fix(compression): exclude completion tokens from compression trigger (#12026)

Cherry-picked from PR #12481 by @Sanjays2402.

Reasoning models (GLM-5.1, QwQ, DeepSeek R1) inflate completion_tokens
with internal thinking tokens. The compression trigger summed
prompt_tokens + completion_tokens, causing premature compression at ~42%
actual context usage instead of the configured 50% threshold.

Now uses only prompt_tokens — completion tokens don't consume context
window space for the next API call.

- 3 new regression tests
- Added AUTHOR_MAP entry for @Sanjays2402

Closes #12026

scripts/release.py

@@ -177,6 +177,7 @@ AUTHOR_MAP = {
     "364939526@qq.com": "luyao618",
     "hgk324@gmail.com": "houziershi",
     "176644217+PStarH@users.noreply.github.com": "PStarH",
+    "51058514+Sanjays2402@users.noreply.github.com": "Sanjays2402",
     "906014227@qq.com": "bingo906",
     "aaronwong1999@icloud.com": "AaronWong1999",
     "agents@kylefrench.dev": "DeployFaith",