@alvera-ai/platform-sdk 0.17.0-next.g97c2ef9 → 0.17.0-next.gae2995f

package/.agent/cookbook/_fixtures/organic-marketing/_lead_submissions_foundation_mdm.liquid

@@ -42,6 +42,7 @@
   "identifiers": [
     {
       "system": "{{ p.source_uri | json_escape }}",
+      "type": "digital_identifier",
       "value": "{{ p.email | json_escape }}"
     }
   ]

package/.agent/cookbook/_fixtures/primary-care-feedback/_cahps_appointments_generic_table.liquid

@@ -16,9 +16,10 @@
   workflow's — a filter that had to know about `"3 - checked out"` would
   be coupled to one vendor's export format.
 
-  `legal_entity_id` is NEVER written here. Contract B's
+  `legal_entity_id` is NEVER declared or written here. Contract B's
   `mdm_input_config` resolves the patient and the platform stamps the
-  subject's id onto the row; a column of that name would shadow it.
+  subject's id onto the row; the name is reserved, so declaring a column
+  of it 422s this create rather than shadowing the stamp.
 
   GT columns:
     * `appointment_id`  — the vendor's id (unique, so a re-ingest updates)

package/.agent/cookbook/_fixtures/subscription-saas/_customers_subscription_generic_table.liquid

@@ -7,8 +7,8 @@
   Contract B also carries an `mdm_input_config` (separate template), so
   the platform resolves each row's subject and stamps `legal_entity_id`
   onto the row. `legal_entity_id` is NEVER declared as a column and
-  never written here — the stamp is the platform's, and a column of the
-  same name would shadow it.
+  never written here — the stamp is the platform's, and the name is
+  reserved, so declaring it 422s this create rather than shadowing it.
 
   GT columns:
     * `customer_number` — Stripe's customer id (the unique column, so a

package/.agent/cookbook/organic-marketing.md

@@ -488,7 +488,7 @@ const ENRICHMENT_OUTPUT_SCHEMA = {
 }
 
 const OLLAMA_BASE_BODY =
-  '{"model": "{{ model }}", "messages": [{"role": "user", "content": "{{ rendered_prompt | json_escape }}", "images": [{% for img in images %}{% unless forloop.first %}, {% endunless %}"{{ img.data }}"{% endfor %}]}], "stream": false, "think": false, "options": {"temperature": 0, "num_ctx": 40960}, "format": {{ schema | to_json }}}'
+  '{"model": "{{ model }}", "messages": [{"role": "user", "content": "{{ rendered_prompt | json_escape }}", "images": [{% for img in images %}{% unless forloop.first %}, {% endunless %}"{{ img.data }}"{% endfor %}]}], "stream": false, "think": false, "options": {"temperature": {{ temperature }}, "num_predict": {{ max_tokens }}, "num_ctx": 40960}, "format": {{ schema | to_json }}}'
 
 const OLLAMA_EXTRACTOR =
   '{"output_json": "{{ msg.message.content | json_escape }}", "explanation": "{{ msg.message.thinking | json_escape }}", "input_tokens": {{ msg.prompt_eval_count | default: 0 }}, "output_tokens": {{ msg.eval_count | default: 0 }}, "total_tokens": {{ msg.prompt_eval_count | default: 0 | plus: msg.eval_count }}}'

package/.agent/cookbook/payments-compliance.md

@@ -547,7 +547,7 @@ const ENRICHMENT_OUTPUT_SCHEMA = {
 }
 
 const OLLAMA_BASE_BODY =
-  '{"model": "{{ model }}", "messages": [{"role": "user", "content": "{{ rendered_prompt | json_escape }}", "images": [{% for img in images %}{% unless forloop.first %}, {% endunless %}"{{ img.data }}"{% endfor %}]}], "stream": false, "think": false, "options": {"temperature": 0, "num_ctx": 40960}, "format": {{ schema | to_json }}}'
+  '{"model": "{{ model }}", "messages": [{"role": "user", "content": "{{ rendered_prompt | json_escape }}", "images": [{% for img in images %}{% unless forloop.first %}, {% endunless %}"{{ img.data }}"{% endfor %}]}], "stream": false, "think": false, "options": {"temperature": {{ temperature }}, "num_predict": {{ max_tokens }}, "num_ctx": 40960}, "format": {{ schema | to_json }}}'
 
 const OLLAMA_EXTRACTOR =
   '{"output_json": "{{ msg.message.content | json_escape }}", "explanation": "{{ msg.message.thinking | json_escape }}", "input_tokens": {{ msg.prompt_eval_count | default: 0 }}, "output_tokens": {{ msg.eval_count | default: 0 }}, "total_tokens": {{ msg.prompt_eval_count | default: 0 | plus: msg.eval_count }}}'
@@ -828,8 +828,8 @@ ingesting a JSON array into it is refused per row —
 still reports a row received.
 
 Do **not** declare a `legal_entity_id` column. The platform stamps it from
-Contract B's MDM resolve in §019, and a column of that name shadows the
-stamp silently.
+Contract B's MDM resolve in §019, and the name is reserved — declaring it
+does not shadow the stamp silently, it 422s the create.
 
 ```typescript
 const screenings = await ctx.ensure(
@@ -2177,4 +2177,4 @@ Running this walk again reuses all of it.
 - `datalakes.md` — the create body, and what the derived pair is for
 - `workflows.md` — scheduling versus firing, and the accessor tables
 - `interoperability_contracts.md` — the contract pair, and the
-  `legal_entity_id` stamp you must not shadow
+  reserved `legal_entity_id` stamp you must not declare

package/.agent/cookbook/primary-care.md

@@ -591,8 +591,8 @@ here is. Each half matters:
   gaps that actually have entries in them.
 
 Do **not** declare a `legal_entity_id` column. The platform stamps it from
-Contract B's resolve, and a column of that name shadows the stamp — which
-would leave the review link minted against nothing.
+Contract B's resolve, and the name is reserved — declaring it does not shadow
+the stamp, it 422s the create, so you lose the table until you drop it.
 
 ```typescript
 const appointments = await ctx.ensure(
@@ -1366,7 +1366,7 @@ const ENRICHMENT_OUTPUT_SCHEMA = {
 const OLLAMA_BASE_BODY =
   '{"model": "{{ model }}", "messages": [{"role": "user", "content": "{{ rendered_prompt | json_escape }}", ' +
   '"images": [{% for img in images %}{% unless forloop.first %}, {% endunless %}"{{ img.data }}"{% endfor %}]}], ' +
-  '"stream": false, "think": false, "options": {"temperature": 0, "num_ctx": 40960}, "format": {{ schema | to_json }}}'
+  '"stream": false, "think": false, "options": {"temperature": {{ temperature }}, "num_predict": {{ max_tokens }}, "num_ctx": 40960}, "format": {{ schema | to_json }}}'
 
 const OLLAMA_EXTRACTOR =
   '{"output_json": "{{ msg.message.content | json_escape }}", ' +

package/.agent/cookbook/subscription-saas.md

@@ -509,8 +509,8 @@ here, and the declaration goes live the moment someone calls
 call rather than being remembered afterwards.
 
 Do **not** declare a `legal_entity_id` column. The platform stamps it from
-the MDM resolve in §012, and a column of that name shadows the stamp — which
-would leave every connected-app link minted against nothing.
+the MDM resolve in §012, and the name is reserved — declaring it does not
+shadow the stamp, it 422s the create, so you lose the table until you drop it.
 
 ```typescript
 const customers = await ctx.ensure(
@@ -1457,7 +1457,7 @@ const ENRICHMENT_OUTPUT_SCHEMA = {
 const OLLAMA_BASE_BODY =
   '{"model": "{{ model }}", "messages": [{"role": "user", "content": "{{ rendered_prompt | json_escape }}", ' +
   '"images": [{% for img in images %}{% unless forloop.first %}, {% endunless %}"{{ img.data }}"{% endfor %}]}], ' +
-  '"stream": false, "think": false, "options": {"temperature": 0, "num_ctx": 40960}, "format": {{ schema | to_json }}}'
+  '"stream": false, "think": false, "options": {"temperature": {{ temperature }}, "num_predict": {{ max_tokens }}, "num_ctx": 40960}, "format": {{ schema | to_json }}}'
 
 const OLLAMA_EXTRACTOR =
   '{"output_json": "{{ msg.message.content | json_escape }}", ' +

package/.agent/data_activation_clients.md

@@ -521,7 +521,9 @@ const { data: search } = await api.datasets.createUserSearch(
   },
 )
 // search.id            — UUID of the materialised result set
-// search.status        — 'completed' on success; 'failed' surfaces error_message
+// search.status        — 'new' | 'in_progress' | 'completed' | 'error'.
+//                        The failure member is 'error', NOT 'failed' — and it is
+//                        'error' that carries error_message. There is no 'failed'.
 // search.results_count — ALWAYS null on the POST response (see Gotcha 5)
 
 // (2) GET paginates rows from the materialised result set.
@@ -529,6 +531,13 @@ const { data: search } = await api.datasets.createUserSearch(
 //       'raw'       — real values verbatim
 //       'tokenized' — masked columns return a stable tok_<hash>
 //       'redacted'  — masked columns return an unjoinable placeholder
+// `search.id` is `string | undefined` on the response type, and
+// `DatasetSearchOptions.userSearchId` is declared `?: string` — optional, but
+// NOT `| undefined`. So an app with `exactOptionalPropertyTypes` will not
+// compile the shorthand, and an app without it gets a runtime 404 that reads
+// like a wrong path. Narrow it first.
+if (!search.id) throw new Error(`createUserSearch returned no id (status ${search.status})`)
+
 const { data: page } = await api.datasets.search(
   tenantSlug,
   datalakeSlug,

package/.agent/datalakes.md

@@ -752,6 +752,24 @@ the SQL between the two calls.
   live — e.g. `WHERE some_boolean = 1` 422s on Postgres (booleans compare to
   `true`/`false`, never `1`). Surface the SQL to a human (or a checking step)
   and expect to edit before `executeSql`.
+- **`executeSql` returns rows as POSITIONAL ARRAYS, not objects keyed by
+  column.** `data` is `unknown[][]`; the column names are in `meta.columns`, in
+  the same order. So `row.legal_entity_id` is silently `undefined` — not an
+  error, just absent — and a probe written against it fails with a message
+  built from its own bug while the data is perfectly correct. Zip them:
+
+  ```ts
+  const { data: res } = await api.datalakes.executeSql(tenantSlug, datalakeSlug, {
+    sql, mode: 'raw',
+  })
+  const cols = res.meta.columns
+  const rows = res.data.map((r) => Object.fromEntries(cols.map((c, i) => [c, r[i]])))
+  // now rows[0].legal_entity_id is real
+  ```
+
+  Worth knowing before you write a richer check than the scaffolds ship: their
+  seeded example only asserts `data.length > 0`, which behaves identically for
+  both shapes, so nothing in the example reveals this.
 - **`executeSql`** body is `{ sql, mode, page?, page_size? }`. It runs the SQL
   **read-only** (INSERT/UPDATE/DELETE/DDL are rejected) against the
   mode-selected lake tier, with Flop-inspired pagination (`page_size` capped server-side). The JSON

package/.agent/generic_tables.md

@@ -283,9 +283,14 @@ and they are yours to read but never to declare:
 **`legal_entity_id` is the one that catches people.** It is not a
 column you declare and fill — a contract's `mdm_input_config`
 resolves the subject and the platform stamps it. Declaring a column
-of that name shadows the stamp, and the symptom is not an error: the
-row lands, the batch reports green, and every connected-app link
-minted from that row points at nobody.
+of that name does not shadow the stamp silently: the create is
+REJECTED with 422, and the message names the offending column
+(`contain reserved system column names: legal_entity_id`). You lose
+the create, not the linkage — so read the 422 as the platform telling
+you the column is already there, and drop it from your definition.
+There is correspondingly **nothing to guard against in a contract
+hook**: a table that declares the column is never created, so an
+`assert` on its absence can never fire.
 
 There is no longer a per-domain reserved list. GH-859 removed the
 industry datalakes and their MDM foreign keys, so names like
@@ -356,11 +361,25 @@ Standard JSON:API envelopes per `errors.md`. Common rejections:
 | `source.pointer`                 | Cause                                              |
 |----------------------------------|----------------------------------------------------|
 | `/title`                         | empty; generates a name colliding with existing; or starts with `alvera_system` prefix |
-| `/columns`                       | empty array; duplicate `column.name`; or zero columns marked `is_unique: true` |
-| `/columns/0/name`                | reserved column name (infrastructure column or the industry's MDM FK; see §2) |
+| `/columns`                       | empty array; duplicate `column.name`; zero columns marked `is_unique: true`; or a RESERVED column name (see §2) |
+| `/columns/0/name`                | too short/long, or not matching `[a-z][a-z0-9_]*`         |
 | `/columns/0/type`                | value not in supported type enum (see §2 column types)   |
 | `/columns/0/privacy_requirement` | value not in enum, OR `tokenize` on a `jsonb` column   |
 
+**Reserved names point at `/columns`, not at the offending index** —
+measured, not inferred. The check runs on the parent changeset
+(`add_error(changeset, :columns, …)`), so it names *every* offending
+column at once rather than the first it meets:
+
+```
+alvera: plan halted at generic_table "lead-submissions": server rejected request:
+  /columns: contain reserved system column names: legal_entity_id
+```
+
+Note where that halted: at **plan**, not apply — the server answering
+during plan's refresh, before any mutation. The per-column rows above
+are indexed because those validations run on the column embed itself.
+
 All of these come back as a 422 `AlveraApiError` thrown from the
 SDK on submit — structural cases (Layer 1) and semantic conflicts
 like name collision / deployed-name reuse (Layer 2). The SDK does

package/.agent/interoperability_contracts.md

@@ -134,8 +134,11 @@ they converge on one legal entity and the platform stamps
 `legal_entity_id` onto the generic-table row.
 
 **Never declare `legal_entity_id` as a column on that table.**
-Declaring it shadows the stamp, and it fails silently — the
-column simply stays empty.
+The name is reserved, so declaring it does not shadow the stamp —
+the create is REJECTED with 422 (`contain reserved system column
+names: legal_entity_id`). You lose the table, not the linkage.
+Drop it from your definition; the platform adds the column itself
+and you read the stamp back off the row.
 
 ### `filter_template` has INVERTED semantics
 

package/.agent/tools.md

@@ -637,13 +637,34 @@ await api.tools.testInvocation(
 inlines the value verbatim; `type: 'system'` references a
 platform-shipped template (see `templates.md`).
 
-**Test-invocation accepts exactly FIVE `tool_call_type` variants** —
-the interactive ones. Its request casts into a `ManualToolInvocation`
-embed (`on_type_not_found: :raise`) whose polymorphic set is
-`sms_request`, `mms_request`, `email_request`, `restapi_request`,
-`aws_lambda_request`. A tool whose body is SFTP / S3 / SQL /
-SharePoint has **no** test-invocation variant and cannot be exercised
-through this endpoint (same shape as the `status_poller` case below).
+**Test-invocation accepts SIX `tool_call_type` variants** — the
+interactive ones. Its request casts into a `ManualToolInvocation` embed
+(`on_type_not_found: :raise`) whose polymorphic set is `sms_request`,
+`mms_request`, `email_request`, `restapi_request`, `aws_lambda_request`
+and `sql_query`.
+
+THREE LISTS LIVE HERE and conflating them is the mistake this paragraph
+used to make. `tool_body_type` says what a tool IS (12 variants — `sns`,
+`twilio`, `s3`, `sql_database`, `sftp`, `sharepoint`, `manual_upload`, …).
+`tool_call_type` says how a CALL is shaped (9). Test-invocation accepts a
+subset of the call types (6). They do not map one-to-one: `sns` and
+`twilio` are both bodies that send SMS, so both call through
+`sms_request`; the `sql_database` body calls through `sql_query`.
+
+So a tool whose body is **S3, SFTP or SharePoint** has no test-invocation
+variant and cannot be exercised through this endpoint (same shape as the
+`status_poller` case below). SFTP and SharePoint are coming; S3 is not
+currently reachable this way either.
+
+**`manual_upload` is the exception worth knowing.** It is excluded from
+test-invocation, but it is NOT unexecutable — it has a real executor
+(`Platform.Tools.ManualUpload`, protocols.ex:105) which routes to the
+`ingest_json` path rather than the automated fetch pipeline. There is
+nothing to dial interactively because the input is a file someone
+supplies; the tool still runs. A born-red contract that demands a
+test-invocation smoke for a manual-upload tool is therefore asking for
+something that cannot exist, and the cure is to assert the tool's
+configuration and its provenance binding instead.
 Those config shapes still exist — but on the broader **workflow-action
 `ToolCallConfig`** surface (see `tool-call-configs.md`), not here. The
 per-branch required-list for the five test-invocable variants:
@@ -671,10 +692,18 @@ per-branch required-list for the five test-invocable variants:
 
    tool_call_type: 'restapi_request'
      required:   path, method, pagination_context_template
-     enums:      method ∈ HTTP methods (GET, POST, PUT, PATCH, DELETE,
-                 HEAD, OPTIONS)
-     optional:   body, params (each TemplateConfig — 'identity' or
-                 'custom' both accepted)
+     enums:      method ∈ 'head' | 'get' | 'put' | 'post' | 'delete' |
+                 'patch' — LOWERCASE. 'POST' is rejected as
+                 `/tool_call/method — Invalid value for enum`.
+     optional:   body, params
+     shapes:     path, body, params and pagination_context_template are
+                 EACH a TemplateConfig ({ type, body }) — 'identity' or
+                 'custom' both accepted. `path` is NOT a plain string;
+                 passing one is `/tool_call/path — Invalid value: Invalid
+                 object. Got: string`. It is an envelope so a path can be
+                 interpolated per row.
+                 pagination_context_template is required even with nothing
+                 to paginate — `{ type: 'null' }` is how you say so.
 
    tool_call_type: 'aws_lambda_request'
      required:   payload (TemplateConfig — 'identity' acceptable)

package/.agent/workflows.md

@@ -789,16 +789,14 @@ Each log carries:
 - `error_message` — coarse failure summary (e.g.
   `"AI enrichment failed: <agent_name>"`); rich detail lives
   in `error.json` (§ Per-step artifacts below)
-- `action_execution_logs` — nested rows, one per action that fired
-  (`message_body` virtual field is rendered when read via
-  `dataAccessMode: 'raw'`)
+- `action_execution_logs` — nested rows, one per action that fired,
+  carrying the `message_body` virtual field
 
 Methods:
 
 ```
 .list(tenantSlug, datalakeSlug, workflowSlug, query?)          Paged
-.get(tenantSlug, datalakeSlug, workflowSlug, logId,
-     { dataAccessMode? })                                      One row
+.get(tenantSlug, datalakeSlug, workflowSlug, logId)            One row
 .download(tenantSlug, datalakeSlug, workflowSlug, logId)       The run's artifact
 ```
 
@@ -818,13 +816,14 @@ await api.workflows.workflowLogs.list(tenantSlug, datalakeSlug, slug, {
 `filters` uses the Flop empty-bracket serialization on the wire —
 the SDK's serializer handles it; never hand-roll the query string.
 
-The `dataAccessMode` query parameter on `.get` controls how
-`message_body` is rendered:
-- `'raw'` — the real rendered body, with the resolved short path
-  `/t/<token>`
-- `'tokenized'` — masked display body, with each masked column as a
-  stable `tok_<hash>`
-- `'redacted'` — masked display body with unjoinable placeholders
+`.get` takes NO `dataAccessMode`. It used to; the platform removed the
+`data_access_mode` query from this endpoint, and the generated type is now
+`query?: never`, so passing one no longer compiles.
+
+An execution log is workflow bookkeeping rather than lake rows, so there is
+no tier to select. Choosing a tier belongs to the reads that return data —
+`datasets.search` and `datalakes.executeSql` both take a mode, and that is
+where `'raw' | 'tokenized' | 'redacted'` still applies.
 
 ### Per-step artifacts (event, filter, enrichment, error)
 

package/dist/index.d.mts

@@ -290,7 +290,7 @@ type AgenticWorkflowResponse = {
   readonly context_datasets?: Array<ContextDatasetResponse>;
   datalake?: DatalakeResponse;
   /**
-   * Dataset type the workflow listens on (e.g. patient, appointment, generic_table)
+   * Dataset type the workflow listens on (e.g. legal_entity, document, generic_table)
    */
   dataset_type: string;
   decision_config?: ComplexTemplateConfigResponse | null;
@@ -526,7 +526,7 @@ type DataActivationClientLogResponse = {
    */
   readonly client_id: string;
   /**
-   * Target dataset table for this slice (e.g. patients, observations)
+   * Target dataset table for this slice (e.g. legal_entities, documents)
    */
   dataset_table: string;
   /**
@@ -866,7 +866,7 @@ type ExecuteActionRequest = {
    */
   dataset_id: string;
   /**
-   * Decision key identifying which action to execute (e.g. 'cahps_survey')
+   * Decision key identifying which action to execute (e.g. 'send_welcome_email')
    */
   decision_key: string;
   /**
@@ -1025,7 +1025,7 @@ type ResolvePageResponse = {
     subject?: string | null;
   } | null;
   /**
-   * Route path within the connected app (e.g. /forms/cahps)
+   * Route path within the connected app (e.g. /forms/onboarding)
    */
   route_path: string;
   /**
@@ -1877,11 +1877,11 @@ type WorkflowLogListResponse = {
 /**
  * SystemDatasetListResponse
  *
- * Industry-registered dataset name strings for the datalake's data domain.
+ * The dataset name strings the platform registers. Identical for every datalake.
  */
 type SystemDatasetListResponse = {
   /**
-   * Sorted unique dataset name strings (e.g. `patient`, `appointment`, `legal_entity`).
+   * Sorted unique dataset name strings (e.g. `legal_entity`, `document`, `action_log`).
    */
   datasets: Array<string>;
 };
@@ -1980,9 +1980,9 @@ type SharePointExcelCallRequest = {
  */
 type DacRawLogFileResponse = {
   /**
-   * Bucket the archive lives in — raw or tokenized
+   * Bucket the archive lives in. One archive is written per log, and it is raw.
    */
-  mode: 'raw' | 'tokenized' | 'redacted';
+  mode: 'raw';
   /**
    * Cloud-storage object key of the merged NDJSON archive
    */
@@ -2238,7 +2238,7 @@ type WorkflowRunListResponse = {
  */
 type MinimalAiAgentResponse = {
   /**
-   * Data access level
+   * Which lake the agent reads. `tokenized` means the agent's context is read from the tokenized copy, so it never sees a real identifier. It is enforced, not advisory: an agent set to `tokenized` in an environment with no tokenized lake fails its enrichment step rather than falling back to raw.
    */
   data_access: 'raw' | 'tokenized';
   /**
@@ -3284,11 +3284,16 @@ type DatalakeMigrateResponse = {
    */
   enqueued_at: string;
   /**
-   * Oban job ID for tracking
+   * Oban job ID for tracking. This datalake's own job — the first of the batch. The derived lakes are migrated by their own jobs, which are not reported here.
    */
   job_id: number;
   /**
-   * Job status (always 'enqueued' at creation)
+   * Always the literal `enqueued` — a constant in the response body, not a
+   * reading of the job's state. A repeat call while a job for this datalake
+   * is still incomplete is deduplicated onto the existing job, so `job_id`
+   * and `enqueued_at` can describe an earlier request while this field
+   * still reads `enqueued`. Poll `GET /datalakes/:id` for real progress.
+   *
    */
   status: 'enqueued';
 };
@@ -4292,9 +4297,10 @@ type ToolSftpResponse = SftpResponse & {
  */
 type ResyncTableResponse = {
   /**
-   * Every table this actually emptied — the one asked for, plus anything that
-   * points at it. All of them are copied again by the same run. Returned rather
-   * than assumed, because a caller that emptied nine tables should be told nine.
+   * Every table the repair emptied — the one asked for, plus anything that
+   * points at it, read from the catalog for this call. All of them are copied
+   * again by the same run. Returned in full because a caller that emptied nine
+   * tables should be told nine.
    *
    */
   emptied: Array<string>;
@@ -4303,7 +4309,13 @@ type ResyncTableResponse = {
    */
   mode: 'tokenized' | 'redacted';
   /**
-   * Always `copying` — the repair starts a first pass that finishes later
+   * Always the literal `copying` — a constant written once the repair's last
+   * statement succeeded, not a reading of the copy. Nothing here queries the
+   * subscription. `copying` is *also* one of the real table states
+   * `GET .../tables` reports, and the two are unrelated: a table that has just
+   * been put back on the subscription usually reads `waiting_to_start` for a
+   * moment first. Poll `GET .../tables` for the state the copy is actually in.
+   *
    */
   status: 'copying';
   /**
@@ -4373,7 +4385,7 @@ type AiAgentResponse = {
    */
   readonly checksum?: string;
   /**
-   * Data access level
+   * Which lake the agent reads. `tokenized` means the agent's context is read from the tokenized copy, so it never sees a real identifier. It is enforced, not advisory: an agent set to `tokenized` in an environment with no tokenized lake fails its enrichment step rather than falling back to raw.
    */
   data_access: 'raw' | 'tokenized';
   datalake?: DatalakeResponse;
@@ -4760,7 +4772,7 @@ type AgenticWorkflowRequestWritable = {
    */
   context_datasets?: Array<ContextDatasetRequestWritable>;
   /**
-   * Dataset type the workflow listens on (e.g. patient, appointment, generic_table)
+   * Dataset type the workflow listens on (e.g. legal_entity, document, generic_table)
    */
   dataset_type: string;
   decision_config?: ComplexTemplateConfigRequest;
@@ -5109,7 +5121,7 @@ type WorkflowAiAgentRequestWritable = {
  */
 type AiAgentRequestWritable = {
   /**
-   * Data access level
+   * Which lake the agent reads. `tokenized` means the agent's context is read from the tokenized copy, so it never sees a real identifier. It is enforced, not advisory: an agent set to `tokenized` in an environment with no tokenized lake fails its enrichment step rather than falling back to raw.
    */
   data_access: 'raw' | 'tokenized';
   /**
@@ -7014,6 +7026,51 @@ type PlatformApiAgenticWorkflowOperationsControllerBatchLogsIndexData = {
   };
   url: '/api/v1/tenants/{tenant_slug}/datalakes/{datalake_slug}/agentic-workflows/{workflow_slug}/batch-logs';
 };
+type PlatformApiDatalakeControllerMetadataData = {
+  body?: never;
+  path: {
+    /**
+     * Tenant slug
+     */
+    tenant_slug: string;
+  };
+  query?: {
+    /**
+     * Page number (1-indexed). Defaults to 1 when omitted.
+     */
+    page?: number;
+    /**
+     * Items per page (1-100). Defaults to the resource's Flop default when omitted.
+     */
+    page_size?: number;
+    /**
+     * Fields to sort by, in order of precedence. Must appear in the resource schema's Flop `sortable:` list — unknown fields return 422.
+     */
+    order_by?: Array<string>;
+    /**
+     * Sort direction(s), pair-wise with `order_by`. `asc` or `desc`. Defaults to `asc` per unpaired `order_by` entry.
+     */
+    order_directions?: Array<'asc' | 'desc'>;
+    /**
+     * Flop-native filter array. URL shape: `?filters[][field]=status&filters[][op]=%3D%3D&filters[][value]=pending` (empty brackets — consecutive `[]` entries group into one filter object per element; indexed brackets parse as a map and fail the array cast with 422). `op` is the symbol, percent-encoded — `%3D%3D` for `==`, `%3E%3D` for `>=` — not a word like `equal`; anything outside the enum above is a 422 before the request reaches Flop. Omit `op` entirely for equality. Unknown fields return 422 via Flop validation at the context layer.
+     */
+    filters?: Array<{
+      /**
+       * Filterable field name (must be in the resource's `filterable:`)
+       */
+      field: string;
+      /**
+       * Comparison operator. Defaults to `==` when omitted.
+       */
+      op?: '==' | '!=' | '<' | '<=' | '>' | '>=' | 'empty' | 'not_empty' | 'like' | 'ilike' | 'like_and' | 'like_or' | 'ilike_and' | 'ilike_or' | 'in' | 'not_in' | 'contains' | 'not_contains';
+      /**
+       * Filter value — shape depends on `field` and `op`.
+       */
+      value: unknown;
+    }>;
+  };
+  url: '/api/v1/tenants/{tenant_slug}/datalakes/metadata';
+};
 type PlatformApiDataActivationClientControllerIndexData = {
   body?: never;
   path: {
@@ -7777,10 +7834,7 @@ declare function _buildApi(myClient: Client): {
       request: Request;
       response: Response;
     }>;
-    metadata: (tenantSlug: string, query?: {
-      page?: number;
-      page_size?: number;
-    }) => Promise<{
+    metadata: (tenantSlug: string, query?: PlatformApiDatalakeControllerMetadataData["query"]) => Promise<{
       data: string;
       request: Request;
       response: Response;
@@ -8424,9 +8478,7 @@ declare function _buildApi(myClient: Client): {
         request: Request;
         response: Response;
       }>;
-      get: (tenantSlug: string, datalakeSlug: string, workflowSlug: string, id: string, opts?: {
-        dataAccessMode?: "raw" | "tokenized" | "redacted";
-      }) => Promise<{
+      get: (tenantSlug: string, datalakeSlug: string, workflowSlug: string, id: string) => Promise<{
         data: WorkflowLogResponse;
         request: Request;
         response: Response;