Files
OmniRoute/open-sse/services
Xiangzhe 2dfb730241 fix(sse): stop re-summarizing a universal handoff that never parses
A universal handoff whose summary comes back unparseable persists nothing,
so shouldGenerateUniversalHandoff keeps answering "generate" and the very
next model switch in the same session re-issues the same full-history
summarization call and discards the answer again — forever.

With a switch-heavy combo strategy (weighted, random, round-robin, p2c) the
models alternate on almost every turn, so that background call lands on a
large fraction of requests: an upstream call whose response nobody reads is
real money on a paid provider and real quota on a metered one. Measured on
the weighted 70/30 matrix, that inflated the observed openai share to 0.895
where routing actually delivered 0.70, and at the unit level 199 of 200
model switches issued a fresh discarded summarization call.

Back off per (session, combo) after an answer that is not a usable handoff:
exponential 5min -> 1h, cleared on the first successful generation, capped
at 500 tracked keys. Deliberately narrow — a transient upstream failure
(!response.ok) is NOT tracked, so it still retries on the next switch, which
is the behavior the context-relay path already depends on.

After the fix, same harness at n=200: 201 upstream calls for 200 requests
(1 extra, 0.5%), and the measured openai share equals the delivered share
(0.725). The unit guard drops 199 discarded calls to 1.

Refs #11552
2026-08-25 19:56:30 -03:00
..
2026-06-29 08:40:06 -03:00
2026-06-29 16:51:03 -03:00
2026-07-13 09:12:40 -03:00
2026-05-26 23:51:47 -03:00
2026-07-06 02:25:17 -03:00
2026-04-19 19:50:30 -03:00
2026-06-25 13:17:40 -03:00
2026-07-04 13:00:30 -03:00
2026-06-23 03:08:29 -03:00
2026-05-24 18:05:58 -03:00
2026-07-13 09:12:40 -03:00
2026-07-04 13:00:30 -03:00
2026-06-13 17:27:40 -03:00
2026-05-26 23:51:47 -03:00
2026-06-29 08:40:06 -03:00
2026-07-13 09:12:40 -03:00
2026-07-04 13:00:30 -03:00
2026-05-23 01:46:59 -03:00
2026-05-24 18:05:58 -03:00
2026-07-13 09:12:40 -03:00
2026-07-13 09:12:40 -03:00
2026-05-10 00:55:06 -03:00
2026-06-19 06:49:01 -03:00
2026-05-29 12:44:29 -03:00
2026-06-07 07:20:02 -03:00
2026-07-04 13:00:30 -03:00
2026-06-21 08:56:51 -03:00
2026-07-13 09:12:40 -03:00
2026-07-02 10:47:13 -03:00
2026-07-13 09:12:40 -03:00
2026-06-04 20:05:38 -03:00
2026-05-10 00:55:06 -03:00
2026-05-10 00:55:06 -03:00
2026-06-25 13:17:40 -03:00
2026-05-10 00:55:06 -03:00
2026-05-10 00:55:06 -03:00
2026-06-13 17:27:40 -03:00
2026-06-19 06:49:01 -03:00
2026-06-04 20:05:38 -03:00
2026-07-06 02:25:17 -03:00
2026-06-22 03:17:02 -03:00