hermes-agent/gateway/platforms
Franci Penov 0afab4a32b feat(gateway): extract auto-TTS markdown strip into prepare_tts_text() hook
Refactor the inlined `re.sub(...)[:4000].strip()` cleanup at the
auto-TTS site in `_process_message_background` into an overridable
method `BasePlatformAdapter.prepare_tts_text(text: str) -> str`.

The default implementation is byte-identical to the previous inline
expression — strip `* _ \` # [ ] ( )` and truncate to 4000 chars — so
every existing adapter (Telegram, Discord, Slack, Matrix, IRC, etc.)
gets exactly the same behaviour as before. Zero behaviour change for
any consumer that doesn't override the method.

Why add the hook: voice-first platform adapters need stricter
cleanup than text-bubble platforms. The default strips a handful of
markdown sigils, which is fine when the output goes into a Discord
embed or a Telegram message bubble — but read aloud by a TTS engine,
URLs (`https://example.com/foo`), fenced code blocks, file paths
(`/Users/x/foo.py`), and `MEDIA:` tags turn into long sequences of
unintelligible characters. With this hook an adapter can drop those
spans before TTS while leaving the data-channel transcript intact
for visual rendering.

Without the hook, voice adapters have to either
  - duplicate the auto-TTS flow inside their own `handle_response`
    pipeline, which means re-implementing the entire `extract_media`,
    `extract_images`, `extract_local_files`, attachment routing and
    error-handling sequence in `_process_message_background`, or
  - live with TTS speaking URLs character-by-character.

Both are worse than a 7-line method addition.

Example consumer:
  https://github.com/kortexa-ai/hermes-livekit — LiveKit WebRTC voice
  gateway plugin. Its `LiveKitAdapter.prepare_tts_text()` additionally
  strips fenced code blocks, inline code, URLs, file paths, and
  `MEDIA:` tags before TTS synthesis, while the full response still
  reaches connected clients via the data channel. Drop-in installable
  via `pip install git+https://github.com/kortexa-ai/hermes-livekit.git`.

Carved out of #3894 (LiveKit WebRTC gateway PR) so the generic hook
can land independently of the LiveKit platform itself.
2026-05-16 23:11:43 -07:00
..
qqbot fix(gateway): keep QQBot reconnect loop alive 2026-05-13 23:13:25 -07:00
__init__.py perf(gateway): defer QQAdapter and YuanbaoAdapter imports via PEP 562 (#22790) 2026-05-09 13:17:48 -07:00
_http_client_limits.py fix(gateway): tighten httpx keepalive and close whatsapp typing-response leak (#18451) 2026-05-02 02:23:37 -07:00
ADDING_A_PLATFORM.md refactor(plugins): add apply_yaml_config_fn registry hook 2026-05-13 22:20:30 -07:00
api_server.py fix(api_server): coerce stringified booleans in request payloads 2026-05-16 23:02:02 -07:00
base.py feat(gateway): extract auto-TTS markdown strip into prepare_tts_text() hook 2026-05-16 23:11:43 -07:00
bluebubbles.py chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) 2026-05-11 11:13:25 -07:00
dingtalk.py fix(gateway): add lazy_deps.ensure() to slack, matrix, dingtalk, feishu adapters (#25014) 2026-05-13 19:28:50 +05:30
discord.py feat(discord): allow_any_attachment config to accept arbitrary file types 2026-05-16 20:26:18 -07:00
email.py chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) 2026-05-11 11:13:25 -07:00
feishu.py fix(async): close unscheduled coroutines in all threadsafe bridges (#26584) 2026-05-15 14:00:01 -07:00
feishu_comment.py chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) 2026-05-11 11:13:25 -07:00
feishu_comment_rules.py chore: ruff auto-fix C401, C416, C408, PLR1722 (#23940) 2026-05-11 11:20:58 -07:00
helpers.py fix(gateway): preserve underscores in plain-text identifiers 2026-05-16 23:11:43 -07:00
homeassistant.py chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) 2026-05-11 11:13:25 -07:00
matrix.py fix(gateway): complete lazy-install rebind for slack/feishu/matrix + add ensure_and_bind helper (#25038) 2026-05-14 10:41:46 +05:30
mattermost.py chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) 2026-05-11 11:13:25 -07:00
msgraph_webhook.py fix(msgraph_webhook): harden auth surface + IP allowlisting + response hygiene 2026-05-08 10:29:58 -07:00
signal.py fix(signal): read groupV2.id in envelope, fall back to legacy groupInfo (#27051) 2026-05-16 11:53:57 -07:00
signal_rate_limit.py feat(gateway/signal): add support for multiple images sending 2026-04-30 04:28:08 -07:00
slack.py fix(gateway): add trust_env=True to aiohttp sessions in SMS, Slack, Teams, Google Chat adapters 2026-05-16 23:11:43 -07:00
sms.py fix(gateway): add trust_env=True to aiohttp sessions in SMS, Slack, Teams, Google Chat adapters 2026-05-16 23:11:43 -07:00
telegram.py fix(telegram): restore DM topic typing indicator 2026-05-16 16:50:02 -07:00
telegram_network.py chore: ruff auto-fix C401, C416, C408, PLR1722 (#23940) 2026-05-11 11:20:58 -07:00
webhook.py fix: remove unused import and hoist module-level constant 2026-05-16 22:49:54 -07:00
wecom.py fix(wecom): update connection status after WebSocket reconnection 2026-05-12 18:48:17 -07:00
wecom_callback.py fix(gateway): tighten httpx keepalive and close whatsapp typing-response leak (#18451) 2026-05-02 02:23:37 -07:00
wecom_crypto.py feat(gateway): add WeCom callback-mode adapter for self-built apps 2026-04-11 15:22:49 -07:00
weixin.py chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) 2026-05-11 11:13:25 -07:00
whatsapp.py fix(gateway): keep running when platforms fail; add per-platform circuit breaker + /platform (#26600) 2026-05-15 14:32:14 -07:00
yuanbao.py refactor(yuanbao): improve quote media fallback — move to DispatchMiddleware, tighten conditions 2026-05-15 01:17:50 -07:00
yuanbao_media.py chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) 2026-05-11 11:13:25 -07:00
yuanbao_proto.py chore: ruff auto-fix PLR6201 — tuple → set in membership tests (#23937) 2026-05-11 11:13:25 -07:00
yuanbao_sticker.py yuanbao platform (#16298) 2026-04-26 18:50:49 -07:00