NCBM 0a3127454d core/agent: char-based token estimate fallback for usage ...

When API usage is missing, estimate prompt/completion tokens at ~4
chars per token and mark source as estimate (or mixed when combined).

2026-07-15 10:52:37 +08:00

..

test_budget.py

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

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

test_compact_summarize.py

core/cli+agent: /compact and resume latest by workspace recency

2026-07-15 10:03:22 +08:00

test_compact.py

core/agent: soft context compact and cooperative cancel points

2026-07-14 23:42:50 +08:00

test_confirm.py

core/agent: optional confirm hook on ToolRegistry execute

2026-07-14 23:30:10 +08:00

test_loop.py

core/agent: emit UsageEvent from stream and non-stream rounds

2026-07-15 10:47:59 +08:00

test_parallel_tools.py

core/agent: parallel tool calls and tool-result char budget

2026-07-14 23:24:11 +08:00

test_stream_merge.py

core/lmproto+agent: use normal stream API for chat loop

2026-07-14 22:40:15 +08:00

test_tools.py

test/agent: cover tools, loop, and memory-backed ChatAgent

2026-07-14 17:45:47 +08:00

test_usage.py

core/agent: char-based token estimate fallback for usage

2026-07-15 10:52:37 +08:00