# Consolidate

## POST `/v1/consolidate`

Extract Claims and group them into Engrams. With workspace, submit source Experiences, wait for committed Recall-ready claims and schedule background consolidation; an optional query also runs Recall. Without workspace, process only this request and return bounded results without persistence or a continuation. stream=true emits provisional claims and one authoritative completed result; one-shot mode also emits engram previews. Workspace collections have resource page URLs; one-shot collections have nextPageUrl:null and a truncated flag. No query endpoints or saved snapshots are supported.

## Authentication

Use an API key with the AugentaKey authorization scheme. See [Authentication](https://augenta.pages.dev/docs/authentication.md).

## Request example

```bash
curl --fail-with-body -X POST "https://api.augenta.ai/v1/consolidate" \
  -H "Authorization: AugentaKey $AUGENTA_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "session": "<string>",
  "messages": [
    {
      "role": "system",
      "content": "<string>"
    }
  ]
}'
```

## Body fields

Send messages with session, or experience envelopes. Include workspace for durable processing and optional Recall/context. Omit workspace for one-shot stateless processing: no data is retained and no continuation is returned. query, budget_tokens and keep_recent apply only to Workspace mode; summaries applies only to one-shot mode.

**Option 1**

<a id="request-body-option-1-stream"></a>

### `request.body.option-1.stream`

`boolean` · optional

<a id="request-body-option-1-include"></a>

### `request.body.option-1.include`

`array<string>` · optional

Which Claim collections to load in a completed-memory result. `claims` loads each Engram's initial Claim page; `extractedClaims` loads a separate page for this call's extraction. Omit this parameter for both, or send \[] for neither. Asynchronous Workspace Experiences rejects output controls.

Default: `["claims","extractedClaims"]`.

Max items: `2`.
Allowed values: `"claims"`, `"extractedClaims"`.

<a id="request-body-option-1-claims_limit"></a>

### `request.body.option-1.claims_limit`

`integer` · optional

Maximum Claims per initial collection page. It does not cap the Engram's total claimCount. Workspace results expose nextPageUrl for more. One-shot results report truncated when items were omitted and cannot be browsed later.

Default: `100`.

Minimum: `1`. Maximum: `500`.

<a id="request-body-option-1-engrams_limit"></a>

### `request.body.option-1.engrams_limit`

`integer` · optional

Maximum Engrams in the initial result page. A shared output bound can make output shorter. Follow Workspace engrams.nextPageUrl for more; one-shot results report truncated instead of a browsing URL.

Default: `100`.

Minimum: `1`. Maximum: `500`.

<a id="request-body-option-1-summaries"></a>

### `request.body.option-1.summaries`

`boolean` · optional

Write summaries for one-shot Engrams (default true). false skips summary writing and omits summary, label and labelSupport. Workspace summaries follow its synthesis policy. Stateless output is not saved.

<a id="request-body-option-1-session"></a>

### `request.body.option-1.session`

`string` · required

Min length: `1`. Max length: `256`.

<a id="request-body-option-1-messages"></a>

### `request.body.option-1.messages`

`array<value>` · required

Min items: `1`. Max items: `100000`.

<a id="request-body-option-1-messages-role"></a>

### `request.body.option-1.messages.role`

`string` · required

Allowed values: `"system"`, `"developer"`, `"user"`, `"assistant"`, `"tool"`.

<a id="request-body-option-1-messages-content"></a>

### `request.body.option-1.messages.content`

`choice` · required

**Option 1**

**Option 2**

**Option 3**

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="request-body-option-1-messages-tool_calls"></a>

### `request.body.option-1.messages.tool_calls`

`array<object>` · optional

<a id="request-body-option-1-messages-tool_calls-id"></a>

### `request.body.option-1.messages.tool_calls.id`

`string` · required

<a id="request-body-option-1-messages-tool_calls-type"></a>

### `request.body.option-1.messages.tool_calls.type`

`string` · optional

<a id="request-body-option-1-messages-tool_calls-function"></a>

### `request.body.option-1.messages.tool_calls.function`

`object` · required

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="request-body-option-1-messages-tool_call_id"></a>

### `request.body.option-1.messages.tool_call_id`

`string` · optional

<a id="request-body-option-1-messages-name"></a>

### `request.body.option-1.messages.name`

`string` · optional

<a id="request-body-option-1-messages-ts"></a>

### `request.body.option-1.messages.ts`

`string` · optional

<a id="request-body-option-1-messages-seq"></a>

### `request.body.option-1.messages.seq`

`integer` · optional

Minimum: `0`.

**Option 2**

<a id="request-body-option-2-stream"></a>

### `request.body.option-2.stream`

`boolean` · optional

<a id="request-body-option-2-include"></a>

### `request.body.option-2.include`

`array<string>` · optional

Which Claim collections to load in a completed-memory result. `claims` loads each Engram's initial Claim page; `extractedClaims` loads a separate page for this call's extraction. Omit this parameter for both, or send \[] for neither. Asynchronous Workspace Experiences rejects output controls.

Default: `["claims","extractedClaims"]`.

Max items: `2`.
Allowed values: `"claims"`, `"extractedClaims"`.

<a id="request-body-option-2-claims_limit"></a>

### `request.body.option-2.claims_limit`

`integer` · optional

Maximum Claims per initial collection page. It does not cap the Engram's total claimCount. Workspace results expose nextPageUrl for more. One-shot results report truncated when items were omitted and cannot be browsed later.

Default: `100`.

Minimum: `1`. Maximum: `500`.

<a id="request-body-option-2-engrams_limit"></a>

### `request.body.option-2.engrams_limit`

`integer` · optional

Maximum Engrams in the initial result page. A shared output bound can make output shorter. Follow Workspace engrams.nextPageUrl for more; one-shot results report truncated instead of a browsing URL.

Default: `100`.

Minimum: `1`. Maximum: `500`.

<a id="request-body-option-2-summaries"></a>

### `request.body.option-2.summaries`

`boolean` · optional

Write summaries for one-shot Engrams (default true). false skips summary writing and omits summary, label and labelSupport. Workspace summaries follow its synthesis policy. Stateless output is not saved.

<a id="request-body-option-2-experiences"></a>

### `request.body.option-2.experiences`

`array<value>` · required

Min items: `1`. Max items: `50`.

<a id="request-body-option-2-experiences-src"></a>

### `request.body.option-2.experiences.src`

`string` · required

Who composed it. Send `service` from your own code.

Allowed values: `"service"`, `"claude-code"`, `"codex"`.

<a id="request-body-option-2-experiences-sid"></a>

### `request.body.option-2.experiences.sid`

`string` · required

The session id: one conversation, one agent run, or one document. Experiences that share it are one stream.

Min length: `1`.

<a id="request-body-option-2-experiences-proj"></a>

### `request.body.option-2.experiences.proj`

`string` · optional

An optional project name, for your own grouping. Defaults to empty.

<a id="request-body-option-2-experiences-type"></a>

### `request.body.option-2.experiences.type`

`string` · optional

`trajectory` (the default) for conversations and agent runs, `doc` for a document.

<a id="request-body-option-2-experiences-events"></a>

### `request.body.option-2.experiences.events`

`array<value>` · optional

A trajectory's steps. Required for a trajectory; not allowed on other types.

<a id="request-body-option-2-experiences-events-seq"></a>

### `request.body.option-2.experiences.events.seq`

`integer` · required

The step's position in the session. Integer; give each step its own, increasing across calls.

<a id="request-body-option-2-experiences-events-ts"></a>

### `request.body.option-2.experiences.events.ts`

`string` · required

When it happened: ISO-8601 with an offset.

<a id="request-body-option-2-experiences-events-kind"></a>

### `request.body.option-2.experiences.events.kind`

`string` · required

`msg` for a message; `session` for context such as a system prompt; `tool` for a tool call or result.

Allowed values: `"msg"`, `"tool"`, `"error"`, `"outcome"`, `"session"`.

<a id="request-body-option-2-experiences-events-role"></a>

### `request.body.option-2.experiences.events.role`

`string` · required

Allowed values: `"user"`, `"assistant"`, `"tool"`, `"system"`.

<a id="request-body-option-2-experiences-events-text"></a>

### `request.body.option-2.experiences.events.text`

`string` · required

What was said or done. Scrub secrets before sending.

<a id="request-body-option-2-experiences-data"></a>

### `request.body.option-2.experiences.data`

`value` · optional

Any JSON. A document's content: `{documentId, title?, text, capturedAt?, deleted?}`. Optional on a trajectory, where it is kept as raw telemetry.

**Option 3**

<a id="request-body-option-3-stream"></a>

### `request.body.option-3.stream`

`boolean` · optional

<a id="request-body-option-3-claims_limit"></a>

### `request.body.option-3.claims_limit`

`integer` · optional

Maximum Claims per initial collection page. It does not cap the Engram's total claimCount. Workspace results expose nextPageUrl for more. One-shot results report truncated when items were omitted and cannot be browsed later.

Default: `100`.

Minimum: `1`. Maximum: `500`.

<a id="request-body-option-3-include"></a>

### `request.body.option-3.include`

`array<string>` · optional

Allowed values: `"extractedClaims"`.

<a id="request-body-option-3-query"></a>

### `request.body.option-3.query`

`string` · optional

Min length: `1`. Max length: `4096`.

<a id="request-body-option-3-budget_tokens"></a>

### `request.body.option-3.budget_tokens`

`integer` · optional

Minimum: `1`. Maximum: `128000`.

<a id="request-body-option-3-keep_recent"></a>

### `request.body.option-3.keep_recent`

`integer` · optional

Minimum: `0`. Maximum: `100000`.

<a id="request-body-option-3-workspace"></a>

### `request.body.option-3.workspace`

`string` · required

Min length: `1`.

<a id="request-body-option-3-session"></a>

### `request.body.option-3.session`

`string` · required

Min length: `1`. Max length: `256`.

<a id="request-body-option-3-messages"></a>

### `request.body.option-3.messages`

`array<value>` · required

Min items: `1`. Max items: `100000`.

<a id="request-body-option-3-messages-role"></a>

### `request.body.option-3.messages.role`

`string` · required

Allowed values: `"system"`, `"developer"`, `"user"`, `"assistant"`, `"tool"`.

<a id="request-body-option-3-messages-content"></a>

### `request.body.option-3.messages.content`

`choice` · required

**Option 1**

**Option 2**

**Option 3**

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="request-body-option-3-messages-tool_calls"></a>

### `request.body.option-3.messages.tool_calls`

`array<object>` · optional

<a id="request-body-option-3-messages-tool_calls-id"></a>

### `request.body.option-3.messages.tool_calls.id`

`string` · required

<a id="request-body-option-3-messages-tool_calls-type"></a>

### `request.body.option-3.messages.tool_calls.type`

`string` · optional

<a id="request-body-option-3-messages-tool_calls-function"></a>

### `request.body.option-3.messages.tool_calls.function`

`object` · required

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="request-body-option-3-messages-tool_call_id"></a>

### `request.body.option-3.messages.tool_call_id`

`string` · optional

<a id="request-body-option-3-messages-name"></a>

### `request.body.option-3.messages.name`

`string` · optional

<a id="request-body-option-3-messages-ts"></a>

### `request.body.option-3.messages.ts`

`string` · optional

<a id="request-body-option-3-messages-seq"></a>

### `request.body.option-3.messages.seq`

`integer` · optional

Minimum: `0`.

**Option 4**

<a id="request-body-option-4-stream"></a>

### `request.body.option-4.stream`

`boolean` · optional

<a id="request-body-option-4-claims_limit"></a>

### `request.body.option-4.claims_limit`

`integer` · optional

Maximum Claims per initial collection page. It does not cap the Engram's total claimCount. Workspace results expose nextPageUrl for more. One-shot results report truncated when items were omitted and cannot be browsed later.

Default: `100`.

Minimum: `1`. Maximum: `500`.

<a id="request-body-option-4-include"></a>

### `request.body.option-4.include`

`array<string>` · optional

Allowed values: `"extractedClaims"`.

<a id="request-body-option-4-query"></a>

### `request.body.option-4.query`

`string` · optional

Min length: `1`. Max length: `4096`.

<a id="request-body-option-4-budget_tokens"></a>

### `request.body.option-4.budget_tokens`

`integer` · optional

Minimum: `1`. Maximum: `128000`.

<a id="request-body-option-4-keep_recent"></a>

### `request.body.option-4.keep_recent`

`integer` · optional

Minimum: `0`. Maximum: `100000`.

<a id="request-body-option-4-workspace"></a>

### `request.body.option-4.workspace`

`string` · required

Min length: `1`.

<a id="request-body-option-4-experiences"></a>

### `request.body.option-4.experiences`

`array<value>` · required

Min items: `1`. Max items: `50`.

<a id="request-body-option-4-experiences-src"></a>

### `request.body.option-4.experiences.src`

`string` · required

Who composed it. Send `service` from your own code.

Allowed values: `"service"`, `"claude-code"`, `"codex"`.

<a id="request-body-option-4-experiences-sid"></a>

### `request.body.option-4.experiences.sid`

`string` · required

The session id: one conversation, one agent run, or one document. Experiences that share it are one stream.

Min length: `1`.

<a id="request-body-option-4-experiences-proj"></a>

### `request.body.option-4.experiences.proj`

`string` · optional

An optional project name, for your own grouping. Defaults to empty.

<a id="request-body-option-4-experiences-type"></a>

### `request.body.option-4.experiences.type`

`string` · optional

`trajectory` (the default) for conversations and agent runs, `doc` for a document.

<a id="request-body-option-4-experiences-events"></a>

### `request.body.option-4.experiences.events`

`array<value>` · optional

A trajectory's steps. Required for a trajectory; not allowed on other types.

<a id="request-body-option-4-experiences-events-seq"></a>

### `request.body.option-4.experiences.events.seq`

`integer` · required

The step's position in the session. Integer; give each step its own, increasing across calls.

<a id="request-body-option-4-experiences-events-ts"></a>

### `request.body.option-4.experiences.events.ts`

`string` · required

When it happened: ISO-8601 with an offset.

<a id="request-body-option-4-experiences-events-kind"></a>

### `request.body.option-4.experiences.events.kind`

`string` · required

`msg` for a message; `session` for context such as a system prompt; `tool` for a tool call or result.

Allowed values: `"msg"`, `"tool"`, `"error"`, `"outcome"`, `"session"`.

<a id="request-body-option-4-experiences-events-role"></a>

### `request.body.option-4.experiences.events.role`

`string` · required

Allowed values: `"user"`, `"assistant"`, `"tool"`, `"system"`.

<a id="request-body-option-4-experiences-events-text"></a>

### `request.body.option-4.experiences.events.text`

`string` · required

What was said or done. Scrub secrets before sending.

<a id="request-body-option-4-experiences-data"></a>

### `request.body.option-4.experiences.data`

`value` · optional

Any JSON. A document's content: `{documentId, title?, text, capturedAt?, deleted?}`. Optional on a trajectory, where it is kept as raw telemetry.

## Response 200

JSON final result or SSE. Computation-stage first claim/engram timings exclude authentication, request parsing and progress events; null means no such item formed. Provisional engrams may be revised; completed Engrams are authoritative.

Content-Type: `application/json`

**Option 1**

<a id="response-200-option-1-billing"></a>

### `response.200.option-1.billing`

`object` · conditional

Present when billing is enabled. USD amount is exact. Receipt references settle only on successful server delivery; retries reuse the original debit.

<a id="response-200-option-1-billing-operationid"></a>

### `response.200.option-1.billing.operationId`

`string` · always present

<a id="response-200-option-1-billing-priceversion"></a>

### `response.200.option-1.billing.priceVersion`

`string` · always present

<a id="response-200-option-1-billing-sourcetokens"></a>

### `response.200.option-1.billing.sourceTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-1-billing-memorytokens"></a>

### `response.200.option-1.billing.memoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-1-billing-measuredmemorytokens"></a>

### `response.200.option-1.billing.measuredMemoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-1-billing-replayed"></a>

### `response.200.option-1.billing.replayed`

`boolean` · always present

<a id="response-200-option-1-billing-complimentary"></a>

### `response.200.option-1.billing.complimentary`

`boolean` · conditional

<a id="response-200-option-1-billing-ratedamount"></a>

### `response.200.option-1.billing.ratedAmount`

`string` · conditional

<a id="response-200-option-1-billing-amount"></a>

### `response.200.option-1.billing.amount`

`string` · always present

<a id="response-200-option-1-billing-receiptids"></a>

### `response.200.option-1.billing.receiptIds`

`array<string>` · always present

<a id="response-200-option-1-experiences"></a>

### `response.200.option-1.experiences`

`array<value>` · always present

<a id="response-200-option-1-experiences-object"></a>

### `response.200.option-1.experiences.object`

`string` · always present

The resource type. Always experience.

Allowed values: `"experience"`.

<a id="response-200-option-1-experiences-id"></a>

### `response.200.option-1.experiences.id`

`string` · always present

The ID Augenta assigns to this submitted source. In Workspace mode, use it with GET /v1/experiences/{id} to check processing status. One-shot source references have no stored status URL.

<a id="response-200-option-1-experiences-status"></a>

### `response.200.option-1.experiences.status`

`string` · always present

Allowed values: `"consolidated"`, `"skipped"`.

<a id="response-200-option-1-experiences-billingoperationid"></a>

### `response.200.option-1.experiences.billingOperationId`

`string` · conditional

Reference to this source's billing operation, when billing is enabled.

<a id="response-200-option-1-experiences-claimids"></a>

### `response.200.option-1.experiences.claimIds`

`array<string>` · always present

<a id="response-200-option-1-extractedclaims"></a>

### `response.200.option-1.extractedClaims`

`object` · conditional

A page of Claims from this call's source material, including Claims that did not form an Engram. A Claim can also appear in an Engram's claims.data with the same ID. Omitted when not requested.

<a id="response-200-option-1-extractedclaims-object"></a>

### `response.200.option-1.extractedClaims.object`

`string` · always present

The collection type. Always list.

Allowed values: `"list"`.

<a id="response-200-option-1-extractedclaims-data"></a>

### `response.200.option-1.extractedClaims.data`

`array<value>` · always present

Claims loaded on this page. A short or empty page can still have a continuation.

<a id="response-200-option-1-extractedclaims-data-object"></a>

### `response.200.option-1.extractedClaims.data.object`

`string` · always present

The resource type. Always claim.

Allowed values: `"claim"`.

<a id="response-200-option-1-extractedclaims-data-id"></a>

### `response.200.option-1.extractedClaims.data.id`

`string` · always present

The ID Augenta assigns to this statement, starting with clm\_. Use it to match a Claim in extractedClaims.data with the same Claim in an Engram's claims.data. It belongs to the Workspace or one-shot result that returned it.

<a id="response-200-option-1-extractedclaims-data-text"></a>

### `response.200.option-1.extractedClaims.data.text`

`string` · always present

The statement extracted from your source, such as Production releases require owner approval. Read this field for the Claim's content. Claims do not have labels.

<a id="response-200-option-1-extractedclaims-data-experience"></a>

### `response.200.option-1.extractedClaims.data.experience`

`string | null` · always present

The id of the Experience this Claim came from. In Workspace mode, use it with GET /v1/experiences/{id} to check processing status. Null means the source could not be identified for an older Claim.

<a id="response-200-option-1-extractedclaims-data-at"></a>

### `response.200.option-1.extractedClaims.data.at`

`string` · always present

When this statement was observed in its source, as an ISO-8601 timestamp. This is not the time you fetched the Claim.

<a id="response-200-option-1-extractedclaims-data-source"></a>

### `response.200.option-1.extractedClaims.data.source`

`object` · conditional

Additional source details, such as a conversation session or document path, when available. The fields depend on how the source was submitted. Omitted when no source details are available.

<a id="response-200-option-1-extractedclaims-nextpageurl"></a>

### `response.200.option-1.extractedClaims.nextPageUrl`

`string | null` · always present

Follow this relative URL unchanged. Null means there is no next page. One-shot output can still omit items when truncated is true.

<a id="response-200-option-1-extractedclaims-url"></a>

### `response.200.option-1.extractedClaims.url`

`string` · conditional

The collection's resource path, when available. Use nextPageUrl, rather than this path, to load the next page.

<a id="response-200-option-1-extractedclaims-truncated"></a>

### `response.200.option-1.extractedClaims.truncated`

`boolean` · conditional

True when a bounded one-shot result omitted items. One-shot results have no browsing continuation; use Workspace-backed memory when you need subsequent retrieval. False means all selected items were returned. Workspace lists use nextPageUrl instead.

<a id="response-200-option-1-extractedclaims-billing"></a>

### `response.200.option-1.extractedClaims.billing`

`object` · conditional

Present when billing is enabled. USD amount is exact. Receipt references settle only on successful server delivery; retries reuse the original debit.

<a id="response-200-option-1-extractedclaims-billing-operationid"></a>

### `response.200.option-1.extractedClaims.billing.operationId`

`string` · always present

<a id="response-200-option-1-extractedclaims-billing-priceversion"></a>

### `response.200.option-1.extractedClaims.billing.priceVersion`

`string` · always present

<a id="response-200-option-1-extractedclaims-billing-sourcetokens"></a>

### `response.200.option-1.extractedClaims.billing.sourceTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-1-extractedclaims-billing-memorytokens"></a>

### `response.200.option-1.extractedClaims.billing.memoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-1-extractedclaims-billing-measuredmemorytokens"></a>

### `response.200.option-1.extractedClaims.billing.measuredMemoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-1-extractedclaims-billing-replayed"></a>

### `response.200.option-1.extractedClaims.billing.replayed`

`boolean` · always present

<a id="response-200-option-1-extractedclaims-billing-complimentary"></a>

### `response.200.option-1.extractedClaims.billing.complimentary`

`boolean` · conditional

<a id="response-200-option-1-extractedclaims-billing-ratedamount"></a>

### `response.200.option-1.extractedClaims.billing.ratedAmount`

`string` · conditional

<a id="response-200-option-1-extractedclaims-billing-amount"></a>

### `response.200.option-1.extractedClaims.billing.amount`

`string` · always present

<a id="response-200-option-1-extractedclaims-billing-receiptids"></a>

### `response.200.option-1.extractedClaims.billing.receiptIds`

`array<string>` · always present

<a id="response-200-option-1-extractedclaimscomplete"></a>

### `response.200.option-1.extractedClaimsComplete`

`boolean` · conditional

Whether extraction coverage could be verified for the selected source material. This is not page completion: check extractedClaims.truncated for omitted output. Omitted when extractedClaims is not requested.

<a id="response-200-option-1-engrams"></a>

### `response.200.option-1.engrams`

`object` · always present

<a id="response-200-option-1-engrams-object"></a>

### `response.200.option-1.engrams.object`

`string` · always present

Allowed values: `"list"`.

<a id="response-200-option-1-engrams-data"></a>

### `response.200.option-1.engrams.data`

`array<value>` · always present

<a id="response-200-option-1-engrams-data-object"></a>

### `response.200.option-1.engrams.data.object`

`string` · always present

The resource type. Always engram. Use this field to recognize Engram objects in API results.

Allowed values: `"engram"`.

<a id="response-200-option-1-engrams-data-id"></a>

### `response.200.option-1.engrams.data.id`

`string` · always present

The ID Augenta assigns to this Engram, starting with `eng_`. In a Workspace, put this value in `GET /v1/engrams/{id}` to retrieve it. A one-shot Engram exists only in that result and has no standalone lookup URL. See [Engram IDs](https://augenta.pages.dev/docs/engrams.md#engram-ids) for examples and how IDs behave as memory changes.

<a id="response-200-option-1-engrams-data-summary"></a>

### `response.200.option-1.engrams.data.summary`

`string | null` · conditional

A readable summary of the Claims grouped in this Engram. Use it to display what the Engram is about. It can change as Claims or summary text change. Null when no summary is available; omitted when summaries:false is requested.

<a id="response-200-option-1-engrams-data-label"></a>

### `response.200.option-1.engrams.data.label`

`string | null` · conditional

A short topic label, such as releases · rollback, for display in lists. Augenta chooses terms that distinguish this Engram from others in the same Workspace or one-shot result. An empty string means no terms qualified; null means a label is unavailable. Omitted with summaries:false.

<a id="response-200-option-1-engrams-data-labelsupport"></a>

### `response.200.option-1.engrams.data.labelSupport`

`number | null` · conditional

How widely the label's terms appear in this Engram's Claims. For each term, Augenta calculates the share of Claims containing it, then averages those shares. Ranges from 0 to 1: at 1, every label term appears in every Claim. It is not confidence in the label's accuracy. Null when unavailable; omitted with summaries:false.

Minimum: `0`. Maximum: `1`.

<a id="response-200-option-1-engrams-data-memoryclass"></a>

### `response.200.option-1.engrams.data.memoryClass`

`string | null` · always present

The kind of content Augenta identified. Common values are `semantic` for facts, `episodic` for past events, `procedural` for how-to knowledge and `prospective` for commitments or future tasks. This does not select one-shot or Workspace mode. Null when unavailable.

<a id="response-200-option-1-engrams-data-status"></a>

### `response.200.option-1.engrams.data.status`

`string | null` · always present

The Engram's recorded state. `weakened` means its strength fell below half its recorded peak; it can return to `active` when its strength recovers. This describes retained memory, not Experience processing progress. Null when unavailable.

Allowed values: `"active"`, `"weakened"`, `null`.

<a id="response-200-option-1-engrams-data-strength"></a>

### `response.200.option-1.engrams.data.strength`

`number | null` · always present

A score describing the structural support for this Engram's group of Claims. Larger values indicate a stronger grouping under the memory process's scoring rules; this is not a probability or a measure of factual correctness. One-shot scores describe its last rebuild; Workspace scores come from its persisted memory history. Compare within the same memory, not across modes. Null when unavailable.

<a id="response-200-option-1-engrams-data-heatshare"></a>

### `response.200.option-1.engrams.data.heatShare`

`number | null` · always present

A relative activity measure: this Engram's share of the memory's recorded activity signal, called heat. Ranges from 0 to 1; 0.25 means one quarter of that memory's heat at the last evaluation. Workspace heat reflects incoming Claims and recorded recall activity; one-shot heat has no recorded recall activity. This is not confidence or billing usage. Null when unavailable.

Minimum: `0`. Maximum: `1`.

<a id="response-200-option-1-engrams-data-claimcount"></a>

### `response.200.option-1.engrams.data.claimCount`

`integer` · always present

The total number of Claims currently in this Engram. Use it to show the size of the group. It can exceed claims.data.length because only one page may be loaded; Claims that have left the Engram are excluded.

Minimum: `0`.

<a id="response-200-option-1-engrams-data-claimtokencount"></a>

### `response.200.option-1.engrams.data.claimTokenCount`

`integer | null` · always present

The total number of text tokens in this Engram's current Claims, excluding its summary. It describes content size, not tokens billed for a request or the size of your eventual model prompt. Null when unavailable.

Minimum: `0`.

<a id="response-200-option-1-engrams-data-bornat"></a>

### `response.200.option-1.engrams.data.bornAt`

`string | null` · always present

When this Engram ID was first published, as an ISO-8601 timestamp. It is not the date of the oldest source Claim. Null when the publication time is unknown for older memory.

<a id="response-200-option-1-engrams-data-updatedat"></a>

### `response.200.option-1.engrams.data.updatedAt`

`string | null` · always present

When the Engram's Claim membership or summary text last changed, as an ISO-8601 timestamp. A summary written after consolidation can advance it. Reads and changes only to scores, status or labels do not. It is not a version for the entire object. Null when the content-change time is unknown.

<a id="response-200-option-1-engrams-data-claims"></a>

### `response.200.option-1.engrams.data.claims`

`object` · conditional

A page of Claims currently in this Engram. Read claims.data for the statements and follow claims.nextPageUrl for more. Workspace detail and completed-memory results load an initial page by default; list requests need include=claims. An omitted field means Claims were not loaded, not that the Engram is empty.

<a id="response-200-option-1-engrams-data-claims-object"></a>

### `response.200.option-1.engrams.data.claims.object`

`string` · always present

The collection type. Always list.

Allowed values: `"list"`.

<a id="response-200-option-1-engrams-data-claims-data"></a>

### `response.200.option-1.engrams.data.claims.data`

`array<value>` · always present

Claims loaded on this page. A short or empty page can still have a continuation.

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="response-200-option-1-engrams-data-claims-nextpageurl"></a>

### `response.200.option-1.engrams.data.claims.nextPageUrl`

`string | null` · always present

Follow this relative URL unchanged. Null means there is no next page. One-shot output can still omit items when truncated is true.

<a id="response-200-option-1-engrams-data-claims-url"></a>

### `response.200.option-1.engrams.data.claims.url`

`string` · conditional

The collection's resource path, when available. Use nextPageUrl, rather than this path, to load the next page.

<a id="response-200-option-1-engrams-data-claims-truncated"></a>

### `response.200.option-1.engrams.data.claims.truncated`

`boolean` · conditional

True when a bounded one-shot result omitted items. One-shot results have no browsing continuation; use Workspace-backed memory when you need subsequent retrieval. False means all selected items were returned. Workspace lists use nextPageUrl instead.

<a id="response-200-option-1-engrams-data-claims-billing"></a>

### `response.200.option-1.engrams.data.claims.billing`

`object` · conditional

Present when billing is enabled. USD amount is exact. Receipt references settle only on successful server delivery; retries reuse the original debit.

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="response-200-option-1-engrams-nextpageurl"></a>

### `response.200.option-1.engrams.nextPageUrl`

`string | null` · always present

<a id="response-200-option-1-engrams-url"></a>

### `response.200.option-1.engrams.url`

`string` · conditional

<a id="response-200-option-1-engrams-truncated"></a>

### `response.200.option-1.engrams.truncated`

`boolean` · conditional

True when a bounded one-shot result omitted items. One-shot results have no browsing continuation; use Workspace-backed memory when you need subsequent retrieval. False means all selected items were returned. Workspace lists use nextPageUrl instead.

<a id="response-200-option-1-engrams-billing"></a>

### `response.200.option-1.engrams.billing`

`object` · conditional

Present when billing is enabled. USD amount is exact. Receipt references settle only on successful server delivery; retries reuse the original debit.

<a id="response-200-option-1-engrams-billing-operationid"></a>

### `response.200.option-1.engrams.billing.operationId`

`string` · always present

<a id="response-200-option-1-engrams-billing-priceversion"></a>

### `response.200.option-1.engrams.billing.priceVersion`

`string` · always present

<a id="response-200-option-1-engrams-billing-sourcetokens"></a>

### `response.200.option-1.engrams.billing.sourceTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-1-engrams-billing-memorytokens"></a>

### `response.200.option-1.engrams.billing.memoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-1-engrams-billing-measuredmemorytokens"></a>

### `response.200.option-1.engrams.billing.measuredMemoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-1-engrams-billing-replayed"></a>

### `response.200.option-1.engrams.billing.replayed`

`boolean` · always present

<a id="response-200-option-1-engrams-billing-complimentary"></a>

### `response.200.option-1.engrams.billing.complimentary`

`boolean` · conditional

<a id="response-200-option-1-engrams-billing-ratedamount"></a>

### `response.200.option-1.engrams.billing.ratedAmount`

`string` · conditional

<a id="response-200-option-1-engrams-billing-amount"></a>

### `response.200.option-1.engrams.billing.amount`

`string` · always present

<a id="response-200-option-1-engrams-billing-receiptids"></a>

### `response.200.option-1.engrams.billing.receiptIds`

`array<string>` · always present

<a id="response-200-option-1-events"></a>

### `response.200.option-1.events`

`array<value>` · always present

<a id="response-200-option-1-events-object"></a>

### `response.200.option-1.events.object`

`string` · always present

The resource type. Always event.

Allowed values: `"event"`.

<a id="response-200-option-1-events-id"></a>

### `response.200.option-1.events.id`

`string` · always present

The ID of this recorded Event, starting with evt\_. Use it with GET /v1/events/{id} in the same Workspace. Read data.object.id for the affected Engram's eng\_ ID. Snapshot Events are returned inline and have no stored lookup URL.

<a id="response-200-option-1-events-type"></a>

### `response.200.option-1.events.type`

`string` · always present

What happened: an Engram was created, changed membership, split, merged or retired. These Events do not report every score or summary update.

Allowed values: `"engram.created"`, `"engram.changed"`, `"engram.split"`, `"engram.merged"`, `"engram.retired"`.

<a id="response-200-option-1-events-created"></a>

### `response.200.option-1.events.created`

`integer` · always present

Recorded event time as Unix seconds. Workspace event feeds follow committed order even when source clocks go backward; one-shot events describe the completed rebuild.

<a id="response-200-option-1-events-data"></a>

### `response.200.option-1.events.data`

`object` · always present

The recorded identity-lineage payload. Completed memory results return the same Event resource in events. This is not a historical Engram snapshot or a complete score/prose audit.

<a id="response-200-option-1-events-data-object"></a>

### `response.200.option-1.events.data.object`

`object` · always present

<a id="response-200-option-1-events-data-object-object"></a>

### `response.200.option-1.events.data.object.object`

`string` · always present

The recorded payload type. Always engram_change.

Allowed values: `"engram_change"`.

<a id="response-200-option-1-events-data-object-kind"></a>

### `response.200.option-1.events.data.object.kind`

`string` · always present

What happened to the affected Engram's identity or Claim membership. The enclosing Event exposes the corresponding dotted type, such as engram.created for born.

Allowed values: `"born"`, `"update"`, `"split"`, `"merge"`, `"retire"`.

<a id="response-200-option-1-events-data-object-id"></a>

### `response.200.option-1.events.data.object.id`

`string` · always present

The ID of the Engram affected by this transition. This is an eng\_ ID, not the Event's evt\_ ID. The Engram may have been retired since this Event was recorded.

<a id="response-200-option-1-events-data-object-claimcountbefore"></a>

### `response.200.option-1.events.data.object.claimCountBefore`

`integer` · always present

The affected Engram's total current Claims immediately before this transition. Zero for a new Engram.

Minimum: `0`.

<a id="response-200-option-1-events-data-object-claimcountafter"></a>

### `response.200.option-1.events.data.object.claimCountAfter`

`integer` · always present

The affected Engram's total current Claims immediately after this transition. Zero when the identity is retired.

Minimum: `0`.

<a id="response-200-option-1-events-data-object-into"></a>

### `response.200.option-1.events.data.object.into`

`array<string>` · always present

New Engram IDs created by a split. Empty for other transition kinds.

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="response-200-option-1-events-data-object-absorbed"></a>

### `response.200.option-1.events.data.object.absorbed`

`array<string>` · always present

Engram IDs merged into this surviving Engram and retired. Empty for other transition kinds.

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="response-200-option-1-events-data-object-at"></a>

### `response.200.option-1.events.data.object.at`

`string` · always present

When this transition was recorded, as an ISO-8601 timestamp. The enclosing Event's created field represents the same time in Unix seconds.

<a id="response-200-option-1-usage"></a>

### `response.200.option-1.usage`

`object` · always present

<a id="response-200-option-1-usage-tokenssent"></a>

### `response.200.option-1.usage.tokensSent`

`integer` · always present

<a id="response-200-option-1-usage-tokenssentsource"></a>

### `response.200.option-1.usage.tokensSentSource`

`string` · conditional

<a id="response-200-option-1-usage-modelinputtokens"></a>

### `response.200.option-1.usage.modelInputTokens`

`integer` · conditional

<a id="response-200-option-1-usage-modeloutputtokens"></a>

### `response.200.option-1.usage.modelOutputTokens`

`integer` · conditional

<a id="response-200-option-1-timing"></a>

### `response.200.option-1.timing`

`object` · always present

<a id="response-200-option-1-timing-firstclaimms"></a>

### `response.200.option-1.timing.firstClaimMs`

`number | null` · always present

<a id="response-200-option-1-timing-firstengramms"></a>

### `response.200.option-1.timing.firstEngramMs`

`number | null` · always present

<a id="response-200-option-1-timing-totalms"></a>

### `response.200.option-1.timing.totalMs`

`number` · always present

**Option 2**

<a id="response-200-option-2-billing"></a>

### `response.200.option-2.billing`

`object` · conditional

Present when billing is enabled. USD amount is exact. Receipt references settle only on successful server delivery; retries reuse the original debit.

<a id="response-200-option-2-billing-operationid"></a>

### `response.200.option-2.billing.operationId`

`string` · always present

<a id="response-200-option-2-billing-priceversion"></a>

### `response.200.option-2.billing.priceVersion`

`string` · always present

<a id="response-200-option-2-billing-sourcetokens"></a>

### `response.200.option-2.billing.sourceTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-2-billing-memorytokens"></a>

### `response.200.option-2.billing.memoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-2-billing-measuredmemorytokens"></a>

### `response.200.option-2.billing.measuredMemoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-2-billing-replayed"></a>

### `response.200.option-2.billing.replayed`

`boolean` · always present

<a id="response-200-option-2-billing-complimentary"></a>

### `response.200.option-2.billing.complimentary`

`boolean` · conditional

<a id="response-200-option-2-billing-ratedamount"></a>

### `response.200.option-2.billing.ratedAmount`

`string` · conditional

<a id="response-200-option-2-billing-amount"></a>

### `response.200.option-2.billing.amount`

`string` · always present

<a id="response-200-option-2-billing-receiptids"></a>

### `response.200.option-2.billing.receiptIds`

`array<string>` · always present

<a id="response-200-option-2-workspace"></a>

### `response.200.option-2.workspace`

`string` · always present

<a id="response-200-option-2-operation"></a>

### `response.200.option-2.operation`

`string` · always present

<a id="response-200-option-2-experiences"></a>

### `response.200.option-2.experiences`

`array<value>` · always present

<a id="response-200-option-2-experiences-object"></a>

### `response.200.option-2.experiences.object`

`string` · always present

The resource type. Always experience.

Allowed values: `"experience"`.

<a id="response-200-option-2-experiences-id"></a>

### `response.200.option-2.experiences.id`

`string` · always present

The ID Augenta assigns to this submitted source. In Workspace mode, use it with GET /v1/experiences/{id} to check processing status. One-shot source references have no stored status URL.

<a id="response-200-option-2-experiences-status"></a>

### `response.200.option-2.experiences.status`

`string` · always present

Allowed values: `"processed"`, `"superseded"`.

<a id="response-200-option-2-experiences-billingoperationid"></a>

### `response.200.option-2.experiences.billingOperationId`

`string` · conditional

Reference to this source's billing operation, when billing is enabled.

<a id="response-200-option-2-experiences-claimids"></a>

### `response.200.option-2.experiences.claimIds`

`array<string>` · conditional

IDs of Claims extracted from this source, when returned. Read extractedClaims.data or an Engram's claims.data for their text.

<a id="response-200-option-2-extractedclaims"></a>

### `response.200.option-2.extractedClaims`

`object` · conditional

A page of Claims from this call's source material, including Claims that did not form an Engram. A Claim can also appear in an Engram's claims.data with the same ID. Omitted when not requested.

<a id="response-200-option-2-extractedclaims-object"></a>

### `response.200.option-2.extractedClaims.object`

`string` · always present

The collection type. Always list.

Allowed values: `"list"`.

<a id="response-200-option-2-extractedclaims-data"></a>

### `response.200.option-2.extractedClaims.data`

`array<value>` · always present

Claims loaded on this page. A short or empty page can still have a continuation.

<a id="response-200-option-2-extractedclaims-data-object"></a>

### `response.200.option-2.extractedClaims.data.object`

`string` · always present

The resource type. Always claim.

Allowed values: `"claim"`.

<a id="response-200-option-2-extractedclaims-data-id"></a>

### `response.200.option-2.extractedClaims.data.id`

`string` · always present

The ID Augenta assigns to this statement, starting with clm\_. Use it to match a Claim in extractedClaims.data with the same Claim in an Engram's claims.data. It belongs to the Workspace or one-shot result that returned it.

<a id="response-200-option-2-extractedclaims-data-text"></a>

### `response.200.option-2.extractedClaims.data.text`

`string` · always present

The statement extracted from your source, such as Production releases require owner approval. Read this field for the Claim's content. Claims do not have labels.

<a id="response-200-option-2-extractedclaims-data-experience"></a>

### `response.200.option-2.extractedClaims.data.experience`

`string | null` · always present

The id of the Experience this Claim came from. In Workspace mode, use it with GET /v1/experiences/{id} to check processing status. Null means the source could not be identified for an older Claim.

<a id="response-200-option-2-extractedclaims-data-at"></a>

### `response.200.option-2.extractedClaims.data.at`

`string` · always present

When this statement was observed in its source, as an ISO-8601 timestamp. This is not the time you fetched the Claim.

<a id="response-200-option-2-extractedclaims-data-source"></a>

### `response.200.option-2.extractedClaims.data.source`

`object` · conditional

Additional source details, such as a conversation session or document path, when available. The fields depend on how the source was submitted. Omitted when no source details are available.

<a id="response-200-option-2-extractedclaims-nextpageurl"></a>

### `response.200.option-2.extractedClaims.nextPageUrl`

`string | null` · always present

Follow this relative URL unchanged. Null means there is no next page. One-shot output can still omit items when truncated is true.

<a id="response-200-option-2-extractedclaims-url"></a>

### `response.200.option-2.extractedClaims.url`

`string` · conditional

The collection's resource path, when available. Use nextPageUrl, rather than this path, to load the next page.

<a id="response-200-option-2-extractedclaims-truncated"></a>

### `response.200.option-2.extractedClaims.truncated`

`boolean` · conditional

True when a bounded one-shot result omitted items. One-shot results have no browsing continuation; use Workspace-backed memory when you need subsequent retrieval. False means all selected items were returned. Workspace lists use nextPageUrl instead.

<a id="response-200-option-2-extractedclaims-billing"></a>

### `response.200.option-2.extractedClaims.billing`

`object` · conditional

Present when billing is enabled. USD amount is exact. Receipt references settle only on successful server delivery; retries reuse the original debit.

<a id="response-200-option-2-extractedclaims-billing-operationid"></a>

### `response.200.option-2.extractedClaims.billing.operationId`

`string` · always present

<a id="response-200-option-2-extractedclaims-billing-priceversion"></a>

### `response.200.option-2.extractedClaims.billing.priceVersion`

`string` · always present

<a id="response-200-option-2-extractedclaims-billing-sourcetokens"></a>

### `response.200.option-2.extractedClaims.billing.sourceTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-2-extractedclaims-billing-memorytokens"></a>

### `response.200.option-2.extractedClaims.billing.memoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-2-extractedclaims-billing-measuredmemorytokens"></a>

### `response.200.option-2.extractedClaims.billing.measuredMemoryTokens`

`integer` · always present

Minimum: `0`.

<a id="response-200-option-2-extractedclaims-billing-replayed"></a>

### `response.200.option-2.extractedClaims.billing.replayed`

`boolean` · always present

<a id="response-200-option-2-extractedclaims-billing-complimentary"></a>

### `response.200.option-2.extractedClaims.billing.complimentary`

`boolean` · conditional

<a id="response-200-option-2-extractedclaims-billing-ratedamount"></a>

### `response.200.option-2.extractedClaims.billing.ratedAmount`

`string` · conditional

<a id="response-200-option-2-extractedclaims-billing-amount"></a>

### `response.200.option-2.extractedClaims.billing.amount`

`string` · always present

<a id="response-200-option-2-extractedclaims-billing-receiptids"></a>

### `response.200.option-2.extractedClaims.billing.receiptIds`

`array<string>` · always present

<a id="response-200-option-2-extractedclaimscomplete"></a>

### `response.200.option-2.extractedClaimsComplete`

`boolean` · conditional

<a id="response-200-option-2-usage"></a>

### `response.200.option-2.usage`

`object` · always present

<a id="response-200-option-2-usage-tokenssent"></a>

### `response.200.option-2.usage.tokensSent`

`integer | null` · always present

<a id="response-200-option-2-usage-tokenssentsource"></a>

### `response.200.option-2.usage.tokensSentSource`

`string | null` · always present

<a id="response-200-option-2-usage-modelinputtokens"></a>

### `response.200.option-2.usage.modelInputTokens`

`integer | null` · always present

<a id="response-200-option-2-usage-modeloutputtokens"></a>

### `response.200.option-2.usage.modelOutputTokens`

`integer | null` · always present

<a id="response-200-option-2-context"></a>

### `response.200.option-2.context`

`object` · always present

<a id="response-200-option-2-context-memory"></a>

### `response.200.option-2.context.memory`

`array<value>` · always present

<a id="response-200-option-2-context-messages"></a>

### `response.200.option-2.context.messages`

`array<value>` · always present

<a id="response-200-option-2-context-messages-role"></a>

### `response.200.option-2.context.messages.role`

`string` · always present

Allowed values: `"system"`, `"developer"`, `"user"`, `"assistant"`, `"tool"`.

<a id="response-200-option-2-context-messages-content"></a>

### `response.200.option-2.context.messages.content`

`choice` · always present

**Option 1**

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

**Option 2**

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

**Option 3**

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="response-200-option-2-context-messages-tool_calls"></a>

### `response.200.option-2.context.messages.tool_calls`

`array<object>` · conditional

See the [OpenAPI specification](https://augenta.pages.dev/docs/openapi.json) for deeper fields.

<a id="response-200-option-2-context-messages-tool_call_id"></a>

### `response.200.option-2.context.messages.tool_call_id`

`string` · conditional

<a id="response-200-option-2-context-messages-name"></a>

### `response.200.option-2.context.messages.name`

`string` · conditional

<a id="response-200-option-2-context-messages-ts"></a>

### `response.200.option-2.context.messages.ts`

`string` · conditional

<a id="response-200-option-2-context-messages-seq"></a>

### `response.200.option-2.context.messages.seq`

`integer` · conditional

Minimum: `0`.

<a id="response-200-option-2-context-budget_tokens"></a>

### `response.200.option-2.context.budget_tokens`

`integer` · always present

<a id="response-200-option-2-context-tokensestimated"></a>

### `response.200.option-2.context.tokensEstimated`

`integer` · always present

<a id="response-200-option-2-context-tokenestimatesource"></a>

### `response.200.option-2.context.tokenEstimateSource`

`string` · always present

Allowed values: `"estimate:utf8-bytes/3.5"`.

<a id="response-200-option-2-context-memorytruncated"></a>

### `response.200.option-2.context.memoryTruncated`

`boolean` · always present

<a id="response-200-option-2-recall"></a>

### `response.200.option-2.recall`

`object` · conditional

<a id="response-200-option-2-timing"></a>

### `response.200.option-2.timing`

`object` · always present

<a id="response-200-option-2-timing-firstclaimms"></a>

### `response.200.option-2.timing.firstClaimMs`

`number | null` · always present

<a id="response-200-option-2-timing-firstengramms"></a>

### `response.200.option-2.timing.firstEngramMs`

`number | null` · always present

<a id="response-200-option-2-timing-totalms"></a>

### `response.200.option-2.timing.totalMs`

`number` · always present

Content-Type: `text/event-stream`
SSE events: accepted (Workspace), progress, claims, engrams, reset (observation gap), completed, error. JSON data payloads. Each provisional engrams event replaces the previous preview; previews are provisional.

## Response 400

invalid_request: malformed input, changed immutable ranges, unsupported native media/tool pairing, a Workspace call's recent group exceeds its budget, query/keep_recent/budget_tokens sent without workspace, summaries sent with a Workspace, or unsupported state/snapshot fields.

Content-Type: `application/json`

<a id="response-400-error"></a>

### `response.400.error`

`object` · always present

<a id="response-400-error-code"></a>

### `response.400.error.code`

`string` · always present

Stable. The Errors page lists every code.

<a id="response-400-error-message"></a>

### `response.400.error.message`

`string` · always present

Human-readable. May change; don't parse it.

<a id="response-400-error-retryable"></a>

### `response.400.error.retryable`

`boolean` · always present

<a id="response-400-error-retryafterseconds"></a>

### `response.400.error.retryAfterSeconds`

`integer` · conditional

Capacity retry interval, also present as Retry-After before stream headers commit. SSE error events retain this field after HTTP 200 is committed.

Minimum: `1`.

<a id="response-400-error-billingurl"></a>

### `response.400.error.billingUrl`

`string` · conditional

Top-up action when error.code is insufficient_balance (HTTP 402).

<a id="response-400-requestid"></a>

### `response.400.requestId`

`string` · always present

The request's id, as in the `X-Request-Id` response header.

## Response 401

unauthenticated: invalid or missing credential.

Content-Type: `application/json`

Response fields use the same schema as Response 400.

## Response 402

insufficient_balance: add credits and explicitly retry with the same Idempotency-Key. Streaming errors retain status 402.

Content-Type: `application/json`

Response fields use the same schema as Response 400.

## Response 403

forbidden or connector_inactive: credential cannot use the inbound Connector.

Content-Type: `application/json`

Response fields use the same schema as Response 400.

## Response 409

cursor_stale: Workspace memory changed repeatedly during the final read.

Content-Type: `application/json`

Response fields use the same schema as Response 400.

## Response 413

payload_too_large, experiences_too_large: configured input or computation output limit exceeded.

Content-Type: `application/json`

Response fields use the same schema as Response 400.

## Response 429

at_capacity (retryable): the deployment is full, or every model provider stayed throttled through the model calls' retries; send the same request after the number of seconds in Retry-After. A stream that already answered 200 ends with an error event carrying error.retryAfterSeconds instead. rate_limited (retryable): your own rate limit.

Content-Type: `application/json`

Response fields use the same schema as Response 400.

## Response 501

stateless_not_available: computation is not configured.

Content-Type: `application/json`

Response fields use the same schema as Response 400.

## Response 502

cognition_failed or cognition_unavailable: processing failed.

Content-Type: `application/json`

Response fields use the same schema as Response 400.

## Response 503

service_unconfigured, cognition_unconfigured or service_unavailable: managed processing is unavailable.

Content-Type: `application/json`

Response fields use the same schema as Response 400.

## Response 504

recall_timeout: a processing or Workspace recall deadline was exceeded. operation_timeout: a JSON call ran past its synchronous deadline (90 s by default); send it with stream: true.

Content-Type: `application/json`

Response fields use the same schema as Response 400.
