Commit 56eea9e4b for llama.cpp
commit 56eea9e4b0f5d125da16b75b551440b170aa8b1f
Author: Adrien Gallouët <angt@huggingface.co>
Date: Sun Nov 22 19:00:05 2026 +0100
server : add offset pagination to grep_search tool (#32792)
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
diff --git a/tools/server/server-tools.cpp b/tools/server/server-tools.cpp
index 63626ddcc..060361968 100644
--- a/tools/server/server-tools.cpp
+++ b/tools/server/server-tools.cpp
@@ -1121,6 +1121,7 @@ struct server_tool_grep_search : server_tool {
{"literal", {{"type", "boolean"}, {"description", "Treat pattern as a literal string instead of a regular expression (default: false)"}}},
{"ignore_case", {{"type", "boolean"}, {"description", "Case-insensitive search (default: false)"}}},
{"context_lines", {{"type", "integer"}, {"description", "Number of lines of context to show before and after each match (default: 0)"}}},
+ {"offset", {{"type", "integer"}, {"description", "Number of matching lines to skip (default: 0)"}}},
}},
{"required", json::array({"path", "pattern"})},
}},
@@ -1137,6 +1138,7 @@ struct server_tool_grep_search : server_tool {
bool literal = json_value(params, "literal", false);
bool ignore_case = json_value(params, "ignore_case", false);
int ctx_lines = std::max(0, json_value(params, "context_lines", 0));
+ uint64_t offset = std::max<int64_t>(0, json_value(params, "offset", int64_t{0}));
std::string pattern_src = pat_str;
if (literal) {
@@ -1164,6 +1166,7 @@ struct server_tool_grep_search : server_tool {
// collect (absolute_path, display_path) pairs to search
std::vector<std::pair<std::string, std::string>> files;
+ bool listing_truncated = false;
const std::string abs_path = io->resolve(path);
if (io->is_regular_file(abs_path)) {
files.emplace_back(abs_path, path);
@@ -1172,6 +1175,7 @@ struct server_tool_grep_search : server_tool {
if (!listing.err.empty()) {
return {{"error", listing.err + ": " + path}};
}
+ listing_truncated = listing.truncated;
for (const auto & entry : listing.entries) {
if (!path_glob_match(include, entry.rel)) continue;
if (!exclude.empty() && path_glob_match(exclude, entry.rel)) continue;
@@ -1180,14 +1184,18 @@ struct server_tool_grep_search : server_tool {
} else {
return {{"error", "path does not exist: " + path}};
}
+ std::sort(files.begin(), files.end(), [](const auto & a, const auto & b) {
+ return a.second < b.second;
+ });
std::ostringstream output_text;
+ uint64_t skipped = 0;
size_t total = 0;
- bool limit_reached = false;
+ bool has_more = false;
bool show_num = show_lineno || ctx_lines > 0;
for (const auto & file_entry : files) {
- if (limit_reached) break;
+ if (has_more) break;
const std::string & fpath = file_entry.first;
const std::string & display_path = file_entry.second;
@@ -1201,11 +1209,15 @@ struct server_tool_grep_search : server_tool {
}
for (size_t i = 0; i < lines.size(); i++) {
+ if (!std::regex_search(lines[i], pattern)) continue;
+ if (skipped < offset) {
+ skipped++;
+ continue;
+ }
if (total >= SERVER_TOOL_GREP_SEARCH_MAX_RESULTS) {
- limit_reached = true;
+ has_more = true;
break;
}
- if (!std::regex_search(lines[i], pattern)) continue;
long ctx_start = ctx_lines > 0 ? std::max<long>(0, (long) i - ctx_lines) : (long) i;
long ctx_end = ctx_lines > 0 ? std::min<long>((long) lines.size() - 1, (long) i + ctx_lines) : (long) i;
@@ -1226,10 +1238,11 @@ struct server_tool_grep_search : server_tool {
}
output_text << "\n---\nTotal matches: " << total << "\n";
- if (limit_reached) {
- output_text << string_format(
- "[%zu matches limit reached. Narrow the path/pattern/include to see more.]\n",
- SERVER_TOOL_GREP_SEARCH_MAX_RESULTS);
+ if (has_more) {
+ output_text << "Continue with offset=" << offset + total << " and the same search arguments.\n";
+ }
+ if (listing_truncated) {
+ output_text << "[results truncated: time budget or unreadable directory]\n";
}
return {{"plain_text_response", output_text.str()}};
diff --git a/tools/server/tests/unit/test_tools_builtin.py b/tools/server/tests/unit/test_tools_builtin.py
index b6673a089..c830b0642 100755
--- a/tools/server/tests/unit/test_tools_builtin.py
+++ b/tools/server/tests/unit/test_tools_builtin.py
@@ -1,4 +1,5 @@
import os
+import re
import shutil
import subprocess
@@ -53,6 +54,85 @@ def test_tools_builtin_grep_search():
assert "Total matches: 1" in text
+def _grep_matches(text: str) -> list[tuple[str, int, str]]:
+ matches = []
+ for line in text.splitlines():
+ match = re.match(r"^(.*):(\d+):(match-\d+)$", line)
+ if match:
+ path, line_number, identity = match.groups()
+ matches.append((path, int(line_number), identity))
+ return matches
+
+
+def test_tools_builtin_grep_search_pagination(tmp_path):
+ global server
+ server.start()
+
+ path = tmp_path / "matches.txt"
+ expected = [f"match-{i:03d}" for i in range(231)]
+ path.write_text("\n".join(expected) + "\n")
+ params = {"path": str(path), "pattern": "match-", "return_line_numbers": True}
+
+ pages = []
+ next_offset = 0
+ for page_index, expected_size in enumerate([100, 100, 31]):
+ page_params = params if not pages else {**params, "offset": next_offset}
+ text = call_tool("grep_search", page_params)["plain_text_response"]
+ matches = _grep_matches(text)
+ pages.append(matches)
+ assert len(matches) == expected_size
+ assert f"\n---\nTotal matches: {expected_size}\n" in text
+
+ continuation = re.search(r"Continue with offset=(\d+) and the same search arguments\.", text)
+ if page_index < 2:
+ assert continuation is not None
+ next_offset = int(continuation.group(1))
+ assert next_offset == (page_index + 1) * 100
+ else:
+ assert continuation is None
+
+ assert [identity for page in pages for _, _, identity in page] == expected
+
+
+def test_tools_builtin_grep_search_exact_page_has_no_continuation(tmp_path):
+ global server
+ server.start()
+
+ path = tmp_path / "matches.txt"
+ path.write_text("".join(f"match-{i:03d}\n" for i in range(100)) + "unrelated\n")
+ res = call_tool("grep_search", {"path": str(path), "pattern": "match-", "return_line_numbers": True})
+ text = res["plain_text_response"]
+
+ assert len(_grep_matches(text)) == 100
+ assert "Total matches: 100" in text
+ assert "Continue with offset=" not in text
+ assert "matches limit reached" not in text
+
+
+def test_tools_builtin_grep_search_page_order_with_context(tmp_path):
+ global server
+ server.start()
+
+ (tmp_path / "z.txt").write_text("".join(f"match-{i:03d}\n" for i in range(50)))
+ (tmp_path / "a.txt").write_text("".join(f"match-{i:03d}\n" for i in range(50, 120)))
+ params = {"path": str(tmp_path), "pattern": "match-", "context_lines": 1}
+
+ first = call_tool("grep_search", {**params, "offset": 0})["plain_text_response"]
+ second = call_tool("grep_search", {**params, "offset": 100})["plain_text_response"]
+ past_end = [call_tool("grep_search", {**params, "offset": offset})["plain_text_response"] for offset in (121, 1 << 32)]
+
+ expected = [("a.txt", line, f"match-{line + 49:03d}") for line in range(1, 71)]
+ expected += [("z.txt", line, f"match-{line - 1:03d}") for line in range(1, 51)]
+ assert _grep_matches(first) == expected[:100]
+ assert _grep_matches(second) == expected[100:]
+ assert "Continue with offset=100 and the same search arguments." in first
+ assert "Continue with offset=" not in second
+ for text in past_end:
+ assert _grep_matches(text) == []
+ assert "Total matches: 0" in text
+ assert "Continue with offset=" not in text
+
+
def test_tools_builtin_read_file(tmp_path):
global server
server.start()