Evidence

An index of every claim on this site, with its source, measurement conditions and date.

ClaimEvidenceSourceVersionObserved
Spool v0.6.2 shipped on 2026-08-24 as a Developer ID–signed, Apple-notarized build for Apple Silicon Macs.Releasegithub.com/KIM-ocean-HZ/spool/releases/tag/v0.6.2 (opens in a new tab)v0.6.2
Spool v0.6.2 has three entry points: a desktop app, an MCP server, and a CLI engine slot. (the CLI engine slot runs the user's own Claude Code, Codex or Gemini CLI as a subprocess; Spool has no command line of its own)Releasegithub.com/KIM-ocean-HZ/spool/blob/v0.6.2/src-tauri/src/engine.rs#L1-L26 (opens in a new tab)v0.6.2
v0.6.2's MCP server exposes 20 tools: 13 read-only and 7 behind a separate write switch. (counted from the released build on 2026-09-23)ReleaseCounted with a tools/list call against the notarized v0.6.2 release on 2026-09-23; the server source is not linked because it quotes private content.Checked v0.6.2
769 tests passed at the v0.6.2 tag: 627 TypeScript, 129 main-crate Rust and 13 sidecar Rust, with 4 skipped by design. (run on 2026-09-23; two timing-sensitive Rust tests failed on the first of 11 main-crate runs)Test suiteRun at the v0.6.2 tag on 2026-09-23 by my AI coding agent; the log is not public, and the suites rerun from the tagged source.Checked v0.6.2
Before v0.6.2, six evaluation rounds made 557 real API calls. (2026-08-20 to 08-24)LogEvaluation log in the Spool repository; not linked because it quotes real library content.Checked v0.6.2 –
The six pre-release evaluation rounds cost at least ¥29.37. (token usage times the vendor's price list; failed calls reported no usage, so this is a floor)LogEvaluation log in the Spool repository; not linked because it quotes real library content.Checked v0.6.2 –
Compressing two projects by 30% and 38% kept 39 of 40 answers correct; the uncompressed baseline scored 40/40. (round six: 20 questions, each asked twice per arm; one model; answers graded by the coding agent; the gap is within noise)LogEvaluation log in the Spool repository; not linked because it quotes real library content.Checked v0.6.2
Four release blockers found in pre-release testing were fixed and re-tested before v0.6.2 shipped. (found in round five on 2026-08-23; re-tested in round six on 2026-08-24)Test suitegithub.com/KIM-ocean-HZ/spool/blob/v0.6.2/src-tauri/sidecar/src/main.rs#L654 (opens in a new tab)v0.6.2 –
Two envelope defects from the last round shipped unfixed: failed calls report no usage, and one empty reply was marked ok. (still open as of 2026-09-23)Releasegithub.com/KIM-ocean-HZ/spool/blob/v0.6.2/src-tauri/sidecar/src/main.rs#L86-L93 (opens in a new tab)v0.6.2
A linear cost estimate landed within ±30% for only 46% of 89 real bills, so the app shows no price. (round five; the bar set in advance was 90%)LogEvaluation log in the Spool repository; not linked because it quotes real library content.Checked v0.6.2
Medium reasoning gave no compression gain over low; it was 3.5× slower and 3.4× costlier. (n = 5 vs 10 runs on one project and one setting, round five; a 5-point gain was required in advance)LogEvaluation log in the Spool repository; not linked because it quotes real library content.Checked v0.6.2
Each project lists what to watch; a follow-up runs the user's own Claude Code with web search and queues sourced findings for approval.Releasegithub.com/KIM-ocean-HZ/spool/blob/v0.6.2/src-tauri/src/lib.rs#L129 (opens in a new tab)v0.6.2
A fix passed its tests but covered one of two relation types; the next offline re-check found 20 exposed blocks. (round six, on a copy of the library; the complete fix landed before the v0.6.2 tag)LogRound-six re-check on a library copy and the follow-up fix commit; not linked because both name a real project.Checked v0.6.2
Spool's main process links no HTTP or TLS library; the only network client in the app is an opt-in subprocess, spool-ai. (MCP clients and the user's own CLI make their own network calls)ReleaseMain-crate dependency tree (cargo tree) at the v0.6.2 tag, checked on 2026-09-23; reproducible from the tagged source.Checked v0.6.2
AI clients get no access until the user turns on the MCP server, and writing has a second, separate switch. (the write switch is on by default once the MCP server is on)Releasegithub.com/KIM-ocean-HZ/spool/blob/v0.6.2/src/stores/settingsStore.ts#L329-L336 (opens in a new tab)v0.6.2
AI-written blocks are append-only and carry the client's name; an AI cannot edit or delete what the user wrote.ScreenshotA real MCP write against the notarized v0.6.2 release in a demo library on 2026-09-23, shown on this page; the server source is not linked because it quotes private content.Checked v0.6.2
A compressed draft that dropped a number or date cannot be saved, and the original text stays on each block. (compression is opt-in, off by default and uses the user's own API key; keeping originals can be turned off)Releasegithub.com/KIM-ocean-HZ/spool/blob/v0.6.2/src/stores/compressStore.ts#L667-L695 (opens in a new tab)v0.6.2
A follow-on study of project memory across AI clients is under way.LogStudy protocol and harness records, kept private until results exist.Checked

Multi-robot control for warehouse sorting

ClaimEvidenceSourceObserved
R&D intern, Jun–Aug 2026.Written confirmationConfirmed in writing by my supervisor at Libiao Robotics; not publicly linkable.Checked –
Worked on a simulation-based multi-robot control system for warehouse sorting, integrating task scheduling, path planning, traffic control, and robot communication.Written confirmationConfirmed in writing by my supervisor at Libiao Robotics; not publicly linkable.Checked –
Reorganized an existing operational simulation into six layers and added seven architecture tests to improve maintainability.Written confirmationConfirmed in writing by my supervisor at Libiao Robotics; not publicly linkable.Checked –
Validated the architecture by replacing GDI+ with SkiaSharp through changes limited to the rendering layer.Written confirmationConfirmed in writing by my supervisor at Libiao Robotics; not publicly linkable.Checked –
Diagnosed deadlocks and rebuilt traffic control around spatiotemporal reservations, validating 20 robots over 90,000 simulation ticks without a collision.Written confirmationConfirmed in writing by my supervisor at Libiao Robotics; not publicly linkable.Checked –
On my own initiative, I added a learned local layer: a PPO policy adjusts each robot's speed along its A* path. (simulation only; not covered by my supervisor's written confirmation)LogMy own code and benchmark report in the internship codebase; company code, not public.Checked –
With four robots, the trained policy cleared all conflicts and deadlocks and cut average task time from 35.4 s to 27.3 s. (one fixed-seed simulation run per scenario, against the same run with the learned layer off; task time also fell with six robots and in a head-on corridor; throughput never dropped below the baseline; with six robots, conflicts rose from 1 to 7; traffic control resolved them and no task failed)LogMy own benchmark report in the internship codebase; company code, not public.Checked