Changelog

AllWhatsApp AgentsCommunity AppPlatformScheduled jobs & exportsSafety RouterWhatsApp ServerPatrolPlatform APIsIntelligent Safety APINamola

Backend for WhatsApp agent flows: media, skill reports, voice, and LLM-powered insights.

1.0

No WhatsApp server release in this audit window

PlatformNote

The wolf-whatsapp-server repository had no new commits on main between 2026-03-22 and 2026-03-25; WhatsApp-adjacent patrol work shipped in wolf-server, wolf-patrol-app, and related services.

Note

wolf-whatsapp-server had no commits on origin/main during 2026-03-22 through 2026-03-25 (local clone after git fetch). There is no git diff artifact for this product in internal/git-audits/2026-03-22-to-03-25/.

Patrol and messaging–related changes in the same calendar window were delivered through wolf-server, wolf-patrol-app, wolf-enterprise-frontend, and wolf-changelog entries for those products.

1.0

Shareable public incident links

FeatureEnterprise

Incident reports can surface stable, shareable links where product policy allows public visibility.

What's New

  • Public links: Support for incident report URLs that can be opened outside WhatsApp when sharing with partners or the community is appropriate.
1.0

Report LLM execution

FeatureEnterprise

Programmatic way to invoke the report-oriented language model flow for automation and internal tools.

What's New

  • Report LLM: Execute endpoint for the report summarization and analysis path, consistent with how other LLM features are exposed.
1.0

Staging integration

EnhancementEnterprise

Batch of backend changes from staging lands on main, aligning WhatsApp services with the latest platform behaviour.

Improvements

  • Release train: Staging work is merged to main so production tracks the same feature set as other Wolf services.
1.0

Insights inference endpoint

FeatureEnterprise

A dedicated path to run the insights model against prepared context, for analytics and operator workflows.

What's New

  • Insights execution: Server-side endpoint to trigger LLM-based insight generation with the same guardrails as the rest of the API.
1.0

Media pipeline release to main

EnhancementBug FixEnterprise

The in-service media work is merged end-to-end, with follow-up fixes for typing and stability.

Improvements

  • Release integration: Branches for the Render-native media pipeline are merged into main in a single coordinated drop.
  • Code quality: Type-safety fixes so builds stay strict as the media surface grows.
1.0

Voice note transcription paths

EnhancementEnterprise

Configurable working directories for voice processing so hosted environments can place temp files on the right volume.

Improvements

  • Transcription: Temporary audio handling can target a directory you control (for disk quotas, permissions, or ephemeral storage).
1.0

Persistent media in skill reports

FeatureEnhancementEnterprise

Media attachments stored with skill reports and leaner message persistence for long-running chats.

What's New

  • Durable attachments: Media linked to skill reports is kept in a form that survives retries and replays.
  • Storage efficiency: Message history layout adjusted to reduce redundant data for high-volume threads.
1.0

In-service media pipeline

FeatureEnhancementEnterprise

Media uploads move onto the same hosted stack as the WhatsApp backend for simpler operations and faster iteration.

What's New

  • Unified media path: Images and files are accepted and processed by the application service directly instead of relying on a separate upload worker.

Improvements

  • Queues and throughput: Tweaks to background handling so bursts of media don’t stall conversations.
1.0

Media reliability and prompt updates

EnhancementBug FixEnterprise

Safer handling of failed media uploads, clearer file metadata, and agent prompt improvements shipped to main.

Improvements

  • Agent prompts: Conversation templates updated alongside the merged prompt-improvements work.
  • Media integrity: Skill reports no longer retain empty media references when an upload does not complete successfully.
  • Metadata: File size and related fields are normalized consistently for downstream processing.
  • Optional backfill: Maintenance tooling added for reconciling older media records where needed.

Bug Fixes

  • Upload edge cases: Hardening around partial or failed media transfers.