feat(clients): sessions+registry+optimize+armor: close gaps, loud list truncation, shared Gemini adapter

sessions: operations get/list/cancel/delete/wait for engine, session, memory and
serving profile; servingProfiles CRUD. registry: ListResult with truncated flag,
v1alpha twins, gateway/policy operations, authz IAM, deny policy update, boundary
patch/bindings. optimize: make_gemini_model over models::VertexModel (DirectModel
removed), generateSyntheticData, online evaluator operations, trace/log writers.
armor: SecurityAdmin for all SCC v2 methods (attack exposure excluded), documented
agent threat categories, floor settings fixed to location global after live run.
check_discovery.py of all four enforce coverage.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-24 05:43:13 +02:00
co-authored by Claude Sonnet 5.5
parent 29d775a923
commit a3396bfc68
83 changed files with 5020 additions and 378 deletions
+59 -18
View File
@@ -17,8 +17,16 @@ Gemini Enterprise Agent Platform, Agent Engine (`reasoningEngines`) children:
create, get, list, patch, delete, purge (explicit, guarded), revisions
(list, get), rollback, topics (managed and custom), scope maps, metadata.
- Long-running operations: every mutating call returns an Operation; the module
waits with `wait_operation` (hard caps in `OperationCaps`). `operation()`,
`cancel_operation()` and `wait()` expose them for one engine only.
waits with `wait_operation` (hard caps in `OperationCaps`). All five
Discovery operations methods (get, list, cancel, delete, wait) are wrapped
for the four places Discovery puts them: under the engine, under a session,
under a memory and under a serving profile (20 table rows). `operation()`,
`list_operations()`, `cancel_operation()`, `delete_operation()`, `wait()`
(client polling) and `wait_server()` (one POST `:wait?timeout=Ns`, 1..60 s)
work for one root only: the engine, or the location for serving profiles.
- Serving profiles (`projects.locations.servingProfiles`, location level, not
engine scoped): create (waits), get, list, patch, delete, with scope
`GEMINI_LIVE`, `INTERACTIONS_API` or `RESPONSE_API`, optional CMEK key.
Everything is against one API surface: `aiplatform` **v1beta1**. See section 6
for why not v1.
@@ -29,15 +37,18 @@ for why not v1.
|---|---|
| `caps.h` | Static ceilings (`SessionsCaps`, `MemoryCaps`) |
| `calls.h` | The ONE table of every REST call (verb, path, discovery method, request fields, query params) |
| `names.h/.cpp` | `EngineName` (validated resource name), `Check` (input validators), wire helpers |
| `names.h/.cpp` | `EngineName`, `LocationName` (validated resource names), `Check` (input validators), wire helpers |
| `operation_names.h/.cpp` | `OperationName`: validates an operation name against its root, picks the table row for each verb by owner (engine, session, memory, serving profile) |
| `operation_service.h/.cpp` | `OperationService : Service`: table-driven `send`, `settle`, loud capped `list_items` (`list_over_limit`), the operations surface |
| `serving_profile.h/.cpp` | `ServingProfileSpec`, `ServingProfilePatch`, `ServingProfile`, `ServingScope`, `ServingProfiles : OperationService` |
| `session_types.h/.cpp` | `SessionSpec`, `Session`, `SessionPatch`, `CompactRequest`, `SessionEvent`, list options |
| `memory_types.h/.cpp` | `Memory`, `MemorySpec`, `MemoryPatch`, `Topic`, `MetadataValue`, `MetadataFilter`, `MemoryGenerateRequest`, `IngestRequest`, `RetrieveRequest`, `PurgeRequest`, `MemoryRevision`, `Profile` |
| `engine_service.h/.cpp` | `EngineService : Service`: table-driven `send`, `settle`, capped `list_items`, operation helpers |
| `engine_service.h/.cpp` | `EngineService : OperationService`: one validated engine and its v1beta1 endpoint |
| `sessions.h/.cpp` | `Sessions : EngineService` |
| `memory_bank.h/.cpp` | `MemoryBank : EngineService` |
| `tools/check_discovery.py` | Verifies `calls.h` and the typed bodies against Google's Discovery document |
Tests: `tests/src/google/sessions/test_sessions.cpp`. Example:
Tests: `tests/src/google/sessions/test_sessions.cpp` and `test_sessions_gaps.cpp`. Example:
`example/app/agent/SessionsDemo.cpp` (routes under `/agent/sessions`), tests in
`tests/example/agent/sessions/`.
@@ -50,7 +61,9 @@ Tests: `tests/src/google/sessions/test_sessions.cpp`. Example:
| Session TTL | `Ns` form, 24 h minimum (Google), 3650 days maximum (ours) |
| session_state / event | 64 KiB / 256 KiB serialized |
| Labels | 20, key and value 64 chars |
| List pages / items | 10 pages of 100, 1000 items; more is `RESULT_TOO_LARGE`, narrow the filter |
| List pages / items | 10 pages of 100, 1000 items; more items OR a further page after the last allowed one is `RESULT_TOO_LARGE` (502), never a silent cut, narrow the filter |
| Server-side operation wait | 1..60 s per call (`kMaxServerWaitSeconds`) |
| Serving profile | id 1..63 `[a-z0-9-]`, display name required 128, description 4000, KMS key name 512 |
| Scope | 1..10 entries, 128 chars, no `*` |
| Fact / description / context | 4000 chars |
| Generate sources | 100 events, 64 KiB; direct memories max 5 (Google) |
@@ -83,10 +96,14 @@ Tests: `tests/src/google/sessions/test_sessions.cpp`. Example:
credential) and fails if a declared call, verb, path, request field, query
parameter, enum value, response key or nested request field is absent.
Result 2026-10-24: `OK 2026-10-24: 23 calls, 7 enums, 25 response keys, 18
nested schemas match aiplatform v1beta1 discovery`. A deliberately misspelled
field made it exit 1 (checked). Rerun it after any change to `calls.h` or the
typed bodies.
Result 2026-10-24: `OK 2026-10-24: 46 calls, 8 enums, 34 response keys, 20
nested schemas match aiplatform v1beta1 discovery`. The script also checks
coverage: every Discovery method under `reasoningEngines.operations`,
`reasoningEngines.sessions`, `reasoningEngines.memories` and `servingProfiles`
must be a table row or listed in `EXCLUDED` (empty: nothing is excluded), so a
method Google adds later fails the check. A deliberately misspelled field made
it exit 1 (checked). Rerun it after any change to `calls.h` or the typed
bodies.
From discovery (v1beta1, `projects.locations.reasoningEngines`):
sessions create (POST, `sessionId` query, returns Operation), get, list
@@ -95,9 +112,12 @@ Operation), appendEvent (POST `:appendEvent`, body `SessionEvent`), compact
(POST `:compact`, returns Operation), events.list (`sessionEvents`);
memories generate / retrieve / retrieveProfiles / create (`memoryId`) / get /
list / patch (`updateMask`) / delete / purge / rollback / ingestEvents,
memories.revisions list / get; operations get / cancel. Discovery also lists
`wait`, `list`, `delete` on operations, which this module does not wrap
(`wait_operation` polls with GET).
memories.revisions list / get; operations get / cancel / list / delete / wait
under the engine, `sessions.operations.*` and `memories.operations.*` (same
five), `locations.servingProfiles` create (`servingProfileId` query, returns
Operation) / get / list / patch (`updateMask`) / delete (returns Empty) and
`servingProfiles.operations.*`. The Method column of a `calls.h` row is
relative to `kDiscoveryPrefix` unless it starts with `aiplatform.`.
## 6. Verified live
@@ -127,6 +147,20 @@ an express key and a token; v1 refuses keys. The opt-in test `sessions_live`
the real client (sessions list / get / events, memories list / get /
revisions) and passed with the key and with the token on 2026-10-24.
Gap-closing round, same day, service-account token, read-only:
| Call | Result |
|---|---|
| GET `v1beta1/.../reasoningEngines/1/operations?pageSize=5`, `.../sessions/abc/operations`, `.../memories/abc/operations` | 200 `{}` (empty list, even though engine 1 does not exist) |
| GET `v1beta1/.../locations/us-central1/servingProfiles?pageSize=5` (also `global` host and `europe-west4`) | 501 `UNIMPLEMENTED` "Operation is not implemented, or supported, or enabled." (not available to this project) |
| GET `v1beta1/.../servingProfiles/probe` | 501 UNIMPLEMENTED |
| GET `v1beta1/.../servingProfiles/probe/operations` | 400 INVALID_ARGUMENT: "the idType servingProfiles is not a documented LRO Parent ID, the associated value must be a Long, but was instead: probe" |
| GET `v1beta1/.../servingProfiles/123/operations?pageSize=1` | 200 `{}` |
The opt-in test `sessions_live.operations_and_serving_profiles_reads` repeats
the operations lists and the servingProfiles list through the real client; it
accepts 200 or 501/403/404 for servingProfiles and prints which one it saw.
No Agent Engine exists in the project, so **no happy path was verified
live**: create, patch, delete, append, compact, generate, ingest, retrieve,
retrieveProfiles, purge, rollback are verified by discovery only. Nothing that
@@ -151,18 +185,25 @@ Neither discovery nor the docs pages read state these; they are inferred:
search model (docs); the error body when it is not is unread.
- Memory Profiles need schema configs on the engine (`MemoryBankConfig` in the
runtime module); the shape of `profile` is free-form and kept raw.
- Serving profile id charset (`[a-z0-9-]`, 1..63 is our choice) and the real
id rule: Google's LRO layer wants a numeric id for operations under a
serving profile (400 above), so Google may assign or require numeric ids.
The create/patch responses (Operation `response` is `Any`) are parsed
tolerantly with a GET fallback. `servingProfiles` itself answers 501 on this
project, so no body of it was ever seen.
- Whether `operations.wait` answers `done: false` at the timeout or an error
(the docs line says "at most the time permitted"): both are handled, a
not-done answer is returned to the caller, not retried.
- Managed topic names beyond the four in discovery, and `thought`/`audio` parts
inside event `content` (typed by `gemini_types.h`, unknown parts dropped).
## 8. Gaps
- `servingProfiles` (location-level create/get/list/patch for Gemini Live,
Interactions and Response APIs) is listed by discovery next to this product
but is not engine-scoped; not implemented here. Owner: the `live` or
`models` module.
- Engine-level Memory Bank configuration (`contextSpec.memoryBankConfig`,
customization, TTL config) is part of the Agent Engine resource: runtime
module.
- Operations `list`, `delete`, `wait` (server-side) are not wrapped.
- `servingProfiles` answers 501 for the test project in three locations, so
the happy path is Discovery-verified only. Owner: a project that has the
feature; test `sessions_live.operations_and_serving_profiles_reads`.
- Session and memory `labels` / `metadata` filters beyond a passthrough string.
- Token refresh is the caller's job (foundation gap).