feat: checkpoint distributed gguf runtime stories

packages/node/meshnet_node/performance_contract.py

@@ -71,6 +71,74 @@ class BenchmarkLane:
         }
 
 
+@dataclass(frozen=True)
+class BenchmarkWorkload:
+    """Identical request shape both recipes must run so speed stays comparable.
+
+    Pinning prompts, context lengths, output lengths, and sampling policy in the
+    versioned contract is what makes the safetensors-versus-GGUF numbers a
+    controlled comparison instead of two differently-configured runs.
+    """
+
+    prompts: tuple[str, ...]
+    context_lengths: tuple[int, ...]
+    output_lengths: tuple[int, ...]
+    sampling_policy: str
+
+    def to_dict(self) -> dict:
+        return {
+            "prompts": list(self.prompts),
+            "context_lengths": list(self.context_lengths),
+            "output_lengths": list(self.output_lengths),
+            "sampling_policy": self.sampling_policy,
+        }
+
+
+@dataclass(frozen=True)
+class QualityPolicy:
+    """Correctness/quality lane kept separate from the performance/fit lanes.
+
+    BF16 safetensors and Q2_K GGUF are not numerically equivalent, so quality is
+    measured as its own lane (output drift against the BF16 reference under a
+    documented tolerance) rather than assumed away by the speed/fit comparison.
+    """
+
+    statement: str
+    reference_lane_runtime: str
+    measured_lane_runtime: str
+    max_output_drift: float
+
+    def to_dict(self) -> dict:
+        return {
+            "statement": self.statement,
+            "reference_lane_runtime": self.reference_lane_runtime,
+            "measured_lane_runtime": self.measured_lane_runtime,
+            "max_output_drift": self.max_output_drift,
+        }
+
+
+@dataclass(frozen=True)
+class ReleaseGate:
+    """Versioned thresholds later release gates (DGR-014) consume unchanged.
+
+    Thresholds live in the contract, not in code, so the release gate cannot be
+    weakened after seeing implementation results.
+    """
+
+    min_decode_speedup: float
+    max_artifact_bytes_ratio: float
+    max_memory_bytes_ratio: float
+    max_quality_drift: float
+
+    def to_dict(self) -> dict:
+        return {
+            "min_decode_speedup": self.min_decode_speedup,
+            "max_artifact_bytes_ratio": self.max_artifact_bytes_ratio,
+            "max_memory_bytes_ratio": self.max_memory_bytes_ratio,
+            "max_quality_drift": self.max_quality_drift,
+        }
+
+
 @dataclass(frozen=True)
 class PerformanceContract:
     """Machine-readable contract for the DGR-001 benchmark story."""