feat: implement tier-a4 tts voice output replies

This commit is contained in:
William Valentin
2026-02-18 10:22:28 -08:00
parent 3eb07875f1
commit a71aa5992d
11 changed files with 482 additions and 4 deletions
+21 -1
View File
@@ -5225,6 +5225,26 @@
"docs/plans/state.json"
],
"test_status": "Docs-only change (no code paths affected)"
},
"tts-voice-output-tier-a4": {
"status": "completed",
"date": "2026-02-18",
"updated": "2026-02-18",
"summary": "Implemented Tier A4 voice output: added configurable OpenAI-compatible TTS (`tts.*`) and integrated channel-gated synthesized reply attachments in daemon routing for both native and external backend responses, with unit/integration tests and docs updates.",
"files_modified": [
"src/models/tts.ts",
"src/models/tts.test.ts",
"src/models/index.ts",
"src/config/schema.ts",
"src/config/index.ts",
"src/config/schema.test.ts",
"src/daemon/routing.ts",
"src/daemon/routing.test.ts",
"README.md",
"config/default.yaml",
"docs/plans/state.json"
],
"test_status": "pnpm test:run src/models/tts.test.ts src/config/schema.test.ts src/daemon/routing.test.ts + pnpm typecheck passing"
}
},
"overall_progress": {
@@ -5248,7 +5268,7 @@
"gmail_auth_cli": "flynn gmail-auth command implemented with OAuth2 flow, doctor check, config routed to Telegram",
"native_audio_support": "completed — smart routing for native audio (Gemini/OpenAI/GitHub) vs Whisper transcription fallback",
"remaining_phases_completion": "Phase 1: 3/3 (100%) — context levels, command registry, memory structure. Phase 2: 3/3 (100%) — component registry, confidence routing, history index. Phase 3: 2/2 (100%) — adaptive memory/compaction, truthfulness/autonomy hardening",
"next_up": "Implement Tier A4 from the OpenClaw roadmap: TTS voice output with channel-aware audio responses"
"next_up": "Implement the reactions/event-trigger automation layer from the OpenClaw roadmap (event pattern matching -> agent action execution)"
},
"soul_md_and_cron_create": {
"date": "2026-02-11",