mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-04 14:12:58 +00:00
Alex
636d4d35d1
Rewrite the default/creative/strict presets (classic + agentic) into
structured sections: grounding and cite-by-title guidance, insufficient-
context behavior, current date, respond-in-user-language, scoped mermaid
usage, an untrusted-content guardrail, and a conditional XML-tagged
document context block. A memory directory listing is injected at render
time via the template prefetch mechanism so the model starts oriented
without burning a tool call.
Fixes along the way:
- Agentic preset swap was dead code: _get_prompt_content cached the
classic preset before create_agent's swap check ran, so agentic and
research agents always got the classic preset. The swap now happens
inside _get_prompt_content.
- Jinja autoescape corrupted document content in custom prompts
(< -> <); prompts are not HTML, autoescape is now off.
- Literal {summaries} leaked into the prompt when no docs were
retrieved; the placeholder is now stripped.
- Agentic/research prompts referenced tool names from a dropped naming
scheme (search_internal, reason_think); they now reference the real
names (search, reason).
- The strict preset told the model to "be very creative and use your
imagination" right after "never make up information".
- extract_tool_usages recorded intermediate attribute chains as
bare-tool usages, which meant "run all actions" at prefetch; only
maximal chains are recorded now.
- Headless runs retrieved docs but never rendered them into the
prompt; the prompt is now rendered like the streaming path.
- Default tools were unreachable by name in prompt templates
(prefetch results were keyed by synthetic id only); defaults now
claim the name key unless an explicit row shadows it.
Tool layer: memory/notes/todo actions are namespaced (memory_view,
note_overwrite, todo_create, ...) with legacy unprefixed names still
accepted via prefix stripping; duplicate action names across tools are
disambiguated with the owning tool's name instead of numeric suffixes;
thin tool descriptions rewritten (brave, duckduckgo, telegram, ntfy,
cryptoprice, read_webpage, internal_search, think).
Docs are now wrapped per chunk in <document index>/<source>/<content>
tags for citation-by-title support.
85 lines
2.9 KiB
Python
85 lines
2.9 KiB
Python
from markdownify import markdownify
|
|
from application.agents.tools.base import Tool
|
|
from application.security.safe_url import UnsafeUserUrlError, pinned_request
|
|
|
|
class ReadWebpageTool(Tool):
|
|
"""
|
|
Read Webpage (browser)
|
|
A tool to fetch the HTML content of a URL and convert it to Markdown.
|
|
"""
|
|
|
|
def __init__(self, config=None):
|
|
"""
|
|
Initializes the tool.
|
|
:param config: Optional configuration dictionary. Not used by this tool.
|
|
"""
|
|
self.config = config
|
|
|
|
def execute_action(self, action_name: str, **kwargs) -> str:
|
|
"""
|
|
Executes the specified action. For this tool, the only action is 'read_webpage'.
|
|
|
|
:param action_name: The name of the action to execute. Should be 'read_webpage'.
|
|
:param kwargs: Keyword arguments, must include 'url'.
|
|
:return: The Markdown content of the webpage or an error message.
|
|
"""
|
|
if action_name != "read_webpage":
|
|
return f"Error: Unknown action '{action_name}'. This tool only supports 'read_webpage'."
|
|
|
|
url = kwargs.get("url")
|
|
if not url:
|
|
return "Error: URL parameter is missing."
|
|
|
|
try:
|
|
response = pinned_request(
|
|
"GET",
|
|
url,
|
|
headers={'User-Agent': 'DocsGPT-Agent/1.0'},
|
|
timeout=10,
|
|
)
|
|
response.raise_for_status()
|
|
|
|
html_content = response.text
|
|
markdown_content = markdownify(html_content, heading_style="ATX", newline_style="BACKSLASH")
|
|
|
|
return markdown_content
|
|
|
|
except UnsafeUserUrlError as e:
|
|
return f"Error: URL validation failed - {e}"
|
|
except Exception as e:
|
|
return f"Error fetching URL {url}: {e}"
|
|
|
|
def get_actions_metadata(self):
|
|
"""
|
|
Returns metadata for the actions supported by this tool.
|
|
"""
|
|
return [
|
|
{
|
|
"name": "read_webpage",
|
|
"description": (
|
|
"Fetch a webpage and return its content as clean Markdown "
|
|
"text. Use it whenever the user shares a URL or the answer "
|
|
"depends on a specific page. Input must be a fully "
|
|
"qualified URL."
|
|
),
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"url": {
|
|
"type": "string",
|
|
"description": "The fully qualified URL of the webpage to read (e.g., 'https://www.example.com').",
|
|
}
|
|
},
|
|
"required": ["url"],
|
|
"additionalProperties": False,
|
|
},
|
|
}
|
|
]
|
|
|
|
def get_config_requirements(self):
|
|
"""
|
|
Returns a dictionary describing the configuration requirements for the tool.
|
|
This tool does not require any specific configuration.
|
|
"""
|
|
return {}
|