Commit graph

379 commits

Author SHA1 Message Date
Dakota
d3e6ddddbc fixed pre-commit :) 2025-06-12 10:12:49 -05:00
teknium1
7a89524345 add readme section for the environment 2025-06-12 00:36:03 -07:00
teknium1
4a7e5b2b7c Many updates 2025-06-12 00:32:50 -07:00
teknium1
199ae15d0b initital letter counting environment 2025-06-11 15:27:21 -07:00
dmahan93
a26794afd2
Merge pull request #168 from maximevtush/main
Minor Fixes: Typo Correction in README and Message Clarification in Tasks
2025-06-09 14:24:07 -05:00
Dakota
e13526d308 Fix API to accept messages without reward field + comprehensive tests
- Made reward field truly optional in messages (no auto-addition)
- Accept custom roles (dog, cat, etc.) beyond standard ones
- Added 24 new tests for edge cases (tuples, unicode, large content)
- Reorganized test structure: moved from testing/ to atroposlib/tests/
- Fixed legacy API tests and removed tests requiring missing data files

All 43 tests pass\! Fixes message handling for SFT use cases.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-06-09 14:03:08 -05:00
Maxim Evtush
16bd33284f
Update tasks.py 2025-06-09 15:39:58 +02:00
Maxim Evtush
d0913d187b
Update README.md 2025-06-09 15:39:04 +02:00
teknium1
f999f90627 add support for composite task 2025-06-08 04:39:50 -07:00
teknium1
398e3ddeaa add randomization for complexity as well as curriculum support 2025-06-08 03:07:07 -07:00
teknium1
a4b22c38d7 make eval vars config options 2025-06-06 15:24:00 -07:00
teknium1
be94857084 add seed to default configs for clarity 2025-06-06 14:56:55 -07:00
teknium1
79188d8d6a Add reasoning gym env 2025-06-05 17:30:25 -07:00
Dakota
61fdc37f61 Replace isort with ruff for import sorting
- Update pre-commit config to use ruff with --select=I for imports only
- Apply ruff import sorting to fix pre-commit issues
- Ruff and black work together without conflicts
2025-06-04 11:28:30 -05:00
Dakota
55cdb83cbf Update pre-commit hooks to latest versions and fix issues
- Update pre-commit hooks: v5.0.0, black 25.1.0, isort 6.0.1, flake8 7.2.0
- Fix isort import ordering in lean_proof_env.py
- Fix flake8 F824 false positive in spatial_env.py with noqa comment
2025-06-04 10:58:37 -05:00
Dakota
f3bbc6a42d Fix import ordering with isort
- Move typing_extensions import to proper location
- Satisfy pre-commit isort requirements
2025-06-04 10:40:41 -05:00
Teknium
eaf1e8e667
Merge pull request #157 from NousResearch/add-struct-output-pydantic-validator-environment
Add Pydantic Schema to Structured Output Environment
2025-06-04 02:10:44 -07:00
teknium1
49adab3f4b Cleanup 2025-06-03 16:10:59 -07:00
teknium1
aa3d01e5ea Add YAML and TOML support, experimental XML support, add multi-format randomizer 2025-06-03 15:06:21 -07:00
teknium1
e359a72b06 add pydantic schema environment 2025-06-02 16:58:12 -07:00
kilavvy
39261643dc
Update open_robot_env.py 2025-06-02 13:56:48 +02:00
kilavvy
33b8e39599
Update README.md 2025-06-02 13:55:02 +02:00
Teknium
134a9713ce
Merge pull request #147 from zeevick10/main
Fix Typos in MCP Tool Calling Environment Documentation
2025-06-01 14:24:54 -07:00
Emmanuel Ferdman
2bc9111139
Fix contribution guide source
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
2025-05-31 13:18:17 -07:00
shannonsands
283877dd88
Intern bootcamp env (#146)
* Created registry and started off the env

* Local testing works

* process working but error in gen

* removed old code

* adding debug, it's still not progressing to collect trajectories

* linting

* removed redundant settings
2025-05-31 11:22:59 +10:00
FT
20a90764ac
Update README.md 2025-05-28 14:33:48 +02:00
shannonsands
ea304892ee
Integrate chinguun101 goofy math (#145)
* Add GoofyMath environment for fun, engaging math learning

* linting, moved to community folder

* linting

---------

Co-authored-by: chinguun101 <chinguun@uni.minerva.edu>
2025-05-28 12:11:02 +10:00
shannonsands
1a79132809
Integrate michaelwaves options iv (#144)
* options iv agent

* bug fix

* outputs

* linted and moved to community folder

* linting

---------

Co-authored-by: michaelwaves <michaelyu713705@gmail.com>
2025-05-28 10:57:24 +10:00
fuder.eth
1862b193ee
Update README.md (#118) 2025-05-28 10:24:12 +10:00
shannonsands
f21154ff49
Integrate aniemerg wikipedia (#143)
* initial commit

* initial draft of wikipedia article creation environment

* add openai for rollouts, update requirements, create script to run, etc.

* add configuration, add debugging, fix tool calls, prevent wikipedia access

* now creates html file

* fix output for html page

* check in Claude plan

* fixed formatting and other issues

* add zip file

* update README

* linting, moved to community folder

* linting

* linting

* linting

* linting

---------

Co-authored-by: Allan Niemerg <niemerg@gmail.com>
2025-05-28 10:22:11 +10:00
shannonsands
b774e97215
Integrate subrahmanyam cybersecurity (#142)
* cybersecurity env for offline RL trajectories

* output file addition

* jsonl outputs

* code cleanup

* pulled out outputs and fixing .gitignore

* removed zip file

* gitignore typo fix

* Integrate cybersecurity Sigma rule generation environment

---------

Co-authored-by: Subrahmanyam Arunachalam <subrahmanyam.arunachalam@FVFGK0VTQ05P.local>
2025-05-28 08:41:51 +10:00
Shannon Sands
d2fb30c4d0 linting 2025-05-27 16:36:14 +10:00
Shannon Sands
6acb4cc91a linting 2025-05-27 16:34:52 +10:00
Shannon Sands
e37e02a94c linting, moved env to community folder 2025-05-27 16:30:11 +10:00
Shannon Sands
a403b16ec4 commiting 2025-05-27 16:18:26 +10:00
Shannon Sands
a6ac7a3e42 linting and moved to community 2025-05-27 16:04:50 +10:00
Shannon Sands
8df34efc56 Resolve merge conflict in .gitignore 2025-05-27 15:56:22 +10:00
Shannon Sands
8f08a398c0 linting 2025-05-27 15:46:10 +10:00
Shannon Sands
a353bb6eb1 linting 2025-05-27 15:45:07 +10:00
Shannon Sands
e7e747a396 linting 2025-05-27 15:43:12 +10:00
Shannon Sands
2efb690a24 linting, moved to community 2025-05-27 15:36:24 +10:00
Shannon Sands
33d5e4a25e linting 2025-05-27 15:12:14 +10:00
Shannon Sands
eba7aac72b linting, moving files into community subdirectory 2025-05-27 15:08:30 +10:00
Shannon Sands
d3803f62f2 Fix trailing whitespace in community README 2025-05-27 13:58:40 +10:00
Shannon Sands
f8912ae41d linting, moved to community folder 2025-05-27 13:50:43 +10:00
Shannon Sands
c6a0439ec6 Integrate Sanskrit Poetry Environment from KhoomeiK - Add ChandasMeterReward to reward function registry - Move sanskrit_poetry_env.py to environments/community/sanskrit_poetry/ - Add comprehensive documentation as entry #25 in community README - Environment supports traditional Sanskrit meter validation using chandas classifier - Includes IAST to SLP1 transliteration for accurate meter analysis - Fixed code formatting with pre-commit hooks 2025-05-27 13:29:45 +10:00
Shannon Sands
f789e01347 more linting 2025-05-27 13:15:26 +10:00
Shannon Sands
b82e23f11d more linting 2025-05-27 13:14:01 +10:00
Shannon Sands
54e574d350 more linting 2025-05-27 13:11:36 +10:00
Shannon Sands
89b38a233b more linting 2025-05-27 13:09:07 +10:00