49 Commits

Author	SHA1	Message	Date
itsrubberduck	d90b494334	fix pm	2026-02-13 08:50:02 +01:00
Remi	93fed93d41	Add unsubscribe endpoint and email footers	2025-11-20 23:29:44 +01:00
Remi	040783f679	Style feedback drip email like invites	2025-11-20 21:26:55 +01:00
Remi	86727e7749	Normalize taxi routes for clearer speech	2025-10-18 21:29:56 +02:00
Remi	124d76760b	Add reply-to support for admin notifications	2025-10-18 16:33:06 +02:00
Remi	faebc91ebb	feat: surface pilot intent from llm decisions	2025-10-16 21:07:21 +02:00
Remi	d9de0c1c93	feat: integrate llm-backed routing with fallback	2025-10-16 19:55:13 +02:00
Remi	4480469c4b	Allow configuring OpenAI base URL	2025-10-16 11:15:31 +02:00
itsrubberduck	87b2e3b215	merge	2025-10-12 15:42:18 +02:00
Remi	0bcaf85c23	Add waitlist invitation sending from admin	2025-10-07 12:34:02 +02:00
Remi	5e519cfd03	Simplify decision routing to avoid unnecessary LLM calls	2025-09-25 23:47:05 +02:00
Remi	648003184e	Align regex auto selection trace with LLM decisions	2025-09-25 23:35:23 +02:00
Remi	66121fc4fa	Refactor route decision selection	2025-09-25 23:00:31 +02:00
Remi	e3c76f452c	Point bridge download to GitHub	2025-09-24 00:01:00 +02:00
Remi	d37b8a631c	Improve flow activation handling and expose active nodes	2025-09-23 23:12:02 +02:00
Remi	ba93c494c9	Add session timeline logging and admin sessions view	2025-09-21 23:08:10 +02:00
Remi	10cae457f9	Enable flow-aware decision routing	2025-09-21 21:16:33 +02:00
Remi	8189e30946	Extend access token lifetime	2025-09-20 20:53:06 +02:00
Remi	cf6748b9bc	Build decision flow editor and runtime integration	2025-09-20 18:33:32 +02:00
itsrubberduck	6999235668	stash	2025-09-20 16:36:35 +02:00
itsrubberduck	59c97d89fc	merge	2025-09-20 09:50:20 +02:00
Remi	9577458482	Fix remaining German comment	2025-09-20 09:46:34 +02:00
Remi	1711ed1e5e	refactor: share llm decision types	2025-09-20 09:27:45 +02:00
Remi	b22b460513	refactor: centralize radio speech normalization	2025-09-19 09:20:04 +02:00
Remi	db4e30292c	Add waitlist admin view and log OpenAI decision traces	2025-09-18 23:30:56 +02:00
Remi	6eb8b98e22	Fix admin notifications formatting	2025-09-18 19:54:04 +02:00
Remi	8a823a4b18	Add readback correction states and improve validation	2025-09-18 19:54:04 +02:00
Remi	de737c5fb7	Refine ATC decision routing and ATIS handling	2025-09-18 19:41:32 +02:00
itsrubberduck	b4710ca0cf	log llm call body	2025-09-18 18:21:01 +02:00
Remi	422035dff7	Add ATIS quick actions and airport frequency data	2025-09-18 18:16:40 +02:00
itsrubberduck	31f3aece9e	add other flights	2025-09-18 18:08:28 +02:00
Remi	3efd64a5b2	Finalize admin tools and transmission fault flow	2025-09-18 14:03:26 +02:00
Remi	e17169655d	Harden runtime config and input validation	2025-09-18 14:03:25 +02:00
Remi	a4b8a0ca2f	Align public messaging and add news banners	2025-09-17 19:22:56 +02:00
itsrubberduck	d033f03f88	merge	2025-09-17 17:27:38 +02:00
Remi	c084e4da3a	Update contact email to info@opensquawk.de	2025-09-17 17:21:12 +02:00
Remi	1741405c3f	Add password reset flow	2025-09-17 16:21:11 +02:00
Remi	e6755d2042	Revise landing messaging and add news feed	2025-09-17 15:44:41 +02:00
Remi	fe66a4c04c	Implement authentication, waitlist, and logging upgrades	2025-09-16 17:28:34 +02:00
itsrubberduck	e155434b57	refactor: update OpenAI TTS integration and cleanup imports ... - index.vue: comment out cockpit simulator image - learn.vue: remove unused imports (useRadioTTS, learnModules) - atc/say.post.ts & utils/normalize.ts: rename openaiOld → normalize, adjust TTS calls, skip ensureDir/writeFile - communicationsEngine.ts: fix atcDecisionTree import path	2025-09-16 16:14:12 +02:00
itsrubberduck	3924bb0b91	even more reduced llm costs but with variables	2025-09-16 13:36:34 +02:00
itsrubberduck	d11633adde	feat(openai): Drastically reduce LLM Tokens ... chore: Optimize the input data sent to the OpenAI API to reduce token usage and improve decision quality. Add quick responses for common pilot utterances like radio checks and emergencies to avoid unnecessary LLM calls. The key changes are: - Use a smaller LLM model (`gpt-5-nano`) to reduce token usage - Optimize the input data by only sending relevant candidate and context information - Implement quick responses for common pilot utterances like radio checks and emergencies - Ensure ATC responses are only included when necessary to reduce token usage	2025-09-16 13:18:57 +02:00
itsrubberduck	059dc656b3	The system now intelligently handles edge cases while maintaining the core decision tree structure. The LLM will follow the schema when possible but can respond naturally when the pilot says something unexpected, making it much more realistic and flexible for training scenarios	2025-09-16 12:38:15 +02:00
itsrubberduck	4b8da310b4	new version of pm using decision tree	2025-09-16 12:23:32 +02:00
itsrubberduck	a9064e0ae3	communcations engine nutzt jetz decision tree	2025-09-16 11:52:37 +02:00
itsrubberduck	bb2e3bd211	claude änderungen	2025-09-15 11:53:50 +02:00
itsrubberduck	4bd7a58953	Track folder with Git LFS	2025-09-15 11:53:39 +02:00
itsrubberduck	d71f0ca8b4	kann ein bisschen normalized sprechen	2025-09-14 23:20:01 +02:00
itsrubberduck	e91c3c6aa9	init	2025-09-14 21:09:47 +02:00