fix(gateway): make Telegram auto-TTS provider-aware - #62040
Closed
giladbau wants to merge 1 commit into
Closed
Conversation
alt-glitch
added
type/bug
giladbau
force-pushed
the
feat/telegram-voice-input-ogg
branch
from
July 10, 2026 14:37
3ae1956 to
1b4a0d5
Compare
teknium1
reviewed
Jul 11, 2026
teknium1
left a comment
teknium1
left a comment
Contributor
There was a problem hiding this comment.
Thanks for covering both gateway auto-TTS paths and preserving command/plugin-provider behavior. The main direction addresses a current Telegram delivery bug.
Problems
tools/tts_tool.py:401classifies Gemini as native Opus, but_generate_gemini_ttsproduces PCM/WAV and needs ffmpeg to encode a valid.ogg/Opus file (tools/tts_tool.py:1768-1810). Without ffmpeg it copies WAV bytes to the.oggpath, while the new routing later marks that path voice-compatible (tools/tts_tool.py:2467-2468). The new Gemini test stubs the generator with OGG bytes, so it does not cover the real codec path.
Suggested changes
- Separate Gemini from native-Opus providers or explicitly model its ffmpeg dependency, and add a regression covering the no-ffmpeg/resulting-codec behavior before advertising a Telegram voice bubble.
Automated hermes-sweeper review.
| "kittentts", | ||
| "piper", | ||
| }) | ||
| NATIVE_OPUS_TTS_PROVIDERS = frozenset({"elevenlabs", "openai", "mistral", "gemini"}) |
Contributor
There was a problem hiding this comment.
Gemini is not native Opus: _generate_gemini_tts receives raw PCM, wraps it as WAV, then uses ffmpeg for .ogg/Opus; without ffmpeg it copies WAV bytes to the .ogg path. Please model that dependency separately and add a regression for the no-ffmpeg path rather than treating Gemini as a native-Opus provider.
teknium1
added
sweeper:risk-compatibility
teknium1
pushed a commit
that referenced
this pull request
Jul 28, 2026
…bbles Salvaged from PR #62040 (@giladbau), simplified per post-#73072 main: the central _repair_ogg_container transcode makes an explicit .ogg output path sufficient — no target_platform plumbing through the TTS tool needed. Root cause (class-level): both gateway auto-TTS delivery call sites relied on the TTS tool reading HERMES_SESSION_PLATFORM to pick Ogg/Opus vs MP3, but that contextvar is cleared by _clear_session_env before the base adapter's post-handler auto-TTS block runs, so want_opus was always False on that path → MP3 → Telegram sent an audio attachment instead of a native voice bubble (#57049, #36685). The runner's _send_voice_reply had the sibling bug: it hardcoded .ogg for Telegram only, leaving Matrix and Feishu runner voice replies as MP3 (#14841, #45557). Fix: new build_auto_tts_output_path(platform) in gateway/platforms/base.py hands an explicit .ogg temp path when the platform is in the TTS tool's OPUS_VOICE_PLATFORMS set (single source of truth — telegram/matrix/feishu/ whatsapp/signal), .mp3 otherwise. Used by BOTH delivery call sites: - BasePlatformAdapter auto-TTS block (also honors the tool's success flag and cleans up requested + returned paths) - GatewayRunner._send_voice_reply (replaces the telegram-only ternary) Fixes #57049 Fixes #36685 Refs #14841 #45557
teknium1
pushed a commit
that referenced
this pull request
Jul 28, 2026
…bbles Salvaged from PR #62040 (@giladbau), simplified per post-#73072 main: the central _repair_ogg_container transcode makes an explicit .ogg output path sufficient — no target_platform plumbing through the TTS tool needed. Root cause (class-level): both gateway auto-TTS delivery call sites relied on the TTS tool reading HERMES_SESSION_PLATFORM to pick Ogg/Opus vs MP3, but that contextvar is cleared by _clear_session_env before the base adapter's post-handler auto-TTS block runs, so want_opus was always False on that path → MP3 → Telegram sent an audio attachment instead of a native voice bubble (#57049, #36685). The runner's _send_voice_reply had the sibling bug: it hardcoded .ogg for Telegram only, leaving Matrix and Feishu runner voice replies as MP3 (#14841, #45557). Fix: new build_auto_tts_output_path(platform) in gateway/platforms/base.py hands an explicit .ogg temp path when the platform is in the TTS tool's OPUS_VOICE_PLATFORMS set (single source of truth — telegram/matrix/feishu/ whatsapp/signal), .mp3 otherwise. Used by BOTH delivery call sites: - BasePlatformAdapter auto-TTS block (also honors the tool's success flag and cleans up requested + returned paths) - GatewayRunner._send_voice_reply (replaces the telegram-only ternary) Fixes #57049 Fixes #36685 Refs #14841 #45557
Contributor
|
Merged into main via consolidated salvage PR #73508 (merge Your contribution is credited to you in git history. Thank you! Closing this PR as merged-via-salvage. |
This was referenced Jul 29, 2026
randlee
pushed a commit
to randlee/hermes-agent
that referenced
this pull request
Aug 11, 2026
…bbles Salvaged from PR NousResearch#62040 (@giladbau), simplified per post-NousResearch#73072 main: the central _repair_ogg_container transcode makes an explicit .ogg output path sufficient — no target_platform plumbing through the TTS tool needed. Root cause (class-level): both gateway auto-TTS delivery call sites relied on the TTS tool reading HERMES_SESSION_PLATFORM to pick Ogg/Opus vs MP3, but that contextvar is cleared by _clear_session_env before the base adapter's post-handler auto-TTS block runs, so want_opus was always False on that path → MP3 → Telegram sent an audio attachment instead of a native voice bubble (NousResearch#57049, NousResearch#36685). The runner's _send_voice_reply had the sibling bug: it hardcoded .ogg for Telegram only, leaving Matrix and Feishu runner voice replies as MP3 (NousResearch#14841, NousResearch#45557). Fix: new build_auto_tts_output_path(platform) in gateway/platforms/base.py hands an explicit .ogg temp path when the platform is in the TTS tool's OPUS_VOICE_PLATFORMS set (single source of truth — telegram/matrix/feishu/ whatsapp/signal), .mp3 otherwise. Used by BOTH delivery call sites: - BasePlatformAdapter auto-TTS block (also honors the tool's success flag and cleans up requested + returned paths) - GatewayRunner._send_voice_reply (replaces the telegram-only ternary) Fixes NousResearch#57049 Fixes NousResearch#36685 Refs NousResearch#14841 NousResearch#45557
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Fixes Telegram auto-TTS voice replies returning MP3 audio cards instead of native Opus voice bubbles.
.oggdirectly; MP3/WAV-native providers use a conversion-safe intermediate before Opus conversion.output_pathbehavior, command/plugin configured formats, andvoice_compatibleopt-in semantics.Closes the gap left by stale PRs #31937 and #32539.
Type of Change
Verification
+538 / -75 lines across 6 files.