Skip to content

Commit da17665

Browse files
xingyaowwxingyaoww
authored
fix: make max_budget_per_task optional in run_agent_controller (All-Hands-AI#3071)
* fix: make max_budget_per_task optional in `run_agent_controller` * update arg for each run infer
1 parent 4099e48 commit da17665

File tree

17 files changed

+21
-2
lines changed

17 files changed

+21
-2
lines changed

‎evaluation/EDA/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -122,6 +122,7 @@ def process_instance(
122122
agent,
123123
instruction,
124124
max_iterations=metadata.max_iterations,
125+
max_budget_per_task=config.max_budget_per_task,
125126
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
126127
agent.__class__.__name__
127128
],

‎evaluation/agent_bench/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -116,6 +116,7 @@ def process_instance(
116116
agent,
117117
instruction,
118118
max_iterations=metadata.max_iterations,
119+
max_budget_per_task=config.max_budget_per_task,
119120
fake_user_response_fn=FAKE_RESPONSES[agent.__class__.__name__],
120121
sandbox=sandbox,
121122
sid=inst_id,

‎evaluation/biocoder/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -169,6 +169,7 @@ def process_instance(
169169
agent,
170170
instruction,
171171
max_iterations=metadata.max_iterations,
172+
max_budget_per_task=config.max_budget_per_task,
172173
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
173174
agent.__class__.__name__
174175
],

‎evaluation/bird/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -213,6 +213,7 @@ def execute_sql(db_path, sql):
213213
agent,
214214
instruction,
215215
max_iterations=metadata.max_iterations,
216+
max_budget_per_task=config.max_budget_per_task,
216217
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
217218
agent.__class__.__name__
218219
],

‎evaluation/browsing_delegation/run_infer.py

Lines changed: 5 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -67,7 +67,11 @@ def process_instance(
6767

6868
state: State | None = asyncio.run(
6969
run_agent_controller(
70-
agent, instruction, max_iterations=metadata.max_iterations, sid=env_id
70+
agent,
71+
instruction,
72+
max_iterations=metadata.max_iterations,
73+
max_budget_per_task=config.max_budget_per_task,
74+
sid=env_id,
7175
)
7276
)
7377

‎evaluation/gaia/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -119,6 +119,7 @@ def process_instance(
119119
agent,
120120
instruction,
121121
max_iterations=metadata.max_iterations,
122+
max_budget_per_task=config.max_budget_per_task,
122123
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
123124
agent.__class__.__name__
124125
],

‎evaluation/gorilla/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -113,6 +113,7 @@ def process_instance(agent, question_id, question, metadata, reset_logger: bool
113113
agent,
114114
instruction,
115115
max_iterations=metadata.max_iterations,
116+
max_budget_per_task=config.max_budget_per_task,
116117
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN.get(
117118
agent.__class__.__name__
118119
),

‎evaluation/gpqa/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -229,6 +229,7 @@ def process_instance(
229229
agent,
230230
instruction,
231231
max_iterations=metadata.max_iterations,
232+
max_budget_per_task=config.max_budget_per_task,
232233
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN.get(
233234
agent.__class__.__name__
234235
),

‎evaluation/humanevalfix/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -182,6 +182,7 @@ def process_instance(
182182
agent,
183183
instruction,
184184
max_iterations=metadata.max_iterations,
185+
max_budget_per_task=config.max_budget_per_task,
185186
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN.get(
186187
agent.__class__.__name__
187188
),

‎evaluation/logic_reasoning/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -180,6 +180,7 @@ def process_instance(
180180
agent,
181181
instruction,
182182
max_iterations=metadata.max_iterations,
183+
max_budget_per_task=config.max_budget_per_task,
183184
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN.get(
184185
agent.__class__.__name__
185186
),

‎evaluation/miniwob/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -81,6 +81,7 @@ def process_instance(
8181
agent,
8282
'PLACEHOLDER_GOAL',
8383
max_iterations=metadata.max_iterations,
84+
max_budget_per_task=config.max_budget_per_task,
8485
runtime_tools_config=runtime_tools_config,
8586
sandbox=get_sandbox(),
8687
sid=env_id,

‎evaluation/mint/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -143,6 +143,7 @@ def process_instance(
143143
agent,
144144
instruction,
145145
max_iterations=metadata.max_iterations,
146+
max_budget_per_task=config.max_budget_per_task,
146147
fake_user_response_fn=fake_user_response_fn,
147148
sandbox=sandbox,
148149
sid=sid,

‎evaluation/ml_bench/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -150,6 +150,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
150150
agent,
151151
instruction,
152152
max_iterations=metadata.max_iterations,
153+
max_budget_per_task=config.max_budget_per_task,
153154
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN.get(
154155
agent.__class__.__name__
155156
),

‎evaluation/swe_bench/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -282,6 +282,7 @@ def process_instance(
282282
agent,
283283
instruction,
284284
max_iterations=metadata.max_iterations,
285+
max_budget_per_task=config.max_budget_per_task,
285286
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
286287
agent.__class__.__name__
287288
],

‎evaluation/toolqa/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -79,6 +79,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
7979
agent,
8080
instruction,
8181
max_iterations=metadata.max_iterations,
82+
max_budget_per_task=config.max_budget_per_task,
8283
fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
8384
agent.__class__.__name__
8485
],

‎evaluation/webarena/run_infer.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -82,6 +82,7 @@ def process_instance(
8282
agent,
8383
'PLACEHOLDER_GOAL',
8484
max_iterations=metadata.max_iterations,
85+
max_budget_per_task=config.max_budget_per_task,
8586
runtime_tools_config=runtime_tools_config,
8687
sandbox=get_sandbox(),
8788
sid=env_id,

‎opendevin/core/main.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -34,7 +34,7 @@ async def run_agent_controller(
3434
agent: Agent,
3535
task_str: str,
3636
max_iterations: int,
37-
max_budget_per_task: float,
37+
max_budget_per_task: float | None = None,
3838
exit_on_message: bool = False,
3939
fake_user_response_fn: Callable[[State | None], str] | None = None,
4040
sandbox: Sandbox | None = None,

0 commit comments

Comments
 (0)