Commit Graph
160 Commits
Author SHA1 Message Date
cflmyandCursor e833dc05e2 feat(agent): attach effect ledger watermark on CheckpointV2 save
Persist effects_watermark with resume checkpoints and pass resume_id into
step tool calls so mutating tools share a stable logical_run scope.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-27 13:48:45 +08:00
cflmyandCursor 11bb7ef277 feat(agent): wire EffectLedger through mutating run_tool
Prepare/start/commit write and execute tools with idempotent dedupe, and refuse
blind retry while ledger state is unknown or interrupted mid-flight (MA-T03).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-27 13:44:45 +08:00
cflmyandCursor 6bd90bb2d0 feat(agent): ship output channels, ContextPackV2, and effect ledger
Open AgentOutputV1/ContextPackV2 capability bits and add EffectLedgerRecordV1
so CheckpointV2 write auto-resume only unlocks on a safe watermark.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-27 13:28:03 +08:00
cflmyandCursor 4683f2e067 feat(agent): ToolSpec registry with authorize-before-call
Add ToolSpecV1 register/search/describe/prepare so CALL and native paths share one schema gate; unauthorized and invalid-arg prepares fail with zero executions.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-27 13:18:55 +08:00
cflmyandCursor 5912164039 feat(agent): CheckpointV2 atomic resume and AgentErrorV1
Replace bare resume writes with temp/fsync/rename, mark legacy loads as manual_review, and expose bounded read-only retry decisions while keeping write auto-resume closed without a ledger.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-27 11:03:39 +08:00
cflmyandCursor 3cabe53da2 release: v2.1.4 isolated HTTP execute (ADR 0009)
Default execute/sse-live/stream to Supervisor worker pool; MR-01 gold;
/_runtime/*; bump CLI/wasm/ext to 2.1.4.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-26 18:33:33 +08:00
cflmyandCursor 1b11fe063a fix(web): fail-fast when invoke lock is busy; document single-interp limit
Long sse-live chats held INVOKE_LOCK indefinitely and starved short routes
(UI freeze). Timed try-lock returns interpreter busy → HTTP 503; ADR 0008
records that HTTP is multi-goroutine while Marqdo evaluation stays single-flight.
Also lands plan/delta streaming and soft map guards used by qdagent chat.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-26 13:27:53 +08:00
cflmyandCursor 9ea5bebfc3 chore(release): bump to 2.1.3 (workbench M00–M06)
Ship ModelSelection/RunContext/DocumentView contracts, LLM selection,
view document CLI, and live/F02 evidence. CLI, wasm, and ext pack aligned.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-25 23:13:27 +08:00
cflmyandCursor c7c329341b feat(workbench): live selection smoke, F02 agent e2e, DocumentView CLI
Hoist llm.ask prompt binding to avoid elevated `p`; prefer reasoning_content
when content is empty; point live/tests at in-tree MARQDO_EXT; add USTC live
gates and mock agent.step selection+resume evidence; view document --out for
read-only browser embed checks. Design stays Partial (not Verified).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-25 23:05:28 +08:00
cflmyandCursor 03396afd02 feat(workbench): land M00–M06 runtime contracts and read-only view
Add capabilities/selection/usage/DocumentView/locator/RunContext with
honest probes, LLM messages+cancel, sse-live cancel bridge, and CI
workbench_contracts gate; record design evidence for verified slices.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-25 10:55:08 +08:00
cflmyandCursor dc853fb580 release: bump to 2.1.2 (EK production chain + View V0–V3 bar)
Ship evidence/closure invalidation, verify/adjudicate, reuse_execute and
agent bind/publish gates, document.extract, KnowledgePresentation + SSE
page_token, and upload max_bytes with the 45-test offline gate.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-24 22:52:03 +08:00
cflmyandCursor b8a4ddd38f release: bump to 2.1.1 (executable-knowledge spine)
Ship BoundCall/NarrativeRef/generation CURRENT notes with Cargo, ext pack, README, debian, and release Highlights.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-23 23:40:35 +08:00
cflmy ae97891266 release: v2.1.0 — file-scoped occlusion 2026-10-23 12:59:28 +00:00
cflmy aea86746e7 feat: migrate corpus to file-scoped occlusion 2026-10-23 12:45:01 +00:00
cflmyandCursor 687c168014 feat(parse): use nested YAML import: maps instead of one-liner binds
Frontmatter imports are now valid YAML (`import:` / `导入:` with bind→target
entries), removing spaced keys. Add `marqdo migrate imports`, hard-error the
old one-liner form, and migrate lib/ext/examples/tests/docs accordingly.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-23 19:33:58 +08:00
cflmy 1a13989230 fix(ext/ai): 变量引用补反引号;prompt 缺失回退空串
- llm/agent 模板中的变量引用统一加反引号
- ask/stream 在 prompt/path 均缺失时回退空串,避免直接退出
- 修正 stream 分支返回缩进;agent workbook 模板改用 ** 代码块
2026-10-23 14:52:26 +08:00
cflmy bf76e069ee release: v2.0.0 — 遮蔽语法落地([描述](实现) / 标签欠据 / 全仓迁移)
Bump CLI, wasm and plugin SDK to 2.0.0; sync ext/VERSION, Cargo.lock,
CHANGELOG (Highlights + 核心表面 Δ), README, release highlights stub,
skills and debian/changelog.
2026-10-22 16:26:29 +08:00
cflmy 4488a3cb70 feat(migrate): M7 迁移与版本门 — per-file markup + migrate labels + 全仓迁移
原计划的"翻转默认 + 旧形硬报错"不可行:`[键](集合)` 与 `[描述](实现)` 外形相同,
翻转会让 506 处取元静默变义,硬报错又拿不到证据。改为**按文件声明**。

一、per-file markup
- frontmatter `markup: occlusion`(或 `标记: 遮蔽`)决定该文件模式
- load.rs 先取模式,用 parse::expr::with_markup(线程局部压栈)包住解析
- 同一进程可同时加载两种模式的文件(imports);MARQDO_MARKUP 仍作进程默认
- 好处:迁移逐文件、可增量、可回滚,不存在半迁移的静默错义

二、`marqdo migrate labels [--write|--json]`
改写规则:
  [键](集合)      → [键](access(集合, "键"))
  [`名`](集合)    → [名](access(集合, `名`))
  - [项](集合)    → - [项](遍历 集合 为 项)

安全模型:改写 → 重解析 → 证明等价 → 才写
- 原文件按 classic 解析得 AST-A;改写后按 occlusion 解析得 AST-B
- 反归一化 B(标签与键同名且 payload 为 access 的遮蔽还原成 Index)
- Debug(A) == Debug(反归一化(B))(抹掉行号)才写入,否则原文件一字不动

只改代码行(LineKind::Code);表格行只改 **…** 单元格,散文 markdown 链接不碰;
链式索引由内向外改写,已迁移的有守卫不二次改。

三、access 提升为宿主函数 HostFn::Access(u16 id 212)
与旧取元逐字一致(Map 按键 / List 1-based / 缺键 missing map key);
进 HostFn 是为了两个后端共用同一实现,interp 里的特例已删除。

四、顺带修的两处真实语义缺陷
1. payload 继承外层"文本模式":`f text=[k](access(c,k))` 中 access 不被当调用
   → `()` 内永远允许 callee(args)
2. 遮蔽形状判定过宽:`[问候] ([格式化] "Bo")` 误判为遮蔽
   → 要求 `]` 后紧跟 `(`,否则落回方括号调用

五、全仓迁移结果
migrate labels: 256 index, 23 loop, 80 file written;0 文件被等价性拒绝;
迁移后 cargo test --release → 604 passed / 0 failed;再跑迁移幂等。

等价性检查先后抓出 4 类改写 bug(表格散文链接、payload 文本模式、链式索引、
遮蔽与方括号调用混淆),每类都是先拦下再修工具,未污染文件。

测试:6 个单测 + 3 个集成(干跑不写盘 / 写入后运行输出不变且幂等 /
等价失败文件不动);全量 604 passed / 0 failed(M3 后 595 + 9);双后端一致。

文档:doc/design/change-m7-migration.md
2026-10-22 15:33:31 +08:00
cflmy 1c90312c02 feat(ai): M10 把「接不了就申报」写进 agent 提示词(standing + how-to-act)
两处:
1) how-to-act 协议段(每轮都带):无法真正接通的capability 不许静默伪造、不许声称完成,
   改写成带状态的遮蔽,例如 [按关键词检索,接口未接,待开发](None);
   桩必须能跑并写清返回值(None 亦可);收尾用 labels.search 自查。
2) 默认 standing(p):追加一句"接不了就在描述里申报(待开发/模拟),别假装成功"。

为什么两处:standing 定基调(每轮开头),how-to-act 定动作(每轮),
只写一处会被长上下文冲淡或缺动机。
设计要点:给范式而非规则(可直接抄)、给返回值要求(对应 label.empty_payload)、
给自查动作(labels.search)、用英文与既有协议一致。

验证:marqdo check ext/ai/agent.mq.md(occlusion 模式)通过;
grep 确认两处文本落地;全量回归 587 passed / 0 failed(不改逻辑)。

文档:doc/design/change-m10-engineering-habits.md
2026-10-22 15:17:43 +08:00
cflmy 33a14d272c release: v1.5.2 — foreign v3 P0/P1 (stdin, plan API, snapshot, capture, persist) 2026-10-18 14:57:15 +08:00
cflmy dff0b700ae release: v1.5.1 — view static/live unified + foreign value passing 2026-10-18 14:05:19 +08:00
cflmy f666eaaf40 release: v1.5.0
Foreign v2 + document-native notebooks, view contrast/themes/resize, public OKF/EKC and Python examples. Bump CLI/wasm/ext to 1.5.0; no core surface delta.
2026-10-18 03:17:53 +08:00
cflmyandCursor bfd468d5e3 release: Marqdo 1.4.5
Streamable HTTP MCP, web invoke Bearer/401, openai/agent json.get hardening.
Bump CLI/Ext/wasm and debian changelog.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-16 17:36:07 +08:00
cflmyandCursor 8353ba38fe Add Streamable HTTP MCP and harden web /v1 invoke auth.
agent_mcp_serve gains http transport; invoke injects Bearer/X-Api-Key and maps
unauthorized to 401; openai/agent field access prefers json.get over footnotes.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-16 17:33:24 +08:00
cflmyandCursor b43a08b2e2 release: Marqdo 1.4.4
Soft LLM transport errors and table-first ext/ai; CLI + Ext + wasm SemVer bump.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-16 14:38:16 +08:00
cflmyandCursor 1908bf1a53 fix(ai): soft LLM transport errors and strip ext/ai json glue
Host/plugin HTTP failures return structured finish|status=error instead of
aborting the VM; agent/llm/openai/智能体 result maps use GFM tables and
table.put. SKILL gains positive copy-paste examples so agents stop mirroring
legacy json.set chains.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-16 14:27:45 +08:00
cflmyandCursor c44ea38ae2 release: Ext pack 1.4.3 — agent.run cold EFI / resolve llm_free
Bump ext/VERSION only (CLI stays 1.4.2). Ships agent facade + native miss-field fix for qdagent cold OKF.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-16 12:56:40 +08:00
cflmyandCursor d489f7c088 fix(ext/ai): cold agent.run EFI — self.preflight and resolve llm_free
Miss resolve omitted llm_free and run called bare preflight, which crashed
qdagent on empty OKF. Align miss fields, use self.preflight + json.get, add
regression gold and research note.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-16 12:54:00 +08:00
cflmyandCursor d5f826a8c8 release: Marqdo 1.4.2
Bump CLI/wasm/ext to 1.4.2 for Agent/LLM optimize O1–O5 (sandbox trial,
promote proof, step_route/EFI, lint, quarantine).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-16 11:51:41 +08:00
cflmyandCursor 0f72173d08 feat(ext/ai): land Agent/LLM optimize waves O1–O5
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 <cursoragent@cursor.com>
2026-10-16 11:47:28 +08:00
cflmyandCursor 63bcb882a6 feat(ext/ai): add CoW sandbox for Marqdo-only agent trials
Give agents a capability-capped run path that stages workspace edits until commit, so generated .mq.md can be verified without polluting the real tree.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-16 11:11:54 +08:00
cflmyandCursor 1bb16dd6db release: Marqdo 1.4.1
View annot leaders mid-to-mid SVG, frame chip id unify; bump CLI/wasm/ext.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-15 20:37:24 +08:00
cflmyandCursor 66926e9e0a release: Marqdo 1.4.0
Prose-unified control flow, formula meta bind, image writeback, view
inferred params; sync CLI/wasm/ext/VERSION and install docs.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-15 15:54:45 +08:00
cflmyandCursor dcf4c05663 fix(ext/net): wrap url.encode via lib/net, not host_*
Gold rule bans host_* from ext/**; encode must go through stdlib.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-15 15:47:07 +08:00
cflmyandCursor 0a8f76d9b4 release: v1.3.3 — view document-surface Structure
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-15 13:18:51 +08:00
cflmy f6374d1593 release: ext pack v1.3.2 trailing slash route fix 2026-10-13 15:37:42 +08:00
cflmyandCursor 3ae8f2c843 release: ext pack v1.3.1 OIDC path redirect_uri
Bump ext/VERSION only; CLI remains 1.3.0.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-08 11:42:08 +08:00
cflmyandCursor e9c1a8a730 feat(web): resolve OIDC redirect_uri from request Host
Allow path-style redirect_uri (/oidc/callback) so apex/www and
proxied HTTPS share one config; persist the absolute URI for token exchange.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-08 11:35:12 +08:00
cflmyandCursor fe15603a91 fix(llm): hoist ask result fields out of the return table
Table cells shadowed self/column names (model, usage), so [model](self)
and [total_tokens](usage) raised "footnote index needs list or map" and
blocked live agent.step / qdagent BUILD.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-28 22:08:48 +08:00
cflmyandCursor ed31a2b31d release: v1.3.0 Engineering Knowledge Compiler (EKC)
Bump CLI/ext/wasm to 1.3.0; document L0–L4 catalog, reuse preflight, and
agent eng_* surfaces for AI-native engineering.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-28 16:46:30 +08:00
cflmyandCursor 56ab52356f feat(knowledge): land Engineering Knowledge Compiler (EKC) from 008
Give agents Engineering First Information before codegen: L0–L4 catalog,
reuse/preflight (REUSE→ADAPT→CREATE), graph, and CLI surfaces so large
repos stop reinventing existing capabilities.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-28 16:44:39 +08:00
cflmyandCursor 46a0263d7f release: v1.2.0 Web Artifact (ADR 0007) Document/Endpoint/Resource
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-28 11:39:25 +08:00
cflmyandCursor 67bac1bf02 feat(web): Document/Endpoint/Resource artifact rewrite (ADR 0007)
Replace the monolithic compose_*/configure author surface with file-level
web|endpoint artifacts, split ext/{web,data,security,net}, and lock
no-degrade rules so the model cannot regress to God-object APIs.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-28 11:06:38 +08:00
cflmyandCursor 33f8b94bb0 release: v1.1.1 AI stack (llm/agent/metadata) + ship plugins/llm
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 20:34:08 +08:00
cflmyandCursor 0ed57b6d54 feat(agent): ext APIs, goldens, and docs for MCP/resume/small-llm routing
Wire mcp_connect/list/call, resume_*, and demote Jev in author docs.
Offline goldens cover MCP client, resume, and small-llm/jev-alias route.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 20:26:55 +08:00
cflmyandCursor f1e82ce4e5 feat(llm): optional plugins/llm Transport ABI for chat completions
OpenAI transport prefers llm_chat_completions when the native plugin is
resolvable, and falls back to lib/net HTTP/SSE so CI stays green without the .so.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 20:26:55 +08:00
cflmyandCursor 2d412e3bba feat(llm): LLMResult.tool_calls from OpenAI-shaped responses
Parse choices[0].message.tool_calls into the ask Result; empty list when
absent. Offline gold covers tool_calls_from.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 20:07:59 +08:00
cflmyandCursor 46d78c6e15 feat(core): Phase 2 Metadata scope lift (no body ${})
Inject bound frontmatter keys into the entry env as ordinary variables.
Reject body ${env…}; bytecode entry prologue seeds the same locals.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 20:05:25 +08:00
cflmyandCursor 81a14f9b38 feat(llm): sys.module_source + entry prompt / meta offline paths
Expose entry source via sys.module_source; ask/stream fall back to
prompt_body of the entry document. Add meta-binding and entry-prompt golds.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 19:52:57 +08:00
cflmyandCursor 88dc6d5a54 feat(core): Artifact Metadata Binding (${env|arg|sys|secret})
Load-time resolve of frontmatter bindings into Module.metadata; Secret
masking; sys.meta / --bind; llm ctor prefers meta over env_get.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 19:51:24 +08:00