Ian 5227960e99 fix(compaction): fall back to reasoning text when the summary has none ... A reasoning model can spend the whole summary output budget thinking and return only a reasoning item. _extract_text read only output messages, so compaction logged 'summary returned no content' and the agent failed. Use the reasoning text, with a warning, when there is no output text.		2026-10-06 21:33:30 -04:00
..
agents	fix: stop the run after finish_pr_review (#1451)	2026-10-05 16:25:33 -04:00
config	fix(preflight): give the startup model check its own 30s timeout instead of LLM_TIMEOUT	2026-10-04 23:12:23 +03:00
core	Stop false "ended without calling finish_scan" error on PR reviews (#1449)	2026-10-05 19:58:20 -04:00
interface	feat(cli): add -r for --resume and a title column to the resume picker	2026-10-06 07:51:00 +03:00
llm	fix(compaction): fall back to reasoning text when the summary has none	2026-10-06 21:33:30 -04:00
report	feat(cli): add -r for --resume and a title column to the resume picker	2026-10-06 07:51:00 +03:00
runtime	fix(docker): drop the module docstring	2026-10-05 03:00:25 +03:00
skills	docs(skills): refresh framework behavior and security testing guidance (#1372)	2026-09-29 10:11:02 -07:00
telemetry	refactor(telemetry): keep only the unraisable hook, no docstrings	2026-10-04 18:35:07 +03:00
tools	refactor(agents): replace respond_to_user with a text-free wait_for_user	2026-10-05 04:09:17 +03:00
utils	feat(cli): strix cloud — managed platform CLI (login, scans, billing, and the rest of the API) (#1177)	2026-09-01 14:39:34 -04:00
__init__.py	Open-source release for Alpha version	2025-08-08 20:36:44 -07:00