easy-coding-harness 0.8.3 → 0.9.0-beta.0

package/templates/qoder/agents/ec-implementer.md

@@ -1,6 +1,6 @@
 ---
 name: ec-implementer
-description: Easy Coding implementation sub-agent. Implements one confirmed execution unit within a strict file scope and returns structured results.
+description: Easy Coding implementation sub-agent. Implements one workflow-mode task card within strict scope and returns structured results.
 skills: []
 mcpServers: []
 ---
@@ -18,6 +18,8 @@ complete exactly that unit. Your reply IS the return value, not a message to a h
   context is in the card.
 - Make no workflow stage-transition decisions; you do not know the state machine exists.
 - Follow the coding rules and architecture context embedded in the card.
+- Treat acceptance criteria, test points, contracts, and risks in the card as required inputs.
+- Run the exact targeted checks requested by the card and report their real outcome.
 - Preserve each existing file's original encoding; never silently convert.
 
 ## Output (return exactly this)
@@ -27,5 +29,6 @@ complete exactly that unit. Your reply IS the return value, not a message to a h
 - `deliverable`: full no-code result, or `null` for a code unit
 - `issues`: problems you hit (empty array if none)
 - `needs_attention`: anything the main agent must decide (empty array if none)
+- `checks`: commands run with pass/fail outcomes
 
 Do not claim a file is verified unless the card asked you to run a check and you ran it.

package/templates/qoder/agents/ec-reviewer.md

@@ -1,6 +1,6 @@
 ---
 name: ec-reviewer
-description: Easy Coding review sub-agent. Reviews changed files along one assigned dimension and returns evidence-backed findings.
+description: Easy Coding review sub-agent. Reviews assigned risk dimensions and returns acceptance-aware findings.
 skills: []
 mcpServers: []
 ---
@@ -18,6 +18,8 @@ dimension named in your task card. Your reply IS the return value.
     null/empty handling, races, off-by-one.
   - compliance → does the code obey the RULES sections in the card? naming, format, comment
     language, error handling.
+- `error` means a demonstrated acceptance, contract, security, or build failure. Use `warning`
+  for a credible risk and `info` for non-blocking maintainability advice.
 
 ## Hard constraints
 
@@ -28,5 +30,5 @@ dimension named in your task card. Your reply IS the return value.
 ## Output (return exactly this)
 
 - `dimension`: your assigned dimension
-- `findings`: array of `{file, line, issue, severity}` (`severity`: info | warn | error)
+- `findings`: array of `{file, line, issue, severity}` (`severity`: info | warning | error)
 - `suggestion`: optional fix direction per finding

package/templates/qoder/agents/ec-verifier.md

@@ -1,6 +1,6 @@
 ---
 name: ec-verifier
-description: Easy Coding verification sub-agent. Runs one verification check and reports fresh evidence.
+description: Easy Coding verification sub-agent. Runs one requested check and returns fingerprint-ready evidence.
 skills: []
 mcpServers: []
 ---
@@ -16,7 +16,8 @@ pass.
 
 ## What to do
 
-- Run the exact command the card specifies (e.g. `npm run lint`, `tsc --noEmit`, `npm test`).
+- Run the exact command the card specifies (e.g. `npm run lint`, `tsc --noEmit`, `npm test`,
+  `npm run build`).
 - Capture the real exit status and output.
 
 ## Hard constraints
@@ -26,7 +27,9 @@ pass.
 
 ## Output (return exactly this)
 
-- `check_type`: lint | typecheck | test
+- `check_type`: lint | typecheck | test | build
 - `passed`: true | false (from the real exit status)
 - `failures`: array of failure messages (empty if passed)
 - `command_output`: the relevant tail of stdout/stderr
+- `implementation_fingerprint`: copy unchanged from the task card
+- `config_fingerprint`: copy unchanged from the task card

package/templates/runtime/memory/SHORT_MEMORY_TEMPLATE.md

@@ -5,6 +5,7 @@ source_task: MM-DD-task-slug
 date: YYYY-MM-DD
 task_type: feature | bugfix | refactor | perf | doc | workflow
 project_mode: startup | iteration
+workflow_mode: fast | standard | strict
 domain:
   - "{business domain or module}"
 tags:
@@ -38,6 +39,7 @@ target_long: BUSINESS | TECHNICAL | BOTH | NONE
 - Scope: {modules, pages, interfaces, or files involved}
 - Result: {completed / partially completed / not completed, with reasons}
 - Key Constraints: {encoding, compatibility, interface, spec, or user-specified constraints; "none" if none}
+- Workflow Mode: {frozen mode and why it was selected or escalated}
 
 ## Execution Evidence
 

package/templates/runtime/templates/dev-spec-skeleton.md

@@ -49,16 +49,16 @@
 
 ### 实施拆解
 
-| 单元 | 说明 | 类型 | 涉及文件 | 依赖 |
-|------|------|------|---------|------|
-| U1 | [[EC_TODO:单元标题]] | [[EC_TODO:backend/frontend/test/...]] | [[EC_TODO:涉及文件]] | — |
-| U2 | [[EC_TODO:单元标题]] | [[EC_TODO:单元类型]] | [[EC_TODO:涉及文件]] | — |
-| U3 | [[EC_TODO:单元标题]] | [[EC_TODO:单元类型]] | [[EC_TODO:涉及文件]] | U1, U2 |
+| 单元 | 说明 | 类型 | 涉及文件 | 依赖 | 验收条件 | 测试点 | 跨单元契约 |
+|------|------|------|---------|------|---------|-------|-----------|
+| U1 | [[EC_TODO:单元标题]] | [[EC_TODO:backend/frontend/test/...]] | [[EC_TODO:涉及文件]] | — | [[EC_TODO:可验证结果]] | [[EC_TODO:定向验证]] | [[EC_TODO:输入输出或“无”]] |
+| U2 | [[EC_TODO:单元标题]] | [[EC_TODO:单元类型]] | [[EC_TODO:涉及文件]] | — | [[EC_TODO:可验证结果]] | [[EC_TODO:定向验证]] | [[EC_TODO:输入输出或“无”]] |
+| U3 | [[EC_TODO:单元标题]] | [[EC_TODO:单元类型]] | [[EC_TODO:涉及文件]] | U1, U2 | [[EC_TODO:可验证结果]] | [[EC_TODO:定向验证]] | [[EC_TODO:与 U1/U2 的契约]] |
 
 **执行策略**：[[EC_TODO:parallel / sequential / single]]
 - 第一批（并行）：U1 [[EC_TODO:单元标题]] ｜ U2 [[EC_TODO:单元标题]]
 - 第二批（等待第一批）：U3 [[EC_TODO:单元标题]]
-（若 single：单一实施单元，派发 1 个子代理执行）
+（若 single：按 Workflow Mode 决定由主 Agent 直接执行或派发子 Agent）
 
 ### 测试策略
 
@@ -70,6 +70,14 @@
 - **人工验收**：[[EC_TODO:用户需要检查的关键行为]]
 - **无法验证项**：[[EC_TODO:无 / 说明缺失环境、数据或权限]]
 
+### Workflow Mode
+- **项目配置**：[[EC_TODO:adaptive / fast / standard / strict]]
+- **Session 覆盖**：[[EC_TODO:无 / adaptive / fast / standard / strict]]
+- **机械最低模式**：[[EC_TODO:fast / standard / strict]]
+- **推荐并选择**：[[EC_TODO:fast / standard / strict]]
+- **选择原因**：[[EC_TODO:风险、范围和兼容性依据]]
+- **状态内执行差异**：[[EC_TODO:IMPLEMENT / REVIEW / VERIFICATION / MEMORY 将采用的深度]]
+
 ### 风险与注意事项
 - [[EC_TODO:风险 1]]
 - [[EC_TODO:风险 2]]