fix(story-mode): what the cold readers believed that was not so (review round 8)

Two agents read only the comic of the eleven recorded sessions (one who
has never written code, one engineering manager skimming), wrote down
what they believed, then compared with the transcripts. Both were misled
in the same places, and the cause was the same: the final panel kept
Claude's first sentence or two, and what a reader must not lose sat
further into its last message.

- Claude's last words now keep key sentences from anywhere in its final
  message (read in full, past the label's clip): an open problem or a
  quirk, something not yet done, checked or confirmed, work still out,
  what you asked for or expected, a correction of an earlier warning
  (with the sentence it refers to). A bare "I didn't" counts only when
  nothing stronger is there; table rows, list intros and questions never.
  "I built the pomodoro timer. Opening the page: it won't work if you
  double-click index.html…"; "…That note makes the current behaviour
  clear, but it doesn't fix it."; "As you expected, git describe --tags
  then failed because the repo has no tags."
- A turn that ended with helpers or a background command still out says
  so: "Done for now", and "Claude's part is done in 36 seconds. Its 2
  helpers finished later and reported back." (`finishedLater`).
- A failure you asked for, or that Claude said it expected, reads as the
  plan: "Test first: the first run fails as planned, the second
  passes.", "The tests don't even load, as planned." A loop that failed
  once on a test and once on another check says both, and the commits
  made inside a loop are part of its story; the final panel counts the
  turn's commits ("5 commits, uploaded").
- One or two files read are named ("Claude checks README.md." in a
  turn a report started); a tool lookup reads "Claude gets the tools it
  needs ready." again (it was overwritten) without its query; the
  advisor is "a stronger AI model", and one that answered with an error
  "gets no answer"; a commit message loses its `feat:` prefix in the
  plain caption.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Codeman maintainer committed 2026-10-18 15:17:54 +02:00
1 parent 8daa158e21
commit 6a7d8393dc
17 files changed
+372 -118

No files matched your search

@@ -11,6 +11,7 @@
"removed": 1,
"helpers": 0,
"helpersRunning": 0,
"finishedLater": 0,
"panels": [
{
"kind": "mission",
@@ -35,7 +36,7 @@
{
"kind": "backup",
"ok": null,
"story": "Claude asks the advisor for a second opinion.",
"story": "Claude asks a stronger AI model for a second opinion.",
"director": "Advisor · a second opinion",
"balloon": null,
"tests": null,
@@ -45,7 +46,7 @@
{
"kind": "loop",
"ok": true,
"story": "Fix and test, 2 rounds: 2 runs fail, then it passes.",
"story": "Fix and test, 2 rounds: a test run fails, then another check, then everything passes. Claude saves the work in 4 commits along the way.",
"director": "3 checks · 5 edits · +218 −1 · last: ok",
"balloon": "All 19 tests pass, ruff check is clean, and the output matches real wc column for column.",
"tests": {
@@ -62,7 +63,7 @@
{
"kind": "save",
"ok": true,
"story": "Claude writes 1 file and saves the work: \"chore: ignore Python and pytest caches\".",
"story": "Claude writes 1 file and saves the work: \"ignore Python and pytest caches\".",
"director": "git commit -q -m \"chore: ignore Python and pytest caches · writes 1 file",
"balloon": null,
"tests": null,
@@ -72,7 +73,7 @@
{
"kind": "backup",
"ok": null,
"story": "Claude asks the advisor for a second opinion.",
"story": "Claude asks a stronger AI model for a second opinion.",
"director": "Advisor · a second opinion",
"balloon": null,
"tests": null,
@@ -94,7 +95,7 @@
"ok": null,
"story": "Done in 3 minutes.",
"director": "turn_duration · 3 min 13 s · 13 tool calls · 3 files changed",
"balloon": "I built wcount.py and test_wcount.py.",
"balloon": "I built wcount.py and test_wcount.py. With a missing file plus a readable one, the total row didn't appear because the code counted files that could be read rather than files that were named.",
"tests": null,
"roundsOk": null,
"events": 0