NCBM 836ac8d6f8 cli/history: never collapse a turn's ends ...

The mixed policy previewed the user row, so a long prompt came back truncated
even though it is half of what the turn is about. Both ends - the human's
message and the model's answer - now print in full at every verbosity level;
--preview remains the explicit one-line skimmer that collapses them too.

Tests cover the ends staying full in the default and -v views (and the rounds
between them staying one-liners) plus a long-prompt regression.

2026-09-22 21:15:07 +08:00

..

test_agent

agent/tools: report missing required arguments before running

2026-09-19 09:50:13 +08:00

test_cli

cli/history: never collapse a turn's ends

2026-09-22 21:15:07 +08:00

test_config

cli/config: --auto-continue flag and [agent] auto_continue_limits

2026-09-09 22:47:39 +08:00

test_lmproto

lmproto: add DeepSeek Anthropic client

2026-08-01 02:30:19 +08:00

test_memory

memory: persist session access grants

2026-09-09 22:17:34 +08:00

test_runtime

runtime/mcp: spawn servers in their own process group

2026-09-19 11:05:33 +08:00

test_tools

prompting: let Ctrl+C cancel poll-based prompt reads

2026-09-22 19:28:03 +08:00

__init__.py

project: init

2026-06-25 23:22:45 +08:00

conftest.py

test/tools: catalog, grants, and async tool helpers

2026-07-24 14:57:03 +08:00

test_prompting.py

prompting: let Ctrl+C cancel poll-based prompt reads

2026-09-22 19:28:03 +08:00