fix: harden DGR-001 performance contract evidence

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

@@ -1,30 +1,43 @@
-# DGR-001 real-benchmark blocker
+# DGR-001 downstream stop-condition handoff
 
-Status: blocked only for the required real-model measurement. The deterministic
-harness, report schema, and immutable contract are implemented and tested; this
-file deliberately does not turn an unrun benchmark into a passing result.
+Status: **DGR-001 is complete; native-track promotion is blocked by the immutable v1 verdict.**
 
-## Verified environment state (2026-07-13)
+This is no longer an execution-prerequisite blocker. The required real benchmark
+ran successfully, every recipe completed at concurrency 1 and 4, artifacts were
+verified, and deterministic/full test gates passed.
 
-- Mounted GGUF artifacts exist under `/run/media/popov/DATA/llm/`.
-- `llama-server` is not on `PATH`.
-- The available Python test environment has neither `torch` nor `transformers`.
-- No matching local safetensors snapshot was found for an installed GGUF recipe.
+## Locked result
 
-Therefore this session cannot run the controlled same-model, same-revision,
-same-machine comparison without downloading/installing new runtime/model assets.
-That is intentionally not inferred from the story request.
+`contract-evaluation.json` records:
 
-## Continuation
+```text
+verdict: stop
+quality_lane_pass: false
+speed_benefit: true
+fit_benefit: true
+stop_condition_met: true
+```
 
-1. Put a matching safetensors snapshot and near-lossless plus quantized GGUF
-   artifacts below one mounted-drive root, never `/home`.
-2. Install or build the pinned `llama-server`, and use `.venv-rocm` when testing
-   the Radeon backend.
-3. Compute each artifact SHA-256 and create a config declaring the same
-   `source_model_id` and `source_model_revision` for every recipe.
-4. Run the command in `commands.txt` with
-   `MESHNET_ENABLE_REAL_INFERENCE_TESTS=1`; save its JSON report and summary in
-   this directory, then evaluate it against `performance-contract.json`.
-5. Only after those results and all quality gates pass may DGR-001 be marked
-   done and DGR-004 consume the baseline.
+The exact-revision BF16 GGUF quality lane compared every prompt but achieved
+`0.3333` exact match and `0.9471` mean similarity against the Transformers BF16
+reference. V1 requires `0.90` and `0.97`. Quantized Q4_K_M had substantial speed
+and fit benefits, but the contract explicitly forbids speed from redeeming a
+failed near-lossless quality lane.
+
+## Scope of this stop
+
+The measured baseline is Qwen2.5-0.5B on CPU using a CPU-only llama.cpp build.
+It is not a Radeon, large-model, distributed, or native-shard result. Therefore:
+
+1. Do not silently mark v1 promoted or weaken its thresholds after observing the
+   data.
+2. Do not let DGR-004 or later runtime stories treat DGR-001 completion as a
+   positive promotion signal.
+3. A human may choose one of these explicit paths:
+   - stop the native GGUF track as v1 directs;
+   - diagnose and fix the BF16 runtime divergence, then rerun the exact v1 plan;
+   - authorize a separately versioned GPU/large-model contract whose scope and
+     workload are locked before its measurements.
+
+All raw evidence, configuration, artifacts, hashes, and reproduction commands
+are in this directory and `README.md`.