> ## Documentation Index > Fetch the complete documentation index at: https://doc.featherhq.com/llms.txt > Use this file to discover all available pages before exploring further. # Mint a fresh test-type v2 conversation bound to an agent or team > conv_* replacement for the retired ``POST /v1/runtime/test-chat``. Mints a ``session_type="test"`` ``Conversation`` on the ``chat`` channel / ``dashboard`` surface (ADR-001 — the operator initiated it, so ``origin="outbound"``). Identity is per ``body.test_features.identity_resolution`` (default off): off binds a throwaway random ``end_user_id`` with no identity-graph call; on binds the authenticated caller's resolved ``internal:`` EndUser. The ``test`` discriminator still gates memory sync / summary generation / extraction / evaluations / knowledge-gap analysis per the resolved snapshot (``src.conversation.test_features``), so a feature-off test session remains as ephemeral as before. The dashboard "Try this …" panel then drives turns via ``POST /conversations/{id}/turns/stream`` passing the returned id. Binds to exactly one of a single Assistant (``agent_id``) or a Team (``team_id`` + optional ``team_revision_id``); the request schema enforces that XOR. Either way the bound entity is resolved + org-scoped BEFORE the conversation is created (``get_agent_for_runtime`` / ``get_team_for_org`` both raise 404 for a missing or cross-org id), so a bare test row can never bind to another org's agent/team. For a team, ``team_revision_id`` defaults to the team's ``active_revision_id`` when omitted; ``bootstrap_team_conversation`` binds the team revision. Under DD-5 the roster resolves LIVE per turn (member pin, else live active revision) — it is not pinned at bind. No first greeting: the legacy endpoint emitted none, so there is nothing to replicate here. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/conversations/test-chat openapi: 3.1.0 info: title: Feather API description: >- Unified customer experience platform API. Manages identity, conversations, memory, agents, procedures, policies, model routing, knowledge bases, integrations, and runtime execution. version: 1.87.0 servers: - url: https://api-sandbox.featherhq.com description: Sandbox - url: http://localhost:8000 description: Local dev security: [] paths: /v1/conversations/test-chat: post: tags: - conversations summary: Mint a fresh test-type v2 conversation bound to an agent or team description: >- conv_* replacement for the retired ``POST /v1/runtime/test-chat``. Mints a ``session_type="test"`` ``Conversation`` on the ``chat`` channel / ``dashboard`` surface (ADR-001 — the operator initiated it, so ``origin="outbound"``). Identity is per ``body.test_features.identity_resolution`` (default off): off binds a throwaway random ``end_user_id`` with no identity-graph call; on binds the authenticated caller's resolved ``internal:`` EndUser. The ``test`` discriminator still gates memory sync / summary generation / extraction / evaluations / knowledge-gap analysis per the resolved snapshot (``src.conversation.test_features``), so a feature-off test session remains as ephemeral as before. The dashboard "Try this …" panel then drives turns via ``POST /conversations/{id}/turns/stream`` passing the returned id. Binds to exactly one of a single Assistant (``agent_id``) or a Team (``team_id`` + optional ``team_revision_id``); the request schema enforces that XOR. Either way the bound entity is resolved + org-scoped BEFORE the conversation is created (``get_agent_for_runtime`` / ``get_team_for_org`` both raise 404 for a missing or cross-org id), so a bare test row can never bind to another org's agent/team. For a team, ``team_revision_id`` defaults to the team's ``active_revision_id`` when omitted; ``bootstrap_team_conversation`` binds the team revision. Under DD-5 the roster resolves LIVE per turn (member pin, else live active revision) — it is not pinned at bind. No first greeting: the legacy endpoint emitted none, so there is nothing to replicate here. operationId: startV2TestChat requestBody: content: application/json: schema: $ref: '#/components/schemas/TestChatStartRequest' required: true responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/TestChatStartResponse' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Authentication required content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] components: schemas: TestChatStartRequest: properties: agent_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Id assistant_revision_id: anyOf: - type: string format: uuid - type: 'null' title: Assistant Revision Id team_id: anyOf: - type: string format: uuid - type: 'null' title: Team Id team_revision_id: anyOf: - type: string format: uuid - type: 'null' title: Team Revision Id tool_input_overrides: anyOf: - additionalProperties: additionalProperties: $ref: '#/components/schemas/InputArgConfig' type: object type: object - type: 'null' title: Tool Input Overrides context_variables: anyOf: - additionalProperties: true type: object - type: 'null' title: Context Variables test_features: anyOf: - $ref: '#/components/schemas/TestSessionFeatureInput' - type: 'null' description: >- Test-session feature toggles. Omitted means all off. The resolved snapshot is echoed back as test_features on TestChatStartResponse. type: object title: TestChatStartRequest description: >- Mint a fresh ``session_type="test"`` chat session for the dashboard. The agent-detail Test chat panel uses this. Identity is controlled by ``test_features.identity_resolution`` (default off): off mints a throwaway random ``end_user_id`` with NO identity-graph call, so dev-side Neo4j churn (wipes, merges, deletes) can never strand the panel with a stale uid; on, the session binds to the authenticated dashboard member's resolved ``internal:`` EndUser, and every "Reset" / "End session" still mints a fresh ``Conversation`` row but reuses that same identity. Mirrors ``POST /v1/voice/web-call`` for text/API. Bind to exactly one of a single Assistant (``agent_id``) or a Team (``team_id`` + optional ``team_revision_id``) — the same single-XOR-team invariant the runtime ``conversations`` table enforces. When ``team_id`` is given without ``team_revision_id``, the handler resolves the team's active revision. TestChatStartResponse: properties: session_id: type: string format: uuid title: Session Id end_user_id: type: string format: uuid title: End User Id test_features: $ref: '#/components/schemas/TestSessionFeatures' type: object required: - session_id - end_user_id - test_features title: TestChatStartResponse ErrorResponse: properties: error: type: string title: Error message: type: string title: Message retryable: anyOf: - type: boolean - type: 'null' title: Retryable retry_after: anyOf: - type: integer - type: 'null' title: Retry After type: object required: - error - message title: ErrorResponse description: Standard error response returned by all API error handlers. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError InputArgConfig: properties: value: title: Value type: $ref: '#/components/schemas/InputArgType' default: default additionalProperties: false type: object required: - value title: InputArgConfig description: >- One operator-configured input field: a ``value`` plus its enforcement ``type``. The wire/stored shape of each entry in the ``input_defaults`` map. ``type`` defaults to ``default`` so a caller can omit it for the common case. TestSessionFeatureInput: properties: identity_resolution: type: boolean title: Identity Resolution default: false memory: type: boolean title: Memory default: false summarization: type: boolean title: Summarization default: false extraction: type: boolean title: Extraction default: false evaluations: type: boolean title: Evaluations default: false knowledge_gap_analysis: type: boolean title: Knowledge Gap Analysis default: false additionalProperties: false type: object title: TestSessionFeatureInput description: Caller-supplied toggles. Unknown fields are rejected. TestSessionFeatures: properties: version: type: integer const: 1 title: Version default: 1 identity_resolution: type: boolean title: Identity Resolution memory: type: boolean title: Memory summarization: type: boolean title: Summarization extraction: type: boolean title: Extraction evaluations: type: boolean title: Evaluations knowledge_gap_analysis: type: boolean title: Knowledge Gap Analysis additionalProperties: false type: object required: - identity_resolution - memory - summarization - extraction - evaluations - knowledge_gap_analysis title: TestSessionFeatures description: Resolved, immutable snapshot persisted on a test conversation. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError InputArgType: type: string enum: - default - pinned title: InputArgType description: |- How an operator-configured input value is enforced. * ``DEFAULT`` — a suggestion the agent may overwrite. * ``PINNED`` — a forced value the caller must use and cannot overwrite. securitySchemes: APIKeyHeader: type: apiKey in: header name: x-api-key ````