fix(story-mode): files written in Bash, the advisor, and honest checks, from review round 2

- Files a Bash call writes through here-documents (`cat > f <<'EOF'`, `tee`)
  are whole-file edits on the event: in the diff drawer, on the code page,
  in "N files changed". Before, a worker that wrote seven files that way
  drew a page with zero files changed. Labels leave the bodies out (the wire
  row was a wall of file text), and a relative target resolves against the
  transcript line's cwd unless the command changed directory first.
- A caption names the part of a one-liner that decided it (`node --test`,
  the commit), not its first line.
- The advisor (a server tool, answer encrypted in the transcript) is drawn:
  "Claude asks the advisor for a second opinion." It is not counted as a
  helper. Server web search maps to the web panel.
- Checks that all pass from the start read "Build and test, N rounds. Every
  check passes.", not as fixing.
- pytest's collection errors are counted apart: "The tests don't even load."
- A result remark replaces a step announcement on its check.
- A turn still open when the next prompt starts has ended; an interrupted
  turn is timed by its span.
- The mission drawer keeps prompts up to 4000 characters.
- Drawer: diff headers, titles and commands read relative to the session
  folder (the folder itself reads "."); a bare name under an `ls dir:`
  header links into that folder; the chosen answer is marked, not struck
  through; boards count errors.
- While a question waits, the pencils say "Waiting for your answer…";
  balloons start below the LIVE tag; the loop's balloon points at its
  verdict, above the board.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

docs/api-reference.md

@@ -1067,7 +1067,7 @@ Responses carry a weak `ETag` with `Cache-Control: no-cache`; a request with a m
 
 A `page` carries the turn's summary fields plus `events` (one per prompt, sentence Claude wrote and tool call, with `intent`, `ok` when the call returned, `edit` hunks in Claude Code's own `structuredPatch` shape, the tail of `output`, `helper`, `tests` counts, and `files` for the files a Bash call printed with `cat`/`head`/`tail`, as the command named them), `panels` (each `{ kind, events, caption: { story, director }, balloon?, files?, ... }`, at most 12 per page, indices into `events`), `filesChanged`, `added`, `removed`, `helpers`, `helpersRunning`, `partial` (the turn began before the part that was read) and `truncated` (older outputs were dropped to keep the page small). A transcript that cannot be read is a `500` with `OPERATION_FAILED`.
 
-A helper started in the background (`helper.background`) carries `helper.running: true` until its `<task-notification>` arrives; that notification starts a turn of its own (origin `task`), whose prompt event carries the helper's answer as `output`, and the answer, tool count and duration are joined back onto the helper in the turn that started it. Claude Code times such a turn from the prompt that started the chain; Story Mode caps a turn's `durationMs` at the turn's own span. A helper started as a teammate (`status: teammate_spawned`) is a background helper too, and its `<teammate-message>` reports join it by name. A prompt that arrives while Claude works (typed, a background job's report, a message from another session) is written by current Claude Code builds as a `queued_command` attachment, not a user line; it joins the running turn, a prompt event carrying `origin` (`human`, `task`, `peer`, `system`), and a report that lands mid-turn is an event with intent `notice` rather than a new mission panel. A turn ends at `turn_duration`, or at the Stop hook's `stop_hook_summary` (unless it prevented the stop) in sessions that never write `turn_duration`, timed then by its own span.
+A helper started in the background (`helper.background`) carries `helper.running: true` until its `<task-notification>` arrives; that notification starts a turn of its own (origin `task`), whose prompt event carries the helper's answer as `output`, and the answer, tool count and duration are joined back onto the helper in the turn that started it. Claude Code times such a turn from the prompt that started the chain; Story Mode caps a turn's `durationMs` at the turn's own span. A helper started as a teammate (`status: teammate_spawned`) is a background helper too, and its `<teammate-message>` reports join it by name. A prompt that arrives while Claude works (typed, a background job's report, a message from another session) is written by current Claude Code builds as a `queued_command` attachment, not a user line; it joins the running turn, a prompt event carrying `origin` (`human`, `task`, `peer`, `system`), and a report that lands mid-turn is an event with intent `notice` rather than a new mission panel. A Bash call that writes files through here-documents (`cat > f <<'EOF'`) carries them as `edits` (whole-file edits, counted in `filesChanged`), and its label leaves the bodies out; `headline` is the part of a one-liner that decided its intent. The advisor (a server tool) is an event with tool `Advisor` and intent `helper`; its answer is encrypted in the transcript. `tests` may carry `errors` (pytest's collection errors). A turn ends at `turn_duration`, or at the Stop hook's `stop_hook_summary` (unless it prevented the stop) in sessions that never write `turn_duration`, timed then by its own span.
 
 ## Git worktrees of a case