Merge branch 'main' into mh/rel0260

Author: mamoodi

Makefile

@@ -1,4 +1,4 @@
-SHELL=/bin/bash
+SHELL=/usr/bin/env bash
 # Makefile for OpenHands project
 
 # Variables

build.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -e
 
 poetry build -v

containers/build.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 # Initialize variables with default values

containers/dev/dev.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -o pipefail
 
 function get_docker() {

evaluation/benchmarks/EDA/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/agent_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/aider_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/biocoder/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/bird/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/browsing_delegation/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/commit0_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/discoverybench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/gaia/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/gorilla/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/gpqa/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/humanevalfix/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/logic_reasoning/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/miniwob/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/mint/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/ml_bench/scripts/cleanup.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 # Step 1: Stop all running containers
 echo "Stopping all running containers..."

evaluation/benchmarks/ml_bench/scripts/run_analysis.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 RESULT_FILE=$1
 MODEL_CONFIG=$2

evaluation/benchmarks/ml_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/scienceagentbench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/swe_bench/scripts/docker/pull_all_eval_docker.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -e
 
 LEVEL=$1

evaluation/benchmarks/swe_bench/scripts/docker/push_eval_docker.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 # This is ONLY used for pushing docker images created by https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md
 

evaluation/benchmarks/swe_bench/scripts/eval/convert_oh_folder_to_swebench_submission.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 FOLDER_PATH=$1
 NEW_FOLDER_PATH=${FOLDER_PATH}.swebench_submission

evaluation/benchmarks/swe_bench/scripts/eval_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 PROCESS_FILEPATH=$1
 if [ -z "$PROCESS_FILEPATH" ]; then

evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 INPUT_FILE=$1

evaluation/benchmarks/swe_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/swe_bench/scripts/setup/instance_swe_entry.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 source ~/.bashrc
 SWEUTIL_DIR=/swe_util

evaluation/benchmarks/swe_bench/scripts/setup/prepare_swe_utils.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 set -e
 EVAL_WORKSPACE="evaluation/benchmarks/swe_bench/eval_workspace"

evaluation/benchmarks/swe_bench/scripts/setup/swe_entry.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 set -e
 

evaluation/benchmarks/the_agent_company/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 ##################################################################################################
 # Adapted from https://github.com/TheAgentCompany/TheAgentCompany/blob/main/evaluation/run_eval.sh

evaluation/benchmarks/toolqa/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/visualwebarena/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/webarena/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/integration_tests/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/regression/cases/hello-name/start/hello_world.sh

@@ -1,2 +1,2 @@
-#!/bin/bash
+#!/usr/bin/env bash
 echo "hello world"

evaluation/utils/scripts/cleanup_remote_runtime.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 
 # API base URL

openhands/core/config/sandbox_config.py

@@ -53,11 +53,11 @@ class SandboxConfig(BaseModel):
     remote_runtime_api_timeout: int = Field(default=10)
     remote_runtime_enable_retries: bool = Field(default=False)
     remote_runtime_class: str | None = Field(
-        default='sysbox'
+        default=None
     )  # can be "None" (default to gvisor) or "sysbox" (support docker inside runtime + more stable)
     enable_auto_lint: bool = Field(
-        default=False  # once enabled, OpenHands would lint files after editing
-    )
+        default=False
+    )  # once enabled, OpenHands would lint files after editing
     use_host_network: bool = Field(default=False)
     runtime_extra_build_args: list[str] | None = Field(default=None)
     initialize_plugins: bool = Field(default=True)

openhands/llm/llm.py

@@ -8,7 +8,6 @@
 import requests
 
 from openhands.core.config import LLMConfig
-from openhands.utils.ensure_httpx_close import EnsureHttpxClose
 
 with warnings.catch_warnings():
     warnings.simplefilter('ignore')
@@ -231,9 +230,9 @@ def wrapper(*args, **kwargs):
 
             # Record start time for latency measurement
             start_time = time.time()
-            with EnsureHttpxClose():
-                # we don't support streaming here, thus we get a ModelResponse
-                resp: ModelResponse = self._completion_unwrapped(*args, **kwargs)
+
+            # we don't support streaming here, thus we get a ModelResponse
+            resp: ModelResponse = self._completion_unwrapped(*args, **kwargs)
 
             # Calculate and record latency
             latency = time.time() - start_time
@@ -288,11 +287,7 @@ def wrapper(*args, **kwargs):
                     'messages': messages,
                     'response': resp,
                     'args': args,
-                    'kwargs': {
-                        k: v
-                        for k, v in kwargs.items()
-                        if k not in ('messages', 'client')
-                    },
+                    'kwargs': {k: v for k, v in kwargs.items() if k != 'messages'},
                     'timestamp': time.time(),
                     'cost': cost,
                 }