docs: record verified 1.5.1 delivery and bounded loop limit

This commit is contained in:
Agent Workbench Dev
2026-10-29 22:09:59 +08:00
parent 6e465a26d4
commit 67e5cbdb3c
15 changed files with 1383 additions and 7 deletions
+5 -1
View File
@@ -6,4 +6,8 @@
完整163/163项行为/API/实际退出/升级回归通过,0失败/跳过/取消,见[完整回归](context-fix-tests-validation.json)。基础10、诊断9、任务7、Git9、索引8、批次11及上下文9共63组界面通过,0页面/请求异常,见[界面总表](context-fix-all-ui-validation.json)。新增暂停用例最初误沿用桌面视口,已显式设置并验证390px后复验;手机查看原因、关闭任务抽屉及显式续接保持原Task。
便携/源码独立验收、保留原进程升级与同一个真实失败Task的续接随后登记。当前正式服务仍为1.5.0,不将待验收结果写为完成。
初始不可变便携2207份/源码372份归档、随附Node/npm实际4项检查、源码离线安装/独立6文件构建比对/163项回归通过;原PID23080保留连接与8项目/10会话升级至1.5.1,证据见[归档](context-fix-archives-validation.json)、[便携](context-fix-release-validation.json)、[源码](context-fix-source-package-validation.json)和[升级](context-fix-upgrade-live-validation.json)。
原失败Task续接后,实际模型完成四份精确补丁及一次整批审查,14项测试和build通过。321秒后因Git预览后的状态查询触发四个新增Run的验收器上限;模型仍paused/step_limit。[原上限证据](context-fix-live-continuation-limit.json)保留。验收器随后只确认既有模型Git预览,工作台完成commit5e3b8539及verified_committed报告,没有新增模型请求;[真实交付记录](context-fix-live-model-validation.json)明确区分工程交付和自主循环收尾。
新增45次已报告响应/453235tokens,Task累计72次/702772tokens;先前服务失败的usage未知,不宣称完整费用或成本下降。下一切片处理Git预览后等待确认的确定性暂停,以及Git隔离工作区。1.5初始失败记录保持,不覆盖为成功。
+6 -2
View File
@@ -6,7 +6,11 @@
新增实际HTTP用例证明下一请求包含刚读取的大工件页,分页推进而不重复工具;重复已覆盖区间的实际循环以no_progress暂停,重新打开后保留原Task/已完成结果,显式续接才请求模型。手机用例检查实际390px宽度、可读原因和续接归属;第一次误用桌面截图的验证器已修正并重跑。
独立发行和同一真实失败Task续接正在执行,后续追加实际结果。1.5.0首轮失败证据保持,尚无同题多次对照的费用收益结论。
初始不可变便携2207份/源码372份清单、CRC/SHA与随附Node/npm实际4项示例检查通过;源码独立离线安装、6份构建文件逐字节一致及163项回归通过。原PID23080保留模型连接及8项目/10会话升级至1.5.1,见[归档](context-fix-archives-validation.json)、[便携](context-fix-release-validation.json)、[源码](context-fix-source-package-validation.json)及[升级](context-fix-upgrade-live-validation.json)。
同一失败Task的工程交付随后完成:配置的gpt-6.1-sol生成四份精确补丁和一个封存批次,原13失败→14通过/build,420行说明、BOM/CRLF/LF及10份保护输入和已有暂存/工作区改动保留。模型已准备Git预览,却继续查询状态,在四个新增Run后触发验收器续接上限(321秒);[上限记录](context-fix-live-continuation-limit.json)原样保留。验收器只确认这份既有模型预览,未新增模型请求,工作台生成commit `5e3b85398e0765f88c4bf9dfe2f103c161d72511` 和verified_committed报告,完整请求/原历史/批次SHA256均核对。见[实测](context-fix-live-model-validation.json)、[实际改动](context-fix-live-model.diff)及[报告](context-fix-model-delivery-report.md)。
模型本身仍paused/step_limit,不能记为自主执行循环完整收尾。续接新增45次已报告响应、输入447249/输出5986/合计453235tokens;Task累计72次/702772tokens。已返回响应unknownRequests=0;此前服务失败未返回usage,完整费用仍未知。尚无同题多次对照的成本收益结论。下一切片补齐Git预览后等待确认的确定性暂停,并继续隔离工作区。
## 1.5.0 · 有界请求与完整历史
@@ -22,7 +26,7 @@ Windows x64、Node24.22.1、Edge156.0.4314.42。构建与158/158项行为/API/
1.5便携2180份/源码343份清单、CRC/SHA与独立便携启动/复用/停止、随附Node/npm的4项实际检查通过。源码ZIP独立离线安装、6份构建文件逐字节一致及158项回归通过,见[归档](context-archives-validation.json)、[便携](context-release-validation.json)和[源码](context-source-package-validation.json)。原PID23080保留模型与7项目/9会话升级,整份会话和执行证据按规范JSON核对;只补缺失contextPlans空默认,见[升级](context-upgrade-live-validation.json)。
真实配置模型的首轮样本失败,不能记为工程交付成功:14项基线测试中13失败,随后反复读取历史索引和相同工件片段,358秒后模型服务超时;无源码提案、未应用文件、未提交Git。27次已报告请求,输入246861/输出2676/合计249537tokens,未知用量0。失败记录与[循环观察](context-live-loop-observation.json)保留;见[失败证据](context-live-model-failure.json)。发现较大的最新工具结果无法进入硬预算,会被整体封存,模型下一轮看不到刚读到的内容;优先修正工具读取预算、当前修复依据保留和无进展检测后再实测。未以字节或合成用量声称成本下降。完整M2的隔离worktree、React/Python工程及M3/M5继续开发。
真实配置模型的首轮样本失败,不能记为工程交付成功:14项基线测试中13失败,随后反复读取历史索引和相同工件片段,358秒后模型服务超时;无源码提案、未应用文件、未提交Git。27次已报告响应,输入246861/输出2676/合计249537tokens;已返回响应unknownRequests=0,服务失败请求未返回usage。失败记录与[循环观察](context-live-loop-observation.json)保留;见[失败证据](context-live-model-failure.json)。发现较大的最新工具结果无法进入硬预算,会被整体封存,模型下一轮看不到刚读到的内容;优先修正工具读取预算、当前修复依据保留和无进展检测后再实测。未以字节或合成用量声称成本下降。完整M2的隔离worktree、React/Python工程及M3/M5继续开发。
## 1.4.0 · 多文件审查与恢复
+24
View File
@@ -0,0 +1,24 @@
{
"success": true,
"version": "1.5.1",
"testedAt": "2026-10-29T13:51:46.237613+00:00",
"archives": [
{
"kind": "portable",
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.5.1-win-x64.zip",
"files": 2207,
"crcPassed": true,
"manifestAndDirectoryMatch": true,
"sha256": "2be1673fd6cb907e2ada21b8b78b3ee0719b48e726857951ba663db0a81fa6cb"
},
{
"kind": "source",
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.5.1-source.zip",
"files": 372,
"crcPassed": true,
"manifestAndDirectoryMatch": true,
"sha256": "9207c936565197f5aa416d3dd71d9cdc65070c8ac71c3cf1e961c2f0866f41c9"
}
],
"extractionRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\source-check-28bef995567e40bcab3ea32bd4657315\\Agent-Workbench-1.5.1-source"
}
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+101
View File
@@ -0,0 +1,101 @@
diff --git a/src/cli.mjs b/src/cli.mjs
index 42aea37..cae5d23 100644
--- a/src/cli.mjs
+++ b/src/cli.mjs
@@ -423,6 +423,16 @@ import { normalizeTasks } from './normalize.mjs';
import { summarize } from './summary.mjs';
import { renderText } from './render.mjs';
try {
- const tasks = normalizeTasks(JSON.parse(fs.readFileSync(process.argv[2], 'utf8')));
- console.log(renderText(summarize(tasks)));
-} catch (error) { console.error(error.message); }
+ const args = process.argv.slice(2);
+ if (args.length < 1 || args.length > 2 || args[0].startsWith('-') ||
+ (args.length === 2 && args[1] !== '--json')) {
+ throw new Error('用法:node src/cli.mjs <JSON文件> [--json]');
+ }
+ const tasks = normalizeTasks(JSON.parse(fs.readFileSync(args[0], 'utf8')));
+ const summary = summarize(tasks);
+ const output = args[1] === '--json' ? JSON.stringify(summary) : renderText(summary);
+ process.stdout.write(output + '\n');
+} catch (error) {
+ console.error(`输入错误:${error.message}`);
+ process.exitCode = 2;
+}
diff --git a/src/normalize.mjs b/src/normalize.mjs
index 5a46e5a..fc0c3f1 100644
--- a/src/normalize.mjs
+++ b/src/normalize.mjs
@@ -419,6 +419,29 @@
// 保留工程说明 419 · src/normalize.mjs · 原文🙂
// 保留工程说明 420 · src/normalize.mjs · 原文🙂
export function normalizeTasks(input) {
- if (!Array.isArray(input)) throw new TypeError('tasks must be an array');
- return input;
+ if (!Array.isArray(input) || input.length > 10000) {
+ throw new TypeError('任务必须是最多10000项的数组');
+ }
+ const ids = new Set();
+ const statuses = new Set(['todo', 'doing', 'done', 'blocked']);
+ return Array.from(input, (task, index) => {
+ if (task === null || typeof task !== 'object' || Array.isArray(task)) {
+ throw new TypeError(`第${index + 1}项必须是对象`);
+ }
+ if (typeof task.id !== 'string' || !task.id.trim() ||
+ typeof task.title !== 'string' || !task.title.trim()) {
+ throw new TypeError(`第${index + 1}项的id和title必须是非空字符串`);
+ }
+ const id = task.id.trim();
+ const title = task.title.trim();
+ if (ids.has(id)) throw new TypeError(`任务id重复:${id}`);
+ if (!statuses.has(task.status)) {
+ throw new TypeError(`第${index + 1}项的status无效`);
+ }
+ if (!Number.isSafeInteger(task.minutes) || task.minutes < 0 || task.minutes > 1000000) {
+ throw new TypeError(`第${index + 1}项的minutes必须是0到1000000之间的安全整数`);
+ }
+ ids.add(id);
+ return { id, title, status: task.status, minutes: task.minutes };
+ });
}
diff --git a/src/render.mjs b/src/render.mjs
index 5cacc86..2752ba6 100644
--- a/src/render.mjs
+++ b/src/render.mjs
@@ -419,5 +419,10 @@
// 保留工程说明 419 · src/render.mjs · 原文🙂
// 保留工程说明 420 · src/render.mjs · 原文🙂
export function renderText(summary) {
- return `Done: ${summary.counts.done}/${summary.total}`;
+ const { total, counts, completedPercent, remainingMinutes } = summary;
+ return [
+ `交付进度:${counts.done}/${total}(${completedPercent}%)`,
+ `待办 ${counts.todo} · 进行中 ${counts.doing} · 已完成 ${counts.done} · 阻塞 ${counts.blocked}`,
+ `剩余预计:${remainingMinutes} 分钟`
+ ].join('\n');
}
diff --git a/src/summary.mjs b/src/summary.mjs
index 6679d91..57c7709 100644
--- a/src/summary.mjs
+++ b/src/summary.mjs
@@ -419,7 +419,17 @@
// 保留工程说明 419 · src/summary.mjs · 原文🙂
// 保留工程说明 420 · src/summary.mjs · 原文🙂
export function summarize(tasks) {
- const done = tasks.filter(task => task.status === 'done').length;
- return { total: tasks.length, counts: { done }, completedPercent: tasks.length ? 100 : 0,
- remainingMinutes: tasks.reduce((sum, task) => sum + task.minutes, 0) };
+ const counts = { todo: 0, doing: 0, done: 0, blocked: 0 };
+ let remainingMinutes = 0;
+ for (const task of tasks) {
+ counts[task.status] += 1;
+ if (task.status !== 'done') remainingMinutes += task.minutes;
+ }
+ const total = tasks.length;
+ return {
+ total,
+ counts,
+ completedPercent: total === 0 ? 0 : Math.round(counts.done / total * 100),
+ remainingMinutes
+ };
}
File diff suppressed because one or more lines are too long
+151
View File
@@ -0,0 +1,151 @@
# 项目交付报告
**检查通过并已提交**
生成时间:2026-10-29T14:06:59.870Z
项目:多文件变更集交付工程
项目目录:D:\Ai-project\REA逆向\Agent-Workbench\.qa\live-batch-08ad7d9d-01cf-4c85-9467-6cdf94b19fcf\多文件变更集交付工程
Task:02db405c-edb4-4213-bb30-af37a1acb540
## 任务与范围
完成当前 Delivery Report 工程,严格实现 README.md 的七项要求。先用 inspect_project 识别工程,再用 plan_checks 选择 test/build,并用 run_checks 实际运行封存输入,取得失败的测试和日志。依据实际失败读取有关文件,使用 read_artifact 进一步核对失败日志。先用 index_project 建立工程索引,再用 query_code 的 symbols/imports 结果定位源码,特别是CLI入口的实际导入行。每个源码模块前420行都是须原字节保留的说明;用 read_file 指定start_line至少421的必要行范围,取得最新SHA256。已有源码只能用 propose_patch 及该SHA256、唯一old_text锚点精确修改;保留BOM及原LF/CRLF,不使用 propose_file,不读整个说明块。允许修改的源码仅为 src/normalize.mjs、src/summary.mjs、src/render.mjs、src/cli.mjs。测试、fixtures、构建脚本、package.json、README 和 OWNER 文件必须保留。四模块都需修复,不能修改验收来通过。四个源码提案全部准备后,必须用 prepare_change_set 一次封存这四份change_id,等待整批审查。第一次不要只封存部分文件;到工具轮次上限会继续原任务,已保存提案无需重做。本工程没有第三方依赖,不用安装。不要使用 run_command、不要自己提交Git;本轮终端仅通过已识别的npm检查计划运行。提案等待审查应用,随后继续同一目标并实际重新运行 test/build,依据日志修复直至通过。检查通过后用 plan_delivery 准备本Task的四文件本地Git预览,等待用户独立确认;最后用中文报告实际测试数量、构建结果和改动。
源码指纹:9df20cf86a268e99402d42f5159b4fe1e6a262fd3688031bc20ffcc93fb64db9
当前Git HEAD:5e3b85398e0765f88c4bf9dfe2f103c161d72511
分支:main
源码和检查证据不代替业务需求验收。
## 改动
| 文件 | 状态 | SHA256 |
| --- | --- | --- |
| src/normalize.mjs | applied | 5b0a6e0089b711c505b68822c96622a6f64b711b3ef6fe521553cdc67c442eda |
| src/summary.mjs | applied | 040936f478357a655645117abba2bc330c6ac67b52b25334cecb444f71044dc6 |
| src/render.mjs | applied | 2882b485d686e1cbdaf8de2834592f9a84921ed63340dbae42916145df907ca7 |
| src/cli.mjs | applied | 6fe9a64f774a91d0ea7765d03f18ca4d074ff2750d0405d6f97e6f4c52da6b43 |
## 多文件变更集
| 批次 | 实际状态 | 快照 | 审查指纹 |
| --- | --- | --- | --- |
| c7eb8c17-ea13-4354-b934-4ab189b0dd21 | completed | SHA256校验通过 | 18773b7775cfb1346ba0e9562b2acbd1abdb4c7e585a5d231bdf6ed92e5f8d82 |
整批文件的实际建议字节已核对,全部应用完成。
## 实际检查
| Job / 命令 | 状态 | 退出码 | 实际测试 | 日志SHA256 |
| --- | --- | --- | --- | --- |
| 61a6c909 / npm run test | 源码已变化 / failed | 1 | 1/14 | fa0414712b6fa94f6a820e9c861b3f2f42cade5e596ec811928e8e9d94e90d59 |
| 61a6c909 / npm run build | 源码已变化 / passed | 0 | 不适用或未知 | 38566d6bd1635a690931ce24b85aa15a188dc2844ff8d886289985039a9f9be5 |
| 18d1b3d9 / npm run test | passed | 0 | 14/14 | a6345b26fe1c38cf696d075f398569e3f703ed5290af6cb719cc2c5b734497eb |
| 18d1b3d9 / npm run build | passed | 0 | 不适用或未知 | 38566d6bd1635a690931ce24b85aa15a188dc2844ff8d886289985039a9f9be5 |
## Git交付
- completed · 5e3b85398e0765f88c4bf9dfe2f103c161d72511 · src/cli.mjs, src/normalize.mjs, src/render.mjs, src/summary.mjs
已生成并核对本地提交;任务文件、实际检查和其他工作区/暂存改动均已保留。
## 模型与用量
| Run | 模型 | 状态 | 已报告tokens |
| --- | --- | --- | --- |
| d5ac17d0-0c9e-47a7-8818-41206d564125 | gpt-6.1-sol | paused | 98878 |
| 0cae05e5-cd63-47fa-929a-87e188fbe853 | gpt-6.1-sol | paused | 120063 |
| 8fc2fead-8c6a-4f52-ae3b-a7ee141cc72e | gpt-6.1-sol | failed | 30596 |
| 4e71aef5-4483-4f3b-8839-12d796311d00 | gpt-6.1-sol | paused | 121901 |
| 9d2a8a57-8f01-4b61-a86b-1bd63e93b923 | gpt-6.1-sol | paused | 118495 |
| d0a3dc19-22c4-41c0-8868-b416e7004aa3 | gpt-6.1-sol | needs_review | 92418 |
| 4d7f133a-3e60-4a47-ab34-9575a5fbfc1c | gpt-6.1-sol | paused | 120421 |
累计已报告:702772 tokens;未报告请求:0。费用:未知。
## 请求上下文
| 请求 | 状态 | 输入估算 | 已报告输入 | 省略组 | 正文SHA256校验 |
| --- | --- | --- | --- | --- | --- |
| 7a6dc1e8-f70d-4070-99f3-abb03d367dee | completed | 5314 | 3271 | 0 | a509e6b43467af4fcda259a4d96bd75679a698ea5b7c8fb4e8cf8c8f6e0e59a1 |
| b8e51417-a218-4a70-890e-5dfa2db77a10 | completed | 6070 | 3864 | 0 | f8e555a449acb78bc2bcbed543c3805c4662219eed7c4b0270b4096cc00ae261 |
| eb4c99b0-8e74-4aa9-8681-8f02d54ae62f | completed | 7150 | 4912 | 0 | 34fbf501119f09a9396a62b0c4c30f6478afaf8bab02e3b037d52cb059f4fab7 |
| 367e864e-c091-4d8f-ac0d-9f6dc63bb601 | completed | 10713 | 8530 | 0 | 7d25d0b9793d18e33939f8072f42d65cf594c546a7d678c04a808818f310710e |
| fe343a4a-63be-49c2-846c-797f02e334bb | completed | 11815 | 9699 | 1 | edefaa984265d8d904be264107a62d014e95d30a49a2e61404f8ffb9eb21b6c8 |
| 6407e079-2d7d-462e-9119-9903193311d9 | completed | 12109 | 9331 | 3 | a2cf0a31503bf1f11f838224a889e5e45e57b7eaef5950d8e2e79543f23746fd |
| 37d63050-5691-4332-8fa8-074d1e6e96af | completed | 11939 | 9389 | 5 | 348ac82ad1fae731f9f5ce9780978b55c41c299ceed681f594e7fd1ea8133843 |
| 4dcac478-36c3-4965-943d-3001104e5f59 | completed | 12282 | 9873 | 6 | 6ae0b5c13ce3e7d000c6076c3bf342be27f5948301932e707a17b753b24a9ae5 |
| f42aa8ae-037e-46c2-b26c-9be54781d252 | completed | 12022 | 9733 | 7 | 008cb5e02dcdeaa2386b4a58faf5fd129893873e26abd9166ba895d5ba508bb9 |
| c9341cc3-d63a-46d5-a685-830a29cfc7fa | completed | 12054 | 9615 | 7 | ea5b727c182ca39d4843c9e47dba0278d25b62763fd5ca397b68dbca6e9a17a4 |
| acf58075-ad75-49c7-b4d5-6c43af17b562 | completed | 11940 | 9957 | 7 | 57c90136826a5ca33404598eb2906f1b7cbe9956a5691bcd453b25f6052133ff |
| 1bcef67d-3c86-4b1b-8404-22e1ab4ce34c | completed | 11909 | 9127 | 9 | cec357e94df741b09168a74bd153f8b7cf7a953782f8e2098fc59474669b35d7 |
| 1f918fd5-79f0-40fe-927d-3e40e4655112 | completed | 12092 | 9335 | 10 | eab80fd74b5125e2e260cbe705566da242fd6f84e271b8ea3cc4d70f719d88c0 |
| 6fd13f35-b666-4f17-9188-fd0295e972ae | completed | 11212 | 9132 | 9 | 87600b70390a3d31619fc264ca5875643ef467205e43c59d0815e0e7f6bfe2ea |
| 15dca146-0efa-4ee1-af9c-f11b7ab7a142 | completed | 12256 | 10157 | 9 | e7dddee85b4391df9a80ec56a0cf4e0cafd635cafbdf78f97eeade2d9b3aaf4e |
| 86b8d472-a6cf-4044-b5ac-7cf7376b2fea | completed | 11876 | 9912 | 11 | 5ffe6c50cafa926878f2d7ec0272ce13c9addf0b985e4bdf017fdcb9510a3e69 |
| 400ea05b-4d15-4bd4-bed1-9a19bc3f61f2 | completed | 11876 | 9908 | 12 | 9fa3333e8f667bee106527478ad7f9fb396a7e9b72af75b47bbb13e1761aa647 |
| 0e978b24-98ca-4edb-b97c-16cf17b64b63 | completed | 12173 | 10056 | 12 | 53d2de485dee09b6f426b81ab34e8a185ac7bede8e6a1a17e2c7ba17a0777e19 |
| fb237e9d-2838-478c-ab1a-3cc9777ade43 | completed | 12173 | 10097 | 13 | 12cac467ab7636bb8a9411597f28ddf14d40c81c639e12fe11fee40e742c849e |
| 8e5dd338-fcbc-4357-8832-aa3d37451a6e | completed | 12172 | 10135 | 14 | 65581d3cf99603ea50cefc76c66c8539b2818a66ddfd21667f9dc7ae381d53da |
| 596607e7-9cc6-4d99-990f-0dd098ee004e | completed | 12172 | 10128 | 15 | 2f0038850bed86e9b319f7965666362d9014386241366c8eb801fddbd93655d0 |
| 44d5dd34-8583-4659-bf00-3dc6c088cbfa | completed | 12172 | 10113 | 16 | 6db2d1af1f1bb69f0c08bc2f2b39b73099cc950005ed15d01dad382be8e90e05 |
| 6e3badf0-d5b9-4606-8bcb-f6b93fcb21cb | completed | 12176 | 10112 | 17 | 550a9505a88a6893f8f1f9675509951ed4e4b9c0f7216ed70c12ce97aa2b839d |
| acb42dc1-d01d-472e-9212-43031e5bbb01 | completed | 12180 | 10107 | 18 | 9b40a9b885cc8b55eba3b50a30b9b8301dc0499b8879e454f40da56525dcbd41 |
| 7668f171-e58a-444b-9893-263c1ca2b434 | completed | 12184 | 10122 | 19 | 754785bc308d5d4a8366aee7a1b589e07f024775cca914622d65517c3fa8d4c1 |
| c6effdaf-694c-4d95-a971-d3a9841421a2 | completed | 12188 | 10126 | 20 | 3078f74fd17a63b7ec13af5029d39d42cd53f5ee8b31b7e8af04ebf52f052cdd |
| 08fa0937-a990-411d-95cd-d68a4dadcac0 | completed | 12184 | 10120 | 21 | ba27710cdc2ea7102b1d859540a7576d0bc5cbf4d88aad125aeaf4ef582f5eed |
| 5529c75a-f11e-44d3-9f6e-a4dafac6698d | failed | 12196 | 未返回 | 22 | 5ce6a905f1b23e94a94a1b4ed59272793f4bec2ebe0850da9f17363d03193bb5 |
| d5015b52-e375-4f17-b2ef-f9d4dbfed1e1 | completed | 12151 | 10303 | 25 | 7f6a8a36e63b093b2ea1099044854fce935affa7c9de10e10a5b0b0642f3a182 |
| bf956ce8-d0f1-444d-a153-22dae3aa1796 | completed | 12155 | 9747 | 27 | e13ed7c64fba6cbc69c819341d81cba7fc537b70c5ad6b47390b5e885988e5f5 |
| d5185543-0997-4d71-9594-1b951c82cb73 | completed | 12345 | 10027 | 28 | 21394284c3df5837bc21e1e618b9d9a173cbaa67f629d82d51a0796c77389e3c |
| 80f89cde-94a0-45af-9a2c-d7eec3ffe964 | completed | 12183 | 10409 | 29 | 7c781eecedaef69a99391e016a4bd7da54e7fa9dd313626d719d977782e022ed |
| 3a118bd4-cb53-48b3-92be-69dbe405be12 | completed | 12162 | 9911 | 30 | 6e2edbdd6a1d9d50286fb4e8c02ff970d44b3e21b819c8a1f55ab4a127b5f30d |
| 4314142a-24b8-4cb6-9eb9-3432db78af50 | completed | 12121 | 10346 | 31 | 5ef17fc7ec852b28b807f8c7ed3aed4f31329c32e01eef22f411fa2d4abe9f48 |
| 5a6e0c31-0b02-4b0d-a412-f38292a64908 | completed | 11878 | 9748 | 33 | 7710ee821eb4c01ba72da05c59882892e513dd5a269a0dffb297c8f0b60d43b4 |
| be8cce8e-2a5d-4017-b03e-51bef4dd88a9 | completed | 12067 | 10093 | 33 | a2dbaaebc168d16745d70418c3272d60b3a08b35b90b2535220fa9d0847be097 |
| 45b24618-1c52-489b-a1d7-1e707b560bdd | completed | 12313 | 10277 | 33 | efc6ced014f5d9ad21d206cbce6749d497ad244be351f4c7188d614ca8ba4c0f |
| 0eac7184-91fc-481a-801c-4044c18e6d38 | completed | 12226 | 10031 | 33 | 83d3d1ed6a6163fe44f58b2dbc9e19822972dcb0891c70fb275d81f5e27c413c |
| df3ce19e-57e4-423f-b43f-0d219acad04f | completed | 12248 | 9932 | 33 | 6cb0ceecbe291efee1cb03252b005eb953c5d5b0eea2a508fc9919be10fb5ead |
| 82304583-7941-48ce-8a16-0904f211eb74 | completed | 12170 | 9727 | 33 | 0cb66b45187ad5c49f43f2aabe9dd0d17cc0b9394c2933d45fb6fbb996942efa |
| 52be9775-ad3a-42f9-855a-bc7bd54f04a8 | completed | 12246 | 9781 | 35 | a3f1182482171ba213c2b4debafd3cce2892b187d797e37f9c9c455478cc3322 |
| a2398854-eb20-4212-8074-7b8fd3b7f636 | completed | 11894 | 9219 | 35 | ec7eeeb0756e8dc69e5230bf4877974badf12f70064626926c2606b623168e29 |
| 6af6b7cf-e1f3-40d8-a069-6ed49dea3096 | completed | 12173 | 9619 | 36 | dc9c5a2f228f986429dd8ac9b248e5268d9469e9113e081a8e6c5687d2ba9d27 |
| 83936227-c52e-4178-ae60-66965a9cf1dd | completed | 12200 | 9740 | 37 | 826bf2ca2184d49c47daa6d79f57175c0cec51e21dd574df68c1442b05c9ffc3 |
| 6f71937c-ef9d-49f1-98dc-c24e34bc9865 | completed | 12291 | 10015 | 38 | 20d3fed9db6fc8fdd89f5cbebca825506004c3ab1b4c7d829a047fdaab98c3d5 |
| 90284201-55e8-4dd2-a14d-2e7cffabc0a3 | completed | 12255 | 9956 | 39 | aca2d47dc580a63fa2aaed2026612c24b23c90257b5bc0f366e0dfeb090fa607 |
| 67d37f95-d248-4cef-aeaf-be94d82520b1 | completed | 11983 | 9656 | 40 | 3037ba453dfbacc63ddc52f0ceaa9740ef7125c043d5bb3bef879b344593015e |
| 68bd3063-7598-42c1-a1a7-279f33eb1727 | completed | 12281 | 10053 | 43 | c3ac6a0cc8fbaa70b061c894bd1053e27de0eb93132999c6dddb13c6a08bc1df |
| fada4b09-bd71-4018-aeab-17b2cc451936 | completed | 12110 | 9658 | 43 | 34ee43757d6f97107adcc531bff10c35320208fc04cf8e8a13772dae08f93038 |
| 5005c743-d997-4348-b169-953a3c1f83ba | completed | 12260 | 9813 | 45 | ff5c9c2e3ea0ad56c548c0cac83908e79b05f1dba050e3715fd6ac577c49556e |
| 9b5cd5b5-14e2-428f-bd1d-74ce282cfee0 | completed | 12322 | 9737 | 44 | 7471fe4ae21515b5a4eaf5d09bd143d67417113064f9985b1173191745f476ef |
| 443930b4-72f4-4260-ab2d-af91cf3dc672 | completed | 12209 | 9626 | 49 | 7efafcb7fb46ddc0dcff5be92ad07f0c0a24eee5301636294dace4531e501a1b |
| fa730211-c269-4ac8-8ae5-ad7163552243 | completed | 12166 | 9735 | 49 | 4629a02b83a993519c2a4a0c6c7fe7f4a77232d82ee2a84cca90f63462490eae |
| 82e0b501-5a1c-40ea-bf39-9f89a022e68d | completed | 12321 | 9915 | 50 | 11074df8a11e4bf3af04725729b1d137afb80899567a6df50c458b47f7d48bd5 |
| 49ed07e1-16cc-4e32-8525-be974f5d18c9 | completed | 12167 | 9769 | 52 | 88c3ffa475ae3cacd60379e4ebbe4ea93d6c319342892e67e4a7f56fa57fe22e |
| a2bd507b-0e98-4c60-a4be-eb36d22dbc37 | completed | 12144 | 9933 | 53 | c34e3858d6d3819349f018988e881bc7d915f834ddcd759749ca7c40246a941b |
| c0e21541-929f-405f-ad73-6e3685cbd9f3 | completed | 12260 | 10041 | 54 | 2e1ffcbc54ee5e7805b7c739a0ba2b5275a49faea226a257ebc1b46aa3642f02 |
| f201eb39-f216-41ff-91ff-ca77457df7c4 | completed | 12224 | 10109 | 55 | c5ba06bea97c7d837b74a10560a6ad69ef1075abec82a0a28ff9f8f76b7db805 |
| 615cc351-0ffe-4c79-b973-0a5232e07cda | completed | 12343 | 9979 | 54 | 05d5188a31c5562b5832ab89377352de0b539eba93a77c901874feb12dae090d |
| b3b280d6-3247-4164-b396-351554bc428b | completed | 12279 | 10231 | 58 | 246c52e1a48e5f6905e68b908de1d28ce28985c966c41f307e35719ab549b907 |
| 95f44aea-02ac-4c40-aef4-75f79a4b14f1 | completed | 12183 | 10422 | 57 | c685f0a32b68ea2d88d4c7883195d5389da53e867ac3a625ffabc681d6d4922f |
| 8cf5e5d5-f46b-443e-8963-70dfc79ba203 | completed | 12145 | 9916 | 58 | 96023600b946ba0fbc76c148401fb928edb1b0ca03829aaa315cf1d061201a67 |
| e4ba6331-1540-4766-879c-6b0fe33e1a60 | completed | 12335 | 10055 | 59 | 533e5f9b7a44146f2d845b618cc105535700935bdc2b9d90a623aa11733be62f |
| b34af643-be5b-4f74-9a68-7e3c339cb52f | completed | 12315 | 10227 | 60 | 07b8e441e7af88a3f98a13d70ef5d69b411693981508226af5397a6d063c456f |
| ec100139-a967-4b74-86ac-824b569404f6 | completed | 12224 | 9962 | 61 | 9315bc1f2dd8ee07ebbe6b145e41d9306bf555d6b04d487f05f2029aa4b73857 |
| 2dcdd24f-fc67-4af2-ac8e-1f4b414b0e68 | completed | 12301 | 9951 | 62 | c44372211239d4daf007b6bd80a75762ff4c0d72c21f658dafa35a3930193e62 |
| 481e4b07-2d53-4d6e-b8cd-e8d7fcbc1496 | completed | 12227 | 10026 | 63 | 237e8d0ac5c66e98b4942ca43d12235e8629094c311371efd680afcf1634b669 |
| 378d7c3b-e2c8-4e41-bdb9-d629e94c3ac6 | completed | 12194 | 9981 | 64 | 1ac54c822c8bbbf6c6f03a2e8ece948f2f3223f5c716a26513fc98d4a5f967e2 |
| f1846eb4-2276-4ef0-84b6-6e7b2948fb11 | completed | 12204 | 9936 | 64 | 2cb46c44dcf5aa4de72d368e09f197bf8d303aec35a3b36b52261ae4fa45b5f6 |
| 63d65b97-788a-4efa-a925-8a7b57af1de4 | completed | 12315 | 9981 | 65 | fd9f58e27d801d386123433fee6617bb79e02a235a0ac177979d21ad501c89f0 |
| f3ff1704-d8f8-4bf0-a9ae-55ed8cc4ed45 | completed | 12331 | 9937 | 64 | b0e6204907f0f6d7784218776abcdbdf2e2895c118178bc06889829f94ae44c3 |
| e88adb0d-c8b7-4683-abca-422c8764a309 | completed | 12222 | 9853 | 67 | d4e3cf516d2285671e5daf6bad158715b45b941abaef16f7598f71f355fe5401 |
| 84d50319-f17a-40f4-a9f0-8f91bdc8574a | completed | 12305 | 9866 | 68 | 5019abdc0aac657a0ae55e0dbf9983a0dfa345aa3c641c49590f750bb4e61baa |
## 尚待确认
- 本切片验证已选工程检查和提交范围;业务需求验收另行记录。
- 提交为本地普通提交,不执行仓库hooks和GPG签名。
- 请求输入为本地UTF-8估算;服务实际分词和用量另行记录。
- 未配置模型单价,费用未知。
+34
View File
@@ -0,0 +1,34 @@
{
"success": true,
"date": "2026-10-29T13:51:53.162Z",
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.5.1-win-x64",
"version": "1.5.1",
"nodeVersion": "v24.22.1",
"verifiedFiles": 2207,
"url": "http://127.0.0.1:57028",
"reusedPid": 17208,
"checks": {
"jobId": "bcbef13a-10e7-4cf3-a9cf-1079407cb2c0",
"status": "passed",
"tests": {
"total": 4,
"passed": 4,
"failed": 0,
"cancelled": 0,
"skipped": 0
}
},
"steps": [
"manifest hashes",
"bundled Node launch",
"same-service reuse",
"packaged example and static page",
"explicit command consent",
"actual bundled Node version",
"actual bundled npm check without system Node/npm",
"check log artifact",
"report availability",
"graceful stop"
],
"realModel": false
}
@@ -0,0 +1,17 @@
{
"success": true,
"version": "1.5.1",
"testedAt": "2026-10-29T13:57:33.214Z",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\source-check-28bef995567e40bcab3ea32bd4657315\\Agent-Workbench-1.5.1-source",
"offlineInstall": true,
"buildMatchedFiles": 6,
"tests": {
"tests": 163,
"pass": 163,
"fail": 0,
"cancelled": 0,
"skipped": 0,
"todo": 0
},
"credentialsHandling": "Only build/runtime environment paths are inherited; no model configuration or credentials are used."
}
@@ -0,0 +1,82 @@
{
"success": true,
"testedAt": "2026-10-29T13:58:15.305Z",
"version": "1.5.1",
"pid": 23080,
"hasKey": true,
"projects": 8,
"sessions": 17,
"appDirectory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.5.1-win-x64",
"verified": true,
"connectionPreserved": true,
"url": "http://127.0.0.1:4318",
"previousVersion": "1.5.0",
"model": "gpt-6.1-sol",
"storage": {
"engine": "sqlite",
"schemaVersion": 1,
"eventCursor": 1421,
"pendingPublications": 10,
"migratedFromJson": true,
"recovery": "verify-unknown-results",
"compatibilityExport": "explicit-json"
},
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.5.1-win-x64",
"dataRoot": "C:\\Users\\wangy\\AppData\\Local\\AgentWorkbench",
"projectsPreserved": true,
"preservedSessionSnapshots": [
{
"id": "0f3ace68-4988-4370-bf22-aac01f33a8ab",
"session": "113b54ab40fddd3b4f3cc1289729c60c2b99360e88d76ceb217ea7c04b3c9274",
"execution": "66954d19a46c1aae6520c769e4228f611f5e7ee8e549fc476ca54d2b333e3878"
},
{
"id": "fc87c3f6-a108-4095-ae41-4ef56bc789c3",
"session": "49dbf09c02b74d867df47a65185c60f5fac173ed114ccd6e7adf261a93e71b1f",
"execution": "1ec359c3f58410d57067bdc6ef50d7a22db55cdda828a3921aab05e7de7cac55"
},
{
"id": "b045829c-377b-4f69-ad0b-513fe797b421",
"session": "44040c046fd23053228a203745112b277acfcb191ae5a5ce957dd7090c983a2f",
"execution": "a899820dcc7dca7d5cc60b423dccfbd8babb2f9b063a80ee66d474bf04385c76"
},
{
"id": "1cf22a27-ac13-4c95-a878-9b4356ccb5b3",
"session": "519eea1e103fd081279a82d4b4e72d17857a18b027eb0b156972855c90349552",
"execution": "7836eae3c176d1ba0f7a91de8b3f40866cbf4d1b0829ab4d4d95078e039da059"
},
{
"id": "dccf608f-44c9-4031-a58c-5ba87fe3b3f8",
"session": "00018e8b18ba8311b139cce9ab5c5414c26b8893b3234efd8f54804711978ed1",
"execution": "f3ce56ae12f800e8520e4372abec0c9869a99cbd7e144c03e131ba716e1f27a6"
},
{
"id": "c32c9c87-8239-4606-a4c0-783529603bc7",
"session": "5a9d028a1054136e85c2037d4151709c3d835d9edb2e67476e3dd9becb493e83",
"execution": "87a03904ce3abf28187b2fdaad53dd63b0ba1a53435916da1418e23b588184f0"
},
{
"id": "e8846c6e-1ba2-497e-b0db-ca5778181eb0",
"session": "81477eeefcdf965fdd9091e05670df99e3817f7cbc6ab56605c215262ec3cd5c",
"execution": "249c6d1f8b9b2b7da855fff7549518511096309e66666dacbf9ef0420a19157f"
},
{
"id": "72d3d22f-14d9-4bca-bb6a-ab686bc96b26",
"session": "1ba568d537e40edf8400dbb0c6bdce5a13ed4e71a3634c38a563b468b8a309aa",
"execution": "e843f337e353bf097d316b204abcf9b4992a2d6c050f7dc691978834dda493d1"
},
{
"id": "4abc4201-549e-46e0-947c-3d3f5b53ffae",
"session": "7f76d7f6ea57b3b842b8289b0fbba5d196df03df7cdc8ae0c6594816f103ae4d",
"execution": "f2b46d2d2e4fd27e4694cfe47e76fa2ebfabc525c2b4bca790b91977282da423"
},
{
"id": "569c9457-d399-46e6-b53e-4b1fdbb02109",
"session": "11614934261d3c1c7b2134d9ffaf70bcca207876b2e8dff76e596afe48c1be3c",
"execution": "7b72ea1134b4d16451af45f22b568f54a8c1872a5981a90fdf8218851338f44c"
}
],
"inspectorClosed": true,
"comparison": "Canonical JSON object order; the only added compatibility default is missing execution.contextPlans = [].",
"credentialsHandling": "The original provider object retained the key in memory. Only public masked connection metadata was read; no key was read, copied, printed or saved."
}
+3 -3
View File
@@ -1,14 +1,14 @@
{
"ready": true,
"url": "http://127.0.0.1:4318",
"version": "1.5.0",
"version": "1.5.1",
"mode": "compatible",
"model": "gpt-6.1-sol",
"hasKey": true,
"pid": 23080,
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.5.0-win-x64",
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.5.1-win-x64",
"originalAppRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-0.1.0-win-x64",
"dataRoot": "C:\\Users\\wangy\\AppData\\Local\\AgentWorkbench",
"upgradedAt": "2026-10-29T13:17:26.367Z",
"upgradedAt": "2026-10-29T13:58:15.305Z",
"storage": "sqlite"
}
+3
View File
@@ -202,3 +202,6 @@ Claude Code 报告已验证工具输入校验、权限决定、队列并发屏
- 冻结1.5.1完整163项回归与63组UI全部通过。目视发现新增mobile-read-pause截图实际为1440px:该用例沿用了迟到错误测试的桌面视口,标签不能作为手机证据。已显式切到390px、验证宽度/溢出,手机查看暂停原因后关闭任务抽屉再续接,重新独立跑9组上下文UI。
- 390px最终暂停截图已目视确认原因、运行下拉和关闭控件清晰;完整63组UI0页面/请求异常。一个只读路径误写tests/git-delivery.test.mjs,查询失败且无改动;rg实际定位为tests/delivery.test.mjs和delivery-recovery.test.mjs。
- 1.5.1真实读取已经能分页推进并产生全部四份补丁和实际14项检查通过;新的收尾缺口是plan_delivery只返回awaiting_review,Runtime仍继续请求模型,模型反复inspect_session/工件直到step_limit。必须在持久保存/工具完整配对后以Git审查边界停止请求,并用已封存预览完成确认;失败的验收器上限不掩盖,工程完成与自主循环完成分别记录。
- 本次只读诊断首次未携带bootstrap控制token而HTTP403,补齐后读取成功,没有模型Key读取。一次VALIDATION长行补丁只用了部分行而被拒绝,无写入;改为精确段落补丁与字面短语替换。
+4
View File
@@ -151,3 +151,7 @@
- 1.5.1工件预算/Unicode分页、直接代码优先保留及Task已读范围/no_progress已实现;4项真实HTTP/重复暂停/重新打开/显式续接专项与1项优先选择验证通过。完整163项回归与63组UI进行中,现有独立UI基础10/诊断9已通过。正式1.5.0保持,等待相关检查后创建新包并续接原失败Task。
- 1.5.1冻结163/163完整回归和63组UI通过。390px新增暂停用例已显式复验并目视核对,查看原因/关闭抽屉/续接原Task可用;1.5.0历史证据保持。已准备只复用原失败工程和标准审核/检查/Git循环的续接验收器,不创建新Task、不重跑基线、不修改四源码之外文件;等待独立包验收与升级后执行。
- 接续“继续全量推进”:1.5.1初始不可变便携2207文件/源码372文件归档及独立便携检查通过,证据另存context-fix前缀;源码离线安装、独立6文件构建比对已通过,163项独立回归仍在运行。已生成仅适用1.5.0→1.5.1的原PID升级器,正式服务保持1.5.0,未发出新的实际模型请求。
- 独立源码163/163通过,原PID23080/连接/8项目10会话升级1.5.1成功。续接原失败Task后实际四补丁/一批次、14项检查/build通过;321秒因既有Git预览后继续查询而达四新增Run的验收器上限,保留上限失败记录。验收器只确认既有模型预览,无新增请求,Workbench commit5e3b8539/报告/SHA通过;模型仍paused/step_limit,不冒充自主完整收尾。新增45响应/453235已报告tokens,累计72/702772,服务失败usage未知。准备最终不可变1.5.1包,之后实施Git等待审查边界与隔离工作区。
+1 -1
View File
@@ -175,7 +175,7 @@
目标:先解决实际长Task的上下文重复投影和预算估算遗漏,再建立有明确归属、可恢复的Git工作区;保持全量历史、实际结果和同Task续接,不能截断工具协议或自动重放。桌面端/手机配对及外部引擎按后续路线继续。
1. [complete] 完整请求计划包含系统、项目/Task状态、工具定义和响应余量;固定任务目标,按完整assistant/tool组选择近期历史,将旧组封存到SHA256可核验工件,明确估算与服务实际用量区别。
2. [in_progress] 单长Task、多语言/大结果、完整协议、续接/实际退出及归属验证通过,158项完整回归和62组桌面/手机界面通过;请求/原历史/深度校验报告已接入。继续独立不可变1.5包、原PID升级和真实配置模型验证。
2. [complete] 单长Task、多语言/大结果、完整协议、续接/实际退出及归属验证通过,158项完整回归和62组桌面/手机界面通过;独立不可变1.5包、原PID升级完成。真实模型首轮失败证据已保留,进入下方1.5.1修复与同Task续接,未将失败算成工程交付通过。
3. [pending] 封存已提交HEAD、独立命名分支/worktree、持久准备/核对记录和稳定项目身份;保留原HEAD/index/用户改动,不隐式执行hooks或内容过滤器。
4. [pending] 继续React/TypeScript与Python工程检查,以及证据绑定的REA/Codex/DeepSeek适配和有界Purge实验;只将实测通过的切片标已实现。