fix(story-mode): Claude's last words keep the sentences aimed at you (review round 9)

Two fresh cold readers (the person who asked for the work, a newcomer to
the project) found the round-8 balloons still cut exactly where Claude
turns from describing to asking, offering or warning: "Want me to add
that?", "I can fix the number format whenever you want", the
http.server instruction, the fix that followed a reported bug.

Key sentences are now picked by kind, one of each, at most three, and
shown in the order Claude wrote them: a problem left (with the fix right
after it, when there is one, so it never reads as open), a question or
offer, how to use what was built, something not done or checked yet, a
step that failed, a word on what you asked for, a corrected warning. A
list intro is judged on its own words and brings its first items; a
pointer ("described below") is skipped; a short offer brings what
"that" was.

The final panel reads "Done, with a catch" for a problem left, "Done,
with a note" for something pending, and "Done, with a question" when
the next move is yours (`openNote` is now 'catch' | 'note'; `asks`).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Codeman maintainer committed 2026-10-18 15:41:57 +02:00
1 parent 9c81e4c425
commit 59d70caeb3
17 files changed
+202 -77

No files matched your search

+1 -1
View File
@@ -1074,7 +1074,7 @@ A turn is one prompt and everything Claude did for it. `origin` says who sent th
### Background work
A helper started in the background (`run_in_background`, or as a teammate: `status: teammate_spawned`) has `helper.background` and `helper.running: true` until it reports back. A `<task-notification>` (matched by tool call) or a `<teammate-message>` (matched by name) joins the answer, tool count and duration back onto the helper in the turn that started it. A report that arrives after that turn ended starts a turn of its own (origin `task`) whose prompt event carries the report as `output` and the helper as `helper`; one that lands mid-turn is an event with intent `notice` instead of a new mission. `page.helpersRunning` counts the helpers still out, and `page.finishedLater` the helpers and background commands that finished only after their turn ended (each such event carries `finishedLater: true`); the final panel then says so instead of a clean finish. `page.openNote` says Claude's last words name an open problem or something not done or checked (one of its `keyPoints`), so that panel is not a celebration either.
A helper started in the background (`run_in_background`, or as a teammate: `status: teammate_spawned`) has `helper.background` and `helper.running: true` until it reports back. A `<task-notification>` (matched by tool call) or a `<teammate-message>` (matched by name) joins the answer, tool count and duration back onto the helper in the turn that started it. A report that arrives after that turn ended starts a turn of its own (origin `task`) whose prompt event carries the report as `output` and the helper as `helper`; one that lands mid-turn is an event with intent `notice` instead of a new mission. `page.helpersRunning` counts the helpers still out, and `page.finishedLater` the helpers and background commands that finished only after their turn ended (each such event carries `finishedLater: true`); the final panel then says so instead of a clean finish. `page.openNote` says Claude's last words leave something open, from its `keyPoints`: `catch` (a problem left) or `note` (something not done, checked or confirmed yet); that panel is not a celebration either. `page.asks` says they ask you something or offer more: the next move is yours.
A Bash call sent to the background (its result is only `Command running in background with ID: …`) has `running: true` and no `ok`: it started, nothing more is known, and its `output` says so instead of carrying the launch note meant for Claude. Its `<task-notification>` settles `ok` from the exit code in the summary (the `output` then names the exit code, and `background: true` stays, so the page says the run happened in the background), and reading the job's output file later is a test run when that output reports test counts.