Niansia a8bb0803ef fix: fall back from a failed context summary without long retries (#10436) ...

* fix: fall back from a failed context summary without long retries

The summary request in LLMSummaryCompressor used the provider's default
retries, so an exhausted quota (HTTP 429) was retried five times with
backoff before compression fell back to truncation, holding up the reply
even after switching the chat model.

Request the summary once, since a failure already falls back to
truncation. When the context still exceeds the limit, drop whole rounds,
oldest first, and recount after each one until it fits, instead of
halving the messages once without checking again. The latest round is
always kept.

Fixes #10433

* fix: leave the token count out of the fallback warning

CodeQL flags values from count_tokens() as sensitive data, so logging the
count in the new warning raised a clear-text logging alert. The count is
already in the "Compress completed" line just before, so drop it here.

* fix: log how many rounds the context fallback dropped

2026-10-08 22:43:14 +09:00

..

test_context_manager.py

fix: fall back from a failed context summary without long retries (#10436)

2026-10-08 22:43:14 +09:00

test_token_counter.py

fix: estimate emoji token cost above the plain text rate (#10216)

2026-09-27 11:24:42 +08:00

test_truncator.py

fix: 截断器丢失唯一 user 消息导致智谱等 provider 返回 400 (#6581)

2026-03-20 10:06:20 +08:00