M3: complete non-destructive history and active-head export

The head-cursor model landed in 903fa7a and stopped there: the backend
moved the head instead of deleting turns, but a bundle still reopened at
its newest row, the browser had no way forward, and five inherited tests
still asserted the contract Undo had just stopped honouring. This is the
rest of the milestone, plus the one unsafe operation the review found.

Export now writes headDepth, and it belongs on the other side of the rule
app/bundle.py states about itself. The head depth used to be derived —
the tip of the head branch, a fact about the nodes that arrived with it —
and that was true while Undo deleted, because the newest row was the only
place a story could be read. It is a decision now: the same tree exports
identically whether the user undid three turns or none, so the file has
to say. An import that ignored it would silently Redo the story to its
newest retained turn, which is the Phase 0B export finding this milestone
exists to close. A file with no headDepth is opened at the tip, which is
not a fallback but the position such a file recorded; a file naming a
depth its own rows do not reach is refused in plan(), before a row is
written, for the reason that module gives about half-written trees.

Which branches the story has left goes into the file for the same reason.
Every row of an abandoned line arrives on an import either way, so the
disposition is the only thing telling it apart from an active one, and a
restored backup that had lost it would have nothing for the later cleanup
and recovery screens to select on. Both keys or neither: a time with no
depth cannot say what was displaced.

The browser gets a Redo button beside Undo, on Ctrl+Shift+Z, and both are
enabled from can_undo/can_redo rather than from the transcript. Neither
is derivable on the client — Undo stops at the campaign opening, which
may be off the top of the loaded window, and Redo depends on the retained
future, which the client is never sent — so the flags now ride on every
window the server hands back, including a scrolled-up page and the
response to an import. Moving the head also refreshes the state panels,
which undo never did: it has rolled the world state back since long
before M3 and the drawer kept showing the old numbers.

An in-place edit is now refused when story descends from the turn and is
not on screen. Editing rewrites one row and re-evaluates nothing, which
is what makes it a correction rather than a continuation, and that is
harmless while everything below the turn is visible — the reader can see
what their change has to agree with. It stops being harmless when the
continuation is undone, or was left behind by a divergence, because the
edit then silently changes the words an invisible stretch of story was
written from. That was the one way M3's retained history could be made to
contradict itself. Refusing is deliberately the whole of the fix: making
such an edit fork is STORY-BRANCH-SEMANTICS.md §14-15, and §15 wants the
state the edited prose implies re-evaluated, which is M5's extraction
pass. The requirement is not weakened, only deferred, and §14A now says
so.

The predicate asks one question rather than two. A descendant is
invisible either because it is past the head on this lineage or because
it is past a fork on a branch the story left, and both are "a live node,
deeper than this one, descending from it, off the path being read". A
first attempt scoped the search to branches other than the active one and
failed the divergence case, correctly: the departed branch is usually an
ancestor of the branch now being read. Only the deepest live node on each
descending branch is examined, because visibility is monotone in depth.

Five inherited tests are rewritten rather than deleted, because what they
were protecting is still worth protecting and only the mechanism changed.
The undo-state pair keeps its state assertions and swaps "the rows are
gone" for "the rows are all here and the story is read from earlier". The
memory test stops asserting that undo prunes memories and starts
asserting the property that replaced it: a memory past the head is
unreachable, still on disk, and retrievable again after Redo, with no
re-embedding. The attempt-group test still proves the group moves as one,
out of the story rather than out of the database. And the fork test
reverses: Undo used to refuse at a fork point because it deleted rows the
parent branch was also reading, and with nothing deleted there is nothing
to protect the parent from, so it now walks into the story the branch
inherits and stops at the campaign opening instead.

tests/test_head_cursor.py is the milestone's acceptance contract, named
by the items it discharges: D01-D10, E01-E04, I01-I03, I07, L01-L02, and
the invariant they all rest on — Undo deletes zero accepted turns,
asserted on row ids over the whole retained tree. E02 has both controls,
because a negative control alone would pass if memory retrieval were
simply broken. L01 records what it does not claim: the head does move by
one on a failed turn, onto the player's retained input, which is A05
rather than a gap. Two of the edit-guard tests exist to prove the guard
stays out of the way — a correction at the tip and a correction mid-story
with everything visible must both still work.

638 backend tests pass. Frontend lint is unchanged at seven pre-existing
warnings, none in the files touched; the bundle builds at 395.85 kB; the
production image builds.

Verified at runtime against the trusted-LAN Ollama over HTTPS: three
turns, two Undos, a Redo, a Retry, an Undo, a divergent continuation,
Redo correctly refused with 400, Undo back to the opening, export, a
process restart that reopened the campaign still undone, and an import
that opened at the same position with its retained future intact. The
browser click-through of that sequence has not been run — no session in
this milestone had a browser to drive — so the Redo control itself is
verified by its endpoint and its lint and build, not by a click.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QF5TcoB86QADgjHz1GZe8u

backend/app/head.py

@@ -228,6 +228,73 @@ def can_undo(db: Session, adventure: models.Adventure) -> bool:
     return undo_target(db, adventure) is not None
 
 
+def displaced_history_under(
+    db: Session, adventure: models.Adventure, node: models.Action
+) -> bool:
+    """Returns whether story the reader cannot see descends from `node`.
+
+    This is the question an in-place edit has to ask. Editing rewrites one row
+    and re-evaluates nothing, which is what makes it a correction rather than a
+    new continuation. That is harmless while everything descending from the row
+    is on screen: the reader can see what their correction has to stay
+    consistent with. It stops being harmless the moment a continuation descends
+    from the row and is *not* on screen, because the edit then silently changes
+    the words an invisible stretch of story was written from. That is the one
+    way M3's retained history can be made to contradict itself.
+
+    Refusing is deliberately the whole of the fix. Making such an edit fork, so
+    the original text and its future stay whole, is
+    `STORY-BRANCH-SEMANTICS.md` §14-15 — and §15 requires re-evaluating the
+    state the edited prose implies, which is M5's extraction pass. Neither is
+    started here.
+
+    The question is asked as one shape rather than two, because the two ways a
+    descendant becomes invisible turn out to be the same fact. An undone future
+    sits past the head on this very lineage; a displaced line sits past a fork
+    on a branch the story left. In both cases there is a live node, deeper than
+    this one, that descends from it and is not on the path being read — and the
+    departed branch is usually an *ancestor* of the branch now being read, which
+    is why "branches other than the active one" is the wrong set to look at.
+
+    Only the deepest live node on each descending branch is examined. Whether a
+    node is on the read path is monotone in depth: a branch is on the path with
+    a cap, and a node is visible when its depth is at or under that cap. So if
+    the deepest one is visible, every shallower one is too, and if it is not,
+    the answer is already yes.
+
+    A node that is not live has no descendants of its own — a take the story
+    moved past keeps a continuation only by being forked, and that fork is a
+    branch this loop asks about anyway — so editing one is always safe.
+    """
+    if not node.live or node.depth is None:
+        return False
+    read = lineage.path_of(db, adventure)
+    branches = (
+        db.query(models.Branch)
+        .filter(models.Branch.adventure_id == adventure.id)
+        .all()
+    )
+    for branch in branches:
+        # Uncapped: the question is what this branch's story descends from, not
+        # how much of it the reader is currently being shown.
+        if not lineage.Path(lineage.entries_of(branch)).contains(node):
+            continue
+        deepest = (
+            db.query(models.Action)
+            .filter(
+                models.Action.adventure_id == adventure.id,
+                models.Action.branch_id == branch.id,
+                models.Action.live.is_(True),
+                models.Action.depth > node.depth,
+            )
+            .order_by(models.Action.depth.desc(), models.Action.id.desc())
+            .first()
+        )
+        if deepest is not None and not read.contains(deepest):
+            return True
+    return False
+
+
 # ------------------------------------------------------------------ writing
 
 def move_to(db: Session, adventure: models.Adventure, depth: int) -> None: