diff options
Diffstat (limited to 'src/ollama_web/tools/fetch.py')
| -rw-r--r-- | src/ollama_web/tools/fetch.py | 20 |
1 files changed, 17 insertions, 3 deletions
diff --git a/src/ollama_web/tools/fetch.py b/src/ollama_web/tools/fetch.py index a9a92f8..65ec511 100644 --- a/src/ollama_web/tools/fetch.py +++ b/src/ollama_web/tools/fetch.py @@ -39,6 +39,20 @@ _FILETYPE_SUFFIXES: dict[str, str] = { _TOOL_NAME = "search_and_fetch" +def _slim_matched(matched: list[dict[str, str]]) -> list[dict[str, str]]: + """Return a token-embeddable view of ``matched`` without the ``body`` field. + + ``search_and_fetch`` embeds the candidate list in its continuation token + so subsequent pages can resume without re-running the web search. The + rendering layer only uses ``title`` and ``href``; the search-engine + snippet (``body``) is unused and can be large (multi-KB for PDF + abstracts). Including it inflates the token to the point where the + model or tool-result trimming may truncate it, corrupting the base64 + payload. Stripping ``body`` keeps the token to a few hundred bytes. + """ + return [{"title": m.get("title", ""), "href": m.get("href", "")} for m in matched] + + def set_session_context(session_id: str | None) -> None: """Set the active session id so fetched files can be persisted later.""" # No-op marker kept for future hooks; storage is keyed by session_id directly. @@ -295,7 +309,7 @@ def _render_file_page( _TOOL_NAME, url, 0, - matched=matched, + matched=_slim_matched(matched), file_idx=file_idx + 1, file_offset=0, ) @@ -328,7 +342,7 @@ def _render_file_page( _TOOL_NAME, url, file_offset + per_file_chars, - matched=matched, + matched=_slim_matched(matched), file_idx=file_idx, file_offset=file_offset + per_file_chars, ) @@ -340,7 +354,7 @@ def _render_file_page( _TOOL_NAME, url, 0, - matched=matched, + matched=_slim_matched(matched), file_idx=file_idx + 1, file_offset=0, ) |