Skip to content

graflo.architecture.schema.context

Bounded schema context: the schema graph as a navigable, budgetable object.

Answers "what can I ask?" about a schema without touching a database. Every export here is layer 2 — pure logical model, no db, no data_source, no embeddings, no tokenizer.

Eager re-exports (this is a package boundary, not a lazy façade).

Modules:

Name Description
budget

Budget accounting for schema context payloads.
card

Compact orientation card: the cheapest useful thing to hand an agent first.
elision

What a bounded projection left out, and how to go and get it.
graph

Adjacency index over a schema's vertex types.
rank

Ranking vertex types by how useful they are to an agent orienting itself.
subschema

Bounded, seeded schema slicing.

Attributes

__all__ = ['BaseCard', 'Budget', 'BudgetAccounting', 'ConnectorCard', 'DatabaseProfileCard', 'EdgeCard', 'ElidedEdge', 'ElidedVertex', 'ElisionReport', 'EntryPoint', 'ManifestCard', 'RankingWeights', 'ResourceCard', 'SchemaCard', 'SchemaGraph', 'SchemaNeighborhood', 'SchemaPath', 'TransformCard', 'VertexCard', 'VertexSignals', 'build_card', 'build_connector_card', 'build_database_profile_card', 'build_edge_card', 'build_manifest_card', 'build_resource_card', 'build_transform_card', 'build_vertex_card', 'estimate_tokens', 'neighborhood_distances', 'score_vertices', 'subschema'] module-attribute

Classes

BaseCard

Bases: ConfigBaseModel

Common foundation for all card types.

Source code in graflo/architecture/schema/context/card.py 
31
32
33
34
35
36
37
38
39
class BaseCard(ConfigBaseModel):
    """Common foundation for all card types."""

    id: str | None = PydanticField(
        default=None, description="Optional stable identifier (UUID)."
    )
    estimated_tokens: int = PydanticField(
        default=0, description="Estimated token cost of this card."
    )

Attributes

estimated_tokens = PydanticField(default=0, description='Estimated token cost of this card.') class-attribute instance-attribute
id = PydanticField(default=None, description='Optional stable identifier (UUID).') class-attribute instance-attribute

Budget

Bases: ConfigBaseModel

Caller-requested ceilings on a schema context payload.

Source code in graflo/architecture/schema/context/budget.py 
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
class Budget(ConfigBaseModel):
    """Caller-requested ceilings on a schema context payload."""

    max_elements: int | None = PydanticField(
        default=60,
        description="Maximum vertices + edges in the slice. None disables the cap.",
        ge=1,
    )
    max_tokens: int | None = PydanticField(
        default=4000,
        description="Maximum estimated tokens for the serialized slice. None disables the cap.",
        ge=1,
    )
    max_properties_per_vertex: int | None = PydanticField(
        default=None,
        description=(
            "Maximum properties retained per vertex. Identity-bearing fields are "
            "never counted against this and never dropped."
        ),
        ge=1,
    )

Attributes

max_elements = PydanticField(default=60, description='Maximum vertices + edges in the slice. None disables the cap.', ge=1) class-attribute instance-attribute
max_properties_per_vertex = PydanticField(default=None, description='Maximum properties retained per vertex. Identity-bearing fields are never counted against this and never dropped.', ge=1) class-attribute instance-attribute
max_tokens = PydanticField(default=4000, description='Maximum estimated tokens for the serialized slice. None disables the cap.', ge=1) class-attribute instance-attribute

BudgetAccounting

Bases: ConfigBaseModel

What the budget actually cost, measured rather than assumed.

Source code in graflo/architecture/schema/context/budget.py 
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
class BudgetAccounting(ConfigBaseModel):
    """What the budget actually cost, measured rather than assumed."""

    requested: Budget = PydanticField(..., description="The budget as asked for.")
    elements_used: int = PydanticField(
        ..., description="Vertices + edges admitted into the slice."
    )
    estimated_tokens: int = PydanticField(
        ..., description="Token estimate for the assembled slice."
    )
    serialized_chars: int = PydanticField(
        ...,
        description=(
            "Exact character count of the compact serialization. Lets a caller "
            "re-estimate with a real tokenizer without trusting CHARS_PER_TOKEN."
        ),
    )
    exhausted_by: Literal["elements", "tokens", "none"] = PydanticField(
        ..., description="Which ceiling stopped admission, if any."
    )

Attributes

elements_used = PydanticField(..., description='Vertices + edges admitted into the slice.') class-attribute instance-attribute
estimated_tokens = PydanticField(..., description='Token estimate for the assembled slice.') class-attribute instance-attribute
exhausted_by = PydanticField(..., description='Which ceiling stopped admission, if any.') class-attribute instance-attribute
requested = PydanticField(..., description='The budget as asked for.') class-attribute instance-attribute
serialized_chars = PydanticField(..., description='Exact character count of the compact serialization. Lets a caller re-estimate with a real tokenizer without trusting CHARS_PER_TOKEN.') class-attribute instance-attribute

ConnectorCard

Bases: BaseCard

Summary of a data connector (File, Table, etc.).

Source code in graflo/architecture/schema/context/card.py 
281
282
283
284
285
286
287
288
289
290
291
292
293
class ConnectorCard(BaseCard):
    """Summary of a data connector (File, Table, etc.)."""

    type: str = PydanticField(
        ..., description="Connector class name (FileConnector, etc.)."
    )
    name: str | None = PydanticField(default=None, description="Authored name.")
    resource_name: str | None = PydanticField(
        default=None, description="Primary resource name bound to this connector."
    )
    summary: str | None = PydanticField(
        default=None, description="Type-specific summary (e.g. path, table name)."
    )

Attributes

name = PydanticField(default=None, description='Authored name.') class-attribute instance-attribute
resource_name = PydanticField(default=None, description='Primary resource name bound to this connector.') class-attribute instance-attribute
summary = PydanticField(default=None, description='Type-specific summary (e.g. path, table name).') class-attribute instance-attribute
type = PydanticField(..., description='Connector class name (FileConnector, etc.).') class-attribute instance-attribute

DatabaseProfileCard

Bases: BaseCard

Summary of physical DB features.

Source code in graflo/architecture/schema/context/card.py 
296
297
298
299
300
301
302
303
304
305
306
307
308
class DatabaseProfileCard(BaseCard):
    """Summary of physical DB features."""

    db_flavor: str = PydanticField(..., description="Target DB flavor.")
    vertex_index_count: int = PydanticField(
        default=0, description="Total secondary vertex indexes."
    )
    edge_spec_count: int = PydanticField(
        default=0, description="Total physical edge specifications."
    )
    target_namespace: str | None = PydanticField(
        default=None, description="LPG namespace override."
    )

Attributes

db_flavor = PydanticField(..., description='Target DB flavor.') class-attribute instance-attribute
edge_spec_count = PydanticField(default=0, description='Total physical edge specifications.') class-attribute instance-attribute
target_namespace = PydanticField(default=None, description='LPG namespace override.') class-attribute instance-attribute
vertex_index_count = PydanticField(default=0, description='Total secondary vertex indexes.') class-attribute instance-attribute

EdgeCard

Bases: BaseCard

Summary of a single edge type.

Source code in graflo/architecture/schema/context/card.py 
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
class EdgeCard(BaseCard):
    """Summary of a single edge type."""

    source: str = PydanticField(..., description="Source vertex type name.")
    target: str = PydanticField(..., description="Target vertex type name.")
    relation: str | None = PydanticField(
        default=None, description="Relation type name."
    )
    directed: bool = PydanticField(
        default=True, description="True if source->target order matters."
    )
    symmetric: bool = PydanticField(
        default=False,
        description="True if the relation is declared its own inverse.",
    )
    inverse: str | None = PydanticField(
        default=None,
        description=(
            "Declared inverse relation: the name for reading this edge from its "
            "target. Usable in a query whether or not anything is stored under it."
        ),
    )
    inverse_state: str | None = PydanticField(
        default=None,
        description=(
            "State of the declared pair: declared (nothing stored; the inverse "
            "reads this edge from its target), native (the database maintains "
            "it), materialized (a declared edge of its own), or partial / "
            "conflicting."
        ),
    )
    identity_count: int = PydanticField(
        default=0, description="Number of logical uniqueness keys."
    )
    property_count: int = PydanticField(
        default=0, description="Total declared properties."
    )
    description: str | None = PydanticField(
        default=None, description="Authored description."
    )

Attributes

description = PydanticField(default=None, description='Authored description.') class-attribute instance-attribute
directed = PydanticField(default=True, description='True if source->target order matters.') class-attribute instance-attribute
identity_count = PydanticField(default=0, description='Number of logical uniqueness keys.') class-attribute instance-attribute
inverse = PydanticField(default=None, description='Declared inverse relation: the name for reading this edge from its target. Usable in a query whether or not anything is stored under it.') class-attribute instance-attribute
inverse_state = PydanticField(default=None, description='State of the declared pair: declared (nothing stored; the inverse reads this edge from its target), native (the database maintains it), materialized (a declared edge of its own), or partial / conflicting.') class-attribute instance-attribute
property_count = PydanticField(default=0, description='Total declared properties.') class-attribute instance-attribute
relation = PydanticField(default=None, description='Relation type name.') class-attribute instance-attribute
source = PydanticField(..., description='Source vertex type name.') class-attribute instance-attribute
symmetric = PydanticField(default=False, description='True if the relation is declared its own inverse.') class-attribute instance-attribute
target = PydanticField(..., description='Target vertex type name.') class-attribute instance-attribute

ElidedEdge

Bases: ConfigBaseModel

An edge left out of the slice.

Source code in graflo/architecture/schema/context/elision.py 
40
41
42
43
44
45
46
47
class ElidedEdge(ConfigBaseModel):
    """An edge left out of the slice."""

    edge_id: EdgeId = PydanticField(..., description="(source, target, relation).")
    reason: EdgeElisionReason = PydanticField(..., description="Why it was dropped.")
    description: str | None = PydanticField(
        default=None, description="Authored description, kept for the same reason."
    )

Attributes

description = PydanticField(default=None, description='Authored description, kept for the same reason.') class-attribute instance-attribute
edge_id = PydanticField(..., description='(source, target, relation).') class-attribute instance-attribute
reason = PydanticField(..., description='Why it was dropped.') class-attribute instance-attribute

ElidedVertex

Bases: ConfigBaseModel

A vertex type left out of the slice.

Source code in graflo/architecture/schema/context/elision.py 
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
class ElidedVertex(ConfigBaseModel):
    """A vertex type left out of the slice."""

    name: str = PydanticField(..., description="Vertex type name.")
    reason: VertexElisionReason = PydanticField(..., description="Why it was dropped.")
    degree: int = PydanticField(..., description="Incident edges in the full schema.")
    hop_distance: int | None = PydanticField(
        default=None, description="Hops from the nearest seed; None when unreachable."
    )
    description: str | None = PydanticField(
        default=None,
        description="Authored description, kept because it may be the reason to drill in.",
    )
    drill_in: str = PydanticField(
        ..., description="Call that would bring this type into a slice."
    )

Attributes

degree = PydanticField(..., description='Incident edges in the full schema.') class-attribute instance-attribute
description = PydanticField(default=None, description='Authored description, kept because it may be the reason to drill in.') class-attribute instance-attribute
drill_in = PydanticField(..., description='Call that would bring this type into a slice.') class-attribute instance-attribute
hop_distance = PydanticField(default=None, description='Hops from the nearest seed; None when unreachable.') class-attribute instance-attribute
name = PydanticField(..., description='Vertex type name.') class-attribute instance-attribute
reason = PydanticField(..., description='Why it was dropped.') class-attribute instance-attribute

ElisionReport

Bases: ConfigBaseModel

Everything the slice does not contain, plus the budget that caused it.

Source code in graflo/architecture/schema/context/elision.py 
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
class ElisionReport(ConfigBaseModel):
    """Everything the slice does not contain, plus the budget that caused it."""

    elided_vertices: list[ElidedVertex] = PydanticField(
        default_factory=list, description="Vertex types not in the slice."
    )
    elided_edges: list[ElidedEdge] = PydanticField(
        default_factory=list, description="Edges not in the slice."
    )
    elided_properties: dict[str, list[str]] = PydanticField(
        default_factory=dict,
        description="Vertex type -> property names dropped from a surviving type.",
    )
    budget: BudgetAccounting = PydanticField(
        ..., description="Measured cost of the slice."
    )

    @property
    def truncated(self) -> bool:
        """Whether anything at all was left out."""
        return bool(self.elided_vertices or self.elided_edges or self.elided_properties)

Attributes

budget = PydanticField(..., description='Measured cost of the slice.') class-attribute instance-attribute
elided_edges = PydanticField(default_factory=list, description='Edges not in the slice.') class-attribute instance-attribute
elided_properties = PydanticField(default_factory=dict, description='Vertex type -> property names dropped from a surviving type.') class-attribute instance-attribute
elided_vertices = PydanticField(default_factory=list, description='Vertex types not in the slice.') class-attribute instance-attribute
truncated property

Whether anything at all was left out.

EntryPoint

Bases: ConfigBaseModel

A vertex type an agent can look up directly.

The single most useful fact about an unfamiliar graph: a type with a natural identity and a secondary index is one you can filter on cheaply, which is where a query should start.

Source code in graflo/architecture/schema/context/card.py 
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
class EntryPoint(ConfigBaseModel):
    """A vertex type an agent can look up directly.

    The single most useful fact about an unfamiliar graph: a type with a natural
    identity *and* a secondary index is one you can filter on cheaply, which is
    where a query should start.
    """

    name: str = PydanticField(..., description="Vertex type name.")
    identity: list[str] = PydanticField(
        ..., description="Primary identity field names."
    )
    identity_mode: str = PydanticField(
        ..., description="natural / hash / assigned / blank."
    )
    secondary_identities: list[str] = PydanticField(
        default_factory=list, description="Declared secondary identity names."
    )
    indexed_fields: list[list[str]] = PydanticField(
        default_factory=list, description="Secondary index field-sets on this type."
    )
    description: str | None = PydanticField(
        default=None, description="Authored description, if any."
    )

Attributes

description = PydanticField(default=None, description='Authored description, if any.') class-attribute instance-attribute
identity = PydanticField(..., description='Primary identity field names.') class-attribute instance-attribute
identity_mode = PydanticField(..., description='natural / hash / assigned / blank.') class-attribute instance-attribute
indexed_fields = PydanticField(default_factory=list, description='Secondary index field-sets on this type.') class-attribute instance-attribute
name = PydanticField(..., description='Vertex type name.') class-attribute instance-attribute
secondary_identities = PydanticField(default_factory=list, description='Declared secondary identity names.') class-attribute instance-attribute

ManifestCard

Bases: BaseCard

Summary of a whole GraphManifest.

Source code in graflo/architecture/schema/context/card.py 
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
class ManifestCard(BaseCard):
    """Summary of a whole GraphManifest."""

    name: str | None = PydanticField(default=None, description="Manifest name.")
    version: str | None = PydanticField(default=None, description="Manifest version.")
    has_schema: bool = PydanticField(..., description="Presence of schema block.")
    has_ingestion: bool = PydanticField(..., description="Presence of ingestion block.")
    has_bindings: bool = PydanticField(..., description="Presence of bindings block.")
    vertex_count: int | None = PydanticField(
        default=None, description="Vertex count if schema present."
    )
    edge_count: int | None = PydanticField(
        default=None, description="Edge count if schema present."
    )
    resource_count: int | None = PydanticField(
        default=None, description="Resource count if ingestion present."
    )

Attributes

edge_count = PydanticField(default=None, description='Edge count if schema present.') class-attribute instance-attribute
has_bindings = PydanticField(..., description='Presence of bindings block.') class-attribute instance-attribute
has_ingestion = PydanticField(..., description='Presence of ingestion block.') class-attribute instance-attribute
has_schema = PydanticField(..., description='Presence of schema block.') class-attribute instance-attribute
name = PydanticField(default=None, description='Manifest name.') class-attribute instance-attribute
resource_count = PydanticField(default=None, description='Resource count if ingestion present.') class-attribute instance-attribute
version = PydanticField(default=None, description='Manifest version.') class-attribute instance-attribute
vertex_count = PydanticField(default=None, description='Vertex count if schema present.') class-attribute instance-attribute

RankingWeights

Bases: ConfigBaseModel

Relative weight of each local signal. Weights need not sum to 1.

Source code in graflo/architecture/schema/context/rank.py 
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
class RankingWeights(ConfigBaseModel):
    """Relative weight of each local signal. Weights need not sum to 1."""

    hop_decay: float = PydanticField(
        default=0.55,
        description="Score multiplier per hop of distance from the nearest seed.",
        gt=0.0,
        le=1.0,
    )
    degree: float = PydanticField(
        default=0.20, description="Weight of normalized incident-edge count.", ge=0.0
    )
    identity: float = PydanticField(
        default=0.15, description="Weight of identity-mode strength.", ge=0.0
    )
    properties: float = PydanticField(
        default=0.10, description="Weight of log-scaled property count.", ge=0.0
    )
    indexed: float = PydanticField(
        default=0.10,
        description="Weight of secondary-index presence (cheap to filter on).",
        ge=0.0,
    )

Attributes

degree = PydanticField(default=0.2, description='Weight of normalized incident-edge count.', ge=0.0) class-attribute instance-attribute
hop_decay = PydanticField(default=0.55, description='Score multiplier per hop of distance from the nearest seed.', gt=0.0, le=1.0) class-attribute instance-attribute
identity = PydanticField(default=0.15, description='Weight of identity-mode strength.', ge=0.0) class-attribute instance-attribute
indexed = PydanticField(default=0.1, description='Weight of secondary-index presence (cheap to filter on).', ge=0.0) class-attribute instance-attribute
properties = PydanticField(default=0.1, description='Weight of log-scaled property count.', ge=0.0) class-attribute instance-attribute

ResourceCard

Bases: BaseCard

Summary of an ingestion resource.

Source code in graflo/architecture/schema/context/card.py 
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
class ResourceCard(BaseCard):
    """Summary of an ingestion resource."""

    name: str = PydanticField(..., description="Resource name.")
    actor_count: int = PydanticField(default=0, description="Number of pipeline steps.")
    vertex_targets: list[str] = PydanticField(
        default_factory=list, description="Top vertex types this resource writes to."
    )
    edge_targets: list[str] = PydanticField(
        default_factory=list, description="Top edge types this resource writes to."
    )
    encoding: str = PydanticField(default="utf-8", description="Character encoding.")
    infer_edges: bool = PydanticField(
        default=True, description="True if greedy edge inference is enabled."
    )

Attributes

actor_count = PydanticField(default=0, description='Number of pipeline steps.') class-attribute instance-attribute
edge_targets = PydanticField(default_factory=list, description='Top edge types this resource writes to.') class-attribute instance-attribute
encoding = PydanticField(default='utf-8', description='Character encoding.') class-attribute instance-attribute
infer_edges = PydanticField(default=True, description='True if greedy edge inference is enabled.') class-attribute instance-attribute
name = PydanticField(..., description='Resource name.') class-attribute instance-attribute
vertex_targets = PydanticField(default_factory=list, description='Top vertex types this resource writes to.') class-attribute instance-attribute

SchemaCard

Bases: BaseCard

Bounded orientation summary of a whole schema.

Source code in graflo/architecture/schema/context/card.py 
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
class SchemaCard(BaseCard):
    """Bounded orientation summary of a whole schema."""

    name: str = PydanticField(..., description="Schema name.")
    version: str | None = PydanticField(default=None, description="Schema version.")
    description: str | None = PydanticField(
        default=None, description="Authored schema description."
    )
    db_flavor: str = PydanticField(
        ..., description="Target database flavor from the db profile."
    )
    vertex_count: int = PydanticField(..., description="Declared vertex types.")
    edge_count: int = PydanticField(..., description="Declared edges.")
    total_property_count: int = PydanticField(
        ..., description="Declared properties across all vertex types."
    )
    hub_types: list[VertexSignals] = PydanticField(
        default_factory=list, description="Highest-ranked types, most central first."
    )
    entry_points: list[EntryPoint] = PydanticField(
        default_factory=list, description="Types that can be looked up directly."
    )
    identity_modes: dict[str, int] = PydanticField(
        default_factory=dict, description="Histogram of vertex identity modes."
    )
    isolated_types: list[str] = PydanticField(
        default_factory=list,
        description="Vertex types with no incident edge, truncated to ``max_names``.",
    )
    isolated_type_count: int = PydanticField(
        default=0, description="Total isolated types, including any not listed."
    )
    relation_vocabulary: list[str] = PydanticField(
        default_factory=list,
        description="Distinct edge relation names, truncated to ``max_names``.",
    )
    relation_count: int = PydanticField(
        default=0, description="Total distinct relations, including any not listed."
    )

Attributes

db_flavor = PydanticField(..., description='Target database flavor from the db profile.') class-attribute instance-attribute
description = PydanticField(default=None, description='Authored schema description.') class-attribute instance-attribute
edge_count = PydanticField(..., description='Declared edges.') class-attribute instance-attribute
entry_points = PydanticField(default_factory=list, description='Types that can be looked up directly.') class-attribute instance-attribute
hub_types = PydanticField(default_factory=list, description='Highest-ranked types, most central first.') class-attribute instance-attribute
identity_modes = PydanticField(default_factory=dict, description='Histogram of vertex identity modes.') class-attribute instance-attribute
isolated_type_count = PydanticField(default=0, description='Total isolated types, including any not listed.') class-attribute instance-attribute
isolated_types = PydanticField(default_factory=list, description='Vertex types with no incident edge, truncated to ``max_names``.') class-attribute instance-attribute
name = PydanticField(..., description='Schema name.') class-attribute instance-attribute
relation_count = PydanticField(default=0, description='Total distinct relations, including any not listed.') class-attribute instance-attribute
relation_vocabulary = PydanticField(default_factory=list, description='Distinct edge relation names, truncated to ``max_names``.') class-attribute instance-attribute
total_property_count = PydanticField(..., description='Declared properties across all vertex types.') class-attribute instance-attribute
version = PydanticField(default=None, description='Schema version.') class-attribute instance-attribute
vertex_count = PydanticField(..., description='Declared vertex types.') class-attribute instance-attribute

SchemaGraph

Read-only adjacency index over a :class:Schema's vertex types.

Built once per schema and never mutates it. Plain dicts throughout — no networkx, because this is layer 2 and the whole point is to stay free of heavyweight dependencies.

Source code in graflo/architecture/schema/context/graph.py 
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
class SchemaGraph:
    """Read-only adjacency index over a :class:`Schema`'s vertex types.

    Built once per schema and never mutates it. Plain dicts throughout — no
    networkx, because this is layer 2 and the whole point is to stay free of
    heavyweight dependencies.
    """

    def __init__(self, schema: Schema) -> None:
        self._schema = schema
        core = schema.core_schema
        self._vertex_types = frozenset(core.vertex_config.vertex_set)
        self._out: dict[str, list[EdgeId]] = {name: [] for name in self._vertex_types}
        self._in: dict[str, list[EdgeId]] = {name: [] for name in self._vertex_types}
        self._edges: dict[EdgeId, Edge] = {}

        for edge in core.edge_config.edges:
            edge_id = edge.edge_id
            self._edges[edge_id] = edge
            source, target, _relation = edge_id
            if source in self._out:
                self._out[source].append(edge_id)
            if target in self._in:
                self._in[target].append(edge_id)

        for adjacency in (self._out, self._in):
            for edge_ids in adjacency.values():
                edge_ids.sort(key=edge_sort_key)

    @classmethod
    def from_schema(cls, schema: Schema) -> SchemaGraph:
        """Build an index for *schema*."""
        return cls(schema)

    @property
    def schema(self) -> Schema:
        """The indexed schema. Treat as read-only."""
        return self._schema

    @property
    def vertex_types(self) -> frozenset[str]:
        """Every declared vertex type name."""
        return self._vertex_types

    @property
    def edge_ids(self) -> list[EdgeId]:
        """Every declared edge id, in deterministic order."""
        return sorted(self._edges, key=edge_sort_key)

    def edge(self, edge_id: EdgeId) -> Edge:
        """Return the declared edge for *edge_id*."""
        return self._edges[edge_id]

    def out_edges(self, vertex_type: str) -> list[EdgeId]:
        """Edges whose source is *vertex_type*."""
        return list(self._out.get(vertex_type, []))

    def in_edges(self, vertex_type: str) -> list[EdgeId]:
        """Edges whose target is *vertex_type*."""
        return list(self._in.get(vertex_type, []))

    def degree(self, vertex_type: str) -> int:
        """Total incident edge count (out + in), counting self-loops twice."""
        return len(self._out.get(vertex_type, [])) + len(self._in.get(vertex_type, []))

    def isolated_types(self) -> list[str]:
        """Vertex types with no incident edge at all."""
        return sorted(name for name in self._vertex_types if self.degree(name) == 0)

    def relation_vocabulary(self) -> list[str]:
        """Distinct relation names a query over this schema may use.

        The names that label declared edges, plus the declared inverse of each:
        an inverse is a valid name for reading its edge from the target, whether
        it is stored, maintained by the database, or only declared.
        """
        edge_config = self._schema.core_schema.edge_config
        stored = {
            relation
            for _source, _target, relation in self._edges
            if relation is not None
        }
        inverses = {edge_config.inverse_of(relation) for relation in stored}
        return sorted(stored | {name for name in inverses if name is not None})

    def _traversable(
        self,
        edge_id: EdgeId,
        anchor: str,
        direction: EdgeDirection,
    ) -> str | None:
        """Return the far endpoint when *edge_id* may be followed from *anchor*.

        An edge declared ``directed=False`` is traversable both ways regardless of
        the requested direction — the same rule
        :func:`~graflo.db.edge_direction_support.default_direction_for_edge`
        applies on the instance plane.
        """
        source, target, _relation = edge_id
        undirected = not self._edges[edge_id].directed
        effective = EdgeDirection.ANY if undirected else direction

        forward = source == anchor and effective in (
            EdgeDirection.OUT,
            EdgeDirection.ANY,
        )
        backward = target == anchor and effective in (
            EdgeDirection.IN,
            EdgeDirection.ANY,
        )
        if forward:
            return target
        if backward:
            return source
        return None

    def _incident(self, vertex_type: str) -> list[EdgeId]:
        """Every edge touching *vertex_type*, deduplicated (self-loops appear once)."""
        seen: set[EdgeId] = set()
        incident: list[EdgeId] = []
        for edge_id in self._out.get(vertex_type, []) + self._in.get(vertex_type, []):
            if edge_id in seen:
                continue
            seen.add(edge_id)
            incident.append(edge_id)
        return sorted(incident, key=edge_sort_key)

    def schema_neighbors(
        self,
        vertex_type: str,
        *,
        hops: int = 1,
        direction: EdgeDirection = EdgeDirection.ANY,
        edge_relations: set[str | None] | None = None,
        edge_ids: set[EdgeId] | None = None,
    ) -> SchemaNeighborhood:
        """Vertex types adjacent to *vertex_type* within *hops*.

        Args:
            vertex_type: Seed vertex type. Must be declared.
            hops: Maximum hop distance. ``0`` returns just the seed.
            direction: Orientation followed from each frontier vertex. Defaults to
                :attr:`EdgeDirection.ANY` — deliberately unlike
                ``Connection.fetch_edges``, which defaults to ``OUT``. "What is
                adjacent to ``person`` in the schema" almost never means "only
                where person is the source"; an agent asking that wants the whole
                local shape. Edges declared ``directed=False`` are followed both
                ways whatever is requested here.
            edge_relations: Restrict traversal to these relation names (``None`` is
                a valid member, matching edges with no relation).
            edge_ids: Restrict traversal to these exact edges. Finer-grained than
                *edge_relations*, which cannot separate two dyads sharing one
                relation name. Both filters apply when both are given.

        Returns:
            SchemaNeighborhood: distances per reachable type and the edges used.

        Raises:
            KeyError: if *vertex_type* is not declared in the schema.
        """
        if vertex_type not in self._vertex_types:
            raise KeyError(
                f"Unknown vertex type {vertex_type!r}; declared: {sorted(self._vertex_types)}"
            )
        if hops < 0:
            raise ValueError(f"hops must be >= 0, got {hops}")

        distances: dict[str, int] = {vertex_type: 0}
        used: set[EdgeId] = set()
        frontier: deque[tuple[str, int]] = deque([(vertex_type, 0)])

        while frontier:
            current, depth = frontier.popleft()
            if depth >= hops:
                continue
            for edge_id in self._incident(current):
                if edge_relations is not None and edge_id[2] not in edge_relations:
                    continue
                if edge_ids is not None and edge_id not in edge_ids:
                    continue
                far = self._traversable(edge_id, current, direction)
                if far is None:
                    continue
                used.add(edge_id)
                if far not in distances:
                    distances[far] = depth + 1
                    frontier.append((far, depth + 1))

        return SchemaNeighborhood(
            origin=vertex_type,
            hops=hops,
            direction=direction,
            distances=distances,
            edges=sorted(used, key=edge_sort_key),
        )

    def relations_between(
        self,
        a: str,
        b: str,
        *,
        max_len: int = 3,
        max_paths: int = 20,
        direction: EdgeDirection = EdgeDirection.ANY,
    ) -> list[SchemaPath]:
        """Simple paths from vertex type *a* to *b*, shortest first.

        Bounded breadth-first enumeration: no vertex repeats within a path, so
        cycles terminate. Results are ordered by ``(length, edge ids)`` and are
        therefore reproducible run to run.

        Args:
            a: Source vertex type.
            b: Target vertex type.
            max_len: Maximum hops per path.
            max_paths: Maximum number of paths returned.
            direction: Orientation followed from each frontier vertex.

        Returns:
            list[SchemaPath]: paths found, possibly empty.

        Raises:
            KeyError: if either endpoint is not declared in the schema.
        """
        for name in (a, b):
            if name not in self._vertex_types:
                raise KeyError(
                    f"Unknown vertex type {name!r}; declared: {sorted(self._vertex_types)}"
                )
        if max_len < 1 or max_paths < 1:
            return []

        found: list[SchemaPath] = []
        queue: deque[tuple[str, list[str], list[EdgeId]]] = deque([(a, [a], [])])

        while queue and len(found) < max_paths:
            current, vertices, edges = queue.popleft()
            if len(edges) >= max_len:
                continue
            for edge_id in self._incident(current):
                far = self._traversable(edge_id, current, direction)
                if far is None:
                    continue
                # Paths stay simple, except that reaching the target closes the
                # walk — which is what makes ``relations_between(a, a)`` return
                # self-loops and cycles rather than nothing.
                if far in vertices and far != b:
                    continue
                next_vertices = [*vertices, far]
                next_edges = [*edges, edge_id]
                if far == b:
                    found.append(SchemaPath(vertices=next_vertices, edges=next_edges))
                    if len(found) >= max_paths:
                        break
                else:
                    queue.append((far, next_vertices, next_edges))

        found.sort(
            key=lambda path: (path.length, [edge_sort_key(e) for e in path.edges])
        )
        return found[:max_paths]

Attributes

edge_ids property

Every declared edge id, in deterministic order.

schema property

The indexed schema. Treat as read-only.

vertex_types property

Every declared vertex type name.

Methods:

__init__(schema)
Source code in graflo/architecture/schema/context/graph.py 
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
def __init__(self, schema: Schema) -> None:
    self._schema = schema
    core = schema.core_schema
    self._vertex_types = frozenset(core.vertex_config.vertex_set)
    self._out: dict[str, list[EdgeId]] = {name: [] for name in self._vertex_types}
    self._in: dict[str, list[EdgeId]] = {name: [] for name in self._vertex_types}
    self._edges: dict[EdgeId, Edge] = {}

    for edge in core.edge_config.edges:
        edge_id = edge.edge_id
        self._edges[edge_id] = edge
        source, target, _relation = edge_id
        if source in self._out:
            self._out[source].append(edge_id)
        if target in self._in:
            self._in[target].append(edge_id)

    for adjacency in (self._out, self._in):
        for edge_ids in adjacency.values():
            edge_ids.sort(key=edge_sort_key)
degree(vertex_type)

Total incident edge count (out + in), counting self-loops twice.

Source code in graflo/architecture/schema/context/graph.py 
135
136
137
def degree(self, vertex_type: str) -> int:
    """Total incident edge count (out + in), counting self-loops twice."""
    return len(self._out.get(vertex_type, [])) + len(self._in.get(vertex_type, []))
edge(edge_id)

Return the declared edge for edge_id.

Source code in graflo/architecture/schema/context/graph.py 
123
124
125
def edge(self, edge_id: EdgeId) -> Edge:
    """Return the declared edge for *edge_id*."""
    return self._edges[edge_id]
from_schema(schema) classmethod

Build an index for schema.

Source code in graflo/architecture/schema/context/graph.py 
103
104
105
106
@classmethod
def from_schema(cls, schema: Schema) -> SchemaGraph:
    """Build an index for *schema*."""
    return cls(schema)
in_edges(vertex_type)

Edges whose target is vertex_type.

Source code in graflo/architecture/schema/context/graph.py 
131
132
133
def in_edges(self, vertex_type: str) -> list[EdgeId]:
    """Edges whose target is *vertex_type*."""
    return list(self._in.get(vertex_type, []))
isolated_types()

Vertex types with no incident edge at all.

Source code in graflo/architecture/schema/context/graph.py 
139
140
141
def isolated_types(self) -> list[str]:
    """Vertex types with no incident edge at all."""
    return sorted(name for name in self._vertex_types if self.degree(name) == 0)
out_edges(vertex_type)

Edges whose source is vertex_type.

Source code in graflo/architecture/schema/context/graph.py 
127
128
129
def out_edges(self, vertex_type: str) -> list[EdgeId]:
    """Edges whose source is *vertex_type*."""
    return list(self._out.get(vertex_type, []))
relation_vocabulary()

Distinct relation names a query over this schema may use.

The names that label declared edges, plus the declared inverse of each: an inverse is a valid name for reading its edge from the target, whether it is stored, maintained by the database, or only declared.

Source code in graflo/architecture/schema/context/graph.py 
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
def relation_vocabulary(self) -> list[str]:
    """Distinct relation names a query over this schema may use.

    The names that label declared edges, plus the declared inverse of each:
    an inverse is a valid name for reading its edge from the target, whether
    it is stored, maintained by the database, or only declared.
    """
    edge_config = self._schema.core_schema.edge_config
    stored = {
        relation
        for _source, _target, relation in self._edges
        if relation is not None
    }
    inverses = {edge_config.inverse_of(relation) for relation in stored}
    return sorted(stored | {name for name in inverses if name is not None})
relations_between(a, b, *, max_len=3, max_paths=20, direction=EdgeDirection.ANY)

Simple paths from vertex type a to b, shortest first.

Bounded breadth-first enumeration: no vertex repeats within a path, so cycles terminate. Results are ordered by (length, edge ids) and are therefore reproducible run to run.

Parameters:

Name Type Description Default
a str

Source vertex type.

 required
b str

Target vertex type.

 required
max_len int

Maximum hops per path.

 3
max_paths int

Maximum number of paths returned.

 20
direction EdgeDirection

Orientation followed from each frontier vertex.

 ANY

Returns:

Type Description
list[SchemaPath]

list[SchemaPath]: paths found, possibly empty.

Raises:

Type Description
KeyError

if either endpoint is not declared in the schema.
Source code in graflo/architecture/schema/context/graph.py 
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
def relations_between(
    self,
    a: str,
    b: str,
    *,
    max_len: int = 3,
    max_paths: int = 20,
    direction: EdgeDirection = EdgeDirection.ANY,
) -> list[SchemaPath]:
    """Simple paths from vertex type *a* to *b*, shortest first.

    Bounded breadth-first enumeration: no vertex repeats within a path, so
    cycles terminate. Results are ordered by ``(length, edge ids)`` and are
    therefore reproducible run to run.

    Args:
        a: Source vertex type.
        b: Target vertex type.
        max_len: Maximum hops per path.
        max_paths: Maximum number of paths returned.
        direction: Orientation followed from each frontier vertex.

    Returns:
        list[SchemaPath]: paths found, possibly empty.

    Raises:
        KeyError: if either endpoint is not declared in the schema.
    """
    for name in (a, b):
        if name not in self._vertex_types:
            raise KeyError(
                f"Unknown vertex type {name!r}; declared: {sorted(self._vertex_types)}"
            )
    if max_len < 1 or max_paths < 1:
        return []

    found: list[SchemaPath] = []
    queue: deque[tuple[str, list[str], list[EdgeId]]] = deque([(a, [a], [])])

    while queue and len(found) < max_paths:
        current, vertices, edges = queue.popleft()
        if len(edges) >= max_len:
            continue
        for edge_id in self._incident(current):
            far = self._traversable(edge_id, current, direction)
            if far is None:
                continue
            # Paths stay simple, except that reaching the target closes the
            # walk — which is what makes ``relations_between(a, a)`` return
            # self-loops and cycles rather than nothing.
            if far in vertices and far != b:
                continue
            next_vertices = [*vertices, far]
            next_edges = [*edges, edge_id]
            if far == b:
                found.append(SchemaPath(vertices=next_vertices, edges=next_edges))
                if len(found) >= max_paths:
                    break
            else:
                queue.append((far, next_vertices, next_edges))

    found.sort(
        key=lambda path: (path.length, [edge_sort_key(e) for e in path.edges])
    )
    return found[:max_paths]
schema_neighbors(vertex_type, *, hops=1, direction=EdgeDirection.ANY, edge_relations=None, edge_ids=None)

Vertex types adjacent to vertex_type within hops.

Parameters:

Name Type Description Default
vertex_type str

Seed vertex type. Must be declared.

 required
hops int

Maximum hop distance. 0 returns just the seed.

 1
direction EdgeDirection

Orientation followed from each frontier vertex. Defaults to :attr:EdgeDirection.ANY — deliberately unlike Connection.fetch_edges, which defaults to OUT. "What is adjacent to person in the schema" almost never means "only where person is the source"; an agent asking that wants the whole local shape. Edges declared directed=False are followed both ways whatever is requested here.

 ANY
edge_relations set[str | None] | None

Restrict traversal to these relation names (None is a valid member, matching edges with no relation).

 None
edge_ids set[EdgeId] | None

Restrict traversal to these exact edges. Finer-grained than edge_relations, which cannot separate two dyads sharing one relation name. Both filters apply when both are given.

 None

Returns:

Name Type Description
SchemaNeighborhood SchemaNeighborhood

distances per reachable type and the edges used.

Raises:

Type Description
KeyError

if vertex_type is not declared in the schema.
Source code in graflo/architecture/schema/context/graph.py 
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
def schema_neighbors(
    self,
    vertex_type: str,
    *,
    hops: int = 1,
    direction: EdgeDirection = EdgeDirection.ANY,
    edge_relations: set[str | None] | None = None,
    edge_ids: set[EdgeId] | None = None,
) -> SchemaNeighborhood:
    """Vertex types adjacent to *vertex_type* within *hops*.

    Args:
        vertex_type: Seed vertex type. Must be declared.
        hops: Maximum hop distance. ``0`` returns just the seed.
        direction: Orientation followed from each frontier vertex. Defaults to
            :attr:`EdgeDirection.ANY` — deliberately unlike
            ``Connection.fetch_edges``, which defaults to ``OUT``. "What is
            adjacent to ``person`` in the schema" almost never means "only
            where person is the source"; an agent asking that wants the whole
            local shape. Edges declared ``directed=False`` are followed both
            ways whatever is requested here.
        edge_relations: Restrict traversal to these relation names (``None`` is
            a valid member, matching edges with no relation).
        edge_ids: Restrict traversal to these exact edges. Finer-grained than
            *edge_relations*, which cannot separate two dyads sharing one
            relation name. Both filters apply when both are given.

    Returns:
        SchemaNeighborhood: distances per reachable type and the edges used.

    Raises:
        KeyError: if *vertex_type* is not declared in the schema.
    """
    if vertex_type not in self._vertex_types:
        raise KeyError(
            f"Unknown vertex type {vertex_type!r}; declared: {sorted(self._vertex_types)}"
        )
    if hops < 0:
        raise ValueError(f"hops must be >= 0, got {hops}")

    distances: dict[str, int] = {vertex_type: 0}
    used: set[EdgeId] = set()
    frontier: deque[tuple[str, int]] = deque([(vertex_type, 0)])

    while frontier:
        current, depth = frontier.popleft()
        if depth >= hops:
            continue
        for edge_id in self._incident(current):
            if edge_relations is not None and edge_id[2] not in edge_relations:
                continue
            if edge_ids is not None and edge_id not in edge_ids:
                continue
            far = self._traversable(edge_id, current, direction)
            if far is None:
                continue
            used.add(edge_id)
            if far not in distances:
                distances[far] = depth + 1
                frontier.append((far, depth + 1))

    return SchemaNeighborhood(
        origin=vertex_type,
        hops=hops,
        direction=direction,
        distances=distances,
        edges=sorted(used, key=edge_sort_key),
    )

SchemaNeighborhood

Bases: ConfigBaseModel

Vertex types reachable from a seed within a hop bound.

Source code in graflo/architecture/schema/context/graph.py 
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
class SchemaNeighborhood(ConfigBaseModel):
    """Vertex types reachable from a seed within a hop bound."""

    origin: str = PydanticField(..., description="Vertex type the walk started from.")
    hops: int = PydanticField(..., description="Hop bound the walk honoured.")
    direction: EdgeDirection = PydanticField(
        ..., description="Orientation followed from each frontier vertex."
    )
    distances: dict[str, int] = PydanticField(
        ...,
        description="Reachable vertex type -> hop distance from origin (origin itself is 0).",
    )
    edges: list[EdgeId] = PydanticField(
        ..., description="Edges traversed to reach the neighbourhood, deduplicated."
    )

    @property
    def vertex_types(self) -> list[str]:
        """Reachable vertex types, nearest first then alphabetical."""
        return sorted(self.distances, key=lambda name: (self.distances[name], name))

Attributes

direction = PydanticField(..., description='Orientation followed from each frontier vertex.') class-attribute instance-attribute
distances = PydanticField(..., description='Reachable vertex type -> hop distance from origin (origin itself is 0).') class-attribute instance-attribute
edges = PydanticField(..., description='Edges traversed to reach the neighbourhood, deduplicated.') class-attribute instance-attribute
hops = PydanticField(..., description='Hop bound the walk honoured.') class-attribute instance-attribute
origin = PydanticField(..., description='Vertex type the walk started from.') class-attribute instance-attribute
vertex_types property

Reachable vertex types, nearest first then alphabetical.

SchemaPath

Bases: ConfigBaseModel

One path between two vertex types, as an alternating vertex/edge walk.

Source code in graflo/architecture/schema/context/graph.py 
36
37
38
39
40
41
42
43
44
45
46
47
48
49
class SchemaPath(ConfigBaseModel):
    """One path between two vertex types, as an alternating vertex/edge walk."""

    vertices: list[str] = PydanticField(
        ..., description="Vertex types visited, from source to target inclusive."
    )
    edges: list[EdgeId] = PydanticField(
        ..., description="Edges traversed, one fewer than ``vertices``."
    )

    @property
    def length(self) -> int:
        """Number of hops (edges) in this path."""
        return len(self.edges)

Attributes

edges = PydanticField(..., description='Edges traversed, one fewer than ``vertices``.') class-attribute instance-attribute
length property

Number of hops (edges) in this path.

vertices = PydanticField(..., description='Vertex types visited, from source to target inclusive.') class-attribute instance-attribute

TransformCard

Bases: BaseCard

Summary of a data transform.

Source code in graflo/architecture/schema/context/card.py 
265
266
267
268
269
270
271
272
273
274
275
276
277
278
class TransformCard(BaseCard):
    """Summary of a data transform."""

    name: str | None = PydanticField(default=None, description="Transform name.")
    functional: bool = PydanticField(
        ..., description="True if it wraps a Python function."
    )
    module: str | None = PydanticField(default=None, description="Python module path.")
    foo: str | None = PydanticField(default=None, description="Python function name.")
    input_count: int = PydanticField(default=0, description="Number of input fields.")
    output_count: int = PydanticField(default=0, description="Number of output fields.")
    strategy: str = PydanticField(
        default="single", description="Functional call strategy (single, each, all)."
    )

Attributes

foo = PydanticField(default=None, description='Python function name.') class-attribute instance-attribute
functional = PydanticField(..., description='True if it wraps a Python function.') class-attribute instance-attribute
input_count = PydanticField(default=0, description='Number of input fields.') class-attribute instance-attribute
module = PydanticField(default=None, description='Python module path.') class-attribute instance-attribute
name = PydanticField(default=None, description='Transform name.') class-attribute instance-attribute
output_count = PydanticField(default=0, description='Number of output fields.') class-attribute instance-attribute
strategy = PydanticField(default='single', description='Functional call strategy (single, each, all).') class-attribute instance-attribute

VertexCard

Bases: BaseCard

Summary of a single vertex type.

Source code in graflo/architecture/schema/context/card.py 
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
class VertexCard(BaseCard):
    """Summary of a single vertex type."""

    name: str = PydanticField(..., description="Vertex type name.")
    identity_mode: str = PydanticField(
        ..., description="natural / hash / blank / assigned."
    )
    property_count: int = PydanticField(..., description="Total declared properties.")
    identity_fields: list[str] = PydanticField(
        default_factory=list, description="Primary identity field names."
    )
    secondary_identity_count: int = PydanticField(
        default=0, description="Number of secondary identity field-sets."
    )
    description: str | None = PydanticField(
        default=None, description="Authored description."
    )

Attributes

description = PydanticField(default=None, description='Authored description.') class-attribute instance-attribute
identity_fields = PydanticField(default_factory=list, description='Primary identity field names.') class-attribute instance-attribute
identity_mode = PydanticField(..., description='natural / hash / blank / assigned.') class-attribute instance-attribute
name = PydanticField(..., description='Vertex type name.') class-attribute instance-attribute
property_count = PydanticField(..., description='Total declared properties.') class-attribute instance-attribute
secondary_identity_count = PydanticField(default=0, description='Number of secondary identity field-sets.') class-attribute instance-attribute

VertexSignals

Bases: ConfigBaseModel

Per-vertex-type ranking inputs and the score derived from them.

Source code in graflo/architecture/schema/context/rank.py 
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
class VertexSignals(ConfigBaseModel):
    """Per-vertex-type ranking inputs and the score derived from them."""

    name: str = PydanticField(..., description="Vertex type name.")
    hop_distance: int | None = PydanticField(
        default=None,
        description="Hops from the nearest seed; None when unreachable.",
    )
    degree: int = PydanticField(..., description="Incident edges (out + in).")
    identity_mode: str = PydanticField(
        ..., description="One of natural / hash / assigned / blank."
    )
    property_count: int = PydanticField(..., description="Declared property count.")
    has_secondary_index: bool = PydanticField(
        ..., description="Whether db_profile declares a secondary index for this type."
    )
    score: float = PydanticField(..., description="Composite rank; higher is better.")

Attributes

degree = PydanticField(..., description='Incident edges (out + in).') class-attribute instance-attribute
has_secondary_index = PydanticField(..., description='Whether db_profile declares a secondary index for this type.') class-attribute instance-attribute
hop_distance = PydanticField(default=None, description='Hops from the nearest seed; None when unreachable.') class-attribute instance-attribute
identity_mode = PydanticField(..., description='One of natural / hash / assigned / blank.') class-attribute instance-attribute
name = PydanticField(..., description='Vertex type name.') class-attribute instance-attribute
property_count = PydanticField(..., description='Declared property count.') class-attribute instance-attribute
score = PydanticField(..., description='Composite rank; higher is better.') class-attribute instance-attribute

Functions:

build_card(schema, *, top_n=10, max_names=25, graph=None, id=None)

Summarize schema for an agent's first contact with it.

Every list on the card is bounded, with a count reported alongside. A card whose size grows with the schema is not a card — it is the problem this wave exists to solve, wearing a summary's clothes.

Parameters:

Name Type Description Default
schema Schema

Schema to summarize. Never mutated.

 required
top_n int

How many hub types and entry points to list.

 10
max_names int

How many isolated types and relation names to list.

 25
graph SchemaGraph | None

Prebuilt index, if the caller already has one.

 None
Source code in graflo/architecture/schema/context/card.py 
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
def build_card(
    schema: Schema,
    *,
    top_n: int = 10,
    max_names: int = 25,
    graph: SchemaGraph | None = None,
    id: str | None = None,
) -> SchemaCard:
    """Summarize *schema* for an agent's first contact with it.

    Every list on the card is bounded, with a count reported alongside. A card
    whose size grows with the schema is not a card — it is the problem this wave
    exists to solve, wearing a summary's clothes.

    Args:
        schema: Schema to summarize. Never mutated.
        top_n: How many hub types and entry points to list.
        max_names: How many isolated types and relation names to list.
        graph: Prebuilt index, if the caller already has one.
    """
    graph = graph or SchemaGraph.from_schema(schema)
    vertex_config = schema.core_schema.vertex_config
    db_profile = schema.db_profile

    ranked = score_vertices(graph)
    isolated = graph.isolated_types()
    relations = graph.relation_vocabulary()
    identity_modes = Counter(
        vertex_config[name].identity_mode for name in graph.vertex_types
    )

    entry_points: list[EntryPoint] = []
    for signal in ranked:
        if len(entry_points) >= top_n:
            break
        vertex = vertex_config[signal.name]
        indexes = db_profile.vertex_secondary_indexes(signal.name)
        # A blank type has no natural key and nothing to filter on: it is not an
        # entry point, whatever its centrality.
        if vertex.identity_mode == "blank" and not indexes:
            continue
        if not vertex.identity and not indexes:
            continue
        entry_points.append(
            EntryPoint(
                name=signal.name,
                identity=list(vertex.identity),
                identity_mode=vertex.identity_mode,
                secondary_identities=vertex.secondary_identity_names,
                indexed_fields=[list(index.fields) for index in indexes],
                description=vertex.description,
            )
        )

    card = SchemaCard(
        id=id,
        name=schema.metadata.name,
        version=schema.metadata.version,
        description=schema.metadata.description,
        db_flavor=str(db_profile.db_flavor),
        vertex_count=len(graph.vertex_types),
        edge_count=len(graph.edge_ids),
        total_property_count=sum(
            len(vertex_config[name].property_names) for name in graph.vertex_types
        ),
        hub_types=ranked[:top_n],
        entry_points=entry_points,
        identity_modes=dict(sorted(identity_modes.items())),
        isolated_types=isolated[:max_names],
        isolated_type_count=len(isolated),
        relation_vocabulary=relations[:max_names],
        relation_count=len(relations),
        estimated_tokens=0,
    )
    card.estimated_tokens = estimate_tokens(card.to_minimal_canonical_dict())
    return card

build_connector_card(connector, id=None)

Build a summary card for a data connector.

Source code in graflo/architecture/schema/context/card.py 
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
def build_connector_card(
    connector: AnyConnector, id: str | None = None
) -> ConnectorCard:
    """Build a summary card for a data connector."""
    from graflo.architecture.contract.bindings.connectors import (
        APIConnector,
        FileConnector,
        KafkaConnector,
        SparqlConnector,
        TableConnector,
    )

    summary: str | None = None
    if isinstance(connector, FileConnector):
        summary = connector.regex or str(connector.sub_path)
    elif isinstance(connector, TableConnector):
        summary = connector.table_name
    elif isinstance(connector, SparqlConnector):
        summary = connector.rdf_class
    elif isinstance(connector, APIConnector):
        summary = connector.path
    elif isinstance(connector, KafkaConnector):
        summary = ",".join(connector.topics)

    card = ConnectorCard(
        id=id,
        type=connector.__class__.__name__,
        name=connector.name,
        resource_name=connector.resource_name,
        summary=summary,
    )
    card.estimated_tokens = estimate_tokens(card.to_minimal_canonical_dict())
    return card

build_database_profile_card(profile, id=None)

Build a summary card for a database profile.

Source code in graflo/architecture/schema/context/card.py 
470
471
472
473
474
475
476
477
478
479
480
481
482
def build_database_profile_card(
    profile: DatabaseProfile, id: str | None = None
) -> DatabaseProfileCard:
    """Build a summary card for a database profile."""
    card = DatabaseProfileCard(
        id=id,
        db_flavor=str(profile.db_flavor),
        vertex_index_count=sum(len(idx) for idx in profile.vertex_indexes.values()),
        edge_spec_count=len(profile.edge_specs),
        target_namespace=profile.target_namespace,
    )
    card.estimated_tokens = estimate_tokens(card.to_minimal_canonical_dict())
    return card

build_edge_card(edge, id=None, *, schema=None)

Build a summary card for a logical edge type.

Parameters:

Name Type Description Default
edge Edge

The edge to summarize.

 required
id str | None

Identifier carried on the card.

 None
schema Schema | None

The schema the edge belongs to. With it the card also states the relation's declared inverse and the state of that pair, which an edge alone cannot know; without it those fields stay empty.

 None
Source code in graflo/architecture/schema/context/card.py 
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
def build_edge_card(
    edge: Edge, id: str | None = None, *, schema: Schema | None = None
) -> EdgeCard:
    """Build a summary card for a logical edge type.

    Args:
        edge: The edge to summarize.
        id: Identifier carried on the card.
        schema: The schema the edge belongs to. With it the card also states the
            relation's declared inverse and the state of that pair, which
            an edge alone cannot know; without it those fields stay empty.
    """
    inverse: str | None = None
    state: str | None = None
    symmetric = False
    if schema is not None and edge.relation is not None:
        edge_config = schema.core_schema.edge_config
        symmetric = edge_config.is_symmetric(edge.relation)
        if not symmetric:
            inverse = edge_config.inverse_of(edge.relation)
        if inverse is not None:
            state = next(
                (
                    pair.state
                    for pair in pair_realizations(schema)
                    if edge.relation in (pair.relation, pair.inverse)
                ),
                None,
            )
    card = EdgeCard(
        id=id,
        source=edge.source,
        target=edge.target,
        relation=edge.relation,
        directed=edge.directed,
        symmetric=symmetric,
        inverse=inverse,
        inverse_state=state,
        identity_count=len(edge.identities),
        property_count=len(edge.properties),
        description=edge.description,
    )
    card.estimated_tokens = estimate_tokens(card.to_minimal_canonical_dict())
    return card

build_manifest_card(manifest, id=None)

Build a summary card for a full graph manifest.

Source code in graflo/architecture/schema/context/card.py 
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
def build_manifest_card(manifest: GraphManifest, id: str | None = None) -> ManifestCard:
    """Build a summary card for a full graph manifest."""
    schema = manifest.graph_schema
    ingestion = manifest.ingestion_model

    card = ManifestCard(
        id=id,
        name=schema.metadata.name if schema else None,
        version=schema.metadata.version if schema else None,
        has_schema=schema is not None,
        has_ingestion=ingestion is not None,
        has_bindings=manifest.bindings is not None,
        vertex_count=len(schema.core_schema.vertex_config.vertices) if schema else None,
        edge_count=len(schema.core_schema.edge_config.edges) if schema else None,
        resource_count=len(ingestion.resources) if ingestion else None,
    )
    card.estimated_tokens = estimate_tokens(card.to_minimal_canonical_dict())
    return card

build_resource_card(resource, id=None, top_n=5)

Build a summary card for an ingestion resource.

Source code in graflo/architecture/schema/context/card.py 
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
def build_resource_card(
    resource: ResourceConfig, id: str | None = None, top_n: int = 5
) -> ResourceCard:
    """Build a summary card for an ingestion resource."""
    # This is a bit expensive if we bind, but here we just collect names.
    from graflo.architecture.contract.ingestion.resource import (
        collect_vertex_names_from_pipeline,
    )

    pipeline_vertices = list(collect_vertex_names_from_pipeline(resource.pipeline))
    edge_targets = [
        f"({e.edge.source}, {e.edge.target}, {e.edge.relation})"
        for e in resource.extra_weights
    ]

    card = ResourceCard(
        id=id,
        name=resource.name,
        actor_count=resource.pipeline_actor_count(),
        vertex_targets=pipeline_vertices[:top_n],
        edge_targets=edge_targets[:top_n],
        encoding=str(resource.encoding),
        infer_edges=resource.infer_edges,
    )
    card.estimated_tokens = estimate_tokens(card.to_minimal_canonical_dict())
    return card

build_transform_card(transform, id=None)

Build a summary card for a data transform.

Source code in graflo/architecture/schema/context/card.py 
419
420
421
422
423
424
425
426
427
428
429
430
431
432
def build_transform_card(transform: Transform, id: str | None = None) -> TransformCard:
    """Build a summary card for a data transform."""
    card = TransformCard(
        id=id,
        name=transform.name,
        functional=transform.functional_transform,
        module=transform.module,
        foo=transform.foo,
        input_count=len(transform.input),
        output_count=len(transform.output),
        strategy=str(transform.strategy),
    )
    card.estimated_tokens = estimate_tokens(card.to_minimal_canonical_dict())
    return card

build_vertex_card(vertex, id=None)

Build a summary card for a logical vertex type.

Source code in graflo/architecture/schema/context/card.py 
330
331
332
333
334
335
336
337
338
339
340
341
342
def build_vertex_card(vertex: Vertex, id: str | None = None) -> VertexCard:
    """Build a summary card for a logical vertex type."""
    card = VertexCard(
        id=id,
        name=vertex.name,
        identity_mode=vertex.identity_mode,
        property_count=len(vertex.properties),
        identity_fields=list(vertex.identity),
        secondary_identity_count=len(vertex.secondary_identities),
        description=vertex.description,
    )
    card.estimated_tokens = estimate_tokens(card.to_minimal_canonical_dict())
    return card

estimate_tokens(payload)

Estimate token count for payload.

Runs over the compact serialization — estimating over a pretty-printed or defaults-included dump overcounts by a factor of two or more, which would make every budget silently pessimistic.

Source code in graflo/architecture/schema/context/budget.py 
75
76
77
78
79
80
81
82
def estimate_tokens(payload: Any) -> int:
    """Estimate token count for *payload*.

    Runs over the compact serialization — estimating over a pretty-printed or
    defaults-included dump overcounts by a factor of two or more, which would make
    every budget silently pessimistic.
    """
    return math.ceil(len(serialize_compact(payload)) / CHARS_PER_TOKEN)

neighborhood_distances(graph, seeds, *, hops=1, direction=EdgeDirection.ANY, edge_relations=None, edge_ids=None)

Hop distance to every type reachable from any seed, nearest seed winning.

The multi-seed union of :meth:SchemaGraph.schema_neighbors. Both consumers of "what is near what I asked about" — rank-then-budget schema context and project_manifest's depth — go through here, so the two cannot drift apart on direction handling, undirected edges or the treatment of hops=0.

Parameters:

Name Type Description Default
graph SchemaGraph

Adjacency index to walk.

 required
seeds Iterable[str]

Vertex types to start from. Each must be declared.

 required
hops int

Maximum hop distance. 0 yields just the seeds.

 1
direction EdgeDirection

Orientation followed from each frontier vertex.

 ANY
edge_relations set[str | None] | None

Restrict traversal to these relation names.

 None
edge_ids set[EdgeId] | None

Restrict traversal to these exact edges.

 None

Returns:

Name Type Description
dict dict[str, int]

reachable vertex type -> distance from the nearest seed (seeds map
dict[str, int]

to 0). Empty when seeds is empty.

Raises:

Type Description
KeyError

if a seed is not declared in the schema.
Source code in graflo/architecture/schema/context/graph.py 
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
def neighborhood_distances(
    graph: SchemaGraph,
    seeds: Iterable[str],
    *,
    hops: int = 1,
    direction: EdgeDirection = EdgeDirection.ANY,
    edge_relations: set[str | None] | None = None,
    edge_ids: set[EdgeId] | None = None,
) -> dict[str, int]:
    """Hop distance to every type reachable from *any* seed, nearest seed winning.

    The multi-seed union of :meth:`SchemaGraph.schema_neighbors`. Both consumers of
    "what is near what I asked about" — rank-then-budget schema context and
    ``project_manifest``'s ``depth`` — go through here, so the two cannot drift
    apart on direction handling, undirected edges or the treatment of ``hops=0``.

    Args:
        graph: Adjacency index to walk.
        seeds: Vertex types to start from. Each must be declared.
        hops: Maximum hop distance. ``0`` yields just the seeds.
        direction: Orientation followed from each frontier vertex.
        edge_relations: Restrict traversal to these relation names.
        edge_ids: Restrict traversal to these exact edges.

    Returns:
        dict: reachable vertex type -> distance from the nearest seed (seeds map
        to ``0``). Empty when *seeds* is empty.

    Raises:
        KeyError: if a seed is not declared in the schema.
    """
    distances: dict[str, int] = {}
    for seed in seeds:
        neighborhood = graph.schema_neighbors(
            seed,
            hops=hops,
            direction=direction,
            edge_relations=edge_relations,
            edge_ids=edge_ids,
        )
        for name, distance in neighborhood.distances.items():
            if name not in distances or distance < distances[name]:
                distances[name] = distance
    return distances

score_vertices(graph, seeds=(), *, weights=None, max_hops=3, direction=EdgeDirection.ANY)

Rank every vertex type in graph, highest score first.

With no seeds, ranking is seed-independent (structure only) and answers "what are the important types here" — which is what the orientation card needs. With seeds, hop distance dominates and answers "what is near what I asked about".

Ties break by vertex name ascending. This is not cosmetic: without a total order the elision report is not reproducible across runs, and the budget tests become flaky.

Source code in graflo/architecture/schema/context/rank.py 
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
def score_vertices(
    graph: SchemaGraph,
    seeds: Sequence[str] = (),
    *,
    weights: RankingWeights | None = None,
    max_hops: int = 3,
    direction: EdgeDirection = EdgeDirection.ANY,
) -> list[VertexSignals]:
    """Rank every vertex type in *graph*, highest score first.

    With no *seeds*, ranking is seed-independent (structure only) and answers
    "what are the important types here" — which is what the orientation card
    needs. With seeds, hop distance dominates and answers "what is near what I
    asked about".

    Ties break by vertex name ascending. This is not cosmetic: without a total
    order the elision report is not reproducible across runs, and the budget tests
    become flaky.
    """
    weights = weights or RankingWeights()
    schema = graph.schema
    vertex_config = schema.core_schema.vertex_config
    db_profile = schema.db_profile

    distances = neighborhood_distances(graph, seeds, hops=max_hops, direction=direction)

    degrees = {name: graph.degree(name) for name in graph.vertex_types}
    max_degree = max(degrees.values(), default=0)
    property_counts = {
        name: len(vertex_config[name].property_names) for name in graph.vertex_types
    }
    max_properties = max(property_counts.values(), default=0)

    signals: list[VertexSignals] = []
    for name in sorted(graph.vertex_types):
        vertex = vertex_config[name]
        hop_distance = distances.get(name) if seeds else None
        degree = degrees[name]
        property_count = property_counts[name]
        has_index = bool(db_profile.vertex_secondary_indexes(name))

        structural = (
            weights.degree * (degree / max_degree if max_degree else 0.0)
            + weights.identity * IDENTITY_MODE_STRENGTH.get(vertex.identity_mode, 0.5)
            + weights.properties
            * (
                math.log1p(property_count) / math.log1p(max_properties)
                if max_properties
                else 0.0
            )
            + weights.indexed * (1.0 if has_index else 0.0)
        )
        if not seeds:
            score = structural
        elif hop_distance is None:
            score = 0.0
        else:
            score = (weights.hop_decay**hop_distance) + structural

        signals.append(
            VertexSignals(
                name=name,
                hop_distance=hop_distance,
                degree=degree,
                identity_mode=vertex.identity_mode,
                property_count=property_count,
                has_secondary_index=has_index,
                score=score,
            )
        )

    signals.sort(key=lambda item: (-item.score, item.name))
    return signals