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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Compare sequential and overlapping requests through both real MCP adapters
with the same preserved engine, selected instruction windows and full graph.
Retain the unexplained model-run anomaly without claiming a speed fix.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Verify both repeated answers and exact discovery calls against unchanged
source facts. Record complete task costs, overlapping requests, unexplained
capture-time variation and the client executor available to both lanes.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Review both complete answers against the precommitted oracle and independent
ELF instruction bytes. Retain all costs, validation retries, discovery noise
and the limits of this single observational pair.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Preserve complete graph facts with a bounded lossless native wire codec and
shared paged Evidence views. Verify both MCP adapters and retained legacy
records, then freeze a control/data-flow question and oracle for real agents.
[AUTOMATED] Exploratory native patch; no upstream integration or PR.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
[AUTOMATED] Add a gated diagnostic overlay and production-owner profiling runner. Preserve actual phase/resource results, disabled-output control and lossless full-graph encoding feasibility without claiming a public codec or model speedup.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Discover declared methods through the shared reference owner before requesting named contracts; preserve the existing default and runtime capability semantics.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Keep operation and slice defaults compact; preserve exact input slots and phi edges, distinguish unretained seeds, and align advertised relation schemas with runtime validation. Pin a seeded wide-PHI model task after real public MCP verification.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Share displayed method names with direct registration, support explicit multi-name selection and unmatched terms, and cache immutable schema conversions by schema identity. Export input-side schemas so defaulted fields stay optional; verify both actual MCP catalogs and named contracts before repeating the unchanged model task.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Share native membership and operand ownership across full and projected facts. Preserve exact phi bindings and definition frontiers when the full graph is unavailable, keep CFG/use coverage explicit, and expose selected reads through the same CLI/SDK/MCP contracts. Verify real SQLite/zlib fidelity, encoded fallback, bounded metadata, and cache reuse; pin the next real-model question and oracle.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Preserve a diagnostic-only patch and reproducible lossless encoding/projection probe. The real VM graph exceeds several public capacities; selected SSA neighborhoods are much smaller, with explicit frontiers. Record actual resource costs and keep public engine/API limits unchanged.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Check the native cleanup Result before clearing the lease and preserve cleanup resources through the MCP error adapter. Reproduce the old false success, then verify real SDK close/replacement ownership and both MCP retry paths with explicit fault injection.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Retain both initial real-model answers and whole-task costs. Both prove the core context connection but omit the oracle-required return-code distinctions; clarify that requirement before the next pair without changing the oracle or supplying addresses.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Preserve the rejected cross-function launch caused by a non-embedded Cargo test build replacing the mutable CLI. Check explicit engine identity before profile creation and after the task; use an independent executable copy for measured runs.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Keep recovered callee identities separate from fspec annotations and SSA argument values separate from passing storage. Add selected calls and function-input reads through the shared fact owner, with real SQLite MCP coverage and a pre-pinned cross-function model task.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Reject oversized error delivery with explicit omission metadata, account for JSON escaping, and retain source observations and their lookup after failure. Reproduce and verify the real MCP path without claiming model-token savings from byte counts.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Record matching six-byte table oracles, real byte-tool use, model response counts and whole-task costs without generalizing a single paired observation.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Keep actual response/MCP counts, whole-task token usage and resource receipts separate. Both adapters complete the local task with explicit missing IR; no general speedup is inferred.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Bound compact native JSON with the existing writer, keep a valid code facet when the graph cannot fit, and pass the supervised byte budget explicitly. Verify real SQLite Parser/Pragma captures, exact preserved C/mappings/graph facts and public MCP reads. Keep string inventory parsing/projection under its own owner.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
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 <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Freeze parsed inventories once at their owning boundary and share the rule with native IR and function views. Verify the real SDK mutation regression and retain corrected equal-depth SQLite model costs, including persistent-cache limitations.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Keep the direct adapter benchmark instructions consistent with its actual registered tools; retain historical trial profiles unchanged.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Keep validated code available when native graph extraction is unavailable, bind output to the actual input/entry, preserve cancellation observations, and share batch source/error semantics. Add filtered function/alias reads and slice field selection across adapters.
Verified 38 focused tests, targeted lint, real stock/native MCP workflows, large SQLite graph-capacity fallback, and real cold/warm MCP reuse. Retain actual model costs and unequal-depth/selection limitations instead of claiming general superiority.
BREAKING CHANGE: Experimental native snapshots may succeed with readable code and an unavailable recovered_ir facet. Inspect facets before graph reads; unavailable graph counts are null/unknown.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
A real model conflated an optimized CFG edge with the bytes at its instruction origin. Make provenance explicit and add bounded, batched instruction windows from the existing Kuna CLI, preserving exact bytes, per-window failures and Evidence. Record the task-cost comparison without treating the incomplete machine-path answer as an equal-quality win.
Verified 33 focused tests, targeted lint, real stock/patched MCP decoding with mixed success, and a real 4096-row capacity run under the resource observer.
BREAKING CHANGE: Experimental operation.address/addresses and block.start become origin_address/origin_addresses and origin_start. Printed CFG target_address becomes target_origin; historical source captures are unchanged.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
The real model uses recovered controllers and indexed phi/value relations, but the first native-IR trial still does not beat the traditional local-question workflow. Record actual whole-task usage and prepare value-origin and small-function counterexamples.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
[AUTOMATED] Preserve the opt-in pinned Kuna exporter as a reproducible source patch. Share typed graph/value reads and derived control dependence through the SDK, CLI and MCP adapters, retaining unknown runtime and memory semantics.
Validated 29 focused tests, lint, actual diagnostic/native MCP workflows and a real zlib CLI composition. C and line mappings match the prior stock capture. Full upstream corpus/workspace gates and revised real-model costs remain unverified.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Retain failed attempts, cached input accounting and payload-exit process-family counters. The first comparison favors the traditional workflow; keep the negative finding explicit.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Record genuine Code Mode use and full model usage rather than response-only estimates. Describe return shapes, permit byte-budgeted internal C reads, separate guest CPU from analysis deadlines, and move subsequent model profiles outside the source tree. Verify lease, admission, cleanup-retry and cancellation semantics.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Add a compact rea-codemode MCP server, bounded QuickJS execution and shared SDK/direct adapters. Reuse native target and process owners; retain evidence and lease-scoped snapshots. Extend the real-model trial runner with an isolated experimental MCP registration. Capability and evaluation work remains in progress.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Verify three repaired zlib mappings, a SQLite call guard and all ordinary 16-bit header values against retained native evidence. Record producer omissions, failed-run costs and the small-function context counterexample. Preserve existing capture outputs with exclusive writes.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Apply the interior-reference counterexample to the facade: label exact-address scope and emit location endpoints while preserving caller selectors separately. Carry canonical target-content provenance through experimental MCP replies and verify it on the real client. Keep original measurements pinned to the v1 response shape. Nine experiment checks and real Kuna lifecycle/context checks pass.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Expose source-owned reference kind, endpoints, function identities and instruction text for experiments. Keep the existing address-only public result and retained-cache shape; materialize richer facts only when explicitly requested. Record prior art, composition rules and the distinction between fact, transport and compute units. Verified 18 producer boundary cases and an independently checked native interior-reference example.
Co-authored-by: gensokyo-dev <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
