<feed xmlns='http://www.w3.org/2005/Atom'>
<title>dotemacs/docs/NOTES.org.backup, branch load-graph-classify-start</title>
<subtitle>My Emacs configuration
</subtitle>
<id>https://git.cjennings.net/dotemacs/atom?h=load-graph-classify-start</id>
<link rel='self' href='https://git.cjennings.net/dotemacs/atom?h=load-graph-classify-start'/>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/dotemacs/'/>
<updated>2025-11-06T06:43:13+00:00</updated>
<entry>
<title>feat: Add AssemblyAI transcription backend with speaker diarization</title>
<updated>2025-11-06T06:43:13+00:00</updated>
<author>
<name>Craig Jennings</name>
<email>c@cjennings.net</email>
</author>
<published>2025-11-06T06:43:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/dotemacs/commit/?id=7110f8c1f41b9c82288efb328c709dd00ed8fcb6'/>
<id>urn:sha1:7110f8c1f41b9c82288efb328c709dd00ed8fcb6</id>
<content type='text'>
Integrated AssemblyAI as the third transcription backend alongside OpenAI
API and local-whisper, now set as the default due to superior speaker
diarization capabilities (up to 50 speakers).

New Features:
- AssemblyAI backend with automatic speaker labeling
- Backend switching UI via C-; T b (completing-read interface)
- Universal speech model supporting 99 languages
- API key management through auth-source/authinfo.gpg

Implementation:
- Created scripts/assemblyai-transcribe (upload → poll → format workflow)
- Updated transcription-config.el with multi-backend support
- Added cj/--get-assemblyai-api-key for secure credential retrieval
- Refactored process environment handling from if to pcase
- Added cj/transcription-switch-backend interactive command

Testing:
- Created test-transcription-config--transcription-script-path.el
- 5 unit tests covering all 3 backends (100% passing)
- Followed quality-engineer.org guidelines (test pure functions only)
- Investigated 18 test failures: documented cleanup in todo.org

Files Modified:
- modules/transcription-config.el - Multi-backend support and UI
- scripts/assemblyai-transcribe - NEW: AssemblyAI integration script
- tests/test-transcription-config--transcription-script-path.el - NEW
- todo.org - Added test cleanup task (Method 3, priority C)
- docs/NOTES.org - Comprehensive session notes added

Successfully tested with 33KB and 4.1MB audio files (3s and 9s processing).
</content>
</entry>
<entry>
<title>refactor: Rename "session" to "workflow" for documented processes</title>
<updated>2025-11-05T18:58:56+00:00</updated>
<author>
<name>Craig Jennings</name>
<email>c@cjennings.net</email>
</author>
<published>2025-11-05T18:58:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.cjennings.net/dotemacs/commit/?id=776b507351d5c8e05c107357c304240764f7d020'/>
<id>urn:sha1:776b507351d5c8e05c107357c304240764f7d020</id>
<content type='text'>
This resolves the ambiguity where "session" meant two different things:
- Working session (time period we work together)
- Documented routine/workflow (process to achieve a goal)

Changes:
- Renamed docs/sessions/ → docs/workflows/
- Renamed create-session.org → create-workflow.org
- Updated all references throughout:
  - "session type" → "workflow"
  - "session workflow" → "workflow"
  - "session definition" → "workflow definition"
  - "Available Session Types" → "Available Workflows"

Updated files:
- docs/NOTES.org - All workflow references updated
- docs/workflows/*.org - All workflow files updated with new terminology
- ~/documents/claude/NOTES.org - Template updated
- ~/documents/claude/NOTES-NEW.org - New template updated

Terminology now clear:
- "Let's run the refactor workflow" = Execute existing workflow
- "I want to create a refactor workflow" = Create new workflow definition
- "This session" = Working time period (unchanged)
</content>
</entry>
</feed>
