feat: checkpoint distributed gguf runtime stories

packages/node/meshnet_node/doctor.py

@@ -36,6 +36,8 @@ from .capability import (
     CapabilityReport,
     build_capability_report,
 )
+from . import __version__ as _PACKAGE_VERSION
+from .runtime_recipe import build_runtime_recipe_identity
 from .recipe_manifest import (
     DEFAULT_RECIPE_ID,
     Recipe,
@@ -43,6 +45,7 @@ from .recipe_manifest import (
     RecipeManifestError,
     load_recipe_manifest,
 )
+from .gguf_ownership import authoritative_dense_llama_ownership
 
 # The probe is deliberately tiny: enough tokens to drive every layer in the
 # shard once, small enough that `doctor` costs seconds beyond the model load.
@@ -464,10 +467,28 @@ def _validate_recipe(
     duration_ms = int((time.monotonic() - started) * 1000)
 
     device = _backend_device(backend, selection)
+    ownership = authoritative_dense_llama_ownership(backend, selection)
+    runtime_recipe = build_runtime_recipe_identity(
+        model_id=selection.model_id,
+        revision=getattr(getattr(backend, "model", None), "revision", None),
+        model_config=_model_config(backend),
+        recipe_params=recipe.params,
+        weight_quantization=selection.quantization,
+        backend_id=recipe.backend_id,
+        runtime_version=_PACKAGE_VERSION,
+        activation_dtype="bfloat16",
+        compute_dtype=_backend_compute_dtype(backend),
+        kv_dtype=_backend_kv_dtype(backend),
+        kv_layout=_backend_kv_layout(backend),
+        tokenizer_revision=_backend_tokenizer_revision(backend, selection),
+        architecture_adapter=_backend_architecture_adapter(backend, recipe.backend_id),
+        boundary_schema_version=1,
+        cache_layout=_backend_cache_layout(backend, recipe.params),
+    )
     report = build_capability_report(
         model_id=selection.model_id,
-        shard_start=selection.shard_start,
-        shard_end=selection.shard_end,
+        shard_start=ownership.start_layer,
+        shard_end=ownership.end_layer,
         recipe_id=recipe.id,
         recipe_version=recipe.version,
         catalogue_version=manifest.catalogue_version,
@@ -477,6 +498,9 @@ def _validate_recipe(
         quantization=selection.quantization,
         runtime=_runtime_versions(),
         model_config=_model_config(backend),
+        runtime_recipe=runtime_recipe,
+        owns_embedding=ownership.owns_embedding,
+        owns_final_head=ownership.owns_final_head,
         status=STATUS_FAILED if category else STATUS_PASSED,
         duration_ms=duration_ms,
         diagnostics=[d for d in diagnostics if d] or None,
@@ -568,6 +592,65 @@ def _runtime_versions() -> dict[str, str]:
     return versions
 
 
+def _backend_compute_dtype(backend: Any) -> str:
+    config = getattr(getattr(backend, "model", None), "config", None)
+    for candidate in (config, getattr(config, "text_config", None)):
+        if candidate is None:
+            continue
+        for attr in ("dtype", "torch_dtype"):
+            value = getattr(candidate, attr, None)
+            if value is None:
+                continue
+            return str(value).removeprefix("torch.")
+    return "bfloat16"
+
+
+def _backend_kv_dtype(backend: Any) -> str:
+    return _backend_compute_dtype(backend)
+
+
+def _backend_kv_layout(backend: Any) -> str:
+    return "session-cache" if getattr(backend, "supports_kv_cache", False) else "stateless"
+
+
+def _backend_tokenizer_revision(backend: Any, selection: DoctorSelection) -> str:
+    model = getattr(backend, "model", None)
+    revision = getattr(model, "revision", None)
+    if isinstance(revision, str) and revision.strip():
+        return revision
+    return selection.model_id
+
+
+def _backend_architecture_adapter(backend: Any, default: str) -> str:
+    config = getattr(getattr(backend, "model", None), "config", None)
+    for candidate in (config, getattr(config, "text_config", None)):
+        if candidate is None:
+            continue
+        for attr in ("architecture_adapter", "model_type"):
+            value = getattr(candidate, attr, None)
+            if isinstance(value, str) and value.strip():
+                return value
+        architectures = getattr(candidate, "architectures", None)
+        if isinstance(architectures, (list, tuple)) and architectures:
+            first = architectures[0]
+            if isinstance(first, str) and first.strip():
+                return first
+    return default
+
+
+def _backend_cache_layout(backend: Any, recipe_params: Mapping[str, Any] | None) -> str:
+    if getattr(backend, "supports_kv_cache", False) is False:
+        return "stateless"
+    if recipe_params is None:
+        return "local-hot-kv"
+    if recipe_params.get("use_cache") is False:
+        return "stateless"
+    value = recipe_params.get("cache_layout")
+    if isinstance(value, str) and value.strip():
+        return value
+    return "local-hot-kv"
+
+
 # --- output -----------------------------------------------------------------
 
 DEFAULT_REPORT_FILENAME = "capability.json"