1 files changed, 183 insertions, 19 deletions

diff --git a/src/core/chunks/selectors.ts b/src/core/chunks/selectors.ts
index b507cf7..8d32fcf 100644
--- a/src/core/chunks/selectors.ts
+++ b/src/core/chunks/selectors.ts
@@ -27,15 +27,163 @@ function sameChunk(p: ProvisionalChunk, c: StoredChunk): boolean {
 }
 
 /**
+ * A committed chunk with no live-event counterpart, so a late-join replay can
+ * never contain it: an image persisted into the turn's history (pasted-image
+ * openings, images a tool attaches mid-turn). Alignment steps over it.
+ */
+function replayless(c: StoredChunk): boolean {
+  return c.chunk.type === "image";
+}
+
+/** Where an alignment walk stopped, and whether it stopped on a mismatch. */
+interface Walk {
+  /** First provisional index NOT matched. */
+  readonly p: number;
+  /** First committed index NOT matched (replayless chunks stepped over). */
+  readonly c: number;
+  readonly matched: number;
+  /** Ended because a side ran out — no mismatch. */
+  readonly complete: boolean;
+}
+
+/**
+ * How many consecutive committed chunks starting at `c` one provisional text /
+ * thinking chunk stands for: their texts must concatenate EXACTLY to its text
+ * (≥ 2 chunks; 0 = no such run). A provider may return several blocks in one
+ * step (Claude emits multiple thinking blocks, each with its own signature)
+ * which history persists as separate chunks, while the delta stream carries
+ * no block boundary — so live (and in the replay) they arrive merged.
+ */
+function mergedRun(
+  state: TranscriptState,
+  text: string,
+  kind: string,
+  role: string,
+  c: number,
+): number {
+  let joined = "";
+  for (let k = c; k < state.committed.length; k++) {
+    const row = state.committed[k];
+    if (row === undefined || row.role !== role || row.chunk.type !== kind) return 0;
+    if (row.chunk.type !== "text" && row.chunk.type !== "thinking") return 0;
+    joined += row.chunk.text;
+    if (joined === text) return k - c + 1 >= 2 ? k - c + 1 : 0;
+    if (!text.startsWith(joined)) return 0;
+  }
+  return 0;
+}
+
+/**
+ * Walk provisional (from `p`) and committed (from `c`) of turn `turnId` in
+ * lockstep, stepping over committed chunks the replay cannot carry and
+ * matching one merged provisional block against its split committed run.
+ * Stops at the first mismatch or when either side runs out.
+ */
+function walk(state: TranscriptState, turnId: string, p: number, c: number): Walk {
+  let matched = 0;
+  for (;;) {
+    const prov = state.provisional[p];
+    let row = state.committed[c];
+    while (row !== undefined && replayless(row) && prov?.chunk.type !== "image") {
+      row = state.committed[++c];
+    }
+    if (prov === undefined || row === undefined) return { p, c, matched, complete: true };
+    if (prov.turnId !== turnId) return { p, c, matched, complete: false };
+    let span = sameChunk(prov, row) ? 1 : 0;
+    if (span === 0 && (prov.chunk.type === "text" || prov.chunk.type === "thinking")) {
+      span = mergedRun(state, prov.chunk.text, prov.chunk.type, prov.role, c);
+    }
+    if (span === 0) return { p, c, matched, complete: false };
+    p++;
+    c += span;
+    matched++;
+  }
+}
+
+/**
+ * Accept a re-anchored alignment. A tool chunk is a unique identity
+ * (`toolCallId`), so a match on one is trusted outright; a text-bearing match
+ * must be confirmed by the WHOLE overlap aligning (no mismatch), so a repeated
+ * text can never hide divergent content.
+ */
+function anchored(w: Walk, anchor: StoredChunk): boolean {
+  if (w.matched === 0) return false;
+  return w.complete || anchor.chunk.type === "tool-call" || anchor.chunk.type === "tool-result";
+}
+
+/**
+ * Align the provisional run with the committed run of turn T (which begins at
+ * committed index `start`). Returns how many leading provisional chunks are
+ * hidden as already committed, and the walk's end.
+ *
+ * Normally both start at the turn's opening. But the chat-limit window (fresh
+ * load `?limit=` / `windowTranscript`) and `trimTranscript` unload the OLDEST
+ * committed chunks, so in a long in-flight turn the committed run is a SUFFIX
+ * of the turn while the late-join replay re-delivers the whole turn from its
+ * `turn-start`: re-anchor on the committed head inside the replay, and hide
+ * the replayed chunks before it too (persisted history, unloaded — pageable
+ * via "Show earlier"). Conversely, provisional overflow trimming can leave the
+ * replay starting after the committed head: re-anchor on the replay's head
+ * inside the committed run. Unverifiable → the plain prefix walk (fail-safe:
+ * a misalignment shows a duplicate, never hides content).
+ */
+function align(state: TranscriptState, turnId: string, start: number): Walk {
+  const direct = walk(state, turnId, 0, start);
+  // Aligned from the turn's head (or fully consistent): plain prefix semantics.
+  if (direct.complete || direct.matched > 0) return direct;
+  let headAt = start;
+  while (
+    state.committed[headAt] !== undefined &&
+    replayless(state.committed[headAt] as StoredChunk)
+  )
+    headAt++;
+  // Anchor on the committed head — or, when the head is unmatchable (e.g. the
+  // window cut between two blocks a merged provisional chunk spans), on the
+  // run's first tool chunk, a unique identity.
+  const anchorsAt = [headAt];
+  for (let i = headAt + 1; i < state.committed.length; i++) {
+    const t = state.committed[i]?.chunk.type;
+    if (t === "tool-call" || t === "tool-result") {
+      anchorsAt.push(i);
+      break;
+    }
+  }
+  for (const at of anchorsAt) {
+    const head = state.committed[at];
+    if (head === undefined) continue;
+    for (let k = 1; k < state.provisional.length; k++) {
+      const p = state.provisional[k];
+      if (p?.turnId !== turnId || !sameChunk(p, head)) continue;
+      const w = walk(state, turnId, k, at);
+      if (anchored(w, head)) return w;
+    }
+  }
+  const p0 = state.provisional[0];
+  if (p0 !== undefined) {
+    for (let j = headAt + 1; j < state.committed.length; j++) {
+      const row = state.committed[j];
+      if (row === undefined || !sameChunk(p0, row)) continue;
+      const w = walk(state, turnId, 0, j);
+      if (anchored(w, row)) return w;
+    }
+  }
+  return direct;
+}
+
+/**
  * How many LEADING provisional chunks are already backed by committed chunks.
  *
  * The backend persists each step of an in-flight turn as it completes (CR-6),
  * so a client that opens a conversation mid-turn gets those steps from history
  * AND again from the late-join event replay (as provisional chunks). Both
  * carry the turn's chunks in the same order, so the provisional run of turn T
- * is aligned position-by-position with the committed run of turn T. Skip the
- * aligned prefix; stop at the first mismatch (fail-safe: a misalignment shows
- * a duplicate, never hides content).
+ * is aligned chunk-by-chunk with the committed run of turn T (see `align`).
+ * Skip the aligned prefix; stop at the first mismatch.
+ *
+ * A failed alignment renders the ENTIRE replay as a duplicate — and because
+ * tool cards de-dup by `toolCallId` onto the first (committed) occurrence,
+ * that duplicate tail shows only thinking/text blocks ("the tool calls
+ * disappear"). Hence the re-anchoring and the replayless-image stepping.
  *
  * Also reports whether the ACCUMULATING chunk is already committed (the step
  * completed + history synced, but the next live event hasn't flushed it yet).
@@ -48,31 +196,47 @@ function committedOverlap(state: TranscriptState): { skip: number; hideAccumulat
   // The committed run for this turn (contiguous at the tail of `committed`).
   let start = state.committed.length;
   while (start > 0 && state.committed[start - 1]?.turnId === turnId) start--;
-  const run = state.committed.length - start;
-  if (run === 0) return { skip: 0, hideAccumulating: false };
-
-  let skip = 0;
-  while (skip < state.provisional.length && skip < run) {
-    const p = state.provisional[skip];
-    const c = state.committed[start + skip];
-    if (p === undefined || c === undefined || p.turnId !== turnId || !sameChunk(p, c)) break;
-    skip++;
-  }
+  if (start === state.committed.length) return { skip: 0, hideAccumulating: false };
+
+  const end = align(state, turnId, start);
+  const skip = end.p;
 
   let hideAccumulating = false;
   const acc = state.accumulating;
-  if (acc !== null && acc.turnId === turnId && skip === state.provisional.length && skip < run) {
-    const c = state.committed[start + skip];
+  if (acc !== null && acc.turnId === turnId && skip === state.provisional.length) {
+    let next = end.c;
+    while (state.committed[next] !== undefined && replayless(state.committed[next] as StoredChunk))
+      next++;
+    const c = state.committed[next];
     hideAccumulating =
-      c !== undefined &&
-      c.role === "assistant" &&
-      c.chunk.type === acc.kind &&
-      c.chunk.text === acc.text;
+      (c !== undefined &&
+        c.role === "assistant" &&
+        c.chunk.type === acc.kind &&
+        c.chunk.text === acc.text) ||
+      mergedRun(state, acc.text, acc.kind, "assistant", next) > 0;
   }
   return { skip, hideAccumulating };
 }
 
 /**
+ * How many chunks `selectChunks` would render, without materializing them.
+ * Provisional chunks hidden as history-backed / replay duplicates of committed
+ * chunks are NOT counted — the chat limit bounds what is on screen, and
+ * counting invisible duplicates would unload real history to make room for them.
+ */
+export function selectRenderedCount(state: TranscriptState): number {
+  const backed = historyBackedProvisional(state);
+  const { skip, hideAccumulating } = committedOverlap(state);
+  let count = state.committed.length;
+  for (let i = skip; i < state.provisional.length; i++) {
+    const p = state.provisional[i];
+    if (p !== undefined && !backed.has(p)) count++;
+  }
+  if (state.accumulating !== null && !hideAccumulating) count++;
+  return count;
+}
+
+/**
  * Select all chunks for rendering: committed first (seq order),
  * then provisional (seq: null), excluding history-backed identities. Unknown
  * accumulating content stays live, even if its text equals an earlier step.