feat: add signed ROCm diagnostic lane

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

@@ -65,9 +65,11 @@ The near-lossless BF16 quality lane compared all three prompts but measured:
 - mean text similarity: **0.9471** (v1 requires at least `0.97`).
 
 Tokenization and stopping were controlled: every runtime saw the same prompt
-token counts and reported 31 post-TTFT decode tokens. The mismatch is genuine
-greedy runtime divergence on two prompts, not missing coverage or a text-length
-artifact. Therefore `contract-evaluation.json` records:
+token counts and reported 31 post-TTFT decode tokens. The v1 mismatch is a
+real greedy-output divergence on two prompts, not missing coverage or a
+text-length artifact. Its root cause remains undetermined; no post-contract
+logit-tie claim is acceptance evidence. Therefore `contract-evaluation.json`
+records:
 
 ```text
 verdict: stop
@@ -79,6 +81,35 @@ stop_condition_met: true
 
 Thresholds were not changed after observing these results.
 
+## Post-contract parity and ROCm diagnostics
+
+`summarize-quality-parity.py` verifies and separates two signed sources. The CPU
+v1 row uses CPU kernels and a Transformers BF16 oracle; it remains at `0.3333`
+exact match with an unexplained divergence. The ROCm row uses a different plan,
+GPU kernels, and a Transformers float32 oracle. In that narrower diagnostic,
+the same BF16 GGUF artifact matches all three 32-token sequences exactly (`1.0`
+exact match and `1.0` similarity). No conversion corruption was observed in
+that three-sequence ROCm sample; this does not prove global conversion
+correctness or explain the CPU result.
+
+A separate HIP build at commit `e920c523` was compiled for `gfx1151` and
+measured `ROCm0: Radeon 8060S Graphics`; its `llama-server` SHA-256 is
+`b6bb4da687dbde86e243ba006cef05919b7b97255cd7e2371e1d451220aca139`.
+A signed `gpu-diagnostic` profile measured zero failures:
+
+| GPU metric | Transformers BF16 ROCm | llama.cpp Q4 ROCm | Q4 ratio |
+|---|---:|---:|---:|
+| Decode tok/s, c=1 | 81.12 | 251.25 | **3.10×** |
+| Aggregate decode tok/s, c=4 | 91.24 | 511.33 | **5.60×** |
+| TTFT p50, c=1 | 13.77 ms | 11.80 ms | **0.857×** |
+
+The GPU report is signed under the distinct
+`run_configured_gpu_diagnostic/v1` producer. The v1 evaluator rejects that
+producer even when its signature is valid. llama-server process VRAM remains
+unmeasured, so this diagnostic cannot replace or satisfy the immutable v1
+contract. Its signed backend detail records the measured `ROCm0: Radeon 8060S
+Graphics` device and `25/25` offloaded layers.
+
 ## Implementation
 
 - `recipe_benchmark.py` provides the runtime-neutral measurement core, true
@@ -86,8 +117,9 @@ Thresholds were not changed after observing these results.
   aggregation, failures, and output drift.
 - `recipe_drivers.py` provides opt-in Transformers and llama-server drivers,
   mounted-drive confinement, exact artifact/runtime verification, equal
-  device/thread budgets, greedy-only validation, measured host provenance, and
-  a CPU-only v1 guard until process VRAM can be measured honestly.
+  device/thread budgets, greedy-only validation, measured host provenance, a
+  CPU-only v1 guard until process VRAM can be measured honestly, and a distinct
+  signed GPU diagnostic profile that the v1 evaluator cannot accept.
 - Peak RSS is runtime-scoped: Transformers reports growth above its pre-runtime
   Python baseline, while llama.cpp reports its isolated server process tree.
   Both are sampled continuously during in-flight requests.
@@ -106,6 +138,8 @@ Thresholds were not changed after observing these results.
 - Every non-synthetic report is Ed25519-signed over the complete canonical JSON,
   including raw outcomes and metrics. The contract pins the public key and exact
   config SHA-256; the private key remains outside Git at mode `0600`.
+- The signer fingerprint is independently anchored outside this evidence
+  directory in `../../trusted-evidence-signers.json` and checked by tests.
 - Quantized drift remains advisory. Only the near-lossless lane can satisfy the
   quality gate, and only performance-fit recipes can earn speed/fit benefits.
 
@@ -117,24 +151,30 @@ Thresholds were not changed after observing these results.
 - `results.txt` — human-readable benchmark summary
 - `baseline.json` — distilled measurements for later comparison
 - `contract-evaluation.json` — fail-closed v1 verdict
+- `quality-parity-diagnosis.json` / `.md` — run/device-scoped signed-evidence summary
+- `summarize-quality-parity.py` — verifies both evidence chains and regenerates it
+- `gpu-diagnostic-config.json` — exact ROCm diagnostic artifacts and runtimes
+- `gpu-diagnostic-results.json` / `.txt` — signed GPU outcomes and summary
 - `commands.txt` — reproducible conversion, benchmark, evaluation, and test commands
 - `BLOCKED.md` — downstream stop-condition handoff
 - `known-unrelated-failure.md` — clean-base reproduction of the tracker race
+- `../../trusted-evidence-signers.json` — repository-reviewed signer fingerprint
 
 ## Verification
 
 ```text
-Targeted: 24 passed
-Full suite: 751 passed, 13 skipped
-Earlier cancellation retry matrix, DGR-001: 4/5 passed
+Targeted: 28 passed (5/5 consecutive focused runs)
+Latest full suite: 755 passed, 13 skipped
+Earlier full suite: 751 passed, 13 skipped
+Current cancellation retry matrix, DGR-001: 4/5 passed
 Earlier cancellation retry matrix, clean d904c40: 4/5 passed
 compileall: passed
 git diff --check: passed
 Evidence JSON parse/integrity checks: passed
 ```
 
-An earlier intermittent tracker cancellation race reproduced at the same rate on
-the clean base and is retained in `known-unrelated-failure.md`; the final suite
+The intermittent tracker cancellation race reproduced at the same rate on the
+clean base and is retained in `known-unrelated-failure.md`; the final full suite
 completed green. DGR-001 changes no tracker/proxy files.
 
 The earlier Ralph claim that the full suite was blocked by Protobuf 6.33.6 was
@@ -144,10 +184,12 @@ project `.venv`, which has the DGR-002-compatible runtime. Real inference used
 
 ## Limitations and dependent-story handoff
 
-- This is a **0.5B CPU baseline**, not evidence for a large model, Radeon GPU,
-  distributed execution, network transport, or native shard worker.
-- The installed llama.cpp build is CPU-only (`GGML_HIP=OFF`). No GPU comparison
-  is claimed.
+- The immutable contract result is a **0.5B CPU baseline**. The separate Radeon
+  diagnostic is real local GPU evidence, but neither result covers a large
+  model, distributed execution, network transport, or a native shard worker.
+- A separate `GGML_HIP=ON` llama.cpp build exists and produced GPU timings, but
+  llama-server process VRAM is not measurable by the current driver; GPU
+  memory/fit claims therefore remain ineligible for v1.
 - Absolute timings are developer-machine measurements; locked ratios and raw
   artifacts are provided for reproducibility.
 - DGR-014 may consume v1 only with the exact plan/evidence requirements enforced