Matthew Meszaros 66aaaa6584 feat: add an ai agent step to campaign sequences

2026-07-21 17:35:11 +02:00

..

campaign_steps.go

feat: remove the HTTP-request action from campaign steps and automations in favor of signed webhooks, keep fire_event for custom payloads, and drop the now-unused outbound quota plumbing

2026-06-15 08:11:35 +02:00

events.go

feat: inbox agent that drafts a suggested unibox reply on inbound human replies for human approve/edit/discard - paid + per-org opt-in (organizations.inbox_agent_enabled) feature where the consumer's reply hook, on a non-automated reply, detaches a goroutine (panic-contained, never blocks ingest) that checks entitlement, dedupes via ai_thread_drafts partial unique indexes (one pending per thread, unique source_message_id), pre-checks balance, grounds a reply in the thread history + org voice + skills via generation.Provider.Complete, reserves a draft row then charges 5 credits (idempotency inbox_agent:<draft.ID>, row unwound on a fresh context if the charge fails so no unpaid draft lingers), and emits an org-scoped AI_DRAFT_READY event gated on access_unibox; the agent never sends - only a human POST to /unibox/agent-drafts/:id/approve sends through the normal reply path, claiming pending->approved before send with an approved->pending revert on send failure, alongside list + discard endpoints; plus the unibox awaiting_agent_draft badge + agent_drafts search scope, an AgentDraftCard in the thread view with inline-editable approve-and-send/discard, the workspace settings opt-in toggle, CanUseInboxAgent paid gate, migration 000065, and docs (inbox-agent guide, endpoints, realtime)

2026-07-14 06:13:27 +02:00

inbound_bounce.go

feat: resolve inbound bounce events back to the original campaign send by message id and record them idempotently through the deliverability pipeline (suppression, campaign progress, breaker), and document permanent-only bounce detection

2026-07-04 11:36:47 +02:00

labels.go

feat: execute campaign AI steps in the scheduler path — one metered completion per contact (SetAI-wired provider + credits with per-step idempotency and refund-on-failure) that labels progress, fills contact custom fields which feed the chosen actions' templates, runs AI-picked pre-configured actions with per-decision campaign logging and tag/label choice resolution, grounds decisions in campaign history and the newest inbound reply via LatestInboundFromContact, and hands instant chains back to the scheduler at AI nodes

2026-07-17 16:26:23 +00:00

reply_actions.go

feat: add an ai agent step to campaign sequences

2026-07-21 17:35:11 +02:00

service.go

feat: add shared run time listing and arg resolving for ai agents

2026-07-21 17:35:11 +02:00