feat(CF-1812): Use confluence-collab for section-based page editing

Replace inline regex section parser in voice.py with confluence_collab
library (BS4 parsing, 409 conflict retry). Bot now loads section outline
into LLM context when Confluence links are detected.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Christian Gick
2026-02-24 11:37:37 +02:00
parent 3e60e822be
commit 9e146da3b0
6 changed files with 52 additions and 64 deletions

View File

@@ -279,67 +279,21 @@ async def _confluence_read_page(page_id: str) -> tuple[str, str, int]:
async def _confluence_update_section(page_id: str, section_heading: str, new_html: str) -> str:
"""Update a section of a Confluence page by heading.
Finds the section by heading, replaces content up to next same-level heading,
PUTs with incremented version.
Uses confluence_collab library for BS4 parsing and 409 conflict retry.
"""
if not CONFLUENCE_URL or not CONFLUENCE_USER or not CONFLUENCE_TOKEN:
return "Confluence credentials not configured."
# Read current page
url = f"{CONFLUENCE_URL}/rest/api/content/{page_id}"
params = {"expand": "body.storage,version,title"}
async with httpx.AsyncClient(timeout=15.0) as client:
resp = await client.get(url, params=params, auth=(CONFLUENCE_USER, CONFLUENCE_TOKEN))
resp.raise_for_status()
data = resp.json()
from confluence_collab.client import Auth
from confluence_collab.editor import section_update
title = data["title"]
version = data["version"]["number"]
body_html = data["body"]["storage"]["value"]
# Find section by heading (h1-h6) and replace content up to next same-level heading
heading_pattern = re.compile(
r'(<h([1-6])[^>]*>.*?' + re.escape(section_heading) + r'.*?</h\2>)',
re.IGNORECASE | re.DOTALL,
)
match = heading_pattern.search(body_html)
if not match:
return f"Section '{section_heading}' not found on page."
heading_tag = match.group(0)
heading_level = match.group(2)
section_start = match.end()
# Find next heading of same or higher level
next_heading = re.compile(
rf'<h[1-{heading_level}][^>]*>',
re.IGNORECASE,
)
next_match = next_heading.search(body_html, section_start)
section_end = next_match.start() if next_match else len(body_html)
# Replace section content
new_body = body_html[:section_start] + new_html + body_html[section_end:]
# PUT updated page
put_data = {
"version": {"number": version + 1},
"title": title,
"type": "page",
"body": {
"storage": {
"value": new_body,
"representation": "storage",
}
},
}
async with httpx.AsyncClient(timeout=15.0) as client:
resp = await client.put(
url,
json=put_data,
auth=(CONFLUENCE_USER, CONFLUENCE_TOKEN),
)
resp.raise_for_status()
return f"Section '{section_heading}' updated successfully."
auth = Auth(base_url=CONFLUENCE_URL, username=CONFLUENCE_USER, api_token=CONFLUENCE_TOKEN)
result = await section_update(page_id, section_heading, new_html, auth)
if result.ok:
msg = f"Section '{section_heading}' updated successfully."
if result.retries > 0:
msg += f" ({result.retries} conflict retries)"
return msg
return result.message
def _build_e2ee_options() -> rtc.E2EEOptions: