Return bounded source excerpts instead of rejecting oversized reads

src/viano_bug_analysis/analysis/investigation_window.py

@@ -110,6 +110,11 @@ def evidence_page(entry, index=0):
         result = capture['result']
         item = {'query':capture['query'], **{k:result[k] for k in
                 ('coverage','truncated','interpretation') if k in result}}
+        if capture['query'].get('kind') == 'source.read' and 'line_limit' in result:
+            item.update({k:result[k] for k in ('requested_start_line','requested_end_line',
+                'requested_line_count','line_limit','line_limit_exceeded','returned_start_line',
+                'returned_end_line','returned_line_count','requested_range_complete','next_start_line','eof')
+                if k in result})
         if capture['query'].get('kind') == 'database.relations':
             item['nodes'] = [{k:node[k] for k in ('node','table','complete','upstream_complete',
                 'local_truncated','returned_rows','distribution','skip_reason') if k in node}

src/viano_bug_analysis/schemas/project-capture-v1.schema.json

@@ -404,6 +404,35 @@
         },
         "selection": {
           "type": "object"
+        },
+        "requested_line_count": {
+          "type": "integer",
+          "minimum": 1
+        },
+        "line_limit": {
+          "type": "integer",
+          "minimum": 1
+        },
+        "line_limit_exceeded": {
+          "type": "boolean"
+        },
+        "returned_line_count": {
+          "type": "integer",
+          "minimum": 0
+        },
+        "requested_range_complete": {
+          "type": "boolean"
+        },
+        "next_start_line": {
+          "type": [
+            "integer",
+            "null"
+          ],
+          "minimum": 1
+        },
+        "read_notice": {
+          "type": "string",
+          "maxLength": 300
         }
       }
     }

src/viano_bug_analysis/tools/repository.py

@@ -69,8 +69,7 @@ class GitSourceProvider:
             if args["path"] not in self.inventory():
                 raise ToolError("PROJECT_SOURCE_NOT_FOUND")
             if (any(type(args[k]) is not int for k in ('start_line', 'end_line'))
-                    or args['start_line'] < 1 or args["end_line"] < args["start_line"]
-                    or args["end_line"]-args["start_line"]+1 > self.limits.max_lines):
+                    or args['start_line'] < 1 or args["end_line"] < args["start_line"]):
                 raise ToolError("PROJECT_SOURCE_RANGE")
         elif "path_prefix" in args:
             safe_path(args["path_prefix"], empty=True)
@@ -204,14 +203,24 @@ class GitSourceProvider:
         if kind == "source.read":
             text, source = self._read(args["path"])
             lines = text.splitlines()
-            end = min(args['end_line'], len(lines))
-            return {"items": [{**source, "line": i+1, "text": lines[i][:2048], "text_truncated":len(lines[i])>2048}
+            requested_count = args['end_line'] - args['start_line'] + 1
+            end = min(args['end_line'], args['start_line'] + self.limits.max_lines - 1, len(lines))
+            truncated = end < min(args['end_line'], len(lines))
+            result = {"items": [{**source, "line": i+1, "text": lines[i][:2048], "text_truncated":len(lines[i])>2048}
                               for i in range(args["start_line"]-1, end)],
-                    "coverage":"selected_lines", "truncated":False,
-                    "total_lines":len(lines), "eof":args['end_line'] >= len(lines),
+                    "coverage":"selected_lines", "truncated":truncated,
+                    "total_lines":len(lines), "eof":end >= len(lines),
                     "requested_start_line":args['start_line'], "requested_end_line":args['end_line'],
                     "returned_start_line":args['start_line'] if args['start_line'] <= end else None,
                     "returned_end_line":end if args['start_line'] <= end else None}
+            if requested_count > self.limits.max_lines:
+                result.update(requested_line_count=requested_count, line_limit=self.limits.max_lines,
+                              line_limit_exceeded=True, returned_line_count=len(result['items']),
+                              requested_range_complete=not truncated,
+                              next_start_line=end+1 if truncated else None,
+                              read_notice=f"Requested {requested_count} lines; at most {self.limits.max_lines} allowed. "
+                                          f"Returned {len(result['items'])} lines; inspect returned range and EOF before drawing conclusions.")
+            return result
         return self._search(args)
 
     @staticmethod