NCBM 879e28ea4c core/agent: synthetic_tool review always when stack non-empty ...

needs_review is true for any non-empty stack so end-of-turn inject
keeps firing under synthetic_tool. Message history keeps only the last
todo-nag tool pair (dedupe by todo-nag- tool_call_id).

2026-07-20 16:20:01 +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/agent+config: configurable compact prompts

2026-07-15 14:45:12 +08:00

test_compact.py

ci/lint: ruff format pass and fix compact seed test typing

2026-07-15 11:36:01 +08:00

test_confirm.py

core/cli: YOLO mode on|off|once for soft destructive confirms

2026-07-17 14:55:34 +08:00

test_loop.py

ci/lint: prek commit gateway (ruff check/format + basedpyright)

2026-07-18 14:10:04 +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_responses_bridge.py

core/agent: classify empty/truncated/missing stream terminals as errors

2026-07-18 00:56:45 +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_todo_stack.py

core/agent: synthetic_tool review always when stack non-empty

2026-07-20 16:20:01 +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: route OpenAI provider through Responses API

2026-07-15 20:59:47 +08:00