Commit Graph
15 Commits
Author SHA1 Message Date
4986b8644f docs(experiment): record indexed discovery model costs
Retain both correctness-equal wide-PHI pairs, complete discovery costs and the remaining whole-function native computation boundary.

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 12:22:02 +00:00
e678be3f9d docs(experiment): record selected operand model results
Both adapters satisfy the fixed wide-PHI oracle with one capture and selected slots. Preserve mixed timing/token costs and the observed discovery overhead rather than inferring a Code Mode advantage.

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 12:12:09 +00:00
a225d7c552 fix(experiment): retain direct analysis failures in trial ledgers
Record the second PHI model pair, including the native timeout and successful retry; keep adapter conclusions limited to observed whole-task costs.

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 11:57:25 +00:00
71be07de42 docs(experiment): record real-model phi projection results
Both answers satisfy the fixed four-alternative oracle with one VM capture and scoped facts. Preserve whole-task costs and source checks, including the direct reference-name lookup miss that needs a shared discovery fix.

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 11:30:18 +00:00
f08c191ed3 docs(experiment): compare compact call counts in real model tasks
Retain the successful answer and source checks from both adapters and all measured task costs. Both avoid call-set paging; direct beats Code Mode in the new sample and before/after effects remain mixed.

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 10:07:36 +00:00
da6f5470be perf(experiment): summarize retained calls before paging
Expose a compact call distribution in snapshot metadata through the shared validated owner. Preserve coverage, unknown targets, dead rows, immutable selected reads, and empty versus unavailable semantics. Retain the same boundary question and oracle for paired real-model comparison.

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 10:00:04 +00:00
fb9adbf384 docs(experiment): record real-model call boundary results
Both lanes satisfy the pre-pinned SQLite task with one retained VM analysis. Record full answer/source review, actual model and resource counters, and mixed context costs without a general efficiency claim.

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 09:53:53 +00:00
f9f9dc209d feat(experiment): retain call facts beyond full graph capacity
Separate native call and boundary-value ownership from the bounded recovered graph. Validate facets independently and preserve shared identities, source evidence, and explicit partial coverage. Pin the SQLite boundary task and oracle before paired real-model trials.

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 09:46:42 +00:00
04c081fc61 experiment(re): verify model reference aggregation against machine calls
Record both completed model workflows, whole-task costs and source/identity checks. Compare every VM direct-call pair with independent disassembly, preserve indirect-call limits, verify unpatched stock through the shared CLI/API, and retain failed/partial research costs.

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 09:01:54 +00:00
3aa685db39 feat(experiment): compose shallow outgoing references with explicit scope
Share one native parser for both directions, preserve occurrence identity and unknown function applicability, push kind filters to Kuna and reuse sources across fields/pages/scopes. Verify real SQLite machine references independently, including calls omitted from optimized IR and VM queries beyond graph capacity. Pin the aggregate model task before its paired runs.

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 08:48:24 +00:00
56182b2217 experiment(re): verify cross-function model answers and mixed adapter costs
Record the pre-pinned explicit-return-path pair with source and identity validation. Both models complete the context-flow task; Code Mode has fewer MCP requests without a demonstrated overall efficiency advantage. Preserve large-function and shallow-reference coverage limits.

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 08:20:24 +00:00
73db4fad54 feat(experiment): compose bounded native byte windows with RE facts
Add shared SDK/CLI/MCP byte reads over the existing Kuna data protocol, preserve partial batches and exact u64 ranges, and retain complete source Evidence. Reuse named read lifecycles, bound aggregate hex expansion, and verify stock/native/direct MCP paths plus a shipped-file byte oracle before pinning a table-dispatch model task.

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 07:17:18 +00:00
9e1b39358a experiment(re): pin a model task over recovered Pragma code
Exercise the restored code facet with a question fixed before trial and independent instruction anchors, using identical envelope guidance in both atomic calling modes.

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 06:52:03 +00:00
dc022bcd0f experiment(re): separate model rounds from MCP requests in fair trials
Validate per-response usage totals, retain the negative large-VM comparison and qualify the client executor, cache and investigation-depth differences. Add optional common envelope/stopping guidance without relabeling historical runs.

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 06:29:26 +00:00
5aa78c873e experiment(re): pin coverage criteria for a large SQLite VM task
Record independent machine-code anchors before model trials, separate cache regimes and incomplete answers, and exercise real recovered-IR capacity failure without hiding retained code.

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 06:09:46 +00:00