xlrrrr
020a879944
feat: track evolution candidate processing lifecycle
2026-04-16 22:04:22 +08:00
xlrrrr
79a98abda7
fix: CAPTURED skills write to correct host agent skill dir
2026-04-10 20:57:17 +08:00
yc111233
f3a064df1c
fix: address 8 runtime bugs found during code review
...
1. Race condition on _addressed_degradations (evolver.py) — add asyncio.Lock
2. Silent exception swallowing in wait_background (evolver.py) — log failures
3. Workspace cleanup could delete user files (tool_layer.py) — add mtime guard
4. WAL cleanup without lock check (store.py) — probe for DB lock first
5. Edit distance threshold too loose (analyzer.py) — adaptive threshold + ambiguity rejection
6. Message truncation drops context (grounding_agent.py) — add truncation notice
7. Whitespace-only empty response not detected (grounding_agent.py) — strip before check
8. Tool name reverse parsing with __ (client.py, manager.py) — use rsplit
2026-04-06 01:02:35 +08:00
warren618
1257f4cfee
fix(evolver): use stem-style matching for confirm/reject/skip keywords
...
Per reviewer feedback: keep strict \byes\b / \bno\b word boundaries to
prevent false positives, but widen confirm/reject/skip to stem-style
\bconfirm\w*\b etc. so common LLM variants like "confirmed", "rejected",
"skipping" still parse correctly instead of falling through to the
default False path.
2026-03-27 13:34:20 +08:00
warren618
9333eaed42
fix(evolver): use word-boundary matching in _parse_confirmation to prevent false positives
2026-03-26 12:06:11 +08:00
spidercatfly
6ff4861f88
initial commit
2026-03-24 16:03:22 +08:00
