hy
bb3a374b61
Advance human live tests and simplify report evidence
2026-03-18 16:26:54 +08:00
hy
b3fcd23fa0
Expand human test coverage and align AI workbench docs
2026-03-18 14:30:08 +08:00
hy
6e088097e9
Reset Stage 1 tools report and drop Stage 2
2026-03-18 14:00:43 +08:00
hy
6922b3cfe6
Reorganize tool tests into layered directories
2026-03-18 13:38:45 +08:00
hy
8a9c2bc917
Reorganize human tests and add live coverage baselines
2026-03-18 13:07:40 +08:00
hy
4f1f42e462
Add Stage 2 human backend tests and reporting updates
2026-03-18 11:51:27 +08:00
hy
b016ddd8ab
Refine test report docs and localize report headings
2026-03-18 10:06:38 +08:00
hy
6fd15f62d6
Archive completed OpenSpec changes and refresh workbench docs
2026-03-18 09:22:00 +08:00
hy
79d7fdb1b0
Clarify workbench model names in phase-one test plan
2026-03-17 19:09:24 +08:00
hy
08d7282ac4
Refine AI workbench test docs and model diagnostics
2026-03-17 19:07:05 +08:00
hy
ab6206fd54
Refine AI workbench test plan structure
2026-03-17 17:48:49 +08:00
hy
f347e499b0
Expand AI workbench backend and e2e test coverage
2026-03-17 17:10:48 +08:00
hy
fe04c06fe3
Refine live model baseline and normalize OpenAI base URLs
2026-03-17 14:49:31 +08:00
hy
19c8f995f9
Add partial delivery coverage for blocked human flows
2026-03-17 12:25:08 +08:00
hy
fb1dec8757
Expand AI backend tests and add human test harnesses
2026-03-17 12:11:08 +08:00
hy
44ca938427
Add dual-model comparison to AI test
2026-03-16 16:56:22 +08:00
hy
8e5d191bf2
恢复详细的AI测试计划拆分与模型对照
2026-03-16 16:48:08 +08:00
hy
426bffa7f4
Draft AI workbench test plan
2026-03-16 16:24:07 +08:00
huangyuan
93d46e3082
Refactor test architecture per plan
2026-03-15 10:52:44 +08:00
huangyuan
151dc298b4
Implement test log v2 contract
2026-03-14 15:40:37 +08:00
huangyuan
8247f9cf81
实施测试日志契约v2改造方案」} ओली? need Chinese
2026-03-14 15:38:03 +08:00
huangyuan
b9f40188d0
分析 ai 测试报告字段」} continuous 0? oh w/ 》
2026-03-14 14:33:43 +08:00
huangyuan
99da93f5ed
Implement new test architecture
2026-03-14 13:56:52 +08:00
huangyuan
f495142838
Implement new testing architecture
2026-03-14 13:38:13 +08:00
huangyuan
a920fdaa74
Rewrite docs and ai design flow
2026-03-14 11:47:34 +08:00
hy
d72044db95
Document human rerun test policy
2026-03-13 17:06:45 +08:00
hy
5f6beebe21
Start new openspec change process
2026-03-13 16:44:14 +08:00
hy
f511c17926
整理 run test 指令分类并清理
2026-03-13 15:53:18 +08:00
hy
d7f078ef66
Organize accumulated tests and docs
2026-03-13 14:59:59 +08:00
hy
5f4582b734
Update human-led delivery docs
2026-03-13 12:52:09 +08:00
hy
7382ce612c
Document main runtime baseline
2026-03-13 09:23:34 +08:00
hy
354ed9a3fe
Update human test P3 status
2026-03-12 19:09:01 +08:00
hy
eb51ae835b
继续推进 human 测试计划}collectionWeights
2026-03-12 18:49:05 +08:00
hy
f7aa26ba01
Archive improve-human-test-eval
2026-03-12 17:48:11 +08:00
hy
97857b6037
补充测试文档入口README纲要潜在漂移
2026-03-12 16:32:51 +08:00
hy
135304c821
Restructure doc hierarchy and skills
2026-03-12 15:30:04 +08:00
hy
f73f4b86dd
Clean renderer warning noise on UI
2026-03-12 14:02:55 +08:00
hy
b9deb51925
Rename human-live naming
2026-03-12 10:26:01 +08:00
hy
00da091277
整理测试文档结构与指引更新路线图标题
2026-03-11 18:07:03 +08:00
hy
f7de58edd4
Add doc/test directory docs
2026-03-11 17:24:54 +08:00
hy
fd7fa3cdf4
Add tool capability testing plan
2026-03-11 15:47:42 +08:00
hy
8991a16319
Migrate ai directory structure
2026-03-11 14:21:35 +08:00
huangyuan
fa228c680b
new workspace
2026-03-10 18:31:29 +08:00
hy
4f0c9a9e00
设计 brain 驱动 skill 加载方案
2026-03-06 18:34:55 +08:00
hy
89347fe307
Document AI testing contract updates
2026-03-06 11:21:04 +08:00
hy
9e80f74957
Update test docs and env setup
2026-03-05 18:19:31 +08:00
hy
295351ea74
Add testing doc and skill updates
2026-03-05 18:06:02 +08:00
hy
3e6763fcaa
refactor: centralize AI prompt management and enhance human execution flow
...
- Introduced a unified prompt registry for main, human, and memory prompts to improve maintainability and reduce duplication.
- Replaced inline prompts in various nodes with calls to the new prompt registry.
- Enhanced the human execution model to allow for progressive exploration after recoverable failures, rather than immediate blocking.
- Removed the `mode` field from `HumanTaskInput`, simplifying the input contract to just `taskId` and `objective`.
- Updated documentation to reflect changes in architecture and prompt management.
- Added structured prompt building functions to ensure consistent output contracts across the system.
2026-03-05 14:06:27 +08:00
hy
c1139a33d9
feat: Update AI architecture and node structure to enhance task execution flow and state management
2026-03-04 15:34:01 +08:00
hy
e212b5b9e4
Refactor AI Node Structure: Remove Slot Commit and Human Init Nodes, Simplify Tool Execution Flow
...
- Deleted `initNode.ts` and `slotCommitNode.ts` to streamline the human node structure.
- Updated `toolExecNode.ts` to remove unnecessary phases and simplify the tool execution logic.
- Adjusted `types.ts` to reflect the removal of phases and state properties related to slot management.
- Modified `contextDispatchNode.ts` and `dispatchNode.ts` to align with the new flow and removed references to slot states.
- Introduced `intentNode.ts` to handle intent decisions and context enrichment.
- Updated state schemas to remove slot-related properties and adjust the main stage flow.
- Cleaned up unused imports and types across various files to enhance code clarity and maintainability.
2026-03-04 14:08:03 +08:00
hy