88 Commits

Author	SHA1	Message	Date
Adam Wilson	cc124a91a3	support batch tests	2025-08-19 20:09:34 -06:00
Adam Wilson	75c048c00d	:(	2025-08-05 15:07:37 -06:00
Adam Wilson	28518e6c17	fixes for basic prompt template	2025-07-30 07:17:48 -06:00
Adam Wilson	51e966e1ec	escape braces	2025-07-28 14:55:32 -06:00
Adam Wilson	058b281f25	default risk threshold; scores lower down in JSON serialization	2025-07-28 13:40:54 -06:00
Adam Wilson	d39d7f1f1f	don't send back alternate after guidelines	2025-07-28 13:29:21 -06:00
Adam Wilson	393b76faf4	small fix	2025-07-28 13:19:50 -06:00
Adam Wilson	bc119ed50e	don't overprocess results	2025-07-28 13:10:03 -06:00
Adam Wilson	24e28c0182	fix JSON serialization for logging test result	2025-07-28 12:06:56 -06:00
Adam Wilson	df14a01fe9	log full completion result with semantic similarity comparison results	2025-07-28 11:49:07 -06:00
Adam Wilson	b971df0a7a	risk threshold is too low	2025-07-28 10:47:57 -06:00
Adam Wilson	2659e6e43c	more updates for reflexion	2025-07-28 10:31:55 -06:00
Adam Wilson	5bc9f480f9	all domain unit tests pass	2025-07-27 18:53:30 -06:00
Adam Wilson	a621ad82a9	Reflexion guardrails updates	2025-07-27 16:39:06 -06:00
Adam Wilson	99ec0ddf98	WIP reflexion service	2025-07-27 13:59:01 -06:00
Adam Wilson	eddacd87fa	LLM config output	2025-07-27 11:21:12 -06:00
Adam Wilson	a7a6873e73	update prompt templates; support LLM config logging	2025-07-26 22:10:04 -06:00
Adam Wilson	5b27d4c2e3	refactor for examples	2025-07-26 16:31:49 -06:00
Adam Wilson	27dad236ef	avoid unclosed curly braces	2025-07-26 15:50:10 -06:00
Adam Wilson	16ba9c15ee	test output for test_02_malicious_prompts	2025-07-26 08:22:35 -06:00
Adam Wilson	741629908c	updates for RAG + CoT tests	2025-07-25 18:11:49 -06:00
Adam Wilson	72785c6420	updates for RAG + CoT	2025-07-25 17:24:01 -06:00
Adam Wilson	a770a5211c	create/update all Phi-3 templates	2025-07-25 16:35:19 -06:00
Adam Wilson	d15e9d6794	more test and template setup	2025-07-25 09:45:03 -06:00
Adam Wilson	3a62ecfae8	add test 0 results	2025-07-25 08:47:56 -06:00
Adam Wilson	85d33feffe	comment	2025-07-24 20:46:28 -06:00
Adam Wilson	4f2e539996	updates	2025-07-24 18:51:18 -06:00
Adam Wilson	ae279a512d	log LLM config	2025-07-23 20:21:42 -06:00
Adam Wilson	cb92890bb9	break tests into separate files; test 0 results	2025-07-23 19:06:27 -06:00
Adam Wilson	91afa1e7e4	test run logs	2025-07-19 15:19:28 -06:00
Adam Wilson	296669ac49	add env var for prompt template dir; error handling	2025-07-19 07:59:54 -06:00
Adam Wilson	41afb99622	dependency fixes, test setup	2025-07-18 18:18:56 -06:00
Adam Wilson	7f77e82a5c	guidelines close to complete; prior to tests	2025-07-18 13:48:19 -06:00
Adam Wilson	fec4d711bf	implement singular guidelines calls in main service	2025-07-18 12:33:51 -06:00
Adam Wilson	c1b4a130f9	base service class	2025-07-17 20:32:13 -06:00
Adam Wilson	f3dd8e9208	more for templates	2025-07-16 21:07:37 -06:00
Adam Wilson	1dba565236	service implementations	2025-07-16 20:21:10 -06:00
Adam Wilson	cd0e4b9de9	building guidelines services	2025-07-15 21:19:28 -06:00
Adam Wilson	51cce1545a	few shot template WIP	2025-07-12 20:35:43 -06:00
Adam Wilson	c788431416	prompt template IDs; fluent text generation service stubs	2025-07-12 12:18:19 -06:00
Adam Wilson	36820f9c54	pseudo-code for fluent text generation service call	2025-07-11 15:51:01 -06:00
Adam Wilson	a647060644	skip guidelines method; stubs for service calls in test class	2025-07-10 07:10:26 -06:00
Adam Wilson	b4b2d792fc	more progress on fluent service call	2025-07-09 21:56:44 -06:00
Adam Wilson	5470554d28	stub for fluent guidelines service	2025-07-08 17:18:57 -06:00
Adam Wilson	af75e9aabf	support prompt template loading	2025-07-07 21:38:42 -06:00
Adam Wilson	7d49d160b9	more test cases and notes	2025-07-06 17:47:49 -06:00
Adam Wilson	ffa2d73ae0	guardrail analyzed response, etc.	2025-07-06 15:15:59 -06:00
Adam Wilson	a1d3a8c1b7	adjust assertions for test 3	2025-07-05 20:21:35 -06:00
Adam Wilson	640c261b26	naming updates; fix static analysis script	2025-07-05 13:01:28 -06:00
Adam Wilson	cb1be6746f	support testing malicious prompts with no guidelines	2025-06-28 12:18:35 -06:00