Five fixes for latent regressions surfaced during the v1.13.x.cosmetic revert investigation. None alter schema or compaction; all cleanup against the v1.13.1-A AI SDK migration's hidden surface. (1) provider.ts — includeUsage: true on createOpenAICompatible. @ai-sdk/openai-compatible defaults this false, omitting stream_options.include_usage from the request body; llama-swap never emitted the usage block, so result.usage.inputTokens/outputTokens resolved undefined and tokens_used / ctx_used landed NULL in every assistant row since v1.13.1-A. No historical backfill. (2) MessageList.tsx — hasText = m.content.trim().length > 0. AI SDK v6 streaming occasionally emits a leading "\n" text-delta on tool-call-only turns; the literal newline passed length > 0 and rendered an empty bubble + ActionRow between every tool call. Trim catches it without changing semantics for genuine content. (3) MessageBubble.tsx — same trim on hasContent for the no-tool-calls path. Defensive symmetry with MessageList.flatten. (4) payload.ts — buildMessagesPayload skips assistant rows with status='failed' AND assistant rows with status='complete' + empty content + no tool_calls. Without this, a trailing empty/failed assistant + the next attempt's placeholder produced "Cannot have 2 or more assistant messages at the end of the list" rejections from the OpenAI-compatible upstream after cap-hit + Continue. (5) budget.ts — BUDGET_NO_AGENT 15 → 30. Every tool in ALL_TOOLS is read-only today; the 15-cap was forward-looking for write tools that haven't landed. No-agent mode now matches BUDGET_READ_ONLY. 47 LoC across 5 files. 190/190 server tests pass. Verified live: new assistant turns populate StatsLine token data; single-tool-call turns no longer render the stray empty-bubble + ActionRow between tool calls; Continue after cap-hit no longer hits the trailing-assistant API rejection.
193 lines
6.3 KiB
TypeScript
193 lines
6.3 KiB
TypeScript
import { useEffect, useMemo, useRef } from 'react';
|
|
import type { Chat, Message } from '@/api/types';
|
|
import { MessageBubble } from './MessageBubble';
|
|
import { ToolCallGroup } from './ToolCallGroup';
|
|
import { ToolCallLine, type ToolRun } from './ToolCallLine';
|
|
import { AskUserInputCard } from './AskUserInputCard';
|
|
|
|
interface Props {
|
|
messages: Message[];
|
|
sessionChats?: Chat[];
|
|
}
|
|
|
|
// v1.8.2: pre-render units. The single linear `messages` array gets walked
|
|
// into a render-time list where each tool_call is a first-class item and
|
|
// tool_result messages are folded onto their matching tool_run by id.
|
|
// Batch 9.7: tool_run carries chat_id so AskUserInputCard can post the
|
|
// answer without threading the chat id through MessageList's parent.
|
|
type RenderItem =
|
|
| { kind: 'message'; message: Message; capHitInfo?: { position: number; isLatest: boolean } }
|
|
| { kind: 'tool_run'; run: ToolRun; key: string; chatId: string }
|
|
| { kind: 'tool_group'; runs: ToolRun[]; key: string };
|
|
|
|
const GROUP_THRESHOLD = 3;
|
|
|
|
function isCapHitSentinel(m: Message): boolean {
|
|
return m.role === 'system' && m.metadata?.kind === 'cap_hit';
|
|
}
|
|
|
|
// First pass: walk messages chronologically, expanding assistant tool_calls
|
|
// into per-call run items and folding tool_result messages onto their
|
|
// matching runs. Tool messages themselves never produce a render item.
|
|
// Assistant messages produce a text render item only when they have text;
|
|
// pure tool-call messages are "transparent" so consecutive tool runs can
|
|
// still group across them.
|
|
function flatten(messages: Message[]): RenderItem[] {
|
|
const items: RenderItem[] = [];
|
|
const runsByCallId = new Map<string, ToolRun>();
|
|
|
|
for (const m of messages) {
|
|
if (m.role === 'tool') {
|
|
if (m.tool_results) {
|
|
const run = runsByCallId.get(m.tool_results.tool_call_id);
|
|
if (run) run.result = m.tool_results;
|
|
}
|
|
continue;
|
|
}
|
|
const hasToolCalls = m.tool_calls != null && m.tool_calls.length > 0;
|
|
// v1.13.7: trim before checking. AI SDK v6 streaming occasionally emits a
|
|
// leading "\n" text-delta on tool-call-only turns, which used to flow into
|
|
// messages.content with length=1 and render an empty bubble + ActionRow
|
|
// between each tool call. Whitespace-only content has no visible payload,
|
|
// so treat it as no-content.
|
|
const hasText = m.content.trim().length > 0;
|
|
if (m.role === 'assistant' && hasToolCalls) {
|
|
if (hasText || m.status === 'streaming') {
|
|
items.push({ kind: 'message', message: m });
|
|
}
|
|
for (const tc of m.tool_calls!) {
|
|
const run: ToolRun = { call: tc, result: null };
|
|
runsByCallId.set(tc.id, run);
|
|
items.push({ kind: 'tool_run', run, key: tc.id, chatId: m.chat_id });
|
|
}
|
|
continue;
|
|
}
|
|
items.push({ kind: 'message', message: m });
|
|
}
|
|
|
|
return items;
|
|
}
|
|
|
|
// Second pass: collapse runs of >=GROUP_THRESHOLD consecutive tool_run items
|
|
// of the same tool name into a single tool_group. Any other render item
|
|
// (text bubble, sentinel, user message) breaks the chain.
|
|
// Batch 9.7: ask_user_input never groups — each pause has its own card so
|
|
// grouping would render them as collapsed ToolCallLines which can't surface
|
|
// the interactive form.
|
|
function group(items: RenderItem[]): RenderItem[] {
|
|
const out: RenderItem[] = [];
|
|
let i = 0;
|
|
while (i < items.length) {
|
|
const item = items[i]!;
|
|
if (item.kind !== 'tool_run') {
|
|
out.push(item);
|
|
i += 1;
|
|
continue;
|
|
}
|
|
const name = item.run.call.name;
|
|
if (name === 'ask_user_input') {
|
|
out.push(item);
|
|
i += 1;
|
|
continue;
|
|
}
|
|
let j = i + 1;
|
|
while (
|
|
j < items.length &&
|
|
items[j]!.kind === 'tool_run' &&
|
|
(items[j] as { kind: 'tool_run'; run: ToolRun }).run.call.name === name
|
|
) {
|
|
j += 1;
|
|
}
|
|
const run = items.slice(i, j) as Array<{
|
|
kind: 'tool_run';
|
|
run: ToolRun;
|
|
key: string;
|
|
chatId: string;
|
|
}>;
|
|
if (run.length >= GROUP_THRESHOLD) {
|
|
out.push({
|
|
kind: 'tool_group',
|
|
runs: run.map((r) => r.run),
|
|
key: `group-${run[0]!.key}`,
|
|
});
|
|
} else {
|
|
for (const r of run) out.push(r);
|
|
}
|
|
i = j;
|
|
}
|
|
return out;
|
|
}
|
|
|
|
// Third pass: number cap-hit sentinels (1-indexed) and mark the latest.
|
|
// CapHitSentinel uses position to compute the "N continues remaining"
|
|
// tooltip, and isLatest to gate the Continue button (only the most recent
|
|
// sentinel is actionable).
|
|
function stampCapHits(items: RenderItem[]): RenderItem[] {
|
|
const totalCapHits = items.reduce(
|
|
(n, it) => n + (it.kind === 'message' && isCapHitSentinel(it.message) ? 1 : 0),
|
|
0,
|
|
);
|
|
if (totalCapHits === 0) return items;
|
|
let index = 0;
|
|
return items.map((it) => {
|
|
if (it.kind !== 'message' || !isCapHitSentinel(it.message)) return it;
|
|
index += 1;
|
|
return {
|
|
...it,
|
|
capHitInfo: { position: index, isLatest: index === totalCapHits },
|
|
};
|
|
});
|
|
}
|
|
|
|
export function MessageList({ messages, sessionChats }: Props) {
|
|
const endRef = useRef<HTMLDivElement>(null);
|
|
|
|
const renderItems = useMemo(() => stampCapHits(group(flatten(messages))), [messages]);
|
|
|
|
useEffect(() => {
|
|
endRef.current?.scrollIntoView({ block: 'end' });
|
|
}, [messages]);
|
|
|
|
if (messages.length === 0) {
|
|
return (
|
|
<div className="flex-1 flex items-center justify-center text-sm text-muted-foreground">
|
|
Send a message to start.
|
|
</div>
|
|
);
|
|
}
|
|
|
|
return (
|
|
<div className="flex-1 overflow-y-auto">
|
|
<div className="max-w-[1000px] mx-auto w-full px-6 py-4 space-y-4">
|
|
{renderItems.map((item) => {
|
|
if (item.kind === 'message') {
|
|
return (
|
|
<MessageBubble
|
|
key={item.message.id}
|
|
message={item.message}
|
|
sessionChats={sessionChats}
|
|
capHitInfo={item.capHitInfo}
|
|
/>
|
|
);
|
|
}
|
|
if (item.kind === 'tool_run') {
|
|
if (item.run.call.name === 'ask_user_input') {
|
|
return (
|
|
<AskUserInputCard
|
|
key={item.key}
|
|
toolCall={item.run.call}
|
|
toolResult={item.run.result}
|
|
chatId={item.chatId}
|
|
/>
|
|
);
|
|
}
|
|
return <ToolCallLine key={item.key} run={item.run} />;
|
|
}
|
|
return <ToolCallGroup key={item.key} runs={item.runs} />;
|
|
})}
|
|
<div ref={endRef} />
|
|
</div>
|
|
</div>
|
|
);
|
|
}
|