#21005: feat(tts): add path delivery mode to prevent duplicate sends
agents
size: S
Cluster:
Voice Call and TTS Improvements
## Summary
- add optional `delivery` parameter to the `tts` tool:
- `auto` (default): existing behavior, emits `MEDIA:` for automatic delivery
- `path`: returns `AUDIO_PATH:` for manual `message.send` workflows
- update tool guidance text to make duplicate-send avoidance explicit
- add unit tests for default auto mode and new path mode
## Why
When callers need manual control (for example, custom Telegram voice-note pipelines), returning a plain path avoids accidental duplicate audio sends while preserving backward compatibility.
## Validation
- `pnpm vitest run --config vitest.unit.config.ts src/agents/tools/tts-tool.test.ts`
Most Similar PRs
#19439: fix(tts): pass audioAsVoice flag through tool result pipeline
by brandonwise · 2026-02-17
60.8%
#20992: fix(tts): apply TTS processing to agentCommand outbound delivery path
by mmyyfirstb · 2026-02-19
59.3%
#21513: Agents: track TTS media in duplicate filter state
by DevvGwardo · 2026-02-20
58.7%
#22844: feat(line): add push-only deliveryMode
by loiie45e · 2026-02-21
58.4%
#18077: fix: deduplicate TTS audio delivered via tool results
by stakeswky · 2026-02-16
58.1%
#18699: feat(hooks): add deliver: "auto" mode for webhook mappings
by larrylobster9735 · 2026-02-17
57.9%
#21110: fix(tts): deliver audio via structured mediaUrl instead of MEDIA: t...
by hydro13 · 2026-02-19
56.4%
#19471: fix(gateway): honor deliver param in chat.send
by kays0x · 2026-02-17
55.5%
#23455: feat(tts) : add per-agent TTS configuration support
by jayy-77 · 2026-02-22
54.6%
#9041: feat(tts): Add post-processing hook for voice modulation
by robottwo · 2026-02-04
54.2%