fix(newos4): GLM review follow-ups for AI read/context (v4.6.47)

- loop guard: a mutation unblocks the replay but no longer erases the repeat counter
  (identical mutating calls could loop forever)
- tool traces are per agent tag, flushed in a catch as well as on success, ring-buffered
  (first 2 + last 10) so verification reads survive
- read_file notes are metadata only (path/range/next_offset); no file bodies, no secrets,
  and web_search/web_fetch output is excluded from durable context (injection surface)
- trace is role:'system' (was 'assistant' — the model re-read it as its own answer)
- surrogate-safe pagination, 500 floor / 16000 cap, prompt limits aligned
- prompt now names checks that exist in the in-page terminal (test, grep -n, wc -l)
- compressed summary capped at 4000 chars; denied-destructive tool result carries tool_call_id

0 files changed, 0 insertions, 0 deletions