> ## Documentation Index > Fetch the complete documentation index at: https://docs.revring.ai/llms.txt > Use this file to discover all available pages before exploring further. # Re-run Analysis > Re-run extraction, evaluation and caller sentiment on one ended call with the agent's current settings. A field or criterion removed from the agent is cleared on the call. ## OpenAPI ````yaml POST /calls/{id}/reanalyze openapi: 3.1.0 info: title: RevRing Voice AI API description: >- RevRing Voice AI platform API for managing AI voice agents, phone calls, SIP trunks, and analytics. Build intelligent voice applications that can handle inbound and outbound phone calls with AI-powered conversational agents. version: 1.0.0 contact: name: RevRing Support url: https://revring.ai servers: - url: https://api.revring.ai/v1 description: Production API security: - apiKeyAuth: [] tags: - name: Messaging Connections description: Connect messaging providers so agents can send text messages - name: Messages description: Send text messages and read your message log - name: Conversations description: List and clear managed conversation threads - name: SIP Trunks description: Manage SIP trunks for connecting agents to the phone network - name: Agents description: Manage AI voice agents and their configuration - name: Agent Folders description: Organize agents into folders for dashboard navigation - name: Calls description: Manage and query phone calls - name: Analytics description: Get analytics and metrics about your calls - name: Knowledge Bases description: >- Manage knowledge bases and sources for agent retrieval-augmented generation - name: Test Suites description: Manage test suites, test cases, and test runs for agent evaluation - name: Voices description: Browse the voices available to your organization for agent speech - name: Webhooks description: Webhook delivery settings for your organization paths: /calls/{id}/reanalyze: post: tags: - Calls summary: Re-run Analysis description: >- Re-run extraction, evaluation and caller sentiment on one ended call with the agent's current settings. A field or criterion removed from the agent is cleared on the call. operationId: reanalyzeCall requestBody: required: false content: application/json: schema: type: object properties: resendWebhook: type: boolean default: false description: Deliver the post-call webhook again with the new results responses: '200': description: The updated call content: application/json: schema: type: object properties: data: $ref: '#/components/schemas/Call' '404': description: not_found content: application/json: schema: type: object properties: error: type: string message: type: string '409': description: content_deleted, nothing_to_analyze or not_ended content: application/json: schema: type: object properties: error: type: string message: type: string components: schemas: Call: type: object description: Phone call record properties: id: type: string format: uuid organizationId: type: string format: uuid agentId: type: string format: uuid nullable: true sipTrunkId: type: string format: uuid nullable: true direction: type: string enum: - INBOUND - OUTBOUND description: Call direction status: type: string enum: - QUEUED - INITIATED - ONGOING - TRANSFERRED - COMPLETED - FAILED - CANCELED description: Current call status fromNumber: type: string description: >- Caller's number (E.164). `anonymous` when the caller withheld their caller ID on an inbound call. For web widget calls, the visitor's anonymous ID in the form visitor:. toNumber: type: string description: Called number (E.164). For web widget calls, the agent ID. source: type: string nullable: true enum: - web_widget - null description: >- How the call originated. web_widget for calls started from the Web Widget call button; null for phone calls. continuedFromCallId: type: string nullable: true description: >- When a dropped web widget call was silently re-dialed, the id of the call this one continues; null otherwise. agentCallerIdName: type: string nullable: true description: Caller ID name shown to recipient agentName: type: string nullable: true description: Name of the agent that handled this call variables: type: object nullable: true description: Template variables used recordingUrl: type: string nullable: true description: URL to call recording (available after call ends) recordingOffsetSeconds: type: number nullable: true description: >- Seconds between the transcript clock's zero and the recording's first audio. Add transcript timestamps to this value to align them with recording playback. Available after the call ends; null on older calls. hangupCause: type: string nullable: true description: >- Reason call ended. Common values: USER_ENDED, END_CALL_TOOL, SILENCE_TIMEOUT, MAX_DURATION, VOICEMAIL_DETECTED errorMessage: type: string nullable: true description: Error message if call failed transcript: type: array nullable: true description: Conversation transcript items: type: object summary: type: string nullable: true description: AI-generated summary extraction: type: object nullable: true additionalProperties: nullable: true oneOf: - type: string - type: number - type: boolean description: >- Structured fields extracted after the call, keyed by the field names in the agent's postCallExtraction config. A field that was not stated on the call is null. null when the agent has no extraction configured or the call had no caller speech example: callback_requested: true preferred_day: Tuesday budget: 450000 evaluation: type: object nullable: true additionalProperties: type: object properties: result: type: string enum: - pass - fail - unknown rationale: type: string description: One sentence citing what in the call decided the result required: - result - rationale description: >- Per-criterion verdicts after the call, keyed by the criterion names in the agent's postCallEvaluation config. unknown means the transcript did not settle it. null when the agent has no evaluation configured or the call had no caller speech example: appointment_confirmed: result: pass rationale: The caller agreed to Tuesday at 10am and the agent confirmed it. callback_requested: result: unknown rationale: A callback was never discussed. agentRevision: type: integer nullable: true description: >- Agent version the call ran on. null for agents in auto publish mode (the agent as saved) and for calls made before publishing existed environment: type: string nullable: true description: Agent environment the call ran in; null means production campaignId: type: string nullable: true description: Campaign that placed the call; null otherwise metrics: type: object nullable: true description: >- Usage measured during the call. Present once the call has ended; counters that do not apply are 0. properties: llm_prompt_tokens: type: number description: Language model input tokens across all turns llm_prompt_cached_tokens: type: number description: >- Input tokens served from the prompt cache (included in llm_prompt_tokens) llm_completion_tokens: type: number description: Language model output tokens across all turns stt_audio_duration: type: number description: Seconds of caller audio transcribed tts_audio_duration: type: number description: Seconds of agent speech synthesized tts_characters_count: type: number description: Characters of agent speech synthesized additionalProperties: type: number piiRedacted: type: boolean description: >- True when personal details were removed from the transcript and summary (agent `storageMode: redact_pii`). initiatedAt: type: string format: date-time description: When call was initiated startedAt: type: string format: date-time nullable: true description: When call was answered (null if never answered) endedAt: type: string format: date-time nullable: true description: When call ended (null if still ongoing) durationSeconds: type: integer nullable: true description: Call duration in seconds (null if never answered) llmModel: type: string nullable: true enum: - revring-standard - revring-max - revring-ultra - null description: >- Language model tier the call ran on, fixed at call start. null for calls placed before model tiers existed (billed at the standard rate). voiceId: type: string nullable: true description: >- Voice the call ran, fixed at call start: the per-call override if one was sent, otherwise the agent's voice at the time. null for calls placed before this was recorded. voiceTier: type: string nullable: true enum: - standard - studio - null description: >- Tier of the voice the call ran on, fixed at call start. 'studio' calls are billed an additional 2 cents per minute. null for calls placed before voice tiers existed (billed at the regular rate). postCallWebhookStatus: type: string nullable: true enum: - sent - retrying - failed - skipped description: >- Post-call webhook delivery: sent | retrying (another attempt is scheduled) | failed (after the last retry) | skipped (no webhook URL); null before delivery was attempted postCallWebhookAttempts: type: integer description: >- Delivery attempts made so far (first send plus retries at 1m, 5m, 30m) preCallWebhookStatus: type: string nullable: true enum: - sent - failed - skipped - null description: Status of pre-call webhook delivery createdAt: type: string format: date-time updatedAt: type: string format: date-time sentiment: type: string nullable: true enum: - positive - neutral - negative - unknown - null description: >- How the caller felt over the call; null when there was no caller speech. required: - id - organizationId - direction - status - fromNumber - toNumber - initiatedAt - createdAt - updatedAt securitySchemes: apiKeyAuth: type: apiKey in: header name: x-api-key description: >- API key for authentication. Generate API keys from the RevRing dashboard. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.