Ray 070293bdca test: the messages max_tokens test follows anthropic 1.1's stop policy ...

anthropic 1.1.0 replaced the runner's refusal special case with an
explicit stop-reason table: every non-tool_use stop is terminal and its
tool_use blocks are never executed (1.0 executed a max_tokens turn's
complete blocks). The envelope already keys on the runner's history, so
the product adapts by design; only the test had the 1.0 behavior baked
in. It now asserts the version-appropriate shape on both sides, and the
run_messages comment describing the old behavior is reworded to name
the policy split.

Verified: 434 green on anthropic 1.1.0 (CI's failing config) and on
0.120.2 (the pre-1.1 branch); no-frameworks collection stays clean.

2026-08-27 03:37:47 +08:00

..

data

…

conftest.py

…

test_agent_tools.py

fix: the LiteLLM lanes hide litellm's bridge usage warning (#430)

2026-08-26 20:03:34 +08:00

test_client.py

fix: the slots accept any Mapping at runtime; eight docstrings stop calling cloud tool scoping server-side (#429)

2026-08-26 17:00:41 +08:00

test_flash_extraction.py

fix: indexing failures surface loud, chat envelopes append verbatim (#421)

2026-08-21 21:35:45 +08:00

test_issue_163.py

…

test_local_chat.py

test: the messages max_tokens test follows anthropic 1.1's stop policy

2026-08-27 03:37:47 +08:00

test_package_surface.py

…

test_page_index_md.py

fix: indexing failures surface loud, chat envelopes append verbatim (#421)

2026-08-21 21:35:45 +08:00

test_page_index.py

…