Frank Xu
48151bdbb0
[feat] WebArena benchmark, MiniWoB++ benchmark and related arch changes ( #2170 )
...
* add webarena, and revamp messaging for webarena eval
* add changes for browsergym
* update infer script
* fix unit tests
* update
* add multiple run for miniwob
* update instruction, remove personal path
* update
* add code for getting final reward, fix integration, add results
* add avg cost calculation
2024-06-06 09:01:20 +08:00
Aaron Xia
42c6b506b5
Lazy launching BrowseEnv / making BrowseEnv optional ( #2155 )
...
* feat: lazy launching browser; browser optional for diffrent agents.
* style: lint
* fix: integration test fail due to browser not started.
* fix: run by cli and integration test failed.
* fix: lint
* fix: lint
---------
Co-authored-by: Graham Neubig <neubig@gmail.com >
2024-05-31 16:40:42 -04:00
Boxuan Li
91f313c914
BrowserEnv: init exception handling ( #2050 )
...
* BrowserEnv: init exception handling
* Revert irrelevant changes
* Remove type ignore
2024-05-25 00:17:25 -07:00
மனோஜ்குமார் பழனிச்சாமி
cfae6821fa
refactored timeout ( #2044 )
2024-05-24 18:19:14 +02:00
Engel Nyst
0eccf31604
Refactor monologue and SWE agent to use the messages in state history ( #1863 )
...
* Refactor monologue to use the messages in state history
* add messages, clean up
* fix monologue
* update integration tests
* move private method
* update SWE agent to use the history from State
* integration tests for SWE agent
* rename monologue to initial_thoughts, since that is what it is
2024-05-23 07:29:12 +00:00
Robert Brennan
5bdacf738d
Refactor session management ( #1810 )
...
* refactor session mgmt
* defer file handling to runtime
* add todo
* refactor sessions a bit more
* remove messages logic from FE
* fix up socket handshake
* refactor frontend auth a bit
* first pass at redoing file explorer
* implement directory suffix
* fix up file tree
* close agent on websocket close
* remove session saving
* move file refresh
* remove getWorkspace
* plumb path/code differently
* fix build issues
* fix the tests
* fix npm build
* add session rehydration
* fix event serialization
* logspam
* fix user message rehydration
* add get_event fn
* agent state restoration
* change history tracking for codeact
* fix responsiveness of init
* fix lint
* lint
* delint
* fix prop
* update tests
* logspam
* lint
* fix test
* revert codeact
* change fileService to use API
* fix up session loading
* delint
* delint
* fix integration tests
* revert test
* fix up access to options endpoints
* fix initial files load
* delint
* fix file initialization
* fix mock server
* fixl int
* fix auth for html
* Update frontend/src/i18n/translation.json
Co-authored-by: Xingyao Wang <xingyao6@illinois.edu >
* refactor sessions and sockets
* avoid reinitializing the same session
* fix reconnect issue
* change up intro message
* more guards on reinit
* rename agent_session
* delint
* fix a bunch of tests
* delint
* fix last test
* remove code editor context
* fix build
* fix any
* fix dot notation
* Update frontend/src/services/api.ts
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk >
* fix up error handling
* Update opendevin/server/session/agent.py
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk >
* Update opendevin/server/session/agent.py
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk >
* Update frontend/src/services/session.ts
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk >
* fix build errs
* fix else
* add closed state
* delint
* Update opendevin/server/session/session.py
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com >
---------
Co-authored-by: Xingyao Wang <xingyao6@illinois.edu >
Co-authored-by: Graham Neubig <neubig@gmail.com >
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk >
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com >
2024-05-22 18:33:16 +00:00
RainRat
43c187b949
fix typos ( #1956 )
...
no functional change
2024-05-21 19:00:48 +00:00
Frank Xu
a84d19f03c
Enable CodeAct agents with browsing, and also enable arbitrary BrowserGym action support ( #1807 )
...
* enable browsing in codeact, and arbitrary browsergym DSL support
* fix
* fix unit test case
* update frontend for the new interactive browsing action
* bump ver
* Fix integration tests
---------
Co-authored-by: OpenDevinBot <bot@opendevin.com >
2024-05-15 11:59:58 -04:00
Xingyao Wang
123968f887
Runtime only close then sandbox if it is created by itself ( #1793 )
2024-05-15 05:47:56 +08:00
Robert Brennan
dcb5d1ce0a
Add permanent storage option for EventStream ( #1697 )
...
* add storage classes
* add minio
* add event stream storage
* storage test working
* use fixture
* event stream test passing
* better serialization
* factor out serialization pkg
* move more serialization
* fix tests
* fix test
* remove __all__
* add rehydration test
* add more rehydration test
* fix fixture
* fix dict init
* update tests
* lock
* regenerate tests
* Update opendevin/events/stream.py
* revert tests
* revert old integration tests
* only add fields if present
* regen tests
* pin pyarrow
* fix unit tests
* remove cause from memories
* revert tests
* regen tests
2024-05-14 11:09:45 -04:00
Robert Brennan
beb74a19f6
Use event stream for the runtime ( #1776 )
...
* rebuild PR from scratch
* fix max_iter
* regenerate tests
* cut down on history
* Update opendevin/controller/agent_controller.py
* regenerate tests
* revert swe agent
* revert some codeact chagnes
* regenerate tests
* add source to dict
* only add source if not none
* try to fix coverage issue
* lock
* add gevent
2024-05-14 13:35:25 +00:00
Xingyao Wang
8bfae8413e
Support passing sandbox as argument and iteration reminder ( #1730 )
...
* support custom sandbox;
add iteration_reminder
* Enable iteration reminder in CodeActAgent integration test
* Don't remove numbers when comparing prompts
* Update tests/integration/README.md
---------
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk >
2024-05-12 07:57:33 +00:00
Jim Su
f8d4b1ab0d
Use generic types ( #1680 )
2024-05-10 04:21:22 +02:00
Robert Brennan
26d82841d5
Create runtime implementation ( #1626 )
...
* first pass at moving runtime
* fix import
* remove github refs
* remove unnecessary import
* remove unnecessary import
* add e2b
* refactor read and write file ops
* remove github test
* rm action
* revert permissions
* regenerate tests
* re-delete file operations
* regenerate integration tests
* Update opendevin/runtime/runtime.py
Co-authored-by: Graham Neubig <neubig@gmail.com >
* fix ref
* add docs
* remove logspam
---------
Co-authored-by: Graham Neubig <neubig@gmail.com >
2024-05-09 19:04:49 -04:00
