@fenglimg/fabric-cli 2.0.0 → 2.1.0-rc.2

package/templates/skills/fabric-archive/ref/e5-cron-recap.md

@@ -0,0 +1,58 @@
+# E5 Scheduled Daily Recap — full reference
+
+> **Loaded on demand.** Only relevant when invocation context = `cron` / `/loop` (E5 entry). SKILL.md's Phase 0 already gates this — if the user just typed `/fabric-archive`, none of the below applies.
+
+## E5 周期触发 (Scheduled Daily Recap)
+
+## Overview
+
+`今日复盘` = E5 entry point. Default scope = today. Falls back to historical scan if today yields no candidates (silent-skip per Phase 4.5).
+
+E5 是 5 入口模型中唯一由 OS 调度器或 Claude Code `/loop` 周期触发的入口形态。fabric 端**零代码**——不提供 `fabric schedule` 子命令,亦不内嵌 daemon。用户基于自己的执行环境二选一接入: `/loop`(Claude Code 原生,推荐) 或 OS cron(跨平台 fallback)。
+
+### /loop sample (primary path for Claude Code)
+
+```
+/loop /fabric-archive 今日复盘 --cron "0 23 * * *"
+```
+
+每晚 23:00 在当前 Claude Code session 中触发 fabric-archive skill,scope = today。`/loop` 复用现有 Claude session 鉴权,无需独立 token。
+
+### OS cron sample (cross-platform alternative)
+
+```
+# crontab -e
+0 23 * * * cd /path/to/project && claude code -p "/fabric-archive 今日复盘" 2>&1 >> /var/log/fabric-daily-recap.log
+```
+
+适用于:
+- 非 Claude Code 环境(纯 server / CI 节点)
+- 希望脱离 /loop session 生命周期独立运行的场景
+- 已有 cron / launchd 调度基础设施的团队
+
+macOS 用户可改用 `launchd` plist;Linux 用户直接 `crontab -e`。命令需自行确保 `claude code` CLI 已安装且鉴权可用。
+
+### E5 prompt parse contract
+
+当用户或 cron 以 `今日复盘` / `daily recap` 字面短语触发 fabric-archive 时,skill 应按以下契约处理:
+
+- **Phase 0 Range Resolution**: 识别 `今日复盘` / `daily recap` 为 magic phrase, 直接设置 `time_window = today` (00:00 local timezone → current ts), 无需 AskUserQuestion 兜底。
+- **Phase 1.5 Onboard Coverage**: 跳过 (entry_point = E5_cron, 非 E2_explicit, 不弹 onboard 弹问)。
+- **Phase 4.5 Persist Archive Attempt**: 始终写入 `session_archive_attempted` event。当今日无 archive 信号触发 viability gate FAIL 时,走 silent-skip 路径(outcome = `skipped_no_signal`),skill 静默退出,cron 日志为空。
+
+### Trade-off table (/loop vs OS cron)
+
+| 维度 | /loop | OS cron |
+|---|---|---|
+| 鉴权 | 复用 Claude session | 独立 token / login |
+| 跨平台 | Claude Code 全平台一致 | macOS launchd / Linux cron 不同 |
+| Token 成本 | 累积 (长 session) | 每 tick fresh, 无累积 |
+| 调试 | Claude UI 可见 | 日志文件 |
+
+### Failure modes
+
+- **/loop session crash**: 归档暂停,用户需重启 `/loop`。无自动恢复机制——`/loop` 与 Claude Code session 生命周期绑定。
+- **OS cron**: 自带恢复(下一个 tick 重新启动),但需独立 `claude code` CLI 安装与鉴权;鉴权 token 过期时 cron job 会静默失败,需人工 `claude login` 重置。
+
+### NOT in scope
+

package/templates/skills/fabric-archive/ref/i18n-policy.md

@@ -0,0 +1,86 @@
+# UX i18n Policy — full reference
+
+> **Shared core (rc.37 NEW-13):** the cross-skill invariants — protected-token
+> NEVER-translate list, AskUserQuestion routing-key rule, layer heuristic, and
+> events-emit convention — live once in `../../lib/shared-policy.md`. This file
+> keeps only the fabric-archive-specific 5-class examples. Read the shared lib
+> for the common rules; do not fork them here.
+
+> **Loaded on demand.** Only consult when rendering bilingual output AND you're unsure which class a string belongs to. SKILL.md gives the operative rule: read `.fabric/fabric-config.json` → `fabric_language`, emit prose in resolved variant, never translate protected tokens. The 5-class taxonomy below disambiguates edge cases.
+
+## UX i18n Policy (5-class bilingualization)
+
+The skill consults `fabric_language` from `.fabric/fabric-config.json`
+(固化于 init 时，via `lib/detect-language.ts:detectExistingLanguage`; default `"en"` when no
+CJK signal is detected in README + docs/; may resolve to `"match-existing"`,
+`"zh-CN"`, `"en"`, or `"zh-CN-hybrid"`). All user-facing text in the
+following 5 categories MUST be rendered in the resolved language:
+
+1. **Roll-up templates** — the `# Archive Review — N candidates` batch
+   review block (one per candidate) AND any final session summary the
+   skill emits after Phase 4 completes. zh-CN ↔ en mirror.
+2. **Errors / Preconditions warnings** — abort + gate-fail messages (e.g.
+   the "没有触发归档信号…" trigger-miss and the "本次会话为常规执行…"
+   viability-gate-FAIL message). zh-CN ↔ en mirror.
+3. **Confirmation prompts** — the per-candidate `Confirm? (Y to accept,
+   edit … inline, N to skip)` line in the batch review template. zh-CN
+   ↔ en mirror.
+4. **Dry-run table headers** — v2.0.0-rc.27 TASK-007 added a dry-run
+   override path (see Phase 4.5 "dry-run") so users can preview the
+   archive proposal without writing pending entries. The dry-run summary
+   header and per-candidate preview labels MUST be bilingualized per
+   this policy. zh-CN ↔ en mirror.
+5. **AskUserQuestion** — `header` + `question` fields (NOT `options[]`).
+   zh-CN ↔ en mirror. fabric-archive itself does not surface
+   AskUserQuestion in the current contract (Phase 3 batch review is a
+   single markdown screen, not a structured question), but if a future
+   version adds one — e.g. to confirm layer flip — this rule applies.
+
+Rendering rule:
+
+- `fabric_language === "zh-CN"` → emit the zh-CN variant; pure monolingual, no language mixing inside a single user-facing block.
+- `fabric_language === "en"` → emit the en variant; pure monolingual, no language mixing inside a single user-facing block.
+- `fabric_language === "zh-CN-hybrid"` → emit Chinese narrative prose with English technical terms preserved. Protected tokens (always EN): MCP tool names (e.g. `fab_get_knowledge_sections`), CLI command names (e.g. `fabric install`), file paths, technical concepts (`Skill`, `SessionStart`, `hook`, `MCP`, `revision_hash`, `pending`, `proven`, `verified`, `draft`).
+- `fabric_language === "match-existing"` or any other value → emit the en variant; pure monolingual.
+
+Protected tokens (`fab_extract_knowledge`, `relevance_scope`,
+`relevance_paths`, `narrow`, `broad`, `source_sessions`, `proposed_reason`,
+`session_context`, `intent_clues`, `tech_stack`, `impact`, `must_read_if`,
+`pending_path`, `layer`, `team`, `personal`,
+`knowledge_scope_degraded`, `MUST`, `NEVER`, `.fabric/knowledge/`, the verbatim
+`强 team` / `强 personal` / `默认 team` heuristic block, etc.) are NEVER
+translated — they appear verbatim in both language variants. The
+bilingualization scope is prose ONLY.
+
+### AskUserQuestion i18n Policy (value vs label)
+
+When a skill (this one or any sibling skill the user is composing with)
+issues an `AskUserQuestion`, the `header` and `question` strings are
+user-facing prose → translated per `fabric_language`. The `options[]`
+array entries (e.g. `["approve", "reject", "modify", "defer", "skip"]` in
+fabric-review, or `["team", "personal"]` for a layer-flip target) are
+**routing keys** consumed by the skill state machine — they MUST remain
+English regardless of `fabric_language`.
+
+```ts
+// EN (fabric_language === "en")
+AskUserQuestion({
+  header: "Layer-flip target",
+  question: "Move '{title}' to which layer? (current: {current_layer})",
+  options: ["team", "personal"]
+})
+
+// zh-CN (fabric_language === "zh-CN")
+AskUserQuestion({
+  header: "Layer 切换目标",
+  question: "将 '{title}' 切换到哪一层？(当前: {current_layer})",
+  options: ["team", "personal"]   // 不翻译 — routing key
+})
+```
+
+Rationale: localizing routing keys would force every routing branch to
+dual-string match (e.g. `if (choice === "team" || choice === "团队")`),
+which doubles the surface area for protected-token regressions and breaks
+the option-list invariants that downstream tooling depends on. Keeping
+`options[]` English-only is contract-locked across all three skills.
+

package/templates/skills/fabric-archive/ref/phase-0-range-resolution.md

@@ -0,0 +1,156 @@
+# Phase 0 — Range Resolution (ref)
+
+> **Loaded on demand.** SKILL.md hot path retains the Phase 0 intro, the Confidence decision rule, and Step 1 (invocation context inspection). This file holds Steps 2-6 (parsing tables, session_id resolution algorithm, AskUserQuestion fallback, carry-forward contract) + worked examples. Read when entry_point ∈ {E2_explicit_user_invoke, E4_user_range_rollback} AND the user prompt likely carries a range hint that needs parsing.
+
+## Step 2 — Time-window parsing
+
+Match the user prompt against the following bilingual patterns (case-insensitive substring match, leftmost-longest wins). The matched span yields a `[ts_start, ts_end]` pair in Unix milliseconds. `now` = the skill invocation timestamp.
+
+### zh-CN pattern table
+
+| Pattern | ts_start | ts_end |
+|---|---|---|
+| `今日` / `今天` | `floor(now, day)` (本地时区 00:00) | `now` |
+| `上周` / `过去一周` | `now - 7d` | `now` |
+| `过去 N 天` / `近 N 天` (N ∈ 1..30) | `now - N*24h` | `now` |
+| `自上次归档` / `自上次 archive` | tail-scan events.jsonl → most recent `knowledge_proposed.ts` (fallback `events[0].ts`) | `now` |
+
+### en pattern table
+
+| Pattern | ts_start | ts_end |
+|---|---|---|
+| `today` | `floor(now, day)` (local TZ 00:00) | `now` |
+| `last week` / `past week` | `now - 7d` | `now` |
+| `past N days` / `last N days` (N ∈ 1..30) | `now - N*24h` | `now` |
+| `since last archive` / `since last archived` | tail-scan events.jsonl → most recent `knowledge_proposed.ts` (fallback `events[0].ts`) | `now` |
+
+Notes:
+
+- Patterns are non-exclusive — if the prompt matches multiple (e.g. "今日 cite policy"), apply time-window THEN topic-keyword as AND.
+- Numeric N must parse as a positive integer ≤ 30; reject anything else as parse-miss.
+- All other date phrasings (specific dates like `5月10日`, relative phrasings like `三天前下午`) are NOT handled here — emit parse-miss and let Step 5 fallback collect a structured answer.
+
+## Step 3 — Topic-keyword extraction
+
+After time-window matching (or alongside it when both apply), extract content keywords from the prompt:
+
+1. Strip recognised time-window tokens (e.g. remove `今日` / `last week` from the residual prompt).
+2. Tokenize residual on whitespace + CJK boundary. Combine adjacent CJK characters into one token; split en words on spaces.
+3. Filter **stop-words**: skill control verbs (`archive`, `归档`, `下`, `的`), articles / particles (`the`, `a`, `an`, `了`, `吧`), pronouns (`it`, `this`, `that`, `这个`, `那个`), and 1-character en tokens.
+4. Retain **2-5 word tokens** (or 1-token CJK content words ≥ 2 chars like `rc.20`, `cite`). Cap at 8 keywords; drop weaker (later-position) ones.
+
+The retained set is `topic_keywords[]`. Empty set = no keyword filter.
+
+## Step 4 — session_id resolution algorithm
+
+Given `time_window = [ts_start, ts_end] | null` and `topic_keywords[] | []`:
+
+```
+Step a — Read events.jsonl tail (last 500 events) via `Bash: tail -n 500
+         .fabric/events.jsonl`. ENOENT → empty list (no resolution possible
+         → emit parse-miss → Step 5 fallback).
+
+Step b — Per distinct session_id present in the tail, compute:
+           ts_min      = min(ts) over events with this session_id
+           ts_max      = max(ts) over events with this session_id
+           digest_path = .fabric/.cache/session-digests/<session_id>.md
+           digest_body = Read(digest_path) if exists, else ""
+
+Step c — TIME-WINDOW FILTER (skip when time_window is null):
+           Keep session_id IFF [ts_min, ts_max] intersects [ts_start, ts_end]
+           (i.e. ts_max >= ts_start AND ts_min <= ts_end).
+           Multiple time intervals are OR'd within the time-window filter
+           category (none currently supported; reserved for future ranges).
+
+Step d — TOPIC-KEYWORD FILTER (skip when topic_keywords is empty):
+           Keep session_id IFF digest_body (case-insensitive) contains
+           AT LEAST ONE keyword from topic_keywords[].
+           Multiple keywords are OR'd within the keyword filter category.
+
+Step e — AND across filter categories:
+           A session must pass BOTH filters when BOTH are present.
+           Pass either filter alone when only one is present.
+           Pass-through (all sessions) when neither is present.
+
+Step f — Result: distinct session_id[] (preserve event-order); if empty AND
+         a parse hit was claimed → degrade to Step 5 fallback (user wanted a
+         range that resolved to zero sessions).
+```
+
+## Step 5 — AskUserQuestion fallback (E2 / E4 only)
+
+When Step 2/3 emit parse-miss OR Step 4 resolves to zero sessions AND the invocation type permits prompting (E2 user-active or E4 user回溯-active — NEVER E1 hook / E3 AI-self / E5 cron), surface a structured question. UX i18n Policy class 5 applies: `header` + `question` translate per `fabric_language`; `options[]` routing keys stay English.
+
+```ts
+AskUserQuestion({
+  header: "Archive range",                              // zh-CN: "归档范围"
+  question:
+    "Which session range should this archive cover? " +
+    "(today = current calendar day; last-week = past 7 days; " +
+    "since-last-archive = newer than last knowledge_proposed event; " +
+    "custom = type a free-form range)",
+  options: ["today", "last-week", "since-last-archive", "custom"]
+})
+```
+
+Routing:
+
+| Choice | Action |
+|---|---|
+| `today` | Re-enter Step 2 with synthetic prompt `今日` / `today` (per `fabric_language`); resolve session_ids; proceed to Phase 0.5. |
+| `last-week` | Re-enter Step 2 with synthetic prompt `上周` / `last week`; proceed to Phase 0.5. |
+| `since-last-archive` | Re-enter Step 2 with synthetic prompt `自上次归档` / `since last archive`; proceed to Phase 0.5. |
+| `custom` | Surface a one-line text prompt to the user ("type a range, e.g. 'rc.20', 'past 3 days', '上周 cite policy'"). Re-enter Phase 0 Step 1 with the user-typed sub-prompt. Loop max 1 time — second parse-miss falls through to `range = "all"` with a warning. |
+
+## Step 6 — Carry-forward contract
+
+Phase 0 produces ONE of:
+
+- `session_id[]` (non-empty array of distinct session_ids) — passed to Phase 1 as the explicit scope filter; Phase 1 skips its own anchor-walk and uses this list directly.
+- `"all"` (sentinel string) — no range hint detected; Phase 1 falls back to the legacy anchor-walk behaviour ("all distinct sessions since last `knowledge_proposed`").
+
+NEVER pass an empty `session_id[]` forward — that case must degrade to Step 5 fallback (or, when fallback is forbidden by invocation type, to `"all"` with a one-line stderr warning).
+
+## Worked examples
+
+### Example A — time-only: `今日复盘`
+
+```
+Step 1: prompt = "今日复盘"; user_invocation_type = E2.
+Step 2: matches `今日` → time_window = [floor(now, day), now].
+Step 3: residual "复盘" survives stop-word filter → topic_keywords = ["复盘"].
+        (Edge case: the residual content word may also filter; if 复盘 is
+        in the stop list it becomes []. Treat as topic-keyword empty.)
+Step 4: tail-scan events.jsonl; keep sessions whose [ts_min, ts_max]
+        intersects today's window. Say 3 sessions match.
+Step 5: skipped (resolution succeeded).
+Step 6: emit session_id[] = ["sess-a", "sess-b", "sess-c"] → Phase 0.5.
+```
+
+### Example B — keyword-only: `rc.20 的归档下`
+
+```
+Step 1: prompt = "rc.20 的归档下"; user_invocation_type = E2.
+Step 2: no time pattern matches → time_window = null.
+Step 3: strip "归档"/"下"/"的" stop-words → topic_keywords = ["rc.20"].
+Step 4: tail-scan events.jsonl; for each session_id, Read its digest;
+        keep those whose digest body matches /rc\.20/i. Say 2 sessions
+        match (one was the rc.20 grilling session, one had a tangential
+        mention).
+Step 5: skipped.
+Step 6: emit session_id[] = ["sess-x", "sess-y"] → Phase 0.5.
+```
+
+### Example C — combined: `上周 rc.20`
+
+```
+Step 1: prompt = "上周 rc.20"; user_invocation_type = E4.
+Step 2: matches `上周` → time_window = [now - 7d, now].
+Step 3: strip "上周" → topic_keywords = ["rc.20"].
+Step 4: AND filter — keep sessions whose [ts_min, ts_max] intersects last
+        week AND whose digest matches /rc\.20/i. Say 1 session matches.
+Step 5: skipped.
+Step 6: emit session_id[] = ["sess-z"] → Phase 0.5.
+```
+
+If Example C had resolved to zero sessions (e.g. user types `上周 rc.99`), Step 4 would degrade into Step 5 — surfacing AskUserQuestion since E4 permits prompting.

package/templates/skills/fabric-archive/ref/phase-1-5-onboard.md

@@ -0,0 +1,218 @@
+# Phase 1.5 — First-run Onboard Phase (ref)
+
+> **Loaded on demand.** SKILL.md hot path only runs this when entry_point ∈ {E2_explicit_user_invoke, E4_user_range_rollback} AND `fabric onboard-coverage --json` reports `missing.length > 0`. For E1/E3/E5 entries OR fully-covered workspaces, this entire phase is skipped — no reason to load.
+
+## Phase 1.5 — First-run Onboard Phase
+
+#### Phase 1.5 Trigger Gate (rc.25 — entry-context aware)
+
+Before running ANY of the onboard coverage steps below, evaluate the
+**entry-context gate**. Onboard slot collection is an interactive,
+one-time project-tone capture flow that REQUIRES live user dialogue.
+Non-user-active entries (hook / AI self-trigger / cron) either interrupt
+the user mid-work or run unattended where dialogue is impossible, so
+they MUST skip Phase 1.5 entirely and fall through to Phase 0.
+
+Read `context.entry_point` — already determined in **Phase 0 Range
+Resolution** (see TASK-04 / Phase 0 section above). The 5-entry model
+is the canonical taxonomy for this gate.
+
+##### Entry-context detection rules
+
+| Entry | Symbol | Detection rule (LLM-native, evaluated at skill entry) |
+|-------|--------|-------------------------------------------------------|
+| **E1** | `hook_passive` | stdout JSON `{decision:'block', ...}` from `archive-hint.cjs` detected at skill entry (the Stop-hook reminder path). |
+| **E2** | `explicit_user_invoke` | User prompt is a direct invocation: `fabric archive` / `/fabric-archive` / `archive what we just did` / `归档一下` / similar imperative. |
+| **E3** | `ai_self_trigger` | AI internal marker `self-archive policy triggered by signal: <X>` present (substring match on the verbatim prefix `self-archive policy triggered by signal` per AGENTS.md self-archive policy section; `<X>` is the signal name. v2.0.0-rc.37 NEW-2 simplified the AGENTS.md taxonomy to 2 categories: `User-driven normative` / `Wrong-turn-and-revert`. Back-compat: legacy 4-state names (`Normative` / `Decision confirmation` / `Explicit dismissal`) still route correctly because the substring gate only matches the verbatim prefix and treats any text after `signal:` as the signal label.) |
+| **E4** | `user_range_rollback` | Prompt contains a **range hint** (parsed in Phase 0 — e.g. `今日` / `上周` / `rc.20`) AND the user is invoking. Sub-mode of E2. |
+| **E5** | `cron` | Prompt contains literal `今日复盘` / `daily recap` / `daily-archive` AND no human is present (running under `/loop`, OS cron, or scheduled trigger). |
+
+##### Gate decision
+
+```
+IF context.entry_point ∈ {E2_explicit_user_invoke, E4_user_range_rollback}:
+    → gate = PROCEED       # user is live, dialogue is possible
+    → continue to Step 1 (Check coverage) below
+ELSE (E1_hook_passive | E3_ai_self_trigger | E5_cron):
+    → gate = SKIP           # no live user, onboard prompting would misfire
+    → emit one-line log: "Phase 1.5 skipped (entry=<E1|E3|E5>, no live user)"
+    → proceed directly to Phase 2
+```
+
+##### Rationale
+
+Onboard slot collection is a one-time project-tone capture flow that
+requires user dialogue. Non-user-active entries (hook / AI / cron)
+interrupt the user mid-work or run unattended where dialogue is
+impossible, so they MUST skip Phase 1.5. The S5 slot semantics
+(`tech-stack-decision`, `architecture-pattern`, ...) are user-validated
+baselines — populating them from a hook fire-and-forget or a cron daily
+recap would defeat the purpose of capturing _user-confirmed_ project
+tone.
+
+##### Tradeoff (documented in CHANGELOG)
+
+A first-time user whose ONLY invocations ever come via hook (never an
+explicit `/fabric-archive`) will not see the onboard prompt; the 5
+onboard slots remain empty. Mitigation: documentation tells users to
+run an explicit `fabric archive` at least once to populate the onboard
+baseline.
+
+##### Worked example
+
+```
+$ /loop 24h /fabric-archive 今日复盘
+  → cron context, no live user
+  → Phase 0 detects literal "今日复盘" + no-human marker
+  → context.entry_point = E5_cron
+  → Phase 1.5 Trigger Gate evaluates: E5 ∉ {E2, E4} → SKIP
+  → emit log "Phase 1.5 skipped (entry=E5, no live user)"
+  → proceed directly to Phase 2 (collect candidates for daily window)
+```
+
+Contrast with E2:
+
+```
+$ /fabric-archive
+  → user typed explicit invocation
+  → Phase 0: context.entry_point = E2_explicit_user_invoke
+  → Phase 1.5 Trigger Gate evaluates: E2 ∈ {E2, E4} → PROCEED
+  → run Step 1 (Check coverage) below
+```
+
+---
+
+After F8a removed the auto-`fabric scan` baseline pipeline, a freshly installed
+Fabric workspace ships with an EMPTY `.fabric/knowledge/` tree. Five fixed
+**S5 onboard slots** capture the "project tone" baseline that the AI needs
+for high-quality plan_context retrieval from day one:
+
+- `tech-stack-decision` — primary languages / frameworks / runtime stack
+- `architecture-pattern` — module layout, service boundaries, layering rules
+- `code-style-tone` — naming / formatting / idiom conventions the project enforces
+- `build-system-idiom` — build tool quirks, scripts, deploy pipeline shape
+- `domain-vocabulary` — business / product terminology that names code entities
+
+This phase runs ONCE per archive-skill invocation, BEFORE Phase 2 evidence
+gathering, so coverage state is fresh for the session.
+
+#### Step 1 — Check coverage
+
+Invoke `fabric onboard-coverage --json` and parse the JSON payload:
+
+```bash
+fabric onboard-coverage --json
+```
+
+Expected shape:
+
+```json
+{
+  "filled":    { "tech-stack-decision": ["KT-DEC-0012"], ... },
+  "missing":   ["architecture-pattern", "code-style-tone"],
+  "opted_out": ["domain-vocabulary"],
+  "total": 5
+}
+```
+
+#### Step 2 — Decide
+
+```
+IF missing.length === 0:
+    → skip Phase 1.5 entirely; proceed to Phase 0.
+ELSE:
+    → ask the user how to handle the missing slots (Step 3).
+```
+
+#### Step 3 — Prompt user
+
+Present a single roll-up listing each missing slot. UX i18n Policy class 5
+applies: the `header` + `question` strings are translated per
+`fabric_language`; the `options[]` routing keys stay English.
+
+```ts
+AskUserQuestion({
+  header: "Onboard coverage",  // zh-CN: "首装基调覆盖"
+  question:
+    "KB is missing the following project-tone slots: " +
+    missing.join(", ") +
+    ". Tour the project and propose pending entries for each?",
+  options: ["fill-all", "fill-each", "dismiss-all", "skip"]
+})
+```
+
+`fab_extract_knowledge` is called with `onboard_slot: <slot>` set so each
+proposed entry counts toward coverage once approved via fab_review.
+
+| User choice    | Action |
+|----------------|--------|
+| `fill-all`     | For EACH slot in `missing`, run Step 4 (Tour-and-propose). All proposals share session_id; one batch review at the end (Phase 3). |
+| `fill-each`    | Loop slot-by-slot through `missing`. Per slot: ask user `confirm | dismiss | skip` (per-slot AskUserQuestion); `confirm` → run Step 4; `dismiss` → `fabric config dismiss-slot <slot>`; `skip` → leave for next archive run. |
+| `dismiss-all`  | For EACH slot in `missing`, invoke `Bash("fabric config dismiss-slot <slot>")`. Print a one-line confirmation each. Skip to Phase 0. |
+| `skip`         | No-op. Slots remain in `missing` for the next archive run. Skip to Phase 0. |
+
+#### Step 4 — Tour-and-propose (per-slot)
+
+For each slot to fill, the LLM independently sources slot-specific evidence
+from the project (no user prompt — this is a Read-only tour):
+
+| Slot                     | Source files (LLM should Read these) |
+|--------------------------|---------------------------------------|
+| `tech-stack-decision`    | `package.json` (+ lockfile), `pyproject.toml` / `Cargo.toml` / `go.mod`, `tsconfig.json`, root README |
+| `architecture-pattern`   | Top-level dir tree (`ls -F`), 1-2 entry-point files (`src/index.ts`, `main.go`, etc.), framework-config files (`next.config`, `vite.config`, `astro.config`) |
+| `code-style-tone`        | `.editorconfig`, `prettier.config.*`, `eslint.config.*`, `biome.*`, `.prettierrc*`, framework lint config, 2-3 representative source files for naming-pattern inference |
+| `build-system-idiom`     | `package.json` `scripts` block, `Makefile`, `taskfile.yaml`, CI yml (`.github/workflows/*.yml`), Dockerfile if present |
+| `domain-vocabulary`      | README, `docs/*.md`, top-level `src/` directory names (often domain-aligned), public API entry types |
+
+After Read-ing the slot-specific sources, classify the observation:
+
+- `tech-stack-decision` → type=`decisions`, `proposed_reason=decision-confirmation`
+- `architecture-pattern` → type=`models`, `proposed_reason=new-dependency-or-pattern`
+- `code-style-tone` → type=`guidelines`, `proposed_reason=explicit-user-mark` (the project ITSELF is the mark)
+- `build-system-idiom` → type=`processes`, `proposed_reason=new-dependency-or-pattern`
+- `domain-vocabulary` → type=`models`, `proposed_reason=new-dependency-or-pattern`
+
+Call `fab_extract_knowledge` with the inferred fields PLUS `onboard_slot:
+<slot>`. The pending file's frontmatter will carry the slot label, and the
+next `fabric onboard-coverage` run will see the slot as filled (once approved
+via fab_review).
+
+Example:
+
+```ts
+mcp__fabric__fab_extract_knowledge({
+  source_sessions: ["<current-session-id>"],
+  recent_paths: ["package.json", "tsconfig.json"],
+  user_messages_summary: "Project uses TypeScript + pnpm workspace + Vitest. Node 20 LTS target. ESM-only.",
+  type: "decisions",
+  slug: "primary-tech-stack",
+  layer: "team",
+  relevance_scope: "broad",        // tech stack applies everywhere
+  relevance_paths: [],
+  proposed_reason: "decision-confirmation",
+  session_context:
+    "Session goal: capture onboard tech-stack baseline.\nTurning point: read package.json + tsconfig.json + pnpm-workspace.yaml; stack confirmed.",
+  onboard_slot: "tech-stack-decision",    // ← claims the slot
+  tech_stack: ["typescript", "nodejs", "pnpm", "vitest"]
+})
+```
+
+#### Onboard phase constraints (DO NOT TRANSLATE)
+
+- MUST run BEFORE Phase 2 evidence gathering — onboard is a separate flow,
+  not interleaved with session-archive candidates.
+- MUST call `fabric onboard-coverage --json` before deciding; never assume
+  coverage state.
+- NEVER fill a slot that is in `opted_out` — `fabric onboard-coverage` already
+  excludes those from `missing`, but the Skill MUST NOT re-propose them
+  even if the user asks "fill all of them" — the dismiss is intentional.
+- NEVER prompt the user when `missing.length === 0` — silent skip.
+- NEVER set `onboard_slot` on a regular session-archive candidate in
+  Phase 4 — that field is RESERVED for the onboard phase. Mixing the
+  two would let session-archive proposals masquerade as onboard
+  coverage and let any random pending file claim a slot.
+- MUST emit `onboard_slot: <slot>` verbatim — the slot name is one of
+  the locked S5 strings (tech-stack-decision / architecture-pattern /
+  code-style-tone / build-system-idiom / domain-vocabulary). The
+  fab_extract_knowledge schema enum will reject anything else.
+

package/templates/skills/fabric-archive/ref/phase-1-cross-session.md

@@ -0,0 +1,62 @@
+# Phase 1 — Collect Cross-Session Digests (ref)
+
+> **Loaded on demand.** SKILL.md hot path retains Phase 1's purpose statement + 5-step summary + graceful-degradation note. This file holds Steps 1-5 detailed implementation (events.jsonl tail-scan, anchor-walk, digest load, rc.25 TASK-05 ledger filter algorithm + constants + worked examples, cross-session context build).
+
+> **v2.0.0-rc.37 NEW-9 — Steps 1-4.5 moved server-side.** The deterministic part of this algorithm (events.jsonl tail-scan, anchor-find, session forward-collect, and the Step 4.5 outcome-ledger filter state machine) now runs in the server and is exposed as the `fab_archive_scan` MCP tool — call it instead of hand-running `tail`/grep. The tool returns the already-filtered `session_ids[]` + `anchor_ts` + `covered_through_ts` + `already_proposed_keys[]`. Steps 1-4.5 below remain as the AUTHORITATIVE SPEC of what the server computes (and the contract tests pin it); the Skill no longer executes them by hand. Step 5 (digest load + cross-session context stitch) stays LLM-side per Boundary B.
+
+## Step 1 — Read events.jsonl tail
+
+Use `Bash` with `tail -n 200 .fabric/events.jsonl` (tolerate ENOENT — empty ledger is a normal first-run state).
+
+## Step 2 — Find the anchor
+
+Walk the tail backwards to locate the most recent `knowledge_proposed` event (`event_type === "knowledge_proposed"`). The anchor's `ts` becomes the lower bound for digest selection. If NO anchor exists, treat all digests in the cache as in-scope.
+
+## Step 3 — Collect session_ids since anchor
+
+Scan the tail forward from the anchor and collect every distinct `session_id` field that appears on any event newer than the anchor. Distinct ordering preserved.
+
+## Step 4 — Load digests
+
+For each collected `session_id`, read `.fabric/.cache/session-digests/<session_id>.md`. Missing digest files degrade silently (the digest write was best-effort, so a Stop hook crash can produce a session_id without a digest). Cap the loaded digest set at `archive_digest_max_sessions` most-recent sessions (config-resolved, default 10) to bound LLM context (~50KB worst-case at default).
+
+## Step 4.5 — Filter via session_archive_attempted ledger (rc.25 TASK-05)
+
+Before Step 5 builds the cross-session context, drop sessions that the outcome ledger says we should not re-scan. For each `session_id` collected in Steps 1-3, scan `.fabric/events.jsonl` for events where `event_type === "session_archive_attempted"` AND `session_id` matches, keep the most-recent one by `ts`, and apply this state machine:
+
+- **(a) Look up the most recent `session_archive_attempted`** event for this `session_id` (none found → fall through to (e)).
+- **(b) `outcome === "user_dismissed"` → drop (permanent skip).** The user explicitly rejected this session's candidates; never auto-re-scan it. Respect the dismissal forever — re-scanning would re-propose the same content the user already declined.
+- **(c) `(nowMs - attempted_event.ts) < ANTI_LOOP_HOURS * 3_600_000` → drop (cooldown skip).** Anti-loop window: even if outcome is otherwise re-scannable, never re-scan a session within 12 hours of the last attempt. Aligns 心智 with the Stop-hook cooldown so a single user does not see the same session repeatedly within one work day.
+- **(d) `covered_through_ts` present → check for high-value signal in `ts > covered_through_ts` events for this `session_id`.** Tail-scan `events.jsonl` for events newer than the watermark whose `session_id` matches. A session passes this gate iff at least ONE of:
+  - ≥1 event with `event_type ∈ HIGH_VALUE_EVENT_TYPES` (`knowledge_context_planned`, `edit_paths_recorded`), OR
+  - the latest `assistant_turn_observed` event body contains ≥1 of `NORMATIVE_KEYWORDS` (substring match, case-insensitive for English entries).
+
+  No high-value signal → drop (no new content worth re-scanning, even though the cooldown has expired). Has signal → keep for re-scan.
+- **(e) Never attempted (no `session_archive_attempted` event found for this `session_id`) → keep.** First-time scan; nothing to filter against.
+- **(f) Cross-session pending dedupe** (operates on candidate observations, not on `session_id` filter): gather all `knowledge_proposed_ids` from `session_archive_attempted` events with `outcome === "proposed"` across ALL sessions in the recent window (NOT just the current candidate session). This builds a global set of idempotency keys already proposed by prior archive runs but not yet reviewed by the user (`.fabric/knowledge/pending/` may still contain them). When classifying new observations in Phase 3, drop any candidate whose computed `idempotency_key` matches an id already in this set — it was already proposed by an earlier archive run, the user just hasn't reviewed it yet, so re-proposing would duplicate pending entries and inflate `candidates_proposed` counts. Per Phase 4.5 dedupe consumer of `knowledge_proposed_ids`.
+
+The resulting filtered `session_id[]` proceeds into Step 5's digest concatenation. Sessions filtered out in this step do NOT contribute to `### Cross-session digest`, are NOT included in `source_sessions` on any fab_extract_knowledge call, and are NOT referenced in `session_context` bodies.
+
+### Constants (rc.25 — verbatim)
+
+- `ANTI_LOOP_HOURS = 12` — cooldown window in hours between consecutive re-scans of the same `session_id`. Rationale: 心智对齐 hook cooldown (`stop_hook_cooldown_hours = 12`); identical mental model avoids user confusion when a session shows up in both hook reminders and archive re-scan candidates.
+- `HIGH_VALUE_EVENT_TYPES = ['knowledge_context_planned', 'edit_paths_recorded']` — event types that count as "new substantive activity worth re-scanning" past `covered_through_ts`. Chat accumulation (`assistant_turn_observed` alone) does NOT count — it would let mere conversation noise trigger re-scans.
+- `NORMATIVE_KEYWORDS = ['以后','always','never','from now on','下次','记一下','永远不要']` — substring patterns scanned against the latest `assistant_turn_observed` body for the session. Mixed CN/EN to cover bilingual users. If any keyword hits, the session is flagged as having high-value chat-only signal even without code edits.
+
+### Worked examples
+
+- **Session X (user_dismissed)** — last `session_archive_attempted` ts = 3 days ago, outcome = `user_dismissed`. Rule (b) fires → permanent skip. Session X is dropped even if 50 new `knowledge_context_planned` events have accumulated since.
+- **Session Y (proposed 6h ago)** — last `session_archive_attempted` ts = 6h ago, outcome = `proposed`. Rule (c) fires: 6h < 12h cooldown window → drop (cooldown skip). Y becomes eligible again after the 12h window closes, provided high-value signal accumulates by then.
+- **Session Z (viability_failed 14h ago + 3 new plan_context)** — last `session_archive_attempted` ts = 14h ago, outcome = `viability_failed`, `covered_through_ts` = T₀. Rules (b)(c) pass. Rule (d) tail-scans for `session_id === Z AND ts > T₀`: finds 3 `knowledge_context_planned` events. HIGH_VALUE_EVENT_TYPES match → keep Z for re-scan. The previous viability failure does not block a re-scan once new substantive activity has accumulated.
+
+## Step 5 — Build cross-session context
+
+Concatenate the loaded digests into a single `### Cross-session digest` block to carry into Phase 2.5 + Phase 1. Use this block to:
+
+- Detect session-spanning patterns (e.g. a discussion that started in session A and continued in session B).
+- Populate the `source_sessions` array on every fab_extract_knowledge call — the array form (T5) replaces the legacy `source_session` string.
+- Inform the `session_context` blob written to each pending entry's body (3-5 lines summarizing goal + key turning point, per T6).
+
+## Graceful degradation
+
+If `.fabric/.cache/session-digests/` is missing entirely, this phase reports an empty context and Phase 2 falls back to the single-session behaviour. Tests that synthesize events.jsonl without populating the digest cache continue to work. If `session_archive_attempted` events are missing entirely (pre-rc.25 ledger or rotation has trimmed older events), treat all sessions as never-attempted (current default behavior) — Step 4.5 rule (e) applies uniformly, so the filter degrades to the legacy "scan everything since anchor" semantics without raising errors.