Commit Graph
142 Commits
Author SHA1 Message Date
cflmy 0f2c12b636 feat(notebook): link statement debugger from view
Expose /debug and /api/debug/* on the live view server; add a notebook Debug button so Marqdo statement stepping is reachable from the same page/session as cell stepping.
2026-10-18 01:44:05 +08:00
cflmy 3001ed7ba5 feat(notebook): document session with shared kernels and view controls
D1/D2: 内核表/会话表 parsing, DocumentSession cell index, named/default kernels, shared state + isolation, run_cell/step/run_all/restart/assign, state bridge, journal, POST /api/session/*, and a live-view notebook bar with status badges, per-cell kernel selector, step/run-all and push/pull state form.
2026-10-18 01:39:36 +08:00
cflmy c21a28c3bc docs(foreign): design kernel runtime and document session
Record the Jupyter-beyond discussion, decisions, and the document-native notebook syntax (内核表/会话表). Split the design into F (foreign kernel runtime) and D (document session) layers, with roadmaps, state bridge, stepping, journal, and security rules.
2026-10-18 00:43:31 +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 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 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
cflmyandCursor 4a2d89406b fix(agent): preserve llm_free resources under plan force
Stop plan from clobbering an existing resources workbook with an explore
skeleton. Add llm.prompt helpers and agent-plan-preserve gold.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 19:34:05 +08:00
cflmyandCursor d8d435fead feat(ai-stack): metrics, named handles, prompt docs, backends, zero-LLM
Finish ai-stack steps 1–5: model_turn usage, fast/reasoning, type:prompt
load, openai/ollama split, and agent-zero-llm gold. Fix compiled-skill
Marqdo syntax so llm_free await no longer falls through to plan+HTTP.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 19:30:25 +08:00
cflmyandCursor 1f8e61f3bf feat(llm): semantic ask/stream/collect surface (005)
Lift ext/ai/llm from OpenAI HTTP client to an intelligence primitive;
keep complete as compat. Add unified ai-stack roadmap linking agent + llm.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 13:35:38 +08:00
cflmyandCursor a9ee858f53 feat(agent): Skill Compilation + Adaptive Routing (v2/P4)
Episode → maybe_learn → llm_free skills, plus abstract router backends
(marqdo/small-llm/jev?/llm/auto) via plugins/agent; no core host changes.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-24 13:28:50 +08:00
cflmyandCursor 5fffb800f9 P4(b) 收口:mimo-v2.6-pro 两跑均端点 infra 不可评估,判据以 deepseek-flash 为准
- perf-validation-report §3 记录重跑终局(12/12→11/12 infra),(b) 判据判定不改
- three-problems-plan Phase 4 落地记录同步

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-23 13:10:28 +08:00
cflmyandCursor 1a729eb9ec P4 验证执行:(a)锚点消融✅/(c)契约消融✅/(d)防漂移✅/(e)守卫演练✅;(b)盲测 deepseek-flash 完成未达标、mimo-v2.6-pro 重跑中
- perf-validation.md:五实验协议/判据/材料(2026-09-23 自设计)
- perf-validation-report-2026-09-23.md:汇总报告(判据逐项对照 + 诚实结论)
- tests/blind_experiment.rs + tests/blind/:盲测 harness(查询通道/修复回路/usage 计量)+ 冻结材料(6 任务书 + docs-bundle)
- tests/contract_ablation.rs:四边界×三情形消融(拦截 100%/误报 0%/零回归)
- tests/drift_drill.rs:9 漂移必报 + 2 负对照
- src/mlsp.rs:syntax 卡片自持化(semantics/rule/sample/doc_quote)
- three-problems.md §5.1 判据矩阵逐行判定(问题 1✅ 2✅ 3❌);three-problems-plan.md Phase 4 落地记录
- 全量干净回归零失败

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-23 05:06:30 +08:00
cflmyandCursor 00c763300e test(repair): mimo-v2.6-flash cross-check + measurement-side hardening
mimo-v2.6-flash 终测:anchor 臂一轮 20/20=100%、plain 90%(最终 95%);
三轮双臂一轮修复率全部 >=85%(目标 >=80%),护栏 0 越界。

'测试不稳定'定性为三类测量端问题并全部加固(与 Marqdo 语义无关):
- 网关空体抖动 -> curl --retry + 5s 退避(加固后 0 次失败)
- 推理模型 reasoning_content 吃光 token 预算 -> max_tokens 2000->8000
- 模型输出格式畸形 -> parse_edits 容错(数组/单对象/NDJSON 多对象流/
  字符串化元素/字符串型行号/围栏/数字后多余引号的确定性修补 unquote_line_nums)

报告按模型分文件(repair-experiment-<date>-<model>.md),cflmy/mimo 双报告并存;
计划记录更新为三轮对照表。干净环境 cargo test 444/444 全绿(零回归);
ext_llm_*/ext_agent_*_live 为环境开关型实况测试,与本期无关。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-23 01:27:01 +08:00
cflmyandCursor 224b3d4a66 test(repair): §5.2(a) 模型在环修复实验 —— 锚点消融:anchor 100%(20/20) vs plain 85%,≥80% 目标达成
- tests/repair_experiment.rs:真实消费 validate → repair_targets → 模型行编辑 → repair_apply(越界必拒)
  → 复验 的完整闭环(≤2 轮;容错重试;cflmy @ llm.cflmy.cn,.env 读取,#[ignore] 不进常规回归)
- 双臂消融:anchor(诊断带 doc_anchor/doc_quote/suggestion)vs plain(剥掉)——
  anchor 一轮修复 20/20=100%;plain 17/20=85%(3 例失败均为网络空体抖动)
- tests/common/mod.rs:golden 20 例与诊断/应用共享件抽出(repair_loop + experiment 同源)
- parse_edits 容错(数组/单对象/字符串化元素/围栏);越界必拒/abstain 由 repair_loop 硬断言覆盖
- 报告:doc/roadmap/repair-experiment-2026-09-22.md;.gitignore 补 .env(密钥不入库)

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-22 21:10:03 +08:00
cflmyandCursor 81d26a265a docs(roadmap): 落地记录 —— T3.4 修复回路工程项完成(护栏 + golden 20 例);T3.3 编号归位
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-22 20:14:32 +08:00
cflmyandCursor 18d89d6cf2 docs(roadmap): 落地记录更新 —— T3.4 完成;T3.3 golden 实验待做
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-22 19:47:19 +08:00
cflmyandCursor db5f0e830b feat(mlsp): Phase 3 MLSP for AI —— locate/syntax/validate/repair_targets/schema(T3.1/T3.2 + T2.6)
- src/mlsp.rs: 行分隔 JSON 协议 + 五 handler;语法唯一事实来源 = CORE_CONSTRUCTS(只加检索别名)
- repair_targets 带有界护栏策略(anchored-local / 越界必拒 abstain / max_attempts=2)
- schema 契约导出(T2.6):形参/返回/字段契约 + 升参清单 + 锚点
- marqdo mlsp 子命令:stdio 行分隔 JSON 服务
- tests/mlsp.rs 7 例全绿;全量回归零失败(含 262 gold)

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-22 19:44:35 +08:00
cflmyandCursor 7a449c40b1 feat(contract): Phase 2 渐进式契约层 —— 契约表提取 + 四边界校验 + marqdo check 防漂移(T2.1–T2.5)
- src/contract.rs: 类型词汇(渐进标注)、参数/返回/字段三形状契约表解析、合并、四边界校验诊断
- src/parse/mod.rs: extract_function_contract —— 位置+形状双重判定,在升参推断之前提取;
  绑定表/普通文档表绝不吃(P1 零回归),契约表从 body 移除(元数据永不执行)
- src/interp.rs: 四边界校验 —— 调用实参(3 条调用路径)/返回/表绑定/字段访问
- src/check.rs + marqdo check [--json]: 漂移双向互查、未知类型名(附建议)、错位契约
- src/load.rs: label_error 保留结构化诊断(错误出口唯一,不拍平成字符串)
- T2.4: 全部契约诊断带 doc_anchor/doc_quote/contract_ref
- tests/contracts.rs 12 例全绿;全量回归零失败(含 262 gold)

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-22 19:40:08 +08:00
cflmyandCursor a49592a3ba docs: 三大问题设计移出 doc/next/ → roadmap/three-problems.md;新增落地计划 three-problems-plan.md
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-22 17:46:09 +08:00
cflmyandCursor b5f43ee993 release: v1.0.0 — markup v0.3 as the 1.0 language surface
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 16:05:29 +08:00
cflmyandCursor 76da97f090 ci(release): require Linux native+CLI zips; document proxy.cflmy.top
Pages was failing on leading-backtick narrative (already fixed on main).
Linux job now waits for the Windows release, then uploads .so plugins and a
Linux CLI bundle. Release skill treats those assets as mandatory.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 16:03:02 +08:00
cflmyandCursor 6994acb91d fix(prose): mid-line italic emphasis is not a return
Skip *very important* / *foo.bar* / *code-as-docs* so narrative emphasis cannot end a function; keep whole-line *n* and 返回*n*.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 15:25:26 +08:00
cflmyandCursor bccfec86ba feat(parse): bold infix expressions are ExprStmt, not calls
`` **n + 1** `` evaluates and discards (design §6.2); keep assign-first and
bare-call fallback. Explicit `` **> …** `` uses standalone bare=text rules.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 15:12:00 +08:00
cflmyandCursor c8f41164c5 fix(parse): keep GAP recovery for unclosed bold
Hard-erroring code-shaped `` **… `` broke tests/structure/gap-star-json-body.mq.md; unclosed bold stays Comment so later statements still run.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 14:41:51 +08:00
cflmyandCursor 6f303ff957 fix(parse): diagnose unclosed code-shaped bold
Treat `` **x = 1 `` as Code and error with a clear unclosed-`**` diagnostic instead of silently skipping it as a comment.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 14:39:58 +08:00
cflmyandCursor 4f09e515ee feat(view): mark prose-inferred params in Structure
Show inferred function parameters with a dashed chip and outline annotation so view surfaces v0.3 param elevation without changing the redundant call surfaces.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 14:04:45 +08:00
cflmyandCursor 551f4ff322 feat(view): preserve bracket-marked calls without modifiers
Track CallExpr.bracket_marked from `[callee]` parse so Structure display keeps `[fn] …` instead of falling back to `> fn …` when there are no pre-modifiers.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 13:39:12 +08:00
cflmyandCursor d5a9301c7f docs(public): finish stdlib bracket-call demos and fix import returns
Prefer [lib.fn] in remaining public/stdlib samples, correct italic returns in structure import modules, and keep lib/系统 narration from starting with backticks.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 13:32:17 +08:00
cflmyandCursor 34915e3b16 docs: align remaining tutorial chapters with markup v0.3
Teach bold-as-code, italic-as-return, link-index, and bracket-marked calls across chapters 1–8/10–14 and Skill reference so teaching matches the runtime.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 13:18:28 +08:00
cflmyandCursor c55aad775e docs: teach link-index and v0.3 markers in tutorial and Skill
Rewrite chapter 9 and Skill examples around [key](coll), bracket-marked
calls, and ** code / * return; keep footnote get as a transitional note.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 13:08:53 +08:00
cflmyandCursor ac3f0633cd refactor(tests): prefer link-index in structure collection golds
Move collection-* structure fixtures to [key](base), and modernize
public/stdlib table/fs/time demos with bracket-marked library calls.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 13:03:03 +08:00
cflmyandCursor abcb141737 refactor: prefer link-index get across examples and tests
Migrate remaining footnote-style collection access in examples,
public/structure, and ext/lib smokes to [key](base); teach link-index in
structure pages and use bracket calls in the cafe journal example.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 12:54:38 +08:00
cflmyandCursor 8d97adc1dc docs(ext): narrate quantum/linalg and link-index public features
Add module intros and missing purpose lines for EN/ZH quantum and linalg
extensions; migrate remaining public/features footnote gets to [key](base).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 12:45:57 +08:00
cflmyandCursor 5c37d54070 refactor(ext): prefer link-index get in web and ai modules
Migrate footnote-style collection access to [key](base) (including nested
chains) in ext/web and ext/ai EN/ZH sources.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 11:55:09 +08:00
cflmyandCursor fecaacd5be docs(lib): narrate remaining stdlib modules (M2)
Add module intros and per-function purpose lines across EN/ZH libs, with
callable examples on the smaller modules; keep + params and host bodies intact.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 11:47:35 +08:00
cflmyandCursor 53bc3538da docs(lib): narrate table/text/json as code-as-docs pilot
Add purpose lines and bracket-call examples in EN/ZH libs and public/stdlib
demos; keep explicit + params so function-body prose cannot be mistaken for
link-index or bold code.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 11:38:24 +08:00
cflmyandCursor 0e0655b316 feat(markup): bracket-marked calls with pre_modifiers
Stabilize `mod… [callee] args` (modifiers → name=True) alongside link-index
disambiguation; expand in interp/bytecode, show in view, and document lib/view
code-as-docs waves before stdlib rewrite.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 11:33:11 +08:00
cflmyandCursor 4a1c9c48a2 feat(markup): prefer [key](collection) for map and list access
Add GFM link-shaped index as the primary get surface, keep footnote
index as transitional compatibility, and align the coffee example.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 10:44:18 +08:00
cflmyandCursor 5e74ff39f2 feat(markup): code-as-docs narration surface (G1–G4) and drop --- body end
Treat --- as Markdown HR everywhere, end side-effect helpers with empty returns,
and accept soft emphasis, float literals, and dynamic footnote keys so LLM-friendly
.mq.md stays runnable. Ship the weekend coffee example plus gold fixtures.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-14 10:16:48 +08:00
cflmyandCursor b5c07385e9 feat(markup): finish v0.3 stock migration and green gold
Migrate remaining .mq.md (tests/ext/public/examples), stop elevating local assigns to params, inject form_target in Go libweb, and skip live LLM gold without a real key.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-13 23:43:44 +08:00
cflmyandCursor bfb10d172b feat(markup): adopt v0.3 as sole mapping (** code, * return)
Make prose-unified Markup the only runtime: bold segments are executable,
italic is return, params can be inferred from body/prose, with no v0.2 dual
mode. Migrate lib and structure/keywords golds; gate on tests/markup-v03.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-13 20:38:53 +08:00
cflmyandCursor 784d5ec346 feat(stdlib): Mid2 M10 stats and log fields
Add thin mean/median/stdev and optional structured fields on log
lines; close Mid2 M7–M10 (zip skipped).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-09 09:42:13 +08:00
cflmyandCursor 955834e453 feat(stdlib): Mid2 M9 fs make_dirs, walk, and stat
Thicken lib/fs with recursive mkdir/rmdir-tree, metadata maps, and
depth-first walk; add gold tests and public demos.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-09 09:27:06 +08:00
cflmyandCursor 435f36b6e9 feat(stdlib): Mid2 M8 toml, html escape, and base32
Add read-only TOML subset parse, HTML escape/unescape, and RFC 4648
base32 on encoding; gold tests and public demos included.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-09 09:22:00 +08:00
cflmyandCursor 08c48f3acb feat(stdlib): Mid2 M7 datetime and url
Add calendar moments as {unix,zone,iso} maps and URL/query parse
helpers in lib/ with thin host_* forwards; gold and public demos.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-09 09:14:18 +08:00
cflmyandCursor ff1870cedc docs: Mid2 gap research and M7–M10 design/roadmap
Inventory stdlib gaps after Mid M1–M6 and lock Mid2 waves
(datetime/url, toml/html, fs++, optional stats).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-09 09:04:29 +08:00