diff --git a/.cursor/skills/marqdo/SKILL.md b/.cursor/skills/marqdo/SKILL.md
index 11e96a9..ab3fea1 100644
--- a/.cursor/skills/marqdo/SKILL.md
+++ b/.cursor/skills/marqdo/SKILL.md
@@ -20,7 +20,7 @@ Canonical design (repo): `doc/design/markdown-mapping.md`, `doc/design/keywords.
2. **Output is not `**bold**`.** Print with `> print text=…` (or `> 打印 内容=…`). Bold `**…**` is **return value only**.
3. **Prose vs code:** after a blank line, an unmarked first line starts a **comment paragraph**; every following non-blank line stays comment until the next blank line. Put a **blank line** between narration and executable lines.
4. **Do not invent keywords** `if` / `else` / `while` / `for` / `def` / `return`. Control flow is Markdown: **`+` params** (under heading), **`1.` `2.` … branches**, **`-` loops**, arm `N. *` = else, `#` = **object/type**, `##`+ = **function/method**, `**…**` = return.
-5. **Identifiers use backticks** — params `` + `name` ``. **Exemptions:** foreach `` - [item](coll) ``; footnote `` name[^key] ``; **inside italic `*…*` / bold `**…**`**, bare ids are variables (strings need `"…"` / `'…'`; ticks still ok). **Drop the backticks on value-expression variable names inside `*…*` / `**…**`** — they are redundant once the `*…*`/`**…**` markers mark the segment as code: `*分类 = 分类[^苹果]*`, `**n * 2**`. **Still required** where a bare word is *not* a variable: inside `"…"` / `'…'` interpolation (`` "Hello, `who`!" ``), inside `> call args` (`` > str `n` ``), and on method-call receivers (`` > `obj`.method ``). **No trailing space** inside `*…*` / `**…**` wrapped code: the closing marker must touch the last token directly (`*`a` = 1*`, `**n**`), never `` *`a` = 1 * ``.
+5. **Identifiers use backticks** — params `` + `name` ``. **Exemptions:** foreach `` - [item](coll) ``; footnote `` name[^key] ``; **inside italic `*…*` / bold `**…**`**, bare ids are **variables** (Python-style unified namespace) and method-call receivers are bare too. **Drop the backticks on value-expression variable names and method receivers inside `*…*` / `**…**`** — they are redundant once the `*…*`/`**…**` markers mark the segment as code: `*分类 = 分类[^苹果]*`, `**n * 2**`, `*p = > page.主体装配 组件=home*`. **Text literals must be quoted**: `*a = > text.split value=src sep=","*`. Backticks **still required** where a bare word is *not* a variable in **standalone `>` calls** (bare = text there): `` > str `n` ``, `` > `obj`.method ``. **No trailing space** inside `*…*` / `**…**` wrapped code: the closing marker must touch the last token directly (`*a = 1*`, `**n**`), never `` *a = 1 * ``.
6. **Structure lines are not wrapped in italics.** `#` `>` `+` `-` `|` lines stand alone; use `*…*` only for general statements (bindings / expressions).
7. **Paths:** In bare *expressions* `/` is division. In **call args / param defaults**, unspaced `a/b` and quoted `".marqdo/agent-kb"` are path text — no `json.parse` needed.
8. Prefer ending side-effect-only function bodies with a lone `---` or `***` line (or `****` empty return) so later siblings are not swallowed.
@@ -123,7 +123,7 @@ import clock:lib/time.mq.md
# main
-*xs = > text.split value=a,b,c sep=,*
+*xs = > text.split value="a,b,c" sep=","*
> print text=`xs`
*t = > clock.now_unix*
```
@@ -155,7 +155,8 @@ Stdlib map: [reference.md](reference.md).
| `# main` then prose then code with no blank line | Blank line before code |
| `if x > 0:` | `1. `x` > 0` |
| `* > print text=hi *` | `> print text=hi` |
-| `` *`a` = 1 * `` (trailing space) | `` *`a` = 1* `` — no trailing space before `*` / `**` |
+| `` *`a` = 1 * `` (trailing space + backticks) | `*a = 1*` — bare bind, no trailing space before `*` / `**` |
+| `*xs = > text.split value=a,b sep=,*` (bare text args) | `*xs = > text.split value="a,b" sep=","*` — quote text literals; bare words are variables |
| Forgetting `---` after nested `##` helper | Add `---` / `***` / `****` |
| Import `lib/text` then call bare `split` | `> text.split …` (qualified) |
| Import `lib/text` then call `拆分` | Match file language (`text.split`, not 文本) |
diff --git a/doc/design/call-arguments.md b/doc/design/call-arguments.md
index c833c46..e4d8ab0 100644
--- a/doc/design/call-arguments.md
+++ b/doc/design/call-arguments.md
@@ -32,6 +32,8 @@ positional ::= value_token
- `value`(具名右侧):可含空格与 `` `var` `` 插值,直到下一个 `ident=` 边界。
- `value_token`(位置):空白分隔的一个词法单元——数字、`` `名` ``、标识/文本词;**不含空格**。多词字符串请用具名,例如 `> print text=Hello World!`。
+- **独立 `>` 调用**:裸词 = 文本字面量。
+- **`*…*` / `**…**` 段内的调用**(如 `*x = > text.split value=src sep=","*`):裸词 = **变量**(Python 统一命名空间),文本字面量必须加引号(`value="a,b"`);`` `名` `` 变量形式仍合法。
- 内置 `print` / `打印` 形参:`text` ≡ `内容`。
- `input` / `输入`:`prompt` ≡ `提示`。
- `len` / `长度`、`str` / `文本`、`int` / `整数`:`value` ≡ `值`。
diff --git a/doc/design/markdown-mapping.md b/doc/design/markdown-mapping.md
index c8b2f05..50345a3 100644
--- a/doc/design/markdown-mapping.md
+++ b/doc/design/markdown-mapping.md
@@ -21,7 +21,7 @@ Markdown **标记即语法**。输出**不是**语言架构原语,而是内置
**豁免:**
- foreach 头 `` - [项](集合) `` 允许裸名或反引号(可混用),推荐裸名;循环体内引用仍用 `` `名` ``。
- 脚注取元 `` 名[^键] ``:基名在紧跟 `` [^…] `` 时可省略反引号(`` `名`[^键] `` 仍合法);链式同理。
- - **斜体语句 / 粗体返回内部**:裸标识符默认是**变量**;字符串须 `"…"` 或 `'…'`;`` `名` `` 仍合法。
+ - **斜体语句 / 粗体返回内部**:裸标识符默认是**变量**(含调用实参与方法接收者);文本字面量须 `"…"` 或 `'…'` 或引号实参(`key="文本"`);`` `名` `` 仍合法。这是 **Python 统一命名空间**:裸点号 `a.b` 在 `a` 为局部变量时为方法调用,否则为库路径。
---
@@ -50,7 +50,7 @@ Markdown **标记即语法**。输出**不是**语言架构原语,而是内置
| 体内 `-` | **循环**(`while` 条件,或 `[项](集合)` / `` [`项`](`集合`) `` 遍历) |
| 分支臂头整行恰为 `*`(在 `N.` 后) | else,如 `2. *` |
| `> 函数 形参=实参` 或 `> 函数 实参` | 调用(具名 / 位置,见 [call-arguments.md](call-arguments.md)) |
-| `` > `对象`.方法 … `` | 方法调用(实例 map 须含 `_type`) |
+| `` > `对象`.方法 … `` | 方法调用(独立 `>`;实例 map 须含 `_type`)。`*…*` 段内接收者裸名:`*x = > 对象.方法 …*` |
| frontmatter `import bind:path.mq.md` / `导入` | 导入文件并绑定库名 |
| frontmatter `import bind:lib.member` / `导入` | 将库路径成员绑为本地短名(与文件导入同形) |
| `> lib.member …` / `> lib.Type.member …` | 点号路径调用(路径段裸名、无反引号) |
@@ -93,7 +93,7 @@ Markdown **标记即语法**。输出**不是**语言架构原语,而是内置
*x = 1*
*y = x + 2*
*answer = ev[^message]*
-*`亦可用` = 1*
+*亦可用 = 1*
```
斜体内部:裸标识符 = 变量;字符串写 `"…"` / `'…'`。行首已是结构标记的构造(`#` `>` `+` `-` `|`、`1.`)**不必**再包一层斜体;斜体用于「一般语句」槽位。
@@ -129,7 +129,7 @@ Markdown **标记即语法**。输出**不是**语言架构原语,而是内置
## 5. Frontmatter 与跨文件
-文件头 `---` 对为元信息。其中 `import bind:path.mq.md` / `导入` 为**文件导入**;`import bind:lib.member` 为**短名**(废除独立 `use` 与 frontmatter `>` 导入)。调用经裸点号路径(`time.parse`、`agent.agent`);实例方法须 `` > `var`.method ``。详见 [module-namespace.md](module-namespace.md)。
+文件头 `---` 对为元信息。其中 `import bind:path.mq.md` / `导入` 为**文件导入**;`import bind:lib.member` 为**短名**(废除独立 `use` 与 frontmatter `>` 导入)。调用经裸点号路径(`time.parse`、`agent.agent`);实例方法在独立 `>` 调用须 `` > `var`.method ``(`*…*` 段内接收者裸名)。详见 [module-namespace.md](module-namespace.md)。
**函数体内的** `---` / `***` 不解释为 frontmatter(见 §11)。
diff --git a/doc/design/module-namespace.md b/doc/design/module-namespace.md
index d72272c..ddb9bc8 100644
--- a/doc/design/module-namespace.md
+++ b/doc/design/module-namespace.md
@@ -107,10 +107,10 @@ import json:lib/json.mq.md
# main
-*`t` = > time.now_unix *
-*`s` = > time.format unix=`t` pattern=%Y-%m-%d *
-*`obj` = > json.parse text={"a":1} *
-*`a` = > json.get value=`obj` key=a *
+*t = > time.now_unix*
+*s = > time.format unix=`t` pattern="%Y-%m-%d"*
+*obj = > json.parse text={"a":1}*
+*a = > json.get value=`obj` key="a"*
> print text=`s`
```
@@ -122,12 +122,18 @@ import json:lib/json.mq.md
实例方法须 `` > `var`.method ``;无接收者的 `库.类型.方法` → 硬错误。
-### 4.4 变量 / 实例 vs 库路径
+### 4.4 变量 / 实例 vs 库路径(Python 统一命名空间)
| 写法 | 含义 |
|------|------|
-| `time.parse` | 库路径(裸名) |
-| `` > `助手`.step `` | 实例方法(接收者反引号) |
+| `time.parse` | 库路径(裸名,第一段非变量) |
+| `` > `助手`.step `` | 独立 `>` 调用:实例方法(接收者反引号) |
+| `*回复 = > 助手.step …*` | `*…*` 段内:若 `助手` 是变量 → 实例方法;否则 → 库路径 |
+
+**统一规则**(与 Python 一致):对裸点号 `a.b`,当 `a` 是当前作用域**局部变量**时解释为**方法调用**(`a` 为接收者);否则解释为**库路径**(`lib.a.b`)。此规则同时应用于树遍历与字节码两后端。
+
+- 在**独立 `>` 调用**中裸词 = 文本,故方法接收者仍须反引号:`` > `助手`.step ``。
+- 在 **`*…*` / `**…**` 段内**裸词 = 变量,接收者不加反引号:`*回复 = 助手.step …*`。
### 4.5 短名示例
@@ -139,8 +145,8 @@ import fmt:time.format
# main
-*`t` = > time.now_unix *
-*`s` = > fmt unix=`t` pattern=%Y-%m-%d *
+*t = > time.now_unix*
+*s = > fmt unix=`t` pattern="%Y-%m-%d"*
```
### 4.6 应用侧完整示例
@@ -210,5 +216,5 @@ import json:lib/json.mq.md
1. 导入 = `import bind:target`(`导入` 等价)。
2. target = `.mq.md` 文件 **或** `库.成员` 点号路径。
-3. 调用以裸名点号路径寻址;实例方法用反引号接收者。
-4. 废除 frontmatter `>` 导入与独立 `use`。
+3. 调用以裸名点号路径寻址;实例方法用反引号接收者(仅独立 `>` 调用;`*…*`/`**…**` 段内接收者不加反引号)。
+4. 裸点号 `a.b`:`a` 为局部变量 → 方法调用,否则 → 库路径(Python 统一命名空间)。
diff --git a/doc/design/objects.md b/doc/design/objects.md
index f7c5167..af1a50d 100644
--- a/doc/design/objects.md
+++ b/doc/design/objects.md
@@ -33,24 +33,24 @@
# 大模型
+ `模型名`
-*`自` = …配置 map…*
-**`自`**
+*自 = …配置 map…*
+**自**
## 运行
+ `提示`
…使用 `自` …
-**`内容`**
+**内容**
# main
-*`模型` = > 大模型 模型名=gpt-4o-mini *
-*`回复` = > `模型`.运行 提示=你好 *
+*模型 = > 大模型 模型名="gpt-4o-mini"*
+*回复 = > 模型.运行 提示="你好"*
> print text=`回复`
```
- `> 大模型 …` — 构造
-- `` > `模型`.运行 … `` — 方法(接收者 + `.` + 方法名)
+- `` > `模型`.运行 … `` — 方法(接收者 + `.` + 方法名;**独立 `>` 调用**需反引号接收者 `` `模型` ``;**在 `*…*` / `**…**` 段内**接收者不加反引号:`*回复 = > 模型.运行 提示="你好"*`)
- `## 自由函数` 挂在模块顶层(非某对象子标题)— 与旧版顶层 `# http_get` 对等,现写为 `## http_get`
## 4. 标准库
@@ -66,16 +66,16 @@
## hello
+ `who`
-*`msg` = "Hello, `who`!" *
-**`msg`**
+*msg = "Hello, `who`!"*
+**msg**
# Loud = > Greeter
## hello
+ `who`
-*`msg` = "HELLO, `who`!" *
-**`msg`**
+*msg = "HELLO, `who`!"*
+**msg**
```
| 规则 | 说明 |
diff --git a/examples/quantum-bell/index.mq.md b/examples/quantum-bell/index.mq.md
index ead26f3..61a0f63 100644
--- a/examples/quantum-bell/index.mq.md
+++ b/examples/quantum-bell/index.mq.md
@@ -19,9 +19,9 @@ H on qubit 0, then CNOT(0→1). Ideal measurement: |00⟩ and |11⟩ each with p
| 1 | H | 0 |
| 2 | CX | 0,1 |
-*`qc` = > quantum.circuit qubits=2 steps=`steps` *
-*`p` = > `qc`.probabilities *
-*`_` = > `qc`.draw path=bell.svg *
-*`_` = > `qc`.draw kind=probs path=bell-probs.svg *
+*qc = > quantum.circuit qubits=2 steps=`steps`*
+*p = > qc.probabilities*
+*_ = > qc.draw path="bell.svg"*
+*_ = > qc.draw kind="probs" path="bell-probs.svg"*
> print text=`p`
diff --git a/examples/quantum-ghz/index.mq.md b/examples/quantum-ghz/index.mq.md
index dcd8963..767b80c 100644
--- a/examples/quantum-ghz/index.mq.md
+++ b/examples/quantum-ghz/index.mq.md
@@ -18,11 +18,11 @@ H on qubit 0, CX(0→1), CX(0→2). Ideal: |000⟩ and |111⟩ each with probabi
| 2 | CX | 0,1 |
| 3 | CX | 0,2 |
-*`qc` = > quantum.circuit qubits=3 steps=`steps` *
-*`p` = > `qc`.probabilities *
-*`_` = > `qc`.draw path=ghz.svg *
-*`_` = > `qc`.draw kind=probs path=ghz-probs.svg *
-*`H` = > quantum.gate name=H *
-*`_` = > `H`.draw kind=matrix path=ghz-h-matrix.svg *
+*qc = > quantum.circuit qubits=3 steps=`steps`*
+*p = > qc.probabilities*
+*_ = > qc.draw path="ghz.svg"*
+*_ = > qc.draw kind="probs" path="ghz-probs.svg"*
+*H = > quantum.gate name="H"*
+*_ = > H.draw kind="matrix" path="ghz-h-matrix.svg"*
> print text=`p`
diff --git a/examples/web-site-zh/db/index.mq.md b/examples/web-site-zh/db/index.mq.md
index 036609d..f66ba24 100644
--- a/examples/web-site-zh/db/index.mq.md
+++ b/examples/web-site-zh/db/index.mq.md
@@ -7,13 +7,13 @@ import articles:articles.mq.md
## open
-*`store` = > 网页.数据库 地址="sqlite:data/site-zh.db" *
-*`fields` = > articles.schema *
+*store = > 网页.数据库 地址="sqlite:data/site-zh.db"*
+*fields = > articles.schema*
> `store`.初始化 名=articles 字段=`fields`
-*`rows` = > `store`.查询 表=articles 上限=1 *
+*rows = > store.查询 表="articles" 上限=1*
1. `rows`
- **`store`**
+ **store**
2. *
- *`seed` = > articles.seed *
+ *seed = > articles.seed*
> `store`.插入 表=articles 行=`seed`
- **`store`**
+ **store**
diff --git a/examples/web-site-zh/index.mq.md b/examples/web-site-zh/index.mq.md
index c77f19b..dec6521 100644
--- a/examples/web-site-zh/index.mq.md
+++ b/examples/web-site-zh/index.mq.md
@@ -24,8 +24,8 @@ import db:db/index.mq.md
| 属性 | 值 | 样式 |
|------|-----|------|
-| `title` | articles.`articles`.title | shell.`card_title` |
-| `body` | articles.`articles`.body | shell.`card_body` |
+| title | articles.`articles`.title | shell.`card_title` |
+| body | articles.`articles`.body | shell.`card_body` |
`article_fields` =
@@ -42,24 +42,24 @@ import db:db/index.mq.md
| title | max:120 | 标题太长 |
| body | max:8000 | 正文太长 |
-*`store` = > db.open *
-*`page` = > 网页.页面 标题="Marqdo 中文站" 引言="
中文站
表格 + 类方法。
" *
-*`page` = > `page`.组件装配 组件=`home` *
-*`page` = > `page`.主体装配 主体=`index` *
+*store = > db.open*
+*page = > 网页.页面 标题="Marqdo 中文站" 引言="中文站
表格 + 类方法。
"*
+*page = > page.组件装配 组件=home*
+*page = > page.主体装配 主体=index*
-*`about` = > 网页.页面 标题="关于" 引言="关于
导入网页.mq.md 即用中文 API。
" *
-*`about` = > `about`.组件装配 组件=`home` *
+*about = > 网页.页面 标题="关于" 引言="关于
导入网页.mq.md 即用中文 API。
"*
+*about = > about.组件装配 组件=home*
-*`article_form` = > 网页.表单 表=articles 动作=插入 *
-*`article_form` = > `article_form`.字段 字段=`article_fields` *
-*`article_form` = > `article_form`.规则 规则=`article_rules` *
+*article_form = > 网页.表单 表="articles" 动作="插入"*
+*article_form = > article_form.字段 字段=article_fields*
+*article_form = > article_form.规则 规则=article_rules*
-*`new` = > 网页.页面 标题="写文章" 引言="写文章
表单嵌在主区。
" *
-*`new` = > `new`.组件装配 组件=`home` *
-*`new` = > `new`.表单装配 id=article 表单=`article_form` *
+*new = > 网页.页面 标题="写文章" 引言="写文章
表单嵌在主区。
"*
+*new = > new.组件装配 组件=home*
+*new = > new.表单装配 id="article" 表单=article_form*
-*`app` = > 网页.应用 页面=`page` 数据库=`store` 后台=True 主机=127.0.0.1 端口=18082 *
-*`app` = > `app`.路由 路径=/about 页面=`about` *
-*`app` = > `app`.路由 路径=/new 页面=`new` *
-*`app` = > `app`.静态 目录=public 挂载=/static *
+*app = > 网页.应用 页面=page 数据库=store 后台=True 主机="127.0.0.1" 端口=18082*
+*app = > app.路由 路径="/about" 页面=about*
+*app = > app.路由 路径="/new" 页面=new*
+*app = > app.静态 目录="public" 挂载="/static"*
> `app`.监听
diff --git a/examples/web-site/db/index.mq.md b/examples/web-site/db/index.mq.md
index d9486af..b24991c 100644
--- a/examples/web-site/db/index.mq.md
+++ b/examples/web-site/db/index.mq.md
@@ -8,13 +8,13 @@ import fs:lib/fs.mq.md
## open
-*`store` = > web.db url="sqlite:data/site.db" *
-*`fields` = > articles.schema *
+*store = > web.db url="sqlite:data/site.db"*
+*fields = > articles.schema*
> `store`.init name=articles fields=`fields`
-*`rows` = > `store`.select table=articles limit=1 *
+*rows = > store.select table="articles" limit=1*
1. `rows`
- **`store`**
+ **store**
2. *
- *`seed` = > articles.seed *
+ *seed = > articles.seed*
> `store`.insert table=articles rows=`seed`
- **`store`**
+ **store**
diff --git a/examples/web-site/index.mq.md b/examples/web-site/index.mq.md
index 082c41a..5e7f063 100644
--- a/examples/web-site/index.mq.md
+++ b/examples/web-site/index.mq.md
@@ -26,8 +26,8 @@ Main content is not a reusable component, so it is authored here.
| 属性 | 值 | 样式 |
|------|-----|------|
-| `title` | articles.`articles`.title | shell.`card_title` |
-| `body` | articles.`articles`.body | shell.`card_body` |
+| title | articles.`articles`.title | shell.`card_title` |
+| body | articles.`articles`.body | shell.`card_body` |
Article create form (design §5.5): field table + rules table.
@@ -46,28 +46,28 @@ Article create form (design §5.5): field table + rules table.
| title | max:120 | Title is too long |
| body | max:8000 | Body is too long |
-*`store` = > db.open *
-*`page` = > web.page title="Marqdo Web Site" intro="Web Site
Tables + class methods.
" *
-*`page` = > `page`.compose_components components=`home` *
-*`page` = > `page`.compose_main main=`index` *
+*store = > db.open*
+*page = > web.page title="Marqdo Web Site" intro="Web Site
Tables + class methods.
"*
+*page = > page.compose_components components=home*
+*page = > page.compose_main main=index*
About page: same shell, different intro (no main bind).
-*`about` = > web.page title="About" intro="About
Marqdo web = tables + class methods.
" *
-*`about` = > `about`.compose_components components=`home` *
+*about = > web.page title="About" intro="About
Marqdo web = tables + class methods.
"*
+*about = > about.compose_components components=home*
-*`article_form` = > web.form table=articles action=insert *
-*`article_form` = > `article_form`.fields fields=`article_fields` *
-*`article_form` = > `article_form`.rules rules=`article_rules` *
+*article_form = > web.form table="articles" action="insert"*
+*article_form = > article_form.fields fields=article_fields*
+*article_form = > article_form.rules rules=article_rules*
New article: form embedded in the page main slot (design §5.5.4).
-*`new` = > web.page title="New article" intro="New article
Form lives in the main slot.
" *
-*`new` = > `new`.compose_components components=`home` *
-*`new` = > `new`.compose_form id=article form=`article_form` *
+*new = > web.page title="New article" intro="New article
Form lives in the main slot.
"*
+*new = > new.compose_components components=home*
+*new = > new.compose_form id="article" form=article_form*
-*`app` = > web.app page=`page` db=`store` admin=True host=127.0.0.1 port=18081 *
-*`app` = > `app`.route path=/about page=`about` *
-*`app` = > `app`.route path=/new page=`new` *
-*`app` = > `app`.static dir=public mount=/static *
+*app = > web.app page=page db=store admin=True host="127.0.0.1" port=18081*
+*app = > app.route path="/about" page=about*
+*app = > app.route path="/new" page=new*
+*app = > app.static dir="public" mount="/static"*
> `app`.listen
diff --git a/ext/ai/agent.mq.md b/ext/ai/agent.mq.md
index 226955f..c8edc22 100644
--- a/ext/ai/agent.mq.md
+++ b/ext/ai/agent.mq.md
@@ -17,32 +17,32 @@ import plugin:lib/plugin.mq.md
Assemble a readable prompt: standing, task, tools, call site, source, skill, and the act protocol (human-visible).
-*`standing` = > json.get value=`agent` key=standing *
+*standing = > json.get value=`agent` key="standing"*
1. `standing`
- *`up` = `standing`*
+ *up = standing*
2. *
- *`up` = None*
+ *up = None*
-*`tools` = > json.get value=`agent` key=tools *
-*`tools_s` = > agent_format_tools tools=`tools` *
-*`src` = > agent_module_source *
-*`site` = > agent_call_site *
-*`site_s` = > json.stringify value=`site` *
-*`skill` = > agent_marqdo_skill *
-*`task_s` = > json.stringify value=`task` *
+*tools = > json.get value=`agent` key="tools"*
+*tools_s = > agent_format_tools tools=`tools`*
+*src = > agent_module_source*
+*site = > agent_call_site*
+*site_s = > json.stringify value=`site`*
+*skill = > agent_marqdo_skill*
+*task_s = > json.stringify value=`task`*
-*`esc` = > json.parse text={"a":"\n\n--- standing ---\n","b":"\n\n--- task ---\n","c":"\n\n--- tools ---\n","d":"\n\n--- call site ---\n","e":"\n\n--- source (.mq.md) ---\n","f":"\n\n--- marqdo skill ---\n","g":"\n\n--- how to act ---\nCall ONLY names listed under --- tools --- (whitelist). If that section is empty or says none, do NOT emit CALL / 调用 — reply with the final answer only.\nNever CALL internal framework helpers (build_step_context, plan, inspect_workbook, etc.).\nWhen calling an allowed tool, reply with exactly one line: CALL:\n(Chinese ok: 调用:)\nOtherwise reply with the final answer only.\nTools run via Marqdo subtask (spawn fn / wait).\n"} *
-*`a` = > json.get value=`esc` key=a *
-*`b` = > json.get value=`esc` key=b *
-*`c` = > json.get value=`esc` key=c *
-*`d` = > json.get value=`esc` key=d *
-*`e` = > json.get value=`esc` key=e *
-*`f` = > json.get value=`esc` key=f *
-*`g` = > json.get value=`esc` key=g *
+*esc = > json.parse text={"a":"\n\n--- standing ---\n","b":"\n\n--- task ---\n","c":"\n\n--- tools ---\n","d":"\n\n--- call site ---\n","e":"\n\n--- source (.mq.md) ---\n","f":"\n\n--- marqdo skill ---\n","g":"\n\n--- how to act ---\nCall ONLY names listed under --- tools --- (whitelist). If that section is empty or says none, do NOT emit CALL / 调用 — reply with the final answer only.\nNever CALL internal framework helpers (build_step_context, plan, inspect_workbook, etc.).\nWhen calling an allowed tool, reply with exactly one line: CALL:\n(Chinese ok: 调用:)\nOtherwise reply with the final answer only.\nTools run via Marqdo subtask (spawn fn / wait).\n"}*
+*a = > json.get value=`esc` key="a"*
+*b = > json.get value=`esc` key="b"*
+*c = > json.get value=`esc` key="c"*
+*d = > json.get value=`esc` key="d"*
+*e = > json.get value=`esc` key="e"*
+*f = > json.get value=`esc` key="f"*
+*g = > json.get value=`esc` key="g"*
-*`p` = "You are a Marqdo agent. The runbook source is your ground truth — code is documentation." *
-*`p` = `p` + `a` + `up` + `b` + `task_s` + `c` + `tools_s` + `g` + `d` + `site_s` + `e` + `src` + `f` + `skill` *
-**`p`**
+*p = "You are a Marqdo agent. The runbook source is your ground truth — code is documentation."*
+*p = p + a + up + b + task_s + c + tools_s + g + d + site_s + e + src + f + skill*
+**p**
---
@@ -51,31 +51,31 @@ Assemble a readable prompt: standing, task, tools, call site, source, skill, and
Find a human-readable call line: `CALL:` or `调用:` / `调用:`.
-*`esc` = > json.parse text={"nl":"\n"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`text` = > trim value=`reply` *
-*`lines` = > split value=`text` sep=`nl` *
-*`found` = None*
+*esc = > json.parse text={"nl":"\n"}*
+*nl = > json.get value=`esc` key="nl"*
+*text = > trim value=`reply`*
+*lines = > split value=`text` sep=`nl`*
+*found = None*
- [`line`](`lines`)
- *`t` = > trim value=`line` *
- *`parts` = > split value=`t` sep=: *
- *`n` = > len value=`parts` *
+ *t = > trim value=`line`*
+ *parts = > split value=`t` sep=":"*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == CALL
- *`found` = `rest`*
+ *found = rest*
2. `head` == 调用
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
-**`found`**
+**found**
---
@@ -85,13 +85,13 @@ Find a human-readable call line: `CALL:` or `调用:` / `调用: agent_tool_allowed tools=`tools` name=`name` *
+*allowed = > agent_tool_allowed tools=`tools` name=`name`*
1. `allowed`
- *`id` = > subtask.spawn fn=`name` *
+ *id = > subtask.spawn fn=`name`*
**> subtask.wait id=`id`**
2. *
- *`msg` = "Tool not allowed:" *
- **`msg` + `name`**
+ *msg = "Tool not allowed:"*
+ **msg + name**
## render_workbook_skeleton
+ `goal`
@@ -99,35 +99,35 @@ Allowlist check, then invoke the runbook `##` via `lib/subtask` (`spawn fn=` →
Build a runnable workbook. `skeleton=single` (default): one worker `step`. `skeleton=dual`: research then write agents. On success the parent chooses DONE; runtime `agent_workbook_solidify` freezes the answer.
-*`q` = > json.quote text=`goal` *
-*`esc` = > json.parse text={"h":"---\ntitle: agent workbook\nimport llm:ext/ai/llm.mq.md\nimport agent:ext/ai/agent.mq.md\nimport json:lib/json.mq.md\nimport sys:lib/sys.mq.md\nimport writeback:lib/writeback.mq.md\nimport subtask:lib/subtask.mq.md\n---\n\n# Goal\n\nParent goal is embedded as JSON in # main.\n\n## Solidify\n\nWhen the child returns a good value, parent DECISION: DONE — runtime agent_workbook_solidify freezes the answer as **return** (do not invent long FIND/REPLACE).\n\n# main\n\n> llm.load_env\n\n","s1":"\u002a\u0060model\u0060 = > llm.llm \u002a\n","s2":"\u002a\u0060tools\u0060 = > json.parse text=[] \u002a\n","s3":"\u002a\u0060worker\u0060 = > agent.agent model=\u0060model\u0060 tools=\u0060tools\u0060 standing=You are a workbook worker. tools=[] means never CALL. Finish the task with a direct final answer; do not invent tools. \u002a\n","s4":"\u002a\u0060wrap\u0060 = > json.parse text={\"task\":","s5":"} \u002a\n","s6":"\u002a\u0060task\u0060 = > json.get value=\u0060wrap\u0060 key=task \u002a\n","s7":"\u002a\u0060out\u0060 = > \u0060worker\u0060.step task=\u0060task\u0060 stream=True \u002a\n","s7b":"\u002a\u0060text\u0060 = > json.get value=\u0060out\u0060 key=result \u002a\n","s8":"\u002a\u002a\u0060text\u0060\u002a\u002a\n","d3":"\u002a\u0060research\u0060 = > agent.agent model=\u0060model\u0060 tools=\u0060tools\u0060 standing=You gather facts for the goal. Be concise. Do not invent tools. \u002a\n","d3b":"\u002a\u0060writer\u0060 = > agent.agent model=\u0060model\u0060 tools=\u0060tools\u0060 standing=You write the final answer from research notes. Do not invent tools. \u002a\n","d4":"\u002a\u0060wrap\u0060 = > json.parse text={\"task\":","d5":"} \u002a\n","d6":"\u002a\u0060task\u0060 = > json.get value=\u0060wrap\u0060 key=task \u002a\n","d7":"\u002a\u0060notes\u0060 = > \u0060research\u0060.step task=\u0060task\u0060 stream=True \u002a\n","d8":"\u002a\u0060ns\u0060 = > json.stringify value=\u0060notes\u0060 \u002a\n","d9":"\u002a\u0060wt\u0060 = Write the final answer. Research notes: \u002a\n","d10":"\u002a\u0060wt\u0060 = \u0060wt\u0060 + \u0060ns\u0060 \u002a\n","d11":"\u002a\u0060out\u0060 = > \u0060writer\u0060.step task=\u0060wt\u0060 stream=True \u002a\n","d11b":"\u002a\u0060text\u0060 = > json.get value=\u0060out\u0060 key=result \u002a\n","d12":"\u002a\u002a\u0060text\u0060\u002a\u002a\n"} *
-*`h` = > json.get value=`esc` key=h *
-*`s1` = > json.get value=`esc` key=s1 *
-*`s2` = > json.get value=`esc` key=s2 *
+*q = > json.quote text=`goal`*
+*esc = > json.parse text={"h":"---\ntitle: agent workbook\nimport llm:ext/ai/llm.mq.md\nimport agent:ext/ai/agent.mq.md\nimport json:lib/json.mq.md\nimport sys:lib/sys.mq.md\nimport writeback:lib/writeback.mq.md\nimport subtask:lib/subtask.mq.md\n---\n\n# Goal\n\nParent goal is embedded as JSON in # main.\n\n## Solidify\n\nWhen the child returns a good value, parent DECISION: DONE — runtime agent_workbook_solidify freezes the answer as **return** (do not invent long FIND/REPLACE).\n\n# main\n\n> llm.load_env\n\n","s1":"\u002a\u0060model\u0060 = > llm.llm \u002a\n","s2":"\u002a\u0060tools\u0060 = > json.parse text=[] \u002a\n","s3":"\u002a\u0060worker\u0060 = > agent.agent model=\u0060model\u0060 tools=\u0060tools\u0060 standing=You are a workbook worker. tools=[] means never CALL. Finish the task with a direct final answer; do not invent tools. \u002a\n","s4":"\u002a\u0060wrap\u0060 = > json.parse text={\"task\":","s5":"} \u002a\n","s6":"\u002a\u0060task\u0060 = > json.get value=\u0060wrap\u0060 key=task \u002a\n","s7":"\u002a\u0060out\u0060 = > \u0060worker\u0060.step task=\u0060task\u0060 stream=True \u002a\n","s7b":"\u002a\u0060text\u0060 = > json.get value=\u0060out\u0060 key=result \u002a\n","s8":"\u002a\u002a\u0060text\u0060\u002a\u002a\n","d3":"\u002a\u0060research\u0060 = > agent.agent model=\u0060model\u0060 tools=\u0060tools\u0060 standing=You gather facts for the goal. Be concise. Do not invent tools. \u002a\n","d3b":"\u002a\u0060writer\u0060 = > agent.agent model=\u0060model\u0060 tools=\u0060tools\u0060 standing=You write the final answer from research notes. Do not invent tools. \u002a\n","d4":"\u002a\u0060wrap\u0060 = > json.parse text={\"task\":","d5":"} \u002a\n","d6":"\u002a\u0060task\u0060 = > json.get value=\u0060wrap\u0060 key=task \u002a\n","d7":"\u002a\u0060notes\u0060 = > \u0060research\u0060.step task=\u0060task\u0060 stream=True \u002a\n","d8":"\u002a\u0060ns\u0060 = > json.stringify value=\u0060notes\u0060 \u002a\n","d9":"\u002a\u0060wt\u0060 = Write the final answer. Research notes: \u002a\n","d10":"\u002a\u0060wt\u0060 = \u0060wt\u0060 + \u0060ns\u0060 \u002a\n","d11":"\u002a\u0060out\u0060 = > \u0060writer\u0060.step task=\u0060wt\u0060 stream=True \u002a\n","d11b":"\u002a\u0060text\u0060 = > json.get value=\u0060out\u0060 key=result \u002a\n","d12":"\u002a\u002a\u0060text\u0060\u002a\u002a\n"}*
+*h = > json.get value=`esc` key="h"*
+*s1 = > json.get value=`esc` key="s1"*
+*s2 = > json.get value=`esc` key="s2"*
1. `skeleton` == dual
- *`s3` = > json.get value=`esc` key=d3 *
- *`s3b` = > json.get value=`esc` key=d3b *
- *`s4` = > json.get value=`esc` key=d4 *
- *`s5` = > json.get value=`esc` key=d5 *
- *`s6` = > json.get value=`esc` key=d6 *
- *`s7` = > json.get value=`esc` key=d7 *
- *`s8` = > json.get value=`esc` key=d8 *
- *`s9` = > json.get value=`esc` key=d9 *
- *`s10` = > json.get value=`esc` key=d10 *
- *`s11` = > json.get value=`esc` key=d11 *
- *`s11b` = > json.get value=`esc` key=d11b *
- *`s12` = > json.get value=`esc` key=d12 *
- **`h` + `s1` + `s2` + `s3` + `s3b` + `s4` + `q` + `s5` + `s6` + `s7` + `s8` + `s9` + `s10` + `s11` + `s11b` + `s12`**
+ *s3 = > json.get value=`esc` key="d3"*
+ *s3b = > json.get value=`esc` key="d3b"*
+ *s4 = > json.get value=`esc` key="d4"*
+ *s5 = > json.get value=`esc` key="d5"*
+ *s6 = > json.get value=`esc` key="d6"*
+ *s7 = > json.get value=`esc` key="d7"*
+ *s8 = > json.get value=`esc` key="d8"*
+ *s9 = > json.get value=`esc` key="d9"*
+ *s10 = > json.get value=`esc` key="d10"*
+ *s11 = > json.get value=`esc` key="d11"*
+ *s11b = > json.get value=`esc` key="d11b"*
+ *s12 = > json.get value=`esc` key="d12"*
+ **h + s1 + s2 + s3 + s3b + s4 + q + s5 + s6 + s7 + s8 + s9 + s10 + s11 + s11b + s12**
2. *
- *`s3` = > json.get value=`esc` key=s3 *
- *`s4` = > json.get value=`esc` key=s4 *
- *`s5` = > json.get value=`esc` key=s5 *
- *`s6` = > json.get value=`esc` key=s6 *
- *`s7` = > json.get value=`esc` key=s7 *
- *`s7b` = > json.get value=`esc` key=s7b *
- *`s8` = > json.get value=`esc` key=s8 *
- **`h` + `s1` + `s2` + `s3` + `s4` + `q` + `s5` + `s6` + `s7` + `s7b` + `s8`**
+ *s3 = > json.get value=`esc` key="s3"*
+ *s4 = > json.get value=`esc` key="s4"*
+ *s5 = > json.get value=`esc` key="s5"*
+ *s6 = > json.get value=`esc` key="s6"*
+ *s7 = > json.get value=`esc` key="s7"*
+ *s7b = > json.get value=`esc` key="s7b"*
+ *s8 = > json.get value=`esc` key="s8"*
+ **h + s1 + s2 + s3 + s4 + q + s5 + s6 + s7 + s7b + s8**
---
@@ -140,49 +140,49 @@ Build a runnable workbook. `skeleton=single` (default): one worker `step`. `skel
Structured observation for the parent developer-agent: source, named writeback slots, exit code, optional child return value, and quiet-captured I/O.
-*`source` = > fs.read_text path=`path` *
-*`slots` = > writeback.scan_path path=`path` *
-*`obs` = > json.parse text={"path":""} *
-*`obs` = > json.set map=`obs` key=path value=`path` *
-*`obs` = > json.set map=`obs` key=source value=`source` *
-*`obs` = > json.set map=`obs` key=slots value=`slots` *
-*`obs` = > json.set map=`obs` key=exit_code value=`exit_code` *
+*source = > fs.read_text path=`path`*
+*slots = > writeback.scan_path path=`path`*
+*obs = > json.parse text={"path":""}*
+*obs = > json.set map=`obs` key="path" value=`path`*
+*obs = > json.set map=`obs` key="source" value=`source`*
+*obs = > json.set map=`obs` key="slots" value=`slots`*
+*obs = > json.set map=`obs` key="exit_code" value=`exit_code`*
1. `value`
- *`obs` = > json.set map=`obs` key=value value=`value` *
+ *obs = > json.set map=`obs` key="value" value=`value`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `stdout`
- *`obs` = > json.set map=`obs` key=stdout value=`stdout` *
+ *obs = > json.set map=`obs` key="stdout" value=`stdout`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `stderr`
- *`obs` = > json.set map=`obs` key=stderr value=`stderr` *
+ *obs = > json.set map=`obs` key="stderr" value=`stderr`*
2. *
- *`_` = 1*
+ *_ = 1*
-*`last_ok` = None*
-*`last_error` = None*
+*last_ok = None*
+*last_error = None*
- [`slot`](`slots`)
- *`k` = > json.get value=`slot` key=key *
- *`body` = > json.get value=`slot` key=body *
+ *k = > json.get value=`slot` key="key"*
+ *body = > json.get value=`slot` key="body"*
1. `k` == ok
- *`last_ok` = `body`*
+ *last_ok = body*
2. `k` == error
- *`last_error` = `body`*
+ *last_error = body*
3. *
- *`_` = 1*
+ *_ = 1*
1. `last_ok`
- *`obs` = > json.set map=`obs` key=last_ok value=`last_ok` *
+ *obs = > json.set map=`obs` key="last_ok" value=`last_ok`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `last_error`
- *`obs` = > json.set map=`obs` key=last_error value=`last_error` *
+ *obs = > json.set map=`obs` key="last_error" value=`last_error`*
2. *
- *`_` = 1*
+ *_ = 1*
-**`obs`**
+**obs**
---
@@ -191,18 +191,18 @@ Structured observation for the parent developer-agent: source, named writeback s
Spawn a workbook file (quiet by default), wait for `{code,value,stdout?,stderr?}`, and inspect.
-*`id` = > subtask.spawn path=`path` *
-*`waited` = > subtask.wait id=`id` *
-*`code` = > json.get value=`waited` key=code *
-*`value` = > json.get value=`waited` key=value *
-*`stdout` = > json.get value=`waited` key=stdout *
-*`stderr` = > json.get value=`waited` key=stderr *
-*`obs` = > inspect_workbook path=`path` exit_code=`code` value=`value` stdout=`stdout` stderr=`stderr` *
-*`out` = > json.parse text={"code":0} *
-*`out` = > json.set map=`out` key=code value=`code` *
-*`out` = > json.set map=`out` key=value value=`value` *
-*`out` = > json.set map=`out` key=observation value=`obs` *
-**`out`**
+*id = > subtask.spawn path=`path`*
+*waited = > subtask.wait id=`id`*
+*code = > json.get value=`waited` key="code"*
+*value = > json.get value=`waited` key="value"*
+*stdout = > json.get value=`waited` key="stdout"*
+*stderr = > json.get value=`waited` key="stderr"*
+*obs = > inspect_workbook path=`path` exit_code=`code` value=`value` stdout=`stdout` stderr=`stderr`*
+*out = > json.parse text={"code":0}*
+*out = > json.set map=`out` key="code" value=`code`*
+*out = > json.set map=`out` key="value" value=`value`*
+*out = > json.set map=`out` key="observation" value=`obs`*
+**out**
---
@@ -211,25 +211,25 @@ Spawn a workbook file (quiet by default), wait for `{code,value,stdout?,stderr?}
+ `max_lines`=80
+ `max_chars`=4000
-*`esc` = > json.parse text={"nl":"\n"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`raw` = > str value=`text` *
-*`lines` = > split value=`raw` sep=`nl` *
-*`acc` = > json.parse text=[] *
-*`chars` = 0*
-*`count` = 0*
+*esc = > json.parse text={"nl":"\n"}*
+*nl = > json.get value=`esc` key="nl"*
+*raw = > str value=`text`*
+*lines = > split value=`raw` sep=`nl`*
+*acc = > json.parse text=[]*
+*chars = 0*
+*count = 0*
- [`line`](`lines`)
1. `count` < `max_lines`
- *`ln` = > len value=`line` *
- *`next` = `chars` + `ln` *
+ *ln = > len value=`line`*
+ *next = chars + ln*
1. `next` > `max_chars`
- *`count` = `max_lines`*
+ *count = max_lines*
2. *
- *`acc` = > json.append list=`acc` item=`line` *
- *`chars` = `next`*
- *`count` = `count` + 1*
+ *acc = > json.append list=`acc` item=`line`*
+ *chars = next*
+ *count = count + 1*
2. *
- *`_` = 1*
+ *_ = 1*
**> join value=`acc` sep=`nl`**
---
@@ -239,31 +239,31 @@ Spawn a workbook file (quiet by default), wait for `{code,value,stdout?,stderr?}
+ `max_lines`=40
+ `max_chars`=2000
-*`esc` = > json.parse text={"nl":"\n"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`raw` = > str value=`text` *
-*`lines` = > split value=`raw` sep=`nl` *
-*`n` = > len value=`lines` *
-*`start` = `n` - `max_lines` *
+*esc = > json.parse text={"nl":"\n"}*
+*nl = > json.get value=`esc` key="nl"*
+*raw = > str value=`text`*
+*lines = > split value=`raw` sep=`nl`*
+*n = > len value=`lines`*
+*start = n - max_lines*
1. `start` < 0
- *`start` = 0*
+ *start = 0*
2. *
- *`_` = 1*
-*`acc` = > json.parse text=[] *
-*`i` = 0*
-*`chars` = 0*
+ *_ = 1*
+*acc = > json.parse text=[]*
+*i = 0*
+*chars = 0*
- [`line`](`lines`)
1. `i` >= `start`
- *`ln` = > len value=`line` *
- *`next` = `chars` + `ln` *
+ *ln = > len value=`line`*
+ *next = chars + ln*
1. `next` > `max_chars`
- *`i` = `n`*
+ *i = n*
2. *
- *`acc` = > json.append list=`acc` item=`line` *
- *`chars` = `next`*
+ *acc = > json.append list=`acc` item=`line`*
+ *chars = next*
2. *
- *`_` = 1*
- *`i` = `i` + 1*
+ *_ = 1*
+ *i = i + 1*
**> join value=`acc` sep=`nl`**
---
@@ -273,39 +273,39 @@ Spawn a workbook file (quiet by default), wait for `{code,value,stdout?,stderr?}
Drop `` blocks (including marqdo-out bodies) so parent excerpts stay structural.
-*`esc` = > json.parse text={"nl":"\n"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`raw` = > str value=`text` *
-*`lines` = > split value=`raw` sep=`nl` *
-*`acc` = > json.parse text=[] *
-*`skip` = None*
+*esc = > json.parse text={"nl":"\n"}*
+*nl = > json.get value=`esc` key="nl"*
+*raw = > str value=`text`*
+*lines = > split value=`raw` sep=`nl`*
+*acc = > json.parse text=[]*
+*skip = None*
- [`line`](`lines`)
1. `skip`
- *`end_parts` = > split value=`line` sep=--> *
- *`en` = > len value=`end_parts` *
+ *end_parts = > split value=`line` sep="-->"*
+ *en = > len value=`end_parts`*
1. `en` > 1
- *`skip` = None*
+ *skip = None*
2. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`start_parts` = > split value=`line` sep= *
- *`en` = > len value=`end_parts` *
+ *_ = 1*
+ *tail = > at value=`start_parts` index=1*
+ *end_parts = > split value=`tail` sep="-->"*
+ *en = > len value=`end_parts`*
1. `en` > 1
- *`skip` = None*
+ *skip = None*
2. *
- *`skip` = 1*
+ *skip = 1*
2. *
- *`acc` = > json.append list=`acc` item=`line` *
+ *acc = > json.append list=`acc` item=`line`*
**> join value=`acc` sep=`nl`**
---
@@ -315,7 +315,7 @@ Drop `` blocks (including marqdo-out bodies) so parent excerpts stay
+ `max_lines`=80
+ `max_chars`=4000
-*`clean` = > strip_html_comments text=`source` *
+*clean = > strip_html_comments text=`source`*
**> text_head_lines text=`clean` max_lines=`max_lines` max_chars=`max_chars`**
---
@@ -325,7 +325,7 @@ Drop `` blocks (including marqdo-out bodies) so parent excerpts stay
+ `max_lines`=80
+ `max_chars`=4000
-*`src` = > fs.read_text path=`path` *
+*src = > fs.read_text path=`path`*
**> workbook_source_excerpt source=`src` max_lines=`max_lines` max_chars=`max_chars`**
---
@@ -334,7 +334,7 @@ Drop `` blocks (including marqdo-out bodies) so parent excerpts stay
+ `path`
+ `depth`=default
-*`src` = > fs.read_text path=`path` *
+*src = > fs.read_text path=`path`*
1. `depth` == deep
**> workbook_source_excerpt source=`src` max_lines=200 max_chars=12000**
2. *
@@ -346,8 +346,8 @@ Drop `` blocks (including marqdo-out bodies) so parent excerpts stay
Callable dotted names (whitelist for `CALL:lib…`) plus static module file list for workbook imports.
-*`out` = > json.parse text={"note":"Direct CALL:lib.. + optional ARGS:{json} for whitelist only. Or import via frontmatter > lib/.mq.md then PATCH / scratch_tool_write.","files":["fs.mq.md","json.mq.md","subtask.mq.md","sys.mq.md","writeback.mq.md","text.mq.md","time.mq.md","math.mq.md","net.mq.md","table.mq.md","plugin.mq.md","foreign.mq.md"],"callable":[{"name":"lib.fs.read_text","desc":"Read UTF-8 text file"},{"name":"lib.fs.exists","desc":"Path exists?"},{"name":"lib.fs.list_dir","desc":"List directory entries"},{"name":"lib.json.parse","desc":"Parse JSON text"},{"name":"lib.json.stringify","desc":"Serialize JSON"},{"name":"lib.sys.cwd","desc":"Process working directory"}]} *
-**`out`**
+*out = > json.parse text={"note":"Direct CALL:lib.. + optional ARGS:{json} for whitelist only. Or import via frontmatter > lib/.mq.md then PATCH / scratch_tool_write.","files":["fs.mq.md","json.mq.md","subtask.mq.md","sys.mq.md","writeback.mq.md","text.mq.md","time.mq.md","math.mq.md","net.mq.md","table.mq.md","plugin.mq.md","foreign.mq.md"],"callable":[{"name":"lib.fs.read_text","desc":"Read UTF-8 text file"},{"name":"lib.fs.exists","desc":"Path exists?"},{"name":"lib.fs.list_dir","desc":"List directory entries"},{"name":"lib.json.parse","desc":"Parse JSON text"},{"name":"lib.json.stringify","desc":"Serialize JSON"},{"name":"lib.sys.cwd","desc":"Process working directory"}]}*
+**out**
---
@@ -356,42 +356,42 @@ Callable dotted names (whitelist for `CALL:lib…`) plus static module file list
Parse `ARGS:{…}` JSON line, or a bare `{…}` line after CALL.
-*`esc` = > json.parse text={"nl":"\n","mark":"ARGS:","brace":"{"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`mark` = > json.get value=`esc` key=mark *
-*`brace` = > json.get value=`esc` key=brace *
-*`empty` = > json.parse text={} *
+*esc = > json.parse text={"nl":"\n","mark":"ARGS:","brace":"{"}*
+*nl = > json.get value=`esc` key="nl"*
+*mark = > json.get value=`esc` key="mark"*
+*brace = > json.get value=`esc` key="brace"*
+*empty = > json.parse text={}*
1. `reply`
- *`text` = > trim value=`reply` *
- *`lines` = > split value=`text` sep=`nl` *
- *`found` = None*
+ *text = > trim value=`reply`*
+ *lines = > split value=`text` sep=`nl`*
+ *found = None*
- [`line`](`lines`)
1. `found`
- *`_` = 1*
+ *_ = 1*
2. *
- *`t` = > trim value=`line` *
- *`chunks` = > split value=`t` sep=`mark` *
- *`cn` = > len value=`chunks` *
+ *t = > trim value=`line`*
+ *chunks = > split value=`t` sep=`mark`*
+ *cn = > len value=`chunks`*
1. `cn` > 1
- *`rest` = > at value=`chunks` index=1 *
- *`found` = > trim value=`rest` *
+ *rest = > at value=`chunks` index=1*
+ *found = > trim value=`rest`*
2. *
- *`chunks` = > split value=`t` sep=`brace` *
- *`cn` = > len value=`chunks` *
- *`prefix` = > at value=`chunks` index=0 *
+ *chunks = > split value=`t` sep=`brace`*
+ *cn = > len value=`chunks`*
+ *prefix = > at value=`chunks` index=0*
1. `cn` > 1
1. `prefix`
- *`_` = 1*
+ *_ = 1*
2. *
- *`found` = `t`*
+ *found = t*
2. *
- *`_` = 1*
+ *_ = 1*
1. `found`
**> json.parse text=`found`**
2. *
- **`empty`**
+ **empty**
2. *
- **`empty`**
+ **empty**
---
@@ -402,7 +402,7 @@ Parse `ARGS:{…}` JSON line, or a bare `{…}` line after CALL.
Truncate a tool result for `tool_end` events (~1KiB).
1. `value`
- *`s` = > json.stringify value=`value` *
+ *s = > json.stringify value=`value`*
**> text_head_lines text=`s` max_lines=40 max_chars=`max_chars`**
2. *
****
@@ -420,20 +420,20 @@ Truncate a tool result for `tool_end` events (~1KiB).
Publish `tool_start` / `tool_end` when `stream=True`.
1. `stream`
- *`ev` = > json.parse text={} *
- *`ev` = > json.set map=`ev` key=type value=`type` *
- *`ev` = > json.set map=`ev` key=name value=`name` *
- *`ev` = > json.set map=`ev` key=kind value=`kind` *
+ *ev = > json.parse text={}*
+ *ev = > json.set map=`ev` key="type" value=`type`*
+ *ev = > json.set map=`ev` key="name" value=`name`*
+ *ev = > json.set map=`ev` key="kind" value=`kind`*
1. `result`
- *`ev` = > json.set map=`ev` key=result value=`result` *
+ *ev = > json.set map=`ev` key="result" value=`result`*
2. *
- *`_` = 1*
- *`events` = > json.append list=`events` item=`ev` *
+ *_ = 1*
+ *events = > json.append list=`events` item=`ev`*
> sys.stream_publish event=`ev`
2. *
- *`_` = 1*
+ *_ = 1*
-**`events`**
+**events**
---
@@ -443,29 +443,29 @@ Publish `tool_start` / `tool_end` when `stream=True`.
Whitelist `CALL:lib..` (+ ARGS). Rejects net/exec/write/delete.
-*`args` = > extract_call_args reply=`reply` *
-*`errs` = > json.parse text={"deny":"Lib CALL not allowed: "} *
+*args = > extract_call_args reply=`reply`*
+*errs = > json.parse text={"deny":"Lib CALL not allowed: "}*
1. `name` == lib.fs.exists
- *`path` = > json.get value=`args` key=path *
+ *path = > json.get value=`args` key="path"*
**> fs.exists path=`path`**
2. `name` == lib.fs.read_text
- *`path` = > json.get value=`args` key=path *
+ *path = > json.get value=`args` key="path"*
**> fs.read_text path=`path`**
3. `name` == lib.fs.list_dir
- *`path` = > json.get value=`args` key=path *
+ *path = > json.get value=`args` key="path"*
**> fs.list_dir path=`path`**
4. `name` == lib.json.parse
- *`text` = > json.get value=`args` key=text *
+ *text = > json.get value=`args` key="text"*
**> json.parse text=`text`**
5. `name` == lib.json.stringify
- *`value` = > json.get value=`args` key=value *
+ *value = > json.get value=`args` key="value"*
**> json.stringify value=`value`**
6. `name` == lib.sys.cwd
**> sys.cwd**
7. *
- *`deny` = > json.get value=`errs` key=deny *
- **`deny` + `name`**
+ *deny = > json.get value=`errs` key="deny"*
+ **deny + name**
---
@@ -475,23 +475,23 @@ Whitelist `CALL:lib..` (+ ARGS). Rejects net/exec/write/delete.
Write a scratch tool workbook under `.marqdo/agent-runs/tools/.mq.md`.
-*`esc` = > json.parse text={"a":".marqdo/agent-runs/tools/","b":".mq.md"} *
-*`a` = > json.get value=`esc` key=a *
-*`b` = > json.get value=`esc` key=b *
-*`dir` = ".marqdo/agent-runs/tools" *
+*esc = > json.parse text={"a":".marqdo/agent-runs/tools/","b":".mq.md"}*
+*a = > json.get value=`esc` key="a"*
+*b = > json.get value=`esc` key="b"*
+*dir = ".marqdo/agent-runs/tools"*
> fs.make_dir path=`dir`
-*`path` = `a` + `name` + `b` *
+*path = a + name + b*
> fs.write_text path=`path` text=`text`
-*`out` = > json.parse text={"ok":True} *
-*`out` = > json.set map=`out` key=path value=`path` *
-**`out`**
+*out = > json.parse text={"ok":True}*
+*out = > json.set map=`out` key="path" value=`path`*
+**out**
---
## skill_brief
+ `max_chars`=1200
-*`skill` = > agent_marqdo_skill *
+*skill = > agent_marqdo_skill*
**> text_head_lines text=`skill` max_lines=40 max_chars=`max_chars`**
---
@@ -501,44 +501,44 @@ Write a scratch tool workbook under `.marqdo/agent-runs/tools/.mq.md`.
Parse READ:source|stderr|stdout|slots (Chinese: 读取:…).
-*`esc` = > json.parse text={"nl":"\n","fw":":"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`fw` = > json.get value=`esc` key=fw *
-*`text` = > trim value=`reply` *
-*`lines` = > split value=`text` sep=`nl` *
-*`found` = None*
+*esc = > json.parse text={"nl":"\n","fw":":"}*
+*nl = > json.get value=`esc` key="nl"*
+*fw = > json.get value=`esc` key="fw"*
+*text = > trim value=`reply`*
+*lines = > split value=`text` sep=`nl`*
+*found = None*
- [`line`](`lines`)
- *`t` = > trim value=`line` *
- *`parts` = > split value=`t` sep=: *
- *`n` = > len value=`parts` *
+ *t = > trim value=`line`*
+ *parts = > split value=`t` sep=":"*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == READ
- *`found` = `rest`*
+ *found = rest*
2. `head` == 读取
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`parts` = > split value=`t` sep=`fw` *
- *`n` = > len value=`parts` *
+ *parts = > split value=`t` sep=`fw`*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == 读取
- *`found` = `rest`*
+ *found = rest*
2. `head` == READ
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
-**`found`**
+ *_ = 1*
+**found**
---
@@ -547,28 +547,28 @@ Parse READ:source|stderr|stdout|slots (Chinese: 读取:…).
Priority: CALL → READ → DECISION. Returns `{kind,name}`.
-*`tool` = > extract_tool_name reply=`reply` *
+*tool = > extract_tool_name reply=`reply`*
1. `tool`
- *`out` = > json.parse text={"kind":"call"} *
- *`out` = > json.set map=`out` key=name value=`tool` *
- **`out`**
+ *out = > json.parse text={"kind":"call"}*
+ *out = > json.set map=`out` key="name" value=`tool`*
+ **out**
2. *
- *`_` = 1*
-*`rk` = > extract_plan_read reply=`reply` *
+ *_ = 1*
+*rk = > extract_plan_read reply=`reply`*
1. `rk`
- *`out` = > json.parse text={"kind":"read"} *
- *`out` = > json.set map=`out` key=name value=`rk` *
- **`out`**
+ *out = > json.parse text={"kind":"read"}*
+ *out = > json.set map=`out` key="name" value=`rk`*
+ **out**
2. *
- *`_` = 1*
-*`dec` = > extract_plan_decision reply=`reply` *
+ *_ = 1*
+*dec = > extract_plan_decision reply=`reply`*
1. `dec`
- *`out` = > json.parse text={"kind":"decision"} *
- *`out` = > json.set map=`out` key=name value=`dec` *
- **`out`**
+ *out = > json.parse text={"kind":"decision"}*
+ *out = > json.set map=`out` key="name" value=`dec`*
+ **out**
2. *
- *`out` = > json.parse text={"kind":"unknown"} *
- **`out`**
+ *out = > json.parse text={"kind":"unknown"}*
+ **out**
---
@@ -577,48 +577,48 @@ Priority: CALL → READ → DECISION. Returns `{kind,name}`.
Parse NAME: id plus a triple-angle body after CALL:scratch_tool_write.
-*`esc` = > json.parse text={"nl":"\n","open":"<<<","close":">>>"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`open` = > json.get value=`esc` key=open *
-*`close` = > json.get value=`esc` key=close *
-*`text` = > trim value=`reply` *
-*`lines` = > split value=`text` sep=`nl` *
-*`name` = None*
-*`body_lines` = > json.parse text=[] *
-*`in_body` = None*
+*esc = > json.parse text={"nl":"\n","open":"<<<","close":">>>"}*
+*nl = > json.get value=`esc` key="nl"*
+*open = > json.get value=`esc` key="open"*
+*close = > json.get value=`esc` key="close"*
+*text = > trim value=`reply`*
+*lines = > split value=`text` sep=`nl`*
+*name = None*
+*body_lines = > json.parse text=[]*
+*in_body = None*
- [`line`](`lines`)
1. `in_body`
- *`t` = > trim value=`line` *
+ *t = > trim value=`line`*
1. `t` == `close`
- *`in_body` = None*
+ *in_body = None*
2. *
- *`body_lines` = > json.append list=`body_lines` item=`line` *
+ *body_lines = > json.append list=`body_lines` item=`line`*
2. *
- *`t` = > trim value=`line` *
- *`parts` = > split value=`t` sep=: *
- *`n` = > len value=`parts` *
+ *t = > trim value=`line`*
+ *parts = > split value=`t` sep=":"*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == NAME
- *`name` = `rest`*
+ *name = rest*
2. `head` == 名称
- *`name` = `rest`*
+ *name = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
1. `t` == `open`
- *`in_body` = 1*
+ *in_body = 1*
2. *
- *`_` = 1*
-*`body` = > join value=`body_lines` sep=`nl` *
-*`out` = > json.parse text={} *
-*`out` = > json.set map=`out` key=name value=`name` *
-*`out` = > json.set map=`out` key=text value=`body` *
-**`out`**
+ *_ = 1*
+*body = > join value=`body_lines` sep=`nl`*
+*out = > json.parse text={}*
+*out = > json.set map=`out` key="name" value=`name`*
+*out = > json.set map=`out` key="text" value=`body`*
+**out**
---
@@ -631,31 +631,31 @@ Parse NAME: id plus a triple-angle body after CALL:scratch_tool_write.
Parent Plan-and-Move tools (helpers + whitelist `CALL:lib…`).
1. `name` == workbook_read
- **> workbook_read path=`path` depth=deep**
+ **> workbook_read path=`path` depth="deep"**
2. `name` == workbook_excerpt
**> workbook_excerpt path=`path`**
3. `name` == lib_catalog
**> lib_catalog**
4. `name` == scratch_tool_write
- *`parsed` = > extract_scratch_tool reply=`reply` *
- *`tn` = > json.get value=`parsed` key=name *
- *`tt` = > json.get value=`parsed` key=text *
- *`errs` = > json.parse text={"a":"scratch_tool_write needs NAME line and fenced body","b":"scratch_tool_write needs NAME id"} *
+ *parsed = > extract_scratch_tool reply=`reply`*
+ *tn = > json.get value=`parsed` key="name"*
+ *tt = > json.get value=`parsed` key="text"*
+ *errs = > json.parse text={"a":"scratch_tool_write needs NAME line and fenced body","b":"scratch_tool_write needs NAME id"}*
1. `tn`
1. `tt`
**> scratch_tool_write name=`tn` text=`tt`**
2. *
- **> json.get value=`errs` key=a**
+ **> json.get value=`errs` key="a"**
2. *
- **> json.get value=`errs` key=b**
+ **> json.get value=`errs` key="b"**
5. *
- *`dots` = > split value=`name` sep=. *
- *`head` = > at value=`dots` index=0 *
+ *dots = > split value=`name` sep=".*"*
+ *head = > at value=`dots` index=0*
1. `head` == lib
**> run_lib_call name=`name` reply=`reply`**
2. *
- *`msg` = "Parent tool not allowed:" *
- **`msg` + `name`**
+ *msg = "Parent tool not allowed:"*
+ **msg + name**
---
@@ -664,28 +664,28 @@ Parent Plan-and-Move tools (helpers + whitelist `CALL:lib…`).
+ `kind`
+ `path`
-*`obs` = `observation` *
+*obs = observation*
1. `kind` == source
- *`ex` = > workbook_read path=`path` depth=deep *
- *`obs` = > json.set map=`obs` key=source_excerpt value=`ex` *
- *`obs` = > json.set map=`obs` key=read_source value=True *
+ *ex = > workbook_read path=`path` depth="deep"*
+ *obs = > json.set map=`obs` key="source_excerpt" value=`ex`*
+ *obs = > json.set map=`obs` key="read_source" value=True*
2. `kind` == stderr
- *`err` = > json.get value=`obs` key=stderr *
- *`tail` = > text_tail_lines text=`err` max_lines=80 max_chars=6000 *
- *`obs` = > json.set map=`obs` key=stderr_tail value=`tail` *
- *`obs` = > json.set map=`obs` key=read_stderr value=True *
+ *err = > json.get value=`obs` key="stderr"*
+ *tail = > text_tail_lines text=`err` max_lines=80 max_chars=6000*
+ *obs = > json.set map=`obs` key="stderr_tail" value=`tail`*
+ *obs = > json.set map=`obs` key="read_stderr" value=True*
3. `kind` == stdout
- *`out` = > json.get value=`obs` key=stdout *
- *`tail` = > text_tail_lines text=`out` max_lines=80 max_chars=6000 *
- *`obs` = > json.set map=`obs` key=stdout_tail value=`tail` *
- *`obs` = > json.set map=`obs` key=read_stdout value=True *
+ *out = > json.get value=`obs` key="stdout"*
+ *tail = > text_tail_lines text=`out` max_lines=80 max_chars=6000*
+ *obs = > json.set map=`obs` key="stdout_tail" value=`tail`*
+ *obs = > json.set map=`obs` key="read_stdout" value=True*
4. `kind` == slots
- *`slots` = > json.get value=`obs` key=slots *
- *`obs` = > json.set map=`obs` key=slots_detail value=`slots` *
- *`obs` = > json.set map=`obs` key=read_slots value=True *
+ *slots = > json.get value=`obs` key="slots"*
+ *obs = > json.set map=`obs` key="slots_detail" value=`slots`*
+ *obs = > json.set map=`obs` key="read_slots" value=True*
5. *
- *`_` = 1*
-**`obs`**
+ *_ = 1*
+**obs**
---
@@ -694,124 +694,124 @@ Parent Plan-and-Move tools (helpers + whitelist `CALL:lib…`).
Bounded observation for the parent prompt (actionable, short).
-*`obs_path` = > json.get value=`observation` key=path *
-*`obs_code` = > json.get value=`observation` key=exit_code *
-*`obs_val` = > json.get value=`observation` key=value *
-*`obs_slots` = > json.get value=`observation` key=slots *
-*`obs_src` = > json.get value=`observation` key=source *
-*`obs_stdout` = > json.get value=`observation` key=stdout *
-*`obs_stderr` = > json.get value=`observation` key=stderr *
-*`src_len` = 0*
-*`has_step` = False*
+*obs_path = > json.get value=`observation` key="path"*
+*obs_code = > json.get value=`observation` key="exit_code"*
+*obs_val = > json.get value=`observation` key="value"*
+*obs_slots = > json.get value=`observation` key="slots"*
+*obs_src = > json.get value=`observation` key="source"*
+*obs_stdout = > json.get value=`observation` key="stdout"*
+*obs_stderr = > json.get value=`observation` key="stderr"*
+*src_len = 0*
+*has_step = False*
1. `obs_src`
- *`src_len` = > len value=`obs_src` *
- *`step_parts` = > split value=`obs_src` sep=worker.step *
- *`n_step` = > len value=`step_parts` *
+ *src_len = > len value=`obs_src`*
+ *step_parts = > split value=`obs_src` sep="worker.step"*
+ *n_step = > len value=`step_parts`*
1. `n_step` > 1
- *`has_step` = True*
+ *has_step = True*
2. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
-*`compact` = > json.parse text={"note":"Plan-and-Move: CALL/READ then DECISION. Success (exit 0 + has_value) → DONE. solidify_on_done. No long prose."} *
-*`compact` = > json.set map=`compact` key=path value=`obs_path` *
-*`compact` = > json.set map=`compact` key=exit_code value=`obs_code` *
-*`compact` = > json.set map=`compact` key=source_len value=`src_len` *
-*`compact` = > json.set map=`compact` key=has_worker_step value=`has_step` *
-*`compact` = > json.set map=`compact` key=solidify_on_done value=True *
+*compact = > json.parse text={"note":"Plan-and-Move: CALL/READ then DECISION. Success (exit 0 + has_value) → DONE. solidify_on_done. No long prose."}*
+*compact = > json.set map=`compact` key="path" value=`obs_path`*
+*compact = > json.set map=`compact` key="exit_code" value=`obs_code`*
+*compact = > json.set map=`compact` key="source_len" value=`src_len`*
+*compact = > json.set map=`compact` key="has_worker_step" value=`has_step`*
+*compact = > json.set map=`compact` key="solidify_on_done" value=True*
1. `obs_src`
- *`ex` = > json.get value=`observation` key=source_excerpt *
+ *ex = > json.get value=`observation` key="source_excerpt"*
1. `ex`
- *`compact` = > json.set map=`compact` key=source_excerpt value=`ex` *
+ *compact = > json.set map=`compact` key="source_excerpt" value=`ex`*
2. *
- *`ex` = > workbook_source_excerpt source=`obs_src` *
- *`compact` = > json.set map=`compact` key=source_excerpt value=`ex` *
+ *ex = > workbook_source_excerpt source=`obs_src`*
+ *compact = > json.set map=`compact` key="source_excerpt" value=`ex`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `obs_stderr`
- *`tail` = > json.get value=`observation` key=stderr_tail *
+ *tail = > json.get value=`observation` key="stderr_tail"*
1. `tail`
- *`compact` = > json.set map=`compact` key=stderr_tail value=`tail` *
+ *compact = > json.set map=`compact` key="stderr_tail" value=`tail`*
2. *
- *`tail` = > text_tail_lines text=`obs_stderr` *
- *`compact` = > json.set map=`compact` key=stderr_tail value=`tail` *
+ *tail = > text_tail_lines text=`obs_stderr`*
+ *compact = > json.set map=`compact` key="stderr_tail" value=`tail`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `obs_stdout`
- *`tail` = > json.get value=`observation` key=stdout_tail *
+ *tail = > json.get value=`observation` key="stdout_tail"*
1. `tail`
- *`compact` = > json.set map=`compact` key=stdout_tail value=`tail` *
+ *compact = > json.set map=`compact` key="stdout_tail" value=`tail`*
2. *
- *`tail` = > text_tail_lines text=`obs_stdout` *
- *`compact` = > json.set map=`compact` key=stdout_tail value=`tail` *
+ *tail = > text_tail_lines text=`obs_stdout`*
+ *compact = > json.set map=`compact` key="stdout_tail" value=`tail`*
2. *
- *`_` = 1*
+ *_ = 1*
-*`val_txt` = > str value=`obs_val` *
-*`val_len` = > len value=`val_txt` *
+*val_txt = > str value=`obs_val`*
+*val_len = > len value=`val_txt`*
1. `obs_val`
- *`compact` = > json.set map=`compact` key=has_value value=True *
- *`compact` = > json.set map=`compact` key=value_len value=`val_len` *
+ *compact = > json.set map=`compact` key="has_value" value=True*
+ *compact = > json.set map=`compact` key="value_len" value=`val_len`*
1. `val_len` > 200
- *`preview` = > text_head_lines text=`val_txt` max_lines=4 max_chars=200 *
- *`compact` = > json.set map=`compact` key=value_preview value=`preview` *
+ *preview = > text_head_lines text=`val_txt` max_lines=4 max_chars=200*
+ *compact = > json.set map=`compact` key="value_preview" value=`preview`*
2. *
- *`compact` = > json.set map=`compact` key=value value=`obs_val` *
+ *compact = > json.set map=`compact` key="value" value=`obs_val`*
2. *
- *`compact` = > json.set map=`compact` key=has_value value=False *
+ *compact = > json.set map=`compact` key="has_value" value=False*
-*`slots_brief` = > json.parse text=[] *
+*slots_brief = > json.parse text=[]*
1. `obs_slots`
- [`slot`](`obs_slots`)
- *`sk` = > json.get value=`slot` key=key *
- *`sl` = > json.get value=`slot` key=line *
- *`sb` = > json.get value=`slot` key=body *
- *`sb_txt` = > str value=`sb` *
- *`sb_len` = > len value=`sb_txt` *
- *`brief` = > json.parse text={"key":""} *
- *`brief` = > json.set map=`brief` key=key value=`sk` *
- *`brief` = > json.set map=`brief` key=line value=`sl` *
- *`brief` = > json.set map=`brief` key=body_len value=`sb_len` *
+ *sk = > json.get value=`slot` key="key"*
+ *sl = > json.get value=`slot` key="line"*
+ *sb = > json.get value=`slot` key="body"*
+ *sb_txt = > str value=`sb`*
+ *sb_len = > len value=`sb_txt`*
+ *brief = > json.parse text={"key":""}*
+ *brief = > json.set map=`brief` key="key" value=`sk`*
+ *brief = > json.set map=`brief` key="line" value=`sl`*
+ *brief = > json.set map=`brief` key="body_len" value=`sb_len`*
1. `sk` == error
- *`prev` = > text_head_lines text=`sb_txt` max_lines=8 max_chars=400 *
- *`brief` = > json.set map=`brief` key=body_preview value=`prev` *
+ *prev = > text_head_lines text=`sb_txt` max_lines=8 max_chars=400*
+ *brief = > json.set map=`brief` key="body_preview" value=`prev`*
2. *
- *`_` = 1*
- *`slots_brief` = > json.append list=`slots_brief` item=`brief` *
+ *_ = 1*
+ *slots_brief = > json.append list=`slots_brief` item=`brief`*
2. *
- *`_` = 1*
-*`compact` = > json.set map=`compact` key=slots value=`slots_brief` *
-*`detail` = > json.get value=`observation` key=slots_detail *
+ *_ = 1*
+*compact = > json.set map=`compact` key="slots" value=`slots_brief`*
+*detail = > json.get value=`observation` key="slots_detail"*
1. `detail`
- *`compact` = > json.set map=`compact` key=slots_detail value=`detail` *
+ *compact = > json.set map=`compact` key="slots_detail" value=`detail`*
2. *
- *`_` = 1*
+ *_ = 1*
-*`tool_result` = > json.get value=`observation` key=tool_result *
+*tool_result = > json.get value=`observation` key="tool_result"*
1. `tool_result`
- *`tr` = > str value=`tool_result` *
- *`tr` = > text_head_lines text=`tr` max_lines=40 max_chars=3000 *
- *`compact` = > json.set map=`compact` key=tool_result value=`tr` *
+ *tr = > str value=`tool_result`*
+ *tr = > text_head_lines text=`tr` max_lines=40 max_chars=3000*
+ *compact = > json.set map=`compact` key="tool_result" value=`tr`*
2. *
- *`_` = 1*
+ *_ = 1*
-*`last_error` = > json.get value=`observation` key=last_error *
+*last_error = > json.get value=`observation` key="last_error"*
1. `last_error`
- *`err_txt` = > str value=`last_error` *
- *`err_len` = > len value=`err_txt` *
+ *err_txt = > str value=`last_error`*
+ *err_len = > len value=`err_txt`*
1. `err_len` > 200
- *`prev` = > text_head_lines text=`err_txt` max_lines=8 max_chars=400 *
- *`compact` = > json.set map=`compact` key=last_error_preview value=`prev` *
- *`compact` = > json.set map=`compact` key=last_error_len value=`err_len` *
+ *prev = > text_head_lines text=`err_txt` max_lines=8 max_chars=400*
+ *compact = > json.set map=`compact` key="last_error_preview" value=`prev`*
+ *compact = > json.set map=`compact` key="last_error_len" value=`err_len`*
2. *
- *`compact` = > json.set map=`compact` key=last_error value=`last_error` *
+ *compact = > json.set map=`compact` key="last_error" value=`last_error`*
2. *
- *`_` = 1*
+ *_ = 1*
-**`compact`**
+**compact**
---
@@ -821,47 +821,47 @@ Bounded observation for the parent prompt (actionable, short).
Parse `DECISION: DONE` / `CONTINUE` / `RUN` (Chinese: `决定:完成` / `继续` / `运行`).
**First** matching DECISION / 决定 line wins (ignore later conflicting decisions in the same reply).
-*`esc` = > json.parse text={"nl":"\n","fw":":"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`fw` = > json.get value=`esc` key=fw *
-*`text` = > trim value=`reply` *
-*`lines` = > split value=`text` sep=`nl` *
-*`found` = None*
+*esc = > json.parse text={"nl":"\n","fw":":"}*
+*nl = > json.get value=`esc` key="nl"*
+*fw = > json.get value=`esc` key="fw"*
+*text = > trim value=`reply`*
+*lines = > split value=`text` sep=`nl`*
+*found = None*
- [`line`](`lines`)
1. `found`
- *`_` = 1*
+ *_ = 1*
2. *
- *`t` = > trim value=`line` *
- *`parts` = > split value=`t` sep=: *
- *`n` = > len value=`parts` *
+ *t = > trim value=`line`*
+ *parts = > split value=`t` sep=":"*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == DECISION
- *`found` = `rest`*
+ *found = rest*
2. `head` == 决定
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`parts` = > split value=`t` sep=`fw` *
- *`n` = > len value=`parts` *
+ *parts = > split value=`t` sep=`fw`*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == 决定
- *`found` = `rest`*
+ *found = rest*
2. `head` == DECISION
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
1. `found` == DONE
**"DONE"**
@@ -884,7 +884,7 @@ Parse `DECISION: DONE` / `CONTINUE` / `RUN` (Chinese: `决定:完成` / `继
10. `found` == 新建
**"NEW"**
11. *
- **`found`**
+ **found**
---
@@ -893,46 +893,46 @@ Parse `DECISION: DONE` / `CONTINUE` / `RUN` (Chinese: `决定:完成` / `继
Parse `SLUG: …` / `标识:…` after a soft-match REUSE decision.
-*`esc` = > json.parse text={"nl":"\n","fw":":"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`fw` = > json.get value=`esc` key=fw *
-*`text` = > trim value=`reply` *
-*`lines` = > split value=`text` sep=`nl` *
-*`found` = None*
+*esc = > json.parse text={"nl":"\n","fw":":"}*
+*nl = > json.get value=`esc` key="nl"*
+*fw = > json.get value=`esc` key="fw"*
+*text = > trim value=`reply`*
+*lines = > split value=`text` sep=`nl`*
+*found = None*
- [`line`](`lines`)
- *`t` = > trim value=`line` *
- *`parts` = > split value=`t` sep=: *
- *`n` = > len value=`parts` *
+ *t = > trim value=`line`*
+ *parts = > split value=`t` sep=":"*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == SLUG
- *`found` = `rest`*
+ *found = rest*
2. `head` == 标识
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`parts` = > split value=`t` sep=`fw` *
- *`n` = > len value=`parts` *
+ *parts = > split value=`t` sep=`fw`*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == 标识
- *`found` = `rest`*
+ *found = rest*
2. `head` == SLUG
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
-**`found`**
+**found**
---
@@ -942,26 +942,26 @@ Parse `SLUG: …` / `标识:…` after a soft-match REUSE decision.
Short parent prompt: REUSE+SLUG or NEW only. Candidates may include lexical `score` (prefer higher).
-*`esc` = > json.parse text={"a":"\n\n--- goal ---\n","b":"\n\n--- candidate tasks (slug | title | score) ---\n","c":"\n\n--- how to act ---\nExact reuse miss; candidates are ranked by local n-gram score when present. Prefer higher scores. Reply with ONE protocol only:\nDECISION: REUSE\nSLUG: \nor\nDECISION: NEW\nNo other prose.\n","nl":"\n","sep":" | ","sp":"score="} *
-*`a` = > json.get value=`esc` key=a *
-*`b` = > json.get value=`esc` key=b *
-*`c` = > json.get value=`esc` key=c *
-*`nl` = > json.get value=`esc` key=nl *
-*`sep` = > json.get value=`esc` key=sep *
-*`sp` = > json.get value=`esc` key=sp *
-*`lines` = > json.parse text=[] *
+*esc = > json.parse text={"a":"\n\n--- goal ---\n","b":"\n\n--- candidate tasks (slug | title | score) ---\n","c":"\n\n--- how to act ---\nExact reuse miss; candidates are ranked by local n-gram score when present. Prefer higher scores. Reply with ONE protocol only:\nDECISION: REUSE\nSLUG: \nor\nDECISION: NEW\nNo other prose.\n","nl":"\n","sep":" | ","sp":"score="}*
+*a = > json.get value=`esc` key="a"*
+*b = > json.get value=`esc` key="b"*
+*c = > json.get value=`esc` key="c"*
+*nl = > json.get value=`esc` key="nl"*
+*sep = > json.get value=`esc` key="sep"*
+*sp = > json.get value=`esc` key="sp"*
+*lines = > json.parse text=[]*
- [`t`](`tasks`)
- *`slug` = > json.get value=`t` key=slug *
- *`title` = > json.get value=`t` key=title *
- *`score` = > json.get value=`t` key=score *
+ *slug = > json.get value=`t` key="slug"*
+ *title = > json.get value=`t` key="title"*
+ *score = > json.get value=`t` key="score"*
1. `score`
- *`row` = `slug` + `sep` + `title` + `sep` + `sp` + `score` *
+ *row = slug + sep + title + sep + sp + score*
2. *
- *`row` = `slug` + `sep` + `title` *
- *`lines` = > json.append list=`lines` item=`row` *
-*`catalog` = > join value=`lines` sep=`nl` *
-*`p` = "Soft-match: same task intent?" *
-**`p` + `a` + `goal` + `b` + `catalog` + `c`**
+ *row = slug + sep + title*
+ *lines = > json.append list=`lines` item=`row`*
+*catalog = > join value=`lines` sep=`nl`*
+*p = "Soft-match: same task intent?"*
+**p + a + goal + b + catalog + c**
---
@@ -970,49 +970,49 @@ Short parent prompt: REUSE+SLUG or NEW only. Candidates may include lexical `sco
First `SUMMARY:` / `汇总:` / `汇总:` line body, else trimmed reply.
-*`esc` = > json.parse text={"nl":"\n","fw":":"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`fw` = > json.get value=`esc` key=fw *
-*`text` = > trim value=`reply` *
-*`lines` = > split value=`text` sep=`nl` *
-*`found` = None*
+*esc = > json.parse text={"nl":"\n","fw":":"}*
+*nl = > json.get value=`esc` key="nl"*
+*fw = > json.get value=`esc` key="fw"*
+*text = > trim value=`reply`*
+*lines = > split value=`text` sep=`nl`*
+*found = None*
- [`line`](`lines`)
- *`t` = > trim value=`line` *
- *`parts` = > split value=`t` sep=: *
- *`n` = > len value=`parts` *
+ *t = > trim value=`line`*
+ *parts = > split value=`t` sep=":"*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == SUMMARY
- *`found` = `rest`*
+ *found = rest*
2. `head` == 汇总
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`parts` = > split value=`t` sep=`fw` *
- *`n` = > len value=`parts` *
+ *parts = > split value=`t` sep=`fw`*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == 汇总
- *`found` = `rest`*
+ *found = rest*
2. `head` == SUMMARY
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
1. `found`
- **`found`**
+ **found**
2. *
- **`text`**
+ **text**
---
@@ -1026,40 +1026,40 @@ First `SUMMARY:` / `汇总:` / `汇总:` line body, else trimmed reply.
Parent Plan-and-Move prompt. Short protocol only — no long monologues.
-*`standing` = > json.get value=`agent` key=standing *
+*standing = > json.get value=`agent` key="standing"*
1. `standing`
- *`up` = `standing`*
+ *up = standing*
2. *
- *`up` = None*
+ *up = None*
-*`skill` = > skill_brief *
-*`compact` = > compact_plan_observation observation=`observation` *
-*`obs_s` = > json.stringify value=`compact` *
-*`goal_s` = > json.stringify value=`goal` *
-*`esc` = > json.parse text={"a":"\n\n--- standing ---\n","b":"\n\n--- goal ---\n","c":"\n\n--- observation ---\n","d":"\n\n--- skill brief ---\n","tools":"\n\n--- parent tools ---\nCALL:workbook_read | workbook_excerpt | lib_catalog | scratch_tool_write\nCALL:lib.fs.read_text|exists|list_dir | lib.json.parse|stringify | lib.sys.cwd (+ ARGS:{json})\nREAD:source | stderr | stdout | slots\nCreate tools: CONTINUE PATCH add ##, or CALL:scratch_tool_write with NAME line and fenced body.\n","e_rev":"\n\n--- how to act ---\nPlan-and-Move parent. Reply with ONE protocol only (no long reasoning). Exactly one DECISION line.\n1) exit_code=0 and has_value → DECISION: DONE + one-line SUMMARY. solidify_on_done. Do not CONTINUE just because has_worker_step.\n2) Need more evidence → READ:kind or CALL:tool (then you will be re-prompted).\n3) Failure / wrong value → DECISION: CONTINUE + short PATCH (<20 lines). Never paste user prose into REPLACE.\n4) Do NOT CONTINUE only to rewrite frontmatter imports; skeleton already uses import llm:/agent:/json:….\nPATCH must use triple-angle blocks only:\n<<<\nFIND\n\n===\nREPLACE\n\n>>>\nDo not use \u0060\u0060\u0060find, \u0060\u0060\u0060replace, or *** Begin Patch ***.\nProtocols:\nCALL:name\nREAD:kind\nDECISION: DONE\nSUMMARY: one line\nDECISION: CONTINUE\n","e_dec":"\n\n--- how to act ---\nPRE-RUN decompose. Reply with ONE protocol only (no long reasoning). Exactly one DECISION line.\n1) Skeleton OK → DECISION: RUN (preferred). Do not rewrite imports; they are already import llm:/agent:/….\n2) Need evidence → READ:source or CALL:workbook_read / lib_catalog.\n3) Reshape body/logic only → DECISION: CONTINUE + short PATCH (<20 lines).\n4) Fixed answer without LLM → PATCH to return, then RUN or DONE.\nPATCH must use <<< FIND === REPLACE >>> only (no \u0060\u0060\u0060find / Begin Patch).\nProtocols:\nCALL:name\nREAD:kind\nDECISION: RUN\nDECISION: DONE\nSUMMARY: one line\nDECISION: CONTINUE\n","f":"\n\n--- explore ---\n"} *
-*`a` = > json.get value=`esc` key=a *
-*`b` = > json.get value=`esc` key=b *
-*`c` = > json.get value=`esc` key=c *
-*`d` = > json.get value=`esc` key=d *
-*`tools` = > json.get value=`esc` key=tools *
-*`f` = > json.get value=`esc` key=f *
+*skill = > skill_brief*
+*compact = > compact_plan_observation observation=`observation`*
+*obs_s = > json.stringify value=`compact`*
+*goal_s = > json.stringify value=`goal`*
+*esc = > json.parse text={"a":"\n\n--- standing ---\n","b":"\n\n--- goal ---\n","c":"\n\n--- observation ---\n","d":"\n\n--- skill brief ---\n","tools":"\n\n--- parent tools ---\nCALL:workbook_read | workbook_excerpt | lib_catalog | scratch_tool_write\nCALL:lib.fs.read_text|exists|list_dir | lib.json.parse|stringify | lib.sys.cwd (+ ARGS:{json})\nREAD:source | stderr | stdout | slots\nCreate tools: CONTINUE PATCH add ##, or CALL:scratch_tool_write with NAME line and fenced body.\n","e_rev":"\n\n--- how to act ---\nPlan-and-Move parent. Reply with ONE protocol only (no long reasoning). Exactly one DECISION line.\n1) exit_code=0 and has_value → DECISION: DONE + one-line SUMMARY. solidify_on_done. Do not CONTINUE just because has_worker_step.\n2) Need more evidence → READ:kind or CALL:tool (then you will be re-prompted).\n3) Failure / wrong value → DECISION: CONTINUE + short PATCH (<20 lines). Never paste user prose into REPLACE.\n4) Do NOT CONTINUE only to rewrite frontmatter imports; skeleton already uses import llm:/agent:/json:….\nPATCH must use triple-angle blocks only:\n<<<\nFIND\n\n===\nREPLACE\n\n>>>\nDo not use \u0060\u0060\u0060find, \u0060\u0060\u0060replace, or *** Begin Patch ***.\nProtocols:\nCALL:name\nREAD:kind\nDECISION: DONE\nSUMMARY: one line\nDECISION: CONTINUE\n","e_dec":"\n\n--- how to act ---\nPRE-RUN decompose. Reply with ONE protocol only (no long reasoning). Exactly one DECISION line.\n1) Skeleton OK → DECISION: RUN (preferred). Do not rewrite imports; they are already import llm:/agent:/….\n2) Need evidence → READ:source or CALL:workbook_read / lib_catalog.\n3) Reshape body/logic only → DECISION: CONTINUE + short PATCH (<20 lines).\n4) Fixed answer without LLM → PATCH to return, then RUN or DONE.\nPATCH must use <<< FIND === REPLACE >>> only (no \u0060\u0060\u0060find / Begin Patch).\nProtocols:\nCALL:name\nREAD:kind\nDECISION: RUN\nDECISION: DONE\nSUMMARY: one line\nDECISION: CONTINUE\n","f":"\n\n--- explore ---\n"}*
+*a = > json.get value=`esc` key="a"*
+*b = > json.get value=`esc` key="b"*
+*c = > json.get value=`esc` key="c"*
+*d = > json.get value=`esc` key="d"*
+*tools = > json.get value=`esc` key="tools"*
+*f = > json.get value=`esc` key="f"*
1. `phase` == decompose
- *`e` = > json.get value=`esc` key=e_dec *
- *`p` = "Plan-and-Move: decompose before first run." *
+ *e = > json.get value=`esc` key="e_dec"*
+ *p = "Plan-and-Move: decompose before first run."*
2. *
- *`e` = > json.get value=`esc` key=e_rev *
- *`p` = "Plan-and-Move: revise after child run." *
-*`p` = `p` + `a` + `up` + `b` + `goal_s` + `c` + `obs_s` + `tools` + `d` + `skill` + `e` *
+ *e = > json.get value=`esc` key="e_rev"*
+ *p = "Plan-and-Move: revise after child run."*
+*p = p + a + up + b + goal_s + c + obs_s + tools + d + skill + e*
1. `explore_attempt`
- *`p` = `p` + `f` *
- *`p` = `p` + Attempt *
- *`p` = `p` + `explore_attempt` *
- *`p` = `p` + of *
- *`p` = `p` + `explore_n` *
- *`p` = `p` + ". Different path; prefer code when fixed." *
+ *p = p + f*
+ *p = p + "Attempt"*
+ *p = p + explore_attempt*
+ *p = p + "of"*
+ *p = p + explore_n*
+ *p = p + ". Different path; prefer code when fixed."*
2. *
- *`_` = 1*
-**`p`**
+ *_ = 1*
+**p**
---
@@ -1078,55 +1078,55 @@ Parent Plan-and-Move prompt. Short protocol only — no long monologues.
LLM Plan → CALL/READ/DECISION loop. Returns `{decision,reply,observation,events}`.
-*`model` = > json.get value=`agent` key=model *
-*`last_obs` = `observation` *
-*`left` = `max_acts` *
-*`decision` = None*
-*`last_reply` = None*
-*`evs_all` = `events` *
+*model = > json.get value=`agent` key="model"*
+*last_obs = observation*
+*left = max_acts*
+*decision = None*
+*last_reply = None*
+*evs_all = events*
- `left` > 0
1. `decision`
- *`left` = 0*
+ *left = 0*
2. *
- *`ctx` = > build_plan_context agent=`agent` goal=`goal` observation=`last_obs` explore_attempt=`explore_attempt` explore_n=`explore_n` phase=`phase` *
+ *ctx = > build_plan_context agent=`agent` goal=`goal` observation=`last_obs` explore_attempt=`explore_attempt` explore_n=`explore_n` phase=`phase`*
1. `stream`
- *`evs` = > `model`.complete prompt=`ctx` stream=True echo=`echo` *
- *`last_reply` = > llm.stream_result events=`evs` *
- *`evs_all` = > plan_merge_deltas events=`evs_all` from=`evs` stream=`stream` *
+ *evs = > model.complete prompt=`ctx` stream=True echo=`echo`*
+ *last_reply = > llm.stream_result events=`evs`*
+ *evs_all = > plan_merge_deltas events=`evs_all` from=`evs` stream=`stream`*
2. *
- *`last_reply` = > `model`.complete prompt=`ctx` *
- *`last_reply` = > trim value=`last_reply` *
- *`act` = > extract_plan_act reply=`last_reply` *
- *`kind` = > json.get value=`act` key=kind *
- *`name` = > json.get value=`act` key=name *
+ *last_reply = > model.complete prompt=`ctx`*
+ *last_reply = > trim value=`last_reply`*
+ *act = > extract_plan_act reply=`last_reply`*
+ *kind = > json.get value=`act` key="kind"*
+ *name = > json.get value=`act` key="name"*
1. `kind` == call
- *`evs_all` = > plan_append_tool events=`evs_all` type=tool_start name=`name` kind=call stream=`stream` *
- *`tool_out` = > run_parent_tool name=`name` path=`path` observation=`last_obs` reply=`last_reply` *
- *`brief` = > tool_result_brief value=`tool_out` *
- *`evs_all` = > plan_append_tool events=`evs_all` type=tool_end name=`name` kind=call result=`brief` stream=`stream` *
- *`last_obs` = > json.set map=`last_obs` key=tool_result value=`tool_out` *
- *`left` = `left` - 1*
+ *evs_all = > plan_append_tool events=`evs_all` type="tool_start" name=`name` kind="call" stream=`stream`*
+ *tool_out = > run_parent_tool name=`name` path=`path` observation=`last_obs` reply=`last_reply`*
+ *brief = > tool_result_brief value=`tool_out`*
+ *evs_all = > plan_append_tool events=`evs_all` type="tool_end" name=`name` kind="call" result=`brief` stream=`stream`*
+ *last_obs = > json.set map=`last_obs` key="tool_result" value=`tool_out`*
+ *left = left - 1*
2. `kind` == read
- *`evs_all` = > plan_append_tool events=`evs_all` type=tool_start name=`name` kind=read stream=`stream` *
- *`last_obs` = > plan_read_deepen observation=`last_obs` kind=`name` path=`path` *
- *`brief` = > tool_result_brief value=`last_obs` *
- *`evs_all` = > plan_append_tool events=`evs_all` type=tool_end name=`name` kind=read result=`brief` stream=`stream` *
- *`left` = `left` - 1*
+ *evs_all = > plan_append_tool events=`evs_all` type="tool_start" name=`name` kind="read" stream=`stream`*
+ *last_obs = > plan_read_deepen observation=`last_obs` kind=`name` path=`path`*
+ *brief = > tool_result_brief value=`last_obs`*
+ *evs_all = > plan_append_tool events=`evs_all` type="tool_end" name=`name` kind="read" result=`brief` stream=`stream`*
+ *left = left - 1*
3. `kind` == decision
- *`decision` = `name`*
- *`evs_all` = > plan_append_decision events=`evs_all` decision=`decision` stream=`stream` *
- *`left` = 0*
+ *decision = name*
+ *evs_all = > plan_append_decision events=`evs_all` decision=`decision` stream=`stream`*
+ *left = 0*
4. *
- *`decision` = "unknown"*
- *`left` = 0*
+ *decision = "unknown"*
+ *left = 0*
-*`out` = > json.parse text={} *
-*`out` = > json.set map=`out` key=decision value=`decision` *
-*`out` = > json.set map=`out` key=reply value=`last_reply` *
-*`out` = > json.set map=`out` key=observation value=`last_obs` *
-*`out` = > json.set map=`out` key=events value=`evs_all` *
-**`out`**
+*out = > json.parse text={}*
+*out = > json.set map=`out` key="decision" value=`decision`*
+*out = > json.set map=`out` key="reply" value=`last_reply`*
+*out = > json.set map=`out` key="observation" value=`last_obs`*
+*out = > json.set map=`out` key="events" value=`evs_all`*
+**out**
---
@@ -1138,14 +1138,14 @@ LLM Plan → CALL/READ/DECISION loop. Returns `{decision,reply,observation,event
Pre-run parent decompose marker. With `stream=True`, publish `{type:decompose}` so view is not silent before the first child.
1. `stream`
- *`ev` = > json.parse text={"type":"decompose"} *
- *`ev` = > json.set map=`ev` key=workbook value=`workbook` *
+ *ev = > json.parse text={"type":"decompose"}*
+ *ev = > json.set map=`ev` key="workbook" value=`workbook`*
> sys.stream_publish event=`ev`
1. `echo`
> print text=plan:decompose
2. *
- *`_` = 1*
- **`ev`**
+ *_ = 1*
+ **ev**
2. *
****
@@ -1158,16 +1158,16 @@ Pre-run parent decompose marker. With `stream=True`, publish `{type:decompose}`
Marker before `await_workbook`. With `stream=True`, publish `{type:await,round,workbook}` so the Stream panel shows progress while the quiet child runs (TTY `echo` optional).
1. `stream`
- *`ev` = > json.parse text={"type":"await"} *
- *`ev` = > json.set map=`ev` key=round value=`round` *
- *`ev` = > json.set map=`ev` key=workbook value=`workbook` *
+ *ev = > json.parse text={"type":"await"}*
+ *ev = > json.set map=`ev` key="round" value=`round`*
+ *ev = > json.set map=`ev` key="workbook" value=`workbook`*
> sys.stream_publish event=`ev`
1. `echo`
> print text=plan:await
> print text=`round`
2. *
- *`_` = 1*
- **`ev`**
+ *_ = 1*
+ **ev**
2. *
****
@@ -1176,11 +1176,11 @@ Marker before `await_workbook`. With `stream=True`, publish `{type:await,round,w
True when source still contains `worker.step` or `.单步`.
-*`src` = > fs.read_text path=`path` *
-*`a` = > split value=`src` sep=worker.step *
-*`na` = > len value=`a` *
-*`b` = > split value=`src` sep=.单步 *
-*`nb` = > len value=`b` *
+*src = > fs.read_text path=`path`*
+*a = > split value=`src` sep="worker.step"*
+*na = > len value=`a`*
+*b = > split value=`src` sep=".单步"*
+*nb = > len value=`b`*
1. `na` > 1
**1**
2. `nb` > 1
@@ -1200,24 +1200,24 @@ True when source still contains `worker.step` or `.单步`.
Append a `round` event when `stream=True`. Optional `result` is the child `# main` return (for view Child cards). Optional `echo` prints a short TTY marker (not the full workbook path).
1. `stream`
- *`ev` = > json.parse text={"type":"round"} *
- *`ev` = > json.set map=`ev` key=round value=`round` *
- *`ev` = > json.set map=`ev` key=workbook value=`workbook` *
- *`ev` = > json.set map=`ev` key=exit_code value=`exit_code` *
+ *ev = > json.parse text={"type":"round"}*
+ *ev = > json.set map=`ev` key="round" value=`round`*
+ *ev = > json.set map=`ev` key="workbook" value=`workbook`*
+ *ev = > json.set map=`ev` key="exit_code" value=`exit_code`*
1. `result`
- *`ev` = > json.set map=`ev` key=result value=`result` *
+ *ev = > json.set map=`ev` key="result" value=`result`*
2. *
- *`_` = 1*
- *`events` = > json.append list=`events` item=`ev` *
+ *_ = 1*
+ *events = > json.append list=`events` item=`ev`*
> sys.stream_publish event=`ev`
1. `echo`
> print text=plan:round
2. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
-**`events`**
+**events**
## plan_append_decision
+ `events`
@@ -1226,18 +1226,18 @@ Append a `round` event when `stream=True`. Optional `result` is the child `# mai
+ `summary`=None
1. `stream`
- *`ev` = > json.parse text={"type":"decision"} *
- *`ev` = > json.set map=`ev` key=decision value=`decision` *
+ *ev = > json.parse text={"type":"decision"}*
+ *ev = > json.set map=`ev` key="decision" value=`decision`*
1. `summary`
- *`ev` = > json.set map=`ev` key=summary value=`summary` *
+ *ev = > json.set map=`ev` key="summary" value=`summary`*
2. *
- *`_` = 1*
- *`events` = > json.append list=`events` item=`ev` *
+ *_ = 1*
+ *events = > json.append list=`events` item=`ev`*
> sys.stream_publish event=`ev`
2. *
- *`_` = 1*
+ *_ = 1*
-**`events`**
+**events**
## plan_merge_deltas
+ `events`
@@ -1248,19 +1248,19 @@ Bubble parent `complete stream=True` reasoning/deltas (and errors) into the plan
1. `stream`
- [`ev`](`from`)
- *`t` = > json.get value=`ev` key=type *
+ *t = > json.get value=`ev` key="type"*
1. `t` == delta
- *`events` = > json.append list=`events` item=`ev` *
+ *events = > json.append list=`events` item=`ev`*
2. `t` == reasoning
- *`events` = > json.append list=`events` item=`ev` *
+ *events = > json.append list=`events` item=`ev`*
3. `t` == error
- *`events` = > json.append list=`events` item=`ev` *
+ *events = > json.append list=`events` item=`ev`*
4. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
-**`events`**
+**events**
## plan_finish_stream
+ `out`
@@ -1272,24 +1272,24 @@ Bubble parent `complete stream=True` reasoning/deltas (and errors) into the plan
When `stream=True`, append `done` and attach `events` on the result map. Optional `trace=True` writes the event list to writeback slot `trace`.
1. `stream`
- *`ev` = > json.parse text={"type":"done"} *
+ *ev = > json.parse text={"type":"done"}*
1. `result`
- *`ev` = > json.set map=`ev` key=result value=`result` *
+ *ev = > json.set map=`ev` key="result" value=`result`*
2. *
- *`_` = 1*
- *`events` = > json.append list=`events` item=`ev` *
+ *_ = 1*
+ *events = > json.append list=`events` item=`ev`*
> sys.stream_publish event=`ev`
- *`out` = > json.set map=`out` key=events value=`events` *
+ *out = > json.set map=`out` key="events" value=`events`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `trace`
- *`body` = > json.stringify value=`events` *
+ *body = > json.stringify value=`events`*
> writeback.record value=`body` key=trace
2. *
- *`_` = 1*
+ *_ = 1*
-**`out`**
+**out**
---
@@ -1300,31 +1300,31 @@ When `stream=True`, append `done` and attach `events` on the result map. Optiona
Load ABI v2 agent plugin once (session bag + context queries).
-*`p` = > plugin.native_path name=agent *
+*p = > plugin.native_path name="agent"*
1. `p`
> plugin.load path=`p`
2. *
> print text=ext/ai/agent: native agent plugin not found (build marqdo_plugin_agent or marqdo ext add agent)
> sys.exit code=1
-*`id` = > agent_alloc *
-*`h` = > json.parse text={"_type":"agent"} *
-*`h` = > json.set map=`h` key=id value=`id` *
-*`h` = > json.set map=`h` key=model value=`model` *
-*`h` = > json.set map=`h` key=tools value=`tools` *
+*id = > agent_alloc*
+*h = > json.parse text={"_type":"agent"}*
+*h = > json.set map=`h` key="id" value=`id`*
+*h = > json.set map=`h` key="model" value=`model`*
+*h = > json.set map=`h` key="tools" value=`tools`*
1. `standing`
- *`h` = > json.set map=`h` key=standing value=`standing` *
+ *h = > json.set map=`h` key="standing" value=`standing`*
2. *
- *`_` = 1*
+ *_ = 1*
-**`h`**
+**h**
## clear_history
Clear the plugin session bag for this agent id.
-*`id` = > json.get value=`self` key=id *
+*id = > json.get value=`self` key="id"*
> agent_history_clear id=`id`
****
@@ -1338,81 +1338,81 @@ One atomic turn: context → LLM → optional tool via subtask. Returns a **map*
With `stream=True`, the model call uses SSE; `echo=True` prints delta text to stdout as it arrives. The returned map is unchanged (final `result` string).
-*`ctx` = > build_step_context agent=`self` task=`task` *
-*`id` = > json.get value=`self` key=id *
-*`model` = > json.get value=`self` key=model *
-*`tools` = > json.get value=`self` key=tools *
+*ctx = > build_step_context agent=`self` task=`task`*
+*id = > json.get value=`self` key="id"*
+*model = > json.get value=`self` key="model"*
+*tools = > json.get value=`self` key="tools"*
-*`user_turn` = > json.parse text={"role":"user"} *
-*`user_turn` = > json.set map=`user_turn` key=content value=`task` *
+*user_turn = > json.parse text={"role":"user"}*
+*user_turn = > json.set map=`user_turn` key="content" value=`task`*
> agent_history_append id=`id` item=`user_turn`
1. `stream`
- *`evs` = > `model`.complete prompt=`ctx` stream=True echo=`echo` *
- *`reply` = > llm.stream_result events=`evs` *
+ *evs = > model.complete prompt=`ctx` stream=True echo=`echo`*
+ *reply = > llm.stream_result events=`evs`*
2. *
- *`reply` = > `model`.complete prompt=`ctx` *
+ *reply = > model.complete prompt=`ctx`*
-*`reply` = > trim value=`reply` *
-*`decision` = `reply`*
-*`tool_name` = > extract_tool_name reply=`reply` *
-*`out` = > json.parse text={"status":"ok"} *
-*`out` = > json.set map=`out` key=task value=`task` *
-*`out` = > json.set map=`out` key=decision value=`decision` *
+*reply = > trim value=`reply`*
+*decision = reply*
+*tool_name = > extract_tool_name reply=`reply`*
+*out = > json.parse text={"status":"ok"}*
+*out = > json.set map=`out` key="task" value=`task`*
+*out = > json.set map=`out` key="decision" value=`decision`*
1. `tool_name`
- *`tool_out` = > run_tool tools=`tools` name=`tool_name` *
- *`tool_s` = > json.stringify value=`tool_out` *
- *`deny` = > split value=`tool_s` sep=Tool not allowed *
- *`deny_n` = > len value=`deny` *
+ *tool_out = > run_tool tools=`tools` name=`tool_name`*
+ *tool_s = > json.stringify value=`tool_out`*
+ *deny = > split value=`tool_s` sep="Tool not allowed"*
+ *deny_n = > len value=`deny`*
1. `deny_n` > 1
- *`task_s` = > json.stringify value=`task` *
- *`fp` = "Tool CALL was rejected (not on the tools whitelist). Do NOT emit CALL. Answer the user task directly with the final answer only.\n\nUser task:\n" *
- *`fp` = `fp` + `task_s` *
+ *task_s = > json.stringify value=`task`*
+ *fp = "Tool CALL was rejected (not on the tools whitelist). Do NOT emit CALL. Answer the user task directly with the final answer only.\n\nUser task:\n"*
+ *fp = fp + task_s*
1. `stream`
- *`evs_retry` = > `model`.complete prompt=`fp` stream=True echo=`echo` *
- *`reply` = > llm.stream_result events=`evs_retry` *
+ *evs_retry = > model.complete prompt=`fp` stream=True echo=`echo`*
+ *reply = > llm.stream_result events=`evs_retry`*
2. *
- *`reply` = > `model`.complete prompt=`fp` *
- *`out` = > json.set map=`out` key=status value=ok *
- *`out` = > json.set map=`out` key=decision value=`decision` *
- *`out` = > json.set map=`out` key=denied_tool value=`tool_name` *
- *`out` = > json.set map=`out` key=result value=`reply` *
+ *reply = > model.complete prompt=`fp`*
+ *out = > json.set map=`out` key="status" value="ok"*
+ *out = > json.set map=`out` key="decision" value=`decision`*
+ *out = > json.set map=`out` key="denied_tool" value=`tool_name`*
+ *out = > json.set map=`out` key="result" value=`reply`*
2. *
- *`task_s` = > json.stringify value=`task` *
- *`fp` = "The user asked:" *
- *`fp` = `fp` + `task_s` *
- *`fp` = `fp` + ". Tool" *
- *`fp` = `fp` + `tool_name` *
- *`fp` = `fp` + "ran via subtask and returned:" *
- *`fp` = `fp` + `tool_s` *
- *`fp` = `fp` + ". Reply to the user briefly." *
+ *task_s = > json.stringify value=`task`*
+ *fp = "The user asked:"*
+ *fp = fp + task_s*
+ *fp = fp + ". Tool"*
+ *fp = fp + tool_name*
+ *fp = fp + "ran via subtask and returned:"*
+ *fp = fp + tool_s*
+ *fp = fp + ". Reply to the user briefly."*
1. `stream`
- *`evs2` = > `model`.complete prompt=`fp` stream=True echo=`echo` *
- *`reply` = > llm.stream_result events=`evs2` *
+ *evs2 = > model.complete prompt=`fp` stream=True echo=`echo`*
+ *reply = > llm.stream_result events=`evs2`*
2. *
- *`reply` = > `model`.complete prompt=`fp` *
- *`out` = > json.set map=`out` key=tool value=`tool_name` *
- *`out` = > json.set map=`out` key=tool_result value=`tool_s` *
- *`out` = > json.set map=`out` key=result value=`reply` *
+ *reply = > model.complete prompt=`fp`*
+ *out = > json.set map=`out` key="tool" value=`tool_name`*
+ *out = > json.set map=`out` key="tool_result" value=`tool_s`*
+ *out = > json.set map=`out` key="result" value=`reply`*
2. *
- *`out` = > json.set map=`out` key=result value=`reply` *
+ *out = > json.set map=`out` key="result" value=`reply`*
-*`as_turn` = > json.parse text={"role":"assistant"} *
-*`as_turn` = > json.set map=`as_turn` key=content value=`reply` *
+*as_turn = > json.parse text={"role":"assistant"}*
+*as_turn = > json.set map=`as_turn` key="content" value=`reply`*
> agent_history_append id=`id` item=`as_turn`
1. `writeback`
- *`body` = > json.stringify value=`out` *
- *`st` = > json.get value=`out` key=status *
+ *body = > json.stringify value=`out`*
+ *st = > json.get value=`out` key="status"*
1. `st` == ok
> writeback.record value=`body` key=ok
2. *
> writeback.record value=`body` key=error
2. *
- *`_` = 1*
+ *_ = 1*
-**`out`**
+**out**
## plan
+ `goal`
@@ -1440,433 +1440,433 @@ Multi-step with OKF agent-kb. Default workbook is `kb_dir/resources/.mq.md
Reuse lookup: exact → alias → canonicalize → optional local n-gram `near` when `near_match=True` and score ≥ `near_threshold`. Non-hit path: optional `soft_match=True` parent REUSE/NEW over ranked `agent_kb_near_match` candidates; else **decompose** before first child spawn (`DECISION: RUN` / `CONTINUE`+patch / solidified `DONE`). Then `await` → revise loop. With `stream=True`, emit parent `delta` / `decision` / `tool_start`/`tool_end` / `round` / `done` on `events`. `echo=True` prints `plan:decompose` / `plan:await` / deltas. `trace=True` writes events to writeback slot `trace`. Quiet child subtasks stay quiet.
-*`tools` = > json.get value=`self` key=tools *
-*`cache` = "miss"*
-*`path` = None*
-*`improve` = None*
-*`explore` = None*
-*`explore_attempt` = None*
-*`skel_kind` = `skeleton`*
-*`events` = > json.parse text=[] *
+*tools = > json.get value=`self` key="tools"*
+*cache = "miss"*
+*path = None*
+*improve = None*
+*explore = None*
+*explore_attempt = None*
+*skel_kind = skeleton*
+*events = > json.parse text=[]*
-*`tf` = > agent_kb_task_files kb_dir=`kb_dir` goal=`goal` tools=`tools` *
-*`nfiles` = > json.get value=`tf` key=count *
+*tf = > agent_kb_task_files kb_dir=`kb_dir` goal=`goal` tools=`tools`*
+*nfiles = > json.get value=`tf` key="count"*
1. `force`
- *`_` = 1*
+ *_ = 1*
2. `optimize`
- *`_` = 1*
+ *_ = 1*
3. `reuse`
- *`hit` = > agent_kb_lookup kb_dir=`kb_dir` goal=`goal` tools=`tools` near_match=`near_match` near_threshold=`near_threshold` *
+ *hit = > agent_kb_lookup kb_dir=`kb_dir` goal=`goal` tools=`tools` near_match=`near_match` near_threshold=`near_threshold`*
1. `hit`
- *`match_kind` = > json.get value=`hit` key=match *
+ *match_kind = > json.get value=`hit` key="match"*
1. `match_kind` == alias
- *`cache_label` = "soft-hit"*
+ *cache_label = "soft-hit"*
2. `match_kind` == canonical
- *`cache_label` = "soft-hit"*
- *`hit_slug` = > json.get value=`hit` key=slug *
+ *cache_label = "soft-hit"*
+ *hit_slug = > json.get value=`hit` key="slug"*
> agent_kb_add_alias kb_dir=`kb_dir` slug=`hit_slug` alias=`goal`
3. `match_kind` == near
- *`cache_label` = "soft-hit"*
- *`hit_slug` = > json.get value=`hit` key=slug *
+ *cache_label = "soft-hit"*
+ *hit_slug = > json.get value=`hit` key="slug"*
> agent_kb_add_alias kb_dir=`kb_dir` slug=`hit_slug` alias=`goal`
4. `match_kind` == soft
- *`cache_label` = "soft-hit"*
+ *cache_label = "soft-hit"*
5. *
- *`cache_label` = "hit"*
- *`lf` = > json.get value=`hit` key=llm_free *
+ *cache_label = "hit"*
+ *lf = > json.get value=`hit` key="llm_free"*
1. `lf`
- *`path` = > json.get value=`hit` key=resource *
- *`aw` = > await_workbook path=`path` *
- *`code` = > json.get value=`aw` key=code *
- *`child_val` = > json.get value=`aw` key=value *
- *`last_obs` = > json.get value=`aw` key=observation *
+ *path = > json.get value=`hit` key="resource"*
+ *aw = > await_workbook path=`path`*
+ *code = > json.get value=`aw` key="code"*
+ *child_val = > json.get value=`aw` key="value"*
+ *last_obs = > json.get value=`aw` key="observation"*
1. `code` == 0
> agent_kb_record_hit kb_dir=`kb_dir` goal=`goal` tools=`tools` improve_every=`improve_every`
- *`cache` = `cache_label`*
- *`out` = > json.parse text={"status":"ok"} *
- *`out` = > json.set map=`out` key=status value=ok *
- *`out` = > json.set map=`out` key=goal value=`goal` *
- *`out` = > json.set map=`out` key=workbook value=`path` *
- *`out` = > json.set map=`out` key=rounds value=1 *
- *`out` = > json.set map=`out` key=cache value=`cache_label` *
- *`sk` = > json.get value=`hit` key=skill *
- *`out` = > json.set map=`out` key=skill value=`sk` *
- *`st` = > json.get value=`hit` key=status *
- *`out` = > json.set map=`out` key=skill_status value=`st` *
- *`sum` = "OKF llm_free skill hit; spawned resource" *
- *`out` = > json.set map=`out` key=summary value=`sum` *
- *`out` = > json.set map=`out` key=observation value=`last_obs` *
- *`out` = > json.set map=`out` key=result value=`child_val` *
- *`events` = > plan_append_round events=`events` round=1 workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo` *
+ *cache = cache_label*
+ *out = > json.parse text={"status":"ok"}*
+ *out = > json.set map=`out` key="status" value="ok"*
+ *out = > json.set map=`out` key="goal" value=`goal`*
+ *out = > json.set map=`out` key="workbook" value=`path`*
+ *out = > json.set map=`out` key="rounds" value=1*
+ *out = > json.set map=`out` key="cache" value=`cache_label`*
+ *sk = > json.get value=`hit` key="skill"*
+ *out = > json.set map=`out` key="skill" value=`sk`*
+ *st = > json.get value=`hit` key="status"*
+ *out = > json.set map=`out` key="skill_status" value=`st`*
+ *sum = "OKF llm_free skill hit; spawned resource"*
+ *out = > json.set map=`out` key="summary" value=`sum`*
+ *out = > json.set map=`out` key="observation" value=`last_obs`*
+ *out = > json.set map=`out` key="result" value=`child_val`*
+ *events = > plan_append_round events=`events` round=1 workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo`*
1. `writeback`
- *`body` = > json.stringify value=`out` *
+ *body = > json.stringify value=`out`*
> writeback.record value=`body` key=ok
2. *
- *`_` = 1*
- *`out` = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace` result=`child_val` *
- **`out`**
+ *_ = 1*
+ *out = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace` result=`child_val`*
+ **out**
2. *
- *`path` = None*
+ *path = None*
2. `nfiles` < `explore_n`
- *`explore` = 1*
- *`cache` = "explore"*
- *`path` = None*
- *`explore_attempt` = `nfiles` + 1*
+ *explore = 1*
+ *cache = "explore"*
+ *path = None*
+ *explore_attempt = nfiles + 1*
1. `explore_attempt` == 2
- *`skel_kind` = "dual"*
+ *skel_kind = "dual"*
2. *
- *`skel_kind` = `skeleton`*
+ *skel_kind = skeleton*
3. *
- *`path` = > json.get value=`hit` key=resource *
- *`aw` = > await_workbook path=`path` *
- *`code` = > json.get value=`aw` key=code *
- *`child_val` = > json.get value=`aw` key=value *
- *`last_obs` = > json.get value=`aw` key=observation *
+ *path = > json.get value=`hit` key="resource"*
+ *aw = > await_workbook path=`path`*
+ *code = > json.get value=`aw` key="code"*
+ *child_val = > json.get value=`aw` key="value"*
+ *last_obs = > json.get value=`aw` key="observation"*
1. `code` == 0
- *`rec` = > agent_kb_record_hit kb_dir=`kb_dir` goal=`goal` tools=`tools` improve_every=`improve_every` *
- *`due` = > json.get value=`rec` key=improve_due *
+ *rec = > agent_kb_record_hit kb_dir=`kb_dir` goal=`goal` tools=`tools` improve_every=`improve_every`*
+ *due = > json.get value=`rec` key="improve_due"*
1. `due`
- *`improve` = 1*
- *`cache` = "improve"*
+ *improve = 1*
+ *cache = "improve"*
2. *
- *`cache` = `cache_label`*
- *`out` = > json.parse text={"status":"ok"} *
- *`out` = > json.set map=`out` key=status value=ok *
- *`out` = > json.set map=`out` key=goal value=`goal` *
- *`out` = > json.set map=`out` key=workbook value=`path` *
- *`out` = > json.set map=`out` key=rounds value=1 *
- *`out` = > json.set map=`out` key=cache value=`cache_label` *
- *`sk` = > json.get value=`hit` key=skill *
- *`out` = > json.set map=`out` key=skill value=`sk` *
- *`st` = > json.get value=`hit` key=status *
- *`out` = > json.set map=`out` key=skill_status value=`st` *
- *`sum` = "OKF skill hit; spawned resource" *
- *`out` = > json.set map=`out` key=summary value=`sum` *
- *`out` = > json.set map=`out` key=observation value=`last_obs` *
- *`out` = > json.set map=`out` key=result value=`child_val` *
- *`events` = > plan_append_round events=`events` round=1 workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo` *
+ *cache = cache_label*
+ *out = > json.parse text={"status":"ok"}*
+ *out = > json.set map=`out` key="status" value="ok"*
+ *out = > json.set map=`out` key="goal" value=`goal`*
+ *out = > json.set map=`out` key="workbook" value=`path`*
+ *out = > json.set map=`out` key="rounds" value=1*
+ *out = > json.set map=`out` key="cache" value=`cache_label`*
+ *sk = > json.get value=`hit` key="skill"*
+ *out = > json.set map=`out` key="skill" value=`sk`*
+ *st = > json.get value=`hit` key="status"*
+ *out = > json.set map=`out` key="skill_status" value=`st`*
+ *sum = "OKF skill hit; spawned resource"*
+ *out = > json.set map=`out` key="summary" value=`sum`*
+ *out = > json.set map=`out` key="observation" value=`last_obs`*
+ *out = > json.set map=`out` key="result" value=`child_val`*
+ *events = > plan_append_round events=`events` round=1 workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo`*
1. `writeback`
- *`body` = > json.stringify value=`out` *
+ *body = > json.stringify value=`out`*
> writeback.record value=`body` key=ok
2. *
- *`_` = 1*
- *`out` = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace` result=`child_val` *
- **`out`**
+ *_ = 1*
+ *out = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace` result=`child_val`*
+ **out**
2. *
- *`path` = None*
+ *path = None*
2. *
1. `soft_match`
- *`near` = > agent_kb_near_match kb_dir=`kb_dir` goal=`goal` *
- *`tasks` = > json.get value=`near` key=candidates *
- *`tn` = > len value=`tasks` *
+ *near = > agent_kb_near_match kb_dir=`kb_dir` goal=`goal`*
+ *tasks = > json.get value=`near` key="candidates"*
+ *tn = > len value=`tasks`*
1. `tn` < 1
- *`listed` = > agent_kb_list_tasks kb_dir=`kb_dir` *
- *`tasks` = > json.get value=`listed` key=tasks *
- *`tn` = > len value=`tasks` *
+ *listed = > agent_kb_list_tasks kb_dir=`kb_dir`*
+ *tasks = > json.get value=`listed` key="tasks"*
+ *tn = > len value=`tasks`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `tn` > 0
- *`soft_prompt` = > build_soft_match_prompt goal=`goal` tasks=`tasks` *
- *`model` = > json.get value=`self` key=model *
+ *soft_prompt = > build_soft_match_prompt goal=`goal` tasks=`tasks`*
+ *model = > json.get value=`self` key="model"*
1. `stream`
- *`evs` = > `model`.complete prompt=`soft_prompt` stream=True echo=`echo` *
- *`soft_reply` = > llm.stream_result events=`evs` *
- *`events` = > plan_merge_deltas events=`events` from=`evs` stream=`stream` *
+ *evs = > model.complete prompt=`soft_prompt` stream=True echo=`echo`*
+ *soft_reply = > llm.stream_result events=`evs`*
+ *events = > plan_merge_deltas events=`events` from=`evs` stream=`stream`*
2. *
- *`soft_reply` = > `model`.complete prompt=`soft_prompt` *
- *`soft_reply` = > trim value=`soft_reply` *
- *`soft_dec` = > extract_plan_decision reply=`soft_reply` *
- *`events` = > plan_append_decision events=`events` decision=`soft_dec` stream=`stream` *
+ *soft_reply = > model.complete prompt=`soft_prompt`*
+ *soft_reply = > trim value=`soft_reply`*
+ *soft_dec = > extract_plan_decision reply=`soft_reply`*
+ *events = > plan_append_decision events=`events` decision=`soft_dec` stream=`stream`*
1. `soft_dec` == REUSE
- *`reuse_slug` = > extract_soft_match_slug reply=`soft_reply` *
+ *reuse_slug = > extract_soft_match_slug reply=`soft_reply`*
1. `reuse_slug`
- *`hit` = > agent_kb_lookup kb_dir=`kb_dir` slug=`reuse_slug` goal=`goal` tools=`tools` *
+ *hit = > agent_kb_lookup kb_dir=`kb_dir` slug=`reuse_slug` goal=`goal` tools=`tools`*
1. `hit`
> agent_kb_add_alias kb_dir=`kb_dir` slug=`reuse_slug` alias=`goal`
- *`cache_label` = "soft-hit"*
- *`path` = > json.get value=`hit` key=resource *
- *`aw` = > await_workbook path=`path` *
- *`code` = > json.get value=`aw` key=code *
- *`child_val` = > json.get value=`aw` key=value *
- *`last_obs` = > json.get value=`aw` key=observation *
+ *cache_label = "soft-hit"*
+ *path = > json.get value=`hit` key="resource"*
+ *aw = > await_workbook path=`path`*
+ *code = > json.get value=`aw` key="code"*
+ *child_val = > json.get value=`aw` key="value"*
+ *last_obs = > json.get value=`aw` key="observation"*
1. `code` == 0
> agent_kb_record_hit kb_dir=`kb_dir` goal=`goal` tools=`tools` improve_every=`improve_every`
- *`cache` = "soft-hit"*
- *`out` = > json.parse text={"status":"ok"} *
- *`out` = > json.set map=`out` key=status value=ok *
- *`out` = > json.set map=`out` key=goal value=`goal` *
- *`out` = > json.set map=`out` key=workbook value=`path` *
- *`out` = > json.set map=`out` key=rounds value=1 *
- *`out` = > json.set map=`out` key=cache value=soft-hit *
- *`sk` = > json.get value=`hit` key=skill *
- *`out` = > json.set map=`out` key=skill value=`sk` *
- *`st` = > json.get value=`hit` key=status *
- *`out` = > json.set map=`out` key=skill_status value=`st` *
- *`sum` = "OKF soft_match REUSE; spawned resource" *
- *`out` = > json.set map=`out` key=summary value=`sum` *
- *`out` = > json.set map=`out` key=observation value=`last_obs` *
- *`out` = > json.set map=`out` key=result value=`child_val` *
- *`events` = > plan_append_round events=`events` round=1 workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo` *
+ *cache = "soft-hit"*
+ *out = > json.parse text={"status":"ok"}*
+ *out = > json.set map=`out` key="status" value="ok"*
+ *out = > json.set map=`out` key="goal" value=`goal`*
+ *out = > json.set map=`out` key="workbook" value=`path`*
+ *out = > json.set map=`out` key="rounds" value=1*
+ *out = > json.set map=`out` key="cache" value="soft-hit"*
+ *sk = > json.get value=`hit` key="skill"*
+ *out = > json.set map=`out` key="skill" value=`sk`*
+ *st = > json.get value=`hit` key="status"*
+ *out = > json.set map=`out` key="skill_status" value=`st`*
+ *sum = "OKF soft_match REUSE; spawned resource"*
+ *out = > json.set map=`out` key="summary" value=`sum`*
+ *out = > json.set map=`out` key="observation" value=`last_obs`*
+ *out = > json.set map=`out` key="result" value=`child_val`*
+ *events = > plan_append_round events=`events` round=1 workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo`*
1. `writeback`
- *`body` = > json.stringify value=`out` *
+ *body = > json.stringify value=`out`*
> writeback.record value=`body` key=ok
2. *
- *`_` = 1*
- *`out` = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace` result=`child_val` *
- **`out`**
+ *_ = 1*
+ *out = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace` result=`child_val`*
+ **out**
2. *
- *`path` = None*
+ *path = None*
2. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
1. `nfiles` < `explore_n`
- *`explore` = 1*
- *`cache` = "explore"*
- *`explore_attempt` = `nfiles` + 1*
+ *explore = 1*
+ *cache = "explore"*
+ *explore_attempt = nfiles + 1*
1. `explore_attempt` == 2
- *`skel_kind` = "dual"*
+ *skel_kind = "dual"*
2. *
- *`skel_kind` = `skeleton`*
+ *skel_kind = skeleton*
2. *
- *`_` = 1*
+ *_ = 1*
4. *
1. `nfiles` < `explore_n`
- *`explore` = 1*
- *`cache` = "explore"*
- *`explore_attempt` = `nfiles` + 1*
+ *explore = 1*
+ *cache = "explore"*
+ *explore_attempt = nfiles + 1*
2. *
- *`_` = 1*
+ *_ = 1*
-*`skel` = > render_workbook_skeleton goal=`goal` skeleton=`skel_kind` *
+*skel = > render_workbook_skeleton goal=`goal` skeleton=`skel_kind`*
1. `workbook`
- *`path` = `workbook`*
- *`ex` = > fs.exists path=`path` *
+ *path = workbook*
+ *ex = > fs.exists path=`path`*
1. `ex`
- *`_` = 1*
+ *_ = 1*
2. *
> fs.write_text path=`path` text=`skel`
2. *
1. `path`
- *`_` = 1*
+ *_ = 1*
2. *
- *`slug` = > agent_goal_slug goal=`goal` *
+ *slug = > agent_goal_slug goal=`goal`*
1. `workbook_dir`
> fs.make_dir path=`workbook_dir`
- *`ts` = > time.now_ms *
- *`parts` = > json.parse text={"a":"/workbook-","b":"-","c":".mq.md"} *
- *`a` = > json.get value=`parts` key=a *
- *`b` = > json.get value=`parts` key=b *
- *`c` = > json.get value=`parts` key=c *
- *`path` = `workbook_dir` + `a` + `slug` + `b` + `ts` + `c` *
+ *ts = > time.now_ms*
+ *parts = > json.parse text={"a":"/workbook-","b":"-","c":".mq.md"}*
+ *a = > json.get value=`parts` key="a"*
+ *b = > json.get value=`parts` key="b"*
+ *c = > json.get value=`parts` key="c"*
+ *path = workbook_dir + a + slug + b + ts + c*
2. `explore`
- *`parts` = > json.parse text={"a":"/explore/","b":"/","c":".mq.md"} *
- *`a` = > json.get value=`parts` key=a *
- *`b` = > json.get value=`parts` key=b *
- *`c` = > json.get value=`parts` key=c *
- *`path` = `kb_dir` + `a` + `slug` + `b` + `explore_attempt` + `c` *
+ *parts = > json.parse text={"a":"/explore/","b":"/","c":".mq.md"}*
+ *a = > json.get value=`parts` key="a"*
+ *b = > json.get value=`parts` key="b"*
+ *c = > json.get value=`parts` key="c"*
+ *path = kb_dir + a + slug + b + explore_attempt + c*
3. *
- *`parts` = > json.parse text={"a":"/resources/","b":".mq.md"} *
- *`a` = > json.get value=`parts` key=a *
- *`b` = > json.get value=`parts` key=b *
- *`path` = `kb_dir` + `a` + `slug` + `b` *
+ *parts = > json.parse text={"a":"/resources/","b":".mq.md"}*
+ *a = > json.get value=`parts` key="a"*
+ *b = > json.get value=`parts` key="b"*
+ *path = kb_dir + a + slug + b*
> fs.write_text path=`path` text=`skel`
1. `confirm`
- *`out` = > json.parse text={"status":"pending"} *
- *`out` = > json.set map=`out` key=goal value=`goal` *
- *`out` = > json.set map=`out` key=workbook value=`path` *
- *`out` = > json.set map=`out` key=summary value=workbook created; confirm to run *
- *`out` = > json.set map=`out` key=cache value=bypass *
+ *out = > json.parse text={"status":"pending"}*
+ *out = > json.set map=`out` key="goal" value=`goal`*
+ *out = > json.set map=`out` key="workbook" value=`path`*
+ *out = > json.set map=`out` key="summary" value="workbook created; confirm to run"*
+ *out = > json.set map=`out` key="cache" value="bypass"*
1. `writeback`
- *`body` = > json.stringify value=`out` *
+ *body = > json.stringify value=`out`*
> writeback.record value=`body` key=ok
2. *
- *`_` = 1*
- *`out` = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace` *
- **`out`**
+ *_ = 1*
+ *out = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace`*
+ **out**
2. *
- *`_` = 1*
+ *_ = 1*
-*`model` = > json.get value=`self` key=model *
-*`round` = 0*
-*`last_obs` = None*
-*`last_reply` = None*
-*`child_val` = None*
-*`done` = None*
-*`summary` = None*
-*`status` = "error"*
-*`err` = "max_rounds exhausted" *
-*`skip_loop` = None*
+*model = > json.get value=`self` key="model"*
+*round = 0*
+*last_obs = None*
+*last_reply = None*
+*child_val = None*
+*done = None*
+*summary = None*
+*status = "error"*
+*err = "max_rounds exhausted"*
+*skip_loop = None*
> plan_echo_decompose workbook=`path` stream=`stream` echo=`echo`
-*`last_obs` = > inspect_workbook path=`path` *
-*`turn` = > plan_llm_act_loop agent=`self` goal=`goal` path=`path` observation=`last_obs` phase=decompose explore_attempt=`explore_attempt` explore_n=`explore_n` stream=`stream` echo=`echo` events=`events` *
-*`dec` = > json.get value=`turn` key=decision *
-*`last_reply` = > json.get value=`turn` key=reply *
-*`last_obs` = > json.get value=`turn` key=observation *
-*`events` = > json.get value=`turn` key=events *
+*last_obs = > inspect_workbook path=`path`*
+*turn = > plan_llm_act_loop agent=`self` goal=`goal` path=`path` observation=`last_obs` phase="decompose" explore_attempt=`explore_attempt` explore_n=`explore_n` stream=`stream` echo=`echo` events=`events`*
+*dec = > json.get value=`turn` key="decision"*
+*last_reply = > json.get value=`turn` key="reply"*
+*last_obs = > json.get value=`turn` key="observation"*
+*events = > json.get value=`turn` key="events"*
1. `dec` == CONTINUE
- *`n` = > fs.apply_patch_blocks path=`path` text=`last_reply` soft=True *
- *`_` = 1*
+ *n = > fs.apply_patch_blocks path=`path` text=`last_reply` soft=True*
+ *_ = 1*
2. `dec` == RUN
- *`_` = 1*
+ *_ = 1*
3. `dec` == DONE
- *`has_step` = > workbook_has_worker_step path=`path` *
+ *has_step = > workbook_has_worker_step path=`path`*
1. `has_step`
- *`_` = 1*
+ *_ = 1*
2. *
> plan_echo_await round=1 workbook=`path` stream=`stream` echo=`echo`
- *`aw` = > await_workbook path=`path` *
- *`code` = > json.get value=`aw` key=code *
- *`child_val` = > json.get value=`aw` key=value *
- *`last_obs` = > json.get value=`aw` key=observation *
- *`round` = 1*
- *`events` = > plan_append_round events=`events` round=1 workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo` *
+ *aw = > await_workbook path=`path`*
+ *code = > json.get value=`aw` key="code"*
+ *child_val = > json.get value=`aw` key="value"*
+ *last_obs = > json.get value=`aw` key="observation"*
+ *round = 1*
+ *events = > plan_append_round events=`events` round=1 workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo`*
1. `code` == 0
- *`done` = 1*
- *`status` = "ok"*
- *`summary` = > extract_plan_summary reply=`last_reply` *
- *`err` = None*
- *`skip_loop` = 1*
+ *done = 1*
+ *status = "ok"*
+ *summary = > extract_plan_summary reply=`last_reply`*
+ *err = None*
+ *skip_loop = 1*
2. *
- *`_` = 1*
+ *_ = 1*
4. *
- *`done` = 1*
- *`status` = "error"*
- *`err` = "unrecognized plan decision" *
- *`summary` = `last_reply`*
- *`skip_loop` = 1*
+ *done = 1*
+ *status = "error"*
+ *err = "unrecognized plan decision"*
+ *summary = last_reply*
+ *skip_loop = 1*
1. `skip_loop`
- *`left` = 0*
+ *left = 0*
2. `improve`
- *`left` = 1*
+ *left = 1*
3. *
- *`left` = `max_rounds`*
+ *left = max_rounds*
- `left` > 0
1. `done`
- *`left` = 0*
+ *left = 0*
2. *
- *`round` = `round` + 1*
+ *round = round + 1*
> plan_echo_await round=`round` workbook=`path` stream=`stream` echo=`echo`
- *`aw` = > await_workbook path=`path` *
- *`code` = > json.get value=`aw` key=code *
- *`child_val` = > json.get value=`aw` key=value *
- *`last_obs` = > json.get value=`aw` key=observation *
- *`events` = > plan_append_round events=`events` round=`round` workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo` *
+ *aw = > await_workbook path=`path`*
+ *code = > json.get value=`aw` key="code"*
+ *child_val = > json.get value=`aw` key="value"*
+ *last_obs = > json.get value=`aw` key="observation"*
+ *events = > plan_append_round events=`events` round=`round` workbook=`path` exit_code=`code` result=`child_val` stream=`stream` echo=`echo`*
Deterministic success stop (loop engineering): when the child already returned a value, do not ask the parent LLM to invent solidify patches — DONE + runtime solidify.
1. `code` == 0
1. `child_val`
1. `improve`
- *`auto_done` = None*
+ *auto_done = None*
2. *
- *`auto_done` = 1*
+ *auto_done = 1*
2. *
- *`auto_done` = None*
+ *auto_done = None*
2. *
- *`auto_done` = None*
+ *auto_done = None*
1. `auto_done`
> agent_workbook_solidify path=`path` observation=`last_obs`
- *`done` = 1*
- *`status` = "ok"*
- *`summary` = "child returned value; solidified" *
- *`err` = None*
- *`dec` = "DONE"*
- *`events` = > plan_append_decision events=`events` decision=`dec` stream=`stream` summary=`summary` *
- *`left` = 0*
+ *done = 1*
+ *status = "ok"*
+ *summary = "child returned value; solidified"*
+ *err = None*
+ *dec = "DONE"*
+ *events = > plan_append_decision events=`events` decision=`dec` stream=`stream` summary=`summary`*
+ *left = 0*
2. *
- *`turn` = > plan_llm_act_loop agent=`self` goal=`goal` path=`path` observation=`last_obs` phase=revise explore_attempt=`explore_attempt` explore_n=`explore_n` stream=`stream` echo=`echo` events=`events` *
- *`dec` = > json.get value=`turn` key=decision *
- *`last_reply` = > json.get value=`turn` key=reply *
- *`last_obs` = > json.get value=`turn` key=observation *
- *`events` = > json.get value=`turn` key=events *
+ *turn = > plan_llm_act_loop agent=`self` goal=`goal` path=`path` observation=`last_obs` phase="revise" explore_attempt=`explore_attempt` explore_n=`explore_n` stream=`stream` echo=`echo` events=`events`*
+ *dec = > json.get value=`turn` key="decision"*
+ *last_reply = > json.get value=`turn` key="reply"*
+ *last_obs = > json.get value=`turn` key="observation"*
+ *events = > json.get value=`turn` key="events"*
1. `dec` == DONE
> agent_workbook_solidify path=`path` observation=`last_obs`
- *`done` = 1*
- *`status` = "ok"*
- *`summary` = > extract_plan_summary reply=`last_reply` *
- *`err` = None*
- *`left` = 0*
+ *done = 1*
+ *status = "ok"*
+ *summary = > extract_plan_summary reply=`last_reply`*
+ *err = None*
+ *left = 0*
2. `dec` == CONTINUE
- *`n` = > fs.apply_patch_blocks path=`path` text=`last_reply` soft=True *
+ *n = > fs.apply_patch_blocks path=`path` text=`last_reply` soft=True*
1. `n`
- *`left` = `left` - 1*
+ *left = left - 1*
2. *
- *`done` = 1*
- *`status` = "error"*
- *`err` = "no patches applied" *
- *`summary` = > extract_plan_summary reply=`last_reply` *
- *`left` = 0*
+ *done = 1*
+ *status = "error"*
+ *err = "no patches applied"*
+ *summary = > extract_plan_summary reply=`last_reply`*
+ *left = 0*
3. `dec` == RUN
- *`left` = `left` - 1*
+ *left = left - 1*
4. *
- *`done` = 1*
- *`status` = "error"*
- *`err` = "unrecognized plan decision" *
- *`summary` = `last_reply`*
- *`left` = 0*
+ *done = 1*
+ *status = "error"*
+ *err = "unrecognized plan decision"*
+ *summary = last_reply*
+ *left = 0*
1. `status` == ok
1. `promote`
- *`prom` = > agent_kb_promote kb_dir=`kb_dir` goal=`goal` workbook=`path` tools=`tools` *
- *`cache` = "refreshed"*
+ *prom = > agent_kb_promote kb_dir=`kb_dir` goal=`goal` workbook=`path` tools=`tools`*
+ *cache = "refreshed"*
2. *
- *`cache` = "miss"*
+ *cache = "miss"*
2. *
- *`_` = 1*
+ *_ = 1*
-*`out` = > json.parse text={"status":"ok"} *
-*`out` = > json.set map=`out` key=status value=`status` *
-*`out` = > json.set map=`out` key=goal value=`goal` *
-*`out` = > json.set map=`out` key=workbook value=`path` *
-*`out` = > json.set map=`out` key=rounds value=`round` *
-*`out` = > json.set map=`out` key=cache value=`cache` *
+*out = > json.parse text={"status":"ok"}*
+*out = > json.set map=`out` key="status" value=`status`*
+*out = > json.set map=`out` key="goal" value=`goal`*
+*out = > json.set map=`out` key="workbook" value=`path`*
+*out = > json.set map=`out` key="rounds" value=`round`*
+*out = > json.set map=`out` key="cache" value=`cache`*
1. `summary`
- *`out` = > json.set map=`out` key=summary value=`summary` *
+ *out = > json.set map=`out` key="summary" value=`summary`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `err`
- *`out` = > json.set map=`out` key=error value=`err` *
+ *out = > json.set map=`out` key="error" value=`err`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `last_obs`
- *`out` = > json.set map=`out` key=observation value=`last_obs` *
+ *out = > json.set map=`out` key="observation" value=`last_obs`*
2. *
- *`_` = 1*
+ *_ = 1*
1. `child_val`
- *`out` = > json.set map=`out` key=result value=`child_val` *
- *`plan_result` = `child_val`*
+ *out = > json.set map=`out` key="result" value=`child_val`*
+ *plan_result = child_val*
2. `summary`
- *`out` = > json.set map=`out` key=result value=`summary` *
- *`plan_result` = `summary`*
+ *out = > json.set map=`out` key="result" value=`summary`*
+ *plan_result = summary*
3. *
- *`plan_result` = None*
+ *plan_result = None*
1. `writeback`
- *`body` = > json.stringify value=`out` *
+ *body = > json.stringify value=`out`*
1. `status` == ok
> writeback.record value=`body` key=ok
2. *
> writeback.record value=`body` key=error
2. *
- *`_` = 1*
+ *_ = 1*
-*`out` = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace` result=`plan_result` *
-**`out`**
+*out = > plan_finish_stream out=`out` events=`events` stream=`stream` trace=`trace` result=`plan_result`*
+**out**
diff --git a/ext/ai/llm.mq.md b/ext/ai/llm.mq.md
index 164984f..3f54c60 100644
--- a/ext/ai/llm.mq.md
+++ b/ext/ai/llm.mq.md
@@ -39,23 +39,23 @@ Reduce a `complete stream=True` event list to the final `done.result` text (or `
Construct an LLM handle from `OPENAI_*` / `MARQDO_LLM_*`.
-*api_key = > sys.env_get name=OPENAI_API_KEY*
+*api_key = > sys.env_get name="OPENAI_API_KEY"*
1. not `api_key`
- *api_key = > sys.env_get name=MARQDO_LLM_API_KEY*
+ *api_key = > sys.env_get name="MARQDO_LLM_API_KEY"*
1. not `api_key`
> print text=ext/ai/llm: set OPENAI_API_KEY or MARQDO_LLM_API_KEY
> sys.exit code=1
-*base_url = > sys.env_get name=OPENAI_BASE_URL*
+*base_url = > sys.env_get name="OPENAI_BASE_URL"*
1. not `base_url`
- *base_url = > sys.env_get name=MARQDO_LLM_BASE_URL*
+ *base_url = > sys.env_get name="MARQDO_LLM_BASE_URL"*
1. not `base_url`
*base_url = "https://api.openai.com/v1"*
-*model = > sys.env_get name=OPENAI_MODEL*
+*model = > sys.env_get name="OPENAI_MODEL"*
1. not `model`
- *model = > sys.env_get name=MARQDO_LLM_MODEL*
+ *model = > sys.env_get name="MARQDO_LLM_MODEL"*
1. not `model`
*model = "gpt-4o-mini"*
@@ -78,7 +78,7 @@ Wire body is `{model, messages:[{role,content}], stream?}`. Messages are an `@`
*url = self[^base_url] + self[^suffix]*
*auth = self[^bearer] + self[^api_key]*
-*headers = > table.put in=None at=Authorization value=`auth`*
+*headers = > table.put in=None at="Authorization" value=`auth`*
`messages` =
@@ -93,7 +93,7 @@ Wire body is `{model, messages:[{role,content}], stream?}`. Messages are an `@`
| self[^model] | `messages` |
1. `stream`
- *req = > table.put in=`req` at=stream value=True*
+ *req = > table.put in=`req` at="stream" value=True*
*body = > json.stringify value=`req`*
*resp = > net.http_post_sse url=`url` body=`body` headers=`headers` echo=`echo`*
1. resp[^status] == 200
@@ -123,4 +123,4 @@ Wire body is `{model, messages:[{role,content}], stream?}`. Messages are an `@`
Alias for `complete`.
-**> `self`.complete prompt=`prompt` stream=`stream` echo=`echo`**
+**> self.complete prompt=`prompt` stream=`stream` echo=`echo`**
diff --git a/ext/ai/大模型.mq.md b/ext/ai/大模型.mq.md
index 72309c1..7480783 100644
--- a/ext/ai/大模型.mq.md
+++ b/ext/ai/大模型.mq.md
@@ -39,23 +39,23 @@ import json:lib/json.mq.md
从 `OPENAI_*` / `MARQDO_LLM_*` 构造句柄。
-*api_key = > 系统.取环境 名=OPENAI_API_KEY*
+*api_key = > 系统.取环境 名="OPENAI_API_KEY"*
1. 非 `api_key`
- *api_key = > 系统.取环境 名=MARQDO_LLM_API_KEY*
+ *api_key = > 系统.取环境 名="MARQDO_LLM_API_KEY"*
1. 非 `api_key`
> 打印 内容=ext/ai/大模型: 请设置 OPENAI_API_KEY 或 MARQDO_LLM_API_KEY
> 系统.退出 码=1
-*base_url = > 系统.取环境 名=OPENAI_BASE_URL*
+*base_url = > 系统.取环境 名="OPENAI_BASE_URL"*
1. 非 `base_url`
- *base_url = > 系统.取环境 名=MARQDO_LLM_BASE_URL*
+ *base_url = > 系统.取环境 名="MARQDO_LLM_BASE_URL"*
1. 非 `base_url`
*base_url = "https://api.openai.com/v1"*
-*model = > 系统.取环境 名=OPENAI_MODEL*
+*model = > 系统.取环境 名="OPENAI_MODEL"*
1. 非 `model`
- *model = > 系统.取环境 名=MARQDO_LLM_MODEL*
+ *model = > 系统.取环境 名="MARQDO_LLM_MODEL"*
1. 非 `model`
*model = "gpt-4o-mini"*
@@ -78,7 +78,7 @@ import json:lib/json.mq.md
*url = 自[^base_url] + 自[^suffix]*
*auth = 自[^bearer] + 自[^api_key]*
-*headers = > 表.改 入=None 于=Authorization 值=`auth`*
+*headers = > 表.改 入=None 于="Authorization" 值=`auth`*
`messages` =
@@ -93,7 +93,7 @@ import json:lib/json.mq.md
| 自[^model] | `messages` |
1. `流式`
- *req = > 表.改 入=`req` 于=stream 值=True*
+ *req = > 表.改 入=`req` 于="stream" 值=True*
*body = > json.stringify value=`req`*
*resp = > 网络.提交流式 地址=`url` 内容=`body` headers=`headers` 打印增量=`打印增量`*
1. resp[^status] == 200
@@ -123,4 +123,4 @@ import json:lib/json.mq.md
运行 的别名。
-**> `自`.运行 提示=`提示` 流式=`流式` 打印增量=`打印增量`**
+**> 自.运行 提示=`提示` 流式=`流式` 打印增量=`打印增量`**
diff --git a/ext/ai/智能体.mq.md b/ext/ai/智能体.mq.md
index 8086d68..67202eb 100644
--- a/ext/ai/智能体.mq.md
+++ b/ext/ai/智能体.mq.md
@@ -16,32 +16,32 @@ import json:lib/json.mq.md
组装可读提示:站立提示、任务、工具、调用位置、源码、Skill,以及人可见的行动约定。
-*`standing` = > json.get value=`智能体` key=standing *
+*standing = > json.get value=`智能体` key="standing"*
1. `standing`
- *`up` = `standing`*
+ *up = standing*
2. *
- *`up` = 空*
+ *up = 空*
-*`tools` = > json.get value=`智能体` key=tools *
-*`tools_s` = > agent_format_tools tools=`tools` *
-*`src` = > agent_module_source *
-*`site` = > agent_call_site *
-*`site_s` = > json.stringify value=`site` *
-*`skill` = > agent_marqdo_skill *
-*`task_s` = > json.stringify value=`任务` *
+*tools = > json.get value=`智能体` key="tools"*
+*tools_s = > agent_format_tools tools=`tools`*
+*src = > agent_module_source*
+*site = > agent_call_site*
+*site_s = > json.stringify value=`site`*
+*skill = > agent_marqdo_skill*
+*task_s = > json.stringify value=`任务`*
-*`esc` = > json.parse text={"a":"\n\n--- standing ---\n","b":"\n\n--- task ---\n","c":"\n\n--- tools ---\n","d":"\n\n--- call site ---\n","e":"\n\n--- source (.mq.md) ---\n","f":"\n\n--- marqdo skill ---\n","g":"\n\n--- how to act ---\nTools are ## functions in the source above. To call one, reply with exactly one line: CALL:\n(Chinese ok: 调用:)\nOtherwise reply with the final answer only.\nTools run via Marqdo subtask (spawn fn / wait).\n"} *
-*`a` = > json.get value=`esc` key=a *
-*`b` = > json.get value=`esc` key=b *
-*`c` = > json.get value=`esc` key=c *
-*`d` = > json.get value=`esc` key=d *
-*`e` = > json.get value=`esc` key=e *
-*`f` = > json.get value=`esc` key=f *
-*`g` = > json.get value=`esc` key=g *
+*esc = > json.parse text={"a":"\n\n--- standing ---\n","b":"\n\n--- task ---\n","c":"\n\n--- tools ---\n","d":"\n\n--- call site ---\n","e":"\n\n--- source (.mq.md) ---\n","f":"\n\n--- marqdo skill ---\n","g":"\n\n--- how to act ---\nTools are ## functions in the source above. To call one, reply with exactly one line: CALL:\n(Chinese ok: 调用:)\nOtherwise reply with the final answer only.\nTools run via Marqdo subtask (spawn fn / wait).\n"}*
+*a = > json.get value=`esc` key="a"*
+*b = > json.get value=`esc` key="b"*
+*c = > json.get value=`esc` key="c"*
+*d = > json.get value=`esc` key="d"*
+*e = > json.get value=`esc` key="e"*
+*f = > json.get value=`esc` key="f"*
+*g = > json.get value=`esc` key="g"*
-*`p` = "You are a Marqdo agent. The runbook source is your ground truth — code is documentation." *
-*`p` = `p` + `a` + `up` + `b` + `task_s` + `c` + `tools_s` + `g` + `d` + `site_s` + `e` + `src` + `f` + `skill` *
-**`p`**
+*p = "You are a Marqdo agent. The runbook source is your ground truth — code is documentation."*
+*p = p + a + up + b + task_s + c + tools_s + g + d + site_s + e + src + f + skill*
+**p**
---
@@ -50,31 +50,31 @@ import json:lib/json.mq.md
解析人可读调用行:`CALL:<名>` 或 `调用:<名>` / `调用:<名>`。
-*`esc` = > json.parse text={"nl":"\n"} *
-*`nl` = > json.get value=`esc` key=nl *
-*`text` = > trim value=`回复` *
-*`lines` = > split value=`text` sep=`nl` *
-*`found` = 空*
+*esc = > json.parse text={"nl":"\n"}*
+*nl = > json.get value=`esc` key="nl"*
+*text = > trim value=`回复`*
+*lines = > split value=`text` sep=`nl`*
+*found = 空*
- [`line`](`lines`)
- *`t` = > trim value=`line` *
- *`parts` = > split value=`t` sep=: *
- *`n` = > len value=`parts` *
+ *t = > trim value=`line`*
+ *parts = > split value=`t` sep=:*
+ *n = > len value=`parts`*
1. `n` > 1
- *`head` = > at value=`parts` index=0 *
- *`head` = > trim value=`head` *
- *`rest` = > at value=`parts` index=1 *
- *`rest` = > trim value=`rest` *
+ *head = > at value=`parts` index=0*
+ *head = > trim value=`head`*
+ *rest = > at value=`parts` index=1*
+ *rest = > trim value=`rest`*
1. `head` == CALL
- *`found` = `rest`*
+ *found = rest*
2. `head` == 调用
- *`found` = `rest`*
+ *found = rest*
3. *
- *`_` = 1*
+ *_ = 1*
2. *
- *`_` = 1*
+ *_ = 1*
-**`found`**
+**found**
---
@@ -84,13 +84,13 @@ import json:lib/json.mq.md
白名单校验后,经 `lib/子任务`(`启动 函数=` → `等待`)调用 runbook 中的 `##`。
-*`allowed` = > agent_tool_allowed tools=`工具` name=`名` *
+*allowed = > agent_tool_allowed tools=`工具` name=`名`*
1. `allowed`
- *`id` = > 子任务.启动 函数=`名` *
+ *id = > 子任务.启动 函数=`名`*
**> 子任务.等待 id=`id`**
2. *
- *`msg` = "Tool not allowed:" *
- **`msg` + `名`**
+ *msg = "Tool not allowed:"*
+ **msg + `名`**
# 智能体
+ `大模型`
@@ -99,31 +99,31 @@ import json:lib/json.mq.md
加载 ABI v2 agent 插件(会话袋 + 上下文查询)。
-*`p` = > 插件.原生路径 名=agent *
+*p = > 插件.原生路径 名="agent"*
1. `p`
> 插件.加载 路径=`p`
2. *
> 打印 内容=ext/ai/智能体: 未找到原生 agent 插件(请先 cargo build -p marqdo_plugin_agent 或 marqdo ext add agent)
> 系统.退出 码=1
-*`id` = > agent_alloc *
-*`h` = > json.parse text={"_type":"智能体"} *
-*`h` = > json.set map=`h` key=id value=`id` *
-*`h` = > json.set map=`h` key=model value=`大模型` *
-*`h` = > json.set map=`h` key=tools value=`工具` *
+*id = > agent_alloc*
+*h = > json.parse text={"_type":"智能体"}*
+*h = > json.set map=`h` key="id" value=`id`*
+*h = > json.set map=`h` key="model" value=`大模型`*
+*h = > json.set map=`h` key="tools" value=`工具`*
1. `站立提示`
- *`h` = > json.set map=`h` key=standing value=`站立提示` *
+ *h = > json.set map=`h` key="standing" value=`站立提示`*
2. *
- *`_` = 1*
+ *_ = 1*
-**`h`**
+**h**
## 清空历史
清空本智能体 id 的插件会话袋。
-*`id` = > json.get value=`自` key=id *
+*id = > json.get value=`自` key="id"*
> agent_history_clear id=`id`
****
@@ -137,72 +137,72 @@ import json:lib/json.mq.md
流式=真 时走 SSE;打印增量=真 边读边打印。返回 map 仍是最终 result 文本。
-*`ctx` = > 构建单步上下文 智能体=`自` 任务=`任务` *
-*`id` = > json.get value=`自` key=id *
-*`model` = > json.get value=`自` key=model *
-*`tools` = > json.get value=`自` key=tools *
+*ctx = > 构建单步上下文 智能体=`自` 任务=`任务`*
+*id = > json.get value=`自` key="id"*
+*model = > json.get value=`自` key="model"*
+*tools = > json.get value=`自` key="tools"*
-*`user_turn` = > json.parse text={"role":"user"} *
-*`user_turn` = > json.set map=`user_turn` key=content value=`任务` *
+*user_turn = > json.parse text={"role":"user"}*
+*user_turn = > json.set map=`user_turn` key="content" value=`任务`*
> agent_history_append id=`id` item=`user_turn`
1. `流式`
- *`evs` = > `model`.运行 提示=`ctx` 流式=真 打印增量=`打印增量` *
- *`reply` = > 大模型.流式结果 事件=`evs` *
+ *evs = > model.运行 提示=`ctx` 流式=真 打印增量=`打印增量`*
+ *reply = > 大模型.流式结果 事件=`evs`*
2. *
- *`reply` = > `model`.运行 提示=`ctx` *
+ *reply = > model.运行 提示=`ctx`*
-*`reply` = > trim value=`reply` *
-*`decision` = `reply`*
-*`tool_name` = > 提取工具名 回复=`reply` *
-*`out` = > json.parse text={"status":"ok"} *
-*`out` = > json.set map=`out` key=task value=`任务` *
-*`out` = > json.set map=`out` key=decision value=`decision` *
+*reply = > trim value=`reply`*
+*decision = reply*
+*tool_name = > 提取工具名 回复=`reply`*
+*out = > json.parse text={"status":"ok"}*
+*out = > json.set map=`out` key="task" value=`任务`*
+*out = > json.set map=`out` key="decision" value=`decision`*
1. `tool_name`
- *`tool_out` = > 运行工具 工具=`tools` 名=`tool_name` *
- *`tool_s` = > json.stringify value=`tool_out` *
- *`deny` = > split value=`tool_s` sep=Tool not allowed *
- *`deny_n` = > len value=`deny` *
+ *tool_out = > 运行工具 工具=`tools` 名=`tool_name`*
+ *tool_s = > json.stringify value=`tool_out`*
+ *deny = > split value=`tool_s` sep="Tool not allowed"*
+ *deny_n = > len value=`deny`*
1. `deny_n` > 1
- *`out` = > json.set map=`out` key=status value=error *
- *`out` = > json.set map=`out` key=error value=`tool_s` *
- *`reply` = `tool_s`*
+ *out = > json.set map=`out` key="status" value="error"*
+ *out = > json.set map=`out` key="error" value=`tool_s`*
+ *reply = tool_s*
2. *
- *`task_s` = > json.stringify value=`任务` *
- *`fp` = "The user asked:" *
- *`fp` = `fp` + `task_s` *
- *`fp` = `fp` + ". Tool" *
- *`fp` = `fp` + `tool_name` *
- *`fp` = `fp` + "ran via subtask and returned:" *
- *`fp` = `fp` + `tool_s` *
- *`fp` = `fp` + ". Reply to the user briefly." *
+ *task_s = > json.stringify value=`任务`*
+ *fp = "The user asked:"*
+ *fp = fp + task_s*
+ *fp = fp + ". Tool"*
+ *fp = fp + tool_name*
+ *fp = fp + "ran via subtask and returned:"*
+ *fp = fp + tool_s*
+ *fp = fp + ". Reply to the user briefly."*
1. `流式`
- *`evs2` = > `model`.运行 提示=`fp` 流式=真 打印增量=`打印增量` *
- *`reply` = > 大模型.流式结果 事件=`evs2` *
+ *evs2 = > model.运行 提示=`fp` 流式=真 打印增量=`打印增量`*
+ *reply = > 大模型.流式结果 事件=`evs2`*
2. *
- *`reply` = > `model`.运行 提示=`fp` *
- *`out` = > json.set map=`out` key=tool value=`tool_name` *
- *`out` = > json.set map=`out` key=tool_result value=`tool_s` *
- *`out` = > json.set map=`out` key=result value=`reply` *
+ *reply = > model.运行 提示=`fp`*
+ *out = > json.set map=`out` key="tool" value=`tool_name`*
+ *out = > json.set map=`out` key="tool_result" value=`tool_s`*
+ *out = > json.set map=`out` key="result" value=`reply`*
2. *
- *`out` = > json.set map=`out` key=result value=`reply` *
+ *out = > json.set map=`out` key="result" value=`reply`*
-*`as_turn` = > json.parse text={"role":"assistant"} *
-*`as_turn` = > json.set map=`as_turn` key=content value=`reply` *
+*as_turn = > json.parse text={"role":"assistant"}*
+*as_turn = > json.set map=`as_turn` key="content" value=`reply`*
> agent_history_append id=`id` item=`as_turn`
1. `写回`
- *`body` = > json.stringify value=`out` *
- *`st` = > json.get value=`out` key=status *
+ *body = > json.stringify value=`out`*
+ *st = > json.get value=`out` key="status"*
1. `st` == ok
> 自写回.写回 值=`body` 键=ok
2. *
> 自写回.写回 值=`body` 键=error
2. *
- *`_` = 1*
+ *_ = 1*
-**`out`**
+**out**
## 多步
+ `目标`
@@ -228,8 +228,8 @@ import json:lib/json.mq.md
多步工作簿默认写入 OKF `知识库目录/resources/.mq.md`;仅当传入 `工作簿目录` 时才用临时 runs。转发至英文 `agent.plan`。`流式` / `打印增量` / `轨迹` 对应 `stream` / `echo` / `trace`;`软命中` → `soft_match`;`近义命中` / `近义阈值` → `near_match` / `near_threshold`。
-*`model` = > json.get value=`self` key=model *
-*`tools` = > json.get value=`self` key=tools *
-*`standing` = > json.get value=`self` key=standing *
-*`en` = > agent.agent model=`model` tools=`tools` standing=`standing` *
-**> `en`.plan goal=`目标` workbook_dir=`工作簿目录` workbook=`工作簿` max_rounds=`最大轮次` confirm=`确认分解` writeback=`写回` skeleton=`骨架` reuse=`复用` optimize=`优化` force=`强制` soft_match=`软命中` near_match=`近义命中` near_threshold=`近义阈值` promote=`晋升` kb_dir=`知识库目录` improve_every=`改进周期` explore_n=`探索次数` stream=`流式` echo=`打印增量` trace=`轨迹`**
+*model = > json.get value=`self` key="model"*
+*tools = > json.get value=`self` key="tools"*
+*standing = > json.get value=`self` key="standing"*
+*en = > agent.agent model=`model` tools=`tools` standing=`standing`*
+**> en.plan goal=`目标` workbook_dir=`工作簿目录` workbook=`工作簿` max_rounds=`最大轮次` confirm=`确认分解` writeback=`写回` skeleton=`骨架` reuse=`复用` optimize=`优化` force=`强制` soft_match=`软命中` near_match=`近义命中` near_threshold=`近义阈值` promote=`晋升` kb_dir=`知识库目录` improve_every=`改进周期` explore_n=`探索次数` stream=`流式` echo=`打印增量` trace=`轨迹`**
diff --git a/ext/quantum/quantum.mq.md b/ext/quantum/quantum.mq.md
index 26a2276..a1febfc 100644
--- a/ext/quantum/quantum.mq.md
+++ b/ext/quantum/quantum.mq.md
@@ -10,7 +10,7 @@ import json:lib/json.mq.md
Load the ABI v2 `quantum` plugin once.
-*`p` = > plugin.native_path name=quantum *
+*p = > plugin.native_path name="quantum"*
1. `p`
> plugin.load path=`p`
2. *
diff --git a/ext/quantum/量子.mq.md b/ext/quantum/量子.mq.md
index cfb67db..f5b2028 100644
--- a/ext/quantum/量子.mq.md
+++ b/ext/quantum/量子.mq.md
@@ -10,7 +10,7 @@ import json:lib/json.mq.md
加载 ABI v2 `quantum` 插件。
-*`p` = > plugin.native_path name=quantum *
+*p = > plugin.native_path name="quantum"*
1. `p`
> plugin.load path=`p`
2. *
diff --git a/ext/web/web.mq.md b/ext/web/web.mq.md
index ef4b318..2584dee 100644
--- a/ext/web/web.mq.md
+++ b/ext/web/web.mq.md
@@ -10,7 +10,7 @@ import json:lib/json.mq.md
Load the ABI v2 `web` plugin once.
-*`p` = > plugin.native_path name=web *
+*p = > plugin.native_path name="web"*
1. `p`
> plugin.load path=`p`
2. *
@@ -53,7 +53,7 @@ Embed a form into the page main slot. `listen` auto-registers `GET|POST /_form/{
Offline HTML for tests / previews.
1. `db`
- *`url` = > json.get value=`db` key=url *
+ *url = > json.get value=`db` key="url"*
**> web_render page=`self` url=`url`**
2. *
**> web_render page=`self`**
@@ -63,14 +63,14 @@ Offline HTML for tests / previews.
Style tables live as `##` exports in site style modules; compose resolves them by path.
-**`self`**
+**self**
## process
+ `style`=None
+ `name`=None
+ `path`=None
-**`self`**
+**self**
# db
+ `url`="sqlite:site.db"
@@ -82,14 +82,14 @@ Style tables live as `##` exports in site style modules; compose resolves them b
+ `name`
+ `fields`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_init url=`url` name=`name` fields=`fields`**
## insert
+ `table`
+ `rows`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_insert url=`url` table=`table` rows=`rows`**
## select
@@ -99,15 +99,15 @@ Style tables live as `##` exports in site style modules; compose resolves them b
Simple filters: one-row map of column→value (AND `=`), or rows `|字段|操作|值|` (`=` `!=` `>` `>=` `<` `<=` `like`).
-*`url` = > json.get value=`self` key=url *
-*`r` = > web_db_select url=`url` table=`table` where=`where` limit=`limit` *
-**> json.get value=`r` key=rows**
+*url = > json.get value=`self` key="url"*
+*r = > web_db_select url=`url` table=`table` where=`where` limit=`limit`*
+**> json.get value=`r` key="rows"**
## get
+ `table`
+ `id`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_get url=`url` table=`table` id=`id`**
## update
@@ -115,21 +115,21 @@ Simple filters: one-row map of column→value (AND `=`), or rows `|字段|操作
+ `id`
+ `row`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_update url=`url` table=`table` id=`id` row=`row`**
## delete
+ `table`
+ `id`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_delete url=`url` table=`table` id=`id`**
## exec
+ `sql`
+ `args`=None
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_exec url=`url` sql=`sql` args=`args`**
# form
@@ -169,7 +169,7 @@ Field table + rules table; submit writes through `# db`.
+ `data`
+ `db`
-*`url` = > json.get value=`db` key=url *
+*url = > json.get value=`db` key="url"*
**> web_form_submit form=`self` data=`data` url=`url`**
# app
diff --git a/ext/web/网页.mq.md b/ext/web/网页.mq.md
index 50627f5..48bedcc 100644
--- a/ext/web/网页.mq.md
+++ b/ext/web/网页.mq.md
@@ -10,7 +10,7 @@ import json:lib/json.mq.md
加载 ABI v2 `web` 插件。
-*`p` = > plugin.native_path name=web *
+*p = > plugin.native_path name="web"*
1. `p`
> plugin.load path=`p`
2. *
@@ -47,7 +47,7 @@ import json:lib/json.mq.md
+ `数据库`=None
1. `数据库`
- *`url` = > json.get value=`数据库` key=url *
+ *url = > json.get value=`数据库` key="url"*
**> web_render page=`self` url=`url`**
2. *
**> web_render page=`self`**
@@ -55,14 +55,14 @@ import json:lib/json.mq.md
# 样式
+ `名`=""
-**`self`**
+**self**
## 样式处理
+ `样式`=None
+ `名`=None
+ `路径`=None
-**`self`**
+**self**
# 数据库
+ `地址`="sqlite:site.db"
@@ -74,14 +74,14 @@ import json:lib/json.mq.md
+ `名`
+ `字段`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_init url=`url` name=`名` fields=`字段`**
## 插入
+ `表`
+ `行`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_insert url=`url` table=`表` rows=`行`**
## 查询
@@ -91,15 +91,15 @@ import json:lib/json.mq.md
简单条件:单行列→值映射(AND `=`),或 `|字段|操作|值|` 表(`=` `!=` `>` `>=` `<` `<=` `like`)。
-*`url` = > json.get value=`self` key=url *
-*`r` = > web_db_select url=`url` table=`表` where=`条件` limit=`上限` *
-**> json.get value=`r` key=rows**
+*url = > json.get value=`self` key="url"*
+*r = > web_db_select url=`url` table=`表` where=`条件` limit=`上限`*
+**> json.get value=`r` key="rows"**
## 获取
+ `表`
+ `id`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_get url=`url` table=`表` id=`id`**
## 更新
@@ -107,21 +107,21 @@ import json:lib/json.mq.md
+ `id`
+ `行`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_update url=`url` table=`表` id=`id` row=`行`**
## 删除
+ `表`
+ `id`
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_delete url=`url` table=`表` id=`id`**
## 执行
+ `sql`
+ `参数`=None
-*`url` = > json.get value=`self` key=url *
+*url = > json.get value=`self` key="url"*
**> web_db_exec url=`url` sql=`sql` args=`参数`**
# 表单
@@ -161,7 +161,7 @@ import json:lib/json.mq.md
+ `数据`
+ `数据库`
-*`url` = > json.get value=`数据库` key=url *
+*url = > json.get value=`数据库` key="url"*
**> web_form_submit form=`self` data=`数据` url=`url`**
# 应用
diff --git a/src/bytecode/compile.rs b/src/bytecode/compile.rs
index 7d1372b..4f10cfc 100644
--- a/src/bytecode/compile.rs
+++ b/src/bytecode/compile.rs
@@ -436,6 +436,12 @@ impl<'a> FnCompiler<'a> {
fn compile_call(&mut self, call: &CallExpr, as_stmt: bool) -> Result<()> {
let mut call = call.clone();
if let Some(path) = &call.path {
+ // Bare dotted callee `a.b`: if `a` is a local variable, it is a method
+ // receiver (Python-style unified namespace); otherwise it's a library path.
+ if path.len() == 2 && self.locals.contains_key(&path[0]) {
+ let recv = path[0].clone();
+ return self.compile_method_call(&recv, &call, as_stmt);
+ }
return self.compile_path_call(path, &call, as_stmt);
}
if let Some(path) = self.flat[self.fn_id].uses.get(&call.callee).cloned() {
diff --git a/src/interp.rs b/src/interp.rs
index 4c254ce..f95e933 100644
--- a/src/interp.rs
+++ b/src/interp.rs
@@ -546,6 +546,13 @@ impl Interpreter {
}
if let Some(path) = &call.path {
+ // Bare dotted callee `a.b`: if `a` is a local variable, it is a method
+ // receiver (Python-style unified namespace); otherwise it's a library path.
+ if path.len() == 2 && env.get(&path[0]).is_some() {
+ let recv = path[0].clone();
+ let method = path[1].clone();
+ return self.eval_method_call(module, fun, env, &recv, &method, &ev_args);
+ }
return self.eval_path_call(module, path, &ev_args);
}
diff --git a/src/parse/expr.rs b/src/parse/expr.rs
index 87cb651..db4f4d0 100644
--- a/src/parse/expr.rs
+++ b/src/parse/expr.rs
@@ -77,6 +77,36 @@ pub fn parse_call_arg_value(input: &str) -> Result {
}
}
+/// Like [`parse_call_arg_value`], but for call args inside `*…*` / `**…**`
+/// value-expression segments: a bare word is a **variable** (not a text literal).
+/// Quoted strings, hyphenated prose, and `/path` prose stay text; `` `x` `` still works.
+pub fn parse_call_arg_value_prefer_var(input: &str) -> Result {
+ let s = input.trim();
+ if s.is_empty() {
+ return Ok(Expr::Literal(Literal::Text(String::new())));
+ }
+ if s.starts_with('"') || s.starts_with('\'') {
+ return match parse_expr(s) {
+ Ok(e) => Ok(e),
+ Err(_) => Ok(parse_interp(s)),
+ };
+ }
+ if has_hyphenated_prose(s) {
+ return Ok(parse_interp(s));
+ }
+ match parse_expr_prefer_var(s) {
+ Ok(e) => Ok(e),
+ Err(_) => {
+ // `/about`, `.marqdo/x`, `nav.`nav`` etc. → prose text, not variables.
+ if s.starts_with('/') || s.contains(".`") {
+ Ok(Expr::Literal(Literal::Text(s.to_string())))
+ } else {
+ Ok(parse_interp(s))
+ }
+ }
+ }
+}
+
fn is_text_only_div_chain(e: &Expr) -> bool {
match e {
Expr::Literal(Literal::Text(_)) => true,
@@ -393,10 +423,13 @@ impl<'a> Parser<'a> {
if self.eat(">") {
// Inline call: `> name k=v`
self.skip_ws();
- return Ok(Expr::Call(parse_call_tail(self.rest()).map(|(c, consumed)| {
- self.i += consumed;
- c
- })?));
+ let prefer_var = self.prefer_var;
+ return Ok(Expr::Call(parse_call_tail(self.rest(), prefer_var).map(
+ |(c, consumed)| {
+ self.i += consumed;
+ c
+ },
+ )?));
}
if self.starts_with("True") && is_word_end(self.rest(), 4) {
self.i += 4;
@@ -591,7 +624,9 @@ fn is_word_end(s: &str, len: usize) -> bool {
/// Parse `name key=val …` / positional args; returns call + bytes consumed.
/// Callee may be a bare name, library path `time.parse`, or method `` `recv`.method ``.
-pub fn parse_call_tail(s: &str) -> Result<(CallExpr, usize)> {
+/// When `prefer_var`, bare call-arg words parse as variables and bare dotted
+/// callees are allowed to be method receivers.
+pub fn parse_call_tail(s: &str, prefer_var: bool) -> Result<(CallExpr, usize)> {
use crate::ast::Arg;
let s = s.trim_start();
@@ -627,9 +662,14 @@ pub fn parse_call_tail(s: &str) -> Result<(CallExpr, usize)> {
seen_named = true;
let val_end = find_next_arg_boundary(after_eq);
let val_raw = after_eq[..val_end].trim_end();
+ let value = if prefer_var {
+ parse_call_arg_value_prefer_var(val_raw)?
+ } else {
+ parse_call_arg_value(val_raw)?
+ };
args.push(Arg::Named {
name: key,
- value: parse_call_arg_value(val_raw)?,
+ value,
});
args_str = after_eq[val_end..].trim_start();
} else {
@@ -640,7 +680,12 @@ pub fn parse_call_tail(s: &str) -> Result<(CallExpr, usize)> {
if tok.is_empty() {
break;
}
- args.push(Arg::Positional(parse_call_arg_value(tok)?));
+ let value = if prefer_var {
+ parse_call_arg_value_prefer_var(tok)?
+ } else {
+ parse_call_arg_value(tok)?
+ };
+ args.push(Arg::Positional(value));
args_str = rest.trim_start();
}
}
@@ -804,8 +849,10 @@ fn end_of_quoted_string(s: &str) -> Option {
}
/// Parse `> callee args` call expression/statement text (without leading `>`).
-pub fn parse_call_after_gt(after_gt: &str) -> Result {
- let (call, _) = parse_call_tail(after_gt.trim())?;
+/// When `prefer_var` (inside `*…*` / `**…**`), bare call-arg words are variables
+/// and a bare dotted callee may be a method receiver (resolved at eval/compile).
+pub fn parse_call_after_gt(after_gt: &str, prefer_var: bool) -> Result {
+ let (call, _) = parse_call_tail(after_gt.trim(), prefer_var)?;
Ok(call)
}
diff --git a/src/parse/mod.rs b/src/parse/mod.rs
index 8d3f07f..5b77191 100644
--- a/src/parse/mod.rs
+++ b/src/parse/mod.rs
@@ -278,7 +278,7 @@ impl<'a> Cursor<'a> {
// Call >
if trimmed.starts_with('>') {
- let call = call_after_gt(trimmed[1..].trim())?;
+ let call = call_after_gt(trimmed[1..].trim(), false)?;
return Ok(Stmt::Call { call, span });
}
@@ -365,7 +365,10 @@ impl<'a> Cursor<'a> {
return Ok((expr, span.line));
}
if rhs.starts_with('>') {
- return Ok((Expr::Call(call_after_gt(rhs[1..].trim())?), span.line));
+ return Ok((
+ Expr::Call(call_after_gt(rhs[1..].trim(), prefer_var)?),
+ span.line,
+ ));
}
let value = if prefer_var {
parse_expr_prefer_var(rhs)?
diff --git a/tests/errors/bad-split-sep.mq.md b/tests/errors/bad-split-sep.mq.md
index d2667c3..55d9156 100644
--- a/tests/errors/bad-split-sep.mq.md
+++ b/tests/errors/bad-split-sep.mq.md
@@ -4,4 +4,4 @@ title: empty split sep
# main
-*xs = > split value=ab sep=*
+*xs = > split value="ab" sep=*
diff --git a/tests/ext/agent-inspect-fixture.mq.md b/tests/ext/agent-inspect-fixture.mq.md
index d9ed87e..911b0ae 100644
--- a/tests/ext/agent-inspect-fixture.mq.md
+++ b/tests/ext/agent-inspect-fixture.mq.md
@@ -9,22 +9,22 @@ import fs:lib/fs.mq.md
# main
*paths = > json.parse text={"f":".marqdo/agent-runs/inspect-fixture.mq.md"}*
-*fixture = > json.get value=`paths` key=f*
+*fixture = > json.get value=`paths` key="f"*
*body = > json.parse text={"t":"# main\n\n> print text=hi\n\n\n"}*
-*t = > json.get value=`body` key=t*
+*t = > json.get value=`body` key="t"*
> fs.write_text path=`fixture` text=`t`
*obs = > agent.inspect_workbook path=`fixture` exit_code=0*
-*code = > json.get value=`obs` key=exit_code*
+*code = > json.get value=`obs` key="exit_code"*
> print text=`code`
-*ok = > json.get value=`obs` key=last_ok*
-*has = > split value=`ok` sep=done*
+*ok = > json.get value=`obs` key="last_ok"*
+*has = > split value=`ok` sep="done"*
*n = > len value=`has`*
1. `n` > 1
> print text=ok-slot
2. *
> print text=ok-missing
-*err = > json.get value=`obs` key=last_error*
+*err = > json.get value=`obs` key="last_error"*
> print text=`err`
diff --git a/tests/ext/agent-kb-alias.mq.md b/tests/ext/agent-kb-alias.mq.md
index 6182bc7..bdbec24 100644
--- a/tests/ext/agent-kb-alias.mq.md
+++ b/tests/ext/agent-kb-alias.mq.md
@@ -10,7 +10,7 @@ import sys:lib/sys.mq.md
# main
-*p = > plugin.native_path name=agent*
+*p = > plugin.native_path name="agent"*
1. `p`
> plugin.load path=`p`
2. *
@@ -25,19 +25,19 @@ import sys:lib/sys.mq.md
> fs.write_text path=`wb` text=`body`
*prom = > agent_kb_promote kb_dir=`kb` goal=`goal` workbook=`wb` aliases=`alias`*
-*okp = > json.get value=`prom` key=promoted*
+*okp = > json.get value=`prom` key="promoted"*
1. `okp`
> print text=promoted
2. *
> print text=promote-fail
-*slug = > json.get value=`prom` key=slug*
+*slug = > json.get value=`prom` key="slug"*
*parts = > json.parse text={"a":"/concepts/tasks/","b":".md"}*
-*a = > json.get value=`parts` key=a*
-*b = > json.get value=`parts` key=b*
+*a = > json.get value=`parts` key="a"*
+*b = > json.get value=`parts` key="b"*
*task = kb + a + slug + b*
*src = > fs.read_text path=`task`*
-*has = > split value=`src` sep=say pong only*
+*has = > split value=`src` sep="say pong only"*
*hn = > len value=`has`*
1. `hn` > 1
> print text=alias-written
@@ -50,17 +50,17 @@ import sys:lib/sys.mq.md
2. *
> print text=alias-miss
-*mk = > json.get value=`hit` key=match*
+*mk = > json.get value=`hit` key="match"*
> print text=`mk`
-*slug_hit = > json.get value=`hit` key=slug*
+*slug_hit = > json.get value=`hit` key="slug"*
1. `slug` == `slug_hit`
> print text=same-slug
2. *
> print text=slug-drift
*exact = > agent_kb_lookup kb_dir=`kb` goal=`goal`*
-*mk2 = > json.get value=`exact` key=match*
+*mk2 = > json.get value=`exact` key="match"*
> print text=`mk2`
*g_trip = "帮我规划明天的行程"*
@@ -68,7 +68,7 @@ import sys:lib/sys.mq.md
*body2 = "---\ntitle: trip\n---\n\n# main\n\n*msg = \"trip-ok\"*\n\n**msg**\n"*
> fs.write_text path=`wb2` text=`body2`
*prom2 = > agent_kb_promote kb_dir=`kb` goal=`g_trip` workbook=`wb2`*
-*ok2 = > json.get value=`prom2` key=promoted*
+*ok2 = > json.get value=`prom2` key="promoted"*
1. `ok2`
> print text=trip-promoted
2. *
@@ -82,11 +82,11 @@ import sys:lib/sys.mq.md
> print text=canonical-ok
2. *
> print text=canonical-miss
-*mk3 = > json.get value=`hit_c` key=match*
+*mk3 = > json.get value=`hit_c` key="match"*
> print text=`mk3`
*listed = > agent_kb_list_tasks kb_dir=`kb`*
-*tc = > json.get value=`listed` key=count*
+*tc = > json.get value=`listed` key="count"*
1. `tc` > 1
> print text=list-ok
2. *
diff --git a/tests/ext/agent-kb-near.mq.md b/tests/ext/agent-kb-near.mq.md
index d2c6df5..0fa47b4 100644
--- a/tests/ext/agent-kb-near.mq.md
+++ b/tests/ext/agent-kb-near.mq.md
@@ -10,7 +10,7 @@ import sys:lib/sys.mq.md
# main
-*p = > plugin.native_path name=agent*
+*p = > plugin.native_path name="agent"*
1. `p`
> plugin.load path=`p`
2. *
@@ -24,13 +24,13 @@ import sys:lib/sys.mq.md
> fs.write_text path=`wb` text=`body`
*prom = > agent_kb_promote kb_dir=`kb` goal=`goal` workbook=`wb`*
-*okp = > json.get value=`prom` key=promoted*
+*okp = > json.get value=`prom` key="promoted"*
1. `okp`
> print text=promoted
2. *
> print text=promote-fail
-*slug = > json.get value=`prom` key=slug*
+*slug = > json.get value=`prom` key="slug"*
*g1 = "帮我规划明天行程"*
*hit1 = > agent_kb_lookup kb_dir=`kb` goal=`g1` near_match=True near_threshold=0.78*
@@ -38,9 +38,9 @@ import sys:lib/sys.mq.md
> print text=near-ok
2. *
> print text=near-miss
-*mk1 = > json.get value=`hit1` key=match*
+*mk1 = > json.get value=`hit1` key="match"*
> print text=`mk1`
-*slug1 = > json.get value=`hit1` key=slug*
+*slug1 = > json.get value=`hit1` key="slug"*
1. `slug` == `slug1`
> print text=same-slug
2. *
@@ -60,16 +60,16 @@ import sys:lib/sys.mq.md
> print text=neg-miss
*ranked = > agent_kb_near_match kb_dir=`kb` goal=`g1`*
-*best = > json.get value=`ranked` key=best*
-*bs = > json.get value=`best` key=slug*
+*best = > json.get value=`ranked` key="best"*
+*bs = > json.get value=`best` key="slug"*
1. `bs` == `slug`
> print text=rank-ok
2. *
> print text=rank-bad
-*tasks = > json.get value=`ranked` key=candidates*
+*tasks = > json.get value=`ranked` key="candidates"*
*prompt = > agent.build_soft_match_prompt goal=`g1` tasks=`tasks`*
-*has = > split value=`prompt` sep=score=*
+*has = > split value=`prompt` sep="score="*
*hn = > len value=`has`*
1. `hn` > 1
> print text=prompt-score-ok
diff --git a/tests/ext/agent-kb-reuse.mq.md b/tests/ext/agent-kb-reuse.mq.md
index c37751f..2f3ef8b 100644
--- a/tests/ext/agent-kb-reuse.mq.md
+++ b/tests/ext/agent-kb-reuse.mq.md
@@ -11,7 +11,7 @@ import sys:lib/sys.mq.md
# main
-*p = > plugin.native_path name=agent*
+*p = > plugin.native_path name="agent"*
1. `p`
> plugin.load path=`p`
2. *
@@ -19,10 +19,10 @@ import sys:lib/sys.mq.md
> sys.exit code=1
*paths = > json.parse text={"kb":".marqdo/agent-kb","wb":".marqdo/agent-runs/pong-solid.mq.md","goal":"Reply with exactly the word pong and nothing else.","body":"---\ntitle: pong skill\n---\n\n# main\n\n*msg = \"pong\"*\n\n**msg**\n"}*
-*kb = > json.get value=`paths` key=kb*
-*wb = > json.get value=`paths` key=wb*
-*goal = > json.get value=`paths` key=goal*
-*body = > json.get value=`paths` key=body*
+*kb = > json.get value=`paths` key="kb"*
+*wb = > json.get value=`paths` key="wb"*
+*goal = > json.get value=`paths` key="goal"*
+*body = > json.get value=`paths` key="body"*
> fs.write_text path=`wb` text=`body`
@@ -33,16 +33,16 @@ import sys:lib/sys.mq.md
> print text=`slug0`
*prom = > agent_kb_promote kb_dir=`kb` goal=`goal` workbook=`wb`*
-*okp = > json.get value=`prom` key=promoted*
+*okp = > json.get value=`prom` key="promoted"*
1. `okp`
> print text=promoted
2. *
> print text=promote-fail
-*st = > json.get value=`prom` key=status*
+*st = > json.get value=`prom` key="status"*
> print text=`st`
-*slug = > json.get value=`prom` key=slug*
+*slug = > json.get value=`prom` key="slug"*
> print text=`slug`
*hit = > agent_kb_lookup kb_dir=`kb` goal=`goal`*
@@ -51,16 +51,16 @@ import sys:lib/sys.mq.md
2. *
> print text=lookup-miss
-*res = > json.get value=`hit` key=resource*
+*res = > json.get value=`hit` key="resource"*
*id = > subtask.spawn path=`res`*
*waited = > subtask.wait id=`id`*
-*code = > json.get value=`waited` key=code*
-*val = > json.get value=`waited` key=value*
+*code = > json.get value=`waited` key="code"*
+*val = > json.get value=`waited` key="value"*
> print text=`code`
> print text=`val`
*hit2 = > agent_kb_lookup kb_dir=`kb` goal=`goal`*
-*res2 = > json.get value=`hit2` key=resource*
+*res2 = > json.get value=`hit2` key="resource"*
1. `res` == `res2`
> print text=stable-path
2. *
diff --git a/tests/ext/agent-lib-call.mq.md b/tests/ext/agent-lib-call.mq.md
index 821ebbd..a79a748 100644
--- a/tests/ext/agent-lib-call.mq.md
+++ b/tests/ext/agent-lib-call.mq.md
@@ -10,25 +10,25 @@ import sys:lib/sys.mq.md
# main
*parts = > json.parse text={"a":"CALL:lib.fs.exists","b":"ARGS:{\"path\":\".\"}","nl":"\n"}*
-*a = > json.get value=`parts` key=a*
-*b = > json.get value=`parts` key=b*
-*nl = > json.get value=`parts` key=nl*
+*a = > json.get value=`parts` key="a"*
+*b = > json.get value=`parts` key="b"*
+*nl = > json.get value=`parts` key="nl"*
*t_ok = a + nl + b + nl*
*act = > agent.extract_plan_act reply=`t_ok`*
-*kind = > json.get value=`act` key=kind*
-*name = > json.get value=`act` key=name*
+*kind = > json.get value=`act` key="kind"*
+*name = > json.get value=`act` key="name"*
> print text=`kind`
> print text=`name`
-*out = > agent.run_parent_tool name=`name` path=. reply=`t_ok`*
+*out = > agent.run_parent_tool name=`name` path="." reply=`t_ok`*
1. `out`
> print text=exists-ok
2. *
> print text=exists-bad
-*deny = > agent.run_parent_tool name=lib.net.get path=. reply=CALL:lib.net.get*
+*deny = > agent.run_parent_tool name="lib.net.get" path="." reply="CALL:lib.net.get"*
*sep = > json.parse text={"s":"not allowed"}*
-*s = > json.get value=`sep` key=s*
+*s = > json.get value=`sep` key="s"*
*dparts = > split value=`deny` sep=`s`*
*pn = > len value=`dparts`*
1. `pn` > 1
@@ -37,7 +37,7 @@ import sys:lib/sys.mq.md
> print text=deny-bad
*cat = > agent.lib_catalog*
-*callable = > json.get value=`cat` key=callable*
+*callable = > json.get value=`cat` key="callable"*
*cn = > len value=`callable`*
1. `cn` > 3
> print text=callable-ok
diff --git a/tests/ext/agent-plan-confirm.mq.md b/tests/ext/agent-plan-confirm.mq.md
index 41e5aad..9f51593 100644
--- a/tests/ext/agent-plan-confirm.mq.md
+++ b/tests/ext/agent-plan-confirm.mq.md
@@ -13,14 +13,14 @@ import fs:lib/fs.mq.md
*model = > llm.llm*
*tools = > json.parse text=[]*
-*助手 = > agent.agent model=`model` tools=`tools` standing=offline plan confirm*
+*助手 = > agent.agent model=`model` tools=`tools` standing="offline plan confirm"*
-*out = > `助手`.plan goal=say hi confirm=True workbook_dir=".marqdo/agent-runs" writeback=False*
+*out = > `助手`.plan goal="say hi" confirm=True workbook_dir=".marqdo/agent-runs" writeback=False*
-*st = > json.get value=`out` key=status*
+*st = > json.get value=`out` key="status"*
> print text=`st`
-*path = > json.get value=`out` key=workbook*
+*path = > json.get value=`out` key="workbook"*
*ex = > fs.exists path=`path`*
1. `ex`
> print text=workbook-ok
@@ -28,7 +28,7 @@ import fs:lib/fs.mq.md
> print text=workbook-missing
*src = > fs.read_text path=`path`*
-*parts = > split value=`src` sep=agent.agent*
+*parts = > split value=`src` sep="agent.agent"*
*n = > len value=`parts`*
1. `n` > 1
> print text=skeleton-ok
diff --git a/tests/ext/agent-plan-decision.mq.md b/tests/ext/agent-plan-decision.mq.md
index fa704f8..b1eadf3 100644
--- a/tests/ext/agent-plan-decision.mq.md
+++ b/tests/ext/agent-plan-decision.mq.md
@@ -9,25 +9,25 @@ import fs:lib/fs.mq.md
# main
*samples = > json.parse text={"done":"DECISION: DONE\nSUMMARY: all good\n","cont":"DECISION: CONTINUE\nPATCH:\n<<<\nFIND\nold\n===\nREPLACE\nnew\n>>>\n","zh":"决定:完成\n汇总:好了\n","run":"DECISION: RUN\n","zh_run":"决定:运行\n"}*
-*d1 = > json.get value=`samples` key=done*
+*d1 = > json.get value=`samples` key="done"*
*r1 = > agent.extract_plan_decision reply=`d1`*
> print text=`r1`
*s1 = > agent.extract_plan_summary reply=`d1`*
> print text=`s1`
-*d2 = > json.get value=`samples` key=cont*
+*d2 = > json.get value=`samples` key="cont"*
*r2 = > agent.extract_plan_decision reply=`d2`*
> print text=`r2`
-*d3 = > json.get value=`samples` key=zh*
+*d3 = > json.get value=`samples` key="zh"*
*r3 = > agent.extract_plan_decision reply=`d3`*
> print text=`r3`
-*d4 = > json.get value=`samples` key=run*
+*d4 = > json.get value=`samples` key="run"*
*r4 = > agent.extract_plan_decision reply=`d4`*
> print text=`r4`
-*d5 = > json.get value=`samples` key=zh_run*
+*d5 = > json.get value=`samples` key="zh_run"*
*r5 = > agent.extract_plan_decision reply=`d5`*
> print text=`r5`
@@ -37,47 +37,47 @@ import fs:lib/fs.mq.md
*act_call = "CALL:lib_catalog"*
*a1 = > agent.extract_plan_act reply=`act_call`*
-*a1k = > json.get value=`a1` key=kind*
-*a1n = > json.get value=`a1` key=name*
+*a1k = > json.get value=`a1` key="kind"*
+*a1n = > json.get value=`a1` key="name"*
> print text=`a1k`
> print text=`a1n`
*act_read = "READ:stderr"*
*a2 = > agent.extract_plan_act reply=`act_read`*
-*a2k = > json.get value=`a2` key=kind*
-*a2n = > json.get value=`a2` key=name*
+*a2k = > json.get value=`a2` key="kind"*
+*a2n = > json.get value=`a2` key="name"*
> print text=`a2k`
> print text=`a2n`
-*act_dec = > json.get value=`samples` key=done*
+*act_dec = > json.get value=`samples` key="done"*
*a3 = > agent.extract_plan_act reply=`act_dec`*
-*a3k = > json.get value=`a3` key=kind*
+*a3k = > json.get value=`a3` key="kind"*
> print text=`a3k`
*cat = > agent.lib_catalog*
-*files = > json.get value=`cat` key=files*
+*files = > json.get value=`cat` key="files"*
*nf = > len value=`files`*
1. `nf` > 5
> print text=catalog-ok
2. *
> print text=catalog-bad
-*dual = > agent.render_workbook_skeleton goal=demo skeleton=dual*
-*has_r = > split value=`dual` sep=research*
+*dual = > agent.render_workbook_skeleton goal="demo" skeleton="dual"*
+*has_r = > split value=`dual` sep="research"*
*n_r = > len value=`has_r`*
1. `n_r` > 1
> print text=dual-ok
2. *
> print text=dual-missing
-*has_s = > split value=`dual` sep=Solidify*
+*has_s = > split value=`dual` sep="Solidify"*
*n_s = > len value=`has_s`*
1. `n_s` > 1
> print text=solidify-ok
2. *
> print text=solidify-missing
-*has_imp = > split value=`dual` sep=import llm:ext/ai/llm.mq.md*
+*has_imp = > split value=`dual` sep="import llm:ext/ai/llm.mq.md"*
*n_imp = > len value=`has_imp`*
1. `n_imp` > 1
> print text=import-ok
@@ -85,19 +85,19 @@ import fs:lib/fs.mq.md
> print text=import-missing
*paths = > json.parse text={"p":".marqdo/agent-runs/decision-patch.md","t":"keep old keep","fence":"alpha beta","p2":".marqdo/agent-runs/decision-fence.md"}*
-*path = > json.get value=`paths` key=p*
-*seed = > json.get value=`paths` key=t*
+*path = > json.get value=`paths` key="p"*
+*seed = > json.get value=`paths` key="t"*
> fs.write_text path=`path` text=`seed`
*n = > fs.apply_patch_blocks path=`path` text=`d2`*
> print text=`n`
*out = > fs.read_text path=`path`*
> print text=`out`
-*path2 = > json.get value=`paths` key=p2*
-*seed2 = > json.get value=`paths` key=fence*
+*path2 = > json.get value=`paths` key="p2"*
+*seed2 = > json.get value=`paths` key="fence"*
> fs.write_text path=`path2` text=`seed2`
*fence_pack = > json.parse text={"t":"DECISION: CONTINUE\n\u0060\u0060\u0060find\nalpha\n\u0060\u0060\u0060\n\u0060\u0060\u0060replace\nALPHA\n\u0060\u0060\u0060\n"}*
-*fence_reply = > json.get value=`fence_pack` key=t*
+*fence_reply = > json.get value=`fence_pack` key="t"*
*n2 = > fs.apply_patch_blocks path=`path2` text=`fence_reply`*
> print text=`n2`
*out2 = > fs.read_text path=`path2`*
diff --git a/tests/ext/agent-plan-live.mq.md b/tests/ext/agent-plan-live.mq.md
index 6730d5d..cdb11e4 100644
--- a/tests/ext/agent-plan-live.mq.md
+++ b/tests/ext/agent-plan-live.mq.md
@@ -13,31 +13,31 @@ import fs:lib/fs.mq.md
*model = > llm.llm*
*tools = > json.parse text=[]*
-*助手 = > agent.agent model=`model` tools=`tools` standing=You are a Marqdo agent-development master. Prefer DONE when the workbook already satisfies the goal.*
+*助手 = > agent.agent model=`model` tools=`tools` standing="You are a Marqdo agent-development master. Prefer DONE when the workbook already satisfies the goal."*
-*out = > `助手`.plan goal=Reply with exactly the word pong and nothing else. max_rounds=3 writeback=False*
+*out = > `助手`.plan goal="Reply with exactly the word pong and nothing else." max_rounds=3 writeback=False*
-*st = > json.get value=`out` key=status*
+*st = > json.get value=`out` key="status"*
> print text=`st`
-*sum = > json.get value=`out` key=summary*
+*sum = > json.get value=`out` key="summary"*
1. `sum`
> print text=`sum`
2. *
> print text=no-summary
-*cache = > json.get value=`out` key=cache*
+*cache = > json.get value=`out` key="cache"*
> print text=`cache`
-*path = > json.get value=`out` key=workbook*
+*path = > json.get value=`out` key="workbook"*
*ex = > fs.exists path=`path`*
1. `ex`
> print text=workbook-ok
2. *
> print text=workbook-missing
-*out2 = > `助手`.plan goal=Reply with exactly the word pong and nothing else. max_rounds=3 writeback=False*
-*st2 = > json.get value=`out2` key=status*
+*out2 = > `助手`.plan goal="Reply with exactly the word pong and nothing else." max_rounds=3 writeback=False*
+*st2 = > json.get value=`out2` key="status"*
> print text=`st2`
-*cache2 = > json.get value=`out2` key=cache*
+*cache2 = > json.get value=`out2` key="cache"*
> print text=`cache2`
diff --git a/tests/ext/agent-plan-observe.mq.md b/tests/ext/agent-plan-observe.mq.md
index c518895..f893b25 100644
--- a/tests/ext/agent-plan-observe.mq.md
+++ b/tests/ext/agent-plan-observe.mq.md
@@ -8,29 +8,29 @@ import fs:lib/fs.mq.md
# main
*paths = > json.parse text={"p":".marqdo/agent-runs/observe-fixture.mq.md"}*
-*path = > json.get value=`paths` key=p*
+*path = > json.get value=`paths` key="p"*
*seed = > json.parse text={"t":"---\ntitle: fixture\n---\n\n# main\n\n\n\n*msg = \"ok\"*\n\n**msg**\n"}*
-*text = > json.get value=`seed` key=t*
+*text = > json.get value=`seed` key="t"*
> fs.write_text path=`path` text=`text`
-*obs = > agent.inspect_workbook path=`path` exit_code=0 value=ok*
+*obs = > agent.inspect_workbook path=`path` exit_code=0 value="ok"*
*compact = > agent.compact_plan_observation observation=`obs`*
-*ex = > json.get value=`compact` key=source_excerpt*
-*parts = > split value=`ex` sep=HUGE_BODY*
+*ex = > json.get value=`compact` key="source_excerpt"*
+*parts = > split value=`ex` sep="HUGE_BODY"*
*n = > len value=`parts`*
1. `n` == 1
> print text=excerpt-stripped
2. *
> print text=excerpt-leak
-*has = > json.get value=`compact` key=has_value*
+*has = > json.get value=`compact` key="has_value"*
1. `has`
> print text=has-value-ok
2. *
> print text=has-value-bad
-*deep = > agent.plan_read_deepen observation=`obs` kind=source path=`path`*
-*ex2 = > json.get value=`deep` key=source_excerpt*
+*deep = > agent.plan_read_deepen observation=`obs` kind="source" path=`path`*
+*ex2 = > json.get value=`deep` key="source_excerpt"*
1. `ex2`
> print text=read-source-ok
2. *
diff --git a/tests/ext/agent-plan-stream-offline.mq.md b/tests/ext/agent-plan-stream-offline.mq.md
index 9d21609..31c0f85 100644
--- a/tests/ext/agent-plan-stream-offline.mq.md
+++ b/tests/ext/agent-plan-stream-offline.mq.md
@@ -10,34 +10,34 @@ import fs:lib/fs.mq.md
# main
*events = > json.parse text=[]*
-*events = > agent.plan_append_round events=`events` round=1 workbook=wb.mq.md exit_code=0 stream=True*
+*events = > agent.plan_append_round events=`events` round=1 workbook="wb.mq.md" exit_code=0 stream=True*
*from = > json.parse text=[{"type":"delta","text":"Hi"},{"type":"done","result":"Hi"}]*
*events = > agent.plan_merge_deltas events=`events` from=`from` stream=True*
-*events = > agent.plan_append_decision events=`events` decision=DONE stream=True summary=ok*
+*events = > agent.plan_append_decision events=`events` decision="DONE" stream=True summary="ok"*
*out = > json.parse text={"status":"ok"}*
-*out = > agent.plan_finish_stream out=`out` events=`events` stream=True result=child*
+*out = > agent.plan_finish_stream out=`out` events=`events` stream=True result="child"*
-*evs = > json.get value=`out` key=events*
+*evs = > json.get value=`out` key="events"*
*n = > len value=`evs`*
> print text=`n`
*e0 = > at value=`evs` index=0*
-*t0 = > json.get value=`e0` key=type*
+*t0 = > json.get value=`e0` key="type"*
> print text=`t0`
*e1 = > at value=`evs` index=1*
-*t1 = > json.get value=`e1` key=type*
-*x1 = > json.get value=`e1` key=text*
+*t1 = > json.get value=`e1` key="type"*
+*x1 = > json.get value=`e1` key="text"*
> print text=`t1`
> print text=`x1`
*e2 = > at value=`evs` index=2*
-*t2 = > json.get value=`e2` key=type*
+*t2 = > json.get value=`e2` key="type"*
> print text=`t2`
*e3 = > at value=`evs` index=3*
-*t3 = > json.get value=`e3` key=type*
-*r3 = > json.get value=`e3` key=result*
+*t3 = > json.get value=`e3` key="type"*
+*r3 = > json.get value=`e3` key="result"*
> print text=`t3`
> print text=`r3`
@@ -45,27 +45,27 @@ import fs:lib/fs.mq.md
*model = > llm.llm*
*tools = > json.parse text=[]*
-*助手 = > agent.agent model=`model` tools=`tools` standing=offline plan stream*
+*助手 = > agent.agent model=`model` tools=`tools` standing="offline plan stream"*
-*pout = > `助手`.plan goal=say hi confirm=True workbook_dir=".marqdo/agent-runs" writeback=False stream=True*
+*pout = > `助手`.plan goal="say hi" confirm=True workbook_dir=".marqdo/agent-runs" writeback=False stream=True*
-*st = > json.get value=`pout` key=status*
+*st = > json.get value=`pout` key="status"*
> print text=`st`
-*pevs = > json.get value=`pout` key=events*
+*pevs = > json.get value=`pout` key="events"*
*pn = > len value=`pevs`*
> print text=`pn`
*plast = > at value=`pevs` index=0*
-*pt = > json.get value=`plast` key=type*
+*pt = > json.get value=`plast` key="type"*
> print text=`pt`
-*aev = > agent.plan_echo_await round=2 workbook=wb.mq.md stream=True*
-*at = > json.get value=`aev` key=type*
+*aev = > agent.plan_echo_await round=2 workbook="wb.mq.md" stream=True*
+*at = > json.get value=`aev` key="type"*
> print text=`at`
-*ar = > json.get value=`aev` key=round*
+*ar = > json.get value=`aev` key="round"*
> print text=`ar`
-*dev = > agent.plan_echo_decompose workbook=wb.mq.md stream=True*
-*dt = > json.get value=`dev` key=type*
+*dev = > agent.plan_echo_decompose workbook="wb.mq.md" stream=True*
+*dt = > json.get value=`dev` key="type"*
> print text=`dt`
diff --git a/tests/ext/agent-run-live.mq.md b/tests/ext/agent-run-live.mq.md
index bb57e61..64aca4a 100644
--- a/tests/ext/agent-run-live.mq.md
+++ b/tests/ext/agent-run-live.mq.md
@@ -11,7 +11,7 @@ import agent:ext/ai/agent.mq.md
## 获取时间
*u = > time.now_unix*
-*s = > time.format unix=`u` pattern=%Y-%m-%d*
+*s = > time.format unix=`u` pattern="%Y-%m-%d"*
**s**
# main
@@ -25,25 +25,25 @@ import agent:ext/ai/agent.mq.md
|------|
| 获取时间 |
-*助手 = > agent.agent model=`模型` tools=`工具表` standing=You are a Marqdo agent. When you need the current date, reply with exactly one line CALL:获取时间 and nothing else.*
+*助手 = > agent.agent model=`模型` tools=`工具表` standing="You are a Marqdo agent. When you need the current date, reply with exactly one line CALL:获取时间 and nothing else."*
-*out = > `助手`.step task=请调用获取时间工具,然后用一句话告诉用户今天的日期。*
+*out = > `助手`.step task="请调用获取时间工具,然后用一句话告诉用户今天的日期。"*
-*status = > json.get value=`out` key=status*
-*回复 = > json.get value=`out` key=result*
+*status = > json.get value=`out` key="status"*
+*回复 = > json.get value=`out` key="result"*
> print text=`回复`
-*cached = > writeback.get key=ok*
+*cached = > writeback.get key="ok"*
1. `cached`
> print text=writeback-ok
2. *
> print text=writeback-missing
-*id = > json.get value=`助手` key=id*
+*id = > json.get value=`助手` key="id"*
*历史 = > agent_history_get id=`id`*
*条数 = > len value=`历史`*
> print text=`条数`
diff --git a/tests/ext/agent-smoke.mq.md b/tests/ext/agent-smoke.mq.md
index f092145..d692c53 100644
--- a/tests/ext/agent-smoke.mq.md
+++ b/tests/ext/agent-smoke.mq.md
@@ -9,7 +9,7 @@ import agent:ext/ai/agent.mq.md
## 获取时间
*esc = > json.parse text={"v":"ok-time"}*
-**> json.get value=`esc` key=v**
+**> json.get value=`esc` key="v"**
# main
@@ -21,34 +21,34 @@ import agent:ext/ai/agent.mq.md
| 获取时间 |
*模型 = > llm.llm*
-*助手 = > agent.agent model=`模型` tools=`工具表` standing=you are a readable Marqdo agent*
+*助手 = > agent.agent model=`模型` tools=`工具表` standing="you are a readable Marqdo agent"*
-*id = > json.get value=`助手` key=id*
+*id = > json.get value=`助手` key="id"*
-*ctx = > agent.build_step_context agent=`助手` task=probe*
+*ctx = > agent.build_step_context agent=`助手` task="probe"*
-*has_skill = > split value=`ctx` sep=Marqdo*
+*has_skill = > split value=`ctx` sep="Marqdo"*
*sk_n = > len value=`has_skill`*
1. `sk_n` > 1
> print text=skill-ok
2. *
> print text=skill-missing
-*has_tools = > split value=`ctx` sep=获取时间*
+*has_tools = > split value=`ctx` sep="获取时间"*
*tool_n = > len value=`has_tools`*
1. `tool_n` > 1
> print text=tools-ok
2. *
> print text=tools-missing
-*has_src = > split value=`ctx` sep=probe*
+*has_src = > split value=`ctx` sep="probe"*
*src_n = > len value=`has_src`*
1. `src_n` > 1
> print text=source-ok
2. *
> print text=source-missing
-*has_act = > split value=`ctx` sep=CALL:*
+*has_act = > split value=`ctx` sep="CALL:"*
*act_n = > len value=`has_act`*
1. `act_n` > 1
> print text=protocol-ok
@@ -56,15 +56,15 @@ import agent:ext/ai/agent.mq.md
> print text=protocol-missing
*samples = > json.parse text={"r":"CALL:获取时间","m":"think\nCALL:获取时间"}*
-*raw1 = > json.get value=`samples` key=r*
+*raw1 = > json.get value=`samples` key="r"*
*name1 = > agent.extract_tool_name reply=`raw1`*
> print text=`name1`
-*raw2 = > json.get value=`samples` key=m*
+*raw2 = > json.get value=`samples` key="m"*
*name2 = > agent.extract_tool_name reply=`raw2`*
> print text=`name2`
-*tool_out = > agent.run_tool tools=`工具表` name=获取时间*
+*tool_out = > agent.run_tool tools=`工具表` name="获取时间"*
> print text=`tool_out`
*turn = > json.parse text={"role":"user","content":"one"}*
@@ -83,5 +83,5 @@ import agent:ext/ai/agent.mq.md
> print text=`n2`
*site = > agent_call_site*
-*fn = > json.get value=`site` key=function*
+*fn = > json.get value=`site` key="function"*
> print text=`fn`
diff --git a/tests/ext/agent-soft-match.mq.md b/tests/ext/agent-soft-match.mq.md
index 85cf2da..f931a22 100644
--- a/tests/ext/agent-soft-match.mq.md
+++ b/tests/ext/agent-soft-match.mq.md
@@ -8,25 +8,25 @@ import json:lib/json.mq.md
# main
*samples = > json.parse text={"reuse":"DECISION: REUSE\nSLUG: trip-plan\n","new":"DECISION: NEW\n","zh":"决定:复用\n标识:行程-a\n"}*
-*r1 = > json.get value=`samples` key=reuse*
+*r1 = > json.get value=`samples` key="reuse"*
*d1 = > agent.extract_plan_decision reply=`r1`*
> print text=`d1`
*s1 = > agent.extract_soft_match_slug reply=`r1`*
> print text=`s1`
-*r2 = > json.get value=`samples` key=new*
+*r2 = > json.get value=`samples` key="new"*
*d2 = > agent.extract_plan_decision reply=`r2`*
> print text=`d2`
-*r3 = > json.get value=`samples` key=zh*
+*r3 = > json.get value=`samples` key="zh"*
*d3 = > agent.extract_plan_decision reply=`r3`*
> print text=`d3`
*s3 = > agent.extract_soft_match_slug reply=`r3`*
> print text=`s3`
*tasks = > json.parse text=[{"slug":"a","title":"Alpha"},{"slug":"b","title":"Beta"}]*
-*prompt = > agent.build_soft_match_prompt goal=demo tasks=`tasks`*
-*has = > split value=`prompt` sep=DECISION: REUSE*
+*prompt = > agent.build_soft_match_prompt goal="demo" tasks=`tasks`*
+*has = > split value=`prompt` sep="DECISION: REUSE"*
*n = > len value=`has`*
1. `n` > 1
> print text=prompt-ok
diff --git a/tests/ext/fs-text-patch.mq.md b/tests/ext/fs-text-patch.mq.md
index 0105d2e..2241f0c 100644
--- a/tests/ext/fs-text-patch.mq.md
+++ b/tests/ext/fs-text-patch.mq.md
@@ -7,8 +7,8 @@ import json:lib/json.mq.md
# main
*paths = > json.parse text={"p":".marqdo/agent-runs/patch-demo.md","t":"alpha beta gamma"}*
-*path = > json.get value=`paths` key=p*
-*seed = > json.get value=`paths` key=t*
+*path = > json.get value=`paths` key="p"*
+*seed = > json.get value=`paths` key="t"*
> fs.write_text path=`path` text=`seed`
> fs.text_patch path=`path` find=beta replace=BETA
@@ -16,7 +16,7 @@ import json:lib/json.mq.md
> print text=`s1`
*reply = > json.parse text={"t":"DECISION: CONTINUE\n<<<\nFIND\nalpha\n===\nREPLACE\nALPHA\n>>>\n<<<\nFIND\ngamma\n===\nREPLACE\nGAMMA\n>>>\n"}*
-*t = > json.get value=`reply` key=t*
+*t = > json.get value=`reply` key="t"*
*n = > fs.apply_patch_blocks path=`path` text=`t`*
> print text=`n`
*s2 = > fs.read_text path=`path`*
diff --git a/tests/ext/llm-complete.mq.md b/tests/ext/llm-complete.mq.md
index b596d86..9b9b5f1 100644
--- a/tests/ext/llm-complete.mq.md
+++ b/tests/ext/llm-complete.mq.md
@@ -10,6 +10,6 @@ import llm:ext/ai/llm.mq.md
*model = > llm.llm*
-*reply = > `model`.complete prompt=Reply with exactly one English word: pong*
+*reply = > `model`.complete prompt="Reply with exactly one English word: pong"*
> print text=`reply`
diff --git a/tests/ext/llm-stream-live.mq.md b/tests/ext/llm-stream-live.mq.md
index 1ea5226..0db5210 100644
--- a/tests/ext/llm-stream-live.mq.md
+++ b/tests/ext/llm-stream-live.mq.md
@@ -11,7 +11,7 @@ import json:lib/json.mq.md
*model = > llm.llm*
-*events = > `model`.complete prompt=Reply with exactly one English word: pong stream=True echo=True*
+*events = > `model`.complete prompt="Reply with exactly one English word: pong" stream=True echo=True*
*n = > len value=`events`*
> print text=`n`
diff --git a/tests/ext/quantum-amp-damp-smoke.mq.md b/tests/ext/quantum-amp-damp-smoke.mq.md
index 5087341..e4a5750 100644
--- a/tests/ext/quantum-amp-damp-smoke.mq.md
+++ b/tests/ext/quantum-amp-damp-smoke.mq.md
@@ -8,7 +8,7 @@ import quantum:ext/quantum/quantum.mq.md
*qc = > quantum.circuit qubits=1*
*qc = > `qc`.x qubit=0*
-*qc = > `qc`.noise kind=amplitude_damping p=1*
+*qc = > `qc`.noise kind="amplitude_damping" p=1*
*r = > `qc`.run shots=32 seed=7*
*c0 = r[^counts][^0]*
diff --git a/tests/ext/quantum-amp-damp-zh-smoke.mq.md b/tests/ext/quantum-amp-damp-zh-smoke.mq.md
index 0cd3ba2..a448569 100644
--- a/tests/ext/quantum-amp-damp-zh-smoke.mq.md
+++ b/tests/ext/quantum-amp-damp-zh-smoke.mq.md
@@ -8,7 +8,7 @@ description: 泡利X 后 振幅阻尼 p=1 全部落回 |0⟩.
*qc = > 量子.电路 比特数=1*
*qc = > `qc`.泡利X 比特=0*
-*qc = > `qc`.噪声 种类=振幅阻尼 概率=1*
+*qc = > `qc`.噪声 种类="振幅阻尼" 概率=1*
*r = > `qc`.运行 次数=32 种子=7*
*c0 = r[^counts][^0]*
diff --git a/tests/ext/quantum-author-api-smoke.mq.md b/tests/ext/quantum-author-api-smoke.mq.md
index 4b122d4..f340340 100644
--- a/tests/ext/quantum-author-api-smoke.mq.md
+++ b/tests/ext/quantum-author-api-smoke.mq.md
@@ -19,7 +19,7 @@ import quantum:ext/quantum/quantum.mq.md
2. *
> print text=state-fail
-*img = > `qc`.draw path=quantum-author-draw.svg*
+*img = > `qc`.draw path="quantum-author-draw.svg"*
*kind = img[^kind]*
1. `kind` == circuit
> print text=draw-ok
diff --git a/tests/ext/quantum-author-api-zh-smoke.mq.md b/tests/ext/quantum-author-api-zh-smoke.mq.md
index e4a5297..5e5db79 100644
--- a/tests/ext/quantum-author-api-zh-smoke.mq.md
+++ b/tests/ext/quantum-author-api-zh-smoke.mq.md
@@ -19,7 +19,7 @@ description: 屏障 / 测量 / 追加 / 态 / 绘图.
2. *
> print text=state-fail
-*img = > `qc`.绘图 路径=quantum-author-zh-draw.svg*
+*img = > `qc`.绘图 路径="quantum-author-zh-draw.svg"*
*kind = img[^kind]*
1. `kind` == circuit
> print text=draw-ok
diff --git a/tests/ext/quantum-custom-gate-smoke.mq.md b/tests/ext/quantum-custom-gate-smoke.mq.md
index 6abc85a..bb60008 100644
--- a/tests/ext/quantum-custom-gate-smoke.mq.md
+++ b/tests/ext/quantum-custom-gate-smoke.mq.md
@@ -12,7 +12,7 @@ $$
\frac{1}{\sqrt{2}}\begin{pmatrix}1&1\\1&-1\end{pmatrix}
$$
-*U = > quantum.gate matrix=`H_matrix` name=U*
+*U = > quantum.gate matrix=`H_matrix` name="U"*
*qc = > quantum.circuit qubits=1*
*qc = > `qc`.apply gate=`U` qubits=0*
*p = > `qc`.probabilities*
diff --git a/tests/ext/quantum-custom-gate-zh-smoke.mq.md b/tests/ext/quantum-custom-gate-zh-smoke.mq.md
index f9c7f03..ebeb15d 100644
--- a/tests/ext/quantum-custom-gate-zh-smoke.mq.md
+++ b/tests/ext/quantum-custom-gate-zh-smoke.mq.md
@@ -12,7 +12,7 @@ $$
\frac{1}{\sqrt{2}}\begin{pmatrix}1&1\\1&-1\end{pmatrix}
$$
-*U = > 量子.门 矩阵=`H矩阵` 名=U*
+*U = > 量子.门 矩阵=`H矩阵` 名="U"*
*qc = > 量子.电路 比特数=1*
*qc = > `qc`.施加 门=`U` 比特=0*
*p = > `qc`.概率*
diff --git a/tests/ext/quantum-draw-smoke.mq.md b/tests/ext/quantum-draw-smoke.mq.md
index 5569a80..39f54ab 100644
--- a/tests/ext/quantum-draw-smoke.mq.md
+++ b/tests/ext/quantum-draw-smoke.mq.md
@@ -14,7 +14,7 @@ import quantum:ext/quantum/quantum.mq.md
| 2 | CX | 0,1 |
*qc = > quantum.circuit qubits=2 steps=`steps`*
-*img = > `qc`.draw kind=probs path=quantum-draw-probs.svg*
+*img = > `qc`.draw kind="probs" path="quantum-draw-probs.svg"*
*kind = img[^kind]*
1. `kind` == probs
@@ -24,7 +24,7 @@ import quantum:ext/quantum/quantum.mq.md
*qc1 = > quantum.circuit qubits=1*
*qc1 = > `qc1`.h qubit=0*
-*bloch = > `qc1`.draw kind=bloch path=quantum-draw-bloch.svg*
+*bloch = > `qc1`.draw kind="bloch" path="quantum-draw-bloch.svg"*
*bk = bloch[^kind]*
1. `bk` == bloch
diff --git a/tests/ext/quantum-gate-heatmap-smoke.mq.md b/tests/ext/quantum-gate-heatmap-smoke.mq.md
index bb8e228..826657e 100644
--- a/tests/ext/quantum-gate-heatmap-smoke.mq.md
+++ b/tests/ext/quantum-gate-heatmap-smoke.mq.md
@@ -6,8 +6,8 @@ import quantum:ext/quantum/quantum.mq.md
# main
-*H = > quantum.gate name=H*
-*img = > `H`.draw kind=matrix path=quantum-gate-heatmap.svg*
+*H = > quantum.gate name="H"*
+*img = > `H`.draw kind="matrix" path="quantum-gate-heatmap.svg"*
*kind = img[^kind]*
1. `kind` == matrix
diff --git a/tests/ext/quantum-gate-matrix-smoke.mq.md b/tests/ext/quantum-gate-matrix-smoke.mq.md
index c50cafb..9aec0bd 100644
--- a/tests/ext/quantum-gate-matrix-smoke.mq.md
+++ b/tests/ext/quantum-gate-matrix-smoke.mq.md
@@ -8,7 +8,7 @@ import json:lib/json.mq.md
# main
*H_matrix = > json.parse text=[[0.7071067811865475,0.7071067811865475],[0.7071067811865475,-0.7071067811865475]]*
-*H = > quantum.gate name=H*
+*H = > quantum.gate name="H"*
*ok = > `H`.matches_matrix matrix=`H_matrix`*
1. `ok`
diff --git a/tests/ext/quantum-noise-smoke.mq.md b/tests/ext/quantum-noise-smoke.mq.md
index 5491594..8b6c310 100644
--- a/tests/ext/quantum-noise-smoke.mq.md
+++ b/tests/ext/quantum-noise-smoke.mq.md
@@ -8,7 +8,7 @@ import quantum:ext/quantum/quantum.mq.md
*qc = > quantum.circuit qubits=1*
*qc = > `qc`.i qubit=0*
-*qc = > `qc`.noise kind=bitflip p=1*
+*qc = > `qc`.noise kind="bitflip" p=1*
*r = > `qc`.run shots=32 seed=3*
*c1 = r[^counts][^1]*
diff --git a/tests/ext/quantum-noise-zh-smoke.mq.md b/tests/ext/quantum-noise-zh-smoke.mq.md
index 07e80d6..0487dc0 100644
--- a/tests/ext/quantum-noise-zh-smoke.mq.md
+++ b/tests/ext/quantum-noise-zh-smoke.mq.md
@@ -8,7 +8,7 @@ description: 噪声 bitflip p=1 后 I 使全部射中 |1⟩.
*qc = > 量子.电路 比特数=1*
*qc = > `qc`.单位 比特=0*
-*qc = > `qc`.噪声 种类=bitflip 概率=1*
+*qc = > `qc`.噪声 种类="bitflip" 概率=1*
*r = > `qc`.运行 次数=32 种子=3*
*c1 = r[^counts][^1]*
diff --git a/tests/ext/quantum-steps-smoke.mq.md b/tests/ext/quantum-steps-smoke.mq.md
index eb13cea..3221e25 100644
--- a/tests/ext/quantum-steps-smoke.mq.md
+++ b/tests/ext/quantum-steps-smoke.mq.md
@@ -28,7 +28,7 @@ import math:lib/math.mq.md
2. *
> print text=steps-fail
-*img = > `qc`.draw path=quantum-steps-draw.svg*
+*img = > `qc`.draw path="quantum-steps-draw.svg"*
*kind = img[^kind]*
1. `kind` == circuit
diff --git a/tests/ext/web-admin-smoke.mq.md b/tests/ext/web-admin-smoke.mq.md
index 710761c..6984ed1 100644
--- a/tests/ext/web-admin-smoke.mq.md
+++ b/tests/ext/web-admin-smoke.mq.md
@@ -13,18 +13,18 @@ import json:lib/json.mq.md
> `store`.init name=articles fields=`schema`
> `store`.exec sql="DELETE FROM articles"
> `store`.exec sql="DELETE FROM sqlite_sequence WHERE name='articles'"
-*url = > json.get value=`store` key=url*
+*url = > json.get value=`store` key="url"*
-*info = > web_db_table_info url=`url` table=articles*
-*cols = > json.get value=`info` key=columns*
+*info = > web_db_table_info url=`url` table="articles"*
+*cols = > json.get value=`info` key="columns"*
*n = > len value=`cols`*
1. `n` >= 2
> print text=schema-ok
2. *
> print text=schema-fail
-*fnew = > web_form_from_schema url=`url` table=articles action=insert*
-*fields = > json.get value=`fnew` key=fields*
+*fnew = > web_form_from_schema url=`url` table="articles" action="insert"*
+*fields = > json.get value=`fnew` key="fields"*
*nf = > len value=`fields`*
1. `nf` >= 1
> print text=new-form-ok
@@ -38,20 +38,20 @@ import json:lib/json.mq.md
| Admin create | via schema form |
*sub = > web_form_submit form=`fnew` data=`row` url=`url`*
-*sok = > json.get value=`sub` key=ok*
+*sok = > json.get value=`sub` key="ok"*
1. `sok`
> print text=insert-ok
2. *
> print text=insert-fail
-*got = > `store`.get table=articles id=1*
-*title = > json.get value=`got` key=title*
+*got = > `store`.get table="articles" id=1*
+*title = > json.get value=`got` key="title"*
1. `title` == "Admin create"
> print text=get-ok
2. *
> print text=get-fail
-*fedit = > web_form_from_schema url=`url` table=articles action=update id=1*
+*fedit = > web_form_from_schema url=`url` table="articles" action="update" id=1*
`patch` =
| title | body |
@@ -59,14 +59,14 @@ import json:lib/json.mq.md
| Admin edited | body updated |
*up = > web_form_submit form=`fedit` data=`patch` url=`url`*
-*uok = > json.get value=`up` key=ok*
+*uok = > json.get value=`up` key="ok"*
1. `uok`
> print text=update-ok
2. *
> print text=update-fail
-*got2 = > `store`.get table=articles id=1*
-*title2 = > json.get value=`got2` key=title*
+*got2 = > `store`.get table="articles" id=1*
+*title2 = > json.get value=`got2` key="title"*
1. `title2` == "Admin edited"
> print text=edit-ok
2. *
@@ -79,7 +79,7 @@ import json:lib/json.mq.md
| | |
*bad = > web_form_submit form=`fnew` data=`empty` url=`url`*
-*bok = > json.get value=`bad` key=ok*
+*bok = > json.get value=`bad` key="ok"*
1. `bok`
> print text=required-should-fail
2. *
diff --git a/tests/ext/web-form-embed-smoke.mq.md b/tests/ext/web-form-embed-smoke.mq.md
index bef4fca..c185223 100644
--- a/tests/ext/web-form-embed-smoke.mq.md
+++ b/tests/ext/web-form-embed-smoke.mq.md
@@ -14,13 +14,13 @@ import json:lib/json.mq.md
| title | Title | text | true | |
| body | Body | textarea | false | |
-*f = > web.form table=articles action=insert*
+*f = > web.form table="articles" action="insert"*
*f = > `f`.fields fields=`fields`*
*page = > web.page title="Compose" intro="Compose
"*
-*page = > `page`.compose_form id=article form=`f`*
+*page = > `page`.compose_form id="article" form=`f`*
-*fid = > json.get value=`page` key=form_id*
+*fid = > json.get value=`page` key="form_id"*
1. `fid`
> print text=form-id-ok
2. *
diff --git a/tests/ext/web-form-smoke.mq.md b/tests/ext/web-form-smoke.mq.md
index c80967f..c250a49 100644
--- a/tests/ext/web-form-smoke.mq.md
+++ b/tests/ext/web-form-smoke.mq.md
@@ -26,7 +26,7 @@ import json:lib/json.mq.md
| title | required | Title is required |
| title | max:120 | Title is too long |
-*f = > web.form table=articles action=insert*
+*f = > web.form table="articles" action="insert"*
*f = > `f`.fields fields=`fields`*
*f = > `f`.rules rules=`rules`*
@@ -37,7 +37,7 @@ import json:lib/json.mq.md
| | hello |
*v = > `f`.validate data=`bad`*
-*ok = > json.get value=`v` key=ok*
+*ok = > json.get value=`v` key="ok"*
1. `ok`
> print text=validate-should-fail
2. *
@@ -50,20 +50,20 @@ import json:lib/json.mq.md
| From form | Body via submit |
*sub = > `f`.submit data=`good` db=`store`*
-*sok = > json.get value=`sub` key=ok*
+*sok = > json.get value=`sub` key="ok"*
1. `sok`
> print text=submit-ok
2. *
> print text=submit-fail
-*rows = > `store`.select table=articles limit=10*
+*rows = > `store`.select table="articles" limit=10*
*n = > len value=`rows`*
1. `n` >= 1
> print text=db-ok
2. *
> print text=db-fail
-*html = > `f`.render id=article*
+*html = > `f`.render id="article"*
1. `html`
> print text=render-ok
2. *
diff --git a/tests/ext/web-part-smoke.mq.md b/tests/ext/web-part-smoke.mq.md
index 7943a0a..f75475f 100644
--- a/tests/ext/web-part-smoke.mq.md
+++ b/tests/ext/web-part-smoke.mq.md
@@ -25,18 +25,18 @@ import json:lib/json.mq.md
*about = > `about`.compose_components components=`layout`*
*app = > web.app page=`home` host=127.0.0.1 port=18081*
-*app = > `app`.route path=/about page=`about`*
+*app = > `app`.route path="/about" page=`about`*
-*routes = > json.get value=`app` key=routes*
+*routes = > json.get value=`app` key="routes"*
*routed = > json.get value=`routes` key="/about"*
-*route = > json.get value=`routed` key=_route*
+*route = > json.get value=`routed` key="_route"*
1. `route` == "/about"
> print text=route-stamp-ok
2. *
> print text=route-stamp-fail
*home_html = > `home`.render*
-*home_chunks = > split value=`home_html` sep=/_part/*
+*home_chunks = > split value=`home_html` sep="/_part/"*
*hn = > len value=`home_chunks`*
1. `hn` >= 2
> print text=home-part-ok
@@ -44,7 +44,7 @@ import json:lib/json.mq.md
> print text=home-part-fail
*about_html = > `routed`.render*
-*about_chunks = > split value=`about_html` sep=/about/_part/*
+*about_chunks = > split value=`about_html` sep="/about/_part/"*
*an = > len value=`about_chunks`*
1. `an` >= 2
> print text=route-part-ok
diff --git a/tests/ext/web-route-smoke.mq.md b/tests/ext/web-route-smoke.mq.md
index ab36a5b..3f1d50f 100644
--- a/tests/ext/web-route-smoke.mq.md
+++ b/tests/ext/web-route-smoke.mq.md
@@ -10,10 +10,10 @@ import json:lib/json.mq.md
*home = > web.page title="Home" intro="Home
"*
*about = > web.page title="About" intro="About
"*
*app = > web.app page=`home` host=127.0.0.1 port=18081*
-*app = > `app`.route path=/about page=`about`*
-*app = > `app`.route path=docs page=`about`*
+*app = > `app`.route path="/about" page=`about`*
+*app = > `app`.route path="docs" page=`about`*
-*routes = > json.get value=`app` key=routes*
+*routes = > json.get value=`app` key="routes"*
*about_page = > json.get value=`routes` key="/about"*
*docs_page = > json.get value=`routes` key="/docs"*
diff --git a/tests/ext/web-select-smoke.mq.md b/tests/ext/web-select-smoke.mq.md
index 3462a2b..004dd97 100644
--- a/tests/ext/web-select-smoke.mq.md
+++ b/tests/ext/web-select-smoke.mq.md
@@ -29,7 +29,7 @@ import json:lib/json.mq.md
|-------|------|
| Alpha | first |
-*hit = > `store`.select table=articles where=`eq` limit=50*
+*hit = > `store`.select table="articles" where=`eq` limit=50*
*n = > len value=`hit`*
1. `n` == 1
> print text=map-where-ok
@@ -42,14 +42,14 @@ import json:lib/json.mq.md
|------|------|-----|
| title | like | %Alpha% |
-*like_rows = > `store`.select table=articles where=`filt` limit=50*
+*like_rows = > `store`.select table="articles" where=`filt` limit=50*
*ln = > len value=`like_rows`*
1. `ln` == 2
> print text=like-ok
2. *
> print text=like-fail
-*all = > `store`.select table=articles limit=50*
+*all = > `store`.select table="articles" limit=50*
*an = > len value=`all`*
1. `an` == 3
> print text=all-ok
diff --git a/tests/ext/web-smoke.mq.md b/tests/ext/web-smoke.mq.md
index 2f58ad2..42a3695 100644
--- a/tests/ext/web-smoke.mq.md
+++ b/tests/ext/web-smoke.mq.md
@@ -16,7 +16,7 @@ import json:lib/json.mq.md
*store = > web.db url="sqlite:web-fixtures/data/smoke.db"*
*fields = > articles.schema*
> `store`.init name=articles fields=`fields`
-*rows = > `store`.select table=articles limit=1*
+*rows = > `store`.select table="articles" limit=1*
1. `rows`
*_ = 1*
2. *
@@ -48,33 +48,33 @@ import json:lib/json.mq.md
2. *
> print text=render-fail
-*nav = > json.get value=`page` key=nav*
+*nav = > json.get value=`page` key="nav"*
1. `nav`
> print text=compose-nav-ok
2. *
> print text=compose-nav-fail
-*side = > json.get value=`page` key=sidebar*
+*side = > json.get value=`page` key="sidebar"*
1. `side`
> print text=compose-side-ok
2. *
> print text=compose-side-fail
-*css = > json.get value=`page` key=styles_css*
+*css = > json.get value=`page` key="styles_css"*
1. `css`
> print text=styles-ok
2. *
> print text=styles-fail
-*parts = > json.get value=`page` key=parts*
-*index_part = > json.get value=`parts` key=index*
+*parts = > json.get value=`page` key="parts"*
+*index_part = > json.get value=`parts` key="index"*
1. `index_part`
> print text=compose-ok
2. *
> print text=compose-fail
-*got = > `store`.get table=articles id=1*
-*title = > json.get value=`got` key=title*
+*got = > `store`.get table="articles" id=1*
+*title = > json.get value=`got` key="title"*
1. `title` == "Hello Marqdo"
> print text=db-ok
2. *
diff --git a/tests/ext/web-static-smoke.mq.md b/tests/ext/web-static-smoke.mq.md
index ff0b7f5..7beb9fc 100644
--- a/tests/ext/web-static-smoke.mq.md
+++ b/tests/ext/web-static-smoke.mq.md
@@ -9,22 +9,22 @@ import json:lib/json.mq.md
*home = > web.page title="Home"*
*app = > web.app page=`home` host=127.0.0.1 port=18081*
-*app = > `app`.static dir=web-fixtures/public mount=/static*
+*app = > `app`.static dir="web-fixtures/public" mount="/static"*
-*dir = > json.get value=`app` key=static_dir*
+*dir = > json.get value=`app` key="static_dir"*
1. `dir` == "web-fixtures/public"
> print text=dir-ok
2. *
> print text=dir-fail
-*mount = > json.get value=`app` key=static_mount*
+*mount = > json.get value=`app` key="static_mount"*
1. `mount` == "/static"
> print text=mount-ok
2. *
> print text=mount-fail
-*app2 = > `app`.static dir=assets mount=/assets*
-*m2 = > json.get value=`app2` key=static_mount*
+*app2 = > `app`.static dir="assets" mount="/assets"*
+*m2 = > json.get value=`app2` key="static_mount"*
1. `m2` == "/assets"
> print text=custom-ok
2. *
diff --git a/tests/ext/web-zh-smoke.mq.md b/tests/ext/web-zh-smoke.mq.md
index ac01295..aeb49e0 100644
--- a/tests/ext/web-zh-smoke.mq.md
+++ b/tests/ext/web-zh-smoke.mq.md
@@ -50,7 +50,7 @@ import json:lib/json.mq.md
2. *
> print text=render-fail
-*nav = > json.get value=`page` key=nav*
+*nav = > json.get value=`page` key="nav"*
1. `nav`
> print text=compose-ok
2. *
@@ -62,10 +62,10 @@ import json:lib/json.mq.md
|------|------|------|------|------|
| title | 标题 | text | true | |
-*f = > 网页.表单 表=articles 动作=插入*
+*f = > 网页.表单 表="articles" 动作="插入"*
*f = > `f`.字段 字段=`fields`*
-*page = > `page`.表单装配 id=article 表单=`f`*
-*fid = > json.get value=`page` key=form_id*
+*page = > `page`.表单装配 id="article" 表单=`f`*
+*fid = > json.get value=`page` key="form_id"*
1. `fid` == "article"
> print text=form-ok
2. *
@@ -73,8 +73,8 @@ import json:lib/json.mq.md
*app = > 网页.应用 页面=`page` 数据库=`store` 主机=127.0.0.1 端口=18082*
*about = > 网页.页面 标题="关于" 引言="关于
"*
-*app = > `app`.路由 路径=/about 页面=`about`*
-*routes = > json.get value=`app` key=routes*
+*app = > `app`.路由 路径="/about" 页面=`about`*
+*routes = > json.get value=`app` key="routes"*
*routed = > json.get value=`routes` key="/about"*
1. `routed`
> print text=route-ok
diff --git a/tests/keywords/input.mq.md b/tests/keywords/input.mq.md
index 475be85..8af5770 100644
--- a/tests/keywords/input.mq.md
+++ b/tests/keywords/input.mq.md
@@ -5,6 +5,6 @@ description: Read one stdin line (optional prompt)
# main
-*name = > input prompt=Name:*
+*name = > input prompt="Name:"*
> print text=Hello `name`!
diff --git a/tests/lib/foreign-run-lang.mq.md b/tests/lib/foreign-run-lang.mq.md
index e61bfab..4a32bf9 100644
--- a/tests/lib/foreign-run-lang.mq.md
+++ b/tests/lib/foreign-run-lang.mq.md
@@ -5,6 +5,6 @@ import foreign:lib/foreign.mq.md
# main
-*out = > foreign.run_lang lang=python source=print(2+2)*
+*out = > foreign.run_lang lang="python" source=print(2+2)*
> print text=`out`
diff --git a/tests/lib/fs-read.mq.md b/tests/lib/fs-read.mq.md
index eead508..e60ecca 100644
--- a/tests/lib/fs-read.mq.md
+++ b/tests/lib/fs-read.mq.md
@@ -5,13 +5,13 @@ import fs:lib/fs.mq.md
# main
-*ok = > fs.exists path=hello.txt*
+*ok = > fs.exists path="hello.txt"*
1. `ok`
> print text=exists
2. *
> print text=missing
-*t = > fs.read_text path=hello.txt*
+*t = > fs.read_text path="hello.txt"*
> print text=`t`
diff --git a/tests/lib/json-quote.mq.md b/tests/lib/json-quote.mq.md
index e6e300e..2e4f2b8 100644
--- a/tests/lib/json-quote.mq.md
+++ b/tests/lib/json-quote.mq.md
@@ -5,6 +5,6 @@ import json:lib/json.mq.md
# main
-*q = > json.quote text=hi*
+*q = > json.quote text="hi"*
> print text=`q`
diff --git a/tests/lib/json-roundtrip.mq.md b/tests/lib/json-roundtrip.mq.md
index 036b3f7..c7b863c 100644
--- a/tests/lib/json-roundtrip.mq.md
+++ b/tests/lib/json-roundtrip.mq.md
@@ -6,7 +6,7 @@ import json:lib/json.mq.md
# main
-*raw = > fs.read_text path=sample.json*
+*raw = > fs.read_text path="sample.json"*
*obj = > json.parse text=`raw`*
@@ -14,7 +14,7 @@ import json:lib/json.mq.md
> print text=`ty`
-*a = > json.get value=`obj` key=a*
+*a = > json.get value=`obj` key="a"*
> print text=`a`
diff --git a/tests/lib/math-formula-chain.mq.md b/tests/lib/math-formula-chain.mq.md
index 2e11404..91ce9c0 100644
--- a/tests/lib/math-formula-chain.mq.md
+++ b/tests/lib/math-formula-chain.mq.md
@@ -10,16 +10,16 @@ $$
x^3
$$
-*df = > math.diff formula=`f` var=x*
+*df = > math.diff formula=`f` var="x"*
*ty = > type `df`*
> print text=`ty`
-*df2 = > math.diff formula=`df` var=x*
+*df2 = > math.diff formula=`df` var="x"*
> print text=`df2`
-*y = > math.eval formula=`df` var=x value=2*
+*y = > math.eval formula=`df` var="x" value=2*
> print text=`y`
diff --git a/tests/lib/math-formula.mq.md b/tests/lib/math-formula.mq.md
index 3ee512f..1c2931f 100644
--- a/tests/lib/math-formula.mq.md
+++ b/tests/lib/math-formula.mq.md
@@ -14,14 +14,14 @@ $$
> print text=`ty`
-*df = > math.diff formula=`f` var=x*
+*df = > math.diff formula=`f` var="x"*
> print text=`df`
-*roots = > math.solve formula=`f` var=x*
+*roots = > math.solve formula=`f` var="x"*
> print text=`roots`
-*y = > math.eval formula=`f` var=x value=3*
+*y = > math.eval formula=`f` var="x" value=3*
> print text=`y`
diff --git a/tests/lib/math-plot.mq.md b/tests/lib/math-plot.mq.md
index 2c05834..7133f2e 100644
--- a/tests/lib/math-plot.mq.md
+++ b/tests/lib/math-plot.mq.md
@@ -10,7 +10,7 @@ $$
x^2
$$
-*svg = > math.plot formula=`f` var=x min=-2 max=2*
+*svg = > math.plot formula=`f` var="x" min=-2 max=2*
*ok = > type `svg`*
diff --git a/tests/lib/net-openai-sse-reasoning.mq.md b/tests/lib/net-openai-sse-reasoning.mq.md
index c2a3152..64b31bb 100644
--- a/tests/lib/net-openai-sse-reasoning.mq.md
+++ b/tests/lib/net-openai-sse-reasoning.mq.md
@@ -14,19 +14,19 @@ import json:lib/json.mq.md
> print text=`n`
*e0 = > at value=`events` index=0*
-*t0 = > json.get value=`e0` key=type*
-*x0 = > json.get value=`e0` key=text*
+*t0 = > json.get value=`e0` key="type"*
+*x0 = > json.get value=`e0` key="text"*
> print text=`t0`
> print text=`x0`
*e1 = > at value=`events` index=1*
-*t1 = > json.get value=`e1` key=type*
-*x1 = > json.get value=`e1` key=text*
+*t1 = > json.get value=`e1` key="type"*
+*x1 = > json.get value=`e1` key="text"*
> print text=`t1`
> print text=`x1`
*e2 = > at value=`events` index=2*
-*t2 = > json.get value=`e2` key=type*
-*r2 = > json.get value=`e2` key=result*
+*t2 = > json.get value=`e2` key="type"*
+*r2 = > json.get value=`e2` key="result"*
> print text=`t2`
> print text=`r2`
diff --git a/tests/lib/net-openai-sse.mq.md b/tests/lib/net-openai-sse.mq.md
index 4f5a988..19ddf97 100644
--- a/tests/lib/net-openai-sse.mq.md
+++ b/tests/lib/net-openai-sse.mq.md
@@ -11,12 +11,12 @@ import json:lib/json.mq.md
*events = > net.openai_sse_parse text=`fixture`*
- [`ev`](`events`)
- *t = > json.get value=`ev` key=type*
+ *t = > json.get value=`ev` key="type"*
1. `t` == "delta"
- *chunk = > json.get value=`ev` key=text*
+ *chunk = > json.get value=`ev` key="text"*
> print text=`chunk`
2. `t` == "done"
- *answer = > json.get value=`ev` key=result*
+ *answer = > json.get value=`ev` key="result"*
> print text=`answer`
3. *
> print text=bad
diff --git a/tests/lib/plugin-demo.mq.md b/tests/lib/plugin-demo.mq.md
index bfe2cc6..939e0f1 100644
--- a/tests/lib/plugin-demo.mq.md
+++ b/tests/lib/plugin-demo.mq.md
@@ -7,7 +7,7 @@ import sys:lib/sys.mq.md
# main
-*p = > sys.env_get name=MARQDO_TEST_PLUGIN*
+*p = > sys.env_get name="MARQDO_TEST_PLUGIN"*
> plugin.load path=`p`
@@ -15,6 +15,6 @@ import sys:lib/sys.mq.md
> print text=`sum`
-*echo = > demo_echo text=ok*
+*echo = > demo_echo text="ok"*
> print text=`echo`
diff --git a/tests/lib/subtask-fn.mq.md b/tests/lib/subtask-fn.mq.md
index cfb31f5..ba38c8c 100644
--- a/tests/lib/subtask-fn.mq.md
+++ b/tests/lib/subtask-fn.mq.md
@@ -8,7 +8,7 @@ import json:lib/json.mq.md
*args = > json.parse text={"n":21}*
-*id = > subtask.spawn fn=worker args=`args`*
+*id = > subtask.spawn fn="worker" args=`args`*
*v = > subtask.wait id=`id`*
diff --git a/tests/lib/subtask-quiet-io.mq.md b/tests/lib/subtask-quiet-io.mq.md
index 230c7d5..8e4c5cb 100644
--- a/tests/lib/subtask-quiet-io.mq.md
+++ b/tests/lib/subtask-quiet-io.mq.md
@@ -6,11 +6,11 @@ import json:lib/json.mq.md
# main
-*id = > subtask.spawn path=subtask-child-print.mq.md*
+*id = > subtask.spawn path="subtask-child-print.mq.md"*
*waited = > subtask.wait id=`id`*
-*code = > json.get value=`waited` key=code*
-*val = > json.get value=`waited` key=value*
-*stdout = > json.get value=`waited` key=stdout*
+*code = > json.get value=`waited` key="code"*
+*val = > json.get value=`waited` key="value"*
+*stdout = > json.get value=`waited` key="stdout"*
1. `code` == 0
1. `val` == "child_ok"
diff --git a/tests/lib/subtask-spawn.mq.md b/tests/lib/subtask-spawn.mq.md
index 9822b89..f05c02a 100644
--- a/tests/lib/subtask-spawn.mq.md
+++ b/tests/lib/subtask-spawn.mq.md
@@ -6,11 +6,11 @@ import json:lib/json.mq.md
# main
-*id = > subtask.spawn path=subtask-child.mq.md quiet=False*
+*id = > subtask.spawn path="subtask-child.mq.md" quiet=False*
*waited = > subtask.wait id=`id`*
-*code = > json.get value=`waited` key=code*
-*val = > json.get value=`waited` key=value*
+*code = > json.get value=`waited` key="code"*
+*val = > json.get value=`waited` key="value"*
1. `code` == 0
> print text=`val`
@@ -19,11 +19,11 @@ import json:lib/json.mq.md
> print text=done
-*id2 = > subtask.spawn path=subtask-child.mq.md*
+*id2 = > subtask.spawn path="subtask-child.mq.md"*
*waited2 = > subtask.wait id=`id2`*
-*code2 = > json.get value=`waited2` key=code*
-*val2 = > json.get value=`waited2` key=value*
+*code2 = > json.get value=`waited2` key="code"*
+*val2 = > json.get value=`waited2` key="value"*
1. `code2` == 0
1. `val2` == "child_ok"
diff --git a/tests/lib/sys-dotenv.mq.md b/tests/lib/sys-dotenv.mq.md
index bc5453a..958a1bf 100644
--- a/tests/lib/sys-dotenv.mq.md
+++ b/tests/lib/sys-dotenv.mq.md
@@ -10,6 +10,6 @@ import fs:lib/fs.mq.md
> sys.load_dotenv path=dotenv-fixture.env
-*v = > sys.env_get name=MARQDO_DOTENV_FIXTURE*
+*v = > sys.env_get name="MARQDO_DOTENV_FIXTURE"*
> print text=`v`
diff --git a/tests/lib/table-collections.mq.md b/tests/lib/table-collections.mq.md
index 0c61095..f669fcf 100644
--- a/tests/lib/table-collections.mq.md
+++ b/tests/lib/table-collections.mq.md
@@ -6,7 +6,7 @@ import table:lib/table.mq.md
# main
-*h = > table.put in=None at=Authorization value=Bearer-x*
+*h = > table.put in=None at="Authorization" value="Bearer-x"*
> print text=`h`[^Authorization]
`xs` =
@@ -16,7 +16,7 @@ import table:lib/table.mq.md
| a |
| b |
-*xs = > table.put in=`xs` at=1 value=A*
+*xs = > table.put in=`xs` at=1 value="A"*
> print text=`xs`[^1]
> print text=`xs`[^2]
@@ -26,15 +26,15 @@ import table:lib/table.mq.md
|-------|----------|
| m1 | None |
-*msg = > table.put in=None at=role value=user*
-*msg = > table.put in=`msg` at=content value=hi*
+*msg = > table.put in=None at="role" value="user"*
+*msg = > table.put in=`msg` at="content" value="hi"*
*messages = > table.append list=None item=`msg`*
-*req = > table.put in=`req` at=messages value=`messages`*
-*req = > table.put in=`req` at=stream value=True*
+*req = > table.put in=`req` at="messages" value=`messages`*
+*req = > table.put in=`req` at="stream" value=True*
> print text=`req`[^messages][^1][^content]
> print text=`req`[^stream]
-*xs = > table.append list=`xs` item=c*
+*xs = > table.append list=`xs` item="c"*
*n = > table.len xs=`xs`*
> print text=`n`
diff --git a/tests/lib/文件-读.mq.md b/tests/lib/文件-读.mq.md
index 86ae6a8..a8fc712 100644
--- a/tests/lib/文件-读.mq.md
+++ b/tests/lib/文件-读.mq.md
@@ -5,13 +5,13 @@ title: 中文文件库
# main
-*有 = > 文件.存在 路径=hello.txt*
+*有 = > 文件.存在 路径="hello.txt"*
1. `有`
> 打印 内容=存在
2. *
> 打印 内容=缺失
-*t = > 文件.读文本 路径=hello.txt*
+*t = > 文件.读文本 路径="hello.txt"*
> 打印 内容=`t`
diff --git a/tests/lib/表-集合.mq.md b/tests/lib/表-集合.mq.md
index 785e55f..15265b3 100644
--- a/tests/lib/表-集合.mq.md
+++ b/tests/lib/表-集合.mq.md
@@ -6,7 +6,7 @@ description: 改 + 列表字典
# main
-*h = > 表.改 入=None 于=Authorization 值=Bearer-x*
+*h = > 表.改 入=None 于="Authorization" 值="Bearer-x"*
> 打印 内容=`h`[^Authorization]
`xs` =
@@ -16,9 +16,9 @@ description: 改 + 列表字典
| a |
| b |
-*xs = > 表.改 入=`xs` 于=1 值=A*
+*xs = > 表.改 入=`xs` 于=1 值="A"*
> 打印 内容=`xs`[^1]
-*xs = > 表.追加 list=`xs` item=c*
+*xs = > 表.追加 list=`xs` item="c"*
*n = > 表.长度 xs=`xs`*
> 打印 内容=`n`
diff --git a/tests/structure/import-lib.mq.md b/tests/structure/import-lib.mq.md
index 6c7bf4e..871d56f 100644
--- a/tests/structure/import-lib.mq.md
+++ b/tests/structure/import-lib.mq.md
@@ -6,7 +6,7 @@ title: import official lib (Chinese)
# main
-*t = > 文本.去空白 s= x*
+*t = > 文本.去空白 s=" x"*
> 打印 内容=`t`
diff --git a/tests/structure/inherit-explicit-super.mq.md b/tests/structure/inherit-explicit-super.mq.md
index ee49e3c..80a3cb2 100644
--- a/tests/structure/inherit-explicit-super.mq.md
+++ b/tests/structure/inherit-explicit-super.mq.md
@@ -7,22 +7,22 @@ import json:lib/json.mq.md
+ `name`
*out = > json.parse text={"role":"parent"}*
-*out = > json.set map=`out` key=name value=`name`*
+*out = > json.set map=`out` key="name" value=`name`*
**out**
# Child = > Parent
+ `name`
*self = > Parent name=`name`*
-*self = > json.set map=`self` key=role value=child*
+*self = > json.set map=`self` key="role" value="child"*
**self**
# main
-*c = > Child name=Ada*
-*ty = > json.get value=`c` key=_type*
-*role = > json.get value=`c` key=role*
-*name = > json.get value=`c` key=name*
+*c = > Child name="Ada"*
+*ty = > json.get value=`c` key="_type"*
+*role = > json.get value=`c` key="role"*
+*name = > json.get value=`c` key="name"*
> print text=`ty`
> print text=`role`
> print text=`name`
diff --git a/tests/structure/inherit-override.mq.md b/tests/structure/inherit-override.mq.md
index c5ea106..c333b1b 100644
--- a/tests/structure/inherit-override.mq.md
+++ b/tests/structure/inherit-override.mq.md
@@ -21,8 +21,8 @@ title: inherit method override
# main
*g = > Greeter*
-*m = > `g`.hello who=world*
+*m = > `g`.hello who="world"*
> print text=`m`
*l = > Loud*
-*m2 = > `l`.hello who=world*
+*m2 = > `l`.hello who="world"*
> print text=`m2`
diff --git a/tests/structure/inherit-parent-method.mq.md b/tests/structure/inherit-parent-method.mq.md
index 135f0f0..fa1d578 100644
--- a/tests/structure/inherit-parent-method.mq.md
+++ b/tests/structure/inherit-parent-method.mq.md
@@ -16,7 +16,7 @@ import json:lib/json.mq.md
# main
*l = > Loud*
-*ty = > json.get value=`l` key=_type*
+*ty = > json.get value=`l` key="_type"*
> print text=`ty`
-*m = > `l`.hello who=world*
+*m = > `l`.hello who="world"*
> print text=`m`
diff --git a/tests/structure/ns/path3.mq.md b/tests/structure/ns/path3.mq.md
index 031ac25..780ec0e 100644
--- a/tests/structure/ns/path3.mq.md
+++ b/tests/structure/ns/path3.mq.md
@@ -5,7 +5,7 @@ import helpers:helpers.mq.md
# main
-*v = > helpers.pack.label s=ok*
+*v = > helpers.pack.label s="ok"*
> print text=`v`
diff --git a/tests/structure/ns/use.mq.md b/tests/structure/ns/use.mq.md
index 10b945e..8a954d5 100644
--- a/tests/structure/ns/use.mq.md
+++ b/tests/structure/ns/use.mq.md
@@ -6,6 +6,6 @@ import trim_text:text.str_trim
# main
-*t = > trim_text s= hi*
+*t = > trim_text s=" hi"*
> print text=`t`
diff --git a/tests/structure/object-handle.mq.md b/tests/structure/object-handle.mq.md
index c76018b..dedff91 100644
--- a/tests/structure/object-handle.mq.md
+++ b/tests/structure/object-handle.mq.md
@@ -8,19 +8,19 @@ import json:lib/json.mq.md
*t = > json.parse text={"p":"{\"n\":","s":"}"}*
*qn = > str `n`*
-*p = > json.get value=`t` key=p*
-*s = > json.get value=`t` key=s*
+*p = > json.get value=`t` key="p"*
+*s = > json.get value=`t` key="s"*
*raw = p + qn + s*
**> json.parse text=`raw`**
## bump
-*n = > json.get value=`self` key=n*
+*n = > json.get value=`self` key="n"*
*n2 = n + 1*
*t = > json.parse text={"p":"{\"n\":","s":"}"}*
*qn = > str `n2`*
-*p = > json.get value=`t` key=p*
-*s = > json.get value=`t` key=s*
+*p = > json.get value=`t` key="p"*
+*s = > json.get value=`t` key="s"*
*raw = p + qn + s*
*m = > json.parse text=`raw`*
**m**
@@ -28,10 +28,10 @@ import json:lib/json.mq.md
# main
*c = > counter n=3*
-*ty = > json.get value=`c` key=_type*
+*ty = > json.get value=`c` key="_type"*
> print text=`ty`
-*n = > json.get value=`c` key=n*
+*n = > json.get value=`c` key="n"*
> print text=`n`
*c2 = > `c`.bump*
-*n2 = > json.get value=`c2` key=n*
+*n2 = > json.get value=`c2` key="n"*
> print text=`n2`