From 0f72173d0832da773321ee801e062d0a6bf9ac7c Mon Sep 17 00:00:00 2001 From: cflmy Date: Fri, 16 Oct 2026 11:47:28 +0800 Subject: [PATCH] =?UTF-8?q?feat(ext/ai):=20land=20Agent/LLM=20optimize=20w?= =?UTF-8?q?aves=20O1=E2=80=93O5?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Wire opt-in sandbox trial into agent, require sandbox proof before OKF promote, add step_route/EFI/cost surfaces, style lint + quarantine, and offline policy optimize script—keeping GFM tables over json glue. Co-authored-by: Cursor --- .cursor/skills/marqdo/SKILL.md | 214 +++-------- .gitignore | 3 + doc/README.md | 5 +- doc/design/ext-ai-optimize.md | 11 +- doc/design/okf.md | 20 +- doc/roadmap/ext-agent-optimize.md | 1 + doc/roadmap/ext-ai-optimize.md | 29 ++ examples/agent-sandbox-okf/README.md | 13 + examples/agent-sandbox-okf/index.mq.md | 59 +++ ext/ai/agent.mq.md | 352 +++++++++++++----- ext/ai/policies/step-route.mq.md | 25 ++ ext/ai/sandbox.mq.md | 92 ++++- ext/ai/智能体.mq.md | 32 +- plugins/agent/src/kb.rs | 171 ++++++++- plugins/agent/src/lib.rs | 10 + scripts/agent-harness.sh | 26 ++ scripts/mq-style-lint.sh | 45 +++ scripts/optimize-standing-policy.sh | 58 +++ skills/marqdo/SKILL.md | 8 +- tests/ext/agent-sandbox-optin.mq.md | 49 +++ tests/ext/agent-sandbox-promote.mq.md | 35 ++ tests/ext/agent-sandbox-quarantine.mq.md | 34 ++ tests/ext/agent-step-route.mq.md | 19 + tests/ext/sandbox-fixtures/promote-bad.mq.md | 8 + tests/ext/sandbox-fixtures/promote-good.mq.md | 12 + tests/gold.rs | 48 +++ 26 files changed, 1107 insertions(+), 272 deletions(-) create mode 100644 doc/roadmap/ext-ai-optimize.md create mode 100644 examples/agent-sandbox-okf/README.md create mode 100644 examples/agent-sandbox-okf/index.mq.md create mode 100644 ext/ai/policies/step-route.mq.md create mode 100755 scripts/mq-style-lint.sh create mode 100755 scripts/optimize-standing-policy.sh create mode 100644 tests/ext/agent-sandbox-optin.mq.md create mode 100644 tests/ext/agent-sandbox-promote.mq.md create mode 100644 tests/ext/agent-sandbox-quarantine.mq.md create mode 100644 tests/ext/agent-step-route.mq.md create mode 100644 tests/ext/sandbox-fixtures/promote-bad.mq.md create mode 100644 tests/ext/sandbox-fixtures/promote-good.mq.md diff --git a/.cursor/skills/marqdo/SKILL.md b/.cursor/skills/marqdo/SKILL.md index 7fab659..123c953 100644 --- a/.cursor/skills/marqdo/SKILL.md +++ b/.cursor/skills/marqdo/SKILL.md @@ -4,95 +4,40 @@ description: >- Author and edit Marqdo programs (.mq.md): Markdown markers are executable syntax (functions, calls, statements, returns, control flow). Use when writing or modifying .mq.md files, teaching Marqdo, generating Marqdo from prose, - importing lib/* or ext/web or ext/quantum or ext/linalg, running marqdo CLI, - building dynamic sites with ext/web, quantum circuits with ext/quantum, - formula-first linear algebra with ext/linalg, or when the user mentions - Marqdo, mq.md, markup-as-syntax, code-as-documentation, web/网页, quantum/量子, - or linalg/线性代数 extension. + importing lib/* or ext/web or ext/quantum, running marqdo CLI, building dynamic + sites with ext/web, quantum circuits with ext/quantum, or when the user + mentions Marqdo, mq.md, markup-as-syntax, code-as-documentation, web/网页, or + quantum/量子 extension. --- # Marqdo development Marqdo = **Markdown markers as syntax**. A `.mq.md` file is both documentation and a runnable program. Read this skill **before** inventing syntax from Markdown habits or Python. -Canonical design (repo): [`markdown-mapping-v0.3.md`](../../doc/design/markdown-mapping-v0.3.md) (**v0.3 · runtime**), `doc/design/keywords.md`. Legacy v0.2 notes: `doc/design/markdown-mapping.md` (historical). Deeper tables: [reference.md](reference.md). Copy-paste patterns: [examples.md](examples.md). +Canonical design (repo): `doc/design/markdown-mapping.md`, `doc/design/keywords.md`. Deeper tables: [reference.md](reference.md). Copy-paste patterns: [examples.md](examples.md). **Authoring / library craft** (GFM-first, no json glue, how to develop Marqdo): use **[marqdo-dev](../marqdo-dev/SKILL.md)** whenever writing or refactoring `.mq.md`, `lib/*`, or `ext/*`. -**Product release** (tag, CHANGELOG, README, public docs, VSIX, GitHub assets, **ext → R2+GitHub**, **CLI → Ubuntu PPA**): use [marqdo-release](../marqdo-release/SKILL.md) — detect versions, **ask for SemVer + mode (`full` / `cli` / `ext`)**, then follow that playbook. Ext-only releases are allowed. If sudo/GPG/PPA steps need the user, print the exact commands. +**Product release** (tag, CHANGELOG, README, public docs, VSIX, GitHub assets): use [marqdo-release](../marqdo-release/SKILL.md) — detect latest version, **ask the user for the next SemVer**, then follow that playbook. Do not invent a version number. ## Hard rules (do not violate) 1. **File suffix** must be `.mq.md` (never plain `.md` for executable sources). -2. **`**…**` = code** (assign / call). **`*…*` = return value**. Output is **not** either marker — use `> print text=…` / `**print text="…"**` / `> 打印 内容=…`. -3. **Prose:** unmarked narrative may contain `` `名` `` (declare/ref), inline `**code**`, and `*return*`. Soft Markdown emphasis that is **not** code-shaped (`**说明**`, mid-line `*only*`) is ignored — see [code-as-docs-gaps.md](../../doc/design/code-as-docs-gaps.md). Dead `` `名` `` (never read) is OK and does not become a param. -4. **Do not invent keywords** `if` / `else` / `while` / `for` / `def` / `return`. Control flow is Markdown: **`1.` `2.` … branches**, **`-` loops**, arm `N. *` = else, `#` = **object/type**, `##`+ = **function/method**. Params: prefer prose `` `名` `` / `` `名`=默认 `` (inferred); `` + `名` `` still accepted. -5. **Identifiers:** `` `名` `` in prose; inside `*…*` / `**…**`, bare ids are **variables**. **Text literals must be quoted** in bold/italic: `**print text="hi"**`. Standalone `>` calls: bare words = text; vars need ticks: `` > str `n` ``. -6. **Structure lines** (`#` `>` `+` `-` `|` `1.`) need not be wrapped in bold. -7. **Paths:** In bare expressions `/` is division. In call args / defaults / table cells, unspaced `a/b` and quoted paths are text. -8. Prefer ending side-effect-only bodies with `*None*` / `*无*` / whole-line `**` / `****` when the next lines must belong to an outer function. Lone `---` / `***` are Markdown thematic breaks (skipped everywhere), not function end. +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** (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 / table cells**, unspaced `a/b` and quoted `".marqdo/agent-kb"` are path text — no `json.parse` needed. Numeric ratios that must stay text use quotes (`"1/5"`, `"16/9"`); bare `1/5` is division. +8. Prefer ending side-effect-only function bodies with `*None*` / `*无*` / whole-line `**` / `****` when later lines must belong to an outer function. Lone `---` / `***` are Markdown thematic breaks (skipped), not function end. 9. **`ext/**` never calls `host_*`.** Agent/OKF helpers are plugin names (`agent_kb_*`, …) after `plugin.load`. Do **not** add agent/OKF domain code to `src/host/` (core bloat). See `doc/design/ext-agent.md` §4. 10. **Browser (route C/D/E/F):** client logic is Marqdo on WASM; official bridge is host glue and **may** implement lists, routing, storage, WebSocket, canvas, file read, observers — authors **must not hand-write business JS**. Use `web.client_embed` / `data-mq-source-url` auto-mount. Client effects: prefer **GFM tables + `lib/browser`** ([marqdo-dev](../marqdo-dev/SKILL.md)). -11. **Code-as-documentation / no bag glue:** Prefer **GFM tables** for maps, lists, wire, commands. Prefer **`table.put` / named helpers** over `json.set` / `json.append` chains. `lib/json` is for parse/stringify/quote only — not a dict builder. Unreadable json pipelines are a style bug. -12. **Bracket-marked calls:** Function name may be marked with `[函数名]`; bare words before `[` are boolean modifiers (`礼貌 [问候] x` → `礼貌=True`). `]` immediately followed by `(` is **index** `[key](coll)`, not a call. Prefer `[k](c)` over footnote index in new code. See [bracket-call-modifiers.md](../../doc/design/bracket-call-modifiers.md). +11. **Code-as-documentation / no bag glue:** Prefer **GFM tables** for maps, lists, wire, commands. Prefer **`table.put` / named helpers** over `json.set` / `json.append` chains. `lib/json` is for parse/stringify/quote only — not a dict builder. Unreadable json pipelines are a style bug. Read collections with **`[key](map)`**, not footnote indexes for new code. +12. **One language per file:** Do not mix EN and ZH API names in the same `.mq.md` (imports, calls, params). Pick English *or* Chinese mirrors for the whole program. +13. **Sandbox trial habit (Agent / generated `.mq.md`):** Prefer `agent.trial` / `run sandbox=True` / `sandbox.open`→`run`→`diff`→`commit` before promoting to the host tree. Host files must stay unchanged until a successful commit. Caps live in `sandbox.profile` GFM tables — do not invent a second dialect. -## 记不住语法细节?查 MLSP(AI 必读) -**不必背 Marqdo 语法细节**——语法可查、程序可验、修复有界。写码前后走**查询式**工作流: - -```bash -printf '%s\n' '{"id":1,"method":"syntax","params":{"query":"返回"}}' | marqdo mlsp -printf '%s\n' '{"id":2,"method":"locate","params":{"path":"a.mq.md","symbol":"加一"}}' | marqdo mlsp -printf '%s\n' '{"id":3,"method":"validate","params":{"path":"a.mq.md"}}' | marqdo mlsp -printf '%s\n' '{"id":4,"method":"schema","params":{"path":"a.mq.md","unit":"加一"}}' | marqdo mlsp -printf '%s\n' '{"id":5,"method":"repair_targets","params":{"code":"contract.arg_mismatch","doc_anchor":"a.mq.md#L9-L15"}}' | marqdo mlsp -``` - -| method | 何时用 | -|--------|--------| -| `syntax` | 不确定某个语法怎么写(关键字/别名 → 构造卡片:「返回」「表」「调用」「循环」…) | -| `locate` | 找符号定义位置 + 契约;或反查构造卡片 | -| `validate` | 提交前校验(结构化诊断数组;`ok:false` 就修) | -| `schema` | 查单元契约(形参/返回/字段) | -| `repair_targets` | 拿错误的**有界**修复靶点:只改锚点范围内行,越界必弃权(abstain) | - -行分隔 JSON:每行请求 `{"id","method","params"}` → 每行响应 `{"id","ok","result"|"error"}`。 -语法唯一事实来源 = `doc/design/core-surface.md`(CI 守卫同步);卡片带 `manual` 指回文档行。 -所有错误诊断都是结构化 JSON:`code` / `severity` / `span` / `suggestion` / `doc_anchor` / `doc_quote` / `contract_ref`。 - -### 渐进式契约(可选标注;schema 就长在文档表里) - -契约是**未绑定文档表**(绑定表是数据,永远不是契约)。三种形状、严格位置: - -| 形状(须含 `类型` 列) | 允许位置 | 附着 | -|--------------------------|----------|------| -| `参数`/`类型`/`说明` 表 + `返回`/`类型`/`说明` 表 | 函数体首个可执行行之前 | 函数 | -| `字段`/`类型`/`可空`/`说明` 表 | 紧邻 `` `名` = `` 绑定之前 | 集合(变量) | -| `字段`/`类型`/`可空`/`说明` 表 | 对象(`#`)体首成员之前 | 对象类型 | - -````text -## 加一 - -对于输入变量`n`,期望是数字。 - -| 参数 | 类型 | 说明 | -|------|------|------| -| n | number | 输入值 | - -| 返回 | 类型 | 说明 | -|------|------|------| -| | number | 加一结果 | - -*n+1* -```` - -- 类型词汇:`text` / `number` / `bool` / `list` / `map` / `any` / `#` 对象名(拼错 ⇒ `contract.unknown_type` + 最近建议)。 -- 契约表**永不执行**、不污染升参推断;无契约文件行为逐字节不变(动态默认,零摩擦)。 -- 运行时只在四个边界校验:调用实参 / 字段访问 `[键](集合)` / 表绑定 / 返回。 -- `marqdo check [FILE] [--json]` 静态互查:契约行 vs 升参推断形参**双向**漂移(错行=Error;新升参未覆盖=Warning)、未知类型、错位契约;有 Error 非零退出。 -- 契约诊断带 `doc_anchor` + `doc_quote`(表原文)——修复只照锚点局部改。 - -## Markup → meaning (v0.3) +## Markup → meaning (v0.2) | Marker | Meaning | |--------|---------| @@ -103,20 +48,17 @@ printf '%s\n' '{"id":5,"method":"repair_targets","params":{"code":"contract.arg_ | `- …` inside body | Loop (`while` or `` [item](coll) `` / `` [`item`](`coll`) ``) | | Line `N. *` | Else arm | | `> fn args` | Call (named `k=v` or positional) | -| `修饰 [fn] args` | Bracket-marked call; leading words → `名=True` | | `` > `obj`.method args `` | Method call (`obj` must be a map with `_type`) | | Frontmatter `import bind:path.mq.md` / `导入` | Import file (bind library name) | | Frontmatter `import bind:lib.member` / `导入` | Short name for a library member (same keyword; no separate `use`) | | `> lib.member …` / `> lib.Type.member …` | Call via bare dotted path (instance methods need `` `var`.m ``) | -| `**…**` | **Code** (assign / call) — closing `**` touches last token; bare ids are variables; quote text literals | -| `*…*` | **Return value** — closing `*` touches last token; bare ids are variables | -| `****` / whole-line `**` / `*None*` | Return `None` and end function body | +| `*…*` | Statement (bind / expr) — closing `*` touches last token, **no trailing space**; bare ids are variables | +| `**…**` | Return value — closing `**` touches last token, **no trailing space**; bare ids are variables | +| `****` or `**` + spaces + `**` | Return `None` and end function body | | Lone `---` / `***` | Markdown thematic break (skip; not function end) | | GFM table after empty RHS bind | Collection; get with `[key](coll)` (preferred) or legacy `` `m`[^key] `` | -| `` ```lang `` | Foreign code block (via `lib/foreign`); bind with `` `name` = `` then fence | -| `$$` + `% marqdo: var=name` | Block formula bind (TeX comment; prefer over empty RHS) | -| `- [item](coll)` | Foreach (**preferred**, nestable). Sugar: `- 对`coll`的每一项`item`` / `- for each `item` in `coll`` | -| `![marqdo-out](path)` | Image writeback form (validated stem.ext / URL); text writeback stays HTML comment | +| `- [item](coll)` | Foreach (unchanged) | +| `` ```lang `` | Foreign code block (via `lib/foreign`) | | `` `"text"` `` | Quoted string (`\n` `\t` `\\` `\"`; `` `var` `` inside); bare tokens unescaped | | Unmarked prose | Comment | @@ -140,19 +82,20 @@ Chinese builtins (same functions, no import): ## Functions, calls, end-body -Prefer **body-inferred params** and **prose-unified** wording (v0.3). `` + `name` `` still works, but teach the inferred form first: - ```markdown # main -**greet who="Marqdo"** +> greet who=Marqdo ## greet + + `who` -When we meet`who`, we **print text="Hello, `who`!"** and close with*None*. +> print text=Hello, `who`! + +*None* ``` -- Call: `**fn key="text"**` (bold; quote text literals) or `> fn key=text` (standalone `>`; bare words are text). +- Call: `> name key=value` or `> name value`. - Nested helpers use deeper `#` (`##`, `###`, …). - After a helper with only side effects, end with `*None*` / whole-line `**` / `****` when later lines must stay in the outer function. Lone `---` is only a thematic break (skipped). - In bold assigns, prefer bare calls: `**摘要 = 结账摘要 …**` (omit `>`). @@ -160,16 +103,17 @@ When we meet`who`, we **print text="Hello, `who`!"** and close with*None*. ## Statements, returns, branches ```markdown -**x = 1** -**y = x + 2** +*x = 1* +*y = x + 2* ## add_one + + `n` -For input`n`, do **n = n + 1** and return*n*. +**n + 1** ``` ```markdown -**n = 0** +*n = 0* 1. `n` > 0 > print text=positive @@ -192,16 +136,16 @@ import clock:lib/time.mq.md # main -**xs = > text.str_split s="a,b,c" sep=","** +*xs = > text.split value="a,b,c" sep=","* > print text=`xs` -**t = > clock.now_unix** +*t = > clock.now_unix* ``` - Import **English** or **Chinese** library file; call that file’s API names via `lib.member` (do not mix languages). - Instance methods stay `` > `obj`.method `` (backticks on the receiver only). - `lib/…` resolves via `MARQDO_LIB`, cwd `lib/`, or `lib/` next to the `marqdo` binary. - Design: [module-namespace.md](../../doc/design/module-namespace.md). -- Official optional extensions (`ext/`, not stdlib): install with `marqdo ext add llm|agent|web|quantum|linalg` (see `doc/design/ext-cli.md`). **`ext/llm`** — intelligence primitive (`ask` / `stream` / `collect`; `complete` is compat); **`ext/agent`** — document-driven agents (see **ext/agent** below); **`ext/web`** — dynamic sites (see below); **`ext/quantum`** — circuits + Q7/Q8 (see below); **`ext/linalg`** — formula-first linear algebra (see below). +- Official optional extensions (`ext/`, not stdlib): install with `marqdo ext add llm|agent|web|quantum` (see `doc/design/ext-cli.md`). `ext/llm` — chat; **`ext/agent`** — document-driven agents (see **ext/agent** below); **`ext/web`** — dynamic sites (see below); **`ext/quantum`** — circuits + Q7/Q8 (see below). - Native plugins: `lib/plugin` — `## load` / `unload` / `list`. C ABI: `include/marqdo_abi.h`. - Prefer `table.put` / `表.改` for list/map element updates; keep `json` for parse/stringify/quote (see `doc/design/stdlib-table.md`). - Builtins (no import): `print`/`打印`, `input`/`输入`, `len`/`长度`, `str`/`文本`, `int`/`整数`; literals `True`/`真`, `False`/`假`, `None`/`空`; logic `and`/`且`, `or`/`或`, `not`/`非`. @@ -216,61 +160,24 @@ Install: `marqdo ext add agent` (ZH: `智能体`). Native: `cargo build --releas 1. **Code is documentation** — the runbook `.mq.md` is the model’s ground truth, not a hidden system prompt bag. 2. **Call site is first-class** — `build_step_context` injects path/function/line so the model knows where it is in the program. -3. **Document is the knowledge base (OKF)** — writeback → promote/solidify → reuse / `llm_free`; MCP/corpus are evidence only. **Engineering Knowledge(EKC)**:`marqdo knowledge|find|reuse|…` + `agent.preflight`(REUSE→ADAPT→CREATE)——见 [engineering-knowledge.md](../../doc/design/engineering-knowledge.md)。 -4. **Skill Compilation (v2)** — successful runs become `.mq.md` episodes; after enough evidence, `maybe_learn` compiles an executable skill (`llm_free`). Prefer `## run` over bare `## plan` when you want learning. -5. **Adaptive Routing (P4)** — router is abstract (`marqdo` / `small-llm` / `llm` / `auto`); `jev` is a compat alias of `small-llm`. Decision via `router_model` (any llm handle). Policy Compilation writes `policies/router.mq.md`. +3. **Document is the knowledge base (OKF)** — writeback → promote/solidify → reuse / `llm_free`; MCP/corpus are evidence only. -APIs: `# agent` / `# 智能体` → `## run` / `## route` / `## step` / `## plan` (+ `resolve` / `record_episode` / `maybe_learn` / `compile` / `compile_policy` / `metrics`). Context: standing + task + **call site** + tools + budgeted source/skill + act protocol (`CALL:` / `READ:`). Inspect without LLM: `dump_step_context`. Inside `writeback=` / `写回=` branches use `host_writeback_record` (param name shadows the writeback import). +APIs: `# agent` / `# 智能体` → `## step` / `## plan`. Context: standing + task + **call site** + tools + budgeted source/skill + act protocol (`CALL:` / `READ:`). -Examples: [agent-pong](../../examples/agent-pong/) · [agent-okf-flywheel](../../examples/agent-okf-flywheel/). Harness: `scripts/agent-harness.sh`. Design: [ext-agent.md](../../doc/design/ext-agent.md) · Wave B: [agent-framework-2026-09.md](../../doc/research/agent-framework-2026-09.md) · v2: [doc/next/003.md](../../doc/next/003.md) · P4: [doc/next/004.md](../../doc/next/004.md). Dev LLM: copy [.env.example](../../.env.example) → `.env` (gitignored). +Examples: [agent-pong](../../examples/agent-pong/) · [agent-okf-flywheel](../../examples/agent-okf-flywheel/) · [agent-sandbox-okf](../../examples/agent-sandbox-okf/). Harness: `scripts/agent-harness.sh`. Design: [ext-agent.md](../../doc/design/ext-agent.md) · optimize O1–O5: [ext-ai-optimize.md](../../doc/roadmap/ext-ai-optimize.md). Dev LLM: copy [.env.example](../../.env.example) → `.env` (gitignored). + +**Sandbox (O1):** `import sandbox:ext/ai/sandbox.mq.md` · `agent.trial` / `智能体.试跑` · `run`/`step` take `sandbox=` / `沙盒=` (default `False`). Profile caps are tables via `sandbox.profile`. Gold: `tests/ext/agent-sandbox-optin.mq.md`. ## Official extension: `ext/web` (Document / Endpoint / Resource) -Install: `marqdo ext add web` (ZH id: `网页`). Build native plugin: `scripts/build-web-plugin.sh` / `marqdo ext add web`. +Install: `marqdo ext add web` (ZH id: `网页`). See ADR 0007 · [ext-web-artifact.md](../../doc/design/ext-web-artifact.md). -**Constitution (ADR 0007 — do not degrade):** +**Do not degrade:** Document/Endpoint metadata; facade `web.page|route|serve|render|inspect`; View `|type|slot|value|attrs|style|` only; no `compose_*` / `configure` / author `ensure_plugin`. DB → `ext/data`; auth → `ext/security`; net → `ext/net`. -1. **Document / Endpoint / Resource** — `.mq.md` with `type: web|endpoint` (ZH `类型: 网页|端点`) is the site surface; not a Flask-style class pile. -2. **Code is documentation** — the file is docs + route + handler. -3. **Table = data** — View schema only `|type|slot|value|attrs|style|`. No `compose_*` dialects, no `json.set` glue. -4. **Facade only** — `web.page` · `web.route` · `web.serve` · `web.render` · `web.inspect`. DB → `ext/data`; auth → `ext/security`; ws/http → `ext/net`. -5. **No author `ensure_plugin` / `host_*`**; import web = capability (plugin auto-load). -6. **Declared vs system routes**; `web.inspect` lists both. No silent user routes. - -Import **one language** per file: - -- EN: `import web:ext/web/web.mq.md` (+ `import data:ext/data/db.mq.md` as needed) +- EN: `import web:ext/web/web.mq.md` - ZH: `导入 网页:ext/web/网页.mq.md` -```markdown ---- -type: web -route: / -title: Hello -import web:ext/web/web.mq.md ---- - -# Hello - -Executable document as a page. -``` - -```markdown ---- -type: endpoint -method: POST -path: /api/ping -response: json ---- - -*{"ok": true}* -``` - -Site entry may `# main` → `web.serve root="."`. Client WASM: `ext/web/client.mq.md` / `lib/browser` — no author JS. - -Design: [ext-web-artifact.md](../../doc/design/ext-web-artifact.md) · ADR [0007](../../doc/adr/0007-web-document-endpoint.md) · rule: `.cursor/rules/web-artifact-no-degrade.mdc` · example: [examples/marqdo-blog/](../../examples/marqdo-blog/). - -Web patterns: [examples.md](examples.md) · API index: [reference.md](reference.md). +Design: [ext-web-artifact.md](../../doc/design/ext-web-artifact.md) · example: [examples/marqdo-blog/](../../examples/marqdo-blog/). ## Official extension: `ext/quantum` (circuits + Q7/Q8) @@ -296,29 +203,13 @@ Install: `marqdo ext add quantum` (ZH id: `量子`). Build: `cargo build --relea Design: [ext-quantum.md](../../doc/design/ext-quantum.md) · Q7: [ext-quantum-q7.md](../../doc/design/ext-quantum-q7.md) · Q8 viz: [ext-quantum-viz-style.md](../../doc/design/ext-quantum-viz-style.md) · examples: [quantum-bell](../../examples/quantum-bell/) · [quantum-entanglement](../../examples/quantum-entanglement/). -## Official extension: `ext/linalg` (formula-first LA) - -Install: `marqdo ext add linalg` (ZH id: `线性代数`). Build: `cargo build --release -p marqdo_plugin_linalg`, then **`marqdo ext add linalg` again** so view loads the new native lib. - -- EN: `import la:ext/linalg/linalg.mq.md` -- ZH: `导入 la:ext/linalg/线性代数.mq.md` - -**Hard rules:** `ext/**` never calls `host_*`; hot path is ABI plugin; prefer top-level `la.symbol` (not `matrix.symbol` without a receiver); quote `kind=` strings; dense `explicit` / factorize obey size guards. - -APIs (EN): `symbol` → `# matrix`;中缀 `+`/`-`/`*`;方法 `` `A`.T `` / ``.simplify`` / ``.ascii`` · `from_formula` / `explicit` / `factorize` / `draw` · `lstsq` / `norm` / `cond` / `rank`. - -Examples: [linalg-svd](../../examples/linalg-svd/) · [linalg-least-squares](../../examples/linalg-least-squares/). Design: [ext-linalg.md](../../doc/design/ext-linalg.md) · formula-doc: [ext-linalg-formula-doc.md](../../doc/design/ext-linalg-formula-doc.md). - ## AI authoring workflow -1. **查再写**:不确定语法就 `marqdo mlsp`(`syntax` / `locate`)——不必背语法细节。 -2. Decide language surface (English builtins + `lib/text.mq.md`, or Chinese + `lib/文本.mq.md`). -3. Write `.mq.md` with `# main`, blank lines around prose, correct markers. -4. 可选:给函数/集合写**渐进式契约**(上节三种表格形状;写全或不写,别写一半)。 -5. Run: `marqdo run path/to/file.mq.md` (cwd = project root so `lib/` resolves). -6. On errors:结构化诊断(含 `doc_anchor` / `suggestion`)→ `repair_targets` 取有界靶点,**只改锚点范围内**的行。 -7. 提交前:`marqdo check path/to/file.mq.md`(或 `mlsp validate`)清到零 Error。 -8. Optional: `marqdo view .` / `marqdo debug .` for structure and breakpoints. +1. Decide language surface (English builtins + `lib/text.mq.md`, or Chinese + `lib/文本.mq.md`). +2. Write `.mq.md` with `# main`, blank lines around prose, correct markers. +3. Run: `marqdo run path/to/file.mq.md` (cwd = project root so `lib/` resolves). +4. On `path:line:col: message`, fix that span; re-run until exit 0. +5. Optional: `marqdo view .` / `marqdo debug .` for structure and breakpoints. ## Anti-patterns (common model mistakes) @@ -339,8 +230,7 @@ Examples: [linalg-svd](../../examples/linalg-svd/) · [linalg-least-squares](../ | Mix `web.page` and `网页.页面` in one file | One import language per `.mq.md` | | Call `host_web_*` from `ext/web` | Use `# app` / `# db` methods; plugin ABI only | | Call `host_*` from `ext/quantum` | Use `# circuit` / `# density` methods; plugin ABI only | -| Call `host_*` from `ext/linalg` | Use `la.*` L1 wrappers; plugin ABI only | -| Bare `kind=eig` inside `*…*` | `kind="eig"` — quote text literals | +| Bare `kind=hinton` inside `*…*` | `kind="hinton"` — quote text literals | | Bare `theme=dark` inside `*…*` | `theme="dark"` — quote; ZH `主题="dark"` | | Rebuild plugin but skip `ext add` | `cargo build -p marqdo_plugin_quantum` then `marqdo ext add quantum` (or set `MARQDO_QUANTUM_PLUGIN`) | @@ -357,5 +247,3 @@ Examples: [linalg-svd](../../examples/linalg-svd/) · [linalg-least-squares](../ - [ ] Browser client: `lib/browser` + tables when returning effects - [ ] Quantum draw: quote `kind=` / `theme=`; rebuild plugin → `ext add quantum` before view - [ ] `marqdo run` succeeds (or errors addressed) -- [ ] 语法拿不准的地方已查 MLSP(`syntax`/`locate`),而不是凭记忆发明 -- [ ] 契约(如有)与升参一致:`marqdo check` 零 Error diff --git a/.gitignore b/.gitignore index 72d50de..88118f6 100644 --- a/.gitignore +++ b/.gitignore @@ -90,3 +90,6 @@ tests/ext/:memory: # sandbox gold leftovers tests/ext/_sbx_cow/ + +tests/ext/_sbx_*/ +examples/**/_example_sbx/ diff --git a/doc/README.md b/doc/README.md index f04a05c..3c38140 100644 --- a/doc/README.md +++ b/doc/README.md @@ -94,11 +94,12 @@ | [design/ext-ai-sandbox.md](design/ext-ai-sandbox.md) | **`ext/ai/sandbox` 设计锁定**:CoW · 能力表 · agent ABI(非 stdlib) | | [roadmap/ext-ai-sandbox.md](roadmap/ext-ai-sandbox.md) | **`ext/ai/sandbox` 实现里程碑** S0–S4 | | [research/ai-agent-llm-optimize-2026-10.md](research/ai-agent-llm-optimize-2026-10.md) | **2026-10 调研**:代码即文档×OKF×沙盒下的 Agent/LLM 优化与问题分析 | -| [design/ext-ai-optimize.md](design/ext-ai-optimize.md) | **方案**:Agent/LLM 优化可行方向全集与推荐波次 O1–O5 | +| [design/ext-ai-optimize.md](design/ext-ai-optimize.md) | **Accepted**:Agent/LLM 优化 O1–O5 locked | +| [roadmap/ext-ai-optimize.md](roadmap/ext-ai-optimize.md) | **O1–O5 实现路线**(沙盒接入→证明晋升→路由/成本→lint→隔离) | | [research/ext-hosting-gaps.md](research/ext-hosting-gaps.md) | **宿主集成缺口**:同域 SSE 中继 · HTTP→`##` · MCP Server · 副端口 · 跨模块 db/corpus | | [design/ext-hosting-fill.md](design/ext-hosting-fill.md) | **宿主缺口补齐设计**(`ext/web` proxy/invoke · `ext/ai` mcp_server) | | [roadmap/ext-hosting.md](roadmap/ext-hosting.md) | **宿主集成 H0–H4**(规划) | -| [roadmap/ext-agent-optimize.md](roadmap/ext-agent-optimize.md) | **`ext/agent` A0–A4 done · Wave B Active** | +| [roadmap/ext-agent-optimize.md](roadmap/ext-agent-optimize.md) | **`ext/agent` A0–A4 done · Wave B Active** · 后续优化见 [ext-ai-optimize](roadmap/ext-ai-optimize.md) O 波次 | 金样例与集成测试:[`tests/`](../tests/)。面向访客的可执行文档:[`public/`](../public/)。Spike 存档:[`spike/`](../spike/)。 diff --git a/doc/design/ext-ai-optimize.md b/doc/design/ext-ai-optimize.md index 80a7fd5..bd2a19e 100644 --- a/doc/design/ext-ai-optimize.md +++ b/doc/design/ext-ai-optimize.md @@ -2,9 +2,10 @@ | | | |---|---| -| 状态 | **Proposed · 方向全集(待选型排期)** | +| 状态 | **Accepted · O1–O5 locked** | | 日期 | 2026-10-16 | | 调研 | [ai-agent-llm-optimize-2026-10.md](../research/ai-agent-llm-optimize-2026-10.md) | +| 路线 | [ext-ai-optimize.md](../roadmap/ext-ai-optimize.md) | | 相关 | [ext-ai-sandbox.md](ext-ai-sandbox.md) · [ext-agent.md](ext-agent.md) · [okf.md](okf.md) · [engineering-knowledge.md](engineering-knowledge.md) · [ext-agent-optimize.md](../roadmap/ext-agent-optimize.md) · [ai-stack.md](../roadmap/ai-stack.md) | --- @@ -112,7 +113,7 @@ sandbox.open → sandbox.run(caps)→ diff --- -## 3. 推荐落地波次(默认建议,可改) +## 3. 执行顺序(O1→O5 locked) | 波次 | 方向组合 | 为何先做 | |------|----------|----------| @@ -123,6 +124,8 @@ sandbox.open → sandbox.run(caps)→ diff | **O5** | B4 + C3 | 失败隔离与离线提示优化 | | **O∞** | C4 / A6 | 研究项,单独立项 | +切片实现见 [ext-ai-optimize.md](../roadmap/ext-ai-optimize.md)。 + --- ## 4. 验收原则(任一波次) @@ -134,6 +137,6 @@ sandbox.open → sandbox.run(caps)→ diff --- -## 5. 下一步 +## 5. 落地 -请从 §2 方向方向中圈选优先级(或确认 §3 默认 O1→O2)。确认后另开 `doc/roadmap/ext-ai-optimize.md` 做切片实现,**仍不改** `doc/next/*`。 +O1–O5 已锁定;实现见 [roadmap/ext-ai-optimize.md](../roadmap/ext-ai-optimize.md)。**仍不改** `doc/next/*`。 diff --git a/doc/design/okf.md b/doc/design/okf.md index da6c36b..6a5e215 100644 --- a/doc/design/okf.md +++ b/doc/design/okf.md @@ -314,10 +314,15 @@ type: Marqdo Agent Skill title: <短名> sig: <12hex> resource: ../../resources/.mq.md -status: stable | candidate +status: stable | candidate | quarantine llm_free: true | false quality: hits: +# O2 optional metadata (from workbook frontmatter; see §7.5): +applies_when: +fixtures: +sandbox_profile: default | readonly | +proof: # alias of fixtures for sandbox gate generated: by: marqdo-agent/plan at: @@ -331,7 +336,7 @@ verified: Prefer spawning `resource` over re-planning. ``` -`status`:`llm_free` 的 resource 晋升为 **stable**(零父 LLM 快路径);否则为 **candidate**(可复用,但按 `improve_every` 偶发再优化,每轮最多 1 次改进)。失败运行不晋升;质量更差不覆盖。 +`status`:`llm_free` 的 resource 晋升为 **stable**(零父 LLM 快路径);否则为 **candidate**(可复用,但按 `improve_every` 偶发再优化,每轮最多 1 次改进)。失败运行不晋升;质量更差不覆盖。**O2:** `agent_kb_promote` 默认要求 sandbox proof(`proof` / `fixtures` / workbook 本身经 `sandbox.run` 成功)才写入;失败返回 `promoted: false` / `reason: sandbox_proof_failed`。传 `require_proof=false` 仅用于明确豁免。 ### 7.3 任务签名 → Concept 路径 @@ -401,6 +406,17 @@ Prefer spawning `resource` over re-planning. | 迭代 | 同 Concept slug/`sig` 覆盖 resource + 刷新 `generated`/`verified` | | 成长 | 命中快路径;`candidate`/`hits`/`improve_every` 驱动再优化;`log.md` 可审计 | | 分发 | 整包 `agent-kb/` 可复制(格式即契约) | +| **证明晋升(O2)** | `applies_when` / `fixtures` / `sandbox_profile` / `proof` 写在技能与 workbook frontmatter;promote 前 `sandbox.run` 绿才 `llm_free` | +| **隔离(O5)** | 失败技能 `status: quarantine`;回归 fixture 跟随 slug | + +### 7.5a 技能 frontmatter 约定(O2 B1) + +| 字段 | 含义 | +|------|------| +| `applies_when` | 适用条件(短文本 / 标签);路由与 harness 可读 | +| `fixtures` | 相对路径:sandbox 证明用 `.mq.md` | +| `sandbox_profile` | `default` / `readonly` / 其它 `sandbox.profile` 名 | +| `proof` | 与 `fixtures` 同义;promote 优先读 `proof` 再 `fixtures`,否则跑 workbook 自身 | --- diff --git a/doc/roadmap/ext-agent-optimize.md b/doc/roadmap/ext-agent-optimize.md index 5b1b358..bb85bcf 100644 --- a/doc/roadmap/ext-agent-optimize.md +++ b/doc/roadmap/ext-agent-optimize.md @@ -7,6 +7,7 @@ | 调研 | [agent-frameworks-and-marqdo.md](../research/agent-frameworks-and-marqdo.md) · [agent-framework-gaps-after-a4.md](../research/agent-framework-gaps-after-a4.md) · **[agent-framework-2026-09.md](../research/agent-framework-2026-09.md)** | | 设计 | [ext-agent.md](../design/ext-agent.md) · [ext-agent-plan.md](../design/ext-agent-plan.md) · [ext-agent-parent.md](../design/ext-agent-parent.md) · [okf.md](../design/okf.md) | | 邻近 | [agent-streaming.md](agent-streaming.md) · [okf-near-match.md](okf-near-match.md) | +| 后续 | 优化波次 O1–O5 见 [ext-ai-optimize.md](ext-ai-optimize.md)(沙盒证明 · Skill Lift · 路由/成本 · lint · 隔离) | --- diff --git a/doc/roadmap/ext-ai-optimize.md b/doc/roadmap/ext-ai-optimize.md new file mode 100644 index 0000000..9d43d6f --- /dev/null +++ b/doc/roadmap/ext-ai-optimize.md @@ -0,0 +1,29 @@ +# Roadmap: Agent/LLM 优化波次 O1–O5 + +| | | +|---|---| +| Status | **Active** | +| Date | 2026-10-16 | +| Design | [ext-ai-optimize.md](../design/ext-ai-optimize.md) | +| Research | [ai-agent-llm-optimize-2026-10.md](../research/ai-agent-llm-optimize-2026-10.md) | +| Prior | [ext-agent-optimize.md](ext-agent-optimize.md) (A0–A4 / Wave B) · [ext-ai-sandbox.md](../design/ext-ai-sandbox.md) | + +## Principles + +1. Executable `.mq.md` remains authority; OKF reuses; sandbox proves; LLM explores. +2. No hidden TOOL: loop; no vector-store memory authority; no default shell Agent. +3. Do not edit `doc/next/*`. + +## Waves + +| Wave | Scope | Gold / deliverable | Status | +|------|-------|--------------------|--------| +| **O1** | A1 opt-in `sandbox=` · A3 profile table · D1 skill · D4 example | `agent-sandbox-optin` · `examples/agent-sandbox-okf` | **done** | +| **O2** | A2 promote proof · B1 OKF meta · B3/E1 harness Skill Lift | `agent-sandbox-promote` · harness subset | **done** | +| **O3** | C1 step route · C2 cost · B6 EFI default | `agent-step-route` · run usage/efi | **done** | +| **O4** | A4/D2 lint · A5 diff review report | `scripts/mq-style-lint.sh` · `sandbox.report` | **done** | +| **O5** | B4 quarantine · C3 offline policy rewrite | `agent-sandbox-quarantine` · `optimize-standing-policy.sh` | **done** | + +## Non-goals + +F1–F5 · wasmtime CLI embed · default `sandbox=True` without ADR · edit `doc/next/*` diff --git a/examples/agent-sandbox-okf/README.md b/examples/agent-sandbox-okf/README.md new file mode 100644 index 0000000..c0b6c2a --- /dev/null +++ b/examples/agent-sandbox-okf/README.md @@ -0,0 +1,13 @@ +# agent-sandbox-okf(O1) + +演示 **opt-in 沙盒试跑 + 表风格**(少 json 胶水):`agent.trial` 写入先落 upper,`commit=False` 时宿主不变,成功后再 `commit=True`。 + +```bash +cargo build --release -p marqdo -p marqdo_plugin_agent +export MARQDO_EXT="$PWD/ext" +./target/release/marqdo run examples/agent-sandbox-okf/index.mq.md +``` + +期望:`dry-ok` · `host-clean` · `wet-ok` · `proof-visible` · `profile-default`。 + +见 [ext-ai-optimize.md](../../doc/roadmap/ext-ai-optimize.md) · 金样 [agent-sandbox-optin.mq.md](../../tests/ext/agent-sandbox-optin.mq.md)。 diff --git a/examples/agent-sandbox-okf/index.mq.md b/examples/agent-sandbox-okf/index.mq.md new file mode 100644 index 0000000..ca36ccc --- /dev/null +++ b/examples/agent-sandbox-okf/index.mq.md @@ -0,0 +1,59 @@ +--- +title: agent-sandbox-okf — trial then commit +description: > + O1 example: opt-in sandbox trial with GFM-table returns and link-index reads. +import agent:ext/ai/agent.mq.md +import fs:lib/fs.mq.md +--- + +# main + +Short demo: write via `agent.trial`, prove the host is clean until commit. + +**had = fs.exists path="_example_sbx"** +1. `had` + > fs.remove path="_example_sbx" +2. * + **_ = 0** + +> fs.make_dir path="_example_sbx" + +**dry = agent.trial root="_example_sbx" write_path="note.txt" text=sandbox-okf commit=False** +**dry_ok = [ok](dry)** +**dry_committed = [committed](dry)** +1. `dry_ok` + 1. not `dry_committed` + > print text=dry-ok + 2. * + > print text=dry-bad-commit +2. * + > print text=dry-fail + +**leaked = fs.exists path="_example_sbx/note.txt"** +1. `leaked` + > print text=host-leaked +2. * + > print text=host-clean + +**wet = agent.trial root="_example_sbx" write_path="note.txt" text=sandbox-okf commit=True** +**wet_ok = [ok](wet)** +**wet_committed = [committed](wet)** +1. `wet_ok` + 1. `wet_committed` + > print text=wet-ok + 2. * + > print text=wet-no-commit +2. * + > print text=wet-fail + +**body = fs.read_text path="_example_sbx/note.txt"** +1. `body` == "sandbox-okf" + > print text=proof-visible +2. * + > print text=proof-missing + +**pname = [name]([profile](wet))** +1. `pname` == "default" + > print text=profile-default +2. * + > print text=profile-other diff --git a/ext/ai/agent.mq.md b/ext/ai/agent.mq.md index 0d94646..8d7bf76 100644 --- a/ext/ai/agent.mq.md +++ b/ext/ai/agent.mq.md @@ -9,6 +9,8 @@ import time:lib/time.mq.md import wb:lib/writeback.mq.md import subtask:lib/subtask.mq.md import plugin:lib/plugin.mq.md +import sandbox:ext/ai/sandbox.mq.md +import table:lib/table.mq.md --- ## build_step_context @@ -247,23 +249,129 @@ Structured observation for the parent developer-agent: source, named writeback s --- +## trial + + `path`=None + + `source`=None + + `root`=None + + `write_path`=None + + `text`=None + + `commit`=True + + `profile`=default + +Opt-in CoW trial (O1): open → optional upper write → optional run → diff → commit on success else discard. +Host tree unchanged until a successful commit. Return map is a GFM table (link-index readable). + +**sb = sandbox.open root=`root` profile=`profile`** +**id = [id](sb)** +**prof = [profile](sb)** +**ok = True** +**stdout = ""** +**stderr = ""** + +1. `write_path` + 1. `text` + > sandbox.write id=`id` path=`write_path` text=`text` + 2. * + **_ = 1** +2. * + **_ = 1** + +1. `source` + **ret = sandbox.run id=`id` source=`source`** + **ok = [ok](ret)** + **stdout = [stdout](ret)** + **stderr = [stderr](ret)** +2. `path` + **ret = sandbox.run id=`id` path=`path`** + **ok = [ok](ret)** + **stdout = [stdout](ret)** + **stderr = [stderr](ret)** +3. * + **_ = 1** + +**pending = sandbox.diff id=`id`** +**committed = False** + +1. `ok` + 1. `commit` + > sandbox.commit id=`id` + **committed = True** + 2. * + > sandbox.discard id=`id` +2. * + > sandbox.discard id=`id` + +**out = ** + +| ok | committed | diff | stdout | stderr | id | profile | +|----|-----------|------|--------|--------|-----|---------| +| `ok` | `committed` | `pending` | `stdout` | `stderr` | `id` | `prof` | + +*out* + +## step_route + + `kind`=default + +O3: map step class (`lookup` | `patch` | `sandbox_run` | `net` | `default`) → Adaptive Routing backend. +Authority is the GFM table in `ext/ai/policies/step-route.mq.md` (mirrored here for offline reads). + +1. `kind` == "lookup" + **backend = "marqdo"** +2. `kind` == "patch" + **backend = "small-llm"** +3. `kind` == "sandbox_run" + **backend = "marqdo"** +4. `kind` == "net" + **backend = "llm"** +5. * + **backend = "auto"** + +**out = table.put in=None at="kind" value=`kind`** +**out = table.put in=`out` at="backend" value=`backend`** +*out* + ## await_workbook + `path` + + `sandbox`=False + + `sandbox_root`=None + + `sandbox_profile`=default -Spawn a workbook file (quiet by default), wait for `{code,value,stdout?,stderr?}`, and inspect. +Spawn a workbook file (quiet by default), wait, and inspect. +With `sandbox=True`, run via `## trial` first (commit on ok); host unchanged until that commit. -**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* +1. `sandbox` + **tr = trial path=`path` root=`sandbox_root` profile=`sandbox_profile` commit=True** + **ok = [ok](tr)** + **stdout = [stdout](tr)** + **stderr = [stderr](tr)** + 1. `ok` + **code = 0** + 2. * + **code = 1** + **value = stdout** + **obs = inspect_workbook path=`path` exit_code=`code` value=`value` stdout=`stdout` stderr=`stderr`** + **out = ** + + | code | value | observation | sandbox | + |------|-------|-------------|---------| + | `code` | `value` | `obs` | `tr` | + + *out* +2. * + **id = subtask.spawn path=`path`** + **waited = subtask.wait id=`id`** + **code = [code](waited)** + **value = [value](waited)** + **stdout = [stdout](waited)** + **stderr = [stderr](waited)** + **obs = inspect_workbook path=`path` exit_code=`code` value=`value` stdout=`stdout` stderr=`stderr`** + **out = ** + + | code | value | observation | + |------|-------|-------------| + | `code` | `value` | `obs` | + + *out* --- @@ -1695,8 +1803,16 @@ Skill resolver (v2): exact → alias → canonical → near. Returns `mode` / `r + `kb_dir`=.marqdo/agent-kb + `memory_dir`=.marqdo/agent-memory + `threshold`=0.78 + + `step_kind`=None Adaptive Routing (Phase 4): abstract router — `marqdo` | `small-llm` | `llm` | `auto`. `jev` is accepted as a **compat alias** of `small-llm` (not a first-class backend). `auto` cascades policy → kb → small-llm request. May return `needs_llm=True` + `prompt` for the caller to complete with `router_model` (any llm handle), then `route_apply`. +Optional `step_kind=` (O3) selects backend via module `## step_route` before the ABI call. + +1. `step_kind` + **sr = step_route kind=`step_kind`** + **backend = [backend](sr)** +2. * + **_ = 1** **tools = > json.get value=`self` key="tools"** *> agent_route task=`task` backend=`backend` kb_dir=`kb_dir` memory_dir=`memory_dir` threshold=`threshold` tools=`tools`* @@ -1747,6 +1863,15 @@ Persist one run as `.mq.md` under `memory_dir/episodes/YYYY/MM/` (v2 Phase 1). M *> agent_record_episode task=`task` status=`status` result=`result` mode=`mode` skill=`skill` observation=`observation` workbook=`workbook` cache=`cache` match=`match` llm_calls=`llm_calls` tool_calls=`tool_calls` error=`error` memory_dir=`memory_dir`* +## quarantine + + `slug` + + `kb_dir`=.marqdo/agent-kb + + `reason`=sandbox_or_harness_failed + +O5: mark OKF skill `status: quarantine` and force `llm_free: false`. Regression fixtures stay with the slug. + +*> agent_kb_quarantine kb_dir=`kb_dir` slug=`slug` reason=`reason`* + ## maybe_learn + `task` + `kb_dir`=.marqdo/agent-kb @@ -1755,6 +1880,7 @@ Persist one run as `.mq.md` under `memory_dir/episodes/YYYY/MM/` (v2 Phase 1). M + `promote`=True Offline learn gate: when ≥ `improve_every` successful episodes share a task hash, generalize → synthesize → compile → optional OKF promote (`llm_free`). Also attempts Policy Compilation for Adaptive Routing. +O2: promote path requires sandbox proof unless `require_proof=false`. **skill_learn = > agent_maybe_learn task=`task` kb_dir=`kb_dir` memory_dir=`memory_dir` improve_every=`improve_every` promote=`promote`** **policy_learn = > agent_maybe_compile_policy memory_dir=`memory_dir` min_evidence=`improve_every`** @@ -1806,45 +1932,51 @@ Reasoning amortization stats over recorded episodes (`avg_llm_calls`, `compiled_ + `router_model`=None + `resume_id`=None + `resume_dir`=.marqdo/agent-resume + + `sandbox`=False + + `sandbox_profile`=default + + `efi`=True Primary author entry (v2 + P4): Adaptive `route` → execute (policy/kb skill) or `plan` → record episode → maybe_learn (skill + policy). `router` = `auto`|`marqdo`|`small-llm`|`llm` (`jev`→`small-llm` alias). Optional `router_model` (llm handle) answers `needs_llm` prompts — small models welcome. +`sandbox=True` (O1 opt-in): workbook paths run via CoW trial before host commit. `efi=True` (O3): EKC preflight before explore; REUSE short-circuits. Pass `efi=False` to keep legacy golds that skip eng knowledge. -**routed = > `self`.route task=`task` backend=`router` kb_dir=`kb_dir` memory_dir=`memory_dir` threshold=`near_threshold`** -**route_matched = > json.get value=`routed` key="matched"** -**needs_llm = > json.get value=`routed` key="needs_llm"** +**efi_pf = None** +1. `efi` + **efi_pf = preflight task=`task`** +2. * + **_ = 1** + +**routed = `self`.route task=`task` backend=`router` kb_dir=`kb_dir` memory_dir=`memory_dir` threshold=`near_threshold`** +**route_matched = [matched](routed)** +**needs_llm = [needs_llm](routed)** **exec_mode = "explore"** **llm_calls = 0** **tokens = 0** +**token_cost = 0** **out = None** -**route_backend = > json.get value=`routed` key="backend"** +**route_backend = [backend](routed)** 1. `route_matched` **path = > json.get value=`routed` key="resource"** 1. `path` - **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"** + **aw = await_workbook path=`path` sandbox=`sandbox` sandbox_profile=`sandbox_profile`** + **code = [code](aw)** + **child_val = [value](aw)** + **last_obs = [observation](aw)** 1. `code` == 0 > agent_kb_record_hit kb_dir=`kb_dir` goal=`task` improve_every=`improve_every` - **lf = > json.get value=`routed` key="llm_free"** + **lf = [llm_free](routed)** 1. `lf` **exec_mode = "compiled"** 2. * **exec_mode = "routed"** - **out = > json.parse text={"status":"ok"}** - **out = > json.set map=`out` key="status" value="ok"** - **out = > json.set map=`out` key="goal" value=`task`** - **out = > json.set map=`out` key="result" value=`child_val`** - **out = > json.set map=`out` key="workbook" value=`path`** - **out = > json.set map=`out` key="cache" value="hit"** - **rmode = > json.get value=`routed` key="mode"** - **out = > json.set map=`out` key="match" value=`rmode`** - **sk = > json.get value=`routed` key="skill"** - **out = > json.set map=`out` key="skill" value=`sk`** - **out = > json.set map=`out` key="observation" value=`last_obs`** - **out = > json.set map=`out` key="summary" value="adaptive route hit"** - **out = > json.set map=`out` key="route" value=`routed`** + **rmode = [mode](routed)** + **sk = [skill](routed)** + **out = ** + + | status | goal | result | workbook | cache | match | skill | observation | summary | route | + |--------|------|--------|----------|-------|-------|-------|-------------|---------|-------| + | ok | `task` | `child_val` | `path` | hit | `rmode` | `sk` | `last_obs` | adaptive route hit | `routed` | + **llm_calls = 0** 2. * **route_matched = False** @@ -1857,33 +1989,28 @@ Primary author entry (v2 + P4): Adaptive `route` → execute (policy/kb skill) o **_ = 1** 2. `needs_llm` 1. `router_model` - **prompt = > json.get value=`routed` key="prompt"** - **turn = > model_turn model=`router_model` prompt=`prompt` stream=`stream` echo=`echo`** - **reply = > json.get value=`turn` key="text"** - **llm_calls = > json.get value=`turn` key="llm_calls"** - **tokens = > json.get value=`turn` key="tokens"** - **applied = > `self`.route_apply task=`task` reply=`reply` kb_dir=`kb_dir` backend=`router`** - **am = > json.get value=`applied` key="matched"** + **prompt = [prompt](routed)** + **turn = model_turn model=`router_model` prompt=`prompt` stream=`stream` echo=`echo`** + **reply = [text](turn)** + **llm_calls = [llm_calls](turn)** + **tokens = [tokens](turn)** + **applied = `self`.route_apply task=`task` reply=`reply` kb_dir=`kb_dir` backend=`router`** + **am = [matched](applied)** 1. `am` - **path = > json.get value=`applied` 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 = [resource](applied)** + **aw = await_workbook path=`path` sandbox=`sandbox` sandbox_profile=`sandbox_profile`** + **code = [code](aw)** + **child_val = [value](aw)** + **last_obs = [observation](aw)** 1. `code` == 0 **exec_mode = "routed"** - **out = > json.parse text={"status":"ok"}** - **out = > json.set map=`out` key="status" value="ok"** - **out = > json.set map=`out` key="goal" value=`task`** - **out = > json.set map=`out` key="result" value=`child_val`** - **out = > json.set map=`out` key="workbook" value=`path`** - **out = > json.set map=`out` key="cache" value="soft-hit"** - **out = > json.set map=`out` key="match" value="routed"** - **sk = > json.get value=`applied` key="skill"** - **out = > json.set map=`out` key="skill" value=`sk`** - **out = > json.set map=`out` key="observation" value=`last_obs`** - **out = > json.set map=`out` key="summary" value="router model selected skill"** - **out = > json.set map=`out` key="route" value=`applied`** + **sk = [skill](applied)** + **out = ** + + | status | goal | result | workbook | cache | match | skill | observation | summary | route | + |--------|------|--------|----------|-------|-------|-------|-------------|---------|-------| + | ok | `task` | `child_val` | `path` | soft-hit | routed | `sk` | `last_obs` | router model selected skill | `applied` | + **route_matched = True** 2. * **route_matched = False** @@ -1897,29 +2024,51 @@ Primary author entry (v2 + P4): Adaptive `route` → execute (policy/kb skill) o 1. `route_matched` **_ = 1** 2. * - **resolved = > `self`.resolve task=`task` kb_dir=`kb_dir` near_match=`near_match` near_threshold=`near_threshold`** - **mode = > json.get value=`resolved` key="mode"** - **llm_free = > json.get value=`resolved` key="llm_free"** + 1. `efi_pf` + **efi_st = [status](efi_pf)** + **efi_dec = [decision](efi_pf)** + **efi_allow = [create_allowed](efi_pf)** + 1. `efi_st` == "missing_knowledge" + **_ = 1** + 2. `efi_dec` == "REUSE" + **_ = 1** + 3. `efi_dec` == "ADAPT" + **_ = 1** + 4. `efi_allow` + **_ = 1** + 5. * + **out = ** + + | status | goal | error | summary | efi | + |--------|------|-------|---------|-----| + | error | `task` | efi_create_denied | EKC preflight denied CREATE | `efi_pf` | + + **exec_mode = "efi"** + 2. * + **_ = 1** + + 1. `out` + **_ = 1** + 2. * + **resolved = `self`.resolve task=`task` kb_dir=`kb_dir` near_match=`near_match` near_threshold=`near_threshold`** + **mode = [mode](resolved)** + **llm_free = [llm_free](resolved)** 1. `llm_free` - **path = > json.get value=`resolved` 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 = [resource](resolved)** + **aw = await_workbook path=`path` sandbox=`sandbox` sandbox_profile=`sandbox_profile`** + **code = [code](aw)** + **child_val = [value](aw)** + **last_obs = [observation](aw)** 1. `code` == 0 > agent_kb_record_hit kb_dir=`kb_dir` goal=`task` improve_every=`improve_every` **exec_mode = "compiled"** - **out = > json.parse text={"status":"ok"}** - **out = > json.set map=`out` key="status" value="ok"** - **out = > json.set map=`out` key="goal" value=`task`** - **out = > json.set map=`out` key="result" value=`child_val`** - **out = > json.set map=`out` key="workbook" value=`path`** - **out = > json.set map=`out` key="cache" value="hit"** - **out = > json.set map=`out` key="match" value=`mode`** - **sk = > json.get value=`resolved` key="skill"** - **out = > json.set map=`out` key="skill" value=`sk`** - **out = > json.set map=`out` key="observation" value=`last_obs`** - **out = > json.set map=`out` key="summary" value="compiled skill (llm_free)"** + **sk = [skill](resolved)** + **out = ** + + | status | goal | result | workbook | cache | match | skill | observation | summary | + |--------|------|--------|----------|-------|-------|-------|-------------|--------| + | ok | `task` | `child_val` | `path` | hit | `mode` | `sk` | `last_obs` | compiled skill (llm_free) | + **llm_calls = 0** 2. * **out = > `self`.plan goal=`task` kb_dir=`kb_dir` writeback=`writeback` reuse=`reuse` near_match=`near_match` near_threshold=`near_threshold` promote=`promote` improve_every=`improve_every` explore_n=`explore_n` max_rounds=`max_rounds` stream=`stream` echo=`echo` trace=`trace` force=`force`** @@ -1966,23 +2115,37 @@ Primary author entry (v2 + P4): Adaptive `route` → execute (policy/kb skill) o 2. * **_ = 1** -**execution = > json.parse text={"mode":"explore","llm_calls":0,"tokens":0}** -**execution = > json.set map=`execution` key="mode" value=`exec_mode`** -**execution = > json.set map=`execution` key="llm_calls" value=`llm_calls`** -**execution = > json.set map=`execution` key="tokens" value=`tokens`** -**execution = > json.set map=`execution` key="skill" value=`sk2`** -**execution = > json.set map=`execution` key="router" value=`route_backend`** -**out = > json.set map=`out` key="execution" value=`execution`** -**out = > json.set map=`out` key="episode" value=`ep`** -**out = > json.set map=`out` key="route" value=`routed`** +**token_cost = tokens** +**usage = ** + +| llm_calls | tokens | token_cost | +|-----------|--------|------------| +| `llm_calls` | `tokens` | `token_cost` | + +**execution = ** + +| mode | llm_calls | tokens | token_cost | skill | router | +|------|-----------|--------|------------|-------|--------| +| `exec_mode` | `llm_calls` | `tokens` | `token_cost` | `sk2` | `route_backend` | + +**out = table.put in=`out` at="execution" value=`execution`** +**out = table.put in=`out` at="episode" value=`ep`** +**out = table.put in=`out` at="route" value=`routed`** +**out = table.put in=`out` at="usage" value=`usage`** +**out = table.put in=`out` at="token_cost" value=`token_cost`** 1. `learning` - **out = > json.set map=`out` key="learning" value=`learning`** + **out = table.put in=`out` at="learning" value=`learning`** +2. * + **_ = 1** + +1. `efi_pf` + **out = table.put in=`out` at="efi" value=`efi_pf`** 2. * **_ = 1** 1. `resume_id` - **_ckpt = > resume_save id=`resume_id` goal=`task` task=`task` status=`st` round=1 workbook=`wb_path` result=`res` route=`routed` resume_dir=`resume_dir`** - **out = > json.set map=`out` key="resume" value=`_ckpt`** + **_ckpt = resume_save id=`resume_id` goal=`task` task=`task` status=`st` round=1 workbook=`wb_path` result=`res` route=`routed` resume_dir=`resume_dir`** + **out = table.put in=`out` at="resume" value=`_ckpt`** 2. * **_ = 1** @@ -1994,10 +2157,13 @@ Primary author entry (v2 + P4): Adaptive `route` → execute (policy/kb skill) o + `stream`=False + `echo`=False + `max_reads`=2 + + `sandbox`=False + + `sandbox_profile`=default One atomic turn: budgeted context → LLM → optional `READ:` deepen → optional tool via subtask. Returns a *map* (`status`, `task`, `decision`, and on success `result` plus optional `tool` / `tool_result`; on failure `error`). By default (`writeback=True`) persists that map under named slots `ok` / `error` at the call site; pass `writeback=False` to skip. 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). Context source/skill start at default budget; up to `max_reads` of `READ:source` / `READ:skill` deepen before CALL/answer. +`sandbox=True` (O1 opt-in): attach the sandbox profile row on the result map (trial via `## trial` / `run sandbox=`). **id = > json.get value=`self` key="id"** **model = > json.get value=`self` key="model"** @@ -2088,6 +2254,12 @@ With `stream=True`, the model call uses SSE; `echo=True` prints delta text to st **out = > json.set map=`out` key="llm_calls" value=`llm_calls`** **out = > json.set map=`out` key="tokens" value=`tokens`** +1. `sandbox` + **prof = sandbox.profile name=`sandbox_profile`** + **out = table.put in=`out` at="sandbox_profile" value=`prof`** +2. * + **_ = 1** + **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` diff --git a/ext/ai/policies/step-route.mq.md b/ext/ai/policies/step-route.mq.md new file mode 100644 index 0000000..defe152 --- /dev/null +++ b/ext/ai/policies/step-route.mq.md @@ -0,0 +1,25 @@ +--- +title: step-route policy (O3) +description: > + Table-driven map from step class → Adaptive Routing backend. + Readable authority for agent.step_route; do not invent a second dialect. +--- + +# Step class → backend + +Authors and `agent.step_route` read this table. Backends match Adaptive Routing: +`marqdo` | `small-llm` | `llm` | `auto`. + +**routes = ** + +| kind | backend | note | +|------|---------|------| +| lookup | marqdo | OKF / kb skill hit — no parent LLM | +| patch | small-llm | Local patch / soft match | +| sandbox_run | marqdo | CoW trial of `.mq.md` | +| net | llm | Needs network / toolful turn | +| default | auto | Cascade policy → kb → small-llm | + +# main + +*routes* diff --git a/ext/ai/sandbox.mq.md b/ext/ai/sandbox.mq.md index ed5b75f..97727e0 100644 --- a/ext/ai/sandbox.mq.md +++ b/ext/ai/sandbox.mq.md @@ -5,10 +5,14 @@ description: >- Native work lives in plugins/agent (`sandbox_*` → host_query). import plugin:lib/plugin.mq.md import sys:lib/sys.mq.md +import table:lib/table.mq.md +import fs:lib/fs.mq.md --- Load the agent plugin once per call (same pattern as other `ext/ai` helpers). +Capability profiles are GFM tables under `## profile` (readable authority; `open` / `inspect` echo them). Do not invent a second table dialect. + ## ensure_plugin **p = plugin.native_path name="agent"** @@ -18,10 +22,38 @@ Load the agent plugin once per call (same pattern as other `ext/ai` helpers). > print text=ext/ai/sandbox: native agent plugin not found (build marqdo_plugin_agent or marqdo ext add agent) > sys.exit code=1 -## open +## profile + + `name`=default + +Named caps row as a map table (`name`, `fs_write`, `exec`, `net`, `plugin`). Unknown names → `default`. + +Catalog (documentation + authority): + +| name | fs_write | exec | net | plugin | +|------|----------|------|-----|--------| +| default | true | false | false | false | +| readonly | false | false | false | false | + +1. `name` == "readonly" + **row = ** + + | name | fs_write | exec | net | plugin | + |------|----------|------|-----|--------| + | readonly | false | false | false | false | + +2. * + **row = ** + + | name | fs_write | exec | net | plugin | + |------|----------|------|-----|--------| + | default | true | false | false | false | + +*row* + +## open_native + `root`=None -Open a CoW session. Optional `root=` (directory). Default: entry file directory. +Native CoW open (plugin ABI italic return). Prefer `## open` for the profile-aware facade. > ensure_plugin @@ -30,6 +62,18 @@ Open a CoW session. Optional `root=` (directory). Default: entry file directory. 2. * *> sandbox_open* +## open + + `root`=None + + `profile`=default + +Open a CoW session. Optional `root=` (directory). Default: entry file directory. +`profile=` selects the caps row from `## profile` (echoed by `inspect`). + +**sess = open_native root=`root`** +**prof = profile name=`profile`** +**sess = table.put in=`sess` at="profile" value=`prof`** +*sess* + ## write + `id` + `path` @@ -100,10 +144,48 @@ Pass `source=` or `path=` (relative to session root). > print text=ext/ai/sandbox.run: need source= or path= > sys.exit code=1 -## inspect +## inspect_native + `id` -Caps defaults, change counts, and availability notes. - > ensure_plugin *> sandbox_inspect id=`id`* + +## inspect + + `id` + + `profile`=default + +Native caps / change counts, plus the GFM `## profile` row under key `profile`. + +**raw = inspect_native id=`id`** +**prof = profile name=`profile`** +**out = table.put in=`raw` at="profile" value=`prof`** +*out* + +## report + + `id` + + `path`=sandbox-diff.md + +O4: write a markdown review of `## diff` for `marqdo view` / HITL (static report file, not a UI rewrite). + +**pending = diff id=`id`** +**n = len value=`pending`** +**body = "# Sandbox diff report\n\nPending changes: "** +**body = body + n** +**body = body + "\n\n| path | kind |\n|------|------|\n"** +- [row](pending) + **p = [path](row)** + **k = [kind](row)** + **body = body + "| "** + **body = body + p** + **body = body + " | "** + **body = body + k** + **body = body + " |\n"** +> fs.write_text path=`path` text=`body` + +**out = ** + +| path | count | +|------|-------| +| `path` | `n` | + +*out* diff --git a/ext/ai/智能体.mq.md b/ext/ai/智能体.mq.md index 9b63eaf..6dea58b 100644 --- a/ext/ai/智能体.mq.md +++ b/ext/ai/智能体.mq.md @@ -3,6 +3,8 @@ title: ext/ai/智能体 description: 文档驱动智能体 v2 — 单步 / 多步 / 运行;技能编译经 ABI v2 agent 插件(情景 → 学习 → llm_free)。 导入 大模型:ext/ai/大模型.mq.md import agent:ext/ai/agent.mq.md +import sandbox:ext/ai/sandbox.mq.md +import table:lib/table.mq.md import json:lib/json.mq.md 导入 系统:lib/系统.mq.md 导入 自写回:lib/自写回.mq.md @@ -106,15 +108,30 @@ import json:lib/json.mq.md > agent_history_clear id=`id` **** +## 试跑 + + `路径`=None + + `源码`=None + + `根目录`=None + + `写入路径`=None + + `文本`=None + + `提交`=真 + + `配置`=default + +O1 可选沙盒试跑。转发 `agent.trial`(表风格返回;宿主树在成功 `提交` 前不变)。 + +*> agent.trial path=`路径` source=`源码` root=`根目录` write_path=`写入路径` text=`文本` commit=`提交` profile=`配置`* + ## 单步 + `任务` + `写回`=真 + `流式`=假 + `打印增量`=假 + + `沙盒`=假 + + `沙盒配置`=default 原子一轮:上下文 → 大模型 → 可选子任务调工具。返回 *map*(`status`、`task`、`decision`;成功含 `result`,可选 `tool` / `tool_result`;失败含 `error`)。默认(`写回=真`)将结果写入调用行下的命名槽 `ok` / `error`;传 `写回=假` 可关闭。 -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。 +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。`沙盒=真` 时结果附带沙盒配置行。 **ctx = > 构建单步上下文 智能体=`自` 任务=`任务`** **id = > json.get value=`自` key="id"** @@ -171,6 +188,12 @@ import json:lib/json.mq.md **as_turn = > json.set map=`as_turn` key="content" value=`reply`** > agent_history_append id=`id` item=`as_turn` +1. `沙盒` + **配置行 = sandbox.profile name=`沙盒配置`** + **out = table.put in=`out` at="sandbox_profile" value=`配置行`** +2. * + **_ = 1** + 1. `写回` **body = > json.stringify value=`out`** **st = > json.get value=`out` key="status"** @@ -296,14 +319,17 @@ Engineering First Information 门闩。转发 `agent.preflight`。 + `强制`=False + `路由`=auto + `路由模型`=None + + `沙盒`=False + + `沙盒配置`=default + + `工程预检`=True -v2+P4 主入口:自适应路由 → 执行 → 记录情景 → 尝试学习(技能 + 策略)。`路由`=`auto`|`marqdo`|`small-llm`|`llm`(`jev` 为 `small-llm` 兼容别名);决策器用 `路由模型`(任意 llm 句柄)。 +v2+P4 主入口:自适应路由 → 执行 → 记录情景 → 尝试学习(技能 + 策略)。`路由`=`auto`|`marqdo`|`small-llm`|`llm`(`jev` 为 `small-llm` 兼容别名);决策器用 `路由模型`(任意 llm 句柄)。`沙盒=真` 走 CoW 试跑;`工程预检` 对应 `efi`。 **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.run task=`任务` kb_dir=`知识库目录` memory_dir=`记忆目录` learn=`学习` verify=`校验` writeback=`写回` reuse=`复用` near_match=`近义命中` near_threshold=`近义阈值` promote=`晋升` improve_every=`改进周期` explore_n=`探索次数` max_rounds=`最大轮次` stream=`流式` echo=`打印增量` trace=`轨迹` force=`强制` router=`路由` router_model=`路由模型`* +*> en.run task=`任务` kb_dir=`知识库目录` memory_dir=`记忆目录` learn=`学习` verify=`校验` writeback=`写回` reuse=`复用` near_match=`近义命中` near_threshold=`近义阈值` promote=`晋升` improve_every=`改进周期` explore_n=`探索次数` max_rounds=`最大轮次` stream=`流式` echo=`打印增量` trace=`轨迹` force=`强制` router=`路由` router_model=`路由模型` sandbox=`沙盒` sandbox_profile=`沙盒配置` efi=`工程预检`* ## 路由 + `任务` diff --git a/plugins/agent/src/kb.rs b/plugins/agent/src/kb.rs index fa60e26..bc375f7 100644 --- a/plugins/agent/src/kb.rs +++ b/plugins/agent/src/kb.rs @@ -511,11 +511,25 @@ fn write_skill_concept( quality: i64, hits: i64, now: &str, + meta: &SkillMeta, ) -> Result<(), String> { if let Some(p) = path.parent() { fs::create_dir_all(p).map_err(|e| format!("mkdir: {e}"))?; } let title: String = goal.chars().take(48).collect(); + let mut extra = String::new(); + if let Some(ref s) = meta.applies_when { + extra.push_str(&format!("applies_when: {}\n", yaml_escape(s))); + } + if let Some(ref s) = meta.fixtures { + extra.push_str(&format!("fixtures: {}\n", yaml_escape(s))); + } + if let Some(ref s) = meta.sandbox_profile { + extra.push_str(&format!("sandbox_profile: {}\n", yaml_escape(s))); + } + if let Some(ref s) = meta.proof { + extra.push_str(&format!("proof: {}\n", yaml_escape(s))); + } let body = format!( r#"--- type: Marqdo Agent Skill @@ -526,7 +540,7 @@ status: {status} llm_free: {llm_free} quality: {quality} hits: {hits} -generated: +{extra}generated: by: marqdo-agent/plan at: {now} verified: @@ -545,11 +559,29 @@ Prefer spawning `resource` over re-planning. llm_free = if llm_free { "true" } else { "false" }, quality = quality, hits = hits, + extra = extra, now = now, ); fs::write(path, body).map_err(|e| format!("write skill: {e}")) } +#[derive(Default)] +struct SkillMeta { + applies_when: Option, + fixtures: Option, + sandbox_profile: Option, + proof: Option, +} + +fn skill_meta_from_src(src: &str) -> SkillMeta { + SkillMeta { + applies_when: extract_fm_field(src, "applies_when"), + fixtures: extract_fm_field(src, "fixtures"), + sandbox_profile: extract_fm_field(src, "sandbox_profile"), + proof: extract_fm_field(src, "proof"), + } +} + fn refresh_index(root: &Path, slug: &str, goal: &str) -> Result<(), String> { let index = root.join("index.md"); let line = format!( @@ -585,6 +617,10 @@ fn arg_text<'a>(args: &'a Value, key: &str) -> Result<&'a str, String> { .ok_or_else(|| format!("missing text `{key}`")) } +fn opt_text<'a>(args: &'a Value, key: &str) -> Option<&'a str> { + args.get(key).and_then(|v| v.as_str()).filter(|s| !s.is_empty()) +} + fn opt_tools(args: &Value) -> Option<&Value> { args.get("tools").filter(|t| !t.is_null()) } @@ -1107,6 +1143,54 @@ pub fn kb_record_hit(args: &Value) -> Result { })) } +/// Run workbook (or FM `proof:` / `fixtures:` path) inside CoW sandbox; discard after. +/// O2: llm_free promote requires this proof to succeed (unless `require_proof=false`). +fn sandbox_proof(workbook: &Path, proof_rel: Option<&str>) -> Result<(bool, String), String> { + let root = workbook + .parent() + .ok_or_else(|| "sandbox_proof: workbook has no parent".to_string())?; + // Always pass an absolute root so host `sandbox_open` does not re-join cwd. + let root_abs = if root.is_absolute() { + root.to_path_buf() + } else { + fs::canonicalize(root).unwrap_or_else(|_| { + std::env::current_dir() + .unwrap_or_else(|_| PathBuf::from(".")) + .join(root) + }) + }; + let root_abs = fs::canonicalize(&root_abs).unwrap_or(root_abs); + let default_name = workbook + .file_name() + .and_then(|s| s.to_str()) + .ok_or_else(|| "sandbox_proof: bad workbook name".to_string())?; + let path = proof_rel.unwrap_or(default_name); + let open = crate::host_query_json_args( + "sandbox_open", + &json!({ "root": root_abs.to_string_lossy() }), + )?; + let id = open + .get("id") + .and_then(|v| v.as_str()) + .ok_or_else(|| "sandbox_proof: open missing id".to_string())? + .to_string(); + let run = crate::host_query_json_args("sandbox_run", &json!({ "id": id, "path": path })); + let _ = crate::host_query_json_args("sandbox_discard", &json!({ "id": id })); + match run { + Ok(r) => { + let ok = r.get("ok").and_then(|v| v.as_bool()).unwrap_or(false); + let detail = r + .get("stderr") + .and_then(|v| v.as_str()) + .or_else(|| r.get("stdout").and_then(|v| v.as_str())) + .unwrap_or("") + .to_string(); + Ok((ok, detail)) + } + Err(e) => Ok((false, e)), + } +} + pub fn kb_promote(args: &Value) -> Result { let kb = arg_text(args, "kb_dir")?; let goal = arg_text(args, "goal")?; @@ -1119,6 +1203,26 @@ pub fn kb_promote(args: &Value) -> Result { let src_path = resolve_path(workbook); let src = fs::read_to_string(&src_path) .map_err(|e| format!("kb_promote read workbook: {e}"))?; + let require_proof = args + .get("require_proof") + .and_then(|v| v.as_bool()) + .unwrap_or(true); + let proof_rel = extract_fm_field(&src, "proof") + .or_else(|| extract_fm_field(&src, "fixtures")); + if require_proof { + let (ok, detail) = sandbox_proof(&src_path, proof_rel.as_deref())?; + if !ok { + return Ok(json!({ + "promoted": false, + "reason": "sandbox_proof_failed", + "detail": detail, + "sig": sig, + "slug": slug, + "workbook": workbook, + "proof": proof_rel.unwrap_or_else(|| src_path.file_name().and_then(|s| s.to_str()).unwrap_or("").to_string()), + })); + } + } let (llm_free, quality) = llm_free_score(&src); let status = if llm_free { "stable" } else { "candidate" }; @@ -1168,6 +1272,7 @@ pub fn kb_promote(args: &Value) -> Result { &now, &extra_aliases, )?; + let meta = skill_meta_from_src(&src); write_skill_concept( &skill_path, &sig, @@ -1178,6 +1283,7 @@ pub fn kb_promote(args: &Value) -> Result { quality, prev_hits, &now, + &meta, )?; refresh_index(&root, &slug, &goal_n)?; @@ -1190,6 +1296,69 @@ pub fn kb_promote(args: &Value) -> Result { "quality": quality, "status": status, "hits": prev_hits, + "proof_ok": true, + "applies_when": meta.applies_when, + "fixtures": meta.fixtures, + "sandbox_profile": meta.sandbox_profile, + })) +} + +/// O5: mark a skill concept as `status: quarantine` and keep fixtures path in FM. +pub fn kb_quarantine(args: &Value) -> Result { + let kb = arg_text(args, "kb_dir")?; + let slug = arg_text(args, "slug")?; + let reason = opt_text(args, "reason").unwrap_or("sandbox_or_harness_failed"); + let root = resolve_path(kb); + let skill_path = root.join("concepts/skills").join(format!("{slug}.md")); + if !skill_path.is_file() { + return Ok(json!({ + "ok": false, + "reason": "skill_not_found", + "slug": slug, + "path": skill_path.to_string_lossy(), + })); + } + let src = fs::read_to_string(&skill_path) + .map_err(|e| format!("kb_quarantine read: {e}"))?; + let mut lines: Vec = Vec::new(); + let mut saw_status = false; + let mut in_fm = false; + for line in src.lines() { + let t = line.trim(); + if t == "---" { + if !in_fm { + in_fm = true; + lines.push(line.to_string()); + continue; + } else { + if !saw_status { + lines.push("status: quarantine".to_string()); + } + lines.push(format!("quarantine_reason: {}", yaml_escape(reason))); + in_fm = false; + lines.push(line.to_string()); + continue; + } + } + if in_fm && t.starts_with("status:") { + lines.push("status: quarantine".to_string()); + saw_status = true; + continue; + } + if in_fm && t.starts_with("llm_free:") { + lines.push("llm_free: false".to_string()); + continue; + } + lines.push(line.to_string()); + } + let body = lines.join("\n") + "\n"; + fs::write(&skill_path, body).map_err(|e| format!("kb_quarantine write: {e}"))?; + Ok(json!({ + "ok": true, + "slug": slug, + "status": "quarantine", + "reason": reason, + "path": skill_path.to_string_lossy(), })) } diff --git a/plugins/agent/src/lib.rs b/plugins/agent/src/lib.rs index 06e5757..0f18841 100644 --- a/plugins/agent/src/lib.rs +++ b/plugins/agent/src/lib.rs @@ -901,6 +901,7 @@ kb_ffi!(agent_corpus_search, corpus::corpus_search, "agent_corpus_search"); kb_ffi!(agent_mcp_fixture, corpus::mcp_fixture, "agent_mcp_fixture"); kb_ffi!(agent_kb_add_alias, kb::kb_add_alias, "agent_kb_add_alias"); kb_ffi!(agent_kb_promote, kb::kb_promote, "agent_kb_promote"); +kb_ffi!(agent_kb_quarantine, kb::kb_quarantine, "agent_kb_quarantine"); kb_ffi!(agent_kb_record_hit, kb::kb_record_hit, "agent_kb_record_hit"); kb_ffi!( agent_workbook_solidify, @@ -1067,6 +1068,15 @@ pub unsafe extern "C" fn marqdo_plugin_init(host: *const MarqdoHostApi) -> c_int { return 1; } + if register( + host, + "agent_kb_quarantine", + "kb_dir,slug", + agent_kb_quarantine, + ) != 0 + { + return 1; + } if register(host, "agent_kb_record_hit", "kb_dir,goal", agent_kb_record_hit) != 0 { return 1; } diff --git a/scripts/agent-harness.sh b/scripts/agent-harness.sh index 55bc987..be31ba4 100755 --- a/scripts/agent-harness.sh +++ b/scripts/agent-harness.sh @@ -39,6 +39,32 @@ run tests/ext/agent-zero-llm.mq.md run tests/ext/agent-plan-preserve.mq.md run examples/agent-okf-flywheel/index.mq.md run examples/agent-pong/index.mq.md +run examples/agent-sandbox-okf/index.mq.md +run tests/ext/agent-sandbox-optin.mq.md +run tests/ext/agent-sandbox-promote.mq.md + +# Skill Lift subset (O2 B3/E1): with-skill vs without — constitution / writeback / call_site markers. +skill_lift_pass=0 +skill_lift_fail=0 +assert_out_has() { + local f="$1" + local needle="$2" + local label="$3" + local out + out="$("$MQ" run "$f" 2>/dev/null || true)" + if printf '%s' "$out" | grep -q -- "$needle"; then + echo "SkillLift OK $label ($needle)" + skill_lift_pass=$((skill_lift_pass + 1)) + else + echo "SkillLift MISS $label (need $needle)" >&2 + skill_lift_fail=$((skill_lift_fail + 1)) + fail=1 + fi +} +assert_out_has tests/ext/agent-constitution-b0.mq.md "constitution-ok" "constitution" +assert_out_has tests/ext/agent-writeback-shadow.mq.md "writeback-shadow-ok" "writeback" +assert_out_has tests/ext/agent-dump-context.mq.md "dump-context-ok" "call_site" +echo "SkillLift summary: pass=$skill_lift_pass fail=$skill_lift_fail" if [[ "${AGENT_HARNESS_LIVE:-}" == "1" ]]; then export AGENT_LIVE=1 diff --git a/scripts/mq-style-lint.sh b/scripts/mq-style-lint.sh new file mode 100755 index 0000000..8d141e3 --- /dev/null +++ b/scripts/mq-style-lint.sh @@ -0,0 +1,45 @@ +#!/usr/bin/env bash +# O4 — style gate: flag json.set dict chains and mixed EN/ZH API hints in .mq.md. +# Exit 0 when clean; 1 when findings (unless MQ_STYLE_LINT_SOFT=1). +set -euo pipefail +ROOT="$(cd "$(dirname "$0")/.." && pwd)" +cd "$ROOT" +TARGETS=("$@") +if [[ ${#TARGETS[@]} -eq 0 ]]; then + TARGETS=(ext/ai/sandbox.mq.md ext/ai/policies examples/agent-sandbox-okf) +fi + +fail=0 +findings=0 + +scan_file() { + local f="$1" + [[ -f "$f" ]] || return 0 + # Long json.set pipelines (3+ consecutive) — style bug per marqdo-dev. + if awk ' + /json\.set/ { c++; if (c >= 3) { found=1 } next } + { c=0 } + END { exit found ? 0 : 1 } + ' "$f"; then + echo "STYLE json.set-chain: $f" >&2 + findings=$((findings + 1)) + fail=1 + fi + # Same file imports both EN agent and ZH 智能体 (or web/网页) — mixed surface. + if grep -qE 'import[[:space:]]+agent:|import[[:space:]]+web:' "$f" \ + && grep -qE '导入[[:space:]]+(智能体|网页):' "$f"; then + echo "STYLE mixed-EN/ZH-import: $f" >&2 + findings=$((findings + 1)) + fail=1 + fi +} + +while IFS= read -r -d '' f; do + scan_file "$f" +done < <(find "${TARGETS[@]}" -type f -name '*.mq.md' -print0 2>/dev/null) + +echo "mq-style-lint: findings=$findings" +if [[ "${MQ_STYLE_LINT_SOFT:-}" == "1" ]]; then + exit 0 +fi +exit "$fail" diff --git a/scripts/optimize-standing-policy.sh b/scripts/optimize-standing-policy.sh new file mode 100755 index 0000000..441b19d --- /dev/null +++ b/scripts/optimize-standing-policy.sh @@ -0,0 +1,58 @@ +#!/usr/bin/env bash +# O5 — offline standing / policy rewrite hint (GEPA-like, products stay repo files). +# Does NOT change the runtime agent path. Reads harness failure log + current files, +# writes a suggested patch under .marqdo/optimize/ for human review. +set -euo pipefail +ROOT="$(cd "$(dirname "$0")/.." && pwd)" +cd "$ROOT" +LOG="${1:-}" +STANDING="${2:-ext/ai/agent.mq.md}" +POLICY="${3:-ext/ai/policies/step-route.mq.md}" +OUT_DIR="${OUT_DIR:-.marqdo/optimize}" +mkdir -p "$OUT_DIR" +STAMP="$(date -u +%Y%m%dT%H%M%SZ)" +REPORT="$OUT_DIR/standing-policy-$STAMP.md" + +{ + echo "# Offline standing / policy optimize suggestion" + echo + echo "Generated: $STAMP" + echo + echo "This is a **review artifact**, not an automatic runtime rewrite." + echo "Strong models may rewrite \`standing\` / \`policies/*.mq.md\` offline;" + echo "commit only after harness green." + echo + echo "## Inputs" + echo + echo "- standing source: \`$STANDING\`" + echo "- policy source: \`$POLICY\`" + if [[ -n "$LOG" && -f "$LOG" ]]; then + echo "- harness log: \`$LOG\`" + echo + echo "## Harness failure excerpt" + echo + echo '```' + tail -n 80 "$LOG" || true + echo '```' + else + echo "- harness log: _(none — pass path as \$1)_" + fi + echo + echo "## Current policy table (copy)" + echo + if [[ -f "$POLICY" ]]; then + echo '```markdown' + cat "$POLICY" + echo '```' + else + echo "_missing $POLICY_" + fi + echo + echo "## Suggested next edits" + echo + echo "1. Keep step-class → backend as a **GFM table** (no json glue)." + echo "2. Quarantine failing skills (\`status: quarantine\`) before promoting again." + echo "3. Re-run \`scripts/agent-harness.sh\` and confirm Skill Lift summary." +} > "$REPORT" + +echo "wrote $REPORT" diff --git a/skills/marqdo/SKILL.md b/skills/marqdo/SKILL.md index 46bb69e..123c953 100644 --- a/skills/marqdo/SKILL.md +++ b/skills/marqdo/SKILL.md @@ -32,7 +32,9 @@ Canonical design (repo): `doc/design/markdown-mapping.md`, `doc/design/keywords. 8. Prefer ending side-effect-only function bodies with `*None*` / `*无*` / whole-line `**` / `****` when later lines must belong to an outer function. Lone `---` / `***` are Markdown thematic breaks (skipped), not function end. 9. **`ext/**` never calls `host_*`.** Agent/OKF helpers are plugin names (`agent_kb_*`, …) after `plugin.load`. Do **not** add agent/OKF domain code to `src/host/` (core bloat). See `doc/design/ext-agent.md` §4. 10. **Browser (route C/D/E/F):** client logic is Marqdo on WASM; official bridge is host glue and **may** implement lists, routing, storage, WebSocket, canvas, file read, observers — authors **must not hand-write business JS**. Use `web.client_embed` / `data-mq-source-url` auto-mount. Client effects: prefer **GFM tables + `lib/browser`** ([marqdo-dev](../marqdo-dev/SKILL.md)). -11. **Code-as-documentation / no bag glue:** Prefer **GFM tables** for maps, lists, wire, commands. Prefer **`table.put` / named helpers** over `json.set` / `json.append` chains. `lib/json` is for parse/stringify/quote only — not a dict builder. Unreadable json pipelines are a style bug. +11. **Code-as-documentation / no bag glue:** Prefer **GFM tables** for maps, lists, wire, commands. Prefer **`table.put` / named helpers** over `json.set` / `json.append` chains. `lib/json` is for parse/stringify/quote only — not a dict builder. Unreadable json pipelines are a style bug. Read collections with **`[key](map)`**, not footnote indexes for new code. +12. **One language per file:** Do not mix EN and ZH API names in the same `.mq.md` (imports, calls, params). Pick English *or* Chinese mirrors for the whole program. +13. **Sandbox trial habit (Agent / generated `.mq.md`):** Prefer `agent.trial` / `run sandbox=True` / `sandbox.open`→`run`→`diff`→`commit` before promoting to the host tree. Host files must stay unchanged until a successful commit. Caps live in `sandbox.profile` GFM tables — do not invent a second dialect. ## Markup → meaning (v0.2) @@ -162,7 +164,9 @@ Install: `marqdo ext add agent` (ZH: `智能体`). Native: `cargo build --releas APIs: `# agent` / `# 智能体` → `## step` / `## plan`. Context: standing + task + **call site** + tools + budgeted source/skill + act protocol (`CALL:` / `READ:`). -Examples: [agent-pong](../../examples/agent-pong/) · [agent-okf-flywheel](../../examples/agent-okf-flywheel/). Harness: `scripts/agent-harness.sh`. Design: [ext-agent.md](../../doc/design/ext-agent.md) · Wave B: [agent-framework-2026-09.md](../../doc/research/agent-framework-2026-09.md). Dev LLM: copy [.env.example](../../.env.example) → `.env` (gitignored). +Examples: [agent-pong](../../examples/agent-pong/) · [agent-okf-flywheel](../../examples/agent-okf-flywheel/) · [agent-sandbox-okf](../../examples/agent-sandbox-okf/). Harness: `scripts/agent-harness.sh`. Design: [ext-agent.md](../../doc/design/ext-agent.md) · optimize O1–O5: [ext-ai-optimize.md](../../doc/roadmap/ext-ai-optimize.md). Dev LLM: copy [.env.example](../../.env.example) → `.env` (gitignored). + +**Sandbox (O1):** `import sandbox:ext/ai/sandbox.mq.md` · `agent.trial` / `智能体.试跑` · `run`/`step` take `sandbox=` / `沙盒=` (default `False`). Profile caps are tables via `sandbox.profile`. Gold: `tests/ext/agent-sandbox-optin.mq.md`. ## Official extension: `ext/web` (Document / Endpoint / Resource) diff --git a/tests/ext/agent-sandbox-optin.mq.md b/tests/ext/agent-sandbox-optin.mq.md new file mode 100644 index 0000000..a247137 --- /dev/null +++ b/tests/ext/agent-sandbox-optin.mq.md @@ -0,0 +1,49 @@ +--- +title: agent trial sandbox opt-in — host unchanged until commit +description: > + O1: agent.trial write stays upper until commit=True. + Prefer link index over json.get. +import agent:ext/ai/agent.mq.md +import sandbox:ext/ai/sandbox.mq.md +import fs:lib/fs.mq.md +--- + +# main + +Reset leftover workspace from prior runs. + +**had = fs.exists path="_sbx_optin"** +1. `had` + > fs.remove path="_sbx_optin" +2. * + **_ = 0** + +> fs.make_dir path="_sbx_optin" + +Trial with `commit=False`: upper write must not touch the host tree. + +**dry = agent.trial root="_sbx_optin" write_path="proof.txt" text=optin-ok commit=False** +**dry_ok = [ok](dry)** +**dry_committed = [committed](dry)** +> print text=`dry_ok` +> print text=`dry_committed` + +**before = fs.exists path="_sbx_optin/proof.txt"** +> print text=`before` + +Trial with `commit=True`: host sees the file after success. + +**wet = agent.trial root="_sbx_optin" write_path="proof.txt" text=optin-ok commit=True** +**wet_ok = [ok](wet)** +**wet_committed = [committed](wet)** +> print text=`wet_ok` +> print text=`wet_committed` + +**after = fs.read_text path="_sbx_optin/proof.txt"** +> print text=`after` + +Profile row is attached (link-index readable). + +**prof = [profile](wet)** +**pname = [name](prof)** +> print text=`pname` diff --git a/tests/ext/agent-sandbox-promote.mq.md b/tests/ext/agent-sandbox-promote.mq.md new file mode 100644 index 0000000..cacdaf9 --- /dev/null +++ b/tests/ext/agent-sandbox-promote.mq.md @@ -0,0 +1,35 @@ +--- +title: promote requires sandbox proof (O2) +description: > + Good workbook promotes; broken workbook is rejected (sandbox_proof_failed). + Link-index reads; no json glue. +import plugin:lib/plugin.mq.md +import fs:lib/fs.mq.md +import sys:lib/sys.mq.md +--- + +# main + +**p = plugin.native_path name="agent"** +1. `p` + > plugin.load path=`p` +2. * + > print text=no-plugin + > sys.exit code=1 + +**kb = "_sbx_promote_kb"** +**had = fs.exists path=`kb`** +1. `had` + > fs.remove path=`kb` +2. * + **_ = 0** + +**prom = agent_kb_promote kb_dir=`kb` goal="sandbox promote good" workbook="sandbox-fixtures/promote-good.mq.md"** +**ok = [promoted](prom)** +> print text=`ok` + +**rej = agent_kb_promote kb_dir=`kb` goal="sandbox promote bad" workbook="sandbox-fixtures/promote-bad.mq.md"** +**rej_ok = [promoted](rej)** +**reason = [reason](rej)** +> print text=`rej_ok` +> print text=`reason` diff --git a/tests/ext/agent-sandbox-quarantine.mq.md b/tests/ext/agent-sandbox-quarantine.mq.md new file mode 100644 index 0000000..f5798bb --- /dev/null +++ b/tests/ext/agent-sandbox-quarantine.mq.md @@ -0,0 +1,34 @@ +--- +title: O5 quarantine skill status +description: Promote good skill then quarantine — status becomes quarantine. +import plugin:lib/plugin.mq.md +import fs:lib/fs.mq.md +import sys:lib/sys.mq.md +--- + +# main + +**p = plugin.native_path name="agent"** +1. `p` + > plugin.load path=`p` +2. * + > print text=no-plugin + > sys.exit code=1 + +**kb = "_sbx_quar_kb"** +**had = fs.exists path=`kb`** +1. `had` + > fs.remove path=`kb` +2. * + **_ = 0** + +**prom = agent_kb_promote kb_dir=`kb` goal="quarantine demo" workbook="sandbox-fixtures/promote-good.mq.md"** +**ok = [promoted](prom)** +**slug = [slug](prom)** +> print text=`ok` + +**q = agent_kb_quarantine kb_dir=`kb` slug=`slug` reason="fixture_regression"** +**qok = [ok](q)** +**st = [status](q)** +> print text=`qok` +> print text=`st` diff --git a/tests/ext/agent-step-route.mq.md b/tests/ext/agent-step-route.mq.md new file mode 100644 index 0000000..6981db8 --- /dev/null +++ b/tests/ext/agent-step-route.mq.md @@ -0,0 +1,19 @@ +--- +title: O3 step_route table backends +description: lookup → marqdo; net → llm; default → auto. +import agent:ext/ai/agent.mq.md +--- + +# main + +**a = agent.step_route kind="lookup"** +**ba = [backend](a)** +> print text=`ba` + +**b = agent.step_route kind="net"** +**bb = [backend](b)** +> print text=`bb` + +**c = agent.step_route kind="default"** +**bc = [backend](c)** +> print text=`bc` diff --git a/tests/ext/sandbox-fixtures/promote-bad.mq.md b/tests/ext/sandbox-fixtures/promote-bad.mq.md new file mode 100644 index 0000000..772a4df --- /dev/null +++ b/tests/ext/sandbox-fixtures/promote-bad.mq.md @@ -0,0 +1,8 @@ +--- +title: promote-bad +proof: promote-bad.mq.md +--- + +# main + +> this_is_not_a_real_builtin_xyz diff --git a/tests/ext/sandbox-fixtures/promote-good.mq.md b/tests/ext/sandbox-fixtures/promote-good.mq.md new file mode 100644 index 0000000..885bb9e --- /dev/null +++ b/tests/ext/sandbox-fixtures/promote-good.mq.md @@ -0,0 +1,12 @@ +--- +title: promote-ok +type: skill +applies_when: demo +fixtures: promote-good.mq.md +sandbox_profile: default +proof: promote-good.mq.md +--- + +# main + +> print text=proof-ok diff --git a/tests/gold.rs b/tests/gold.rs index 0ceca41..db8dd45 100644 --- a/tests/gold.rs +++ b/tests/gold.rs @@ -2986,6 +2986,54 @@ inspect-ok", ); } +#[test] +fn ext_ai_agent_sandbox_optin() { + ensure_agent_plugin_built(); + assert_out( + "tests/ext/agent-sandbox-optin.mq.md", + "True +False +False +True +True +optin-ok +default", + ); +} + +#[test] +fn ext_ai_agent_sandbox_promote() { + ensure_agent_plugin_built(); + assert_out( + "tests/ext/agent-sandbox-promote.mq.md", + "True +False +sandbox_proof_failed", + ); +} + +#[test] +fn ext_ai_agent_step_route() { + ensure_agent_plugin_built(); + assert_out( + "tests/ext/agent-step-route.mq.md", + "marqdo +llm +auto", + ); +} + +#[test] +fn ext_ai_agent_sandbox_quarantine() { + ensure_agent_plugin_built(); + assert_out( + "tests/ext/agent-sandbox-quarantine.mq.md", + "True +True +quarantine", + ); +} + #[test] fn ext_llm_named_offline() { let root = std::path::PathBuf::from(env!("CARGO_MANIFEST_DIR"));