Skip to main content
GET
Get a v2 conversation with recent turns

Authorizations

x-api-key
string
header
required

Path Parameters

conversation_id
string<uuid>
required

Response

Successful Response

id
string<uuid>
required
organization_id
string<uuid>
required
end_user_id
string<uuid>
required
channel
string
required
surface
string
required
status
enum<string>
required
Available options:
queued,
ringing,
active,
paused,
waiting_for_human,
transferred,
awaiting_approval,
pending_dispatch,
closed,
expired,
error,
superseded
priority
enum<string>
required
Available options:
low,
normal,
high,
urgent
message_count
integer
required
started_at
string<date-time>
required
created_at
string<date-time>
required
updated_at
string<date-time>
required
external_session_id
string | null
session_type
enum<string>
default:live
Available options:
live,
test,
simulation
subject
string | null
assigned_agent_id
string<uuid> | null
retention_policy_id
string<uuid> | null
summary
string | null
metadata
Metadata · object
context_variables
Context Variables · object
first_message_at
string<date-time> | null
last_message_at
string<date-time> | null
ended_at
string<date-time> | null
closed_at
string<date-time> | null
ttl_expires_at
string<date-time> | null
retention_expires_at
string<date-time> | null
archived_at
string<date-time> | null
memory_sync_state
enum<string>
default:pending
Available options:
pending,
synced,
skipped,
suppressed
duration_ms
integer | null
summary_preview
string | null
has_recording
boolean
default:false
eval_summary
SessionEvalSummary · object

Rollup of eval runs that targeted a session.

succeeded = runs where status='completed' AND every score has passed=true. failed = total - succeeded - pending (failed-status runs + completed-but-not-all-passed). pending = runs still queued or running.

The critical_* counterparts restrict the same aggregation to runs whose binding was marked is_critical=True (snapshotted onto the run). They drive the session headline pill — non-critical evals still run and display but don't move the verdict. eval_status collapses the critical counts to a single headline label (none when no criticals are configured).

test_features
TestSessionFeatures · object | null

Resolved, immutable snapshot persisted on a test conversation.

revision_id
string<uuid> | null
revision_name
string | null
revision_version
integer | null
team_revision_id
string<uuid> | null
team_revision_name
string | null
from_number
string | null
to_number
string | null
email
string | null
recent_turns
TurnResponse · object[]
recording_url
string | null