docs: seal 1.24.1 reliability repair delivery and retained-state evidence

This commit is contained in:
Agent Workbench Dev
2026-11-03 08:56:37 +08:00
parent ba07713a36
commit 7313fd2588
211 changed files with 368713 additions and 11 deletions
+8
View File
@@ -134,3 +134,11 @@ docs/live-original-purge-e-offline-*.txt binary
docs/original-purge-release-f-evidence/** -text
docs/original-purge-release-f-evidence/files/** binary
docs/original-purge-release-f-offline.txt binary
docs/delivery-reliability-g-evidence/** -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol
docs/delivery-reliability-g-evidence/**/*.log binary
docs/delivery-reliability-g-evidence/**/*.tap binary
docs/delivery-reliability-g-evidence/**/*.txt binary
docs/delivery-reliability-g-offline.txt binary
docs/delivery-reliability-g-git-index.txt binary
docs/delivery-reliability-release-identity.json -text
+4 -4
View File
@@ -1,8 +1,8 @@
# Agent Workbench项目执行规范
当前优先G:用户要求先修完已总结问题。1.24.1已实现完整变更批次同轮结算后审查交接、必要小源码先保留和原生容量/剩余预算准确诊断;停止、新提案、冲突、未知与篡改不冒充完整交接,应用后仍显式续接。E原第7–12请求离线复现估算完全一致,修复前六文件保留6/5/5/4/2/2,修复后均6/6且原硬预算保持。正式仍1.24.0/PID36552/Provider,当前正在完成1.24.1冻结回归、两视口和发行安装收口,见docs/QA-DELIVERY-RELIABILITY-G.md。新真实模型/Purge收益未重测,旧失败不改写;用户最新优先修复覆盖下方历史“先补原生窗口”的顺序,不以旧Escape暂停阻塞源码工作。
G已完成本地交付:1.24.1完整批次同轮结算后交还审查、小源码先保留和容量/剩余预算准确诊断已修复;应用后显式续接,未知/篡改/冲突/停止不冒充完整交接。冻结155/155、原件六次均6/6源码且硬预算保持、源码ZIP522输入/22编译一致、两份10组界面、11组批次、实际便携和12组安装及安装副本16+9组通过。最终source ba07713/候选20261103000853284,正式原PID36552/Provider、42项目/58会话/4953记录/10329事件/2850工件及模型中心精确保持,9229关闭;正式原生窗口3项/2图及随后再次原状态核对通过。200份/43758910字节证据离线通过,当前身份见docs/delivery-reliability-release-identity.json及docs/QA-DELIVERY-RELIABILITY-G.md。原失败与新真实模型/Purge未重测的边界保持,不把离线复现当真实交付收益。
当前F固定安装已完成:1.24.0/source c03860d/候选20261102152844546,原PID36552/Provider保持,原42项目/58会话/4953记录/10329事件/2850工件/公开模型中心精确保持,调试端口关闭。独立源码ZIP514输入/22编译完全一致、三归档、实际便携、12组隔离安装及安装副本16组成果/9组文件流程通过;69份/46795742字节证据离线通过。首候选安装管理器漏编译及原60秒QA超时保持失败,见docs/QA-ORIGINAL-PURGE-RELEASE-F.md。正式原生窗口回看被物理Escape停止,未验收;不能宣称本切片全部体验验收完成。先补该项,再按docs/LIVE-DELIVERY-EFFICIENCY-PLAN.md处理原小源码保留抖动和完整批次后的检视空转。不得以新的发行源码重写D/E原编译身份或收益结论。
历史F固定安装:1.24.0/source c03860d/候选20261102152844546,原PID36552/Provider保持,原42项目/58会话/4953记录/10329事件/2850工件/公开模型中心精确保持,调试端口关闭。独立源码ZIP514输入/22编译完全一致、三归档、实际便携、12组隔离安装及安装副本16组成果/9组文件流程通过;69份/46795742字节证据离线通过。首候选安装管理器漏编译及原60秒QA超时保持失败,见docs/QA-ORIGINAL-PURGE-RELEASE-F.md。当时正式原生窗口回看被物理Escape停止,未验收;G已在1.24.1实际正式窗口补验,不能倒写为原F版本目视通过。小源码保留和批次交接也由G完成,不以新发行源码重写D/E原编译身份或收益结论。
E实测完成:同源修复载荷、真实claude-opus-5-5/Chat/32K六新例52请求/621486报告tokens/0未知;Python原6/6/编译/审查Git通过,React和四原版AB/BA未交付。两次原版实际apply与11开启/17关闭输入通过核对,不证明收益。889份证据见docs/LIVE-RETEST-E-RESULTS.md;46原会话/2143工件/原表每行与96原尝试保持,公开参数和原池恢复。F现已固定安装:21份执行服务/网页/桌面编译与E保持,一个安装管理器入口补齐已修正脚本的重新编译。不重跑旧失败,不擅自扩大预算,不复制Key。
@@ -30,7 +30,7 @@ D固定可信来源生产策略已完成:实现9106655/最终验收d05a741,6
## 范围与目标
当前接续优先级:A–D可靠性/固定原版接入与E新真实批次完成,F固定本地安装完成但正式原生窗口回看因Escape待补。先补该项并按docs/LIVE-DELIVERY-EFFICIENCY-PLAN.md修复已定位的上下文保留与审查交接问题;不重跑旧失败或将未交付的对照宣称有收益。docs/PLAN-1.25.md及新iPhone/其它供应商方案保留,按当前证据逐切片推进。
当前接续优先级:G已完成用户要求的已确认问题修复、正式部署和原生窗口回看。后续真实模型自主交付/Purge收益须新开有界样本、分别记录,不重跑旧失败或将未交付对照宣称有收益;docs/PLAN-1.25.md及新iPhone/其它供应商方案保留。发布前多轮完整目录核验耗时已记录为后续性能审查,不在运行中的安装流程削弱核验或改写载荷。
本仓库专注AI编程与能力研究工作台。其他项目不纳入本项目计划或代码。用户确定的研究对象为Codex、Claude Code、Cursor、DeepSeek Harness、WorkBuddy及DSH-purge;目标是将有证据的机制独立开发成自有Harness内置能力。
@@ -88,7 +88,7 @@ D固定可信来源生产策略已完成:实现9106655/最终验收d05a741,6
## 当前本地服务与Windows
- 正式服务入口http://127.0.0.1:4318,当前1.24.0,沿用原PID36552与Provider;当前身份以docs/original-purge-release-identity.json为准。原模型连接、全部表/会话/工件保持;普通源码/规划/Git工作不重启服务、不读取或复制Key。正式窗口目视回看因本轮物理Escape停止待补,隔离安装界面通过不代替该项。
- 正式服务入口http://127.0.0.1:4318,当前1.24.1,沿用原PID36552与Provider;当前身份以docs/delivery-reliability-release-identity.json为准。原模型连接、全部表/会话/工件精确保持;普通源码/规划/Git工作不重启服务、不读取或复制Key。正式原生窗口已通过Computer Use实际回看,当前保留1个窗口;旧F的Escape失败作为历史保留。
- 浏览器/fixture验证使用独立端口与数据目录;用户项目与研究对象的登录/会话配置不用于测试凭据。
- Windows执行环境以实测shell为准。现有工具使用PowerShell 5.1和UTF-8;不用&&/||拼接命令,使用换行和$LASTEXITCODE核对结果。
- 桌面与移动共用执行宿主。手机127.0.0.1指手机,远程接入通过未来经验证的配对网关。
+2 -2
View File
@@ -1,11 +1,11 @@
# Agent Workbench 更新记录
## 1.24.1 · 审查交接与上下文可靠性修复
## 1.24.1 · 审查交接与上下文可靠性修复(已本地交付)
- 完整文件批次封存并结算同轮工具后立即进入审查,停止额外模型调用;应用后显式续接原任务。
- 优先稳定保留有原工具与SHA来源的小源码,下一页按实际保留量分配空间;保留上下文和累计预算硬限制。
- 原生引擎区分上下文窗口不足和剩余预算不足,保留旧失败与原用量。
- 原件离线复现、边界回归、实际编译HTTP/审查/检查与两视口验证分别记录,见docs/QA-DELIVERY-RELIABILITY-G.md;真实模型收益未重测。
- 已完成155项冻结回归、源码ZIP独立重建、源码/便携界面和实际安装验证;正式保留原进程、模型连接与全部原数据升级,并完成原生窗口回看。见docs/QA-DELIVERY-RELIABILITY-G.md;真实模型收益未重测。
## 1.24.0 · 已有成果续接与真实交付(已本地交付)
+16 -2
View File
@@ -28,7 +28,11 @@
最终1.24.1编译界面10组通过,桌面/390px的批次审查、刷新、整批应用、显式续接与实际Node检查均完成;实际原图已目视核对,两视口预算诊断可读、无横向溢出。额外11组批次界面验收通过,包括实际外部冲突、原字节回退、未知恢复、跨项目迟到响应保护,页面及请求错误均为0。
不可变源码独立重建、便携/安装和正式原状态核对正在执行。正式当前仍1.24.0/PID36552/Provider保留;全部会话以新只读快照为准,bootstrap仅显示其中48个,不能把它当作全部58个会话计数。正式原生窗口回看尚待补验。
最终不可变候选20261103000853284/source ba07713已本地安装为1.24.1。三归档原字节/CRC/目录身份通过,源码ZIP的522份构建输入经离线安装和实际完整重建后保持,22份编译与便携版逐字节一致。实际便携的3项REA、原生SDK、浏览器和受控工程检查通过;最终便携新界面10组、实际安装生命周期12组及安装副本16组已有成果/9组本地HTML流程通过。
正式保留原PID36552与Provider,42项目/58全部会话/4953记录/10329事件/2850工件文件、全部原表每行/完整导出/工件字节/公开模型中心精确保持,9229关闭。bootstrap仅显示其中48个会话,不能当作全部会话计数。Computer Use在实际已安装1.24.1窗口完成3项回看并保存2张原图;原目标、原历史失败、按用户约定不测试的交付状态和Task/Run/模型用量记录均可见。回看后再次原状态比较通过,当前保留1个正式窗口;没有执行或续接原任务。
200份/43,758,910字节证据已按原字节封存,[manifest](delivery-reliability-g-evidence/manifest.json) SHA256为`08dd8c47274792edfbf12883b8fb23440ccfa337786ee548b574303aeb589d2a`。独立[离线核验](delivery-reliability-g-offline.txt)通过,原E/F封存SHA保持。[发行身份](delivery-reliability-release-identity.json)绑定新源码、安装程序、22份编译和正式运行目录;本轮真实模型请求0,原52请求的失败和Purge无收益证明结论不改写。
可复用验收入口:`scripts/verify-live-context-retention.mjs`和`scripts/verify-delivery-reliability-ui.mjs`。各自要求新输出目录,保留既有失败,不覆盖旧证据。
@@ -36,4 +40,14 @@
首候选便携UI第二轮完成两项交接检查后,在390px视口刚切换时误用尚未稳定的侧栏可见状态,选择控件随后被响应式收起,原2请求/超时/截图保留。按既有批次验收的真实导航契约,等待移动端“展开项目栏”出现并打开、确认选择控件可见后操作,不强制点击或修改产品。
修正验证器后的首候选便携UI第三轮10组全部通过,5次本机声明夹具请求、0真实模型请求;产品12份冻结输入保持。接下来由该QA修正的新Git来源生成最终不可变候选,并为新包独立记录归档、重建、便携、安装和正式保留状态结果。
修正验证器后的首候选便携UI第三轮10组全部通过,5次本机声明夹具请求、0真实模型请求;产品12份冻结输入保持。其后的ba07713新来源生成最终候选20261103000853284,已独立完成全部最终包验证,不混用首候选收据。
正式窗口恢复中,启动器先退出再暴露Electron子窗口,首launch_app未直接发现目标;重新列举实际窗口找到唯一已安装子进程,没有重新启动。一次过度转义路径过滤得到0个候选,按工具返回的窗口ID纠正后才操作;点击任务记录后的第一帧尚未切换,刷新观察到实际面板后才保存为回看成功证据。两次定位和过渡帧均不作产品成功依据。
回顾发现正式目录完整性核对耗时明显,已按原进度scope核对为预检、目录清单、实际加载输入和发布前再次核验的有限流程,并非安装器重放。作为后续性能优化记录;此次未降低完整性、防篡改和发布前状态复核,也未修改正在运行的载荷。
封存格式复查发现Computer Use传输原图为JPEG,但初次保存扩展名为.png。两份原始图像字节与原194份manifest及首次离线收据全部保留;增补两份同字节.jpg副本、格式说明和首格式审查失败记录,未转码。最终200份manifest以当前发行身份为准;首次字节核验通过不等于当时扩展名正确。
首次Git索引核对发现通用.gitignore排除了证据目录内的.log,普通目录暂存没有包含全部原日志,检查明确拒绝。随后仅对manifest列明的证据文件逐项显式暂存;.qa私有目录继续排除,所有证据以Git索引原始blob与磁盘原件逐字节一致作为收尾条件。
最终[Git索引核对](delivery-reliability-g-git-index.txt)通过:200份证据加manifest共201份/43,818,454字节,索引blob与磁盘原件逐字节一致,原E/F封存身份保持。收尾仅文档/证据变化,不重建或改写已验证发行载荷。
@@ -0,0 +1,170 @@
✔ input that fits the engine window but exceeds remaining credit diagnoses the credit limit (0.4781ms)
✔ window overflow and historical pauses retain distinct and honest diagnoses (0.0846ms)
✔ a budget pause persists concrete text/tool/history/image breakdown and never dispatches an oversized request (2254.359ms)
✔ explicit frozen preview resumes the same Task in a new Run, preserves completed tools and does not change global config or selected model (3163.6716ms)
✔ insufficient budgets, silently clamped capacity and arbitrary config fields reject without a physical request or mutating task budget (2515.9725ms)
✔ changed session, changed registry, expiry and altered frozen preview all require a new explicit preview (2396.7525ms)
✔ preview preserves unknown invocation status and increasing Task allowance is committed only with confirmed new Run (3280.2137ms)
✔ batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart (6288.6768ms)
✔ delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files (4014.9419ms)
✔ a compatible model can seal proposals through the real HTTP loop while application stays behind user review (6595.7798ms)
✔ a sealed batch at the step limit hands off and continues the same Task into actual checks without replaying saved tools (15211.4275ms)
✔ applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation (2469.6939ms)
▶ complete sealed batch hands off after all tools settle with no next model request
✔ complete (4214.6965ms)
✔ later-error (4835.0104ms)
✔ complete sealed batch hands off after all tools settle with no next model request (9050.3886ms)
▶ partial, changed, failed or cancelled batches cannot claim complete review handoff
✔ partial (4499.5806ms)
✔ new-proposal (4157.7788ms)
✔ failed (4456.5093ms)
✔ conflict (4586.3256ms)
✔ cancelled (3893.4829ms)
✔ unknown (4707.8593ms)
✔ tampered (5051.9704ms)
✔ partial, changed, failed or cancelled batches cannot claim complete review handoff (31354.9596ms)
✔ actual process exit at file-batch prepared preserves durable identity and never replays writes (1810.9369ms)
✔ actual process exit at file-batch application_started preserves durable identity and never replays writes (2144.4908ms)
✔ actual process exit at file-batch write_intent preserves durable identity and never replays writes (1985.2734ms)
✔ actual process exit at file-batch staged preserves durable identity and never replays writes (2348.0761ms)
✔ actual process exit at file-batch replaced preserves durable identity and never replays writes (2281.0135ms)
✔ actual process exit at file-batch file_recorded preserves durable identity and never replays writes (2542.0479ms)
✔ actual process exit at file-batch finished preserves durable identity and never replays writes (2645.7507ms)
✔ actual process exit at file-batch rollback_started preserves durable identity and never replays writes (3307.3518ms)
✔ actual process exit at file-batch restore_intent preserves durable identity and never replays writes (3203.6028ms)
✔ actual process exit at file-batch restore_staged preserves durable identity and never replays writes (2872.6014ms)
✔ actual process exit at file-batch restored preserves durable identity and never replays writes (3207.1629ms)
✔ actual process exit at file-batch restore_recorded preserves durable identity and never replays writes (3456.625ms)
✔ actual process exit at file-batch rollback_finished preserves durable identity and never replays writes (3291.3962ms)
warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it
warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it
✔ sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files (2892.13ms)
Switched to a new branch 'owner-branch'
✔ a conflict in the last file or Git branch prevents writing every file in the batch (2881.8143ms)
✔ duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch (1391.4823ms)
✔ fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target (2466.4145ms)
✔ a failure after replacement restores only batch bytes and never retries an old application (1727.9885ms)
✔ rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery (2384.1335ms)
✔ an unattempted owner-created file identical to a suggestion remains external and is never removed (1809.7168ms)
✔ active batch requests are serialized and cancellation leaves a verifiable ended batch (1452.2638ms)
✔ batch application and rollback preserve unrelated Git index and worktree bytes (3214.0272ms)
✔ recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection (2623.7291ms)
✔ one Task can seal pending proposals from earlier Runs while snapshots retain each source Run (1615.13ms)
✔ controlled installation pins the native kernel and bridge independently of the existing connection-probe identity (959.0218ms)
✔ controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract (0.5566ms)
✔ owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations (5.3393ms)
✔ bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch (735.109ms)
✔ bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect (929.2965ms)
✔ bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity (637.5648ms)
✔ stopped and oversized bridge requests never reach a local model or tool callback (764.412ms)
✔ sealed r1-off failure fits its original 16K config with authentic latest status and readable source (14.1493ms)
✔ sealed r1-on failure fits its original 16K config with authentic latest status and readable source (10.7966ms)
✔ sealed r2-on failure fits its original 16K config with authentic latest status and readable source (8.5914ms)
✔ sealed r2-off failure fits its original 16K config with authentic latest status and readable source (8.7137ms)
✔ archived native call pairs require exact saved arguments/results rather than model-written summaries (8.3391ms)
✔ full system/user requirements and mandatory current failure can refuse rather than be trimmed (13.0742ms)
✔ small native input is byte-preserving; developer instructions remain mandatory after compaction (0.2426ms)
✔ older failing checks and pending proposals remain visible after a later large file read (14.7652ms)
✔ bounded result keeps every check status and cuts Unicode only on whole characters (0.4404ms)
✔ controlled engine HTTP freezes one child, pages original owned input/report, rejects foreign reads and prevents changed-source reuse (15113.5555ms)
✔ native text and call IDs preserve original result pairing while unsupported content fails closed (1.3291ms)
✔ one engine child freezes real installation identity before creating tasks and rejects a changed source (8460.0535ms)
✔ owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs (26594.9272ms)
✔ forged native scope cannot change a parent file and a final completion claim cannot replace worker proof (13479.2898ms)
✔ duplicate native IDs are rejected without replaying a saved tool (11901.6727ms)
✔ native input exceeding the context budget is retained and sends no model request (10305.5649ms)
✔ bounded native sends verify original tool provenance and reject forged views or missing versions (13687.7538ms)
✔ stop retains a late reported model usage once and executes no tool from that output (10848.4664ms)
✔ a source change after the original model intent stops before native tools execute (10222.0307ms)
✔ an engine source change while approval is pending invalidates the old permission before any check starts (14590.1925ms)
✔ missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text (0.5232ms)
✔ closed root with an original live descendant remains unknown and retains its process tree (0.2726ms)
✔ host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes (15021.7273ms)
✔ corrupted model reservation cannot reduce recovered budget or permit a new engine request (12877.3045ms)
✔ saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance (695.6396ms)
✔ owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched (813.027ms)
✔ Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes (1908.0632ms)
✔ mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools (2258.6802ms)
▶ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool
✔ Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial" (1290.5845ms)
✔ Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal (1700.8777ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal (1602.5777ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte (1630.9884ms)
✔ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool (6225.922ms)
▶ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay
✔ chat-completions (1812.3813ms)
✔ responses (1808.9892ms)
✔ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay (3621.9089ms)
✔ wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint (0.2591ms)
✔ connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions (685.0721ms)
✔ reservation uses actual known usage from the same route, never lowers estimates or rewrites original receipts (1.7281ms)
✔ reservation verification binds original Task/Run consumption and rejects changed usage or foreign provenance (0.48ms)
✔ known high input calibrates the next request and stops before dispatch while preserving the completed read (1447.5822ms)
✔ one reported overrun stops legacy requests and keeps actual use and excess (1214.2904ms)
✔ one reported overrun stops pool requests and keeps actual use and excess (1782.9067ms)
✔ one reported overrun stops connection requests and keeps actual use and excess (1641.352ms)
✔ reported usage below the limit prevents an unaffordable legacy retry before another dispatch (1083.9795ms)
✔ reported usage below the limit prevents an unaffordable pool retry before another dispatch (1931.2061ms)
✔ native bridge seals calibrated refusal with original consumption and preserves versioned request verification (12627.0073ms)
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (1.8553ms)
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.6019ms)
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.6355ms)
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3638ms)
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (3561.2758ms)
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (3629.9503ms)
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (4839.0984ms)
✔ context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs (3409.9772ms)
✔ delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification (1692.5361ms)
✔ native seed framing reserves capacity before optional history without changing the selected window (664.3132ms)
✔ direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget (1424.1889ms)
✔ one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments (3589.1491ms)
✔ tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests (866.638ms)
✔ oversized required user instructions pause intact and can be explicitly resumed after increasing the window (1282.7167ms)
✔ all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix (817.1144ms)
✔ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (698.5481ms)
✔ invalid orphan result is rejected before archive or network preparation (492.6358ms)
✔ invalid missing result is rejected before archive or network preparation (537.6192ms)
✔ invalid wrong result is rejected before archive or network preparation (484.0046ms)
✔ invalid duplicate call is rejected before archive or network preparation (570.5568ms)
✔ a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON (1414.5826ms)
✔ changed or missing archived evidence stops reuse and is never silently recreated (960.8616ms)
✔ transaction failure prevents publishing a plan and any corresponding model request (797.6377ms)
✔ the Provider rejects body mutation after a sealed plan before calling HTTP (690.4846ms)
✔ HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command (7196.0068ms)
✔ a real process exit after plan persistence marks interruption and never issues an automatic model request (1120.1729ms)
✔ a stop from the event loop interrupts immediate model replies before later tools (1106.1643ms)
✔ a stop after the first tool preserves a complete interrupted multi-call protocol group (1398.4979ms)
✔ the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands (4600.2004ms)
✔ denial prevents command execution and produces a paired denied result (1364.1836ms)
✔ stopping during approval interrupts pending calls without executing or replaying them (1018.3062ms)
✔ stopping a running fixture command terminates its own process tree and retains uncertain state (1522.848ms)
✔ command output decodes split UTF-8 and excludes the workbench key from child environment (1016.0014ms)
✔ model-list testing uses a tentative key without changing the saved connection and redacts service errors (6.8813ms)
✔ truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities (2093.9969ms)
✔ request projection keeps exact tool pairs and complete recent user instructions while preserving disk history (1535.6741ms)
✔ the latest oversized session result reaches the next request together with already read source modules (2051.5081ms)
✔ every call in a large latest group keeps its actual outcome, including denied and unknown results (1080.2312ms)
✔ a small complete latest tool group is sent once and needs no duplicate feedback view (865.6272ms)
✔ real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing (2529.9692ms)
✔ small code and actual failed command stay visible when their original multi-tool group cannot fit (1481.1618ms)
✔ mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes (1718.8272ms)
✔ working observations are bound to the current Task and stop treating a pre-application file revision as current evidence (2250.6173ms)
✔ a sealed observation rejects changed or missing original result artifacts instead of recreating evidence (1370.3846ms)
✔ a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid (5238.7316ms)
✔ budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries (4.237ms)
✔ actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening (9468.6392ms)
✔ actual HTTP file pagination advances over a long file with each returned page visible in the next request (3985.3817ms)
✔ later mixed history pages cannot displace the actual module sources and complete requirements (5271.0972ms)
✔ a later narrow page of the same file revision cannot evict the wider actual observation (4200.7842ms)
✔ six small source files stay complete across metadata turns even when mandatory evidence exceeds the soft target (3110.5548ms)
✔ historical read-artifact navigation points to the original artifact and next page, never its result wrapper (1155.7987ms)
✔ a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view (1261.4608ms)
✔ actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes (9257.7856ms)
ℹ tests 155
ℹ suites 0
ℹ pass 155
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 241938.7563
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,242 @@
{
"schemaVersion": 1,
"manifestSha256": "1eafc592adb267f6487cf9b48893480e9b8a987780307d1f945befa4e851ba22",
"scope": "Offline context-selection counterfactual using original E system/tools/history/source bytes and remaining credits. No model requests or task execution. Historical outcomes unchanged.",
"realModelRequests": 0,
"reports": [
{
"request": 7,
"originalInputTokens": 15714,
"inputTokens": 15714,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": true
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": true
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": true
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 8,
"originalInputTokens": 15873,
"inputTokens": 15873,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": false
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": true
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": true
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 9,
"originalInputTokens": 15905,
"inputTokens": 15905,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": true
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": false
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": true
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 10,
"originalInputTokens": 15779,
"inputTokens": 15779,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": false
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": true
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": false
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 11,
"originalInputTokens": 16000,
"inputTokens": 16000,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": false
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": false
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": false
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": false
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 12,
"originalInputTokens": 15999,
"inputTokens": 15999,
"inputBudget": 21197,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": false
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": false
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": false
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": false
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
}
]
}
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,242 @@
{
"schemaVersion": 1,
"manifestSha256": "1eafc592adb267f6487cf9b48893480e9b8a987780307d1f945befa4e851ba22",
"scope": "Offline context-selection counterfactual using original E system/tools/history/source bytes and remaining credits. No model requests or task execution. Historical outcomes unchanged.",
"realModelRequests": 0,
"reports": [
{
"request": 7,
"originalInputTokens": 15714,
"inputTokens": 15714,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": true
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": true
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": true
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 8,
"originalInputTokens": 15873,
"inputTokens": 16110,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": true
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": true
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": true
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 9,
"originalInputTokens": 15905,
"inputTokens": 16383,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": true
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": true
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": true
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 10,
"originalInputTokens": 15779,
"inputTokens": 16504,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": true
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": true
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": true
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 11,
"originalInputTokens": 16000,
"inputTokens": 16993,
"inputBudget": 27552,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": true
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": true
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": true
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
},
{
"request": 12,
"originalInputTokens": 15999,
"inputTokens": 16945,
"inputBudget": 21197,
"softTarget": 16000,
"sources": [
{
"path": "src/query.ts",
"characters": 142,
"retained": true
},
{
"path": "src/summary.ts",
"characters": 155,
"retained": true
},
{
"path": "src/transition.ts",
"characters": 167,
"retained": true
},
{
"path": "src/App.tsx",
"characters": 1991,
"retained": true
},
{
"path": "src/types.ts",
"characters": 82,
"retained": true
},
{
"path": "test/domain.test.mjs",
"characters": 1715,
"retained": true
}
]
}
]
}
@@ -0,0 +1,81 @@
✔ large source receipts use cursor-preserving invalidation without filling the event stream or changing the session (5.5225ms)
✔ small event updates retain the current session and actual cursor (0.1217ms)
✔ the bundled local service enforces host, origin, token and JSON object contracts (2465.9083ms)
✔ an in-flight connection probe prevents configuration changes and another probe until its actual result returns (2381.8793ms)
✔ API review applies verified content, detects conflicts, exports sessions and keeps keys in memory (4088.3691ms)
✔ a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume (9055.84ms)
✔ runtime diagnostics and model-response validation use actual records and preserve the saved connection (2327.2061ms)
✔ persistent event replay is read-only and keeps run/artifact identity across reconnects (14783.4854ms)
✔ real browser HTTP plans, original field pages and PNG bytes preserve ownership and survive host restart (7695.8738ms)
✔ self harness browser tools require approval and feed verified actual page fields back to the original Task (10610.5524ms)
✔ browser host recovery retains unknown root outcome, blocks replay, and requires an explicit owned acknowledgement (3707.6218ms)
✔ late HTTP stop of a finished browser job cannot interrupt a later job in the same Task (13785.0277ms)
✔ actual failed page blocks source-passed delivery; a new passing page permits a bound commit and preserves both original records (36403.3305ms)
✔ a build-only change after Git review invalidates the actual browser evidence and leaves HEAD and the protected index intact (23745.6859ms)
✔ actual DOM controls include validated unique CSS selectors across repeated parent buttons and escaped labels (16593.7498ms)
✔ browser field coverage distinguishes sections and Run windows while retaining original source identity (0.5774ms)
✔ repeated original browser pages pause a live Task without re-opening the browser or breaking tool pairing (15840.4029ms)
✔ browser plan rejects outside builds, invalid interaction scope and unbounded steps before execution (0.9447ms)
✔ real owned Edge interactions, assertions, raw PNG and stopped process survive exact result reuse and host reopen (9004.83ms)
✔ failed real page assertion preserves actual value and forbids silent retry of the original plan (14967.5778ms)
✔ build/source mutation and sealed step tampering reject before browser dispatch; earlier task cannot execute plan (4162.8053ms)
✔ outside network never reaches another local service, and original JavaScript/console failures remain failures (9385.1204ms)
✔ stopping a real in-flight browser preserves finished steps, closes its owned root and never replays (8032.3232ms)
✔ 原PNG损坏使原结果校验失败,不能以已有通过状态复用 (9042.1969ms)
✔ fixed browsing contracts reject local host APIs, credential URLs, protocols, cross-origin and arbitrary execution (0.9681ms)
✔ attested desktop queue preserves same-tab observations, original PNG bytes and approval-bound one-shot actions (7456.3948ms)
✔ page data cannot grant domains, interaction or other Task scope; nonce and ownership remain fixed (5601.6133ms)
✔ unknown dispatched submission blocks even after a new observation, rejects late success and retains explicit acknowledgement (10248.9541ms)
✔ downloads require exact approved address, remain original binary artifacts, and cannot reuse consumed observation (6205.1931ms)
✔ revoking shared persistent profile closes all its tabs and clears only that profile after original desktop acknowledgement (8845.9822ms)
✔ service recovery never reopens old tabs or replays dispatched actions and keeps unknown original receipts (9101.8456ms)
✖ agent browser flow waits for original Task/Run approval, dispatches once, and returns paired original results (16444.6787ms)
✔ changed approved input and stopped dispatched agent action cannot be accepted or replayed (7102.5465ms)
✔ browser inventory gives bounded metadata and original references instead of repeating full website histories (8319.3059ms)
✔ receipt storage failure settles the original dispatched action as unknown and never hangs or accepts late success (5814.6232ms)
✔ input that fits the engine window but exceeds remaining credit diagnoses the credit limit (0.4757ms)
✔ window overflow and historical pauses retain distinct and honest diagnoses (0.0788ms)
✔ a budget pause persists concrete text/tool/history/image breakdown and never dispatches an oversized request (12404.6894ms)
✔ explicit frozen preview resumes the same Task in a new Run, preserves completed tools and does not change global config or selected model (18964.926ms)
✔ insufficient budgets, silently clamped capacity and arbitrary config fields reject without a physical request or mutating task budget (11748.2077ms)
✔ changed session, changed registry, expiry and altered frozen preview all require a new explicit preview (15208.0456ms)
✔ preview preserves unknown invocation status and increasing Task allowance is committed only with confirmed new Run (16158.1136ms)
✔ batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart (18217.3806ms)
✔ delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files (15929.0942ms)
✔ a compatible model can seal proposals through the real HTTP loop while application stays behind user review (31265.0482ms)
✖ a sealed batch at the step limit hands off and continues the same Task into actual checks without replaying saved tools (26721.9547ms)
✔ applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation (9690.6008ms)
▶ complete sealed batch hands off after all tools settle with no next model request
✔ complete (22696.4831ms)
✔ later-error (27555.9118ms)
✔ complete sealed batch hands off after all tools settle with no next model request (50253.2766ms)
▶ partial, changed, failed or cancelled batches cannot claim complete review handoff
✔ partial (18851.6978ms)
✔ new-proposal (20224.9103ms)
✔ failed (14673.0008ms)
✔ conflict (8352.5869ms)
✔ cancelled (8403.1607ms)
✔ unknown (9430.3025ms)
✔ tampered (4530.3145ms)
✔ partial, changed, failed or cancelled batches cannot claim complete review handoff (84467.5836ms)
✔ actual process exit at file-batch prepared preserves durable identity and never replays writes (7550.2296ms)
✔ actual process exit at file-batch application_started preserves durable identity and never replays writes (5116.2041ms)
✔ actual process exit at file-batch write_intent preserves durable identity and never replays writes (6952.7421ms)
✔ actual process exit at file-batch staged preserves durable identity and never replays writes (4560.8702ms)
✔ actual process exit at file-batch replaced preserves durable identity and never replays writes (3838.0471ms)
✔ actual process exit at file-batch file_recorded preserves durable identity and never replays writes (4595.3718ms)
✔ actual process exit at file-batch finished preserves durable identity and never replays writes (5998.144ms)
✔ actual process exit at file-batch rollback_started preserves durable identity and never replays writes (6248.5168ms)
✔ actual process exit at file-batch restore_intent preserves durable identity and never replays writes (3169.4283ms)
✔ actual process exit at file-batch restore_staged preserves durable identity and never replays writes (2683.0346ms)
✔ actual process exit at file-batch restored preserves durable identity and never replays writes (2761.9481ms)
✔ actual process exit at file-batch restore_recorded preserves durable identity and never replays writes (3159.9094ms)
✔ actual process exit at file-batch rollback_finished preserves durable identity and never replays writes (3144.6465ms)
warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it
warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it
✔ sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files (2466.9384ms)
Switched to a new branch 'owner-branch'
✔ a conflict in the last file or Git branch prevents writing every file in the batch (3280.9547ms)
✔ duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch (1308.819ms)
✔ fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target (2614.4166ms)
✔ a failure after replacement restores only batch bytes and never retries an old application (1788.4982ms)
@@ -0,0 +1 @@
{"success": true, "version": "1.24.1", "testedAt": "2026-11-03T00:13:17.999263+00:00", "archives": [{"kind": "portable", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261103000853284.zip", "files": 10927, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "1f0126bb3109d5217ab74a348db7f57ab5c34cefd6bb950b65590838449a3965"}, {"kind": "source", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-source-20261103000853284.zip", "files": 26423, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "6e07d0cf75870b412a4785478336a3e56e5c27a7872b2840e6d08ef2905ccaba"}, {"kind": "evidence", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-evidence-20261103000853284.zip", "files": 15203, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "717c18cd04ca6169ac55b78210f353977d0fc4551da6fd8979f0c1691d4d8abc"}], "extractionRoot": null}
@@ -0,0 +1 @@
{"success": true, "version": "1.24.1", "testedAt": "2026-11-03T00:03:05.284326+00:00", "archives": [{"kind": "portable", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796.zip", "files": 10927, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "bd79094ec6a2813f17870cfb30c7160b03aeba04586b5405352dfa565e9e905b"}, {"kind": "source", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-source-20261102235819796.zip", "files": 26423, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "c012273c93a277117aa926a13f27e03498446623734bf790e47dec8e3eb93ea0"}, {"kind": "evidence", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-evidence-20261102235819796.zip", "files": 15203, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "f2645e02ebbd130ddb7acbef6ba21cabf91ccd3ad31b33d3d29faf759cf16cef"}], "extractionRoot": null}
@@ -0,0 +1,29 @@
{
"success": true,
"version": "1.24.1",
"testedAt": "2026-11-02T23:56:19.047Z",
"cases": [
"Desktop batch scope, per-file diffs, sealed single-write guard and pre-apply bytes",
"Three-file reviewed application preserves exact BOM/CRLF/LF and creates the new file",
"Explicit batch rollback restores exact originals and removes only the reviewed new file",
"A last-file owner conflict blocks the whole batch and shows the real recovery direction",
"Durable partial recovery reads actual hashes and preserves owner content during rollback",
"Changed observation fingerprints reject stale acknowledgement without releasing the project",
"Explicit owner-content acknowledgement ends recovery without claiming successful application",
"Switching projects clears the previous task notification while retaining its durable error and recovery history",
"390px step-limit review, same-task continuation entry, rollback confirmation and keyboard close fit the viewport",
"A delayed preparation response never opens a different project or changes its selected session",
"A failed batch response after its component unmounts cannot display an error in the newly selected project"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/delivery-reliability-batch-desktop-review.png",
".qa/screenshots/delivery-reliability-batch-desktop-conflict.png",
".qa/screenshots/delivery-reliability-batch-desktop-recovery.png",
".qa/screenshots/delivery-reliability-batch-mobile-review.png",
".qa/screenshots/delivery-reliability-batch-mobile-rollback.png"
],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\batch-ui-c32248b4-ae65-4150-aca2-a252ec93daff",
"scope": "Real independent demo host and durable batch states; UI fixtures include actual owner conflict/rollback results. No real model credentials or user project were used."
}
@@ -0,0 +1,19 @@
node:internal/modules/run_main:107
triggerUncaughtException(
^
AssertionError [ERR_ASSERTION]: The UI host must match this package version.
'1.24.0' !== '1.24.1'
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/scripts/verify-change-sets-ui.mjs:37:8
at process.processTicksAndRejections (node:internal/process/task_queues:104:5) {
generatedMessage: false,
code: 'ERR_ASSERTION',
actual: '1.24.0',
expected: '1.24.1',
operator: 'strictEqual',
diff: 'simple'
}
Node.js v24.22.1
@@ -0,0 +1,20 @@
> local-agent-workbench@1.24.1 build
> tsc --noEmit && vite build && node scripts/build-mobile.mjs && node scripts/build-server.mjs
vite v7.3.7 building client environment for production...
transforming...
✓ 1753 modules transformed.
rendering chunks...
computing gzip size...
dist-client/index.html 0.60 kB │ gzip: 0.41 kB
dist-client/.vite/manifest.json 0.65 kB │ gzip: 0.24 kB
dist-client/mobile.html 0.84 kB │ gzip: 0.47 kB
dist-client/assets/mobile-joLHctQw.css 12.39 kB │ gzip: 3.22 kB
dist-client/assets/desktop-BYZSVsL1.css 165.03 kB │ gzip: 31.29 kB
dist-client/assets/mobile-4zqcwTeD.js 27.19 kB │ gzip: 9.34 kB
dist-client/assets/approval-presentation-Chut4EFA.js 226.80 kB │ gzip: 71.65 kB
dist-client/assets/desktop-CHREzle3.js 392.10 kB │ gzip: 110.98 kB
✓ built in 1.22s
Mobile shell built: 3 allowed assets; API and project data are never cached.
Server bundle built.
@@ -0,0 +1,20 @@
> local-agent-workbench@1.24.0 build
> tsc --noEmit && vite build && node scripts/build-mobile.mjs && node scripts/build-server.mjs
vite v7.3.7 building client environment for production...
transforming...
✓ 1753 modules transformed.
rendering chunks...
computing gzip size...
dist-client/index.html 0.60 kB │ gzip: 0.41 kB
dist-client/.vite/manifest.json 0.65 kB │ gzip: 0.24 kB
dist-client/mobile.html 0.84 kB │ gzip: 0.47 kB
dist-client/assets/mobile-joLHctQw.css 12.39 kB │ gzip: 3.22 kB
dist-client/assets/desktop-BYZSVsL1.css 165.03 kB │ gzip: 31.29 kB
dist-client/assets/mobile-4zqcwTeD.js 27.19 kB │ gzip: 9.34 kB
dist-client/assets/approval-presentation-Chut4EFA.js 226.80 kB │ gzip: 71.65 kB
dist-client/assets/desktop-CHREzle3.js 392.10 kB │ gzip: 110.98 kB
✓ built in 1.40s
Mobile shell built: 3 allowed assets; API and project data are never cached.
Server bundle built.
@@ -0,0 +1,20 @@
> local-agent-workbench@1.24.1 build
> tsc --noEmit && vite build && node scripts/build-mobile.mjs && node scripts/build-server.mjs
vite v7.3.7 building client environment for production...
transforming...
✓ 1753 modules transformed.
rendering chunks...
computing gzip size...
dist-client/index.html 0.60 kB │ gzip: 0.41 kB
dist-client/.vite/manifest.json 0.65 kB │ gzip: 0.24 kB
dist-client/mobile.html 0.84 kB │ gzip: 0.47 kB
dist-client/assets/mobile-joLHctQw.css 12.39 kB │ gzip: 3.22 kB
dist-client/assets/desktop-BYZSVsL1.css 165.03 kB │ gzip: 31.29 kB
dist-client/assets/mobile-4zqcwTeD.js 27.19 kB │ gzip: 9.34 kB
dist-client/assets/approval-presentation-Chut4EFA.js 226.80 kB │ gzip: 71.65 kB
dist-client/assets/desktop-CHREzle3.js 392.10 kB │ gzip: 110.98 kB
✓ built in 1.20s
Mobile shell built: 3 allowed assets; API and project data are never cached.
Server bundle built.
@@ -0,0 +1,20 @@
> local-agent-workbench@1.24.1 build
> tsc --noEmit && vite build && node scripts/build-mobile.mjs && node scripts/build-server.mjs
vite v7.3.7 building client environment for production...
transforming...
✓ 1753 modules transformed.
rendering chunks...
computing gzip size...
dist-client/index.html 0.60 kB │ gzip: 0.41 kB
dist-client/.vite/manifest.json 0.65 kB │ gzip: 0.24 kB
dist-client/mobile.html 0.84 kB │ gzip: 0.47 kB
dist-client/assets/mobile-joLHctQw.css 12.39 kB │ gzip: 3.22 kB
dist-client/assets/desktop-BYZSVsL1.css 165.03 kB │ gzip: 31.29 kB
dist-client/assets/mobile-4zqcwTeD.js 27.19 kB │ gzip: 9.34 kB
dist-client/assets/approval-presentation-Chut4EFA.js 226.80 kB │ gzip: 71.65 kB
dist-client/assets/desktop-CHREzle3.js 392.10 kB │ gzip: 110.98 kB
✓ built in 1.22s
Mobile shell built: 3 allowed assets; API and project data are never cached.
Server bundle built.
@@ -0,0 +1,5 @@
> local-agent-workbench@1.24.0 build
> tsc --noEmit && vite build && node scripts/build-mobile.mjs && node scripts/build-server.mjs
src/client/BudgetPausePanel.tsx(7,41): error TS7016: Could not find a declaration file for module '../shared/budget-presentation.mjs'. 'D:/Ai-project/REA逆向/Agent-Workbench/src/shared/budget-presentation.mjs' implicitly has an 'any' type.
@@ -0,0 +1 @@
{"schemaVersion":1,"manifestSha256":"1eafc592adb267f6487cf9b48893480e9b8a987780307d1f945befa4e851ba22","scope":"Offline context-selection counterfactual using original E system/tools/history/source bytes and remaining credits. No model requests or task execution. Historical outcomes unchanged.","realModelRequests":0,"reports":[{"request":7,"originalInputTokens":15714,"inputTokens":15714,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":8,"originalInputTokens":15873,"inputTokens":16062,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":9,"originalInputTokens":15905,"inputTokens":16383,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":10,"originalInputTokens":15779,"inputTokens":16504,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":11,"originalInputTokens":16000,"inputTokens":16993,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":12,"originalInputTokens":15999,"inputTokens":16945,"inputBudget":21197,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]}]}
@@ -0,0 +1 @@
{"schemaVersion":1,"manifestSha256":"1eafc592adb267f6487cf9b48893480e9b8a987780307d1f945befa4e851ba22","scope":"Offline context-selection counterfactual using original E system/tools/history/source bytes and remaining credits. No model requests or task execution. Historical outcomes unchanged.","realModelRequests":0,"reports":[{"request":7,"originalInputTokens":15714,"inputTokens":15714,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":8,"originalInputTokens":15873,"inputTokens":16000,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":false},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":9,"originalInputTokens":15905,"inputTokens":15949,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":false},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":10,"originalInputTokens":15779,"inputTokens":15954,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":false},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":11,"originalInputTokens":16000,"inputTokens":16000,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":false},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":false}]},{"request":12,"originalInputTokens":15999,"inputTokens":15967,"inputBudget":21197,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":false},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]}]}
@@ -0,0 +1,11 @@
file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-e-context-replay-g.mjs:35
store.state.sessions.push(session);
^
TypeError: Cannot read properties of undefined (reading 'sessions')
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-e-context-replay-g.mjs:35:17
at ModuleJob.run (node:internal/modules/esm/module_job:561:25)
at async node:internal/modules/esm/loader:647:26
at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:101:5)
Node.js v24.22.1
@@ -0,0 +1,21 @@
file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/storage/state-database.mjs:58
this.database.prepare('INSERT INTO sessions(id,project_id,revision,payload) VALUES(?,?,?,?) ON CONFLICT(id) DO UPDATE SET revision=excluded.revision,payload=excluded.payload').run(
^
Error: FOREIGN KEY constraint failed
at StateDatabase.writeSession (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/storage/state-database.mjs:58:181)
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/storage/state-database.mjs:98:12
at StateDatabase.transaction (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/storage/state-database.mjs:37:26)
at StateDatabase.save (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/storage/state-database.mjs:97:17)
at Store.save (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/server/store.mjs:386:36)
at Store.putRecord (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/server/store.mjs:662:10)
at RequestPlanner.prepare (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/context/request-plan.mjs:347:16)
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-e-context-replay-g.mjs:50:30
at ModuleJob.run (node:internal/modules/esm/module_job:561:25)
at async node:internal/modules/esm/loader:647:26 {
code: 'ERR_SQLITE_ERROR',
errcode: 787,
errstr: 'constraint failed'
}
Node.js v24.22.1
@@ -0,0 +1,13 @@
file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/shared/contracts/model-reservation.mjs:80
if(JSON.stringify(expected)!==JSON.stringify(reservation))throw new Error('模型预算预留与原估算/用量/实际线路不一致。');
^
Error: 模型预算预留与原估算/用量/实际线路不一致。
at verifyModelReservation (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/shared/contracts/model-reservation.mjs:80:67)
at verifyPlanEvidence (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/context/request-plan.mjs:369:28)
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-e-context-replay-g.mjs:54:5
at ModuleJob.run (node:internal/modules/esm/module_job:561:25)
at async node:internal/modules/esm/loader:647:26
at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:101:5)
Node.js v24.22.1
@@ -0,0 +1 @@
{"schemaVersion":1,"manifestSha256":"1eafc592adb267f6487cf9b48893480e9b8a987780307d1f945befa4e851ba22","scope":"Offline context-selection counterfactual using original E system/tools/history/source bytes and remaining credits. No model requests or task execution. Historical outcomes unchanged.","realModelRequests":0,"reports":[{"request":7,"originalInputTokens":15714,"inputTokens":15332,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":8,"originalInputTokens":15873,"inputTokens":15316,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":9,"originalInputTokens":15905,"inputTokens":15725,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":10,"originalInputTokens":15779,"inputTokens":15856,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":11,"originalInputTokens":16000,"inputTokens":15671,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":12,"originalInputTokens":15999,"inputTokens":15985,"inputBudget":21197,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]}]}
@@ -0,0 +1 @@
{"schemaVersion":1,"manifestSha256":"1eafc592adb267f6487cf9b48893480e9b8a987780307d1f945befa4e851ba22","scope":"Offline context-selection counterfactual using original E system/tools/history/source bytes and remaining credits. No model requests or task execution. Historical outcomes unchanged.","realModelRequests":0,"reports":[{"request":7,"originalInputTokens":15714,"inputTokens":15714,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":8,"originalInputTokens":15873,"inputTokens":15873,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":false},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":9,"originalInputTokens":15905,"inputTokens":15905,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":false},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":10,"originalInputTokens":15779,"inputTokens":15779,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":false},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":false},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":11,"originalInputTokens":16000,"inputTokens":16000,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":false},{"path":"src/summary.ts","characters":155,"retained":false},{"path":"src/transition.ts","characters":167,"retained":false},{"path":"src/App.tsx","characters":1991,"retained":false},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":12,"originalInputTokens":15999,"inputTokens":15999,"inputBudget":21197,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":false},{"path":"src/summary.ts","characters":155,"retained":false},{"path":"src/transition.ts","characters":167,"retained":false},{"path":"src/App.tsx","characters":1991,"retained":false},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]}]}
@@ -0,0 +1,16 @@
file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/server/store.mjs:472
if (!session) throw Object.assign(new Error('会话不存在。'), { status: 404 });
^
Error: 会话不存在。
at Store.session (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/server/store.mjs:472:39)
at Store.owned (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/server/store.mjs:667:80)
at RequestPlanner.prepare (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/context/request-plan.mjs:163:29)
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-e-context-replay-g.mjs:47:30
at ModuleJob.run (node:internal/modules/esm/module_job:561:25)
at async node:internal/modules/esm/loader:647:26
at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:101:5) {
status: 404
}
Node.js v24.22.1
@@ -0,0 +1 @@
{"schemaVersion":1,"manifestSha256":"1eafc592adb267f6487cf9b48893480e9b8a987780307d1f945befa4e851ba22","scope":"Offline context-selection counterfactual using original E system/tools/history/source bytes and remaining credits. No model requests or task execution. Historical outcomes unchanged.","realModelRequests":0,"reports":[{"request":7,"originalInputTokens":15714,"inputTokens":15714,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":8,"originalInputTokens":15873,"inputTokens":16110,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":9,"originalInputTokens":15905,"inputTokens":16383,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":10,"originalInputTokens":15779,"inputTokens":16504,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":11,"originalInputTokens":16000,"inputTokens":16993,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":12,"originalInputTokens":15999,"inputTokens":16945,"inputBudget":21197,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]}]}
@@ -0,0 +1 @@
{"schemaVersion":1,"manifestSha256":"1eafc592adb267f6487cf9b48893480e9b8a987780307d1f945befa4e851ba22","scope":"Offline context-selection counterfactual using original E system/tools/history/source bytes and remaining credits. No model requests or task execution. Historical outcomes unchanged.","realModelRequests":0,"reports":[{"request":7,"originalInputTokens":15714,"inputTokens":15714,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":8,"originalInputTokens":15873,"inputTokens":16110,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":9,"originalInputTokens":15905,"inputTokens":16383,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":10,"originalInputTokens":15779,"inputTokens":16504,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":11,"originalInputTokens":16000,"inputTokens":16993,"inputBudget":27552,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]},{"request":12,"originalInputTokens":15999,"inputTokens":16945,"inputBudget":21197,"softTarget":16000,"sources":[{"path":"src/query.ts","characters":142,"retained":true},{"path":"src/summary.ts","characters":155,"retained":true},{"path":"src/transition.ts","characters":167,"retained":true},{"path":"src/App.tsx","characters":1991,"retained":true},{"path":"src/types.ts","characters":82,"retained":true},{"path":"test/domain.test.mjs","characters":1715,"retained":true}]}]}
@@ -0,0 +1,39 @@
✔ native seed framing reserves capacity before optional history without changing the selected window (2039.7228ms)
✔ direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget (2446.9514ms)
✔ one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments (3863.3558ms)
✔ tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests (928.2012ms)
✔ oversized required user instructions pause intact and can be explicitly resumed after increasing the window (1714.7245ms)
✔ all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix (1350.4595ms)
✔ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (809.835ms)
✔ invalid orphan result is rejected before archive or network preparation (592.7567ms)
✔ invalid missing result is rejected before archive or network preparation (714.997ms)
✔ invalid wrong result is rejected before archive or network preparation (657.1018ms)
✔ invalid duplicate call is rejected before archive or network preparation (726.3918ms)
✔ a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON (1934.7044ms)
✔ changed or missing archived evidence stops reuse and is never silently recreated (1353.31ms)
✔ transaction failure prevents publishing a plan and any corresponding model request (1167.6815ms)
✔ the Provider rejects body mutation after a sealed plan before calling HTTP (1295.8821ms)
✔ HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command (12256.14ms)
✔ a real process exit after plan persistence marks interruption and never issues an automatic model request (1493.1791ms)
✔ small code and actual failed command stay visible when their original multi-tool group cannot fit (2817.5421ms)
✔ mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes (2935.5331ms)
✔ working observations are bound to the current Task and stop treating a pre-application file revision as current evidence (2209.6653ms)
✔ a sealed observation rejects changed or missing original result artifacts instead of recreating evidence (1974.3203ms)
✔ a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid (6319.2793ms)
✔ budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries (4.4512ms)
✔ actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening (18421.1531ms)
✔ actual HTTP file pagination advances over a long file with each returned page visible in the next request (2954.4126ms)
✔ later mixed history pages cannot displace the actual module sources and complete requirements (5429.4631ms)
✔ a later narrow page of the same file revision cannot evict the wider actual observation (3259.3701ms)
✔ six small source files stay complete across metadata turns even when mandatory evidence exceeds the soft target (2831.2465ms)
✔ historical read-artifact navigation points to the original artifact and next page, never its result wrapper (1134.8138ms)
✔ a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view (1190.842ms)
✔ actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes (9762.9155ms)
ℹ tests 31
ℹ suites 0
ℹ pass 31
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 61529.4006
@@ -0,0 +1,73 @@
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (1.8342ms)
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.6263ms)
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.2333ms)
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3434ms)
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (7168.2766ms)
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (7126.1239ms)
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (7218.8157ms)
✔ native seed framing reserves capacity before optional history without changing the selected window (2024.8494ms)
✔ direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget (3087.7985ms)
✔ one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments (5799.3675ms)
✔ tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests (1093.7909ms)
✔ oversized required user instructions pause intact and can be explicitly resumed after increasing the window (1965.754ms)
✔ all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix (1585.0679ms)
✖ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (1171.4455ms)
✔ invalid orphan result is rejected before archive or network preparation (787.392ms)
✔ invalid missing result is rejected before archive or network preparation (777.1528ms)
✔ invalid wrong result is rejected before archive or network preparation (773.6971ms)
✔ invalid duplicate call is rejected before archive or network preparation (750.3214ms)
✔ a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON (2390.9915ms)
✔ changed or missing archived evidence stops reuse and is never silently recreated (1109.0773ms)
✔ transaction failure prevents publishing a plan and any corresponding model request (957.0372ms)
✔ the Provider rejects body mutation after a sealed plan before calling HTTP (1192.0419ms)
✔ HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command (9590.2848ms)
✔ a real process exit after plan persistence marks interruption and never issues an automatic model request (1583.4676ms)
✔ the latest oversized session result reaches the next request together with already read source modules (4240.8591ms)
✔ every call in a large latest group keeps its actual outcome, including denied and unknown results (2334.4132ms)
✔ a small complete latest tool group is sent once and needs no duplicate feedback view (1822.7439ms)
✔ real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing (4930.5822ms)
✔ small code and actual failed command stay visible when their original multi-tool group cannot fit (3487.7511ms)
✔ mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes (3612.0072ms)
✔ working observations are bound to the current Task and stop treating a pre-application file revision as current evidence (3276.0903ms)
✔ a sealed observation rejects changed or missing original result artifacts instead of recreating evidence (2023.1842ms)
✔ a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid (7235.6425ms)
✔ budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries (4.203ms)
✔ actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening (13892.5968ms)
✔ actual HTTP file pagination advances over a long file with each returned page visible in the next request (4120.3793ms)
✔ later mixed history pages cannot displace the actual module sources and complete requirements (4872.1759ms)
✔ a later narrow page of the same file revision cannot evict the wider actual observation (3008.7191ms)
✔ six small source files stay complete across metadata turns even when mandatory evidence exceeds the soft target (2781.0973ms)
✔ historical read-artifact navigation points to the original artifact and next page, never its result wrapper (1151.7872ms)
✔ a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view (1170.9574ms)
✔ actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes (23827.7338ms)
ℹ tests 42
ℹ suites 0
ℹ pass 41
ℹ fail 1
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 74660.6056
✖ failing tests:
test at tests\request-plan.test.mjs:127:1
✖ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (1171.4455ms)
AssertionError [ERR_ASSERTION]: The expression evaluated to a falsy value:
assert.ok(plan.record.estimatedInputTokens > plan.record.budget.targetInputTokens)
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/request-plan.test.mjs:136:10)
at Test.runInAsyncScope (node:async_hooks:227:14)
at Test.run (node:internal/test_runner/test:1402:25)
at Test.processPendingSubtests (node:internal/test_runner/test:974:18)
at Test.postRun (node:internal/test_runner/test:1542:19)
at Test.run (node:internal/test_runner/test:1467:12)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: false,
expected: true,
operator: '==',
diff: 'simple'
}
@@ -0,0 +1,13 @@
PASS actual clean user-level installation
PASS actual installer rejects an open attested desktop window
PASS actual update rejects a pending owned model request
PASS actual installer rejects a persistent original task approval
PASS actual manifest fault installer preserves original pointer, PID and all data
PASS actual pointer-published fault rolls original host and pointer back
PASS actual update retains original PID, instance, DPAPI ciphertext and every persistent byte
PASS installed native bootstrap verifies and opens the registered release
PASS native desktop remains registered before explicit owned cleanup
PASS real host restart restores the owned saved credential and actual HTTP authentication
PASS actual installed current results and saved HTML user paths
PASS actual uninstall closes only the idle owned host and preserves user data
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\desktop-install-70f0d012-97e5-4410-99ef-12f805bf4c09
@@ -0,0 +1,37 @@
✔ agent browser flow waits for original Task/Run approval, dispatches once, and returns paired original results (4671.946ms)
✖ a sealed batch at the step limit hands off and continues the same Task into actual checks without replaying saved tools (6422.1075ms)
ℹ tests 2
ℹ suites 0
ℹ pass 1
ℹ fail 1
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 6605.5165
✖ failing tests:
test at tests\change-set-api.test.mjs:75:1
✖ a sealed batch at the step limit hands off and continues the same Task into actual checks without replaying saved tools (6422.1075ms)
AssertionError [ERR_ASSERTION]: The input did not match the regular expression /变更集/. Input:
'Error: 请先审查待处理改动;继续请求模型不能代替文件审核。'
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
at async TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/change-set-api.test.mjs:105:3)
at async Test.run (node:internal/test_runner/test:1409:7)
at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: Error: 请先审查待处理改动;继续请求模型不能代替文件审核。
at Object.api (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/helpers.mjs:107:43)
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
at async waitForActual (node:assert:646:5)
at async strict.rejects (node:assert:769:25)
at async TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/change-set-api.test.mjs:105:3)
at async Test.run (node:internal/test_runner/test:1409:7)
at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3),
expected: /变更集/,
operator: 'rejects',
diff: 'simple'
}
@@ -0,0 +1,164 @@
✔ input that fits the engine window but exceeds remaining credit diagnoses the credit limit (0.4772ms)
✔ window overflow and historical pauses retain distinct and honest diagnoses (0.0852ms)
✔ a budget pause persists concrete text/tool/history/image breakdown and never dispatches an oversized request (2289.0781ms)
✔ explicit frozen preview resumes the same Task in a new Run, preserves completed tools and does not change global config or selected model (3281.4316ms)
✔ insufficient budgets, silently clamped capacity and arbitrary config fields reject without a physical request or mutating task budget (2319.3069ms)
✔ changed session, changed registry, expiry and altered frozen preview all require a new explicit preview (2561.6087ms)
✔ preview preserves unknown invocation status and increasing Task allowance is committed only with confirmed new Run (3368.5301ms)
✔ batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart (6183.6659ms)
✔ delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files (4166.4571ms)
✔ a compatible model can seal proposals through the real HTTP loop while application stays behind user review (7035.2368ms)
✔ a sealed batch at the step limit hands off and continues the same Task into actual checks without replaying saved tools (16179.7998ms)
✔ applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation (2376.4348ms)
▶ complete sealed batch hands off after all tools settle with no next model request
✔ complete (4778.2753ms)
✔ later-error (5124.2499ms)
✔ complete sealed batch hands off after all tools settle with no next model request (9903.25ms)
▶ partial, changed, failed or cancelled batches cannot claim complete review handoff
✔ partial (4367.8721ms)
✔ new-proposal (4670.0788ms)
✔ failed (3984.8518ms)
✔ conflict (4780.9337ms)
✔ cancelled (4050.7866ms)
✔ unknown (4783.6294ms)
✔ tampered (4320.9493ms)
✔ partial, changed, failed or cancelled batches cannot claim complete review handoff (30960.5505ms)
✔ actual process exit at file-batch prepared preserves durable identity and never replays writes (1958.466ms)
✔ actual process exit at file-batch application_started preserves durable identity and never replays writes (2141.3829ms)
✔ actual process exit at file-batch write_intent preserves durable identity and never replays writes (1903.4023ms)
✔ actual process exit at file-batch staged preserves durable identity and never replays writes (2181.5025ms)
✔ actual process exit at file-batch replaced preserves durable identity and never replays writes (2603.3938ms)
✔ actual process exit at file-batch file_recorded preserves durable identity and never replays writes (2711.7967ms)
✔ actual process exit at file-batch finished preserves durable identity and never replays writes (2792.3029ms)
✔ actual process exit at file-batch rollback_started preserves durable identity and never replays writes (3211.5358ms)
✔ actual process exit at file-batch restore_intent preserves durable identity and never replays writes (3090.5842ms)
✔ actual process exit at file-batch restore_staged preserves durable identity and never replays writes (3054.1173ms)
✔ actual process exit at file-batch restored preserves durable identity and never replays writes (3422.2453ms)
✔ actual process exit at file-batch restore_recorded preserves durable identity and never replays writes (3428.2859ms)
✔ actual process exit at file-batch rollback_finished preserves durable identity and never replays writes (3268.199ms)
warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it
warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it
✔ sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files (2789.106ms)
Switched to a new branch 'owner-branch'
✔ a conflict in the last file or Git branch prevents writing every file in the batch (3138.8255ms)
✔ duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch (1401.5944ms)
✔ fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target (2630.57ms)
✔ a failure after replacement restores only batch bytes and never retries an old application (2052.9028ms)
✔ rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery (2371.6453ms)
✔ an unattempted owner-created file identical to a suggestion remains external and is never removed (1812.6214ms)
✔ active batch requests are serialized and cancellation leaves a verifiable ended batch (1578.6312ms)
✔ batch application and rollback preserve unrelated Git index and worktree bytes (4063.2938ms)
✔ recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection (2186.2208ms)
✔ one Task can seal pending proposals from earlier Runs while snapshots retain each source Run (1758.31ms)
✔ controlled installation pins the native kernel and bridge independently of the existing connection-probe identity (913.9585ms)
✔ controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract (0.5076ms)
✔ owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations (4.9788ms)
✔ bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch (911.7935ms)
✔ bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect (896.0863ms)
✔ bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity (777.3973ms)
✔ stopped and oversized bridge requests never reach a local model or tool callback (647.5694ms)
✔ native text and call IDs preserve original result pairing while unsupported content fails closed (0.8548ms)
✔ one engine child freezes real installation identity before creating tasks and rejects a changed source (12113.3469ms)
✔ owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs (34838.6695ms)
✔ forged native scope cannot change a parent file and a final completion claim cannot replace worker proof (12766.7581ms)
✔ duplicate native IDs are rejected without replaying a saved tool (12244.7175ms)
✖ native input exceeding the context budget is retained and sends no model request (10231.6607ms)
✔ bounded native sends verify original tool provenance and reject forged views or missing versions (13910.8387ms)
✔ stop retains a late reported model usage once and executes no tool from that output (10764.0046ms)
✔ a source change after the original model intent stops before native tools execute (10878.0128ms)
✔ an engine source change while approval is pending invalidates the old permission before any check starts (14440.3452ms)
✔ missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text (0.5113ms)
✔ closed root with an original live descendant remains unknown and retains its process tree (0.276ms)
✔ host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes (15173.7566ms)
✔ corrupted model reservation cannot reduce recovered budget or permit a new engine request (11399.5634ms)
✔ reservation uses actual known usage from the same route, never lowers estimates or rewrites original receipts (1.6494ms)
✔ reservation verification binds original Task/Run consumption and rejects changed usage or foreign provenance (0.5599ms)
✔ known high input calibrates the next request and stops before dispatch while preserving the completed read (1459.3979ms)
✔ one reported overrun stops legacy requests and keeps actual use and excess (1056.8394ms)
✔ one reported overrun stops pool requests and keeps actual use and excess (1440.2433ms)
✔ one reported overrun stops connection requests and keeps actual use and excess (1383.0982ms)
✔ reported usage below the limit prevents an unaffordable legacy retry before another dispatch (1058.4368ms)
✔ reported usage below the limit prevents an unaffordable pool retry before another dispatch (1725.2826ms)
✔ native bridge seals calibrated refusal with original consumption and preserves versioned request verification (21403.8819ms)
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (2.477ms)
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.6507ms)
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.9559ms)
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3856ms)
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (3914.7979ms)
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (4138.5565ms)
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (4226.3619ms)
✔ context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs (3569.4716ms)
✔ delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification (1689.8337ms)
✔ native seed framing reserves capacity before optional history without changing the selected window (724.4385ms)
✔ direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget (1372.5234ms)
✔ one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments (3293.3926ms)
✔ tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests (711.6186ms)
✔ oversized required user instructions pause intact and can be explicitly resumed after increasing the window (1191.9811ms)
✔ all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix (1375.2786ms)
✔ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (899.1092ms)
✔ invalid orphan result is rejected before archive or network preparation (622.664ms)
✔ invalid missing result is rejected before archive or network preparation (549.8002ms)
✔ invalid wrong result is rejected before archive or network preparation (538.4463ms)
✔ invalid duplicate call is rejected before archive or network preparation (557.9724ms)
✔ a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON (1348.7152ms)
✔ changed or missing archived evidence stops reuse and is never silently recreated (779.1231ms)
✔ transaction failure prevents publishing a plan and any corresponding model request (647.6709ms)
✔ the Provider rejects body mutation after a sealed plan before calling HTTP (565.72ms)
✔ HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command (7571.2057ms)
✔ a real process exit after plan persistence marks interruption and never issues an automatic model request (1035.0103ms)
✔ a stop from the event loop interrupts immediate model replies before later tools (1013.9589ms)
✔ a stop after the first tool preserves a complete interrupted multi-call protocol group (1523.4857ms)
✔ the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands (4367.8721ms)
✔ denial prevents command execution and produces a paired denied result (1646.7693ms)
✔ stopping during approval interrupts pending calls without executing or replaying them (1174.5599ms)
✔ stopping a running fixture command terminates its own process tree and retains uncertain state (1774.138ms)
✔ command output decodes split UTF-8 and excludes the workbench key from child environment (949.2318ms)
✔ model-list testing uses a tentative key without changing the saved connection and redacts service errors (7.4022ms)
✔ truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities (2022.9889ms)
✔ request projection keeps exact tool pairs and complete recent user instructions while preserving disk history (1174.8941ms)
✔ the latest oversized session result reaches the next request together with already read source modules (2136.7538ms)
✔ every call in a large latest group keeps its actual outcome, including denied and unknown results (1232.4305ms)
✔ a small complete latest tool group is sent once and needs no duplicate feedback view (1373.7421ms)
✔ real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing (3238.5874ms)
✔ small code and actual failed command stay visible when their original multi-tool group cannot fit (1218.3437ms)
✔ mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes (1655.731ms)
✔ working observations are bound to the current Task and stop treating a pre-application file revision as current evidence (1984.6639ms)
✔ a sealed observation rejects changed or missing original result artifacts instead of recreating evidence (1300.0902ms)
✔ a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid (5803.0905ms)
✔ budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries (4.1628ms)
✔ actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening (9861.9122ms)
✔ actual HTTP file pagination advances over a long file with each returned page visible in the next request (2883.8982ms)
✔ later mixed history pages cannot displace the actual module sources and complete requirements (6923.8193ms)
✔ a later narrow page of the same file revision cannot evict the wider actual observation (3869.6365ms)
✔ six small source files stay complete across metadata turns even when mandatory evidence exceeds the soft target (3272.3634ms)
✔ historical read-artifact navigation points to the original artifact and next page, never its result wrapper (1180.1926ms)
✔ a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view (1202.8665ms)
✔ actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes (12322.1705ms)
ℹ tests 131
ℹ suites 0
ℹ pass 130
ℹ fail 1
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 235230.262
✖ failing tests:
test at tests\engine-worker.test.mjs:90:1
✖ native input exceeding the context budget is retained and sends no model request (10231.6607ms)
AssertionError [ERR_ASSERTION]: The input did not match the regular expression /预算/. Input:
'原引擎必需输入超过上下文窗口可用容量,未发送模型请求。原输入和容量分项已保存;请核对模型容量后显式继续。'
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/engine-worker.test.mjs:98:91)
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
at async Test.run (node:internal/test_runner/test:1409:7)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: '原引擎必需输入超过上下文窗口可用容量,未发送模型请求。原输入和容量分项已保存;请核对模型容量后显式继续。',
expected: /预算/,
operator: 'match',
diff: 'simple'
}
@@ -0,0 +1 @@
{"success":true,"version":"1.24.0","pid":36552,"projects":42,"sessions":58,"tables":{"events":10329,"metadata":6,"outbox":10329,"projects":42,"records":4953,"sessions":58,"sqlite_sequence":1},"runtimeRoot":"C:\\Users\\wangy\\AppData\\Local\\Programs\\AgentWorkbench\\versions\\Agent-Workbench-1.24.0-win-x64-20261102152844546","sourceCommit":"ba07713a3610134057881d17c9db9116bbc58135","hasKey":true,"active":[],"mode":"before","startedAt":"2026-11-03T00:35:01.822Z","finishedAt":"2026-11-03T00:35:20.046Z","realModelRequests":0,"scope":"Public API/full original row/export/artifact hashes; installer retains original running host and Provider. No credential extraction or task replay."}
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,170 @@
✔ input that fits the engine window but exceeds remaining credit diagnoses the credit limit (0.4781ms)
✔ window overflow and historical pauses retain distinct and honest diagnoses (0.0846ms)
✔ a budget pause persists concrete text/tool/history/image breakdown and never dispatches an oversized request (2254.359ms)
✔ explicit frozen preview resumes the same Task in a new Run, preserves completed tools and does not change global config or selected model (3163.6716ms)
✔ insufficient budgets, silently clamped capacity and arbitrary config fields reject without a physical request or mutating task budget (2515.9725ms)
✔ changed session, changed registry, expiry and altered frozen preview all require a new explicit preview (2396.7525ms)
✔ preview preserves unknown invocation status and increasing Task allowance is committed only with confirmed new Run (3280.2137ms)
✔ batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart (6288.6768ms)
✔ delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files (4014.9419ms)
✔ a compatible model can seal proposals through the real HTTP loop while application stays behind user review (6595.7798ms)
✔ a sealed batch at the step limit hands off and continues the same Task into actual checks without replaying saved tools (15211.4275ms)
✔ applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation (2469.6939ms)
▶ complete sealed batch hands off after all tools settle with no next model request
✔ complete (4214.6965ms)
✔ later-error (4835.0104ms)
✔ complete sealed batch hands off after all tools settle with no next model request (9050.3886ms)
▶ partial, changed, failed or cancelled batches cannot claim complete review handoff
✔ partial (4499.5806ms)
✔ new-proposal (4157.7788ms)
✔ failed (4456.5093ms)
✔ conflict (4586.3256ms)
✔ cancelled (3893.4829ms)
✔ unknown (4707.8593ms)
✔ tampered (5051.9704ms)
✔ partial, changed, failed or cancelled batches cannot claim complete review handoff (31354.9596ms)
✔ actual process exit at file-batch prepared preserves durable identity and never replays writes (1810.9369ms)
✔ actual process exit at file-batch application_started preserves durable identity and never replays writes (2144.4908ms)
✔ actual process exit at file-batch write_intent preserves durable identity and never replays writes (1985.2734ms)
✔ actual process exit at file-batch staged preserves durable identity and never replays writes (2348.0761ms)
✔ actual process exit at file-batch replaced preserves durable identity and never replays writes (2281.0135ms)
✔ actual process exit at file-batch file_recorded preserves durable identity and never replays writes (2542.0479ms)
✔ actual process exit at file-batch finished preserves durable identity and never replays writes (2645.7507ms)
✔ actual process exit at file-batch rollback_started preserves durable identity and never replays writes (3307.3518ms)
✔ actual process exit at file-batch restore_intent preserves durable identity and never replays writes (3203.6028ms)
✔ actual process exit at file-batch restore_staged preserves durable identity and never replays writes (2872.6014ms)
✔ actual process exit at file-batch restored preserves durable identity and never replays writes (3207.1629ms)
✔ actual process exit at file-batch restore_recorded preserves durable identity and never replays writes (3456.625ms)
✔ actual process exit at file-batch rollback_finished preserves durable identity and never replays writes (3291.3962ms)
warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it
warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it
✔ sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files (2892.13ms)
Switched to a new branch 'owner-branch'
✔ a conflict in the last file or Git branch prevents writing every file in the batch (2881.8143ms)
✔ duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch (1391.4823ms)
✔ fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target (2466.4145ms)
✔ a failure after replacement restores only batch bytes and never retries an old application (1727.9885ms)
✔ rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery (2384.1335ms)
✔ an unattempted owner-created file identical to a suggestion remains external and is never removed (1809.7168ms)
✔ active batch requests are serialized and cancellation leaves a verifiable ended batch (1452.2638ms)
✔ batch application and rollback preserve unrelated Git index and worktree bytes (3214.0272ms)
✔ recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection (2623.7291ms)
✔ one Task can seal pending proposals from earlier Runs while snapshots retain each source Run (1615.13ms)
✔ controlled installation pins the native kernel and bridge independently of the existing connection-probe identity (959.0218ms)
✔ controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract (0.5566ms)
✔ owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations (5.3393ms)
✔ bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch (735.109ms)
✔ bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect (929.2965ms)
✔ bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity (637.5648ms)
✔ stopped and oversized bridge requests never reach a local model or tool callback (764.412ms)
✔ sealed r1-off failure fits its original 16K config with authentic latest status and readable source (14.1493ms)
✔ sealed r1-on failure fits its original 16K config with authentic latest status and readable source (10.7966ms)
✔ sealed r2-on failure fits its original 16K config with authentic latest status and readable source (8.5914ms)
✔ sealed r2-off failure fits its original 16K config with authentic latest status and readable source (8.7137ms)
✔ archived native call pairs require exact saved arguments/results rather than model-written summaries (8.3391ms)
✔ full system/user requirements and mandatory current failure can refuse rather than be trimmed (13.0742ms)
✔ small native input is byte-preserving; developer instructions remain mandatory after compaction (0.2426ms)
✔ older failing checks and pending proposals remain visible after a later large file read (14.7652ms)
✔ bounded result keeps every check status and cuts Unicode only on whole characters (0.4404ms)
✔ controlled engine HTTP freezes one child, pages original owned input/report, rejects foreign reads and prevents changed-source reuse (15113.5555ms)
✔ native text and call IDs preserve original result pairing while unsupported content fails closed (1.3291ms)
✔ one engine child freezes real installation identity before creating tasks and rejects a changed source (8460.0535ms)
✔ owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs (26594.9272ms)
✔ forged native scope cannot change a parent file and a final completion claim cannot replace worker proof (13479.2898ms)
✔ duplicate native IDs are rejected without replaying a saved tool (11901.6727ms)
✔ native input exceeding the context budget is retained and sends no model request (10305.5649ms)
✔ bounded native sends verify original tool provenance and reject forged views or missing versions (13687.7538ms)
✔ stop retains a late reported model usage once and executes no tool from that output (10848.4664ms)
✔ a source change after the original model intent stops before native tools execute (10222.0307ms)
✔ an engine source change while approval is pending invalidates the old permission before any check starts (14590.1925ms)
✔ missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text (0.5232ms)
✔ closed root with an original live descendant remains unknown and retains its process tree (0.2726ms)
✔ host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes (15021.7273ms)
✔ corrupted model reservation cannot reduce recovered budget or permit a new engine request (12877.3045ms)
✔ saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance (695.6396ms)
✔ owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched (813.027ms)
✔ Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes (1908.0632ms)
✔ mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools (2258.6802ms)
▶ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool
✔ Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial" (1290.5845ms)
✔ Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal (1700.8777ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal (1602.5777ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte (1630.9884ms)
✔ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool (6225.922ms)
▶ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay
✔ chat-completions (1812.3813ms)
✔ responses (1808.9892ms)
✔ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay (3621.9089ms)
✔ wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint (0.2591ms)
✔ connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions (685.0721ms)
✔ reservation uses actual known usage from the same route, never lowers estimates or rewrites original receipts (1.7281ms)
✔ reservation verification binds original Task/Run consumption and rejects changed usage or foreign provenance (0.48ms)
✔ known high input calibrates the next request and stops before dispatch while preserving the completed read (1447.5822ms)
✔ one reported overrun stops legacy requests and keeps actual use and excess (1214.2904ms)
✔ one reported overrun stops pool requests and keeps actual use and excess (1782.9067ms)
✔ one reported overrun stops connection requests and keeps actual use and excess (1641.352ms)
✔ reported usage below the limit prevents an unaffordable legacy retry before another dispatch (1083.9795ms)
✔ reported usage below the limit prevents an unaffordable pool retry before another dispatch (1931.2061ms)
✔ native bridge seals calibrated refusal with original consumption and preserves versioned request verification (12627.0073ms)
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (1.8553ms)
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.6019ms)
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.6355ms)
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3638ms)
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (3561.2758ms)
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (3629.9503ms)
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (4839.0984ms)
✔ context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs (3409.9772ms)
✔ delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification (1692.5361ms)
✔ native seed framing reserves capacity before optional history without changing the selected window (664.3132ms)
✔ direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget (1424.1889ms)
✔ one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments (3589.1491ms)
✔ tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests (866.638ms)
✔ oversized required user instructions pause intact and can be explicitly resumed after increasing the window (1282.7167ms)
✔ all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix (817.1144ms)
✔ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (698.5481ms)
✔ invalid orphan result is rejected before archive or network preparation (492.6358ms)
✔ invalid missing result is rejected before archive or network preparation (537.6192ms)
✔ invalid wrong result is rejected before archive or network preparation (484.0046ms)
✔ invalid duplicate call is rejected before archive or network preparation (570.5568ms)
✔ a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON (1414.5826ms)
✔ changed or missing archived evidence stops reuse and is never silently recreated (960.8616ms)
✔ transaction failure prevents publishing a plan and any corresponding model request (797.6377ms)
✔ the Provider rejects body mutation after a sealed plan before calling HTTP (690.4846ms)
✔ HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command (7196.0068ms)
✔ a real process exit after plan persistence marks interruption and never issues an automatic model request (1120.1729ms)
✔ a stop from the event loop interrupts immediate model replies before later tools (1106.1643ms)
✔ a stop after the first tool preserves a complete interrupted multi-call protocol group (1398.4979ms)
✔ the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands (4600.2004ms)
✔ denial prevents command execution and produces a paired denied result (1364.1836ms)
✔ stopping during approval interrupts pending calls without executing or replaying them (1018.3062ms)
✔ stopping a running fixture command terminates its own process tree and retains uncertain state (1522.848ms)
✔ command output decodes split UTF-8 and excludes the workbench key from child environment (1016.0014ms)
✔ model-list testing uses a tentative key without changing the saved connection and redacts service errors (6.8813ms)
✔ truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities (2093.9969ms)
✔ request projection keeps exact tool pairs and complete recent user instructions while preserving disk history (1535.6741ms)
✔ the latest oversized session result reaches the next request together with already read source modules (2051.5081ms)
✔ every call in a large latest group keeps its actual outcome, including denied and unknown results (1080.2312ms)
✔ a small complete latest tool group is sent once and needs no duplicate feedback view (865.6272ms)
✔ real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing (2529.9692ms)
✔ small code and actual failed command stay visible when their original multi-tool group cannot fit (1481.1618ms)
✔ mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes (1718.8272ms)
✔ working observations are bound to the current Task and stop treating a pre-application file revision as current evidence (2250.6173ms)
✔ a sealed observation rejects changed or missing original result artifacts instead of recreating evidence (1370.3846ms)
✔ a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid (5238.7316ms)
✔ budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries (4.237ms)
✔ actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening (9468.6392ms)
✔ actual HTTP file pagination advances over a long file with each returned page visible in the next request (3985.3817ms)
✔ later mixed history pages cannot displace the actual module sources and complete requirements (5271.0972ms)
✔ a later narrow page of the same file revision cannot evict the wider actual observation (4200.7842ms)
✔ six small source files stay complete across metadata turns even when mandatory evidence exceeds the soft target (3110.5548ms)
✔ historical read-artifact navigation points to the original artifact and next page, never its result wrapper (1155.7987ms)
✔ a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view (1261.4608ms)
✔ actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes (9257.7856ms)
ℹ tests 155
ℹ suites 0
ℹ pass 155
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 241938.7563
@@ -0,0 +1,19 @@
▶ complete sealed batch hands off after all tools settle with no next model request
✔ complete (2822.2958ms)
✔ later-error (3434.1729ms)
✔ complete sealed batch hands off after all tools settle with no next model request (6257.3216ms)
▶ partial, changed, failed or cancelled batches cannot claim complete review handoff
✔ partial (2641.3252ms)
✔ new-proposal (2934.5419ms)
✔ failed (2418.7157ms)
✔ conflict (2945.6362ms)
✔ cancelled (2617.2764ms)
✔ partial, changed, failed or cancelled batches cannot claim complete review handoff (13558.658ms)
ℹ tests 9
ℹ suites 0
ℹ pass 9
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 20005.5195
@@ -0,0 +1,65 @@
▶ complete sealed batch hands off after all tools settle with no next model request
✖ complete (3065.3274ms)
✖ later-error (3120.0606ms)
✖ complete sealed batch hands off after all tools settle with no next model request (6186.3072ms)
▶ partial, changed, failed or cancelled batches cannot claim complete review handoff
✔ partial (2706.109ms)
✔ new-proposal (2911.6234ms)
✔ failed (2621.5918ms)
✔ conflict (2927.4698ms)
✔ cancelled (2389.9656ms)
✔ partial, changed, failed or cancelled batches cannot claim complete review handoff (13558.1116ms)
ℹ tests 9
ℹ suites 0
ℹ pass 6
ℹ fail 3
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 19967.9408
✖ failing tests:
test at tests\change-set-handoff.test.mjs:49:59
✖ complete (3065.3274ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+ actual - expected
+ 'paused'
- 'needs_review'
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/change-set-handoff.test.mjs:51:12)
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
at async Test.run (node:internal/test_runner/test:1409:7)
at async TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/change-set-handoff.test.mjs:49:51)
at async Test.run (node:internal/test_runner/test:1409:7)
at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: 'paused',
expected: 'needs_review',
operator: 'strictEqual',
diff: 'simple'
}
test at tests\change-set-handoff.test.mjs:49:59
✖ later-error (3120.0606ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+ actual - expected
+ 'paused'
- 'needs_review'
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/change-set-handoff.test.mjs:51:12)
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
at async Test.run (node:internal/test_runner/test:1409:7)
at async TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/change-set-handoff.test.mjs:49:51)
at async Test.run (node:internal/test_runner/test:1409:7)
at async startSubtestAfterBootstrap (node:internal/test_runner/harness:387:3) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: 'paused',
expected: 'needs_review',
operator: 'strictEqual',
diff: 'simple'
}
@@ -0,0 +1,68 @@
✔ input that fits the engine window but exceeds remaining credit diagnoses the credit limit (0.4841ms)
✔ window overflow and historical pauses retain distinct and honest diagnoses (0.0826ms)
✔ batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart (10477.3994ms)
✔ delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files (7468.871ms)
✖ a compatible model can seal proposals through the real HTTP loop while application stays behind user review (11227.3288ms)
✖ a sealed batch at the step limit hands off and continues the same Task into actual checks without replaying saved tools (33311.8808ms)
✔ applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation (3676.7642ms)
warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it
warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it
✔ sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files (5577.3002ms)
Switched to a new branch 'owner-branch'
✔ a conflict in the last file or Git branch prevents writing every file in the batch (4923.5528ms)
✔ duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch (2688.2753ms)
✔ fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target (4060.515ms)
✔ a failure after replacement restores only batch bytes and never retries an old application (3174.7804ms)
✔ rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery (2638.6914ms)
✔ an unattempted owner-created file identical to a suggestion remains external and is never removed (2533.6339ms)
✔ active batch requests are serialized and cancellation leaves a verifiable ended batch (2071.9668ms)
✔ batch application and rollback preserve unrelated Git index and worktree bytes (4692.8647ms)
✔ recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection (3178.6308ms)
✔ one Task can seal pending proposals from earlier Runs while snapshots retain each source Run (2714.9003ms)
✔ a stop from the event loop interrupts immediate model replies before later tools (4451.7161ms)
✔ a stop after the first tool preserves a complete interrupted multi-call protocol group (3357.7394ms)
✔ the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands (10108.7927ms)
✔ denial prevents command execution and produces a paired denied result (3149.9767ms)
✔ stopping during approval interrupts pending calls without executing or replaying them (2196.6602ms)
✔ stopping a running fixture command terminates its own process tree and retains uncertain state (2976.6ms)
✔ command output decodes split UTF-8 and excludes the workbench key from child environment (1243.4248ms)
✔ model-list testing uses a tentative key without changing the saved connection and redacts service errors (7.3075ms)
✔ truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities (3860.5172ms)
✔ request projection keeps exact tool pairs and complete recent user instructions while preserving disk history (2350.0765ms)
ℹ tests 28
ℹ suites 0
ℹ pass 26
ℹ fail 2
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 66415.5375
✖ failing tests:
test at tests\change-set-api.test.mjs:46:1
✖ a compatible model can seal proposals through the real HTTP loop while application stays behind user review (11227.3288ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
3 !== 2
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/change-set-api.test.mjs:70:10)
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
at async Test.run (node:internal/test_runner/test:1409:7)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: 3,
expected: 2,
operator: 'strictEqual',
diff: 'simple'
}
test at tests\change-set-api.test.mjs:75:1
✖ a sealed batch at the step limit hands off and continues the same Task into actual checks without replaying saved tools (33311.8808ms)
Error: Timed out waiting for test state.
at until (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/helpers.mjs:39:38)
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
at async TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/change-set-api.test.mjs:99:3)
at async Test.run (node:internal/test_runner/test:1409:7)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7)
File diff suppressed because it is too large Load Diff
@@ -0,0 +1 @@
{"success":true,"version":"1.24.1","sourceCommit":"ba07713a3610134057881d17c9db9116bbc58135","files":194,"bytes":43407618,"manifestSha256":"a868e43222f95244eea9cff05977168e1a00ab7a846cbd30c77fb1b8bc0c3e94","regression":{"total":155,"passed":155,"failed":0},"originalRetained":[6,5,5,4,2,2],"fixedRetained":[6,6,6,6,6,6],"compiledFiles":22,"uiGroups":20,"realModelRequests":0,"scope":"Offline sealed-byte and actual-receipt verification. No new model calls, task execution, or claim of real-model/Purge success."}
@@ -0,0 +1,5 @@
Native screenshot format audit failed before Git staging.
Expected PNG signature: 89504e470d0a1a0a
Actual JPEG signature: ffd8ffe000104a46
Computer Use returned data:image/jpeg;base64; the raw JPEG bytes were saved with a .png filename.
Original screenshot bytes and first manifest are retained. Correctly named JPEG copies are added without transcoding.
@@ -0,0 +1,9 @@
✔ native input exceeding the context budget is retained and sends no model request (8594.1726ms)
ℹ tests 1
ℹ suites 0
ℹ pass 1
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 8781.0827
@@ -0,0 +1,84 @@
{
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261103000853284",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-source-20261103000853284",
"evidenceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-evidence-20261103000853284",
"portable": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261103000853284.zip",
"bytes": 242460501,
"sha256": "1f0126bb3109d5217ab74a348db7f57ab5c34cefd6bb950b65590838449a3965"
},
"source": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-source-20261103000853284.zip",
"bytes": 845439122,
"sha256": "6e07d0cf75870b412a4785478336a3e56e5c27a7872b2840e6d08ef2905ccaba"
},
"evidence": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-evidence-20261103000853284.zip",
"bytes": 604386826,
"sha256": "717c18cd04ca6169ac55b78210f353977d0fc4551da6fd8979f0c1691d4d8abc"
},
"documentation": {
"sourceCommit": "ba07713a3610134057881d17c9db9116bbc58135",
"originalFiles": 15203,
"originalBytes": 1819799545,
"shippedFiles": 132,
"shippedBytes": 1043150,
"evidenceManifestSha256": "c0edde6293f48e3369156f51d3aba9447591d06b42c732ec4c872992f7d10b16"
},
"installer": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261103000853284-Setup.exe",
"bytes": 212884727,
"sha256": "8e79aee3a2d54693e097b4f4a4d08c95be93c47650a4a016f554c002e97579af",
"compiler": {
"version": "6.3.1",
"sha256": "3b22d36fc7e7c421d8caf780008ecdb42b14b3f0371b9bafe3cad64e6648d9cf"
},
"source": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\installer-build-90021e9e-b0fa-4698-8c58-f630577cb7ab\\installer.iss",
"version": "1.24.1",
"candidateDirectory": "Agent-Workbench-1.24.1-win-x64-20261103000853284",
"qaFixture": null
},
"desktopRuntime": {
"version": "45.2.0",
"sha256": "010ea51bfb528c8143513439aa93fb40754403daa2023f9decd4517da71706ab",
"bytes": 249810432,
"executable": "desktop/AgentWorkbench.exe",
"scope": "Fixed original Windows Electron runtime, full license texts, isolated application loader and native bootstrap; original executable hash unchanged."
},
"nativeLauncher": {
"bytes": 12288,
"sha256": "e3d31cb7ce5009d3ca5a96d04dc16b1add0bd1f5cde7e1304461de6713d37463",
"inputs": {
"compiler": "46809206887326d2d24db1eff1f3064de972c3451abe766b49111450a5e08e00",
"source": "1c8e7d7ee5c383897bec48e9aadb8051b47c09686f74bbf34e0b6b695cd01ae5",
"icon": "f1879074e45f01c480ad9bf50b818637cc60ad56526056c886f808a4812d7b0c"
},
"compiler": "Windows .NET Framework C# compiler; source-bound cached original output, no deterministic-build claim."
},
"nodeVersion": "v24.22.1",
"reaRuntime": {
"version": "6.8.0",
"protocolVersion": "2025-03-26",
"packages": 149,
"files": 8413,
"bytes": 142395402,
"lockSha256": "687fb3fa3089a12f239dd5e87d9fa07df55a87df4935931d495a92600a1b0f6e"
},
"portableFiles": 10927,
"licenseTexts": 135,
"browserRuntime": {
"playwrightVersion": "1.64.1",
"packages": [
{
"name": "playwright",
"version": "1.64.1",
"files": 60
},
{
"name": "playwright-core",
"version": "1.64.1",
"files": 115
}
]
}
}
@@ -0,0 +1,84 @@
{
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-source-20261102235819796",
"evidenceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-evidence-20261102235819796",
"portable": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796.zip",
"bytes": 242459952,
"sha256": "bd79094ec6a2813f17870cfb30c7160b03aeba04586b5405352dfa565e9e905b"
},
"source": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-source-20261102235819796.zip",
"bytes": 845438143,
"sha256": "c012273c93a277117aa926a13f27e03498446623734bf790e47dec8e3eb93ea0"
},
"evidence": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-evidence-20261102235819796.zip",
"bytes": 604386277,
"sha256": "f2645e02ebbd130ddb7acbef6ba21cabf91ccd3ad31b33d3d29faf759cf16cef"
},
"documentation": {
"sourceCommit": "c1521e6cd2ef0db48b1b7656a9af11d741433cd5",
"originalFiles": 15203,
"originalBytes": 1819798387,
"shippedFiles": 132,
"shippedBytes": 1041992,
"evidenceManifestSha256": "4ea9eafab877552d7b5bb2f05e8efda5d0a18b84b396f127ff8817bb55e7e655"
},
"installer": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796-Setup.exe",
"bytes": 212884163,
"sha256": "1a851f33438288b274eb259628694117117a2d107d73d75340e676fb97bfafa3",
"compiler": {
"version": "6.3.1",
"sha256": "3b22d36fc7e7c421d8caf780008ecdb42b14b3f0371b9bafe3cad64e6648d9cf"
},
"source": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\installer-build-feaecdac-2b59-4515-be3b-ccdb464c66d2\\installer.iss",
"version": "1.24.1",
"candidateDirectory": "Agent-Workbench-1.24.1-win-x64-20261102235819796",
"qaFixture": null
},
"desktopRuntime": {
"version": "45.2.0",
"sha256": "010ea51bfb528c8143513439aa93fb40754403daa2023f9decd4517da71706ab",
"bytes": 249810432,
"executable": "desktop/AgentWorkbench.exe",
"scope": "Fixed original Windows Electron runtime, full license texts, isolated application loader and native bootstrap; original executable hash unchanged."
},
"nativeLauncher": {
"bytes": 12288,
"sha256": "e3d31cb7ce5009d3ca5a96d04dc16b1add0bd1f5cde7e1304461de6713d37463",
"inputs": {
"compiler": "46809206887326d2d24db1eff1f3064de972c3451abe766b49111450a5e08e00",
"source": "1c8e7d7ee5c383897bec48e9aadb8051b47c09686f74bbf34e0b6b695cd01ae5",
"icon": "f1879074e45f01c480ad9bf50b818637cc60ad56526056c886f808a4812d7b0c"
},
"compiler": "Windows .NET Framework C# compiler; source-bound cached original output, no deterministic-build claim."
},
"nodeVersion": "v24.22.1",
"reaRuntime": {
"version": "6.8.0",
"protocolVersion": "2025-03-26",
"packages": 149,
"files": 8413,
"bytes": 142395402,
"lockSha256": "687fb3fa3089a12f239dd5e87d9fa07df55a87df4935931d495a92600a1b0f6e"
},
"portableFiles": 10927,
"licenseTexts": 135,
"browserRuntime": {
"playwrightVersion": "1.64.1",
"packages": [
{
"name": "playwright",
"version": "1.64.1",
"files": 60
},
{
"name": "playwright-core",
"version": "1.64.1",
"files": 115
}
]
}
}
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,66 @@
{
"createdAt": "2026-11-02T23:52:28.496Z",
"version": "1.24.1",
"files": [
{
"path": "src/core/context/request-plan.mjs",
"bytes": 40633,
"sha256": "0525beddf1ca05d84d780972e9a97c013f48de69e716a77be1c86ff3a2952e7d"
},
{
"path": "src/core/context/working-set.mjs",
"bytes": 11071,
"sha256": "a8e9183321c3b5bc2afb7955a6daf496ff72d3e938be9b9ec514eaacfa7352be"
},
{
"path": "src/core/workspaces/change-sets.mjs",
"bytes": 28215,
"sha256": "868377bcc441d959794dc9a7b5daaad7b6d9b185c0237eea0e6e5265141965f1"
},
{
"path": "src/server/runtime.mjs",
"bytes": 86961,
"sha256": "74e3e72430adf686b7bdd004d6b4ef4ae408c08ed67ac561b8f1ab5a75a1ae7b"
},
{
"path": "src/core/engines/engine-runner.mjs",
"bytes": 26238,
"sha256": "4df6ec31de04f2a1d50316ee06177fe399172cd4ba677a547d696101b5203a69"
},
{
"path": "src/server/diagnostics.mjs",
"bytes": 12955,
"sha256": "e931ba032c8527dabdeaec912f736a8bb1f0f67e79456a05068103897237a603"
},
{
"path": "src/shared/budget-presentation.mjs",
"bytes": 1131,
"sha256": "23baec4a153ba3d00a5b75820997d1f35897f4758d76ee40890d903cef5eeb8a"
},
{
"path": "src/client/BudgetPausePanel.tsx",
"bytes": 10000,
"sha256": "4e1007c1c8b20114669535bfe8eb667fd03ba1558783f7896621c12e31533bf9"
},
{
"path": "src/client/TaskPanel.tsx",
"bytes": 23576,
"sha256": "46b304a9332fc227e911ba70bfdb7f5473ee07635a8f281daad207f11d83514a"
},
{
"path": "src/client/types.ts",
"bytes": 40786,
"sha256": "3f409bf6f5708769994b52dfcaa44b915c40bfcfb60161b77e6964db8f7e39d1"
},
{
"path": "package.json",
"bytes": 3907,
"sha256": "de6beaa08943c85a56ed393248a8d4c6eeb14a444764b2925c1b23bc6adfb8f4"
},
{
"path": "package-lock.json",
"bytes": 105467,
"sha256": "9aea9fff1f59d690c3f87c17d072393e4dcf91e3169f0f8f7295e234d007e0fb"
}
]
}
@@ -0,0 +1,8 @@
{
"success": true,
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-50be9ee4-27af-4388-aeed-3b360fb6ba93",
"output": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-50be9ee4-27af-4388-aeed-3b360fb6ba93\\result.json",
"inputCount": 522,
"compiledFiles": 22,
"mismatches": 0
}
@@ -0,0 +1,3 @@
PASS offline-install
PASS build
{"success":true,"root":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-50be9ee4-27af-4388-aeed-3b360fb6ba93","output":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-50be9ee4-27af-4388-aeed-3b360fb6ba93\\result.json","inputCount":522,"compiledFiles":22,"mismatches":0}
@@ -0,0 +1,8 @@
{
"success": true,
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-a0edcfd2-daa5-4ae0-bd8e-5646b8ddca61",
"output": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-a0edcfd2-daa5-4ae0-bd8e-5646b8ddca61\\result.json",
"inputCount": 522,
"compiledFiles": 22,
"mismatches": 0
}
@@ -0,0 +1,3 @@
PASS offline-install
PASS build
{"success":true,"root":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-a0edcfd2-daa5-4ae0-bd8e-5646b8ddca61","output":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-a0edcfd2-daa5-4ae0-bd8e-5646b8ddca61\\result.json","inputCount":522,"compiledFiles":22,"mismatches":0}
@@ -0,0 +1,2 @@
A read-only guessed installation.json path did not exist; no file or service mutation. Enumerated the actual installed root before further desktop launch checks.
Formal installation repeated verify-current/verify-candidate scopes were inspected against install-manager.mjs: finite full-manifest, directory-inventory and loaded-input checks at preparation and before pointer publication. No automatic installer retry or live-file edit occurred. The cost of repeated full-directory integrity checks is a later performance review item; preserve publication/tamper guards.
@@ -0,0 +1,32 @@
{
"success": true,
"version": "1.24.1",
"testedAt": "2026-11-03T00:03:05.284326+00:00",
"archives": [
{
"kind": "portable",
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796.zip",
"files": 10927,
"crcPassed": true,
"manifestAndDirectoryMatch": true,
"sha256": "bd79094ec6a2813f17870cfb30c7160b03aeba04586b5405352dfa565e9e905b"
},
{
"kind": "source",
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-source-20261102235819796.zip",
"files": 26423,
"crcPassed": true,
"manifestAndDirectoryMatch": true,
"sha256": "c012273c93a277117aa926a13f27e03498446623734bf790e47dec8e3eb93ea0"
},
{
"kind": "evidence",
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-evidence-20261102235819796.zip",
"files": 15203,
"crcPassed": true,
"manifestAndDirectoryMatch": true,
"sha256": "f2645e02ebbd130ddb7acbef6ba21cabf91ccd3ad31b33d3d29faf759cf16cef"
}
],
"extractionRoot": null
}
File diff suppressed because one or more lines are too long
@@ -0,0 +1,20 @@
> local-agent-workbench@1.24.1 build
> tsc --noEmit && vite build && node scripts/build-mobile.mjs && node scripts/build-server.mjs
vite v7.3.7 building client environment for production...
transforming...
✓ 1753 modules transformed.
rendering chunks...
computing gzip size...
dist-client/index.html  0.60 kB │ gzip: 0.41 kB
dist-client/.vite/manifest.json  0.65 kB │ gzip: 0.24 kB
dist-client/mobile.html  0.84 kB │ gzip: 0.47 kB
dist-client/assets/mobile-joLHctQw.css  12.39 kB │ gzip: 3.22 kB
dist-client/assets/desktop-BYZSVsL1.css 165.03 kB │ gzip: 31.29 kB
dist-client/assets/mobile-4zqcwTeD.js  27.19 kB │ gzip: 9.34 kB
dist-client/assets/approval-presentation-Chut4EFA.js 226.80 kB │ gzip: 71.65 kB
dist-client/assets/desktop-CHREzle3.js 392.10 kB │ gzip: 110.98 kB
✓ built in 1.25s
Mobile shell built: 3 allowed assets; API and project data are never cached.
Server bundle built.
@@ -0,0 +1,8 @@
{
"success": true,
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-a0edcfd2-daa5-4ae0-bd8e-5646b8ddca61",
"output": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\packaged-build-a0edcfd2-daa5-4ae0-bd8e-5646b8ddca61\\result.json",
"inputCount": 522,
"compiledFiles": 22,
"mismatches": 0
}
@@ -0,0 +1,2 @@
added 137 packages in 7s
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,84 @@
{
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-source-20261102235819796",
"evidenceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-evidence-20261102235819796",
"portable": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796.zip",
"bytes": 242459952,
"sha256": "bd79094ec6a2813f17870cfb30c7160b03aeba04586b5405352dfa565e9e905b"
},
"source": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-source-20261102235819796.zip",
"bytes": 845438143,
"sha256": "c012273c93a277117aa926a13f27e03498446623734bf790e47dec8e3eb93ea0"
},
"evidence": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-evidence-20261102235819796.zip",
"bytes": 604386277,
"sha256": "f2645e02ebbd130ddb7acbef6ba21cabf91ccd3ad31b33d3d29faf759cf16cef"
},
"documentation": {
"sourceCommit": "c1521e6cd2ef0db48b1b7656a9af11d741433cd5",
"originalFiles": 15203,
"originalBytes": 1819798387,
"shippedFiles": 132,
"shippedBytes": 1041992,
"evidenceManifestSha256": "4ea9eafab877552d7b5bb2f05e8efda5d0a18b84b396f127ff8817bb55e7e655"
},
"installer": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796-Setup.exe",
"bytes": 212884163,
"sha256": "1a851f33438288b274eb259628694117117a2d107d73d75340e676fb97bfafa3",
"compiler": {
"version": "6.3.1",
"sha256": "3b22d36fc7e7c421d8caf780008ecdb42b14b3f0371b9bafe3cad64e6648d9cf"
},
"source": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\installer-build-feaecdac-2b59-4515-be3b-ccdb464c66d2\\installer.iss",
"version": "1.24.1",
"candidateDirectory": "Agent-Workbench-1.24.1-win-x64-20261102235819796",
"qaFixture": null
},
"desktopRuntime": {
"version": "45.2.0",
"sha256": "010ea51bfb528c8143513439aa93fb40754403daa2023f9decd4517da71706ab",
"bytes": 249810432,
"executable": "desktop/AgentWorkbench.exe",
"scope": "Fixed original Windows Electron runtime, full license texts, isolated application loader and native bootstrap; original executable hash unchanged."
},
"nativeLauncher": {
"bytes": 12288,
"sha256": "e3d31cb7ce5009d3ca5a96d04dc16b1add0bd1f5cde7e1304461de6713d37463",
"inputs": {
"compiler": "46809206887326d2d24db1eff1f3064de972c3451abe766b49111450a5e08e00",
"source": "1c8e7d7ee5c383897bec48e9aadb8051b47c09686f74bbf34e0b6b695cd01ae5",
"icon": "f1879074e45f01c480ad9bf50b818637cc60ad56526056c886f808a4812d7b0c"
},
"compiler": "Windows .NET Framework C# compiler; source-bound cached original output, no deterministic-build claim."
},
"nodeVersion": "v24.22.1",
"reaRuntime": {
"version": "6.8.0",
"protocolVersion": "2025-03-26",
"packages": 149,
"files": 8413,
"bytes": 142395402,
"lockSha256": "687fb3fa3089a12f239dd5e87d9fa07df55a87df4935931d495a92600a1b0f6e"
},
"portableFiles": 10927,
"licenseTexts": 135,
"browserRuntime": {
"playwrightVersion": "1.64.1",
"packages": [
{
"name": "playwright",
"version": "1.64.1",
"files": 60
},
{
"name": "playwright-core",
"version": "1.64.1",
"files": 115
}
]
}
}
@@ -0,0 +1,8 @@
{
"success": false,
"checks": [],
"errors": [],
"screenshots": [],
"error": "Error: ENOENT: no such file or directory, open 'D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796\\package.json'\n at Object.openSync (node:fs:621:18)\n at Object.readFileSync (node:fs:487:35)\n at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/scripts/verify-delivery-reliability-ui.mjs:55:54\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)",
"requests": 0
}
@@ -0,0 +1,47 @@
PASS Actual compiled HTTP model loop settles both tools and hands off after exactly two fixture requests without writing files
PASS Review handoff persists across refresh without another model request
node:internal/modules/run_main:107
triggerUncaughtException(
^
locator.selectOption: Timeout 30000ms exceeded.
Call log:
- waiting for getByLabel('当前项目', { exact: true })
- locator resolved to <select aria-label="当前项目">…</select>
- attempting select option action
2 × waiting for element to be visible and enabled
- element is not visible
- retrying select option action
- waiting 20ms
2 × waiting for element to be visible and enabled
- element is not visible
- retrying select option action
- waiting 100ms
58 × waiting for element to be visible and enabled
- element is not visible
- retrying select option action
- waiting 500ms
at choose (D:\Ai-project\REA逆向\Agent-Workbench\scripts\verify-delivery-reliability-ui.mjs:67:20)
at async file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/scripts/verify-delivery-reliability-ui.mjs:86:60 {
log: [
" - waiting for getByLabel('当前项目', { exact: true })",
' - locator resolved to <select aria-label="当前项目">…</select>',
' - attempting select option action',
' 2 × waiting for element to be visible and enabled',
' - element is not visible',
' - retrying select option action',
' - waiting 20ms',
' 2 × waiting for element to be visible and enabled',
' - element is not visible',
' - retrying select option action',
' - waiting 100ms',
' 58 × waiting for element to be visible and enabled',
' - element is not visible',
' - retrying select option action',
' - waiting 500ms'
],
name: 'TimeoutError'
}
Node.js v24.22.1
Binary file not shown.

After

Width:  |  Height:  |  Size: 146 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 43 KiB

@@ -0,0 +1,14 @@
{
"success": false,
"checks": [
"Actual compiled HTTP model loop settles both tools and hands off after exactly two fixture requests without writing files",
"Review handoff persists across refresh without another model request"
],
"errors": [],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-b\\desktop-review-handoff.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-b\\failure.png"
],
"error": "locator.selectOption: Timeout 30000ms exceeded.\nCall log:\n\u001b[2m - waiting for getByLabel('当前项目', { exact: true })\u001b[22m\n\u001b[2m - locator resolved to <select aria-label=\"当前项目\">…</select>\u001b[22m\n\u001b[2m - attempting select option action\u001b[22m\n\u001b[2m 2 × waiting for element to be visible and enabled\u001b[22m\n\u001b[2m - element is not visible\u001b[22m\n\u001b[2m - retrying select option action\u001b[22m\n\u001b[2m - waiting 20ms\u001b[22m\n\u001b[2m 2 × waiting for element to be visible and enabled\u001b[22m\n\u001b[2m - element is not visible\u001b[22m\n\u001b[2m - retrying select option action\u001b[22m\n\u001b[2m - waiting 100ms\u001b[22m\n\u001b[2m 58 × waiting for element to be visible and enabled\u001b[22m\n\u001b[2m - element is not visible\u001b[22m\n\u001b[2m - retrying select option action\u001b[22m\n\u001b[2m - waiting 500ms\u001b[22m\n\n at choose (D:\\Ai-project\\REA逆向\\Agent-Workbench\\scripts\\verify-delivery-reliability-ui.mjs:67:20)\n at async file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/scripts/verify-delivery-reliability-ui.mjs:86:60",
"requests": 2
}
@@ -0,0 +1,11 @@
PASS Actual compiled HTTP model loop settles both tools and hands off after exactly two fixture requests without writing files
PASS Review handoff persists across refresh without another model request
PASS 390px reviewed whole-batch application waits for explicit continuation
PASS Explicit same-Task continuation runs two actual Node assertions and never replays proposals or sealing
PASS 1440px remaining diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 1440px window diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 1440px legacy diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 390px remaining diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 390px window diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 390px legacy diagnosis renders actual limit, numbers and historical fallback without overflow
{"success":true,"checks":10,"output":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c"}
Binary file not shown.

After

Width:  |  Height:  |  Size: 110 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 111 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 110 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 49 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 146 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 60 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 44 KiB

@@ -0,0 +1,46 @@
{
"success": true,
"version": "1.24.1",
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796",
"checks": [
"Actual compiled HTTP model loop settles both tools and hands off after exactly two fixture requests without writing files",
"Review handoff persists across refresh without another model request",
"390px reviewed whole-batch application waits for explicit continuation",
"Explicit same-Task continuation runs two actual Node assertions and never replays proposals or sealing",
"1440px remaining diagnosis renders actual limit, numbers and historical fallback without overflow",
"1440px window diagnosis renders actual limit, numbers and historical fallback without overflow",
"1440px legacy diagnosis renders actual limit, numbers and historical fallback without overflow",
"390px remaining diagnosis renders actual limit, numbers and historical fallback without overflow",
"390px window diagnosis renders actual limit, numbers and historical fallback without overflow",
"390px legacy diagnosis renders actual limit, numbers and historical fallback without overflow"
],
"errors": [],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c\\desktop-review-handoff.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c\\mobile-batch-review.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c\\mobile-check-approval.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c\\1440-budget-remaining.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c\\1440-budget-window.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c\\1440-budget-legacy.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c\\390-budget-remaining.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c\\390-budget-window.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-c\\390-budget-legacy.png"
],
"fixtureRequests": 5,
"realModelRequests": 0,
"taskId": "fb5919b5-6baf-4fbb-8a24-994d5d72d3f5",
"runs": [
{
"id": "4cc0b7e5-4e1f-4f99-9751-4edc52d6a717",
"status": "needs_review",
"stopReason": "change_set_review"
},
{
"id": "228b618d-04eb-4bc9-8861-866735b631bb",
"status": "completed",
"stopReason": null
}
],
"scope": "Declared local HTTP model fixture with actual engineering tools/checks, persisted review state and seeded diagnostic cases. No real model or user project.",
"browser": "156.0.4314.50"
}
@@ -0,0 +1,11 @@
PASS Actual compiled HTTP model loop settles both tools and hands off after exactly two fixture requests without writing files
PASS Review handoff persists across refresh without another model request
PASS 390px reviewed whole-batch application waits for explicit continuation
PASS Explicit same-Task continuation runs two actual Node assertions and never replays proposals or sealing
PASS 1440px remaining diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 1440px window diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 1440px legacy diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 390px remaining diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 390px window diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 390px legacy diagnosis renders actual limit, numbers and historical fallback without overflow
{"success":true,"checks":10,"output":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\portable-final"}
@@ -0,0 +1,16 @@
node:internal/modules/run_main:107
triggerUncaughtException(
^
Error: ENOENT: no such file or directory, open 'D:\Ai-project\REA逆向\Agent-Workbench\releases\Agent-Workbench-1.24.1-win-x64-20261102235819796\package.json'
at Object.openSync (node:fs:621:18)
at Object.readFileSync (node:fs:487:35)
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/scripts/verify-delivery-reliability-ui.mjs:55:54
at process.processTicksAndRejections (node:internal/process/task_queues:104:5) {
errno: -4058,
code: 'ENOENT',
syscall: 'open',
path: 'D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796\\package.json'
}
Node.js v24.22.1
@@ -0,0 +1,8 @@
{
"success": false,
"checks": [],
"errors": [],
"screenshots": [],
"error": "Error: ENOENT: no such file or directory, open 'D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.24.1-win-x64-20261102235819796\\package.json'\n at Object.openSync (node:fs:621:18)\n at Object.readFileSync (node:fs:487:35)\n at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/scripts/verify-delivery-reliability-ui.mjs:55:54\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)",
"requests": 0
}
@@ -0,0 +1,11 @@
PASS Actual compiled HTTP model loop settles both tools and hands off after exactly two fixture requests without writing files
PASS Review handoff persists across refresh without another model request
PASS 390px reviewed whole-batch application waits for explicit continuation
PASS Explicit same-Task continuation runs two actual Node assertions and never replays proposals or sealing
PASS 1440px remaining diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 1440px window diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 1440px legacy diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 390px remaining diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 390px window diagnosis renders actual limit, numbers and historical fallback without overflow
PASS 390px legacy diagnosis renders actual limit, numbers and historical fallback without overflow
{"success":true,"checks":10,"output":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\efficiency-fixes-g\\ui\\source-b"}
Binary file not shown.

After

Width:  |  Height:  |  Size: 110 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 111 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 110 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 49 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 145 KiB

Some files were not shown because too many files have changed in this diff Show More