Files
Codeman/test
Codeman maintainer a5a1b6f9a2 fix(custom-model): pi is told the endpoint's context window
A pi session on a custom endpoint got a model list entry with only the
model id. pi then takes the model for a 128,000-token one (its footer
reads "/128k") and asks for 16,384 reply tokens, so on a 65,536 or
32,768 window it never compacts before the server's real window is full.

The entry now carries `contextWindow` (the full window) and `maxTokens`
(a quarter of it, 8,192 at most) whenever the endpoint's context length
is known: the same two figures the DeepSeek Harness patch already
carries, now from one helper. An unknown length writes neither, as
before.

Measured on pi 1.5.2: with both fields `pi --list-models` shows the
window, and the request carries `max_tokens: 8192`.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 09:53:12 +01:00
..
2026-06-19 17:58:06 -04:00
2026-06-19 17:58:06 -04:00
2026-08-22 14:13:57 +02:00
2026-07-20 02:36:02 +02:00
2026-06-19 13:10:17 -04:00