feat: add output truncation and offset paging to all large-output tools

- coding_tools: list_files (max_entries=200, sorted), run_command
  (max_chars=8000, output_offset), grep_search (max_lines=100, offset);
  added _truncate_output helper for run_command paging
- pr_tools: get_pull_request_diff / get_pull_request_patch now truncate
  at 15k chars with hunk-boundary awareness and char_offset paging;
  get_pull_request_comments gains limit/offset paging
- issue_tools: get_issue_comments gains limit/offset paging
- file_tools: get_file_content / get_file_content_with_ref now paginate
  by line (offset=1, limit=250), matching existing read_file convention;
  added _paginate_lines helper
- research_tools: fetch_url gains char_offset parameter; _smart_truncate
  now slices from an offset and embeds next char_offset in the footer
- gitea_tools facade: all new params threaded through
This commit is contained in:
Michael
2026-06-28 19:57:14 +02:00
parent c0c9278d75
commit bf13a979c2
6 changed files with 383 additions and 69 deletions
+61 -8
View File
@@ -8,21 +8,74 @@ class FileTools:
def __init__(self, client: GiteaClient) -> None:
self._client = client
def get_file_content(self, owner: str, repo: str, path: str) -> str:
def _paginate_lines(
self,
content: str,
offset: int,
limit: int,
) -> str:
"""Return lines[offset-1 : offset-1+limit] with a paging footer if truncated.
Uses the same 1-indexed convention as CodingTools.read_file.
"""
lines: list[str] = content.splitlines()
total: int = len(lines)
start: int = offset - 1 # convert to 0-indexed
page: list[str] = lines[start : start + limit]
formatted: list[str] = [
f"{start + i + 1}: {line}" for i, line in enumerate(page)
]
result: str = "\n".join(formatted)
end_line: int = start + len(page)
if end_line < total:
next_offset: int = end_line + 1
result += (
f"\n\n[{total} lines total — showing lines {offset}{end_line}. "
f"Re-call with offset={next_offset} to read more.]"
)
return result
def get_file_content(
self,
owner: str,
repo: str,
path: str,
offset: int = 1,
limit: int = 250,
) -> str:
"""Get the content of a file from a Gitea repository with line paging.
Args:
offset: 1-indexed line to start from (default 1).
limit: Maximum number of lines to return (default 250).
"""
try:
content = self._client.get_file_content(owner, repo, path)
if isinstance(content, list):
return "\n".join(content)
return content
raw: str = "\n".join(content) if isinstance(content, list) else content
return self._paginate_lines(raw, offset, limit)
except Exception as e:
return f"Error getting file content: {str(e)}"
def get_file_content_with_ref(self, owner: str, repo: str, path: str, ref: str = "master") -> str:
def get_file_content_with_ref(
self,
owner: str,
repo: str,
path: str,
ref: str = "master",
offset: int = 1,
limit: int = 250,
) -> str:
"""Get file content at a specific git ref with line paging.
Args:
ref: Branch, tag, or commit SHA (default 'master').
offset: 1-indexed line to start from (default 1).
limit: Maximum number of lines to return (default 250).
"""
try:
content = self._client.get_file_content(owner, repo, path, ref)
if isinstance(content, list):
return "\n".join(content)
return content
raw: str = "\n".join(content) if isinstance(content, list) else content
return self._paginate_lines(raw, offset, limit)
except Exception as e:
return f"Error getting file content: {str(e)}"