned-range reports from loaded engine state.
+
+The ``meshnet-range-report`` native tool loads one dense-Llama GGUF through
+the Meshnet owned-range loader and prints a JSON document derived from the
+loaded model state. ``meshnet_node.range_report`` is the strict consumer:
+it must accept exactly the documents that encode the dense-Llama ownership
+contract and fail closed on everything else — invalid, empty, or
+out-of-model ranges, endpoint registrations that disagree with the loaded
+state, gapped or unexpected tensor registrations, and inconsistent byte
+counts.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+import pytest
+
+from meshnet_node.range_report import (
+    OwnedRangeReport,
+    RangeReportError,
+    parse_owned_range_report,
+)
+
+N_LAYER = 40
+LAYER_BYTES = 300 * 2**20
+EMBD_BYTES = 360 * 2**20
+OUT_BYTES = 525 * 2**20
+FILE_BYTES = 13669 * 2**20
+
+
+def _doc(**overrides: Any) -> dict[str, Any]:
+    """A valid middle-range [10, 20) mmap report the consumer must accept."""
+    doc: dict[str, Any] = {
+        "ok": True,
+        "model": "/models/dense.gguf",
+        "architecture": "llama",
+        "n_layer": N_LAYER,
+        "file_bytes": FILE_BYTES,
+        "requested_range": [10, 20],
+        "reported_range": [10, 20],
+        "mmap": True,
+        "touched": False,
+        "use_extra_bufts": True,
+        "has_token_embeddings": False,
+        "has_output_head": False,
+        "tied_output_head": False,
+        "mapped_bytes": 10 * LAYER_BYTES,
+        "resident_bytes": 10 * LAYER_BYTES,
+        "registered_tensors": 90,
+        "registered_bytes": 10 * LAYER_BYTES,
+        "unexpected_registered_tensors": [],
+        "missing_owned_layers": [],
+        "vm_size_bytes": FILE_BYTES + 2**28,
+        "vm_rss_bytes": 2**28,
+        "vm_hwm_bytes": 2**28,
+    }
+    doc.update(overrides)
+    return doc
+
+
+def _head_doc(**overrides: Any) -> dict[str, Any]:
+    base = _doc(
+        requested_range=[0, 10],
+        reported_range=[0, 10],
+        has_token_embeddings=True,
+        mapped_bytes=10 * LAYER_BYTES + EMBD_BYTES,
+        resident_bytes=10 * LAYER_BYTES + EMBD_BYTES,
+        registered_tensors=91,
+        registered_bytes=10 * LAYER_BYTES + EMBD_BYTES,
+    )
+    base.update(overrides)
+    return base
+
+
+def _tail_doc(**overrides: Any) -> dict[str, Any]:
+    base = _doc(
+        requested_range=[30, 40],
+        reported_range=[30, 40],
+        has_output_head=True,
+        mapped_bytes=10 * LAYER_BYTES + OUT_BYTES,
+        resident_bytes=10 * LAYER_BYTES + OUT_BYTES,
+        registered_tensors=92,
+        registered_bytes=10 * LAYER_BYTES + OUT_BYTES,
+    )
+    base.update(overrides)
+    return base
+
+
+class TestAcceptance:
+    def test_middle_range_registers_only_per_layer_tensors(self) -> None:
+        report = parse_owned_range_report(_doc())
+        assert (report.start_layer, report.end_layer) == (10, 20)
+        assert not report.is_head and not report.is_tail
+        assert not report.has_token_embeddings and not report.has_output_head
+
+    def test_head_range_owns_embeddings_only_at_the_head(self) -> None:
+        report = parse_owned_range_report(_head_doc())
+        assert report.is_head and not report.is_tail
+        assert report.has_token_embeddings and not report.has_output_head
+
+    def test_tail_range_owns_norm_and_output_only_at_the_tail(self) -> None:
+        report = parse_owned_range_report(_tail_doc())
+        assert report.is_tail and not report.is_head
+        assert report.has_output_head and not report.has_token_embeddings
+
+    def test_whole_model_range_owns_both_endpoints(self) -> None:
+        report = parse_owned_range_report(
+            _head_doc(
+                requested_range=[0, 40],
+                reported_range=[0, 40],
+                has_output_head=True,
+                mapped_bytes=FILE_BYTES,
+                resident_bytes=FILE_BYTES,
+                registered_tensors=363,
+                registered_bytes=N_LAYER * LAYER_BYTES + EMBD_BYTES + OUT_BYTES,
+            )
+        )
+        assert report.is_head and report.is_tail
+        assert report.has_token_embeddings and report.has_output_head
+
+    def test_tied_output_tail_registers_the_embedding_as_its_output_head(self) -> None:
+        report = parse_owned_range_report(
+            _tail_doc(
+                has_token_embeddings=True,
+                tied_output_head=True,
+                registered_tensors=91,
+                registered_bytes=10 * LAYER_BYTES + EMBD_BYTES,
+                mapped_bytes=10 * LAYER_BYTES + EMBD_BYTES,
+                resident_bytes=10 * LAYER_BYTES + EMBD_BYTES,
+            )
+        )
+        assert report.tied_output_head and report.has_output_head
+
+    def test_non_mmap_load_reports_resident_allocation_only(self) -> None:
+        report = parse_owned_range_report(
+            _doc(mmap=False, mapped_bytes=0, resident_bytes=10 * LAYER_BYTES)
+        )
+        assert report.mapped_bytes == 0
+        assert report.resident_bytes == 10 * LAYER_BYTES
+
+    def test_process_counters_may_be_absent_off_linux(self) -> None:
+        report = parse_owned_range_report(
+            _doc(vm_size_bytes=None, vm_rss_bytes=None, vm_hwm_bytes=None)
+        )
+        assert report.vm_hwm_bytes is None
+
+
+class TestRangeRejection:
+    def test_rejected_load_fails_closed_with_the_tool_error(self) -> None:
+        with pytest.raises(RangeReportError, match="dense Llama only"):
+            parse_owned_range_report(
+                {"ok": False, "error": "owned-range load rejected the artifact or range: dense Llama only"}
+            )
+
+    def test_reported_range_must_match_the_requested_range(self) -> None:
+        with pytest.raises(RangeReportError, match="loaded engine state"):
+            parse_owned_range_report(_doc(reported_range=[10, 21]))
+
+    def test_out_of_model_range_is_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="outside the model"):
+            parse_owned_range_report(
+                _doc(requested_range=[30, 41], reported_range=[30, 41], has_output_head=True)
+            )
+
+    def test_empty_range_is_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="empty or"):
+            parse_owned_range_report(_doc(requested_range=[10, 10], reported_range=[10, 10]))
+
+    def test_inverted_range_is_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="empty or"):
+            parse_owned_range_report(_doc(requested_range=[20, 10], reported_range=[20, 10]))
+
+    def test_boolean_range_bounds_are_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="integer pair"):
+            parse_owned_range_report(_doc(reported_range=[True, 20]))
+
+
+class TestEndpointRejection:
+    def test_embeddings_registered_below_the_head_are_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="embeddings belong to the head"):
+            parse_owned_range_report(_doc(has_token_embeddings=True))
+
+    def test_output_head_registered_above_the_tail_is_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="output head belong to the tail"):
+            parse_owned_range_report(_tail_doc(requested_range=[20, 30], reported_range=[20, 30]))
+
+    def test_tail_without_an_output_head_is_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="output head belong to the tail"):
+            parse_owned_range_report(_tail_doc(has_output_head=False))
+
+    def test_tied_output_below_the_tail_is_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="only belong to the tail"):
+            parse_owned_range_report(_doc(tied_output_head=True))
+
+    def test_unexpected_registered_tensors_are_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="unexpected_registered_tensors"):
+            parse_owned_range_report(
+                _doc(unexpected_registered_tensors=["blk.10.attn_q.weight.extra"])
+            )
+
+    def test_missing_owned_layers_are_rejected_as_gaps(self) -> None:
+        with pytest.raises(RangeReportError, match="missing_owned_layers"):
+            parse_owned_range_report(_doc(missing_owned_layers=[12]))
+
+
+class TestByteCountRejection:
+    def test_mapped_span_must_cover_the_registered_tensors(self) -> None:
+        with pytest.raises(RangeReportError, match="undercounts"):
+            parse_owned_range_report(_doc(mapped_bytes=LAYER_BYTES))
+
+    def test_mapped_span_must_not_exceed_the_artifact(self) -> None:
+        with pytest.raises(RangeReportError, match="exceeds the artifact"):
+            parse_owned_range_report(
+                _tail_doc(mapped_bytes=FILE_BYTES + 1, resident_bytes=FILE_BYTES + 1)
+            )
+
+    def test_non_mmap_load_must_not_claim_a_mapped_span(self) -> None:
+        with pytest.raises(RangeReportError, match="must not claim"):
+            parse_owned_range_report(_doc(mmap=False, mapped_bytes=LAYER_BYTES))
+
+    def test_resident_allocation_must_cover_the_registered_tensors(self) -> None:
+        with pytest.raises(RangeReportError, match="undercounts"):
+            parse_owned_range_report(
+                _doc(mmap=False, mapped_bytes=0, resident_bytes=LAYER_BYTES)
+            )
+
+    def test_an_empty_registration_is_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="no tensors"):
+            parse_owned_range_report(_doc(registered_tensors=0, registered_bytes=0))
+
+
+class TestSchemaRejection:
+    def test_wrong_architecture_is_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="dense Llama only"):
+            parse_owned_range_report(_doc(architecture="qwen2"))
+
+    def test_missing_field_is_rejected(self) -> None:
+        doc = _doc()
+        del doc["mapped_bytes"]
+        with pytest.raises(RangeReportError, match="missing field"):
+            parse_owned_range_report(doc)
+
+    def test_boolean_bytes_are_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="non-negative integer"):
+            parse_owned_range_report(_doc(mapped_bytes=True))
+
+    def test_non_mapping_document_is_rejected(self) -> None:
+        with pytest.raises(RangeReportError, match="JSON object"):
+            parse_owned_range_report(["not", "a", "report"])  # type: ignore[arg-type]
+
+
+def test_owned_range_report_rejects_direct_construction_outside_the_contract() -> None:
+    with pytest.raises(RangeReportError, match="dense Llama only"):
+        OwnedRangeReport(
+            architecture="qwen2",
+            n_layer=N_LAYER,
+            start_layer=10,
+            end_layer=20,
+            has_token_embeddings=False,
+            has_output_head=False,
+            tied_output_head=False,
+            mapped_bytes=10 * LAYER_BYTES,
+            resident_bytes=10 * LAYER_BYTES,
+            registered_tensors=90,
+            registered_bytes=10 * LAYER_BYTES,
+            file_bytes=FILE_BYTES,
+            mmap=True,
+            touched=False,
+            vm_size_bytes=None,
+            vm_rss_bytes=None,
+            vm_hwm_bytes=None,
+        )