refactor: remove search_surfsense_docs tool and related references

- Deleted the `search_surfsense_docs` tool and its associated files, streamlining the agent's toolset.
- Updated various components and prompts to remove references to the now-removed tool, ensuring consistency across the codebase.
- Adjusted documentation to direct users to the SurfSense documentation link for product-related queries instead.
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2026-05-28 22:35:14 -07:00
parent 9b9e6828c7
commit 40ca9e6ed2
71 changed files with 232 additions and 1676 deletions

View file

@ -1,15 +1,11 @@
"""Pre-agent context shaping: mentioned-doc rendering and todos extraction."""
"""Pre-agent context shaping: todos extraction."""
from __future__ import annotations
from app.tasks.chat.streaming.context.deepagents_todos import (
extract_todos_from_deepagents,
)
from app.tasks.chat.streaming.context.mentioned_docs import (
format_mentioned_surfsense_docs_as_context,
)
__all__ = [
"extract_todos_from_deepagents",
"format_mentioned_surfsense_docs_as_context",
]

View file

@ -1,58 +0,0 @@
"""Render user-mentioned SurfSense docs as XML context for the agent."""
from __future__ import annotations
import json
from app.db import SurfsenseDocsDocument
from app.utils.surfsense_docs import surfsense_docs_public_url
def format_mentioned_surfsense_docs_as_context(
documents: list[SurfsenseDocsDocument],
) -> str:
if not documents:
return ""
context_parts = ["<mentioned_surfsense_docs>"]
context_parts.append(
"The user has explicitly mentioned the following SurfSense documentation pages. "
"These are official documentation about how to use SurfSense and should be used to answer questions about the application. "
"Use [citation:CHUNK_ID] format for citations (e.g., [citation:doc-123])."
)
for doc in documents:
public_url = surfsense_docs_public_url(doc.source)
metadata_json = json.dumps(
{"source": doc.source, "public_url": public_url}, ensure_ascii=False
)
context_parts.append("<document>")
context_parts.append("<document_metadata>")
context_parts.append(f" <document_id>doc-{doc.id}</document_id>")
context_parts.append(" <document_type>SURFSENSE_DOCS</document_type>")
context_parts.append(f" <title><![CDATA[{doc.title}]]></title>")
context_parts.append(f" <url><![CDATA[{public_url}]]></url>")
context_parts.append(
f" <metadata_json><![CDATA[{metadata_json}]]></metadata_json>"
)
context_parts.append("</document_metadata>")
context_parts.append("")
context_parts.append("<document_content>")
if hasattr(doc, "chunks") and doc.chunks:
for chunk in doc.chunks:
context_parts.append(
f" <chunk id='doc-{chunk.id}'><![CDATA[{chunk.content}]]></chunk>"
)
else:
context_parts.append(
f" <chunk id='doc-0'><![CDATA[{doc.content}]]></chunk>"
)
context_parts.append("</document_content>")
context_parts.append("</document>")
context_parts.append("")
context_parts.append("</mentioned_surfsense_docs>")
return "\n".join(context_parts)