Two modes
Switch between them with Metadata only in the same panel. The switch takes effect on the next
request. Choose metadata only when you need attribution and volume rather than content, or when
full bodies would be a large share of your SIEM ingest.
What a metadata record looks like
One object per exchange. This is a Claude Code turn that ended in a tool call:timestamp,exchange_id: when the exchange completed, and the id in the object key.client_id: the engineer the key is attributed to.harness,surfaceanduser_agentsay which tool sent the request, read from the request itself.request_id: Valar’s id for the request, the one to quote to support.session_id: the session id the tool sent, when it sent one (Claude Code does), so you can group a conversation.status: always200. Only exchanges whose response reached the client are exported, so a failed request never produces a record. A stream that was cut after it started still reads200, withstop_reasonnull.latency_ms: from Valar starting the response to its last byte.request: the model the client asked for and the request’s shape.messagesandtoolsare counts,bytesis the size of the body as sent. The messages, system prompt, tool definitions and metadata block themselves are not exported.response: the model name returned to the client, the model that answered, why it stopped, the token counts, and the size of what reached the client.served_modelis present only when your organization has turned on Show serving model name in the response body in Settings; it names a model, never a provider.
What a full record looks like
Two objects per exchange that share the same key prefix. The request object carries the same attribution fields above and abody with the request exactly as the client sent it, before Valar
touched it. The response object carries the attribution, latency_ms, and a body with the
response as the client received it, limited to the standard fields of the Anthropic Messages API:
type, role, model, served_model, content, stop_reason, stop_sequence and the token
counts in usage. Inside content, each block keeps only its standard fields.
What never leaves Valar
Records are built from a fixed list of fields rather than by removing fields from what an upstream returned, so anything Valar has not explicitly allowed cannot reach your bucket, including fields a future API version adds. In particular, nothing about how the request was served is exported: no provider, no route, no cost, no internal identifiers. The upstream’s own message id is not exported; correlation usesrequest_id and the object key.
Object layout
Objects are partitioned by hour in UTC:_valar-access-check/last-check.txt is a small text object that Check access in Settings
overwrites each time you run it. It contains no request data and can be excluded from ingest with
one prefix.
Setting it up
- Create the bucket in your AWS account, in a region listed in the Settings dropdown.
- Add a bucket policy that grants
s3:PutObjecton the bucket’s objects to the writer principal shown in Settings > ValarCode > Audit export. Nothing else is needed, and nothing else should be granted. If the bucket uses a KMS key, the key policy must also allowkms:GenerateDataKeyandkms:Encryptfor the same principal. - Send the bucket name and region to your Valar contact. Valar allows each bucket on its side before the first write.
- Enter the bucket name and region, choose Metadata only if you want it, and save.
- Click Check access. Valar writes the access-check object and reports the result, which is also kept with the setting so the panel shows when the bucket was last verified.