Merge branch 'main' into feat/memory-condenser-switch

config.template.toml

@@ -234,6 +234,10 @@ codeact_enable_jupyter = true
 # List of microagents to disable
 #disabled_microagents = []
 
+# Whether history should be truncated to continue the session when hitting LLM context
+# length limit
+enable_history_truncation = true
+
 [agent.RepoExplorerAgent]
 # Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
 # useful when an agent doesn't demand high quality but uses a lot of tokens

docs/modules/usage/configuration-options.md

@@ -340,6 +340,11 @@ The agent configuration options are defined in the `[agent]` and `[agent.<agent_
   - Default: `false`
   - Description: Whether Jupyter is enabled in the action space
 
+- `enable_history_truncation`
+  - Type: `bool`
+  - Default: `true`
+  - Description: Whether history should be truncated to continue the session when hitting LLM context length limit
+
 ### Microagent Usage
 - `enable_prompt_extensions`
   - Type: `bool`

evaluation/README.md

@@ -20,6 +20,8 @@ To evaluate an agent, you can provide the agent's name to the `run_infer.py` pro
 ### Evaluating Different LLMs
 
 OpenHands in development mode uses `config.toml` to keep track of most configuration.
+**IMPORTANT: For evaluation, only the LLM section in `config.toml` will be used. Other configurations, such as `save_trajectory_path`, are not applied during evaluation.**
+
 Here's an example configuration file you can use to define and use multiple LLMs:
 
 ```toml
@@ -40,6 +42,8 @@ api_key = "XXX"
 temperature = 0.0
 ```
 
+For other configurations specific to evaluation, such as `save_trajectory_path`, these are typically set in the `get_config` function of the respective `run_infer.py` file for each benchmark.
+
 ## Supported Benchmarks
 
 The OpenHands evaluation harness supports a wide variety of benchmarks across [software engineering](#software-engineering), [web browsing](#web-browsing), [miscellaneous assistance](#misc-assistance), and [real-world](#real-world) tasks.

frontend/src/api/open-hands.ts

@@ -239,9 +239,6 @@ class OpenHands {
       body,
     );
 
-    // TODO: remove this once we have a multi-conversation UI
-    localStorage.setItem("latest_conversation_id", data.conversation_id);
-
     return data;
   }
 

frontend/src/components/features/conversation-panel/conversation-panel.tsx

@@ -73,9 +73,9 @@ export function ConversationPanel({ onClose }: ConversationPanelProps) {
     <div
       ref={ref}
       data-testid="conversation-panel"
-      className="w-[350px] h-full border border-neutral-700 bg-base-secondary rounded-xl overflow-y-auto"
+      className="w-[350px] h-full border border-neutral-700 bg-base-secondary rounded-xl overflow-y-auto absolute"
     >
-      <div className="pt-4 px-4 flex items-center justify-between">
+      <div className="w-full h-full absolute flex justify-center items-center">
         {isFetching && <LoadingSpinner size="small" />}
       </div>
       {error && (

frontend/src/routes/_oh._index/route.tsx

@@ -1,8 +1,6 @@
 import React from "react";
 import { useDispatch } from "react-redux";
-import { useTranslation } from "react-i18next";
 import posthog from "posthog-js";
-import { I18nKey } from "#/i18n/declaration";
 import { setImportedProjectZip } from "#/state/initial-query-slice";
 import { convertZipToBase64 } from "#/utils/convert-zip-to-base64";
 import { useGitHubUser } from "#/hooks/query/use-github-user";
@@ -14,7 +12,6 @@ import { HeroHeading } from "#/components/shared/hero-heading";
 import { TaskForm } from "#/components/shared/task-form";
 
 function Home() {
-  const { t } = useTranslation();
   const dispatch = useDispatch();
   const formRef = React.useRef<HTMLFormElement>(null);
 
@@ -26,8 +23,6 @@ function Home() {
     gitHubClientId: config?.GITHUB_CLIENT_ID || null,
   });
 
-  const latestConversation = localStorage.getItem("latest_conversation_id");
-
   return (
     <div className="bg-base-secondary h-full rounded-xl flex flex-col items-center justify-center relative overflow-y-auto px-2">
       <HeroHeading />
@@ -56,19 +51,6 @@ function Home() {
           />
         </div>
       </div>
-      {latestConversation && (
-        <div className="flex gap-4 w-full text-center mt-8">
-          <p className="text-center w-full">
-            {t(I18nKey.LANDING$OR)}&nbsp;
-            <a
-              className="underline"
-              href={`/conversations/${latestConversation}`}
-            >
-              {t(I18nKey.LANDING$RECENT_CONVERSATION)}
-            </a>
-          </p>
-        </div>
-      )}
     </div>
   );
 }

openhands/agenthub/browsing_agent/response_parser.py

@@ -10,17 +10,24 @@
 
 
 class BrowsingResponseParser(ResponseParser):
-    def __init__(self):
+    def __init__(self) -> None:
         # Need to pay attention to the item order in self.action_parsers
         super().__init__()
         self.action_parsers = [BrowsingActionParserMessage()]
         self.default_parser = BrowsingActionParserBrowseInteractive()
 
-    def parse(self, response: str) -> Action:
-        action_str = self.parse_response(response)
+    def parse(
+        self, response: str | dict[str, list[dict[str, dict[str, str | None]]]]
+    ) -> Action:
+        if isinstance(response, str):
+            action_str = response
+        else:
+            action_str = self.parse_response(response)
         return self.parse_action(action_str)
 
-    def parse_response(self, response) -> str:
+    def parse_response(
+        self, response: dict[str, list[dict[str, dict[str, str | None]]]]
+    ) -> str:
         action_str = response['choices'][0]['message']['content']
         if action_str is None:
             return ''
@@ -47,9 +54,7 @@ class BrowsingActionParserMessage(ActionParser):
     - BrowseInteractiveAction(browser_actions) - unexpected response format, message back to user
     """
 
-    def __init__(
-        self,
-    ):
+    def __init__(self) -> None:
         pass
 
     def check_condition(self, action_str: str) -> bool:
@@ -69,9 +74,7 @@ class BrowsingActionParserBrowseInteractive(ActionParser):
     - BrowseInteractiveAction(browser_actions) - handle send message to user function call in BrowserGym
     """
 
-    def __init__(
-        self,
-    ):
+    def __init__(self) -> None:
         pass
 
     def check_condition(self, action_str: str) -> bool:

openhands/agenthub/browsing_agent/utils.py

@@ -5,7 +5,7 @@
 import yaml
 
 
-def yaml_parser(message):
+def yaml_parser(message: str) -> tuple[dict, bool, str]:
     """Parse a yaml message for the retry function."""
     # saves gpt-3.5 from some yaml parsing errors
     message = re.sub(r':\s*\n(?=\S|\n)', ': ', message)
@@ -22,7 +22,9 @@ def yaml_parser(message):
     return value, valid, retry_message
 
 
-def _compress_chunks(text, identifier, skip_list, split_regex='\n\n+'):
+def _compress_chunks(
+    text: str, identifier: str, skip_list: list[str], split_regex: str = '\n\n+'
+) -> tuple[dict[str, str], str]:
     """Compress a string by replacing redundant chunks by identifiers. Chunks are defined by the split_regex."""
     text_list = re.split(split_regex, text)
     text_list = [chunk.strip() for chunk in text_list]
@@ -44,7 +46,7 @@ def _compress_chunks(text, identifier, skip_list, split_regex='\n\n+'):
     return def_dict, compressed_text
 
 
-def compress_string(text):
+def compress_string(text: str) -> str:
     """Compress a string by replacing redundant paragraphs and lines with identifiers."""
     # Perform paragraph-level compression
     def_dict, compressed_text = _compress_chunks(
@@ -67,7 +69,7 @@ def compress_string(text):
     return definitions + '\n' + compressed_text
 
 
-def extract_html_tags(text, keys):
+def extract_html_tags(text: str, keys: list[str]) -> dict[str, list[str]]:
     """Extract the content within HTML tags for a list of keys.
 
     Parameters
@@ -102,7 +104,12 @@ class ParseError(Exception):
     pass
 
 
-def parse_html_tags_raise(text, keys=(), optional_keys=(), merge_multiple=False):
+def parse_html_tags_raise(
+    text: str,
+    keys: list[str] | None = None,
+    optional_keys: list[str] | None = None,
+    merge_multiple: bool = False,
+) -> dict[str, str]:
     """A version of parse_html_tags that raises an exception if the parsing is not successful."""
     content_dict, valid, retry_message = parse_html_tags(
         text, keys, optional_keys, merge_multiple=merge_multiple
@@ -112,7 +119,12 @@ def parse_html_tags_raise(text, keys=(), optional_keys=(), merge_multiple=False)
     return content_dict
 
 
-def parse_html_tags(text, keys=(), optional_keys=(), merge_multiple=False):
+def parse_html_tags(
+    text: str,
+    keys: list[str] | None = None,
+    optional_keys: list[str] | None = None,
+    merge_multiple: bool = False,
+) -> tuple[dict[str, str], bool, str]:
     """Satisfy the parse api, extracts 1 match per key and validates that all keys are present
 
     Parameters
@@ -133,26 +145,30 @@ def parse_html_tags(text, keys=(), optional_keys=(), merge_multiple=False):
     str
         A message to be displayed to the agent if the parsing was not successful.
     """
-    all_keys = tuple(keys) + tuple(optional_keys)
+    keys = keys or []
+    optional_keys = optional_keys or []
+    all_keys = list(keys) + list(optional_keys)
     content_dict = extract_html_tags(text, all_keys)
     retry_messages = []
+    result_dict: dict[str, str] = {}
 
     for key in all_keys:
         if key not in content_dict:
             if key not in optional_keys:
                 retry_messages.append(f'Missing the key <{key}> in the answer.')
         else:
             val = content_dict[key]
-            content_dict[key] = val[0]
             if len(val) > 1:
                 if not merge_multiple:
                     retry_messages.append(
                         f'Found multiple instances of the key {key}. You should have only one of them.'
                     )
                 else:
                     # merge the multiple instances
-                    content_dict[key] = '\n'.join(val)
+                    result_dict[key] = '\n'.join(val)
+            else:
+                result_dict[key] = val[0]
 
     valid = len(retry_messages) == 0
     retry_message = '\n'.join(retry_messages)
-    return content_dict, valid, retry_message
+    return result_dict, valid, retry_message

openhands/agenthub/codeact_agent/function_calling.py

@@ -475,8 +475,9 @@ def combine_thought(action: Action, thought: str) -> Action:
 def response_to_actions(response: ModelResponse) -> list[Action]:
     actions: list[Action] = []
     assert len(response.choices) == 1, 'Only one choice is supported for now'
-    assistant_msg = response.choices[0].message
-    if assistant_msg.tool_calls:
+    choice = response.choices[0]
+    assistant_msg = choice.message
+    if hasattr(assistant_msg, 'tool_calls') and assistant_msg.tool_calls:
         # Check if there's assistant_msg.content. If so, add it to the thought
         thought = ''
         if isinstance(assistant_msg.content, str):
@@ -592,7 +593,10 @@ def response_to_actions(response: ModelResponse) -> list[Action]:
             actions.append(action)
     else:
         actions.append(
-            MessageAction(content=assistant_msg.content, wait_for_response=True)
+            MessageAction(
+                content=str(assistant_msg.content) if assistant_msg.content else '',
+                wait_for_response=True,
+            )
         )
 
     assert len(actions) >= 1

openhands/agenthub/micro/agent.py

@@ -22,7 +22,7 @@ def parse_response(orig_response: str) -> Action:
     return action_from_dict(action_dict)
 
 
-def to_json(obj, **kwargs):
+def to_json(obj: object, **kwargs: dict) -> str:
     """Serialize an object to str format"""
     return json.dumps(obj, **kwargs)
 
@@ -32,7 +32,9 @@ class MicroAgent(Agent):
     prompt = ''
     agent_definition: dict = {}
 
-    def history_to_json(self, history: list[Event], max_events: int = 20, **kwargs):
+    def history_to_json(
+        self, history: list[Event], max_events: int = 20, **kwargs: dict
+    ) -> str:
         """
         Serialize and simplify history to str format
         """
@@ -60,7 +62,7 @@ def __init__(self, llm: LLM, config: AgentConfig):
         super().__init__(llm, config)
         if 'name' not in self.agent_definition:
             raise ValueError('Agent definition must contain a name')
-        self.prompt_template = Environment(loader=BaseLoader).from_string(self.prompt)
+        self.prompt_template = Environment(loader=BaseLoader()).from_string(self.prompt)
         self.delegates = all_microagents.copy()
         del self.delegates[self.agent_definition['name']]
 
@@ -74,7 +76,7 @@ def step(self, state: State) -> Action:
             delegates=self.delegates,
             latest_user_message=last_user_message,
         )
-        content = [TextContent(text=prompt)]
+        content: list[TextContent | ImageContent] = [TextContent(text=prompt)]
         if self.llm.vision_is_active() and last_image_urls:
             content.append(ImageContent(image_urls=last_image_urls))
         message = Message(role='user', content=content)

openhands/agenthub/visualbrowsing_agent/visualbrowsing_agent.py

@@ -29,7 +29,9 @@ def get_error_prefix(obs: BrowserOutputObservation) -> str:
     return f'## Error from previous action:\n{obs.last_browser_action_error}\n'
 
 
-def create_goal_prompt(goal: str, image_urls: list[str] | None):
+def create_goal_prompt(
+    goal: str, image_urls: list[str] | None
+) -> tuple[str, list[str]]:
     goal_txt: str = f"""\
 # Instructions
 Review the current state of the page and all other information to find the best possible next action to accomplish your goal. Your answer will be interpreted and executed by a program, make sure to follow the formatting instructions.
@@ -52,7 +54,7 @@ def create_observation_prompt(
     focused_element: str,
     error_prefix: str,
     som_screenshot: str | None,
-):
+) -> tuple[str, str | None]:
     txt_observation = f"""
 # Observation of current step:
 {tabs}{axtree_txt}{focused_element}{error_prefix}
@@ -273,7 +275,9 @@ def step(self, state: State) -> Action:
         observation_txt, som_screenshot = create_observation_prompt(
             cur_axtree_txt, tabs, focused_element, error_prefix, set_of_marks
         )
-        human_prompt = [TextContent(type='text', text=goal_txt)]
+        human_prompt: list[TextContent | ImageContent] = [
+            TextContent(type='text', text=goal_txt)
+        ]
         if len(goal_images) > 0:
             human_prompt.append(ImageContent(image_urls=goal_images))
         human_prompt.append(TextContent(type='text', text=observation_txt))