> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyreach.ai/llms.txt > Use this file to discover all available pages before exploring further. # Advanced configuration > Pre/post-conversation workflows, recording locations, and noise cancellation. The agent wizard covers the common fields, but `AgentConfig` exposes top-level options that the wizard does not surface: pre- and post-conversation workflows, custom recording locations, and noise cancellation. Set them in the agent config JSON or via the API. The full, authoritative shape of every field is published as a JSON Schema. Fetch it before building requests so you always match the deployed version: ```bash theme={null} curl https://api.anyreach.ai/core/agent-config-schema \ -H "Authorization: Bearer " ``` `GET /core/agent-config-schema` returns the JSON Schema generated directly from the `AgentConfig` model, so it is the source of truth for field names, types, defaults, and enum values. ## Pre-conversation workflow `pre_conversation_workflow` runs a workflow before the agent starts. Use it to look up the caller, gate access, or seed the agent with context. The workflow can return three optional outputs: | Output | Type | Effect | | ----------------- | --------- | -------------------------------------------------------------- | | `reject` | `boolean` | Set to `true` to abort the conversation (defaults to `false`). | | `initial_context` | `string` | Context injected into the agent's system prompt. | | `custom_metadata` | `object` | Custom metadata attached to the conversation. | The field accepts a `WorkflowAction`. Reference a published workflow, or supply an inline definition: | Field | Type | Default | Description | | ------------------ | ------------ | ------------ | ----------------------------------------------------------------------------------------------------------------------- | | `type` | `"workflow"` | `"workflow"` | Action type. | | `workflow_id` | `string` | — | ID of a published workflow. Pair with `workflow_version`. | | `workflow_version` | `integer` | — | Version of the referenced workflow. | | `initial_step` | `string` | — | Step to start from. Required when using `workflow_id`/`workflow_version`; defaults to `trigger` for inline definitions. | | `definition` | `object` | — | Inline workflow definition. Mutually exclusive with `workflow_id`/`workflow_version`. | | `condition` | `string` | — | Optional condition controlling whether the action runs. | | `reject_on_error` | `boolean` | `false` | If `true`, abort the conversation when the workflow fails. | You must specify either `workflow_id` plus `workflow_version`, or an inline `definition` — not both, and not neither. When referencing a workflow, `initial_step` is required. ```json theme={null} { "pre_conversation_workflow": { "type": "workflow", "workflow_id": "wf_...", "workflow_version": 3, "initial_step": "trigger", "reject_on_error": true } } ``` `reject_on_error: true` plus a `reject` output gives you a hard gate: if the lookup fails or the workflow decides to, the conversation never starts. ## Post-conversation workflow `post_conversation_workflow` runs a workflow after the conversation ends — for logging, CRM updates, follow-up, or downstream automation. It accepts the same `WorkflowAction` shape as the pre-conversation workflow. Its outputs do not affect the (already finished) conversation, so `reject` has no effect here. ```json theme={null} { "post_conversation_workflow": { "type": "workflow", "workflow_id": "wf_...", "workflow_version": 1, "initial_step": "trigger" } } ``` Both hooks invoke standard workflows. For how an agent embeds and triggers a workflow, see [Agent-embedded triggers](/workflows/triggers/agent-embedded). ## Custom recording locations By default Anyreach stores recordings for you. Set `custom_recording_locations` to copy recordings into your own object storage instead. The field is a list (minimum one entry); each entry is discriminated by `provider`. Every provider supports `file_type`, either `ogg` (default) or `mp4`. | Field | Type | Default | Description | | ------------------- | ------------------ | ------- | ----------------------- | | `provider` | `"s3"` | `"s3"` | Provider discriminator. | | `bucket` | `string` | — | Target bucket. | | `region` | `string` | — | Bucket region. | | `access_key` | `string` | — | AWS access key ID. | | `secret_access_key` | `string` | — | AWS secret access key. | | `file_type` | `"ogg"` \| `"mp4"` | `"ogg"` | Recording file format. | ```json theme={null} { "custom_recording_locations": [ { "provider": "s3", "bucket": "my-recordings", "region": "us-east-1", "access_key": "AKIA...", "secret_access_key": "...", "file_type": "ogg" } ] } ``` | Field | Type | Default | Description | | ------------- | ------------------ | ------- | -------------------------------- | | `provider` | `"gcp"` | `"gcp"` | Provider discriminator. | | `bucket` | `string` | — | Target bucket. | | `credentials` | `string` | — | GCP service-account credentials. | | `file_type` | `"ogg"` \| `"mp4"` | `"ogg"` | Recording file format. | ```json theme={null} { "custom_recording_locations": [ { "provider": "gcp", "bucket": "my-recordings", "credentials": "...", "file_type": "mp4" } ] } ``` | Field | Type | Default | Description | | ---------------- | ------------------ | --------- | ----------------------- | | `provider` | `"azure"` | `"azure"` | Provider discriminator. | | `container_name` | `string` | — | Target container. | | `account_name` | `string` | — | Storage account name. | | `account_key` | `string` | — | Storage account key. | | `file_type` | `"ogg"` \| `"mp4"` | `"ogg"` | Recording file format. | ```json theme={null} { "custom_recording_locations": [ { "provider": "azure", "container_name": "recordings", "account_name": "myaccount", "account_key": "...", "file_type": "ogg" } ] } ``` For S3, Anyreach can mint a presigned URL to play back a recording from your bucket. GCP and Azure store the recording but do not return a playback URL. ## Noise cancellation `noise_cancellation` enables LiveKit noise-cancellation models on the audio stream. It holds a `models` list with at least one entry; each entry is discriminated by `provider` and `model.name`. | `provider` | `model.name` | When to use | | ---------- | --------------- | ---------------------------------------------------------------------------------- | | `livekit` | `bvc` | General-purpose background voice cancellation for wideband audio (web, SIP, VoIP). | | `livekit` | `bvc_telephony` | Background voice cancellation tuned for narrowband telephony (PSTN phone calls). | ```json theme={null} { "noise_cancellation": { "models": [ { "provider": "livekit", "model": { "name": "bvc_telephony" } } ] } } ``` Match the model to the channel: use `bvc_telephony` for inbound/outbound phone calls and `bvc` for web or higher-fidelity audio. ## Reference These fields live at the top level of `AgentConfig` (alongside `version`, `agent`, and `metadata`). Always validate against the live schema before sending requests. | Field | Type | Description | | ---------------------------- | ---------------------------- | --------------------------------------------------------------------------------------------------------- | | `pre_conversation_workflow` | `WorkflowAction` | Workflow run before the agent starts; can reject, inject `initial_context`, and attach `custom_metadata`. | | `post_conversation_workflow` | `WorkflowAction` | Workflow run after the conversation ends. | | `custom_recording_locations` | array of recording locations | Store recordings in your own S3, GCP, or Azure storage. | | `noise_cancellation` | object | LiveKit `bvc` / `bvc_telephony` noise-cancellation models. | Create and update agents, including these config fields, over the API. How agents invoke workflows for pre- and post-conversation hooks.