f71a005d55
refactor: privatize remain_time_duration and use remain_time() ( #1027 )
2025-07-07 18:52:17 +08:00
a0015c1511
chore: sort trace by loop_id ( #977 )
...
* last as sota to submit
* chore: sort trace by loop_id
* Update rdagent/log/ui/utils.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* reformat
* update _log_path_hash_func
* compare sota_exp_to_submit
* fix ui storage
* move sota_exp_to_submit setting to record(from direct_exp_gen)
* save sota_exp_to_submit
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
Co-authored-by: Bowen Xian <xianbowen@outlook.com >
2025-07-07 17:08:55 +08:00
ea86b537eb
fix: support experimental support for Deepseek models and update docs about configuration ( #1024 )
...
* fix qlib running bug for deepseek and add configuration docs about deepseek
2025-07-07 14:18:56 +08:00
4bf16d03cf
chore: restore parameter timeout in loop ( #1022 )
...
* restore parameter timeout in loop
2025-07-05 14:55:26 +08:00
6dbef13837
chore: document APIBackend parameters and remove sparse dep ( #1019 )
2025-07-04 20:31:06 +08:00
eff5dcc879
add trace DAG in trace, make exp show compatible with old versions ( #1018 )
2025-07-04 15:47:45 +08:00
4608a0c63e
feat: try coder on whole data ( #1017 )
...
* commit all code
* fix feedback bug
* add debug mode in ds
* update prompt
* prioritize performance than time lit
* use run instead
* store running time
* move all data running into running phase
* fix a bug
* use sample data as default
---------
Co-authored-by: Xu Yang <xuyang1@microsoft.com >
2025-07-04 14:30:40 +08:00
6e57d0adc4
chore: ui server updates ( #951 )
...
* ui server update
* update
* fix bugs
* updates
* use randomname
* fix
* fix bugs
* change time interval in debug server
* some change
* fix CI
* time interval change
* updates
* some changes
* fix
* fix curves
* one IP, one pointers to show msgs return progress
* enable /control
* fix bugs
* fix CI
* fix isort
2025-07-04 12:32:14 +08:00
76660b1ace
feat: show first evo round codes diff ( #1009 )
...
* log settings
* add first diff in evolving
* save dict settings
* load settings in data science ui
2025-07-03 19:21:14 +08:00
05bb19ad4b
docs: add README for exp_gen folder structure proposal ( #1010 )
...
* docs: add README for exp_gen folder structure proposal
* docs: update README with tool strategy and adjust folder structure
* docs: rename 'Tool strategy' section to 'Tools' in exp_gen README
2025-07-03 11:31:51 +08:00
7a7f865733
refactor: replace run_ret_code with run and adjust helper methods ( #1013 )
2025-07-03 11:24:05 +08:00
92bb49fc8f
fix: fix a minor bug in DS eval ( #1012 )
2025-07-02 23:31:29 +08:00
a67ec5ba01
chore: add devcontainer Dockerfile, devcontainer.json, and env ( #997 )
...
* chore: add devcontainer Dockerfile, devcontainer.json, and env
* style: remove unnecessary comment on ENABLE_CACHE setting
* docs: add internal devcontainer README with setup instructions
* Update README in .devcontainer based on PR #997
---------
Co-authored-by: jingyuanlm <842442862@qq.com >
2025-07-02 18:54:49 +08:00
c4007b4655
chore: sample data map ( #1005 )
...
* chore: map data sampler
2025-07-02 15:11:57 +08:00
3d227787e8
feat: added running time statistics for the DS scenario experiment ( #1007 )
...
* added running time statistics for the DS scenario experiment
* update execute_ret_code to return running_time
* fix
* fix
* update describe
* add EnvResult
* update corresponding calls
* add RunningInfo class
* fix
* fix
* fix
* fix ci
* rename function name
* fix ci
* fix
* refine running_time logic
* fix ci
2025-07-02 15:11:18 +08:00
92ce8a898b
add code diff in evolving window ( #1008 )
2025-06-30 20:10:34 +08:00
55f7ccc93d
feat: add hide_base_name option and update data folder prompts ( #1004 )
...
* feat: add hide_base_name option and update data folder prompts
* rename folder
2025-06-29 21:22:16 +08:00
49aec3135e
feat: add code change summary ( #1000 )
...
* feat: add code change summary and dict_get_with_warning util
* feat: support code_change_summary in feedback classes
* lint
* feat: validate response_format using BaseModel and warn unknown formats
2025-06-29 13:40:15 +08:00
69500fc52d
refactor: convert data describe functions to class-based implementation and add output example ( #999 )
...
* feat: Enhance data folder description for clarity and robustness
* fix bug
* fix present bugs
* delete useless files
* add output example and refactor the hole util.py
* fix bug for file tree
* add corner case example
* delete useless file
2025-06-28 21:23:40 +08:00
d89fb2a82e
chore: release 0.6.1
...
Release-As: 0.6.1
2025-06-28 20:06:57 +08:00
976b86664f
fix: fix mount ( #1001 )
...
* docs: document extra_volumes dict format in DockerConf
* feat: accept dict values in extra_volumes to specify bind and mode
* fix: skip invalid PDF reports to prevent infinite loop
* from break to raise self.LoopTerminationError
* format with black
---------
Co-authored-by: Young <afe.young@gmail.com >
2025-06-28 20:01:14 +08:00
05b584b184
fix: handle the bug of wrong dag_parant index ( #996 )
...
* fix the dag_parant_index bug caused by the wrong calling order of
* auto-lint
2025-06-27 17:01:29 +08:00
c701a8105b
fix: improve log folder sorting and selection UX ( #993 )
...
* fix ui
* update
2025-06-27 11:38:05 +08:00
f075824a16
chore: release 0.6.0
...
Release-As: 0.6.0
2025-06-26 22:32:15 +08:00
5c5508c8cc
fix: add async to direct_exp_gen avoid infinite loop ( #992 )
...
* refactor: convert direct_exp_gen to async and enforce parallel limit
* fix bug
* change coroutine function position
* fix fin_quant's direct_exp_gen
* format with isort
---------
Co-authored-by: Bowen Xian <xianbowen@outlook.com >
Co-authored-by: SunsetWolf <Lv.Linlang@hotmail.com >
2025-06-26 22:10:52 +08:00
a5c5c7172b
feat: async mechanism for multi-trace ( #981 )
...
* start to work on multi-trace + async
* init ver of async-multi-tarce, to test
* add eng-ver log
* complete version of async+ mul-trace
* debug
* fix bug on DS_RD_SETTING.get()
* update
* fix bug + simplif the usage of async in multi-trace
* fix mini bug of arg_name
* Move local_selection into class Experiment & clean the code
2025-06-26 15:49:47 +08:00
58b5cc1458
fix: refine prompt ( #987 )
...
* refactor: rename failed_exp_and_feedback_list to include _after_sota suffix
* refactor: merge prompts_v3 into prompts_v2 and update references
2025-06-26 12:08:31 +08:00
80d81c8ea9
support tar in dataset & fix a small bug in loop ( #986 )
...
Co-authored-by: Xu Yang <xuyang1@microsoft.com >
2025-06-25 15:32:37 +08:00
1b762ceddd
fix LLM log bug ( #985 )
2025-06-25 10:38:20 +08:00
ed84b6b0a3
chore: merge with more trace ( #982 )
...
* merge support more traces
* use feedback from all traces
2025-06-24 10:47:45 +08:00
46367e15f5
fix: refine details ( #979 )
...
* feat: add parquet preview and extract common DataFrame preview logic
* refactor: improve error messages, prompts, regex, and session loading
* lint
2025-06-23 10:38:27 +08:00
0859b9f3a2
fix: fix a bug and update the docs ( #978 )
2025-06-20 10:58:14 +08:00
e03fca3206
fix: docker container cleanup to prevent accumulation and system slowdown ( #975 )
...
* Initial plan for issue
* Fix Docker container cleanup issue by using try-finally block
Co-authored-by: peteryang1 <25981102+peteryang1@users.noreply.github.com >
* Fix additional Docker container leaks in health_check and GPU test functions
Co-authored-by: peteryang1 <25981102+peteryang1@users.noreply.github.com >
* Remove temporary test files and finalize Docker container cleanup fix
Co-authored-by: peteryang1 <25981102+peteryang1@users.noreply.github.com >
* Refactor container cleanup code to reduce duplication as requested in review feedback
Co-authored-by: peteryang1 <25981102+peteryang1@users.noreply.github.com >
* Refactor container cleanup to use shared function and always stop before remove
Co-authored-by: peteryang1 <25981102+peteryang1@users.noreply.github.com >
* fix CI
* Fix mypy type checking errors for Docker container cleanup
Co-authored-by: peteryang1 <25981102+peteryang1@users.noreply.github.com >
* fix CI
* Remove unnecessary _cleanup_container wrapper method in DockerEnv class
Co-authored-by: peteryang1 <25981102+peteryang1@users.noreply.github.com >
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com >
Co-authored-by: peteryang1 <25981102+peteryang1@users.noreply.github.com >
Co-authored-by: Xu Yang <xuyang1@microsoft.com >
2025-06-19 18:32:50 +08:00
977136f1f3
fix: merge datascience v3 and v2 ( #974 )
...
* add coder version
* merge cooder and feedback prompts
* align v2 and v3 proposal prompts
* fix a small bug
* fix a bug
* fix another bug
* support both function calling and json mode in v2 proposal
* fix minor bug
* reformat
* remove proposal v3
* fix a small bug in json mode
* fix CI
* remove tmp file
* remove v3 check
---------
Co-authored-by: Xu Yang <xuyang1@microsoft.com >
2025-06-19 13:25:10 +08:00
bf9efe127d
chore: release 0.5.0
...
Release-As: 0.5.0
2025-06-18 15:08:11 +08:00
243d5259f7
docs: update readme for v0.5.0 release ( #973 )
2025-06-18 14:49:24 +08:00
dd10ddf9fd
fix: main bug ( #938 )
...
* feat: parameterize cache paths with USER to avoid conflicts
* guide for missing training_hyperparameters
* guidance for KeyError: 'concise_reason'
* fixed three bugs in the test
* fix general_model task bug
* fixed some bugs in the med_model scenario
* delete comments
* format with black
* fix mypy error
* fix ruff error
* fix isort error
* sync code
* revert cache_path code
* revert cache_path code
* delete data mining scenario
* fix factor report loop
* fix LiteLLMAPIBackend log_llm_chat_content setting
* refine fin factor report scenario
* remove unused LogColors
* fix UI
* remove medical scenario docs
* change **kaggle** to **data_science**
* remove default dataset_path in create_debug_data
* remove KAGGLE_SETTINGS in kaggle_crawler
* limit litellm versions
* reformat with black
* change README
* fix_data_science_docs
* make hypothesis observations string
* Hiding old versions of kaggle docs
* hidding kaggle agent docs
---------
Co-authored-by: Young <afe.young@gmail.com >
Co-authored-by: Bowen Xian <xianbowen@outlook.com >
Co-authored-by: yuanteli <1957922024@qq.com >
2025-06-18 14:35:45 +08:00
a619ff999b
refactor: refactor RD-Agent(Q) configuration files ( #972 )
...
* refactor rdagent(q) conf files
* fix
* fix ci
2025-06-18 12:28:29 +08:00
c215e735c2
fix: use simple stdout and stderr ( #966 )
...
* use simple stdout and stderr
* add live_output config in LocalConf
2025-06-18 11:54:27 +08:00
0c219b81e0
docs: update the documentation for custom dataset ( #969 )
2025-06-18 10:58:28 +08:00
9f793d58b3
fix: get_metric_direction for aerial-cactus-identification ( #970 )
2025-06-17 18:06:38 +08:00
f0deace7a7
docs: add readme for custom data in R&D Agent DS scenario ( #968 )
2025-06-17 16:29:07 +08:00
682f657637
chore: break when loop_n runs out ( #964 )
...
* raise loop termination in execute_loop
* add SENTINEL
2025-06-17 15:46:38 +08:00
af5898211b
refactor: add custom data setting for data science scene ( #967 )
...
* add custom data setting for the data science scene
* fix ci?
* fix ci
* add custom data as an example
* fix ci
* add package
* fix test_import ci error
2025-06-17 14:55:11 +08:00
1a1e88c47c
fix: log info ( #965 )
...
* fix log caller_info
* make env info beauty
2025-06-16 19:52:44 +08:00
9890bb4b00
docs: update explanation for separate config use in litellm ( #958 )
...
* docs: update explanation for separate config use in litellm
* docs: update default backend to `rdagent.oai.backend.LiteLLMAPIBackend`
* docs: update .rst format
* Update installation_and_configuration.rst
2025-06-13 18:32:39 +08:00
5a3a2bf2be
chore: remove redundant tag in old scenarios ( #917 )
...
* remove state.times in old ui
* remove "r" tag
* remove "d" tag
* remove "ef" tag
* remove "init" tag
* fix CI
* remove old tag in app UI
* fix bugs
* fix CI
* some updates
* filter tags
2025-06-13 17:49:58 +08:00
77e9f186d5
fix: add missing semicolon after chmod in env shell command ( #955 )
2025-06-12 21:02:07 +08:00
2187081905
feat: replace hard-coded cache paths with dynamic cache_path config ( #952 )
...
* feat: replace hard-coded cache paths with dynamic cache_path config
* style: reorder wait_retry import and format chmod list
* refactor: pass workspace_path to chmod command and use DockerConf check
2025-06-12 17:44:31 +08:00
698f89e07c
print out the qlib data generation error message to help user find the problem ( #954 )
...
Co-authored-by: Xu Yang <xuyang1@microsoft.com >
2025-06-12 17:34:51 +08:00
you-n-g