From 0145f3a5855e1426a529dbafde40078e3bacb273 Mon Sep 17 00:00:00 2001 From: Peter Steinberger Date: Wed, 26 Nov 2025 02:18:39 +0100 Subject: [PATCH] docs: note auto-reply helper split --- CHANGELOG.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 060c5c6bf..8f20256ed 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,6 +8,8 @@ - Sessions can now send the system prompt only once: set `inbound.reply.session.sendSystemOnce` (optional `sessionIntro` for the first turn) to avoid re-sending large prompts every message. - While commands run, typing indicators refresh every 30s by default (tune with `inbound.reply.typingIntervalSeconds`); helps keep WhatsApp “composing” visible during longer Claude runs. - Optional voice-note transcription: set `inbound.transcribeAudio.command` (e.g., OpenAI Whisper CLI) to turn inbound audio into text before templating/Claude; verbose logs surface when transcription runs. Prompts now include the original media path plus a `Transcript:` block so models see both. +- Auto-reply command engine was split into focused helpers; now returns structured `{ payload, meta }`, supports injected queues for tests, respects `mediaMaxMb` for local media, and logs Claude metadata. Timeout messages include the command `cwd` when set. +- Added unit coverage for command helper edge cases (Claude flags, session args, media tokens, timeouts) and transcription download/command invocation. ## 1.0.4 — 2025-11-25