Add option to include speaker labels in summary prompts when diarization
is available. When enabled, transcripts are formatted as:
[SPEAKER_NAME] Text here...
The prompt also includes a hint to the LLM that speaker labels are present,
helping it produce summaries that attribute statements to specific speakers.
Changes:
- Add IncludeSpeakerInfo field to SummaryTemplate model
- Add toggle UI in summary template dialog
- Format transcript with speaker labels when generating summary
- Update prompt prefix to indicate speaker labels are present
Closes#353🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change cookie SameSite policy from Strict to Lax (Strict blocks media subresources on mobile)
- Decouple Secure cookie flag from APP_ENV:
- Add SECURE_COOKIES config (defaults to true in prod, but can be overridden)
- Allows testing production builds over HTTP (home network)
- Increase gocyclo threshold to 25 to accommodate complex handlers
- Fix refresh token cookie Secure flag bug (was hardcoded to false)
- Wire up AllowedOrigins config in CORS middleware (router, handlers, chat, SSE)
- Add APP_ENV=production to Dockerfile and Dockerfile.cuda
- Update all docker-compose files with APP_ENV and ALLOWED_ORIGINS examples
- CORS now validates origins in production, allows all in development
- Increase gocyclo threshold from 20 to 25 for complex handlers
Phase 5: Refactor queue.go (10 DB calls removed)
- Added JobRepository to TaskQueue struct and constructor
- Added UpdateStatus, UpdateError, FindByStatus, CountByStatus methods to JobRepository
- Replaced all database.DB calls with repository methods
Phase 6: Refactor chat_handlers.go and summarize_handlers.go (6 DB calls removed)
- Added GetMessageCountsBySessionIDs and GetLastMessagesBySessionIDs to ChatRepository
- Added UpdateSummary to JobRepository
- Replaced batch queries and update calls with repository methods
- Removed database import from both files
Phase 7: Refactor quick_transcription.go (3 DB calls removed)
- Added JobRepository injection to QuickTranscriptionService
- Updated constructor and all callers
Summary: 46+ database.DB calls replaced with repository methods across 7 phases.
All tests pass, build succeeds.
Phase 1: Define interfaces
- Created internal/interfaces/ package with AuthServiceInterface, TaskQueueInterface, JobProcessorInterface
Phase 2: Refactor handlers.go (21 DB calls removed)
- Replaced all database.DB calls with repository methods
- Added RefreshTokenRepository for token management
- Added new repository methods: Count, FindActiveTrackJobs, FindLatestCompletedExecution, FindByName
Phase 3: Refactor dropzone.go (3 DB calls removed)
- Added CountWithAutoTranscription to UserRepository
- Injected JobRepository and UserRepository into Service
Phase 4: Refactor multitrack_processor.go
- Changed constructor to accept *gorm.DB and JobRepository
- Updated Handler to inject MultiTrackProcessor
Updated all test files with new dependencies and mock implementations.
- GetTranscript returns 200 with available=false when transcript not ready
- GetJobExecutionData returns 200 with available=false when no execution
- GetJobLogs returns JSON with available=false when no logs exist
- Updated frontend hooks to handle new response format with available field
- Added .gitignore entries for prompt.txt and .agent folder
- Add Transfer-Encoding chunked and X-Accel-Buffering headers to chat and summarize handlers
- Start response immediately with c.Status(http.StatusOK)
- Fix SummaryDialog: wider desktop, reading font, no inner border, darker text
- Add generating animation while waiting for first LLM chunk
Fix for enhancement issue #194
Added option to use custom OpenAI API base URL.
If not configured the default OpenAI API base URL (https://api.openai.com/v1) will be used.
Does not change current behavior of apiKey, i.e if apiKey is already configured it will not have to be re-entered when modifying base URL.
Instead of sending transcript (raw transcript json) we send cleanTranscript (formated and uses MUCH less tokens) to LLM.
Before we sent transcript:
"{"text":" Testar lite, ett, två, tre.","language":"sv","segments":[{"start":1.347,"end":4.253,"text":" Testar lite, ett, två, tre.","speaker":"SPEAKER_00"}],"word_segments":[{"start":1.347,"end":2.013,"word":"Testar","score":0.887,"speaker":"SPEAKER_00"},{"start":2.094,"end":2.74,"word":"lite,","score":0.936,"speaker":"SPEAKER_00"},{"start":2.76,"end":3.002,"word":"ett,","score":0.984,"speaker":"SPEAKER_00"},{"start":3.103,"end":3.668,"word":"två,","score":0.859,"speaker":"SPEAKER_00"},{"start":3.688,"end":4.253,"word":"tre.","score":0.88,"speaker":"SPEAKER_00"}],"confidence":0,"processing_tim... ..."
Now we send cleanTranscript:
"[SPEAKER_00] [00:00:01 - 00:00:04] Testar lite, ett, två, tre."
YouTube downloads were failing with "exit status 1" error. Root cause:
YouTube now requires yt-dlp to use a JavaScript runtime for video cipher
decryption.
Changes:
- Install Deno runtime in both Dockerfiles (standard and CUDA)
- Upgrade from yt-dlp to yt-dlp[default] to include all optional dependencies
- Add stderr capture to YouTube download handler for better error diagnostics
- Add performance logging for YouTube downloads (timing and file size)
Fixes#224
See: https://github.com/yt-dlp/yt-dlp/issues/14404
