NCBM 7d6e367143 tools: keep tool output whole and let the request-prep pass cap it ...

run_argv, run_argv_batch, fetch, fetch_local, and the vcs tools now return
their output whole, so the request-prep cap trims it on the wire and names
its document. A fetched page or a long log reads on from the tool message,
with no re-fetch and no re-run.

The run_argv_batch run budget stays as an execution guard: it stops a
runaway batch from spawning further huge-output steps.

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>

2026-10-29 14:13:36 +08:00

..

test_agent

core/agent: cap tool results in the request-prep pass

2026-10-29 10:04:32 +08:00

test_cli

test: cover the limit prompt line while a notification offers buttons

2026-10-26 00:52:58 +08:00

test_config

core/config: re-read [skills] on reload

2026-10-21 20:26:08 +08:00

test_lmproto

core/lmproto+agent: carry image parts on user and tool messages

2026-10-21 18:43:29 +08:00

test_memory

config: rename the DeepSeek flash model to deepseek-flash

2026-10-06 21:22:35 +08:00

test_runtime

core/tools: show images instead of describing them

2026-10-21 18:43:29 +08:00

test_skills

test: make the suite run under Windows

2026-10-21 19:28:49 +08:00

test_tools

tools: keep tool output whole and let the request-prep pass cap it

2026-10-29 14:13:36 +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

test: cover the body a prompt notification carries

2026-10-24 04:22:00 +08:00