Require a vector on the record type nothing reads back (speedkick) - #1603

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01MbYdqGZsuws6Z2WHYfCCR5

…emMachine#1603)

Require a vector on the record type nothing reads back

`Record` is written and never returned, so `vector` being optional
described nothing a caller could do. Every store rejected `None` at its
own `upsert` with the same message, four copies of one rule that the type
could state once. `properties` was optional in the same way, so Qdrant
carried `record.properties if record.properties is not None else {}`.

The vector is required and the properties default to `{}`. The four
checks go, and rejection moves to the model, where a caller finds it at
construction rather than at a write.

Claude-Session: https://claude.ai/code/session_01NKmF9xNph9QH3ozNw3ZnJL

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>

…emMachine#1603)

Require a vector on the record type nothing reads back

`Record` is written and never returned, so `vector` being optional
described nothing a caller could do. Every store rejected `None` at its
own `upsert` with the same message, four copies of one rule that the type
could state once. `properties` was optional in the same way, so Qdrant
carried `record.properties if record.properties is not None else {}`.

The vector is required and the properties default to `{}`. The four
checks go, and rejection moves to the model, where a caller finds it at
construction rather than at a write.

Claude-Session: https://claude.ai/code/session_01NKmF9xNph9QH3ozNw3ZnJL

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>

…emMachine#1603)

Require a vector on the record type nothing reads back

`Record` is written and never returned, so `vector` being optional
described nothing a caller could do. Every store rejected `None` at its
own `upsert` with the same message, four copies of one rule that the type
could state once. `properties` was optional in the same way, so Qdrant
carried `record.properties if record.properties is not None else {}`.

The vector is required and the properties default to `{}`. The four
checks go, and rejection moves to the model, where a caller finds it at
construction rather than at a write.


Claude-Session: https://claude.ai/code/session_01NKmF9xNph9QH3ozNw3ZnJL

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>

…emMachine#1603)

Require a vector on the record type nothing reads back

`Record` is written and never returned, so `vector` being optional
described nothing a caller could do. Every store rejected `None` at its
own `upsert` with the same message, four copies of one rule that the type
could state once. `properties` was optional in the same way, so Qdrant
carried `record.properties if record.properties is not None else {}`.

The vector is required and the properties default to `{}`. The four
checks go, and rejection moves to the model, where a caller finds it at
construction rather than at a write.


Claude-Session: https://claude.ai/code/session_01NKmF9xNph9QH3ozNw3ZnJL

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>

…emMachine#1603)

Require a vector on the record type nothing reads back

`Record` is written and never returned, so `vector` being optional
described nothing a caller could do. Every store rejected `None` at its
own `upsert` with the same message, four copies of one rule that the type
could state once. `properties` was optional in the same way, so Qdrant
carried `record.properties if record.properties is not None else {}`.

The vector is required and the properties default to `{}`. The four
checks go, and rejection moves to the model, where a caller finds it at
construction rather than at a write.

Claude-Session: https://claude.ai/code/session_01NKmF9xNph9QH3ozNw3ZnJL

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>
(cherry picked from commit cdeef88)

…emMachine#1603)

Require a vector on the record type nothing reads back

`Record` is written and never returned, so `vector` being optional
described nothing a caller could do. Every store rejected `None` at its
own `upsert` with the same message, four copies of one rule that the type
could state once. `properties` was optional in the same way, so Qdrant
carried `record.properties if record.properties is not None else {}`.

The vector is required and the properties default to `{}`. The four
checks go, and rejection moves to the model, where a caller finds it at
construction rather than at a write.

Claude-Session: https://claude.ai/code/session_01NKmF9xNph9QH3ozNw3ZnJL

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>
(cherry picked from commit cdeef88)

…emMachine#1603)

Require a vector on the record type nothing reads back

`Record` is written and never returned, so `vector` being optional
described nothing a caller could do. Every store rejected `None` at its
own `upsert` with the same message, four copies of one rule that the type
could state once. `properties` was optional in the same way, so Qdrant
carried `record.properties if record.properties is not None else {}`.

The vector is required and the properties default to `{}`. The four
checks go, and rejection moves to the model, where a caller finds it at
construction rather than at a write.

Claude-Session: https://claude.ai/code/session_01NKmF9xNph9QH3ozNw3ZnJL

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>
(cherry picked from commit cdeef88)

…emMachine#1603)

Require a vector on the record type nothing reads back

`Record` is written and never returned, so `vector` being optional
described nothing a caller could do. Every store rejected `None` at its
own `upsert` with the same message, four copies of one rule that the type
could state once. `properties` was optional in the same way, so Qdrant
carried `record.properties if record.properties is not None else {}`.

The vector is required and the properties default to `{}`. The four
checks go, and rejection moves to the model, where a caller finds it at
construction rather than at a write.

Claude-Session: https://claude.ai/code/session_01NKmF9xNph9QH3ozNw3ZnJL

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>
(cherry picked from commit cdeef88)

…emMachine#1603)

Require a vector on the record type nothing reads back

`Record` is written and never returned, so `vector` being optional
described nothing a caller could do. Every store rejected `None` at its
own `upsert` with the same message, four copies of one rule that the type
could state once. `properties` was optional in the same way, so Qdrant
carried `record.properties if record.properties is not None else {}`.

The vector is required and the properties default to `{}`. The four
checks go, and rejection moves to the model, where a caller finds it at
construction rather than at a write.

Claude-Session: https://claude.ai/code/session_01NKmF9xNph9QH3ozNw3ZnJL

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>
(cherry picked from commit cdeef88)

Record is input-only since queries answer UUIDs and scores, but its types
still made both fields optional: `vector: list[float] | None = None` and
`properties: ... | None = None`, the `None` once meaning "not requested"
on a returned record. So every store re-checked the vector at upsert
(four copies of "has vector=None, which is not allowed on input") and
Milvus and Qdrant coalesced `None` properties to `{}`.

As MemMachine#1603 did (MemMachine#1663 on main): `vector: list[float]` is required, and
`properties` defaults to `{}` through `Field(default_factory=dict)`. The
model rejects a missing vector at construction, so the four checks and
the coalescing go, along with the in-memory test collection's.

The tests of a store refusing a `None` vector become tests that the model
refuses a missing one, built with `Record.model_validate` rather than a
type ignore, plus one that properties default to `{}` and one that a
record without properties is stored. The stores' `_make_record` helpers
require a vector.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

Every embedder MemMachine ships produces vectors meant to be compared by
cosine -- OpenAI hard-coded it, Bedrock defaulted to it, SentenceTransformer
only reported what the model declared -- while every layer that touched a
score paid for the other three metrics in direction flags, threshold
directions, and per-backend tables mapping the enum onto native metric
names. `SimilarityMetric` is gone; scores are cosine similarities in
[-1, 1] and the names say so: `QueryMatch.score` and `SearchMatch.score`
become `cosine_similarity`, and `query(score_threshold=)` becomes
`query(min_cosine_similarity=)`, which no longer needs a direction to be
meaningful and is refused when not finite, as the threshold was. A store
and its partitions no longer have a `similarity_metric`, the schema a
partition is registered under no longer records one, and a search engine
factory takes the dimensions alone. The Bedrock embedder's
`similarity_metric` config key and semantic memory's
`vector_similarity_metric` go with it, and the install and configuration
docs drop them.

The vector graph stores carried a metric per stored embedding, as a
companion property beside every vector; that is gone and `Node.embeddings`
holds plain vectors. NebulaGraph's `cosine()` cannot take `APPROXIMATE` and
its vector indexes offer only L2 and IP. Cosine similarity between unit
vectors is their inner product, so embeddings are normalized on the way in
and compared with `inner_product()` against an IP index.

The cosine half of MemMachine#1598 (`abf92a3a4` on speedkick), re-derived on the
one-collection store: the rest of MemMachine#1598 (queries answer record UUIDs and
scores, no `get`, semantic memory's `vector_uuid`) and all of MemMachine#1603 are in
registry-backed base and its partition handle lose the metric, the stores'
own threshold checks become `require_valid_min_cosine_similarity`, and the
design documents describe cosine scoring and a schema without a metric.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01ESpWYTmCR7X3bJEpoA8SAn