Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

Post-Call CRM & Analytics Telemetry Collector for livekit/agents

Aperta
  • Qualcosa non va?
#6,664 6 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
5/5
Tempo stimato
Più di una settimana
Idoneità per principianti
25/100
Tipo di issue
Funzionalità
Chiarezza
Abbastanza chiara
Stato di attività
Tranquilla
Stack tecnologico
python
Ambito
backend-api-design

Direzione di ricerca

Start by reading the proposed placement in beta/livekit.agents.beta.gtm_telemetry and the listed event hooks: conversation_item_added, tool_execution_updated, function_tools_executed, and metrics_collected. Check how beta features and telemetry are structured in the repository before assessing the proposed collector and report schema. Done means a reviewable scope for the structured report, webhook behavior, and CRM payload builders; the issue says the author has already implemented a solution.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

enhancement
Feature Type

Nice to have

Feature Description

When building enterprise GTM voice agents (e.g., inbound sales discovery, lead qualification, or support bots), syncing post-call session data to systems of record (Salesforce, BigQuery) is a core requirement.

While LiveKit offers OpenTelemetry (for OTLP trace spans to SigNoz/Langfuse) and Server Webhooks (for room lifecycle events), there is currently a gap for developers who need a single, structured JSON document containing full transcripts + @function_tool execution records to send to business webhooks. Server webhooks do not contain transcripts or tool logs, and OpenTelemetry spans are split across micro-events designed for APM tools rather than CRM ingestion.

Describe the solution you'd like: Add a lightweight, opt-in PostCallTelemetryCollector and standardized PostCallReport schema to livekit.agents.beta.gtm_telemetry.

Placement note: The module lives in beta/ (the repo's established opt-in staging area for features like EndCallTool and workflows) rather than the top-level telemetry/ package, which is reserved for OTel/Cloud plumbing with private exports. This avoids expanding the stable public API surface before the feature graduates.

Key capabilities:

Automatically records transcript turns (via conversation_item_added), @function_tool executions (via tool_execution_updated + function_tools_executed — with self-timed latency, arguments, results, and errors), and session metrics (via metrics_collected).
Generates a clean, serializable PostCallReport JSON payload with float-epoch timestamps (matching the repo-wide created_at: float = Field(default_factory=time.time) convention — avoids the deprecated datetime.utcnow() and stays deterministic under the virtual-time test harness).
Built-in resilient webhook dispatcher with HMAC-SHA256 signing (X-LiveKit-Signature header) and exponential backoff (max 3 attempts, 5xx + network retries, no retry on 4xx).
Standardized adapters for HubSpot Engagements API & Salesforce Activity Tasks (pure payload builders — no network or CRM SDK dependencies).
How this complements existing LiveKit features:

Does not replace OpenTelemetry (OTel continues to trace micro-spans).
Does not replace Server Webhooks (Server webhooks continue handling room lifecycle).
Provides self-hosted and cloud users with an application-level GTM summary payload.
Works with or without a JobContext, on both the pipeline (STT→LLM→TTS) and real-time paths.
I have implemented a fully tested solution and am ready to submit a PR if this aligns with the framework roadmap!

Workarounds / Alternatives

No response

Additional Context

No response

Lingua principale
Python
Stelle
14.6k
Fork
3.9k
Merge medio
2g 23h
PR unite (30g)
177

Preparare l'ambiente

Questo progetto non fornisce container di sviluppo, Dockerfile né guida per i contributori, quindi l'ambiente è a tuo carico: parti dal suo README e consulta la nostra guida al primo contributo per i passaggi generali.

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di livekit/agents

Tutte le issue di livekit/agents

Issue simili

Altre issue su Python

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.