NCBM b1223c8189 core/agent: calibrate soft-compact with last-request prompt_tokens ...

After the first model call, scale char-based token estimates by
API/resolved prompt size so budget checks track near-real tokens.
/compact uses the same calibration when available.

2026-07-15 11:11:15 +08:00

..

test_agent

core/agent: calibrate soft-compact with last-request prompt_tokens

2026-07-15 11:11:15 +08:00

test_cli

core/agent+cli: treat last-request prompt_tokens as context size

2026-07-15 11:07:52 +08:00

test_config

core/agent+config: soft context budget in estimated tokens

2026-07-15 10:58:01 +08:00

test_lmproto

core/lmproto: await async AsyncResponse.content

2026-07-15 10:41:33 +08:00

test_memory

ci/lint: per-file ignores for tests in ruff and basedpyright

2026-07-15 10:35:30 +08:00

test_runtime

test/memory+runtime: cover store and client factory

2026-07-14 17:25:22 +08:00

test_tools

ci/lint: per-file ignores for tests in ruff and basedpyright

2026-07-15 10:35:30 +08:00

__init__.py

project: init

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