cloud/music_library
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Extract a default prompt

Browse Source
This commit is contained in:
Claudio Ortolina
2026-04-04 23:31:20 +01:00
parent 86fd3134f1
commit ec12be613b
4 changed files with 33 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/architecture.md
+1
View File
@@ -129,6 +129,7 @@ Last.fm schemas (separate, not Ecto-persisted to main DB):
| `Chats.StreamProvider` | Behaviour for streaming AI chat (`stream_response/3` callback) |
| `Chats.RecordChat` | Chat implementation for records (OpenAI streaming, web search enabled) |
| `Chats.ArtistChat` | Chat implementation for artists (OpenAI streaming, uses Wikipedia/artist context) |
| `Chats.DefaultPrompt` | Shared default prompt fragments (identity, approach) for chat implementations |
| `Country` | Country code (alpha-2, alpha-3, subdivision, IETF) to flag emoji conversion |
| `ErrorTracker.ErrorNotifier` | GenServer: attaches to ErrorTracker telemetry, skips muted errors, throttles repeated errors, dispatches email notifications |
| `ErrorTracker.ErrorNotifier.Email` | Builds and sends Swoosh error notification emails with stack trace formatting |