sync: auto-sync from GURU-5070 at 2026-06-08 07:55:26

Author: Mike Swanson
Machine: GURU-5070
Timestamp: 2026-06-08 07:55:26

.claude/commands/save.md

@@ -68,25 +68,26 @@ When in doubt, include MORE detail — future sessions search these logs to reco
 
 ---
 
-## Phase 3 — Wiki Compile (before sync)
+## Phase 3 — Wiki: DECOUPLED (do NOT recompile inline)
 
-Fold what you just worked on into the wiki article so it ships in the **same commit** as the session log. This runs before sync and **re-synthesizes** the article (via a **Sonnet subagent** — `model: "sonnet"`, not Ollama), so new findings/patterns actually land — not just dynamic fields.
+Wiki synthesis is **decoupled from `/save`** (harness v1.2.0+, Task 2). Running a full
+Sonnet recompile inline on every save, on every machine, caused concurrent-recompile
+rebase conflicts — and once committed unresolved conflict markers into a wiki article.
+So **`/save` no longer touches the wiki**: it writes the session log and syncs, nothing
+more. Do NOT recompile the wiki here, and never block/delay the sync on wiki work.
 
-1. Derive the slug from the session-log path written in Phase 2:
-   - `clients/<slug>/session-logs/...` → client `<slug>`
-   - `projects/<project>/session-logs/...` → project article slug (e.g. `guru-rmm`, `guru-connect`)
-   - Root `session-logs/...` → **skip this phase entirely** (no single article is implied)
+To refresh the wiki for this session's work, run `/wiki-compile` **separately** — it is
+now **serialized** (per-article coord lock) and **staged** (writes a proposed update to
+`.claude/wiki_staging/` for review before it touches the live article).
 
-2. Run the `/wiki-compile` generation for that target, writing the article + updating `wiki/index.md`, but **stop before its commit/push step** — `sync.sh` (Phase 4) commits everything together in one commit:
-   - **Article exists** → **full recompile** (`/wiki-compile <type>:<slug> --full`): the Sonnet subagent re-synthesizes, **preserving Patterns and History verbatim** (unless the new session log shows an item resolved) and refreshing everything else, absorbing this session's work. Clients also refresh live Syncro fields (hours, tickets).
-   - **No article yet** → **seed** (full synthesis) to create it.
-   - The main agent reviews the subagent's draft before writing — verify IPs/paths; never invent vault paths (use `(verify)`); keep billing fields Syncro-authoritative.
+After the sync completes, derive the slug from the session-log path (Phase 2) and emit
+the exact command for the operator to run when ready:
+- `clients/<slug>/session-logs/...` → `[INFO] Wiki decoupled — run: /wiki-compile client:<slug> --full  (serialized + staged)`
+- `projects/<project>/session-logs/...` → `[INFO] Wiki decoupled — run: /wiki-compile project:<slug> --full  (serialized + staged)`
+- Root `session-logs/...` → no single article implied; emit nothing.
 
-3. **Softfail (critical) — a wiki failure must NEVER block the save:**
-   - If the synthesis subagent fails or is unavailable, fall back to a surgical **refresh** (bump `last_compiled` + `sources`; refresh client Syncro fields) so the article still records the session, and emit `[WARN] wiki refreshed, not recompiled; run /wiki-compile --full later`.
-   - Any other failure: log it and continue to sync.
-
-The article + `wiki/index.md` are committed alongside the session log by `sync.sh` (Phase 4).
+The session log + `sync.sh` are the durable record; the wiki is refreshed deliberately,
+not on every save.
 
 ---
 

.claude/commands/wiki-compile.md

@@ -342,12 +342,33 @@ If the subagent is unavailable, the main agent writes the article directly using
 
 ---
 
-## Phase 5 — Write Article + Update Index
+## Phase 5 — Serialize, Stage, Review, Apply (Task 2)
 
-**Write the article:**
-- Seed: write `wiki/clients/<slug>.md` from generated content
-- Full: overwrite `wiki/clients/<slug>.md`
-- Refresh: edits already applied in Phase 4
+Wiki writes are SERIALIZED + STAGED so two machines never recompile the same article
+into a conflict, and no synthesis lands in the live article without a review.
+
+**5.0 Claim a per-article coord lock** (via the `coord` skill):
+`lock claim claudetools wiki/<type>/<slug> "wiki-compile <slug>" --ttl 1`.
+- The TTL auto-evicts a dead session's lock (no permanent stranding).
+- If the lock is **already held** → emit `[SKIP] wiki/<type>/<slug> is being compiled on
+  another machine; try again shortly` and exit cleanly.
+- If **coord is unreachable** → emit `[WARN] coord down — proceeding without lock` and continue.
+- RELEASE the lock in 5.3 — and on ANY error/abort before then.
+
+**5.1 Write the synthesized article to STAGING, not the live tree:**
+- Staging path: `.claude/wiki_staging/<type>-<slug>.md` (`mkdir -p .claude/wiki_staging`).
+  Write the generated/recompiled article THERE. Do NOT touch `wiki/...` yet.
+
+**5.2 Review the staged diff (NO blind merge):**
+- `diff -u "<live wiki path>" ".claude/wiki_staging/<type>-<slug>.md" | head -120` (or
+  `(new article)` if none). The main agent reviews: Patterns/History preserved on full
+  recompile, IPs/paths/vault-paths accurate, billing Syncro-authoritative, NO structural
+  corruption or duplicated headers. If the diff looks wrong → STOP, fix the staged file or
+  abort (release the lock); do not apply.
+
+**5.3 Apply the staged article to the live tree** (then index + commit in Phase 6):
+- `cp .claude/wiki_staging/<type>-<slug>.md <live wiki path>` (seed/full); refresh edits
+  already applied in Phase 4 still go via this staging review.
 
 **Update `wiki/index.md`:**
 - Check if `wiki/clients/<slug>.md` is listed in the Clients table
@@ -366,7 +387,11 @@ If the subagent is unavailable, the main agent writes the article directly using
 cd "$CLAUDETOOLS_ROOT"
 git add "wiki/clients/${SLUG}.md" wiki/index.md
 git commit -m "wiki: compile ${SLUG} (${MODE})"
+git fetch origin && git rebase origin/main   # serialized, but rebase defensively
 git push origin main
+# Release the per-article lock and clear staging (ALWAYS — even on an earlier abort):
+$PY "$CLAUDETOOLS_ROOT/.claude/skills/coord/scripts/coord.py" lock release claudetools "wiki/${TYPE}/${SLUG}" 2>/dev/null || true
+rm -f "$CLAUDETOOLS_ROOT/.claude/wiki_staging/${TYPE}-${SLUG}.md"
 ```
 
 Emit:

.claude/harness/CHANGELOG.md

@@ -17,3 +17,10 @@ or old harness during a heterogeneous rollout. See
 - Task 4: `harness-guard.sh` wired into `sync.sh` pre-commit, WARN-ONLY (logs conflict
   markers / unencrypted sops / private keys to .claude/harness/guard.log; does not block
   unless HARNESS_GUARD_FATAL=1; SKIP_HARNESS_GUARD=1 bypasses).
+
+## 1.2.0 — 2026-06-08
+- Task 2: wiki synthesis DECOUPLED from /save (the concurrent-recompile conflict source).
+  /save now only writes the log + syncs and emits the exact /wiki-compile command to run.
+  /wiki-compile is now SERIALIZED (per-article coord lock, TTL orphan-evict, coord-down =
+  warn+proceed) and STAGED (writes .claude/wiki_staging/<type>-<slug>.md -> review diff ->
+  apply to live -> commit -> release lock). No blind background auto-merge.

.claude/harness/VERSION

@@ -1 +1 @@
-1.1.0
+1.2.0

.claude/wiki_staging/README.md

@@ -0,0 +1,6 @@
+# wiki_staging
+
+Transient staging for `/wiki-compile` (Task 2 of the harness-optimization spec). The
+synthesized article is written here FIRST, the diff vs the live `wiki/` article is
+reviewed, and only then applied to the live tree and committed. Staged `*.md` files are
+gitignored and removed after apply — nothing here is canonical.