haiku.rag/tests/sandbox
Yiorgis Gozadinos bae359e3bf
Align the MCP guidance with the analysis instructions and move to Monty 0.0.23
The execute_code description gains the toc.json node shape, the patterns
the evals put into the analysis instructions (one list_documents call to
map a title to an id, files carry no source, toc before search for a known
document, doc_item_refs are items self_refs, chunk ids join files and are
not citations) and the sandbox's read-only, no-network, time-limit and
output facts, which the analysis instructions now state too. The skill
gains pictures as images, image search when offered, and citing chunk
metadata locators. docs/mcp.md lists the interpreter's limits under Code.

pydantic-monty>=0.0.23 brings collections, itertools, functools,
dataclasses, function decorators and str.format into the sandbox; every
layer names the same modules, and a test imports them. Monty now caps host
callbacks per checkout at 1000 by default; the sandbox raises it out of
reach, since the time budgets govern.
2026-09-07 12:02:33 +03:00
..
__init__.py Delete the standalone QA and analysis agents 2026-05-19 11:39:20 +03:00
conftest.py Delete the standalone QA and analysis agents 2026-05-19 11:39:20 +03:00
test_models.py Delete the standalone QA and analysis agents 2026-05-19 11:39:20 +03:00
test_sandbox.py Align the MCP guidance with the analysis instructions and move to Monty 0.0.23 2026-09-07 12:02:33 +03:00
test_sandbox_multi_db.py One reference and one placement for a database 2026-09-03 15:12:08 +03:00
test_sandbox_multimodal.py Delete the standalone QA and analysis agents 2026-05-19 11:39:20 +03:00
test_sandbox_toc.py Make toc.json item_range the line slice it documents 2026-09-07 10:27:02 +03:00