HKUDS/DeepTutor · error · OpValidationError

edit: text length must be 1..{_MAX_TEXT_LEN} (got {len(op.ne

Error message

edit: text length must be 1..{_MAX_TEXT_LEN} (got {len(op.new_text)})

What it means

OpValidationError raised in _validate when an EditOp's new_text is empty or longer than _MAX_TEXT_LEN. Replacement text for an existing entry is bounded by the same limit as AddOp text so entries stay within the memory document's size budget; invalid replacement text is rejected before the edit is applied (apply is all-or-nothing).

Source

Thrown at deeptutor/services/memory/ops.py:91

        if isinstance(op, AddOp):
            if not op.text or len(op.text) > _MAX_TEXT_LEN:
                raise OpValidationError(
                    f"add: text length must be 1..{_MAX_TEXT_LEN} (got {len(op.text)})"
                )
            if not op.section or len(op.section) > _MAX_SECTION_LEN:
                raise OpValidationError(f"add: invalid section {op.section!r}")
            if not op.refs:
                raise OpValidationError("add: refs must be non-empty")
            for ref in op.refs:
                if not is_valid_ref(ref):
                    raise OpValidationError(f"add: malformed ref {ref!r}")
        elif isinstance(op, EditOp):
            if not is_entry_id(op.target_id):
                raise OpValidationError(f"edit: malformed target_id {op.target_id!r}")
            if doc.find(op.target_id) is None:
                raise OpValidationError(f"edit: target_id {op.target_id} not found")
            if not op.new_text or len(op.new_text) > _MAX_TEXT_LEN:
                raise OpValidationError(
                    f"edit: text length must be 1..{_MAX_TEXT_LEN} (got {len(op.new_text)})"
                )
            if not op.new_refs:
                raise OpValidationError("edit: refs must be non-empty")
            for ref in op.new_refs:
                if not is_valid_ref(ref):
                    raise OpValidationError(f"edit: malformed ref {ref!r}")
            if op.target_id in deletes:
                raise OpValidationError(
                    f"batch conflict: edit and delete on same id {op.target_id}"
                )
            edits.add(op.target_id)
        elif isinstance(op, DeleteOp):
            if not is_entry_id(op.target_id):
                raise OpValidationError(f"delete: malformed target_id {op.target_id!r}")
            if doc.find(op.target_id) is None:
                raise OpValidationError(f"delete: target_id {op.target_id} not found")
            if op.reason not in _DELETE_REASONS:

View on GitHub (pinned to 3e82f13042)

Solutions

  1. Clamp/reject: require 1.._MAX_TEXT_LEN (import the constant from ops.py) before building the EditOp
  2. To remove content use the dedicated DeleteOp rather than an empty-text edit
  3. Summarize or split oversized replacement text; surface a clear error to the LLM/caller so it retries shorter

Example fix

# before
op = EditOp(target_id=eid, new_text=rewritten, new_refs=[ref])

# after
from deeptutor.services.memory.ops import _MAX_TEXT_LEN
rewritten = rewritten.strip()
if not rewritten or len(rewritten) > _MAX_TEXT_LEN:
    raise ValueError("replacement text out of range")
op = EditOp(target_id=eid, new_text=rewritten, new_refs=[ref])
Defensive patterns

Strategy: validation

Validate before calling

from deeptutor.services.memory.ops import _MAX_TEXT_LEN
new_text = new_text.strip() if new_text else ""
if not (1 <= len(new_text) <= _MAX_TEXT_LEN):
    raise ValueError("replacement text out of range")

Type guard

def is_valid_edit_text(text: str) -> bool:
    return bool(text) and len(text) <= _MAX_TEXT_LEN

Try / catch

try:
    ops.apply(doc, [op])
except OpValidationError as e:
    if e.args[0].startswith("edit: text length"):
        op = replace(op, new_text=op.new_text[:_MAX_TEXT_LEN])
        ops.apply(doc, [op])
    else:
        raise

Prevention

When it happens

Trigger: EditOp(..., new_text='' or new_text longer than _MAX_TEXT_LEN) passed to ops.apply — typically an LLM rewriting an entry into an oversized blob, or code passing None/empty string as 'no change' semantics that the API does not support.

Common situations: LLM-generated replacements without clamping; 'clear this entry' implemented as empty text instead of a delete op; diffs or concatenations accidentally producing huge strings; tests probing boundaries.

Related errors


AI-assisted analysis of HKUDS/DeepTutor@3e82f13042 (2026-08-27). Data as JSON: /api/errors/7762141defacbacd. Report an issue: GitHub.