[event memory 7/7] Render session blocks and id markers (port of #1632) - #1688

…ck) (MemMachine#1606)

* Regenerate the OpenAPI document under the locked FastAPI

`docs/openapi.json` predates the FastAPI release in `uv.lock`
(0.141.1), whose `ValidationError` component carries `input` and `ctx`;
regenerating the document with `docs/tools/generate_openapi.py` adds the
two fields and changes nothing else. Separate from the API changes above
it so their diffs of this file show only what they change.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01ESpWYTmCR7X3bJEpoA8SAn

* Remove per-project filterable properties

A project could declare `properties_schema`, a set of caller property keys
with types, on its long-term memory configuration; the event backend merged
it into the vector store collection's indexed schema and rejected filters on
any other `m.<key>`. That let a tenant create database resources (indexes,
columns) by naming them in a request, which is what forced per-collection
native resources named by a hash of their schema on the backends that limit
them.

The option is removed from the server configuration, the project API and
the memory-configuration API, the Python SDK, the sample configurations,
the configuration docs and the OpenAPI document. A filter may name any
`m.<key>`; the stores evaluate it on the properties they hold. What a store
indexes is decided by the deployment, not per project.

A breaking API change on `speedkick`.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01ESpWYTmCR7X3bJEpoA8SAn

Rebased onto MemMachine#1631: the per-project schema also leaves MemMachine#1631's service
locator, which creates the session's collection in a retry loop, and the
commented option goes from the event sample configuration MemMachine#1698 added.

---------

Co-authored-by: Claude Opus 5 (1M context) <[email protected]>
(cherry picked from commit a8322a7)

A round that never ended was counted by the next claim, which took a
CASE-shaped update that both recorded the lost round and ended its claim;
the count lived apart from the claims that made it.

Each claim now counts its attempt: the claim is a plain update that
increments `consecutive_attempts` (renamed from `consecutive_failed_rounds`),
stamps `claimed_at`, and bumps the generation, and `_TombstoneClaim.attempt`
carries the count. A tombstone is claimable when it has no attempts, when no
claim is open and the backoff has passed since its last failure, or when an
open claim has outlived its lease plus the backoff. A raised round ends its
claim and stamps `last_failed_at`; a cancelled round ends its claim and takes
its attempt back; a round that found records resets the attempts. After
`_MAX_PURGE_ATTEMPTS` attempts a tombstone is dead-lettered, and a last
attempt that raises is reported. A retry logs which attempt it is, and a
raised round's error names its incarnation and attempt. The registry tests,
the purge design document, and the registry design document follow.

The same change as MemMachine#1734's 1732038, for this PR's partition registry.

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

`consecutive_attempts` counted the purge rounds claimed since a round last
found records, but its name said only that they were in a row. It is
`attempts_without_progress`, and `_MAX_PURGE_ATTEMPTS` is
`_MAX_PURGE_ATTEMPTS_WITHOUT_PROGRESS`. The column's comment, the claim's
attempt, the backoff parameter's description, the dead-letter log, the
class docstring, the tests, the purge design document, and the registry
design document's table follow; nothing else changes.

The same change as MemMachine#1734's 96a8b5b, for this PR's partition registry.

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

…urrent claim

The measured cost of the claim came from earlier forms of it, which held a
transaction across the round. The section now gives the figures measured on
2026-10-06 against the claim this registry ports, naming the MemMachine#1734 commits
they were taken at: the backoff scan with 1k, 10k, and 100k tombstones
backing off, and interactive throughput and liveness latency beside two
sweepers on PostgreSQL and on SQLite.

The same change as MemMachine#1734's bab379b, for this PR's purge document.

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

MemMachine#1736's review round, for this PR's Milvus store:

- Filter strings reach Milvus as UTF-8, so a character outside the Basic
  Multilingual Plane parses, and an undeclared property's condition requires
  the stored type tag to be one the value compares with.
- Startup's already-exists guard goes, with its mocked-client test: Milvus
  answers a create of an existing collection with the same schema with
  success.
- The store no longer re-sorts search results, which Milvus returns best
  first.
- The mocked-client purge test disposes its registry engine when it fails.

The same changes as MemMachine#1736's 1a7fffa, d6fc219, 9fd7f76, 6fcd8c5, and
c264b3d, for this PR's store. MemMachine#1736's 28e8c50 and b3ef4f1 have no
counterpart here: startup prepares the store's one native collection before
any purge round runs, and the store refuses an unsupported metric at
construction, before anything is reserved.

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

The declared path counted an int and a float as comparable either way, so
a float filter value on a declared int property reached Milvus as a float
literal against an INT64 field, which Milvus refuses to parse ("cannot
cast value to Int64", code 1100). A float now compares only with a float
property, and matches no int one, as a value of another type matches
nothing; an int still compares with a float property by value.

The new test filters a declared float property with an int and a declared
int property with a float; it fails with the float counted as comparable
with an int property.

The same change as MemMachine#1736's 31fc7c4, for this PR's store.

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

…y name

MemMachine#1736's baabf48 creates Milvus native collections at Bounded by name,
and this PR's base carries that into startup's create, so the read level
the purge and the tombstone retention rely on no longer comes from
pymilvus's default. The consistency test now spies create_collection and
checks the level it names, as MemMachine#1736's test does; it fails with the level
dropped from the create. The design document and the store's docstring
say the store creates its one native collection at Bounded.

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

MemMachine#1736's f56686f halves a Milvus upsert refused with RESOURCE_EXHAUSTED,
and this PR's base carries the halving into the partition handle's
`_upsert`. Its tests come here in partition terms: the integration test
upserts 1,200 records with a 60,000-character property, about 72 MB, and
fails with RESOURCE_EXHAUSTED without the halving; the mocked-client tests
pin the halving, a single refused entity raising, and a timeout or another
refusal sent once, on a handle `_partition_on` builds, which the mocked
delete test now uses too.

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

…nt alone

MemMachine#1736's 49b9ec2 drops the offset field beside a declared Milvus
datetime, keeping its UTC instant alone, and this PR's base carries that
into the store. The tests follow in partition terms: the native
collection's fields are exactly the fixed ones and one per declared
property; a declared datetime is stored as its instant in UTC; and a store
whose declared datetime has the longest property key, 32 bytes, writes its
one field, reads it back, and matches the record by its instant, the test
MemMachine#1736's b015229 adds.

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

The test of MemMachine#1813, merged into this PR's base, in partition terms: the
server defaults new collections to strict mode, the store's collection
reads back with it off, and a filter on a partition's unindexed property
is served.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

A partition stored every property of a record and filtered on any key,
which made a caller's arbitrary keys part of the store's schema: the
SQLite stores kept them in a JSON column and filtered with json_extract,
Milvus the keys its schema did not declare in a JSON field, and a filter
on a key the store never indexed scanned. Since EventMemory routes a
filter on an undeclared key to the segment store, the vector store need
not hold undeclared keys at all.

A partition now stores the properties its store declares and no others.
`upsert` raises UndeclaredPropertyKeyError before anything is sent for a
record naming an undeclared key, and PropertyTypeMismatchError for a
value of another type than its key declares; `query` raises
UndeclaredPropertyKeyError for a filter naming an undeclared key and
UnsupportedFilterError for a node outside the partition's
`supported_filter_nodes`. Both SQLite stores keep one typed, indexed,
nullable column per declared key on the records table (sql_columns.py);
sqlite-vec 0.1.9 rejects NULL in a vec0 metadata column and a declared
key is optional per record, so that store keeps the columns on the
records table and hands the KNN a `rowid IN (SELECT ...)` allowlist,
evaluating the filter during the search instead of after it. Qdrant
drops the JSON copy and keeps a payload field per declared key; Milvus
drops its JSON field and keeps its typed field per declared key.
Datetimes are stored as microseconds since the epoch where a backend has
no datetime type.

Since every key a filter may name is now indexed, the Qdrant store
creates its collection in strict mode (`unindexed_filtering_retrieve`
and `_update` false, Qdrant Cloud's default): a filter on an unindexed key is refused by the server instead
of scanned for. A leaf whose value is of another type than its key
declares matches nothing, as on the SQL stores; the Qdrant compiler
answers it with a filter no point satisfies, since the server would
refuse the condition for the field's index, and Milvus no longer
compares an int with a float key. Local mode does not record the
setting, so a unit test checks the request and integration tests the
server's answer.

`declared_schema_contract.py` states the contract every backend's test
module runs: which records a filtered search admits, over fixtures small
enough that every backend searches them exactly, checked after each
upsert so an approximate index fails on recall, by name, and not on the
filter.

On the registry-backed stores, the checks are the base handle's: `upsert`
runs require_declared_properties in place of the type check it ran, and
`query` runs require_supported_filter against the subclass's
`supported_filter_nodes`, which each subclass now implements. A datetime
column on the SQLite stores has a `tz_<key>` column beside it holding the
UTC offset in seconds, written with the value and read by no filter, so a
stored datetime is the value written, as on Milvus, Qdrant and the segment
store; the microseconds column alone would keep only the instant.

The Qdrant and Milvus design documents describe the declared-only
properties and Qdrant's strict mode.

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

A declared datetime on the SQLite stores had a `tz_<key>` column beside its
microseconds column, holding the UTC offset in seconds that no filter
reads. The vector stores keep a datetime property's instant only, as
MemMachine#1736 now does for Milvus and MemMachine#1788 for Qdrant, and the segment store
keeps the offset, so the column, `offset_column_name`, and the value
written to it go: each declared property is one column, and a datetime
stays microseconds since the epoch.

The tests read a stored datetime back as its instant in UTC, and the
roundtrip test checks that the stored instant equals the written one.

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

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

…hine#1597, without session)

The part of MemMachine#1597 that is not session: events and segments carry a
nullable source id; query and expand take since/until and source_ids;
expand walks outward from a seed, which is an address located whatever
the filters say, and returns a Neighborhood that excludes it; query
answers QueryHits (score, seed, neighborhood); rendering is
render_segments with a DateTimeFormat; the segment store answers
get_segments and get_segment_neighborhoods in place of
get_segment_contexts; the v2 adapter lifts timestamp/created_at bounds
and producer_id conjuncts out of the filter into the typed parameters;
reserved property keys live in their own module and a caller cannot
write one; the timestamp column holds a UTC instant.

On this base:
- A neighborhood is MemMachine#1713's walk: the partition's order next to the
  seed, filters applied inside its window of 1,000 segments per side.
  The ordering index keeps main's shape.
- The vector stage gets MemMachine#1684's predicates on the reserved keys and,
  joined with AND, the conjuncts of the property filter the vector store
  declares, as MemMachine#1702's routing has it; the segment store still gets the
  whole filter. A record's declared properties come from its
  derivative's segment.
- Episode uids are UUIDs since MemMachine#1707: the search path reads each hit's
  `_episode_uid` back as a UUID, and the tests key their episodes by
  `_uid(name)` as main's do.
- Session and block kind are split out: the block kind column,
  parameter and record key go to the kinds PR, which is their first
  consumer, and session goes to its own PR.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

The segment store gains a write transaction, `write()`, whose block the
caller may fill with work of its own: the event memory upserts its vector
records inside it, so segments commit only once the vector store has
acknowledged their records, and a failed upsert rolls them back. A forget
can then only see links whose records exist, and its delete is issued
after the upsert's acknowledgment, which closes the orphan race between
encode and forget rather than repairing after it.

An event is held at most once: a new event table, keyed by incarnation
and event uuid, is inserted first with ON CONFLICT DO NOTHING RETURNING,
and a batch naming a held event is rejected whole with
`SegmentStoreEventAlreadyStoredError` before anything is stored. Segments
carry a cascading foreign key to the event row; `delete_events` replaces
forget's by-event path, `delete_segments` stays for eviction and leaves
the event held, and `get_derivative_uuids_by_event_uuids` replaces the
two lookups whose only caller was forget. The purge reclaims event rows
after the segments, on the same budget.

The residue a crash can leave, a record acknowledged by the vector store
whose commit never happened, is repaired on retrieval: a hit without a
link is re-checked under `write(exclusive=True)`, which waits for every
write in flight, and a record still without a link is deleted after the
fence is released. An upsert that fails deletes the same ids before the
error propagates, since it may have been applied first.

On this base the change meets MemMachine#1661's final store: the writer's inserts
are the store's own, moved; the leaked-link reclaim MemMachine#1661 dropped stays
dropped; and the event rows purge the way the segments do, after them,
continuing from a cursor of their own on the queue entry,
events_purged_through, since a call that ends exactly on the last
segment leaves purged_through naming a segment.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

Deleting the segment partition first waits for every write in flight,
whose records land before it commits, and blocks new ones, so the
vector partition's deletion that follows removes every record that
could ever have landed in it.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

Mechanical: the store now holds events, segments and links, so its name
follows its dependent. `SegmentStore` and every derived name become
`EventMemoryStore` and theirs, the module and test directories move with
them, the tables and indexes take the `event_memory_store_` prefix, and
the configuration key `segment_store` becomes `event_memory_store` in the
API spec, the client, the docs, the sample configs, the Helm chart and
the compose files. No behavior changes; tables are recreated. Applied by
the same substitutions to this tree rather than rebased.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

Ported from the agentic_expansion branch, cosine only. EventMemory
takes an optional EvictionOptions: a cosine similarity threshold at or
above which eviction is considered, the number of stored derivatives
at or above it fetched per new derivative, and how many of a new
derivative and those stored ones to keep when there are more. None
keeps every derivative and issues no query.

At encode, after embedding, `_decide_eviction` settles the whole
decision before anything is written: the batch's predecessors of each
derivative are computed from the batch's own embeddings, earlier
indices only, so a batch evicts what serial ingestion would; one
batched neighbor query fetches the stored derivatives at or above the
threshold; the stored ones' timestamps come from their segments
through the store's lookup, since the vector store answers uuids and
scores only, and a neighbor whose segment is gone is not a member;
then, per derivative, the members over target_size are trimmed from
the temporal middle, the earliest target_size // 2 and the latest
remainder kept. The batch is sorted by timestamp first, so the
predecessor rule matches serial order.

The encode's write() block then carries both link writes: it adds the
surviving links and unlinks the displaced derivatives through
delete_derivatives, which the writer interface, the SQLAlchemy writer
and the fake writer gain, and upserts the surviving records inside the
same transaction, with the compensating delete an upsert failure
already had. The displaced records leave the vector store only after
that block commits: a delete that fails then leaves records no link
names, which read repair reclaims, rather than links naming records
that are gone. Skipped batch derivatives are never written, and a
displaced derivative's segment stays stored.

Tests: the branch's eviction tests on the new shapes, and
delete_derivatives through write() on both dialects, including an
unlink rolled back with its block.

On this base the surviving records carry their segment's declared
properties, as every record does since the routing change, and the
eviction's neighbor query and deletes go to the vector store partition.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

Moved here from MemMachine#1684's port, where every block was text and the column
would have held one value with nothing dispatching on it; this PR's
kind-keyed segmenter and deriver tables are its first consumer. The
segment row carries its block's kind in a column of its own, filled by
the store from the block, since the codec's bytes are opaque to SQL;
query, expand, get_segments and get_segment_neighborhoods take
block_kinds; and the vector record carries the kind under its reserved
key, which the vector stage filters with an In predicate.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

…s (speedkick)

The second half of the event memory handoff, on top of the
source/expansion/eviction change: the content model and the processing
steps become registered families keyed by kind.

Blocks. `Block` is an ABC with `kind` as the discriminator every
registered family uses and `render(options) -> str | None`; the union
stays closed over `TextBlock`; the segment row's `block_kind` reads
`block.kind`.

Context. `Context = Mapping[str, ContextPart]`, keyed by part kind,
never None; `Author` is the first registered kind, an unregistered
kind decodes to `UnknownPart` and round-trips unchanged; `with_part` composes one. `ProducerContext`, `NullContext` and the
discriminated union go; the codec encodes a context as `{kind:
fields}`. The server puts the producer id in an `Author` part beside
`source_id`, so rendering keeps its `producer: text` shape.

Segmenter and deriver. `Segmenter` and `Deriver` are tables from block
kind to handler, built from handlers in order with a later handler
replacing an earlier one for its kind. `BlockSegmenter[B]` and `BlockDeriver[B]` are the one-kind
handler contracts, typed by the block class: `split(event, block) ->
list[Piece]` and `derive(segment, block) -> list[str]`. The table
builds every envelope; a handler decides pieces or texts and nothing
else. A kind with no handler passes through as one segment and derives
nothing; nothing raises on a kind. `TextSegmenter`, `WholeTextDeriver`
and `SentenceTextDeriver` keep their names as `text` handlers;
`PassthroughSegmenter` and its configuration name go: one segment per
block is the identity segmentation, and a default gets no name, so an
omitted `segmenter` means it.

Composition. A derivative is text (`Derivative.text`, the text to
embed, plus the segment's `block_kind` for the record), so every
derivative gets the same context processing. `format_header` is the
one composition point for the embedded text and the rendered header:
the timestamp, then the context parts `parts` names in that order
(default `("author",)`), then the content. Parts carry no order; a part
not listed contributes nothing; a new kind is placed by listing it.
`parts` is a parameter of the composers, the handler and `render`,
not a field of `DatetimeFormat`, which writes a timestamp and nothing
else. A handler owns the composition of what it embeds, its
`datetime_format` and `parts`, so a kind or a handler can embed under
its own; the Deriver table composes each derivative's text with them;
rendering for display takes the caller's per call.

Tests: table dispatch, override order, envelope copying; text handlers returning bare
content; composition order, unlisted parts, kind-name validation, and
the anchor over a derivative; context and block round-trips including
an unregistered part kind.

On this base events carry no session, so no segment, derivative or
record copies one; the test harness builds records on the vector store
partition; main's splitting-segmenter test compares the default
segmenter with a text handler; and the event sample configuration main
added documents the text handler as the other sample configurations do.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

RegisteredBlock as the field type left three type errors where a
handler's or the codec's Block was assigned to the field. The fields
are typed Block, decoded through the registered union by a
before-validator and serialized as the concrete kind; the handler
tests keep a typed block in hand instead of narrowing the field.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

A context was a mapping the caller keyed by hand, and the rule that
the key equals the part's kind lived in prose. Context is a class now:
built from parts, read by kind, so there is no key to get wrong; two
parts of one kind are rejected at construction. It owns its wire form
through a Pydantic core schema, so a model field of the type accepts
an instance or `{kind: fields}` and serializes to `{kind: fields}`,
and the per-model validators, `with_part`, `encode_context` and
`decode_context` go.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

The kind-keyed tables removed its config, its service-locator branch
and its test, and the module survived with no consumer. The long-term
memory's over-fetch comment named it too; it now says why a segmenter
can carry one episode several times. The expand_context comment main
added names it as well; it now says "no segmenter handler".

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

A coding agent's transcript carries more than messages: the tool calls
the agent makes, what those tools return, and text that entered the
conversation without a user typing it. Each is a block kind of its own,
registered so the v1 events route accepts it and the timeline holds it.

`tool_call` carries the tool's name and its input. The input is a JSON
object rather than a mapping of property values: a tool's arguments
nest, and a block is content the event carries, not something the event
is filtered by. `tool_result` carries the tool's name, its output, and
whether the tool failed instead of returning; a result says nothing
about failure unless it says so. `injected` carries the text and what
put it there: a hook, a skill, a compaction, a reminder, a command, or
something else.

Each kind renders on one line, through the same `render` a timeline
reader already gets for a message: a call's input as compact JSON, a
failed result behind an `[error]` marker, injected text behind its
source. A window mixing messages and tool events reads as one timeline.

None of the three declares a segmenter or a deriver, so the tables'
fallbacks decide: one segment per block, however long, and no
derivative and no vector record. A tool event is on the timeline
and off the search surface, reached by expanding from a
message, which is the capture policy the coding-agent integration
settled on.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

The kinds' round trip through the codec, their encoded form, and what
each renders: a call as its tool and its input on one line, a result as
its tool and its output with an `[error]` marker when it failed, and
injected text as its source and its text. An empty or overlong tool
name, an unlisted injection source and an unregistered kind are
rejected.

Segmentation and derivation are asserted where the tables decide them:
a long tool result is one segment while the text handler splits the
message beside it, and the text deriver derives nothing from any of the
three. End to end, an event carrying a message, a call and a result is
three segments and one vector record, the query reaches the message,
and expanding from it returns the two tool events.

The route's tests go with the v1 route, which sits above this change.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

Capture holds everything the session log holds, never what a model
selected, so the agent's reasoning is a kind of its own rather than
something dropped on the way in: `{"kind": "thinking", "text": ...}`,
holding the reasoning as the transcript recorded it.

It is treated as the tool events are. It declares no segmenter and no
deriver, so reasoning is one segment however long and yields no
derivative and no vector record: it is on the timeline and off the
search surface, reached by expanding from a message. It renders as
`thinking: <text>`, one line of the same timeline a message and a tool
event render into.

The v1 route, which sits above this change, accepts it through the
registered union and names it with the other kinds.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

An event belongs to a session, a conversation's own timeline, and a
walk never leaves it. Event, Segment and Derivative carry a required,
bounded session_id; the segment row holds it in a NOT NULL column, the
ordering index's second, after the incarnation
(event_memory_store_sg__in_se_ts_ev_ix_of), and
a neighborhood's walk pins the seed's session, on SQLite as a bound
parameter per seed and on PostgreSQL through the lateral join, inside
the same context window. query, expand and get_segments take
session_ids, an empty list keeping nothing and None every session; the
vector record carries the session under its reserved key, so the vector
stage evaluates session_ids too; expand raises LookupError for a seed
outside the named sessions, which it checks through get_segments. The v2
adapter has no conversation id to give, so every event it ingests is in
one reserved session, memmachine_default.

On this base the session goes onto the event memory store's names, the
write transaction's segment insert and the kind-keyed segmenter and
deriver tables, which copy it into every segment and derivative they
build.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE

`render` takes any segments, drops one given twice, and lays them out as
a block per session, the sessions in the order of their latest
timestamps with a blank line between, each block in the store's order,
one line per run of adjacent pieces of one event. Nothing in the text
says whether two lines are adjacent in the store, since a filtered walk
can omit a neighbor and no segment carries a position.

`ids` marks what a reader can name back: `"session"` heads each block
with `[session:"<id>"]`, the id JSON-quoted since a session id is any
string; `"segment"` starts each line with `[segment:<hex>]`, or
`[segments:<first>..<last>]` when the line holds more than one, so the
marker says which id opens the event and which closes it without a word
of prompting, and a one-segment event carries one id. Uuids are 32 hex
digits. With no ids and one session the text is what `render` produced
before, which `rerank` relies on.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01YBbQgZiCqeoLu83EkbEFHE