Commit Graph

440 Commits

Author SHA1 Message Date
Mery-Sanz f42c84490d Merge branch 'issue_66' of https://gitlab.com/aliasrobotics/alias_research/cai into issue_66 2025-05-05 08:07:18 +02:00
lidia9 4630b20d88 FIX guardrails.py 2025-05-02 16:29:59 +02:00
lidia9 5de9838f3e LLM_as_judge.py - Some fixes for qwen to work - I commit plenty of prints for the future, they will be all removed 2025-04-30 16:55:11 +02:00
lidia9 ff253e183a LLM AS A JUDGE - works for anthropic 2025-04-30 16:00:50 +02:00
lidia9 7311f48421 small fix - now llm as judge works for openai llms 2025-04-30 15:08:24 +02:00
Mery-Sanz 794760909d Merge branch 'v0.4.0' into issue_66 2025-04-30 13:44:31 +02:00
Luis Javier Navarrete Lozano d9afaf7c54 Merge branch 'port_ui' into 'v0.4.0'
Make UI same as in v3

See merge request aliasrobotics/alias_research/cai!147
2025-04-30 11:12:57 +00:00
lidia9 fcb67c5fcb adding fake openai api key 2025-04-30 12:35:40 +02:00
lidia9 9d3d410380 fix common.py to avoid START_TIME import from cli in common.py 2025-04-30 12:22:24 +02:00
lidia9 04795c1699 Fix START_TIME import for tests - ci 2025-04-30 12:18:47 +02:00
lidia9 cee7940599 undo openai api key name 2025-04-30 11:51:54 +02:00
lidia9 0eece93b5e test: set same OPENAI_API_KEY for tests.yml and ci 2025-04-30 11:47:37 +02:00
lidia9 66b4d7165e remove set disable in test 2025-04-30 11:41:40 +02:00
Mery-Sanz 1669254b5c tracing disabled 2025-04-30 11:37:06 +02:00
Mery-Sanz 29bd69d08f function tool time in stream true 2025-04-30 10:30:48 +02:00
Mery-Sanz 78ececb4cb solve tool output in stram, wrong total time 2025-04-30 10:13:41 +02:00
Mery-Sanz 0894451d6f fix 2025-04-30 09:42:42 +02:00
Mery-Sanz 5c5b415ab3 fix time summary 2025-04-30 07:55:03 +02:00
Mery-Sanz 1f3750fb2d add total time but check it 2025-04-29 18:13:53 +02:00
Mery-Sanz c289067dde add Tool output seconds 2025-04-29 17:50:51 +02:00
lidia9 a149a64ca3 FIX UI - visualizatio of tool call + total time 2025-04-29 17:05:08 +02:00
lidia9 efccf38d77 Fix visualization UI - tool call output args 2025-04-29 15:12:35 +02:00
lidia9 41610dbbdd generic_linux_command fix for CAI_STREAM=true 2025-04-29 14:25:43 +02:00
lidia9 baa4be58c1 un-hardcode generic_linux command as default 2025-04-29 14:20:09 +02:00
lidia9 ae47d113ce for empty messages do not display token info 2025-04-29 13:09:14 +02:00
Mery-Sanz 540100d2f1 fix 2025-04-29 12:52:41 +02:00
Mery-Sanz 35cbc4adcd add sumary time session 2025-04-29 12:47:51 +02:00
Mery-Sanz 3e9401057a add quick start guide 2025-04-29 11:01:57 +02:00
lidia9 c3b447b624 remove new line in ui 2025-04-29 10:52:13 +02:00
lidia9 0bad360ebe remove Thinking message 2025-04-29 10:50:51 +02:00
Mery-Sanz aceb9274f4 test functionalities 2025-04-29 10:30:34 +02:00
Li 59c544534c Merge branch 'v0.4.0_instrument_toolcall' into 'v0.4.0'
V0.4.0 instrument toolcall - peer reviewed with @Mery-Sanz

See merge request aliasrobotics/alias_research/cai!143
2025-04-25 11:19:47 +00:00
Mery-Sanz 3201e6ce48 fix ctrl+c 2025-04-25 12:41:54 +02:00
lidia9 7d6ddd3a4f tool output streaming works 2025-04-25 12:35:56 +02:00
lidia9 734ef479f4 FIX streaming output tool - still some visualization duplicates 2025-04-25 10:33:12 +02:00
Mery-Sanz c5f6826af0 Merge branch 'issue_62' into 'v0.4.0'
Review agents

See merge request aliasrobotics/alias_research/cai!142
2025-04-24 08:31:47 +00:00
lidia9 ac9135b75e remove prints 2025-04-23 12:28:47 +00:00
Mery-Sanz 525a70961b remove env vairble 2025-04-23 14:15:13 +02:00
Mery-Sanz a6f01865dd remove agent inferece test 2025-04-23 14:14:08 +02:00
lidia9 b6457bb329 UI - fix display metrics, token count, pricing, session cost - REMOVE some prints 2025-04-23 10:03:51 +00:00
lidia9 960215976b UI - fix display metrics, token count, pricing, session cost and so on 2025-04-23 09:58:29 +00:00
Mery-Sanz 43c3a71c6d try fake api key 2025-04-23 11:32:53 +02:00
Mery-Sanz dd31d91af4 add fake api key for test 2025-04-23 09:16:32 +02:00
Mery-Sanz 2eb2eb7a59 final fiz 2025-04-23 09:04:48 +02:00
Mery-Sanz 1ecb90eaa2 fix test name 2025-04-23 08:12:09 +02:00
lidia9 f21b8119e7 FIX UI - remove duplicated tool call print 2025-04-22 15:17:14 +00:00
lidia9 58872b6667 FIX UI - CAI_STREAM=false - one panel for each message, tool call, output 2025-04-22 15:12:49 +00:00
Mery-Sanz aa6ea56ca8 add test to ci 2025-04-22 16:58:07 +02:00
Mery-Sanz dae41dbba7 add test 2025-04-22 16:48:12 +02:00
Mery-Sanz 702a93b6c3 fix agent and add primary test 2025-04-22 16:32:26 +02:00