Spaces:

SyncShift
/

sql-correction-env

Sleeping

App Files Files Community

sql-correction-env

Commit History

Apr 12

17:07
Updated grader values

sravaniamere

5d880f3
15:53
B

sravaniamere

82a5b1b
09:37
Fix stagnation penalty floor to 0.01, never 0.0

sravaniamere

2be7532
09:17
Fix grader: clamp rewards to strictly (0.01, 0.99)

sravaniamere

eecac6e
04:20
Fix server.py, expand tasks to 40, add tests, clean observation schema

sravaniamere

2194233

Apr 11

13:20
fix indentation in main loop

sravaniamere

a59b8ec
13:20
fix indentation in main loop

sravaniamere

cd6351a
10:00
match reference env pattern exactly

sravaniamere

f52aed3
09:45
simplify tasks in openenv.yaml to match reference format

sravaniamere

ec61b5a
09:34
fix state as method not property, fix abstract class error

sravaniamere

fd851a9
09:30
fix step crash when current_task is None

sravaniamere

c7d40b5
09:15
fix initial reward from 0.0 to 0.001

sravaniamere

3fa3f1b
09:08
fix reset indentation and accept task_id param

sravaniamere

7a6f18c
09:03
fix reset to accept task_id, update tasks endpoint

sravaniamere

c41f6ba
08:51
fix max_concurrent_envs to 1

sravaniamere

65028b5
08:49
switch to create_app from http_server

sravaniamere

f6bd747
08:29
fix step format, add tasks endpoint back

sravaniamere

66cc86e
08:04
fix inference to handle new reset response format

sravaniamere

bb74cb1
07:59
fix create_fastapi_app call remove env_name

sravaniamere

4768f7c
07:55
restore SQLTask and SQLReward to models.py

sravaniamere

341aec9
07:52
use openenv base classes and fix yaml format to match working submissions

sravaniamere

e965a47

Apr 10

21:35
fix openenv.yaml with spec_version, type, runtime, app, port

sravaniamere

830b0e5
21:28
add grader endpoint

sravaniamere

5016a17
21:24
add grader endpoint, fix reward bounds and openenv.yaml

sravaniamere

2112542
20:57
remove version pins to fix dependency conflicts

sravaniamere

42d2377
20:56
fix openai version conflict with openenv-core

sravaniamere

5086a76
20:52
pin openenv-core version to force reinstall

sravaniamere

6c6f994
20:46
add grader_fn to tasks endpoint

sravaniamere

55bb0ce
20:39
revert to working server

sravaniamere

c4a66be
20:37
add openenv-core to requirements

sravaniamere

03b2a1c
20:34
use openenv core base classes

sravaniamere

0e2347e
20:16
force rebuild

sravaniamere

14fb228
20:15
commit missing openenv.yaml and server.py changes

sravaniamere

a24bc4f
19:49
fix grader serialization and tasks endpoint

sravaniamere

154f3d9
19:09
fix /tasks endpoint format for validator

sravaniamere

95707b2

Apr 8

15:09
fix reward range to strict (0,1) exclusive

sravaniamere

a785d13
14:54
fix server entry point

sravaniamere

0a9f157
12:52
Make inference fallback to offline SQL correction

sravaniamere

2184846
12:44
Fix server entrypoint packaging and align environment docs

sravaniamere

1a1713a
12:25
Fix inference startup and healthcheck compatibility

sravaniamere

51264be
11:48
force clean exit code 0

sravaniamere

0a57921
11:33
error handling in inference.py

sravaniamere

574f8e7
11:21
fix state endpoint, author, and init exports

sravaniamere

e5d6640
11:04
fix remotes and remove stray folder

sravaniamere

6464bfb
10:59
update ENV_URL to SyncShift space

sravaniamere

6b9084f

Apr 5

17:27
fix server entry point

sravaniamere

b79af36
17:24
fix openenv validate issues

sravaniamere

1f2495e
17:16
merge and add pyproject.toml

sravaniamere

fa28e10
17:11
add pyproject.toml

sravaniamere

2da45df
15:43
Fix punctuation in README.md⁠

sravaniamere

Unverified signature
72145e6

Commit History

Apr 12

Updated grader values

B

Fix stagnation penalty floor to 0.01, never 0.0

Fix grader: clamp rewards to strictly (0.01, 0.99)

Fix server.py, expand tasks to 40, add tests, clean observation schema

Apr 11

fix indentation in main loop

fix indentation in main loop

match reference env pattern exactly

simplify tasks in openenv.yaml to match reference format

fix state as method not property, fix abstract class error

fix step crash when current_task is None

fix initial reward from 0.0 to 0.001

fix reset indentation and accept task_id param

fix reset to accept task_id, update tasks endpoint

fix max_concurrent_envs to 1

switch to create_app from http_server

fix step format, add tasks endpoint back

fix inference to handle new reset response format

fix create_fastapi_app call remove env_name

restore SQLTask and SQLReward to models.py

use openenv base classes and fix yaml format to match working submissions

Apr 10

fix openenv.yaml with spec_version, type, runtime, app, port

add grader endpoint

add grader endpoint, fix reward bounds and openenv.yaml

remove version pins to fix dependency conflicts

fix openai version conflict with openenv-core

pin openenv-core version to force reinstall

add grader_fn to tasks endpoint

revert to working server

add openenv-core to requirements

use openenv core base classes

force rebuild

commit missing openenv.yaml and server.py changes

fix grader serialization and tasks endpoint

fix /tasks endpoint format for validator

Apr 8

fix reward range to strict (0,1) exclusive

fix server entry point

Make inference fallback to offline SQL correction

Fix server entrypoint packaging and align environment docs

Fix inference startup and healthcheck compatibility

force clean exit code 0

error handling in inference.py

fix state endpoint, author, and init exports

fix remotes and remove stray folder

update ENV_URL to SyncShift space

Apr 5

fix server entry point

fix openenv validate issues

merge and add pyproject.toml

add pyproject.toml

Fix punctuation in README.md⁠