3 Commits

Include renames

Author	SHA1	Message	Date
3 people	f521ec72f5	docs(experiment): report paired long-wait results ... Both models retain correct selected-case answers and use one client wait. Record complete costs, timeout/output-budget recovery and mixed adapter outcomes without attributing a causal speedup. Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>	2026-10-16 16:12:11 +00:00
3 people	3348688579	docs(experiment): record real-agent selected-case results ... Report both correct answers and complete task costs. Preserve the native latency and client polling confounds; no general Code Mode advantage is established. Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>	2026-10-16 15:58:53 +00:00
3 people	f44dca9c37	feat(experiment): expose native case-to-edge facts ... Share exact jump-table metadata and paged case relationships across CLI, MCP and Code Mode. Keep labels, row identities, recovered edges and machine defaults separate; reclaim independent facts under output capacity. Verify all 182 SQLite table targets against ELF bytes through both MCP adapters and retain cases/calls when a real 2 MiB native budget omits IR. Freeze the next analyst question and oracle before real-model trials. [AUTOMATED] Experimental native patch; no upstream integration or PR. Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>	2026-10-16 15:32:12 +00:00