From 68238f0b6a2e609a1d42b36425bf1558728f333c Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Thu, 30 Jul 2026 11:21:18 +0300
Subject: [PATCH] Name the readlines workaround when sandbox code iterates a
 file

50 executions across 40 cases in an 822-case run died on
'_io.TextIOWrapper' object is not iterable, and those cases scored 37.5%
judged against 60.1% and cited 12.5% against 55.2%.
---
 CHANGELOG.md                                  |  1 +
 .../haiku/rag/capabilities/analysis.py        | 20 ++++++++++++-
 tests/capabilities/test_capabilities.py       | 29 +++++++++++++++++++
 3 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7c775455..838472a8 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,7 @@
 
 ### Fixed
 
+- A failed `analysis_execute_code` call that iterated a file object reports the `.readlines()` workaround alongside the `TypeError`.
 - A capability that reaches its request limit keeps its cite tool for two further model requests while its other tools are removed, so an exhausted run can still register citations.
 - A cited chunk id that does not match a retrieved id exactly resolves to the closest one above a 0.75 similarity cutoff, recovering ids mistyped from search results.
 - Dotfiles are parsed as their actual format instead of a single unstructured text block. Docling ignores the extension of a name starting with a dot, so converters strip leading dots from the name they hand it.
diff --git a/haiku_rag_slim/haiku/rag/capabilities/analysis.py b/haiku_rag_slim/haiku/rag/capabilities/analysis.py
index 2d754840..cea8a878 100644
--- a/haiku_rag_slim/haiku/rag/capabilities/analysis.py
+++ b/haiku_rag_slim/haiku/rag/capabilities/analysis.py
@@ -37,6 +37,21 @@ def instructions() -> str:
     return _instructions_path.read_text().strip()
 
 
+def _recovery_hint(stderr: str) -> str:
+    """Name the workaround for sandbox limits models trip over repeatedly.
+
+    The instructions already say file objects are not iterable, and models write
+    ``for line in open(...)`` regardless. Carrying the fix in the error gives
+    them something to act on for the retry.
+    """
+    if "TextIOWrapper" in stderr and "not iterable" in stderr:
+        return (
+            "\n\nHint: file objects cannot be iterated here. Read lines with "
+            '.readlines() or .read().split("\\n").'
+        )
+    return ""
+
+
 @dataclass
 class AnalysisCapability(RAGCapabilityBase[AnalysisState]):
     """Deferred capability for sandboxed computation over a RAG corpus."""
@@ -103,7 +118,10 @@ class AnalysisCapability(RAGCapabilityBase[AnalysisState]):
             )
         )
         if not result.success:
-            raise ToolFailed(f"{result.stderr}\n\nOutput: {result.stdout}")
+            raise ToolFailed(
+                f"{result.stderr}{_recovery_hint(result.stderr)}"
+                f"\n\nOutput: {result.stdout}"
+            )
         return result.stdout or "No output."
 
     def get_toolset(self) -> FunctionToolset[Any]:
diff --git a/tests/capabilities/test_capabilities.py b/tests/capabilities/test_capabilities.py
index 45dc36cf..ac99b1d9 100644
--- a/tests/capabilities/test_capabilities.py
+++ b/tests/capabilities/test_capabilities.py
@@ -589,6 +589,35 @@ async def test_cite_tool_is_withdrawn_after_the_grace_window(temp_db_path):
     assert kept == []
 
 
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    ("stderr", "expect_hint"),
+    [
+        ("TypeError: '_io.TextIOWrapper' object is not iterable", True),
+        ("TypeError: 'list' object is not an iterator", False),
+    ],
+)
+async def test_sandbox_iteration_failure_carries_the_workaround(
+    temp_db_path, stderr, expect_hint
+):
+    """A model that iterates a file object gets told what to do instead."""
+    capability = create_analysis(db_path=temp_db_path, config=AppConfig())
+    capability.state = AnalysisState()
+    sandbox = AsyncMock()
+    sandbox.execute.return_value = SandboxResult(
+        stdout="", stderr=stderr, success=False
+    )
+    sandbox._search_results = []
+    capability.sandbox = cast(Sandbox, sandbox)
+
+    with pytest.raises(ToolFailed) as failure:
+        await capability._execute_code(
+            "for line in open('/documents/x/items.jsonl'): pass"
+        )
+
+    assert (".readlines()" in str(failure.value)) is expect_hint
+
+
 @pytest.mark.asyncio
 async def test_analysis_sandbox_failure_records_execution_and_fails_the_tool(
     temp_db_path,