MIME strings like 'audio/webm; codecs=opus' were incorrectly matched by
the 'opus' branch (contains-check) before reaching the 'webm' branch,
returning 'voice.opus' instead of 'voice.webm'. This could cause the
Groq Whisper API to reject or misidentify the file format.
Fix: split on ';' to extract only the base MIME type, then match
exhaustively. Also add 'audio/x-wav' as a wav alias.
Adds a regression test: audio_mime_to_filename('audio/webm; codecs=opus')
must return 'voice.webm'.
Reported by CodeRabbit in PR review.
(cherry picked from commit 84861c727a)
Audio/voice messages on the WhatsApp Web channel were silently dropped
because `text_content()` returns an empty string for non-text messages
and no transcription path existed (unlike the Telegram channel which
already uses `transcription::transcribe_audio()`).
Changes:
- **Cargo.toml**: Move `qrcode` and all `wa-rs-*` crates out of the
`[target.'cfg(any(linux|macos|windows))'.dependencies]` section into
the unconditional `[dependencies]` section. All affected crates are
`optional = true`, so they add no compile cost unless
`--features whatsapp-web` is active. The previous placement caused
Cargo to exclude them when targeting `android` (target_os = "android"
does not match the cfg predicate), producing E0433 unresolved-crate
errors for every wa-rs import in `whatsapp_web.rs` and
`whatsapp_storage.rs` on Android cross-compilation.
- **whatsapp_web.rs**:
- Add `transcription: Option<TranscriptionConfig>` field.
- Add `with_transcription()` builder (mirrors `TelegramChannel`).
- Add `audio_mime_to_filename()` helper mapping WhatsApp MIME types
(e.g. `audio/ogg; codecs=opus`) to filenames the Groq Whisper API
accepts.
- Extend `Event::Message` handler: when text is empty, check
`msg.audio_message`; download and decrypt audio via
`client.download(audio_msg.as_ref())` (`.as_ref()` required because
prost boxes nested proto fields as `Box<AudioMessage>`, which does
not itself implement `Downloadable`); forward decrypted bytes to
`transcription::transcribe_audio()`.
- Add three unit tests: builder enable/disable guard and MIME mapping.
- **mod.rs**: Chain `.with_transcription(config.transcription.clone())`
onto `WhatsAppWebChannel::new(...)` in the `"web"` factory branch so
transcription is active whenever the global `[transcription]` section
is enabled.
Activation: set `[transcription] enabled = true` and export
`GROQ_API_KEY` in the environment.
(cherry picked from commit 325241aeb6)
Register /new, /model, and /models commands with Telegram's Bot API
on startup so they appear in the command menu for users. Registration
is non-fatal — if the API call fails, a warning is logged and the
bot continues listening normally.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Split the catch-all `_` match arm on the deleteMessage result into
separate `Ok(r)` and `Err(e)` arms so that HTTP status codes and
network errors are logged individually. The response body is not
logged (security policy).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When editMessageText returns 'message is not modified', the draft
already contains the correct content from update_draft. Detect this
Telegram API response and treat it as success rather than falling
through to the delete+send fallback, which would create a visible
duplicate message.
Also guard the final fallback: only send a new message after
successfully deleting the draft. If deleteMessage fails, the draft
still shows the response text, so sending would create a duplicate.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add support for Chrome, Firefox, and Edge browsers to the browser_open tool,
which previously only supported Brave. Users can now specify the browser
via the browser_open config option.
Changes:
- Add browser_open config field: "disable" | "brave" | "chrome" | "firefox" | "edge" | "default"
- Implement platform-specific launch commands for Chrome, Firefox, and Edge
- When set to "disable", only the browser automation tool is registered, not the browser_open tool
- Update tool descriptions and error messages to reflect browser selection
Co-Authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(ci): retrigger PR checks after intake body update
* fix(ci): stabilize local quality gates on rebased main
---------
Co-authored-by: Chummy <chumyin0912@gmail.com>
Co-authored-by: xj <gh-xj@users.noreply.github.com>
Implement CostObserver that intercepts LlmResponse observer events and
records token usage to the CostTracker with proper cost calculations.
Changes:
- Add src/observability/cost.rs: CostObserver implementation
- Listens for LlmResponse events with token counts
- Looks up model pricing from CostConfig (with fallback defaults)
- Records usage via CostTracker.record_usage()
- Includes model family matching for pricing lookups
- Update src/observability/mod.rs:
- Export CostObserver
- Add create_observer_with_cost_tracking() helper that wraps base
observer with CostObserver when cost tracking is enabled
- Update src/gateway/mod.rs:
- Use create_observer_with_cost_tracking() to wire cost observer
into the gateway observer stack when config.cost.enabled is true
The /api/cost endpoint already exists and will now return accurate
session/daily/monthly cost data populated by the CostObserver.
Resolves#2111
Phase 2 of ClawWork integration. Implements:
- TaskClassifier with 44 BLS occupations and wage data
- OccupationCategory enum (Tech/Business/Healthcare/Legal)
- Keyword-based classification with confidence scoring
- Hours estimation based on instruction complexity
- Fuzzy matching for occupation lookup
Reference: ClawWork/clawmode_integration/task_classifier.py
Add SiliconFlow provider factory support and alias/env handling.
Normalize onboarding UX to volcengine while preserving doubao/ark runtime aliases.
Add integration registry entries and provider resolution coverage tests.
Expand provider and command docs with setup and validation examples.
