docs(dsh): живая проверка guard, require-plan и bootstrap

docs/superpowers/plans/2026-10-24-dsh-port-spike.md

@@ -36,8 +36,13 @@
 - [x] `dsh/install.sh`, `mcp.codegraph.yml`, README/PORT.
 - [x] `bash dsh/tests/run.sh` — 25 тестов зелёные.
 - [x] `bash tests/run.sh` — 630 тестов зелёные (регрессий нет).
-- [ ] Живая проверка в DSH: маркер, guard на main, `/role`, acceptance
+- [x] Живой `guard-main`: `write` и `bash` на main → `BLOCKED`.
-      superpowers.
+- [x] Живой `require-plan`: `src/probe.ts` без `.bounded` → `BLOCKED`;
+      с `.bounded` → разрешено.
+- [x] Bootstrap: marker `6b676dd9bb8a0234` пришёл в контекст сессии.
+- [ ] `/role dev` — проверить в UI.
+- [ ] Acceptance superpowers в чистой сессии.
+- [ ] `/compact` → повторный bootstrap.
 - [ ] Решение по SDD (async controller vs workflow).
 
 ## Acceptance

dsh/PORT.md

@@ -1,6 +1,7 @@
 # DSH port — design and spike notes
 
-Status: **spike 0.1.0, live verification pending**. This directory is the
+Status: **spike 0.1.0, live guard/require-plan/bootstrap verified; `/role` and
+fresh-session acceptance pending**. This directory is the
 DeepSeek Harness adapter for `claude-harness`; the Claude Code installation and
 the repository's source of truth are unchanged.
 
@@ -200,6 +201,20 @@ Live checks:
    `<!-- DSH-HARNESS-BOOTSTRAP:<hash> -->`; after compaction a new marker is
    appended.
 
+Verified live on 2026-10-24 in the desktop profile:
+
+- the bootstrap marker `<!-- DSH-HARNESS-BOOTSTRAP:6b676dd9bb8a0234 -->` and the
+  full `using-superpowers` body arrived in a fresh session, and the skill
+  catalog showed the superpowers skills;
+- `write` to a file on `main` returned `BLOCKED [guard-main]`;
+- a Bash redirect write on `main` returned `BLOCKED [guard-main]`;
+- a `write` on a feature branch was allowed;
+- `write` to `src/probe.ts` on the branch returned `BLOCKED [require-plan]`,
+  and the same write succeeded after creating `.bounded`.
+
+Still pending: `/role dev`, the fresh-session "react todo list" acceptance, and
+re-injection after `/compact`.
+
 Automated tests:
 
 ```bash
@@ -235,11 +250,11 @@ profile was removed; the real `desktop` profile was not touched.
   cwd resolution async, the adapter needs a `tools/pre-execute` fallback. The
   guard is global and monotonic; it runs after `tools/pre-execute`, so an earlier
   user approval cannot turn a `guard-main` denial back into permission.
-- **`agent/pre-step` injection.** The code follows the shipped skill-catalog
+- **`agent/pre-step` injection.** Verified live: the bootstrap marker and body
-  pattern (`next()` then append `messages`), but the live behavior of
+  arrived in a fresh session, and the skill catalog showed the superpowers
-  `createUserMessage({source:{kind:"user"}})` in a host bundle still needs a
+  skills. The local `createUserMessage` copy works with `source.kind: "user"`,
-  smoke test. The source kind is intentionally `user` to avoid an unknown
+  which avoids an unknown session source variant. Re-injection after compaction
-  session source variant.
+  is still pending.
 - **Subagent bootstrap.** `isSubagent` probes common fields; if none are present
   on this version, the bootstrap reaches children too. The skill's
   `<SUBAGENT-STOP>` makes that harmless but token-expensive.
@@ -254,7 +269,8 @@ profile was removed; the real `desktop` profile was not touched.
 
 ## 8. Next phases
 
-1. Live smoke test in DSH: guard, bootstrap marker, `/role`.
+1. Finish the live smoke test: `/role dev`, the fresh-session superpowers
+   acceptance, and bootstrap re-injection after `/compact`.
 2. Add `harness-check` and optional `role-hint` as non-blocking pre-step
    injections.
 3. Build `briefing` as an agent preset (read-only tools + model route).