Index agent message consumption analytics

[flvndvd]

Description

This PR indexes the consumption documents produced for each billed agent message. The existing attribution workflow now runs a second activity after attribution is stored, which loads the message data, builds its LLM and tool documents, and writes them to Elasticsearch.

Each indexing pass replaces the complete snapshot for the message. This prevents documents from an earlier message version from remaining in the index and being counted twice. Writes use deterministic IDs and failures are retried by Temporal.

It also ensures the authoritative bill and skill snapshot are persisted before attribution starts.

Tests

Risk

Deploy Plan

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

2 Skipped Deployments

Project	Deployment	Actions	Updated (UTC)
playground	Ignored	Preview	Aug 10, 2026 8:39am
storybook	Ignored	Preview	Aug 10, 2026 8:39am

[dust-agent]

Coding Rules LGTM \o/

[github-actions]

Warnings

⚠️

Temporal workflow/activity files have been modified: - front/temporal/agent_loop/activities/finalize.ts - front/temporal/analytics_queue/activities/consumption_attribution.ts - front/temporal/analytics_queue/workflows.ts **IMPORTANT**: Renaming activity functions can cause non-deterministic errors in Temporal workflows. Running workflows may still reference the old activity names, which will cause failures when they try to execute. Best practices: - **DO NOT** rename existing activity functions - **DO** create new activities with new names if you need different behavior - **DO** use activity versioning patterns if you must change activity signatures - **DO** ensure all running workflows complete before removing old activities If you're only adding new activities or fixing bugs within existing ones, this warning can be ignored.

Generated by 🚫 dangerJS against 3b626fb