{"repo":"NousResearch/hermes-agent","public_id":"11686","display_label":"WeChat/multi-gateway inbound voice STT fixes","summary":"These issues and PRs address bugs in processing inbound voice messages across WeChat (Weixin) and other gateways, focusing on Silk-to-WAV conversion, STT routing, and cases where audio was skipped or mishandled when a text hint was present.","subsystem":"gateway","counts":{"members":10,"open_issues":3,"open_issues_distinct":3,"open_prs":1,"closed_issues":1,"merged_prs":1,"attempt_prs":5},"landed_fix":{"status":"merged_to_main","basis":"structural","pr":73515},"resolution":{"state":"partially_resolved","by":"pr-73515"},"freshness":{"state":"verified","last_verified_at":"2026-07-28T21:06:57+00:00","is_stale":false},"grouping":{"backbone":"STRUCTURAL_PARTIAL","link_density":0.19555555555555557},"fix_edges":[{"issue_number":16524,"pr_number":73515,"tier":"verified","basis":"closing_ref","confidence":0.95,"recoverable_from_timeline":true},{"issue_number":27300,"pr_number":73515,"tier":"verified","basis":"closing_ref","confidence":0.95,"recoverable_from_timeline":true},{"issue_number":30822,"pr_number":73515,"tier":"verified","basis":"closing_ref","confidence":0.95,"recoverable_from_timeline":true},{"issue_number":35704,"pr_number":73515,"tier":"verified","basis":"closing_ref","confidence":0.95,"recoverable_from_timeline":true},{"issue_number":38211,"pr_number":73515,"tier":"verified","basis":"closing_ref","confidence":0.95,"recoverable_from_timeline":true},{"issue_number":57882,"pr_number":73515,"tier":"verified","basis":"superseded_ref","confidence":0.9,"recoverable_from_timeline":false},{"issue_number":64831,"pr_number":73515,"tier":"verified","basis":"closing_ref","confidence":0.95,"recoverable_from_timeline":true},{"issue_number":66325,"pr_number":73515,"tier":"verified","basis":"closing_ref","confidence":0.95,"recoverable_from_timeline":true}],"members":[{"kind":"issue","number":11686,"title":"[Bug]: Weixin inbound voice messages skip audio download when text hint exists","url":null,"state":"open"},{"kind":"issue","number":27300,"title":"WeChat voice messages use Tencent Cloud STT which garbles non-Chinese languages — should route through Hermes' own STT pipeline","url":null,"state":"closed"},{"kind":"issue","number":32196,"title":"Weixin(WeChat) voice messages in Silk format skip STT — russian transcription broken","url":null,"state":"open"},{"kind":"issue","number":42084,"title":"fix(gateway): convert WeChat Silk voice messages to WAV via pysilk for STT","url":null,"state":"open"},{"kind":"pr","number":11689,"title":"fix(weixin): keep inbound voice audio when text hint exists","url":null,"state":"closed","close_reason":{"category":"silent_close","implication":"active"},"merged":false},{"kind":"pr","number":27316,"title":"fix(weixin): opt into local STT for inbound voice messages (#27300)","url":null,"state":"closed","close_reason":{"category":"stale_abandoned","implication":"active"},"merged":false},{"kind":"pr","number":42141,"title":"fix(weixin): convert Silk voice messages to WAV via pilk for STT","url":null,"state":"open","close_reason":{"refs":[{"kind":"pr","value":"#31487","number":31487}],"category":"wontfix_bydesign","implication":"wontfix"},"merged":false},{"kind":"pr","number":51924,"title":"fix(weixin): 5 WeChat bug fixes — voice STT, polling hang, msg truncation, session split, interrupt","url":null,"state":"closed","close_reason":{"refs":[{"kind":"pr","value":"#51924","number":51924}],"category":"uncategorized","implication":"needs_llm"},"merged":false},{"kind":"pr","number":73515,"title":"fix(gateway): inbound voice classification/routing for Feishu, DingTalk, LINE, QQ, Photon, WhatsApp, Weixin","url":null,"state":"merged","close_reason":{"category":"merged","implication":"superseded"},"merged":true,"is_fix_pr":true,"fix_tier":"verified","files_changed":["contributors/emails/[redacted:email]","contributors/emails/[redacted:email]","contributors/emails/[redacted:email]","contributors/emails/[redacted:email]","contributors/emails/[redacted:email]","contributors/emails/[redacted:email]","gateway/platforms/qqbot/adapter.py","gateway/platforms/weixin.py","gateway/run.py","plugins/platforms/dingtalk/adapter.py","plugins/platforms/feishu/adapter.py","plugins/platforms/line/adapter.py","plugins/platforms/photon/adapter.py","plugins/platforms/whatsapp/adapter.py","tests/gateway/test_dingtalk.py","tests/gateway/test_feishu.py","tests/gateway/test_feishu_voice_message_type.py","tests/gateway/test_line_plugin.py","tests/gateway/test_qqbot.py","tests/gateway/test_stt_config.py","tests/gateway/test_weixin.py","tests/gateway/test_whatsapp_formatting.py","tests/plugins/platforms/photon/test_inbound.py","tests/tools/test_transcription.py","tests/tools/test_transcription_tools.py","tools/transcription_tools.py"]},{"kind":"pr","number":83763,"title":"fix(weixin): convert Silk voice messages to WAV via pilk for STT","url":null,"state":"closed","close_reason":{"refs":[{"kind":"pr","value":"#42141","number":42141}],"category":"duplicate_of","implication":"duplicate"},"merged":false}],"trust":{"default_tier":"verified","includes_suggested":false}}