Microsoft-fara

AI/Microsoft-fara

Fork 0

mirror of https://github.com/microsoft/fara.git synced 2026-08-22 02:00:18 +08:00

Commit Graph

Select branches

Hide Pull Requests

SpencerWhitehead-patch-1

ataymano/vllm_start_fix

azhao/webtailbench-results

corby/fix-trajectory-diagnostics-nameerror

corby/port-cp-aware-verifier-and-taxonomy

corby/universal-verifier

corby/webtailbench-rubric-viz

corby/webtailbench-v1-v2-diff

dependabot/pip/src/fara/vllm/transformers-5.0.0rc3

dependabot/pip/src/fara/vllm/vllm-0.20.0

dependabot/pip/webeval/src/webeval/benchmarks/om2w/impl/pillow-12.2.0

dependabot/pip/webeval/transformers-5.0.0rc3

dependabot/pip/webeval/vllm-0.19.0

hmozannar/fara15

husseinmozannar-patch-1

husseinmozannar-patch-2

husseinmozannar-patch-3

husseinmozannar-patch-4

main

multi-round

windows_support

#1

#10

#11

#13

#16

#19

#2

#23

#25

#26

#3

#30

#31

#37

#4

#40

#41

#41

#44

#45

#47

#5

#52

#53

#54

#54

#55

#6

#60

#62

#62

#64

#64

#65

#66

#67

#68

#69

#69

#7

#70

#70

#73

#73

#74

#76

#77

#8

#80

#83

#83

#84

#84

#87

#87

#9

a675d6d61c Fara-1.5: single Fara15Agent, self-contained env/core, updated CLI + README (#80) main Spencer Whitehead 2026-07-22 13:03:30 -04:00
c54f6c2c8a update readme hmozannar/fara15 SpencerWhitehead 2026-07-22 07:43:57 -07:00
08d0363a35 updates Hussein Mozannar 2026-07-17 13:04:48 -07:00
2322f2f674 recover Hussein Mozannar 2026-07-17 13:03:07 -07:00
879afdd82c more cleanup Hussein Mozannar 2026-07-17 12:59:27 -07:00
5c8247a5f2 minor Hussein Mozannar 2026-07-17 12:52:27 -07:00
eda8e982d8 clean up 1 Hussein Mozannar 2026-07-17 12:31:25 -07:00
8e33bdec69 comments Hussein Mozannar 2026-07-17 12:18:04 -07:00
522a9ccbae remove Hussein Mozannar 2026-07-17 12:14:04 -07:00
d58a16cb6a stage1 Hussein Mozannar 2026-07-17 11:46:48 -07:00
16aa6c0007 readme update Hussein Mozannar 2026-07-17 10:32:14 -07:00
5274e1ee06 Delete empty .gitmodules Hussein MozannarandClaude Fable 5 2026-07-17 09:58:20 -07:00
ca3da813b9 Remove unused autogen submodule Hussein MozannarandClaude Fable 5 2026-07-17 09:58:06 -07:00
9b8af39c87 Port CP-aware verifier + error taxonomy (#77) Corby Rosset 2026-06-16 19:27:57 -04:00
c529b48511 llm_helpers: unwrap CreateResult.content defensively (fix Step 9b on gateway) corby/port-cp-aware-verifier-and-taxonomy corbyandClaude Opus 4.8 2026-05-29 12:52:36 -07:00
19224e97da graceful_client: guarantee create() terminates; fix infinite retry hang corbyandClaude Opus 4.8 2026-05-29 12:52:36 -07:00
13f9e77d17 Port CP-aware verifier + error taxonomy from agento_next corbyandClaude Opus 4.7 2026-05-28 13:49:05 -07:00
796ae4f2bf Update README (#76) Hussein Mozannar 2026-05-21 17:27:42 -04:00
29bc9c33a0 Fix formatting in update entry for Fara 1.5 husseinmozannar-patch-4 Hussein Mozannar 2026-05-21 17:27:30 -04:00
1a7ad8384d Update README Hussein Mozannar 2026-05-21 17:26:57 -04:00
8d823d72c3 docs: WebTailBench V1↔V2 diff page + README refresh note (#74) Corby Rosset 2026-05-12 18:22:24 -04:00
80d96b1ffc README: rename split test-v2 -> test_v2 corby/webtailbench-v1-v2-diff corbyandClaude Opus 4.7 2026-05-12 15:16:43 -07:00
406b26d4a3 docs: add WebTailBench V1↔V2 diff page; note refresh in README corbyandClaude Opus 4.7 2026-05-12 15:10:51 -07:00
1b6cb4c540 Bump vllm from 0.10.0 to 0.20.0 in /src/fara/vllm dependabot/pip/src/fara/vllm/vllm-0.20.0 dependabot[bot] 2026-05-06 18:04:00 +00:00
037285473d Bump transformers from 4.53.3 to 5.0.0rc3 in /webeval dependabot/pip/webeval/transformers-5.0.0rc3 dependabot[bot] 2026-04-23 07:42:54 +00:00
4c4664ccd1 Bump vllm from 0.10.0 to 0.19.0 in /webeval dependabot/pip/webeval/vllm-0.19.0 dependabot[bot] 2026-04-23 06:34:39 +00:00
44908264c8 Fix NameError from orphaned TrajectoryDiagnosticsResult reference (#68) Corby Rosset 2026-04-23 01:42:24 -04:00
ea3ce6eac4 Drop leftover TrajectoryDiagnosticsResult reference corby/fix-trajectory-diagnostics-nameerror corbyandClaude Opus 4.7 2026-04-22 22:41:39 -07:00
a92fa12222 WebTailBench results (#67) corby/universal-verifier Corby Rosset 2026-04-23 01:39:55 -04:00
cde2ebcd6d Corby/universal verifier (#66) Corby Rosset 2026-04-23 01:39:12 -04:00
acc14047f0 Remove TrajectoryDiagnosticsResult class Corby Rosset 2026-04-23 01:38:28 -04:00
b0030f7abe Update __init__.py Corby Rosset 2026-04-23 01:33:57 -04:00
7ea1e441c4 Add example_trajectory + expand webeval trajectory-format docs corbyandClaude Opus 4.7 2026-04-22 22:30:04 -07:00
273614e6f4 Update WebTailBench results and success rate definition azhao/webtailbench-results Corby Rosset 2026-04-20 18:13:41 -04:00
3e07b2be83 WebTailBench results Andrew.Zhao 2026-04-19 18:51:37 -07:00
8cd48183e0 Add CUAVerifierBench dataset (build script + README + repo references) corbyandClaude Opus 4.7 2026-04-18 20:01:57 -07:00
9f14b6e340 Universal Verifier (MMRubricAgent) + WebTailBench, autogen-free clients corbyandClaude Opus 4.7 2026-04-18 17:08:58 -07:00
2c27710499 Add WebTailBench rubric comparison visualizer (#65) Corby Rosset 2026-04-17 00:34:52 -04:00
2ec67d7236 Add WebTailBench rubric comparison visualizer corby/webtailbench-rubric-viz corbyandClaude Opus 4.7 2026-04-16 21:12:47 -07:00
83c9789c83 Bump pillow in /webeval/src/webeval/benchmarks/om2w/impl dependabot/pip/webeval/src/webeval/benchmarks/om2w/impl/pillow-12.2.0 dependabot[bot] 2026-04-13 22:29:38 +00:00
1d0b7977c4 Bump transformers from 4.55.0 to 5.0.0rc3 in /src/fara/vllm dependabot/pip/src/fara/vllm/transformers-5.0.0rc3 dependabot[bot] 2026-04-08 08:00:04 +00:00
0aa8a48430 update README (#52) Spencer Whitehead 2026-01-14 15:09:53 -05:00
e648c0e844 update README Andrew Zhao 2026-01-14 15:03:24 -05:00
6261cdb6fc Add citation for Fara-7B in README (#47) Hussein Mozannar 2025-12-15 11:33:48 -05:00
76f38253e9 Add citation for Fara-7B in README SpencerWhitehead-patch-1 Spencer Whitehead 2025-12-15 11:17:43 -05:00
3f3f1fd82c docs: fix typos and formatting in README (#44) Hussein Mozannar 2025-12-10 12:08:47 -05:00
9d7efb0e11 Fix typos and enhance clarity in README.md Mehul Jariwala 2025-12-10 10:52:24 +05:30
6cbb4f3694 Windows Support (#40) Hussein Mozannar 2025-12-03 17:28:43 -05:00
82637b54df fixes windows_support Hussein Mozannar 2025-12-02 14:01:05 -08:00
879dc9561a online mind2web works (#23) Corby Rosset 2025-12-02 00:16:35 -05:00
a3e2750c6a Merge branch 'main' into corby/om2w corby 2025-12-01 21:13:43 -08:00
5ebe2590f8 Update README with Magentic-UI instructions (#37) Hussein Mozannar 2025-11-28 20:49:34 -05:00
5745ea715f Enhance README with video demos for Magentic-UI husseinmozannar-patch-3 Hussein Mozannar 2025-11-28 20:49:18 -05:00
2b81016788 Update README with Magentic-UI instructions Hussein Mozannar 2025-11-28 20:48:25 -05:00
f10b9319b3 Refine Fara-7B description in README (#31) Hussein Mozannar 2025-11-28 14:30:48 -05:00
ccdc3def6e Refine Fara-7B description in README husseinmozannar-patch-2 Hussein Mozannar 2025-11-28 14:30:31 -05:00
21469308d6 Update README with Windows and memory usage notes (#30) Hussein Mozannar 2025-11-28 13:35:43 -05:00
b555f0874b Update README with Windows and memory usage notes husseinmozannar-patch-1 Hussein Mozannar 2025-11-28 13:34:46 -05:00
01f8a17ffd forgot om2w score file type corby 2025-11-27 11:37:43 -08:00
ca1d3868f4 fix(fara-cli): refactor logging for action execution in FaraAgent (#25) Wassim Chegham 2025-11-26 16:39:45 +01:00
1d6d1d64a6 online mind2web works corby 2025-11-25 22:47:53 -08:00
222c2a38e7 Multi round Fara fix (#16) Corby Rosset 2025-11-25 23:49:56 -05:00
f71083c9bd other fixes to webeval multi-round corby 2025-11-25 20:47:34 -08:00
3fa15aa99a split to two devices corby 2025-11-25 20:04:24 -08:00
2816cb10a3 update cli Hussein Mozannar 2025-11-25 15:40:56 -08:00
c2472e5a37 nicer experience Hussein Mozannar 2025-11-25 15:22:42 -08:00
d330c93b22 use logging Hussein Mozannar 2025-11-25 14:59:49 -08:00
9238221c15 small fix Hussein Mozannar 2025-11-25 14:13:35 -08:00
d18cd7b675 Merge branch 'main' into multi-round Hussein Mozannar 2025-11-25 16:45:27 -05:00
4b093dd243 self-hosted scenario fix (#13) Alexey Taymanov 2025-11-24 23:12:38 -05:00
1d0e145150 revert back az vllm Hussein Mozannar 2025-11-25 13:39:54 -08:00
e6a0174662 fix multi-turn Hussein Mozannar 2025-11-25 13:36:24 -08:00
38c58ca681 cleanup 1 Hussein Mozannar 2025-11-25 13:03:48 -08:00
2606c8e1c4 self-hosted scenario fix (#13) Alexey Taymanov 2025-11-24 23:12:38 -05:00
b37cd4eb33 readme update ataymano/vllm_start_fix Alexey Taymanov 2025-11-25 03:33:00 +00:00
9edb064d9c vllm config Alexey Taymanov 2025-11-25 03:28:48 +00:00
0e6f814167 vllm requirements Alexey Taymanov 2025-11-25 03:28:20 +00:00
40824d9491 import fix Alexey Taymanov 2025-11-25 03:25:36 +00:00
ff0dbac1d1 Initial commit ataymano@microsoft.com 2025-11-24 10:32:01 -05:00

1 2