fuli-context 0.7.2 → 0.7.4-beta.1

package/README.md

@@ -14,14 +14,15 @@
   <a href="LICENSE"><img src="https://img.shields.io/npm/l/fuli-context?style=flat" alt="license" /></a>
 </p>
 
-Fuli is a local-first collaboration context graph for AI agents. It turns reusable knowledge,
-experience, decision rationale, and preferences from human–AI project work into assets with
-provenance, scope, authority, and temporal history. Codex, Claude Code, and Cursor can then reuse
-those assets in later tasks instead of relearning the same context.
+Fuli is a local-first collaboration relationship graph for AI agents. Continued human–Agent
+dialogue gradually connects projects, people, decisions, preferences, workflow steps, and evidence.
+Those nodes may point to Fuli-local content, an external knowledge base, or another data source.
+Codex, Claude Code, and Cursor can then reuse the taste, personality, judgment preferences, and
+working methods formed through that collaboration.
 
-Fuli is not a transcript archive, and it is not an attempt to build a personality model that
-replaces human judgment. AI retrieves, summarizes, warns, and executes; humans retain final
-authority.
+Fuli is not a transcript archive or a knowledge base whose goal is to collect more documents, and
+it is not an attempt to build a personality model that replaces human judgment. AI retrieves,
+summarizes, warns, and executes; humans retain final authority.
 
 ## npm packages
 
@@ -69,10 +70,11 @@ preview followed by an explicit, one-time, atomic action.
 ### 4. Assemble context, then retrieve evidence on demand
 
 Fuli does not inject the complete history at session start. The entry step always loads effective
-personal-global preferences and preferences from one exactly matched project. When the current task
-signals that a stable prior fact, method, URL, decision, release, deployment, or authentication
-runbook may matter, the same step also performs a small bounded recall from that project and its
-authorized knowledge sources. The agent uses focused on-demand search when more evidence is needed.
+personal-global preferences, preferences from one exactly matched project, and explicitly
+propagating preferences from authorized parent projects. When the current task signals that a
+stable prior fact, method, URL, decision, release, deployment, or authentication runbook may matter,
+the same step also performs a small bounded recall from that project and its authorized knowledge
+sources. The agent uses focused on-demand search when more evidence is needed.
 Retrieval alone is not usage; a usage event is recorded only when an item materially affects an
 answer, implementation, or decision.
 
@@ -96,12 +98,18 @@ Activity platform (parent: shared runbooks)
 
 When an agent works in the hotel project, it searches hotel-local knowledge first, then follows
 explicit outgoing `PART_OF` or `USES_KNOWLEDGE_FROM` relationships to authorized sources, up to two
-hops. A child item with the same stable key overrides an inherited item. Generic `RELATED_TO`
-relationships do not expand scope, and project-scoped personal preferences are not inherited.
-
-Similar items from multiple children create only a common-knowledge candidate. Current clustering
-is a lexical heuristic, not proof of semantic equivalence. A human must select the canonical item,
-duplicates, parent project, and rationale before an atomic promotion can occur.
+hops. A child item with the same stable key overrides an inherited item. Project-scoped personal
+preferences remain exact by default; only preferences explicitly marked `descendants` or
+`selected_projects` may propagate over the same authorized relationships, with origin project,
+path, and distance preserved. Equally near parent conflicts require human judgment and are never
+resolved by weight. Generic `RELATED_TO` relationships do not expand scope automatically; search
+returns only a one-time read-only expansion suggestion that the Agent must ask the user to approve.
+
+Similar items from multiple children create only a common-knowledge candidate. A shared preference
+across projects without one common parent likewise creates only a personal-global candidate while
+preserving each source text, qualifier, and provenance. Current clustering is a lexical heuristic,
+not proof of semantic equivalence. A human must choose the content, scope, and rationale before it
+can apply.
 
 ### 7. Local first; no personal model in the shared layer
 
@@ -110,6 +118,136 @@ transcripts, credentials, temporary logs, or command output. The team-shared lay
 confirmed project or domain knowledge with context and provenance—not personal taste, personality,
 or judgment preferences.
 
+## Practical use: classification, scope, project resolution, and retrieval
+
+### Decide what to store before deciding where to store it
+
+Content type and effective scope are independent dimensions. The first three rows are personal
+collaboration preferences and carry a `profileAspect`. Project facts have no `profileAspect` and do
+not appear on the Personal preferences page.
+
+| Type | What belongs here | Example |
+| --- | --- | --- |
+| Taste (`taste`) | Outcomes, styles, and quality directions the user explicitly likes or rejects across UI, writing, product, architecture, or engineering work | “Use fewer large gradients and avoid cards nested inside cards.” |
+| Personality (`personality`) | A stable working or collaboration trait explicitly described by the user | “I communicate directly and want the Agent to move work forward proactively.” |
+| Judgment preference (`judgment_preference`) | Decision conditions, priorities, risk posture, and operational boundaries used when making trade-offs | “Discuss directional ambiguity first; never `git push` without explicit authorization.” |
+| Project knowledge | Reusable objective facts, terminology, requirements, routes, APIs, architecture, rationale, and runbooks | “A GitHub Release triggers Fuli's npm publication.” |
+
+Four questions provide a quick classifier: “What outcome do I want?” is taste; “How do I work over
+the long term?” is personality; “How do I decide under a trade-off?” is judgment preference; and
+“How does this system objectively work?” is project knowledge. One-off commands, temporary output,
+unverified guesses, raw chat, and credentials are not retained.
+
+Personality is not a catch-all category for everything learned about a person. Only an explicit,
+stable self-description can be confirmed with a human basis. A personality inferred by an Agent
+from one behavior must remain `pending`; it cannot masquerade as human-confirmed. An empty
+Personality filter on `/preferences` therefore usually means there is no qualifying item in the
+selected scope, not that capture failed. “Keep copy concise” is more likely taste, while “do not
+push without authorization” is more likely a judgment preference. To make the intent explicit,
+say: `This is a long-term collaboration trait; save it as a personal-global personality preference: I communicate directly.` An Agent-inferred candidate can be confirmed, corrected, or invalidated
+by the user from `/preferences` or `/flreview`.
+
+### Personal-global, project-scoped, and shared
+
+| Scope | When to use it | Key write fields | Retrieval rule |
+| --- | --- | --- | --- |
+| Personal-global preference | The behavior should remain the same in unrelated projects | `targetKind: "personal"`; omit `personalProjectId`; set `profileAspect` | Loaded for every task |
+| Project-scoped personal preference | The collaboration behavior belongs to one project or project family | Same fields plus the exact `personalProjectId`; default to `local_only` and never inherited by child projects; explicitly use `descendants` or `selected_projects` when propagation is intended | Exact project wins; propagation follows only the explicit inheritance mode and authorized relationships, and score never resolves a conflict automatically |
+| Project knowledge | A fact belongs to one project or to a designated parent/source project | `targetKind: "personal"`; set `personalProjectId`; omit `profileAspect` | Search the current project first, then authorized `PART_OF` / `USES_KNOWLEDGE_FROM` sources up to two hops |
+| Team-shared knowledge | Human-confirmed project or domain knowledge genuinely needed by a team | `targetKind: "project"` after preview/review | Visible only from explicitly selected or subscribed public projects; personal preferences never enter this layer |
+
+To choose a preference scope, ask: **Should this change the Agent's behavior in a completely
+unrelated project?** If yes, use personal-global. If it applies only to Fuli, use a project-scoped
+preference. If it applies to a project family, keep it project-scoped and explicitly choose whether
+it may propagate to descendants. Do not turn an objective project fact into a personal-global item
+merely because more than one project may reuse it. Put it in an explicit parent or knowledge-source
+project and add a directional authorization relation. When global and project-scoped variants have
+the same stable `attributes.preferenceKey`, human/source confirmation authority is resolved first;
+at equal authority, the exact project variant overrides the global one.
+
+### How Fuli identifies the current project
+
+Fuli matches only stable `project_id` values already registered under Personal projects; it does
+not guess from fuzzy directory similarity. Normally the `project_id` matches the repository
+directory name, so `/workspace/fuli` maps to `fuli`. Standard calls pass only the current working
+directory, and resolution follows this order:
+
+1. Find the nearest Git repository root and match its directory name exactly to a registered
+   `project_id`.
+2. For a Codex worktree, recover the original repository ID from its `.git` pointer.
+3. Match the current directory name exactly to a registered project ID.
+4. At a workspace root, match one registered direct child only when exactly one child contains
+   `.git`, `package.json`, `pyproject.toml`, `Cargo.toml`, or `go.mod`.
+5. Multiple candidates return `ambiguous`; no candidate returns `unmatched`. Neither state applies
+   project preferences or guesses a project.
+
+For an unregistered repository with an unambiguous identity, the installed capture skill may call
+`upsert_personal_project` before the first project-scoped write to create a minimal local private
+project. It never creates or subscribes to a public project automatically. If a workspace has
+multiple candidates, run the Agent from the exact project directory or explicitly register and
+select the project first.
+
+### Which tool the Agent calls and when
+
+Normal use does not require manual MCP calls: submit a task to the Agent from the project directory.
+The Claude Code hook calls `begin_task_context`; Codex and Cursor prompt fallback call the following
+once at the start of each task:
+
+```json
+{
+  "tool": "get_collaboration_preferences",
+  "arguments": {
+    "projectPath": "/workspace/fuli",
+    "taskPrompt": "Fix npm publishing and reuse this project's existing release conventions."
+  }
+}
+```
+
+The important part of a matched response resembles:
+
+```json
+{
+  "context": {
+    "personal_project_id": "fuli",
+    "project_resolution": {
+      "status": "matched",
+      "basis": "repository_root",
+      "personal_project_id": "fuli"
+    }
+  },
+  "effective_preferences": ["personal-global preferences + exact fuli preferences"]
+}
+```
+
+If entry-time `task_knowledge_recall` did not answer a stable project fact, search with one to four
+short queries centered on an action, artifact, target system, or identifier. Do not use the full
+user request verbatim as the only query:
+
+```json
+{
+  "tool": "search_current_project_knowledge",
+  "arguments": {
+    "projectPath": "/workspace/fuli",
+    "queries": ["npm publication runbook", "GitHub Release trigger"],
+    "includePending": false
+  }
+}
+```
+
+At task end, hook mode calls `checkpoint_task_knowledge`: use `capture_candidates` only for a small,
+durable, evidence-backed batch; otherwise use `retain_nothing`. A prompt-fallback Agent applies the
+same rule and writes through `capture_session_knowledge`. Personal preferences set the correct
+`profileAspect` and stable `attributes.preferenceKey`; project facts omit `profileAspect`. If
+automatic capture is disabled under Settings, writes return `capture_disabled` and no category is
+created.
+
+Run these local contract tests to check that the README and project-path behavior still match the
+implementation:
+
+```bash
+npm run test:node -- test/acceptance-docs.test.js test/project-path-context.test.js
+```
+
 ## Agent interaction sequence
 
 This is the simplified lifecycle for a normal task. The Chinese
@@ -321,7 +459,7 @@ system locale. User data such as paths and space names is displayed unchanged.
 | `fuli --help` / `fuli -h` | List every public command and its available options |
 | `fuli --version` / `fuli -v` | Print the installed Fuli CLI version |
 | `fuli setup [options]` | Initialize the Provider, UI, agent integrations, and Skills; safe to rerun |
-| `fuli start [options]` | Start the Provider and UI, optionally opening a browser, rebuilding containers, or enabling LAN access |
+| `fuli start [options]` | Check Agent integrations, then start the Provider and UI; optionally open a browser, rebuild containers, or enable LAN access |
 | `fuli stop [--data-dir DIR]` | Stop services without deleting data |
 | `fuli restart [options]` | Restart local services using the same runtime options as `start` |
 | `fuli status [--json] [--data-dir DIR] [--port PORT]` | Show UI, personal graph, and shared-service status; `--json` emits machine-readable output |
@@ -345,6 +483,9 @@ are used. LAN mode listens on private IPv4 addresses and prints the reachable UR
 `fuli` username, and a temporary access code generated for that start. The default remains
 loopback-only; internal Providers and Neo4j ports are never exposed by `--lan`. LAN mode uses
 HTTP Basic Auth and is intended only for trusted home or office Wi-Fi, not public deployment.
+Before starting, `fuli start` performs a read-only check of detected Agent MCP, Skill, Codex bootstrap,
+and Claude lifecycle integrations. If any are missing or outdated, it still starts the local services
+and tells you to run `fuli setup`; it never applies setup changes implicitly.
 
 `setup` and `update` accept:
 
@@ -383,17 +524,28 @@ reuse the same data.
 ## Agent integrations and primary tools
 
 Fuli installs the `capturing-session-knowledge`, `grilling-project`, and `flreview` Skills for
-supported agents. `/flreview` offers all knowledge, personal preferences, or personal-project
-scope. If the user has no patience, it skips mood, time, and token questions and reviews only a
-small number of highest-priority items.
+supported agents. `/flreview` asks FULI for ranked candidates, then the invoking Agent generates a
+fresh interactive review artifact. FULI remains the durable source of truth and write surface; no
+permanent review tab or one-question-at-a-time chat flow is required.
 Claude Code uses `UserPromptSubmit` and `Stop` hooks for the task lifecycle. Codex's user-level
 `AGENTS.md` and Cursor instructions use prompt fallback. Preference content remains in local Fuli as
 the single source of truth and is not copied into agent configuration.
 
+FULI also exposes read-only `fuli://` resources for each local personal project and for global taste.
+Agents with MCP mention support can select them from the `@` picker; a project resource selects one
+exact project and never expands the search to other projects or `RELATED_TO` projects.
+
+When a task needs a taste or judgment recommendation, `get_user_taste_skill` generates a bounded,
+read-only `user-taste` Skill projection from the effective personal profile and prior task data.
+The projection labels evidence status and scope, returns task-matched recommendations, and is
+regenerated as preferences are added or revised. It never overwrites a user-authored taste Skill;
+the durable graph remains the source of truth.
+
 | Tool | Purpose |
 | --- | --- |
 | `begin_task_context` | Hook entry: resolve the task, run bounded recall when signaled, and create a task token |
 | `get_collaboration_preferences` | Fallback entry: read effective preferences and bounded task recall |
+| `get_user_taste_skill` | Generate the current evidence-labeled taste Skill projection and task recommendations |
 | `search_current_project_knowledge` | Search the child first, then authorized knowledge sources |
 | `search_knowledge_graph` | Run a general query within an explicit bounded scope |
 | `search_connected_knowledge` | Search the graph, project-bound read-only sources, and selected public projects without merging provenance |

package/README.zh-CN.md

@@ -14,12 +14,13 @@
   <a href="LICENSE"><img src="https://img.shields.io/npm/l/fuli-context?style=flat" alt="许可证" /></a>
 </p>
 
-复利是一个面向 AI Agent 的本地优先协作上下文图谱。它把人与 AI 在项目中产生的、经得起
-复用的知识、经验、决策理由和偏好组织成有来源、有作用域、有时间关系的资产，让 Codex、
-Claude Code 和 Cursor 在后续任务中少重复学习一次。
+复利是一个面向 AI Agent 的本地优先协作关系图谱。人与 Agent 的持续对话会逐步形成项目、
+人物、决定、偏好、行为步骤和证据之间的关系；关系节点可以指向 Fuli 本地内容，也可以连接
+外部知识库或其他数据源。Codex、Claude Code 和 Cursor 因而能在后续任务中复用已经形成的
+品味、个性、判断偏好与协作方法。
 
-复利不是聊天记录仓库，也不试图建立一个替代人的“人格模型”。AI 负责检索、提醒、归纳和
-执行；人始终保留最终判断权。
+复利不是聊天记录仓库，也不是以“收集更多文档”为目标的知识库，更不试图建立一个替代人的
+“人格模型”。AI 负责检索、提醒、归纳和执行；人始终保留最终判断权。
 
 ## npm 包
 
@@ -61,9 +62,10 @@ AI 可以发现候选、指出冲突、建议公共化，也可以在得到授
 
 ### 4. 先组装上下文，再按需取证
 
-Fuli 不会在会话开始时把全部历史塞给模型。入口阶段始终加载当前任务实际生效的个人全局偏好
-和精确项目偏好；当任务信号表明可能需要稳定的历史事实、方法、网址、决策、发布、部署或认证
-Runbook 时，同一步骤还会在精确项目及其获授权知识来源中执行一次小规模、有界的自动召回。
+Fuli 不会在会话开始时把全部历史塞给模型。入口阶段始终加载当前任务实际生效的个人全局偏好、
+精确项目偏好和显式允许传播的上级项目偏好；当任务信号表明可能需要稳定的历史事实、方法、
+网址、决策、发布、部署或认证 Runbook 时，同一步骤还会在精确项目及其获授权知识来源中执行
+一次小规模、有界的自动召回。
 需要更多证据时，Agent 再使用聚焦查询按需检索。只有真正影响回答、实现或决策的知识才记录为
 一次使用，单纯检索不会增加权重。
 
@@ -86,10 +88,14 @@ Runbook 时，同一步骤还会在精确项目及其获授权知识来源中执
 
 Agent 在酒店项目工作时先搜索酒店本地知识，再沿显式的 `PART_OF` 或
 `USES_KNOWLEDGE_FROM` 关系向上搜索允许继承的知识，最多两跳。同稳定键的子项目内容覆盖
-父项目内容；普通 `RELATED_TO` 关系不会扩大作用域，项目级个人偏好也不会向下继承。
+父项目内容。项目级个人偏好默认只在精确项目生效；只有显式设置为 `descendants` 或
+`selected_projects` 的偏好才可沿同样的授权关系传播，并返回来源项目、路径和距离。多个同层
+父项目冲突时必须交给人判断，不能靠权重选胜者。普通 `RELATED_TO` 不会自动扩大作用域；
+搜索结果只返回一次性只读扩展建议，由 Agent 先询问用户。
 
-多个子项目中相似的内容只会形成公共化候选。当前聚类是词法启发式信号，不是语义等价证明；
-必须由人选择规范项、重复项、上级项目和理由后，才能原子提升。
+多个子项目中相似的内容只会形成公共化候选。跨无共同父级项目出现的共同偏好也只能形成个人
+全局候选，并完整保留每个项目的原文、限定词和来源。当前聚类是词法启发式信号，不是语义
+等价证明；必须由人选择内容、作用域和理由后，才能生效。
 
 ### 7. 本地优先，公开层不包含个人模型
 
@@ -97,6 +103,121 @@ Agent 在酒店项目工作时先搜索酒店本地知识，再沿显式的 `PAR
 原始命令输出。团队共享层只承载经过确认、具有上下文和来源的项目或领域知识，不包含个人的
 品味、个性和判断偏好。
 
+## 实际怎么用：分类、作用域、项目识别与取回
+
+### 先判断存什么，再判断存在哪里
+
+“内容类型”和“生效范围”是两个独立维度。前三类是个人协作偏好，会带有
+`profileAspect`；项目事实不带 `profileAspect`，也不会出现在“个人偏好”页中。
+
+| 类型 | 应该存什么 | 例子 |
+| --- | --- | --- |
+| 品味 `taste` | 用户明确喜欢或排斥的结果、风格与质量方向，适用于界面、文案、产品、架构和工程结果 | “页面少用大渐变，不要卡片套卡片” |
+| 个性 `personality` | 用户明确自我描述、并且预计长期稳定的工作或协作特点 | “我习惯直接沟通，希望 Agent 主动推进” |
+| 判断偏好 `judgment_preference` | 面对取舍时的决策条件、优先级、风险倾向和操作边界 | “方向性歧义先讨论；未明确时禁止 `git push`” |
+| 项目知识 | 可复用的客观项目事实、术语、需求、路由、API、架构、决策理由和 Runbook | “Fuli 的 npm 发布由 GitHub Release 触发” |
+
+可以用四个问题快速分类：它描述的是“想要什么结果”时存品味；描述“我是怎样长期协作的”时
+存个性；描述“遇到取舍时怎么决定”时存判断偏好；描述“这个系统客观上如何工作”时存项目
+知识。一次性命令、临时输出、未经验证的猜测、原始聊天和凭据都不沉淀。
+
+“个性”不是所有个人信息的兜底分类。只有用户明确给出的稳定自我描述可以直接带着人工依据
+确认；Agent 仅从一次行为推断出的个性必须先保持 `pending`，不能伪装成人工确认。因此
+`/preferences` 的“个性”为空，通常表示当前范围内还没有符合这个标准的条目，而不是沉淀
+失败。像“文案简洁”更可能是品味，“未授权不推送”更可能是判断偏好。需要明确沉淀时，可以
+直接说：`这是我的长期协作个性，请作为个人全局偏好保存：我习惯直接沟通。` Agent 推断的
+候选可在 `/preferences` 或 `/flreview` 中由用户确认、纠正或失效。
+
+### 全局、项目级和公共层
+
+| 范围 | 何时使用 | 写入关键字段 | 取回规则 |
+| --- | --- | --- | --- |
+| 个人全局偏好 | 在无关项目中也应该保持不变 | `targetKind: "personal"`，不传 `personalProjectId`，设置 `profileAspect` | 每个任务都加载 |
+| 项目级个人偏好 | 协作方式属于一个项目或项目族 | 同上，同时传精确的 `personalProjectId`；默认 `local_only`，不向子项目继承；需传播时显式使用 `descendants` 或 `selected_projects` | 精确项目优先；仅按显式继承模式沿获授权关系传播，冲突不按分数自动裁决 |
+| 项目知识 | 事实只属于一个项目，或应由某个上级项目统一维护 | `targetKind: "personal"`，传 `personalProjectId`，不设置 `profileAspect` | 先查当前项目，再沿获授权的 `PART_OF` / `USES_KNOWLEDGE_FROM` 最多向上两跳 |
+| 团队公共知识 | 经人工确认、确实需要共享的项目或领域知识 | `targetKind: "project"`，并经过预览/审核 | 只有明确订阅或选择的公共项目可见；个人偏好永不进入这一层 |
+
+判断作用域时问一句：**换到完全无关的项目，这条协作偏好还应该改变 Agent 的行为吗？**
+“是”就存个人全局；“否，只在 Fuli 项目或项目族”就存项目级偏好，并明确是否允许向子项目
+传播。客观项目事实不要因为多个项目都可能用到就改存个人全局；应放在明确的上级或知识源
+项目，再建立有方向的授权关系。全局和项目级存在同一 `attributes.preferenceKey` 时，
+确认权威必须先裁决；权威相同时才由精确项目版本覆盖全局版本。
+
+### Fuli 怎么识别当前项目
+
+Fuli 只匹配已经登记在“个人项目”中的稳定 `project_id`，不根据目录内容做模糊猜测。通常让
+`project_id` 与仓库目录名一致，例如仓库 `/workspace/fuli` 对应项目 `fuli`。标准调用只传
+当前工作目录，解析顺序如下：
+
+1. 向上找到最近的 Git 仓库根；仓库目录名与已登记 `project_id` 完全相同时命中。
+2. 如果当前目录是 Codex worktree，从 `.git` 指向的原始仓库恢复项目 ID。
+3. 当前目录名与已登记项目 ID 完全相同时命中。
+4. 如果当前目录是工作区根，并且正好只有一个已登记的直接子目录带 `.git`、`package.json`、
+   `pyproject.toml`、`Cargo.toml` 或 `go.mod`，命中这个唯一子项目。
+5. 多个候选返回 `ambiguous`，没有候选返回 `unmatched`；两种情况都不会应用项目级偏好，也
+   不会猜一个项目。
+
+第一次进入尚未登记、但身份明确的仓库时，已安装的沉淀 Skill 可以在首次项目级写入前通过
+`upsert_personal_project` 创建最小的本机私有项目；它不会自动创建或订阅公共项目。若工作区
+有多个候选，应进入精确项目目录运行 Agent，或先在“个人项目”中明确选择和登记。
+
+### Agent 什么时候调用什么
+
+正常使用时，不需要手工调用 MCP 工具：在项目目录中向 Agent 提任务即可。Claude Code Hook
+调用 `begin_task_context`；Codex 和 Cursor 的 Prompt fallback 在每个任务开始调用一次：
+
+```json
+{
+  "tool": "get_collaboration_preferences",
+  "arguments": {
+    "projectPath": "/workspace/fuli",
+    "taskPrompt": "修复 npm 发布流程，并沿用这个项目已有的发布约定"
+  }
+}
+```
+
+命中后，返回值中的关键部分类似：
+
+```json
+{
+  "context": {
+    "personal_project_id": "fuli",
+    "project_resolution": {
+      "status": "matched",
+      "basis": "repository_root",
+      "personal_project_id": "fuli"
+    }
+  },
+  "effective_preferences": ["个人全局偏好 + fuli 的精确项目偏好"]
+}
+```
+
+入口返回的 `task_knowledge_recall` 没有回答稳定项目事实时，再用 1 至 4 条面向动作、产物、目标
+系统或标识符的短查询检索；不要把整段用户请求原样当成唯一查询：
+
+```json
+{
+  "tool": "search_current_project_knowledge",
+  "arguments": {
+    "projectPath": "/workspace/fuli",
+    "queries": ["npm 发布 Runbook", "GitHub Release 触发条件"],
+    "includePending": false
+  }
+}
+```
+
+任务结束时，Hook 模式调用 `checkpoint_task_knowledge`：只有少量、可复用且有证据的内容才用
+`capture_candidates`；否则使用 `retain_nothing`。Prompt fallback Agent 遵守相同判断标准，并
+通过 `capture_session_knowledge` 写入。写个人偏好时设置正确的 `profileAspect` 和稳定的
+`attributes.preferenceKey`；写项目事实时不设置 `profileAspect`。如果“设置”中的自动沉淀已
+关闭，写入会返回 `capture_disabled`，不会产生任何类别的条目。
+
+本地可先运行下面两个契约测试，验证 README 说明和项目路径解析仍与实现一致：
+
+```bash
+npm run test:node -- test/acceptance-docs.test.js test/project-path-context.test.js
+```
+
 ## Agent 交互时序
 
 下面是日常任务的简化时序。更完整的项目继承、使用计数、写入预览和来源标记流程见
@@ -289,7 +410,7 @@ CLI 的帮助、交互提示、状态和错误信息固定使用英文，不跟
 | `fuli --help` / `fuli -h` | 显示所有公开命令及其可用参数 |
 | `fuli --version` / `fuli -v` | 显示当前安装的 Fuli CLI 版本 |
 | `fuli setup [选项]` | 初始化 Provider、管理界面、Agent 接入和 Skills；可重复执行 |
-| `fuli start [选项]` | 启动 Provider 和管理界面；可选择启动后打开浏览器、重建容器或启用 LAN 访问 |
+| `fuli start [选项]` | 检查 Agent 接入后启动 Provider 和管理界面；可选择启动后打开浏览器、重建容器或启用 LAN 访问 |
 | `fuli stop [--data-dir DIR]` | 停止服务并保留数据 |
 | `fuli restart [选项]` | 使用与 `start` 相同的运行参数重启本机服务 |
 | `fuli status [--json] [--data-dir DIR] [--port PORT]` | 查看管理界面、个人图谱和公共服务状态；`--json` 输出机器可读结果 |
@@ -314,6 +435,9 @@ fuli stop
 口令。默认启动仍只监听 `127.0.0.1`；内部 Provider、Neo4j Browser 和 Bolt 不会随
 `--lan` 开放。局域网模式使用 HTTP Basic Auth，只适合可信家庭或办公 Wi-Fi，不等同于
 HTTPS 公网部署。
+`fuli start` 启动前会只读检查已检测到的 Agent 的 MCP、Skill、Codex bootstrap 和 Claude
+生命周期接入。如果有缺失或过期，它仍会启动本机服务，但会提示执行 `fuli setup`；不会在
+后台隐式修改接入配置。
 
 `setup` 和 `update` 支持：
 
@@ -357,10 +481,20 @@ Code 使用 `UserPromptSubmit` 和 `Stop` Hook 接入任务生命周期；Codex
 `AGENTS.md` 与 Cursor 指令使用 Prompt fallback。偏好正文始终以本机 Fuli 为唯一来源，
 不会复制到 Agent 配置中。
 
+FULI MCP 还提供只读的 `fuli://` resources：每个本地个人项目和“全局品味”各有一个可选条目。
+支持 MCP mention 的 Agent 可以在 `@` 选择器里选中它们；项目条目只代表一个精确项目，
+不会因为选择而自动扩大到其他项目或 `RELATED_TO` 项目。
+
+当任务需要品味或判断建议时，`get_user_taste_skill` 会根据当前生效的个人档案和历史任务
+数据生成一份有界、只读的 `user-taste` Skill 结论。它会标注证据状态与作用域，返回与当前
+任务匹配的推荐，并在偏好新增或修订后重新生成；不会覆盖用户自己编写的 taste Skill，持久
+图谱仍是唯一来源。
+
 | 工具 | 用途 |
 | --- | --- |
 | `begin_task_context` | Hook 入口：解析任务、在命中信号时执行有界召回并创建任务令牌 |
 | `get_collaboration_preferences` | Fallback 入口：读取生效偏好和有界任务召回 |
+| `get_user_taste_skill` | 生成当前带证据状态的 taste Skill 结论和任务推荐 |
 | `search_current_project_knowledge` | 子项目优先、按授权关系向上检索 |
 | `search_knowledge_graph` | 在明确的有界范围内执行更通用的查询 |
 | `search_connected_knowledge` | 分开检索图谱、项目绑定的只读来源和选定公共项目，保留来源边界 |

package/compose.graphiti.yml

@@ -47,6 +47,8 @@ services:
       FULI_PROVIDER_ID: local-personal
       FULI_PROVIDER_NAME: Fuli Personal Provider
       FULI_BOOTSTRAP_TOKEN: ${FULI_PERSONAL_BOOTSTRAP_TOKEN}
+      FULI_HUMAN_REVIEW_TOKEN: ${FULI_PERSONAL_HUMAN_REVIEW_TOKEN}
+      FULI_WORKFLOW_OBSERVATION_TOKEN: ${FULI_PERSONAL_WORKFLOW_OBSERVATION_TOKEN}
       FULI_NEO4J_URI: bolt://personal-neo4j:7687
       FULI_NEO4J_USER: neo4j
       FULI_NEO4J_PASSWORD: ${FULI_PERSONAL_NEO4J_PASSWORD}

package/dist/web/assets/{AboutPage-DfnZo7Lo.js → AboutPage-CftRexSY.js}

@@ -1 +1 @@
-import{Q as e,_ as t,a as n,b as r,f as i,j as a,k as o,m as s,p as c,tt as l,x as u}from"./i18n-BQcns1PH.js";import{t as d}from"./fuli-logo-Bu9WBuQe.js";import{t as f}from"./_plugin-vue_export-helper-BDNMzG2s.js";var p=[`aria-label`],m={class:`label-dimension-strip`},h=[`data-dimension`],g={class:`label-guide-sheet`},_={class:`label-guide-section profile-guide`},v={class:`label-definition-list`},y=[`data-kind`],b={class:`label-guide-section quadrant-guide`},x={class:`quadrant-explainer`},S={class:`quadrant-y-axis`,"aria-hidden":`true`},C={class:`quadrant-grid`},w=[`data-quadrant`],T={class:`quadrant-x-axis`,"aria-hidden":`true`},E={class:`quadrant-notes`},D={class:`label-guide-section confirmation-guide`},O={class:`status-definition-list`},k=[`data-status`],A={class:`status-boundaries`},j={class:`label-example`},M={class:`label-example-tags`,"aria-hidden":`true`},N={class:`label-token profile-token`,"data-kind":`taste`},P={class:`label-token origin-token`},ee={class:`label-token status-token`,"data-status":`confirmed`},F={class:`label-all-note`},I=f(u({__name:`LabelGuide`,setup(r){let u=c(()=>[{key:`profile`,title:n(`about.dimensions.profile.title`),question:n(`about.dimensions.profile.question`),timing:n(`about.dimensions.profile.timing`)},{key:`origin`,title:n(`about.dimensions.origin.title`),question:n(`about.dimensions.origin.question`),timing:n(`about.dimensions.origin.timing`)},{key:`confirmation`,title:n(`about.dimensions.confirmation.title`),question:n(`about.dimensions.confirmation.question`),timing:n(`about.dimensions.confirmation.timing`)}]),d=c(()=>[{key:`taste`,label:n(`about.profiles.taste.label`),short:n(`about.profiles.taste.short`),description:n(`about.profiles.taste.description`)},{key:`personality`,label:n(`about.profiles.personality.label`),short:n(`about.profiles.personality.short`),description:n(`about.profiles.personality.description`)},{key:`judgment`,label:n(`about.profiles.judgment.label`),short:n(`about.profiles.judgment.short`),description:n(`about.profiles.judgment.description`)}]),f=c(()=>[{key:`known-unknown`,label:n(`about.quadrants.knownUnknown.label`),coordinate:n(`about.quadrants.knownUnknown.coordinate`),description:n(`about.quadrants.knownUnknown.description`)},{key:`known-known`,label:n(`about.quadrants.knownKnown.label`),coordinate:n(`about.quadrants.knownKnown.coordinate`),description:n(`about.quadrants.knownKnown.description`)},{key:`unknown-unknown`,label:n(`about.quadrants.unknownUnknown.label`),coordinate:n(`about.quadrants.unknownUnknown.coordinate`),description:n(`about.quadrants.unknownUnknown.description`)},{key:`unknown-known`,label:n(`about.quadrants.unknownKnown.label`),coordinate:n(`about.quadrants.unknownKnown.coordinate`),description:n(`about.quadrants.unknownKnown.description`)}]),I=c(()=>[{key:`pending`,label:n(`about.statuses.pending.label`),description:n(`about.statuses.pending.description`),rule:n(`about.statuses.pending.rule`)},{key:`agent-confirmed`,label:n(`about.statuses.agentConfirmed.label`),description:n(`about.statuses.agentConfirmed.description`),rule:n(`about.statuses.agentConfirmed.rule`)},{key:`confirmed`,label:n(`about.statuses.confirmed.label`),description:n(`about.statuses.confirmed.description`),rule:n(`about.statuses.confirmed.rule`)}]);return(r,c)=>(o(),t(`section`,{class:`label-guide`,"aria-label":e(n)(`about.labelsAria`)},[s(`div`,m,[(o(!0),t(i,null,a(u.value,e=>(o(),t(`article`,{key:e.key,"data-dimension":e.key},[c[0]||=s(`i`,{"aria-hidden":`true`},null,-1),s(`div`,null,[s(`strong`,null,l(e.title),1),s(`p`,null,l(e.question),1),s(`small`,null,l(e.timing),1)])],8,h))),128))]),s(`div`,g,[s(`section`,_,[s(`header`,null,[s(`span`,null,l(e(n)(`about.sections.profile.index`)),1),s(`div`,null,[s(`h3`,null,l(e(n)(`about.sections.profile.title`)),1),s(`p`,null,l(e(n)(`about.sections.profile.meta`)),1)])]),s(`div`,v,[(o(!0),t(i,null,a(d.value,e=>(o(),t(`article`,{key:e.key,class:`label-definition-row`},[s(`span`,{class:`label-token profile-token`,"data-kind":e.key},l(e.label),9,y),s(`div`,null,[s(`strong`,null,l(e.short),1),s(`p`,null,l(e.description),1)])]))),128))])]),s(`section`,b,[s(`header`,null,[s(`span`,null,l(e(n)(`about.sections.origin.index`)),1),s(`div`,null,[s(`h3`,null,l(e(n)(`about.sections.origin.title`)),1),s(`p`,null,l(e(n)(`about.sections.origin.meta`)),1)])]),s(`div`,x,[s(`div`,S,[s(`span`,null,l(e(n)(`about.quadrants.aware`)),1),s(`strong`,null,l(e(n)(`about.quadrants.awareness`)),1),s(`span`,null,l(e(n)(`about.quadrants.unaware`)),1)]),s(`div`,C,[(o(!0),t(i,null,a(f.value,e=>(o(),t(`article`,{key:e.key,"data-quadrant":e.key},[s(`span`,null,l(e.coordinate),1),s(`strong`,null,l(e.label),1),s(`p`,null,l(e.description),1)],8,w))),128))]),s(`div`,T,[s(`span`,null,l(e(n)(`about.quadrants.unmastered`)),1),s(`strong`,null,l(e(n)(`about.quadrants.mastery`)),1),s(`span`,null,l(e(n)(`about.quadrants.mastered`)),1)]),s(`div`,E,[s(`p`,null,l(e(n)(`about.quadrants.immutable`)),1),s(`p`,null,l(e(n)(`about.quadrants.unclassified`)),1)])])]),s(`section`,D,[s(`header`,null,[s(`span`,null,l(e(n)(`about.sections.confirmation.index`)),1),s(`div`,null,[s(`h3`,null,l(e(n)(`about.sections.confirmation.title`)),1),s(`p`,null,l(e(n)(`about.sections.confirmation.meta`)),1)])]),s(`div`,null,[s(`div`,O,[(o(!0),t(i,null,a(I.value,r=>(o(),t(`article`,{key:r.key,class:`status-definition-row`},[s(`span`,{class:`label-token status-token`,"data-status":r.key},l(r.label),9,k),s(`p`,null,l(r.description),1),s(`div`,null,[s(`span`,null,l(e(n)(`about.statuses.entryCondition`)),1),s(`strong`,null,l(r.rule),1)])]))),128))]),s(`div`,A,[s(`p`,null,l(e(n)(`about.statuses.usageBoundary`)),1),s(`p`,null,l(e(n)(`about.statuses.resetBoundary`)),1)])])]),s(`section`,j,[s(`div`,null,[s(`span`,null,l(e(n)(`about.example.title`)),1),s(`strong`,null,l(e(n)(`about.example.item`)),1)]),s(`div`,M,[s(`span`,N,l(e(n)(`about.example.profile`)),1),s(`span`,P,l(e(n)(`about.example.origin`)),1),s(`span`,ee,l(e(n)(`about.example.status`)),1)]),s(`p`,null,l(e(n)(`about.example.description`)),1)]),s(`p`,F,l(e(n)(`about.allFilter`)),1)])],8,p))}}),[[`__scopeId`,`data-v-b79b7e68`]]),L={class:`open-source-credits`},R={class:`credits-roll`},z={class:`credit-grid`},B=[`href`],V={class:`credit-mark`},H=[`src`,`alt`],U={class:`credit-copy`},W={class:`credit-source-note`},G={class:`fuli-finale`},K={class:`finale-brand`},q=[`src`],J=f(u({__name:`OpenSourceCredits`,setup(r){let u=c(()=>[{name:`Vue.js`,role:n(`about.credits.roles.vue`),logo:`https://raw.githubusercontent.com/vuejs/docs/main/src/public/logo.svg`,url:`https://vuejs.org/`},{name:`Vite`,role:n(`about.credits.roles.vite`),logo:`https://raw.githubusercontent.com/vitejs/vite/main/docs/public/logo-without-border.svg`,url:`https://vite.dev/`},{name:`Pinia`,role:n(`about.credits.roles.pinia`),logo:`https://raw.githubusercontent.com/vuejs/pinia/v4/packages/docs/public/logo.svg`,url:`https://pinia.vuejs.org/`},{name:`D3.js`,role:n(`about.credits.roles.d3`),logo:`https://raw.githubusercontent.com/d3/d3-logo/master/d3.svg`,url:`https://d3js.org/`},{name:`Vitest`,role:n(`about.credits.roles.vitest`),logo:`https://raw.githubusercontent.com/vitest-dev/vitest/main/docs/public/logo-without-border.svg`,url:`https://vitest.dev/`},{name:`Hono`,role:n(`about.credits.roles.hono`),logo:`https://raw.githubusercontent.com/honojs/website/main/public/images/logo.svg`,url:`https://hono.dev/`},{name:`Neo4j`,role:n(`about.credits.roles.neo4j`),logo:`https://avatars.githubusercontent.com/u/201120?v=4`,url:`https://neo4j.com/`},{name:`Zod`,role:n(`about.credits.roles.zod`),logo:`https://raw.githubusercontent.com/colinhacks/zod/main/packages/docs/public/logo/logo_square.png`,url:`https://zod.dev/`},{name:`FastAPI`,role:n(`about.credits.roles.fastapi`),logo:`https://raw.githubusercontent.com/fastapi/fastapi/master/docs/en/docs/img/favicon.png`,url:`https://fastapi.tiangolo.com/`},{name:`Graphiti`,role:n(`about.credits.roles.graphiti`),logo:`https://avatars.githubusercontent.com/u/132832125?s=128&v=4`,url:`https://github.com/getzep/graphiti`},{name:`Model Context Protocol`,role:n(`about.credits.roles.mcp`),logo:`https://raw.githubusercontent.com/modelcontextprotocol/docs/main/favicon.svg`,url:`https://modelcontextprotocol.io/`}]);return(r,c)=>(o(),t(`section`,L,[s(`div`,R,[s(`header`,null,[s(`h3`,null,l(e(n)(`about.credits.title`)),1),s(`p`,null,l(e(n)(`about.credits.description`)),1)]),s(`div`,z,[(o(!0),t(i,null,a(u.value,e=>(o(),t(`a`,{key:e.name,href:e.url,target:`_blank`,rel:`noreferrer`},[s(`span`,V,[s(`img`,{src:e.logo,alt:e.name},null,8,H)]),s(`span`,U,[s(`strong`,null,l(e.name),1),s(`small`,null,l(e.role),1)])],8,B))),128))]),s(`p`,W,l(e(n)(`about.credits.sourceNote`)),1)]),s(`footer`,G,[s(`div`,K,[s(`img`,{src:e(d),alt:``,"aria-hidden":`true`},null,8,q),s(`div`,null,[s(`strong`,null,l(e(n)(`common.brand`)),1),c[0]||=s(`span`,null,`Context Graph`,-1)])]),s(`p`,null,l(e(n)(`about.credits.finale`)),1)])]))}}),[[`__scopeId`,`data-v-8676884b`]]),Y={class:`product-principles`},X={class:`principles-lede`},Z={class:`principle-sequence`},Q={class:`principle-boundaries`},$=[`data-boundary`],te=f(u({__name:`ProductPrinciples`,setup(r){let u=c(()=>[{key:`capture`,index:n(`about.philosophy.capture.index`),title:n(`about.philosophy.capture.title`),description:n(`about.philosophy.capture.description`)},{key:`project`,index:n(`about.philosophy.project.index`),title:n(`about.philosophy.project.title`),description:n(`about.philosophy.project.description`)},{key:`review`,index:n(`about.philosophy.review.index`),title:n(`about.philosophy.review.title`),description:n(`about.philosophy.review.description`)},{key:`reuse`,index:n(`about.philosophy.reuse.index`),title:n(`about.philosophy.reuse.title`),description:n(`about.philosophy.reuse.description`)}]),d=c(()=>[{key:`local`,title:n(`about.philosophy.local.title`),description:n(`about.philosophy.local.description`)},{key:`authority`,title:n(`about.philosophy.authority.title`),description:n(`about.philosophy.authority.description`)},{key:`scope`,title:n(`about.philosophy.scope.title`),description:n(`about.philosophy.scope.description`)}]);return(r,c)=>(o(),t(`section`,Y,[s(`header`,X,[s(`h3`,null,l(e(n)(`about.philosophy.title`)),1),s(`p`,null,l(e(n)(`about.philosophy.intro`)),1),s(`p`,null,l(e(n)(`about.philosophy.support`)),1)]),s(`div`,Z,[(o(!0),t(i,null,a(u.value,e=>(o(),t(`article`,{key:e.key},[s(`span`,null,l(e.index),1),s(`div`,null,[s(`h4`,null,l(e.title),1),s(`p`,null,l(e.description),1)])]))),128))]),s(`div`,Q,[s(`strong`,null,l(e(n)(`about.philosophy.boundariesTitle`)),1),s(`div`,null,[(o(!0),t(i,null,a(d.value,e=>(o(),t(`article`,{key:e.key},[s(`i`,{"data-boundary":e.key,"aria-hidden":`true`},null,8,$),s(`h4`,null,l(e.title),1),s(`p`,null,l(e.description),1)]))),128))])])]))}}),[[`__scopeId`,`data-v-d823b02d`]]),ne=[`aria-label`],re={class:`about-content`},ie={class:`about-labels-section`},ae=f(u({__name:`AboutPage`,setup(i){return(i,a)=>(o(),t(`section`,{class:`view about-view`,"aria-label":e(n)(`about.aria`)},[s(`div`,re,[r(te),s(`section`,ie,[s(`header`,null,[s(`h3`,null,l(e(n)(`about.labelsIntro.title`)),1),s(`p`,null,l(e(n)(`about.labelsIntro.description`)),1)]),r(I)]),r(J)])],8,ne))}}),[[`__scopeId`,`data-v-6bd30c79`]]);export{ae as default};
+import{Q as e,_ as t,a as n,b as r,f as i,j as a,k as o,m as s,p as c,tt as l,x as u}from"./i18n-CWfd8Dtt.js";import{t as d}from"./fuli-logo-Bu9WBuQe.js";import{t as f}from"./_plugin-vue_export-helper-BDNMzG2s.js";var p=[`aria-label`],m={class:`label-dimension-strip`},h=[`data-dimension`],g={class:`label-guide-sheet`},_={class:`label-guide-section profile-guide`},v={class:`label-definition-list`},y=[`data-kind`],b={class:`label-guide-section quadrant-guide`},x={class:`quadrant-explainer`},S={class:`quadrant-y-axis`,"aria-hidden":`true`},C={class:`quadrant-grid`},w=[`data-quadrant`],T={class:`quadrant-x-axis`,"aria-hidden":`true`},E={class:`quadrant-notes`},D={class:`label-guide-section confirmation-guide`},O={class:`status-definition-list`},k=[`data-status`],A={class:`status-boundaries`},j={class:`label-example`},M={class:`label-example-tags`,"aria-hidden":`true`},N={class:`label-token profile-token`,"data-kind":`taste`},P={class:`label-token origin-token`},ee={class:`label-token status-token`,"data-status":`confirmed`},F={class:`label-all-note`},I=f(u({__name:`LabelGuide`,setup(r){let u=c(()=>[{key:`profile`,title:n(`about.dimensions.profile.title`),question:n(`about.dimensions.profile.question`),timing:n(`about.dimensions.profile.timing`)},{key:`origin`,title:n(`about.dimensions.origin.title`),question:n(`about.dimensions.origin.question`),timing:n(`about.dimensions.origin.timing`)},{key:`confirmation`,title:n(`about.dimensions.confirmation.title`),question:n(`about.dimensions.confirmation.question`),timing:n(`about.dimensions.confirmation.timing`)}]),d=c(()=>[{key:`taste`,label:n(`about.profiles.taste.label`),short:n(`about.profiles.taste.short`),description:n(`about.profiles.taste.description`)},{key:`personality`,label:n(`about.profiles.personality.label`),short:n(`about.profiles.personality.short`),description:n(`about.profiles.personality.description`)},{key:`judgment`,label:n(`about.profiles.judgment.label`),short:n(`about.profiles.judgment.short`),description:n(`about.profiles.judgment.description`)}]),f=c(()=>[{key:`known-unknown`,label:n(`about.quadrants.knownUnknown.label`),coordinate:n(`about.quadrants.knownUnknown.coordinate`),description:n(`about.quadrants.knownUnknown.description`)},{key:`known-known`,label:n(`about.quadrants.knownKnown.label`),coordinate:n(`about.quadrants.knownKnown.coordinate`),description:n(`about.quadrants.knownKnown.description`)},{key:`unknown-unknown`,label:n(`about.quadrants.unknownUnknown.label`),coordinate:n(`about.quadrants.unknownUnknown.coordinate`),description:n(`about.quadrants.unknownUnknown.description`)},{key:`unknown-known`,label:n(`about.quadrants.unknownKnown.label`),coordinate:n(`about.quadrants.unknownKnown.coordinate`),description:n(`about.quadrants.unknownKnown.description`)}]),I=c(()=>[{key:`pending`,label:n(`about.statuses.pending.label`),description:n(`about.statuses.pending.description`),rule:n(`about.statuses.pending.rule`)},{key:`agent-confirmed`,label:n(`about.statuses.agentConfirmed.label`),description:n(`about.statuses.agentConfirmed.description`),rule:n(`about.statuses.agentConfirmed.rule`)},{key:`confirmed`,label:n(`about.statuses.confirmed.label`),description:n(`about.statuses.confirmed.description`),rule:n(`about.statuses.confirmed.rule`)}]);return(r,c)=>(o(),t(`section`,{class:`label-guide`,"aria-label":e(n)(`about.labelsAria`)},[s(`div`,m,[(o(!0),t(i,null,a(u.value,e=>(o(),t(`article`,{key:e.key,"data-dimension":e.key},[c[0]||=s(`i`,{"aria-hidden":`true`},null,-1),s(`div`,null,[s(`strong`,null,l(e.title),1),s(`p`,null,l(e.question),1),s(`small`,null,l(e.timing),1)])],8,h))),128))]),s(`div`,g,[s(`section`,_,[s(`header`,null,[s(`span`,null,l(e(n)(`about.sections.profile.index`)),1),s(`div`,null,[s(`h3`,null,l(e(n)(`about.sections.profile.title`)),1),s(`p`,null,l(e(n)(`about.sections.profile.meta`)),1)])]),s(`div`,v,[(o(!0),t(i,null,a(d.value,e=>(o(),t(`article`,{key:e.key,class:`label-definition-row`},[s(`span`,{class:`label-token profile-token`,"data-kind":e.key},l(e.label),9,y),s(`div`,null,[s(`strong`,null,l(e.short),1),s(`p`,null,l(e.description),1)])]))),128))])]),s(`section`,b,[s(`header`,null,[s(`span`,null,l(e(n)(`about.sections.origin.index`)),1),s(`div`,null,[s(`h3`,null,l(e(n)(`about.sections.origin.title`)),1),s(`p`,null,l(e(n)(`about.sections.origin.meta`)),1)])]),s(`div`,x,[s(`div`,S,[s(`span`,null,l(e(n)(`about.quadrants.aware`)),1),s(`strong`,null,l(e(n)(`about.quadrants.awareness`)),1),s(`span`,null,l(e(n)(`about.quadrants.unaware`)),1)]),s(`div`,C,[(o(!0),t(i,null,a(f.value,e=>(o(),t(`article`,{key:e.key,"data-quadrant":e.key},[s(`span`,null,l(e.coordinate),1),s(`strong`,null,l(e.label),1),s(`p`,null,l(e.description),1)],8,w))),128))]),s(`div`,T,[s(`span`,null,l(e(n)(`about.quadrants.unmastered`)),1),s(`strong`,null,l(e(n)(`about.quadrants.mastery`)),1),s(`span`,null,l(e(n)(`about.quadrants.mastered`)),1)]),s(`div`,E,[s(`p`,null,l(e(n)(`about.quadrants.immutable`)),1),s(`p`,null,l(e(n)(`about.quadrants.unclassified`)),1)])])]),s(`section`,D,[s(`header`,null,[s(`span`,null,l(e(n)(`about.sections.confirmation.index`)),1),s(`div`,null,[s(`h3`,null,l(e(n)(`about.sections.confirmation.title`)),1),s(`p`,null,l(e(n)(`about.sections.confirmation.meta`)),1)])]),s(`div`,null,[s(`div`,O,[(o(!0),t(i,null,a(I.value,r=>(o(),t(`article`,{key:r.key,class:`status-definition-row`},[s(`span`,{class:`label-token status-token`,"data-status":r.key},l(r.label),9,k),s(`p`,null,l(r.description),1),s(`div`,null,[s(`span`,null,l(e(n)(`about.statuses.entryCondition`)),1),s(`strong`,null,l(r.rule),1)])]))),128))]),s(`div`,A,[s(`p`,null,l(e(n)(`about.statuses.usageBoundary`)),1),s(`p`,null,l(e(n)(`about.statuses.resetBoundary`)),1)])])]),s(`section`,j,[s(`div`,null,[s(`span`,null,l(e(n)(`about.example.title`)),1),s(`strong`,null,l(e(n)(`about.example.item`)),1)]),s(`div`,M,[s(`span`,N,l(e(n)(`about.example.profile`)),1),s(`span`,P,l(e(n)(`about.example.origin`)),1),s(`span`,ee,l(e(n)(`about.example.status`)),1)]),s(`p`,null,l(e(n)(`about.example.description`)),1)]),s(`p`,F,l(e(n)(`about.allFilter`)),1)])],8,p))}}),[[`__scopeId`,`data-v-b79b7e68`]]),L={class:`open-source-credits`},R={class:`credits-roll`},z={class:`credit-grid`},B=[`href`],V={class:`credit-mark`},H=[`src`,`alt`],U={class:`credit-copy`},W={class:`credit-source-note`},G={class:`fuli-finale`},K={class:`finale-brand`},q=[`src`],J=f(u({__name:`OpenSourceCredits`,setup(r){let u=c(()=>[{name:`Vue.js`,role:n(`about.credits.roles.vue`),logo:`https://raw.githubusercontent.com/vuejs/docs/main/src/public/logo.svg`,url:`https://vuejs.org/`},{name:`Vite`,role:n(`about.credits.roles.vite`),logo:`https://raw.githubusercontent.com/vitejs/vite/main/docs/public/logo-without-border.svg`,url:`https://vite.dev/`},{name:`Pinia`,role:n(`about.credits.roles.pinia`),logo:`https://raw.githubusercontent.com/vuejs/pinia/v4/packages/docs/public/logo.svg`,url:`https://pinia.vuejs.org/`},{name:`D3.js`,role:n(`about.credits.roles.d3`),logo:`https://raw.githubusercontent.com/d3/d3-logo/master/d3.svg`,url:`https://d3js.org/`},{name:`Vitest`,role:n(`about.credits.roles.vitest`),logo:`https://raw.githubusercontent.com/vitest-dev/vitest/main/docs/public/logo-without-border.svg`,url:`https://vitest.dev/`},{name:`Hono`,role:n(`about.credits.roles.hono`),logo:`https://raw.githubusercontent.com/honojs/website/main/public/images/logo.svg`,url:`https://hono.dev/`},{name:`Neo4j`,role:n(`about.credits.roles.neo4j`),logo:`https://avatars.githubusercontent.com/u/201120?v=4`,url:`https://neo4j.com/`},{name:`Zod`,role:n(`about.credits.roles.zod`),logo:`https://raw.githubusercontent.com/colinhacks/zod/main/packages/docs/public/logo/logo_square.png`,url:`https://zod.dev/`},{name:`FastAPI`,role:n(`about.credits.roles.fastapi`),logo:`https://raw.githubusercontent.com/fastapi/fastapi/master/docs/en/docs/img/favicon.png`,url:`https://fastapi.tiangolo.com/`},{name:`Graphiti`,role:n(`about.credits.roles.graphiti`),logo:`https://avatars.githubusercontent.com/u/132832125?s=128&v=4`,url:`https://github.com/getzep/graphiti`},{name:`Model Context Protocol`,role:n(`about.credits.roles.mcp`),logo:`https://raw.githubusercontent.com/modelcontextprotocol/docs/main/favicon.svg`,url:`https://modelcontextprotocol.io/`}]);return(r,c)=>(o(),t(`section`,L,[s(`div`,R,[s(`header`,null,[s(`h3`,null,l(e(n)(`about.credits.title`)),1),s(`p`,null,l(e(n)(`about.credits.description`)),1)]),s(`div`,z,[(o(!0),t(i,null,a(u.value,e=>(o(),t(`a`,{key:e.name,href:e.url,target:`_blank`,rel:`noreferrer`},[s(`span`,V,[s(`img`,{src:e.logo,alt:e.name},null,8,H)]),s(`span`,U,[s(`strong`,null,l(e.name),1),s(`small`,null,l(e.role),1)])],8,B))),128))]),s(`p`,W,l(e(n)(`about.credits.sourceNote`)),1)]),s(`footer`,G,[s(`div`,K,[s(`img`,{src:e(d),alt:``,"aria-hidden":`true`},null,8,q),s(`div`,null,[s(`strong`,null,l(e(n)(`common.brand`)),1),c[0]||=s(`span`,null,`Context Graph`,-1)])]),s(`p`,null,l(e(n)(`about.credits.finale`)),1)])]))}}),[[`__scopeId`,`data-v-8676884b`]]),Y={class:`product-principles`},X={class:`principles-lede`},Z={class:`principle-sequence`},Q={class:`principle-boundaries`},$=[`data-boundary`],te=f(u({__name:`ProductPrinciples`,setup(r){let u=c(()=>[{key:`capture`,index:n(`about.philosophy.capture.index`),title:n(`about.philosophy.capture.title`),description:n(`about.philosophy.capture.description`)},{key:`project`,index:n(`about.philosophy.project.index`),title:n(`about.philosophy.project.title`),description:n(`about.philosophy.project.description`)},{key:`review`,index:n(`about.philosophy.review.index`),title:n(`about.philosophy.review.title`),description:n(`about.philosophy.review.description`)},{key:`reuse`,index:n(`about.philosophy.reuse.index`),title:n(`about.philosophy.reuse.title`),description:n(`about.philosophy.reuse.description`)}]),d=c(()=>[{key:`local`,title:n(`about.philosophy.local.title`),description:n(`about.philosophy.local.description`)},{key:`authority`,title:n(`about.philosophy.authority.title`),description:n(`about.philosophy.authority.description`)},{key:`scope`,title:n(`about.philosophy.scope.title`),description:n(`about.philosophy.scope.description`)}]);return(r,c)=>(o(),t(`section`,Y,[s(`header`,X,[s(`h3`,null,l(e(n)(`about.philosophy.title`)),1),s(`p`,null,l(e(n)(`about.philosophy.intro`)),1),s(`p`,null,l(e(n)(`about.philosophy.support`)),1)]),s(`div`,Z,[(o(!0),t(i,null,a(u.value,e=>(o(),t(`article`,{key:e.key},[s(`span`,null,l(e.index),1),s(`div`,null,[s(`h4`,null,l(e.title),1),s(`p`,null,l(e.description),1)])]))),128))]),s(`div`,Q,[s(`strong`,null,l(e(n)(`about.philosophy.boundariesTitle`)),1),s(`div`,null,[(o(!0),t(i,null,a(d.value,e=>(o(),t(`article`,{key:e.key},[s(`i`,{"data-boundary":e.key,"aria-hidden":`true`},null,8,$),s(`h4`,null,l(e.title),1),s(`p`,null,l(e.description),1)]))),128))])])]))}}),[[`__scopeId`,`data-v-d823b02d`]]),ne=[`aria-label`],re={class:`about-content`},ie={class:`about-labels-section`},ae=f(u({__name:`AboutPage`,setup(i){return(i,a)=>(o(),t(`section`,{class:`view about-view`,"aria-label":e(n)(`about.aria`)},[s(`div`,re,[r(te),s(`section`,ie,[s(`header`,null,[s(`h3`,null,l(e(n)(`about.labelsIntro.title`)),1),s(`p`,null,l(e(n)(`about.labelsIntro.description`)),1)]),r(I)]),r(J)])],8,ne))}}),[[`__scopeId`,`data-v-6bd30c79`]]);export{ae as default};