feat(tool-call-cards): pair calls and results in summarized collapsible bubbles

3 files changed, 134 insertions, 226 deletions

diff --git a/src/core/chunks/groups.test.ts b/src/core/chunks/groups.test.ts
index db632a3..cc2aa40 100644
--- a/src/core/chunks/groups.test.ts
+++ b/src/core/chunks/groups.test.ts
@@ -3,16 +3,16 @@ import { describe, expect, it } from "vitest";
 import { groupRenderedChunks } from "./groups";
 import type { RenderedChunk } from "./types";
 
-const text = (seq: number, role: Role, t: string, provisional = false): RenderedChunk => ({
+const text = (seq: number, role: Role, t: string): RenderedChunk => ({
   seq,
   role,
   chunk: { type: "text", text: t },
-  provisional,
+  provisional: false,
 });
-
 const call = (seq: number, id: string, stepId?: string, provisional = false): RenderedChunk => ({
   seq,
   role: "assistant",
+  provisional,
   chunk: {
     type: "tool-call",
     toolCallId: id,
@@ -20,12 +20,11 @@ const call = (seq: number, id: string, stepId?: string, provisional = false): Re
     input: { id },
     ...(stepId !== undefined ? { stepId: stepId as StepId } : {}),
   },
-  provisional,
 });
-
 const result = (seq: number, id: string, stepId?: string, provisional = false): RenderedChunk => ({
   seq,
   role: "tool",
+  provisional,
   chunk: {
     type: "tool-result",
     toolCallId: id,
@@ -34,165 +33,120 @@ const result = (seq: number, id: string, stepId?: string, provisional = false):
     isError: false,
     ...(stepId !== undefined ? { stepId: stepId as StepId } : {}),
   },
-  provisional,
 });
 
+function toolGroups(rows: readonly RenderedChunk[]) {
+  return groupRenderedChunks(rows).map((g) => {
+    if (g.kind !== "tool") throw new Error("expected a tool group");
+    return g;
+  });
+}
+
 describe("groupRenderedChunks", () => {
   it("returns no groups for an empty stream", () => {
     expect(groupRenderedChunks([])).toEqual([]);
   });
-
-  it("passes non-tool chunks through as single groups, in order", () => {
-    const groups = groupRenderedChunks([text(1, "user", "hi"), text(2, "assistant", "hello")]);
-    expect(groups).toHaveLength(2);
-    expect(groups.every((g) => g.kind === "single")).toBe(true);
-  });
-
-  it("does NOT batch a single tool call (one per step) — call+result stay separate singles", () => {
-    const groups = groupRenderedChunks([call(1, "a", "s1"), result(2, "a", "s1")]);
-    expect(groups).toHaveLength(2);
-    expect(groups.map((g) => g.kind)).toEqual(["single", "single"]);
+  it("passes non-tool chunks through unchanged and in order", () => {
+    const rows = [text(1, "user", "hi"), text(2, "assistant", "hello")];
+    expect(groupRenderedChunks(rows)).toEqual(rows.map((chunk) => ({ kind: "single", chunk })));
   });
-
-  it("does NOT batch tool calls that have no stepId (pre-0.2.0 replay)", () => {
-    const groups = groupRenderedChunks([
-      call(1, "a"),
-      call(2, "b"),
-      result(3, "a"),
-      result(4, "b"),
+  it("pairs a single call and result into one group", () => {
+    const c = call(1, "a", "s1");
+    const r = result(2, "a", "s1");
+    expect(toolGroups([c, r])).toEqual([
+      {
+        kind: "tool",
+        entry: { toolCallId: "a", toolName: "tool-a", call: c.chunk, result: r.chunk },
+        stepId: "s1",
+        provisional: false,
+      },
     ]);
-    expect(groups).toHaveLength(4);
-    expect(groups.every((g) => g.kind === "single")).toBe(true);
   });
-
-  it("batches 2+ calls sharing a stepId into one group, pairing each with its result", () => {
-    const groups = groupRenderedChunks([
+  it("renders parallel calls independently in call order, with out-of-order results", () => {
+    const groups = toolGroups([
       call(1, "a", "s1"),
       call(2, "b", "s1"),
-      result(3, "a", "s1"),
-      result(4, "b", "s1"),
+      result(3, "b", "s1"),
+      result(4, "a", "s1"),
     ]);
-    expect(groups).toHaveLength(1);
-    const g = groups[0];
-    if (g?.kind !== "tool-batch") throw new Error("expected a tool-batch group");
-    expect(g.stepId).toBe("s1");
-    expect(g.entries).toHaveLength(2);
-    expect(g.entries[0]?.call.toolCallId).toBe("a");
-    expect(g.entries[0]?.result?.content).toBe("result-a");
-    expect(g.entries[1]?.call.toolCallId).toBe("b");
-    expect(g.entries[1]?.result?.content).toBe("result-b");
+    expect(groups.map((g) => g.entry.toolCallId)).toEqual(["a", "b"]);
+    expect(groups.map((g) => g.entry.result?.content)).toEqual(["result-a", "result-b"]);
   });
-
-  it("positions the batch at the first call and keeps surrounding chunks in order", () => {
+  it("pairs legacy chunks without stepId and mismatching stepIds by toolCallId", () => {
+    const groups = toolGroups([
+      call(1, "a"),
+      result(2, "a"),
+      call(3, "b", "s1"),
+      result(4, "b", "s2"),
+    ]);
+    expect(groups).toHaveLength(2);
+    expect(groups[0]?.entry.result).not.toBeNull();
+    expect(groups[1]?.stepId).toBe("s1");
+  });
+  it("keeps surrounding text at its position and absorbs results", () => {
     const groups = groupRenderedChunks([
       text(1, "assistant", "before"),
       call(2, "a", "s1"),
-      call(3, "b", "s1"),
-      result(4, "a", "s1"),
-      result(5, "b", "s1"),
-      text(6, "assistant", "after"),
+      text(3, "assistant", "between"),
+      call(4, "b", "s1"),
+      result(5, "a"),
+      result(6, "b"),
+      text(7, "assistant", "after"),
     ]);
-    expect(groups.map((g) => g.kind)).toEqual(["single", "tool-batch", "single"]);
+    expect(groups.map((g) => g.kind)).toEqual(["single", "tool", "single", "tool", "single"]);
   });
-
-  it("marks the batch provisional when any of its calls/results is provisional", () => {
-    const groups = groupRenderedChunks([call(1, "a", "s1"), call(2, "b", "s1", true)]);
-    const g = groups[0];
-    if (g?.kind !== "tool-batch") throw new Error("expected a tool-batch group");
-    expect(g.provisional).toBe(true);
-    expect(g.entries).toHaveLength(2);
-    expect(g.entries[1]?.result).toBeNull(); // dangling call (no result yet)
+  it("keeps pending calls and orphan results", () => {
+    const groups = toolGroups([call(1, "pending"), result(2, "orphan", "s2", true)]);
+    expect(groups[0]?.entry.result).toBeNull();
+    expect(groups[1]?.entry.call).toBeNull();
+    expect(groups[1]?.entry.toolName).toBe("tool-orphan");
+    expect(groups[1]?.provisional).toBe(true);
+    expect(groups[1]?.stepId).toBe("s2");
   });
-
-  it("batches one step while leaving a different single-call step ungrouped", () => {
-    const groups = groupRenderedChunks([
-      call(1, "a", "s1"),
-      call(2, "b", "s1"),
-      call(3, "c", "s2"),
-      result(4, "a", "s1"),
-      result(5, "b", "s1"),
-      result(6, "c", "s2"),
-    ]);
-    expect(groups.map((g) => g.kind)).toEqual(["tool-batch", "single", "single"]);
-    const batch = groups[0];
-    if (batch?.kind !== "tool-batch") throw new Error("expected a tool-batch group");
-    expect(batch.entries).toHaveLength(2);
-    // the s2 single call + its result remain as separate single groups
-    const singles = groups.slice(1);
-    expect(singles[0]?.kind === "single" && singles[0].chunk.chunk.type).toBe("tool-call");
-    expect(singles[1]?.kind === "single" && singles[1].chunk.chunk.type).toBe("tool-result");
+  it.each([
+    [true, false],
+    [false, true],
+    [false, false],
+  ])("combines call/result provisional flags (%s, %s)", (cp, rp) => {
+    expect(toolGroups([call(1, "a", "s1", cp), result(2, "a", "s1", rp)])[0]?.provisional).toBe(
+      cp || rp,
+    );
   });
-
-  // --- Duplicate toolCallId hardening (fix-toolcall-duplicate-keys) ---
-  // A provider double-emission (e.g. openrouter/stealth/ox-alpha) can persist the
-  // SAME toolCallId twice within one step. The renderer must NEVER crash on that
-  // (Svelte `each_key_duplicate` aborts the reactive flush — the tab appears dead).
-
-  it("dedupes duplicate toolCallIds within a batch", () => {
-    // The PII_REDACTED_CONVERSATION_SHORT_01 pattern: every id emitted twice, in order (seq 1,2 then 3,4).
-    const groups = groupRenderedChunks([
-      call(1, "a", "s1"),
-      call(2, "b", "s1"),
-      call(3, "a", "s1"),
-      call(4, "b", "s1"),
+  it("prefers call provenance, falling back to result provenance", () => {
+    const groups = toolGroups([
+      { ...call(1, "a", "s1"), turnId: "t1" },
+      { ...result(2, "a", "s2"), turnId: "t2" },
+      call(3, "b"),
+      { ...result(4, "b", "s3"), turnId: "t3" },
     ]);
-    expect(groups).toHaveLength(1);
-    const g = groups[0];
-    if (g?.kind !== "tool-batch") throw new Error("expected a tool-batch group");
-    expect(g.entries).toHaveLength(2);
-    expect(g.entries.map((e) => e.call.toolCallId)).toEqual(["a", "b"]);
-  });
-
-  it("dedupes duplicate toolCallIds and pairs each unique call with its result", () => {
-    const groups = groupRenderedChunks([
-      call(1, "a", "s1"),
-      call(2, "b", "s1"),
-      call(3, "a", "s1"),
-      call(4, "b", "s1"),
-      result(5, "a", "s1"),
-      result(6, "b", "s1"),
-      result(7, "a", "s1"),
-      result(8, "b", "s1"),
+    expect(groups.map((g) => [g.stepId, g.turnId])).toEqual([
+      ["s1", "t1"],
+      ["s3", "t3"],
     ]);
-    expect(groups).toHaveLength(1);
-    const g = groups[0];
-    if (g?.kind !== "tool-batch") throw new Error("expected a tool-batch group");
-    expect(g.entries).toHaveLength(2);
-    expect(g.entries[0]?.call.toolCallId).toBe("a");
-    expect(g.entries[0]?.result?.content).toBe("result-a");
-    expect(g.entries[1]?.call.toolCallId).toBe("b");
-    expect(g.entries[1]?.result?.content).toBe("result-b");
   });
-
-  it("keeps the first occurrence of a duplicate toolCallId and skips the second", () => {
-    const firstA = call(1, "a", "s1"); // first occurrence of a
-    const firstB = call(2, "b", "s1"); // first occurrence of b
-    const groups = groupRenderedChunks([
-      firstA,
-      firstB,
-      call(3, "a", "s1"), // duplicate of a — skipped
-      call(4, "b", "s1"), // duplicate of b — skipped
+  it("dedupes calls/results across steps, first occurrence wins", () => {
+    const first = call(1, "a", "s1", true);
+    const firstResult = result(4, "a", "s1");
+    const groups = toolGroups([
+      first,
+      call(2, "a", "s2"),
+      call(3, "b"),
+      firstResult,
+      result(5, "a", "s2"),
+      result(6, "b"),
+      result(7, "b"),
     ]);
-    const g = groups[0];
-    if (g?.kind !== "tool-batch") throw new Error("expected a tool-batch group");
-    expect(g.entries).toHaveLength(2);
-    // The FIRST occurrence (by stream order) is the one kept — referential
-    // equality against the seq-1 / seq-2 chunks (the entry stores the inner
-    // chunk; the outer `seq` lives on the RenderedChunk wrapper).
-    expect(g.entries[0]?.call).toBe(firstA.chunk);
-    expect(g.entries[1]?.call).toBe(firstB.chunk);
+    expect(groups).toHaveLength(2);
+    expect(groups[0]?.entry.call).toBe(first.chunk);
+    expect(groups[0]?.entry.result).toBe(firstResult.chunk);
+    expect(groups[0]?.provisional).toBe(true);
   });
-
-  it("keeps the first (provisional) occurrence of a duplicate and marks the batch provisional", () => {
-    // One provisional + one committed chunk with the SAME id: the first
-    // (provisional) occurrence wins, and the batch stays provisional.
-    const prov = call(1, "a", "s1", true);
-    const groups = groupRenderedChunks([prov, call(2, "a", "s1")]);
-    const g = groups[0];
-    if (g?.kind !== "tool-batch") throw new Error("expected a tool-batch group");
-    expect(g.provisional).toBe(true);
-    expect(g.entries).toHaveLength(1);
-    expect(g.entries[0]?.call).toBe(prov.chunk);
-    expect(g.entries[0]?.result).toBeNull();
+  it("dedupes orphan results too", () => {
+    expect(toolGroups([result(1, "a"), result(2, "a")])).toHaveLength(1);
+  });
+  it("positions a card at its call even when its result came first", () => {
+    const c = call(3, "a");
+    const groups = groupRenderedChunks([result(1, "a"), text(2, "assistant", "before call"), c]);
+    expect(groups.map((g) => g.kind)).toEqual(["single", "tool"]);
   });
 });
diff --git a/src/core/chunks/groups.ts b/src/core/chunks/groups.ts
index 9df0fa5..c8493cc 100644
--- a/src/core/chunks/groups.ts
+++ b/src/core/chunks/groups.ts
@@ -1,111 +1,65 @@
 import type { ToolCallChunk, ToolResultChunk } from "@dispatch/wire";
 import type { RenderedChunk } from "./types";
 
-/**
- * One tool call within a batch, paired with its result (matched by `toolCallId`).
- * `result` is null while the call is still pending (no result chunk yet).
- */
-export interface ToolBatchEntry {
-  readonly call: ToolCallChunk;
+/** One tool call and its response. Null call = unloaded history; null result = pending. */
+export interface ToolEntry {
+  readonly toolCallId: string;
+  readonly toolName: string;
+  readonly call: ToolCallChunk | null;
   readonly result: ToolResultChunk | null;
 }
 
-/**
- * A render group: either a single rendered chunk (rendered as today) or a batch
- * of tool calls the model emitted together in one step (shared `stepId`), to be
- * rendered as one grouped unit.
- */
 export type RenderGroup =
   | { readonly kind: "single"; readonly chunk: RenderedChunk }
   | {
-      readonly kind: "tool-batch";
-      readonly stepId: string;
-      readonly entries: readonly ToolBatchEntry[];
+      readonly kind: "tool";
+      readonly entry: ToolEntry;
       readonly provisional: boolean;
-      /** The producing turn (from the batch's first call chunk), when known. */
+      readonly stepId?: string;
       readonly turnId?: string;
     };
 
 /**
- * Group a flat rendered-chunk stream for display. Tool calls sharing a `stepId`
- * (the backend's authoritative batch key) where the step has 2+ calls become one
- * `tool-batch` group, positioned at the first call and pairing each call with its
- * `tool-result` (by `toolCallId`); the absorbed result chunks are not emitted on
- * their own. Single tool calls (one per step, or no `stepId` — e.g. pre-0.2.0
- * replay rows) and every non-tool chunk render as `single` groups, in order.
- *
- * Pure: input → output, no DOM, no Svelte.
+ * One independent group per call, at the call's position, absorbing its result
+ * by toolCallId (including legacy chunks without stepId). Orphan results stay
+ * visible at their own position. First occurrence wins for duplicate ids, so
+ * the stable t<toolCallId> render keys are always unique, even on corrupt replay.
+ * Pure: input → output; no DOM, effects, or Svelte.
  */
 export function groupRenderedChunks(rendered: readonly RenderedChunk[]): readonly RenderGroup[] {
-  // 1. Steps that batched 2+ tool calls.
-  const callsPerStep = new Map<string, number>();
-  for (const rc of rendered) {
-    if (rc.chunk.type === "tool-call" && rc.chunk.stepId !== undefined) {
-      callsPerStep.set(rc.chunk.stepId, (callsPerStep.get(rc.chunk.stepId) ?? 0) + 1);
-    }
-  }
-  const batchSteps = new Set<string>();
-  for (const [stepId, count] of callsPerStep) {
-    if (count >= 2) batchSteps.add(stepId);
-  }
-
-  // 2. toolCallIds belonging to a batch (so their results are absorbed), and a
-  //    lookup of result chunks by toolCallId for pairing.
-  const batchCallIds = new Set<string>();
-  const resultByCallId = new Map<string, ToolResultChunk>();
+  const calls = new Map<string, RenderedChunk>();
+  const results = new Map<string, RenderedChunk>();
   for (const rc of rendered) {
-    const chunk = rc.chunk;
-    if (chunk.type === "tool-call" && chunk.stepId !== undefined && batchSteps.has(chunk.stepId)) {
-      batchCallIds.add(chunk.toolCallId);
-    } else if (chunk.type === "tool-result" && !resultByCallId.has(chunk.toolCallId)) {
-      resultByCallId.set(chunk.toolCallId, chunk);
-    }
+    const c = rc.chunk;
+    if (c.type === "tool-call" && !calls.has(c.toolCallId)) calls.set(c.toolCallId, rc);
+    if (c.type === "tool-result" && !results.has(c.toolCallId)) results.set(c.toolCallId, rc);
   }
 
-  // 3. Emit groups in stream order; each batch lands at its first call.
   const groups: RenderGroup[] = [];
-  const emittedSteps = new Set<string>();
+  const emitted = new Set<string>();
   for (const rc of rendered) {
-    const chunk = rc.chunk;
-
-    if (chunk.type === "tool-call" && chunk.stepId !== undefined && batchSteps.has(chunk.stepId)) {
-      const stepId = chunk.stepId;
-      if (emittedSteps.has(stepId)) continue;
-      emittedSteps.add(stepId);
-
-      const entries: ToolBatchEntry[] = [];
-      // Dedupe by toolCallId within the batch: a provider double-emission (or any
-      // corrupted transcript) can carry the SAME call id on multiple tool-call
-      // chunks in one step. The first occurrence (stream order) wins; later ones
-      // are skipped so the keyed `{#each}` in the UI never sees duplicate keys
-      // (Svelte `each_key_duplicate` aborts the reactive flush — tab appears dead).
-      const seenCallIds = new Set<string>();
-      let provisional = false;
-      let turnId: string | undefined;
-      for (const inner of rendered) {
-        if (inner.chunk.type === "tool-call" && inner.chunk.stepId === stepId) {
-          if (seenCallIds.has(inner.chunk.toolCallId)) continue;
-          seenCallIds.add(inner.chunk.toolCallId);
-          const result = resultByCallId.get(inner.chunk.toolCallId) ?? null;
-          entries.push({ call: inner.chunk, result });
-          if (inner.provisional) provisional = true;
-          turnId ??= inner.turnId;
-        }
-      }
-      groups.push(
-        turnId !== undefined
-          ? { kind: "tool-batch", stepId, entries, provisional, turnId }
-          : { kind: "tool-batch", stepId, entries, provisional },
-      );
+    const c = rc.chunk;
+    if (c.type !== "tool-call" && c.type !== "tool-result") {
+      groups.push({ kind: "single", chunk: rc });
       continue;
     }
-
-    if (chunk.type === "tool-result" && batchCallIds.has(chunk.toolCallId)) {
-      continue; // absorbed into its batch
-    }
-
-    groups.push({ kind: "single", chunk: rc });
+    if (emitted.has(c.toolCallId)) continue;
+    // A matching call owns the card's position, even if the result came first.
+    if (c.type === "tool-result" && calls.has(c.toolCallId)) continue;
+    emitted.add(c.toolCallId);
+    const callRow = calls.get(c.toolCallId);
+    const resultRow = results.get(c.toolCallId);
+    const call = callRow?.chunk.type === "tool-call" ? callRow.chunk : null;
+    const result = resultRow?.chunk.type === "tool-result" ? resultRow.chunk : null;
+    const stepId = call?.stepId ?? result?.stepId;
+    const turnId = callRow?.turnId ?? resultRow?.turnId;
+    groups.push({
+      kind: "tool",
+      entry: { toolCallId: c.toolCallId, toolName: call?.toolName ?? c.toolName, call, result },
+      provisional: Boolean(callRow?.provisional || resultRow?.provisional),
+      ...(stepId !== undefined ? { stepId } : {}),
+      ...(turnId !== undefined ? { turnId } : {}),
+    });
   }
-
   return groups;
 }
diff --git a/src/core/chunks/index.ts b/src/core/chunks/index.ts
index bdd6ce4..3822a79 100644
--- a/src/core/chunks/index.ts
+++ b/src/core/chunks/index.ts
@@ -1,4 +1,4 @@
-export type { RenderGroup, ToolBatchEntry } from "./groups";
+export type { RenderGroup, ToolEntry } from "./groups";
 export { groupRenderedChunks } from "./groups";
 export { resolveImageUrl } from "./image-url";
 export {