Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 agent_coder
|
6f3237bc41 | ||
|
agent_coder
|
8125b7e700 |
@@ -27,7 +27,6 @@ vi.mock("@/features/ai-chat/utils/markdown.ts", async () => {
|
||||
|
||||
import MessageItem from "./message-item";
|
||||
import { messageSignature } from "@/features/ai-chat/utils/message-signature.ts";
|
||||
import { splitPlainChunks } from "./streaming-plain-text";
|
||||
|
||||
// matchMedia (read by MantineProvider) is stubbed globally in vitest.setup.ts.
|
||||
|
||||
@@ -115,89 +114,3 @@ describe("MessageItem markdown memoization", () => {
|
||||
expect(queryByText("streamed answer")).not.toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
// PERF SMOKE (#492): the whole point of the incremental streaming render is that
|
||||
// the ANSWER path costs O(number of markdown blocks), NOT O(number of throttled
|
||||
// ~20Hz ticks). Pre-#492 the finalized MarkdownPart re-parsed the WHOLE growing
|
||||
// answer on every delta — a synthetic ~100 KB stream measured 394 renderChatMarkdown
|
||||
// calls (one per tick). With the incremental render each STABILIZED block is parsed
|
||||
// exactly once (memoized in MarkdownChunk) and the live tail is cheap plain text, so
|
||||
// the call count collapses to ~= the block count regardless of tick granularity.
|
||||
describe("MessageItem streaming answer render is O(blocks), not O(ticks)", () => {
|
||||
// ~100 KB answer. Each section is a heading + a paragraph — TWO blank-line
|
||||
// delimited markdown blocks — so the safe-cut block count is ~2× the section
|
||||
// count. The perf claim is about the BLOCK count (the memoization granularity),
|
||||
// measured directly with splitPlainChunks below, not the section count.
|
||||
const buildAnswer = () => {
|
||||
const SECTIONS = 100;
|
||||
const paragraphs: string[] = [];
|
||||
for (let i = 0; i < SECTIONS; i++) {
|
||||
paragraphs.push(`## Section ${i}\n\n` + "lorem ipsum dolor ".repeat(55));
|
||||
}
|
||||
const full = paragraphs.join("\n\n");
|
||||
// The number of memoized markdown blocks the incremental render splits into
|
||||
// (all but the live tail are parsed once each).
|
||||
return { full, blocks: splitPlainChunks(full).length };
|
||||
};
|
||||
|
||||
const streamMsg = (text: string, state: "streaming" | "done"): UIMessage =>
|
||||
({
|
||||
id: "m1",
|
||||
role: "assistant",
|
||||
parts: [{ type: "text", text, state }],
|
||||
}) as UIMessage;
|
||||
|
||||
it("parses each block ~once over a 100KB stream (≈blocks, ≪ ticks)", () => {
|
||||
renderChatMarkdownSpy.mockClear();
|
||||
const { full, blocks } = buildAnswer();
|
||||
const CHUNK = 128; // a realistic ~20Hz throttled delta size
|
||||
const ticks = Math.ceil(full.length / CHUNK);
|
||||
|
||||
let msg = streamMsg(full.slice(0, CHUNK), "streaming");
|
||||
const { rerender } = render(
|
||||
<MantineProvider>
|
||||
<MessageItem
|
||||
message={msg}
|
||||
signature={messageSignature(msg)}
|
||||
turnStreaming
|
||||
/>
|
||||
</MantineProvider>,
|
||||
);
|
||||
for (let end = 2 * CHUNK; end < full.length; end += CHUNK) {
|
||||
msg = streamMsg(full.slice(0, end), "streaming");
|
||||
rerender(
|
||||
<MantineProvider>
|
||||
<MessageItem
|
||||
message={msg}
|
||||
signature={messageSignature(msg)}
|
||||
turnStreaming
|
||||
/>
|
||||
</MantineProvider>,
|
||||
);
|
||||
}
|
||||
// Finalize: the streaming→done flip renders the whole answer through ONE
|
||||
// canonical pass (visual parity), so the finished DOM matches the pre-#492
|
||||
// output. This is the single extra parse on top of the per-block ones.
|
||||
const done = streamMsg(full, "done");
|
||||
rerender(
|
||||
<MantineProvider>
|
||||
<MessageItem message={done} signature={messageSignature(done)} />
|
||||
</MantineProvider>,
|
||||
);
|
||||
|
||||
const calls = renderChatMarkdownSpy.mock.calls.length;
|
||||
// Sanity: the stream really had far more ticks than blocks (else the test is
|
||||
// vacuous — the point is that calls scale with blocks, not ticks).
|
||||
expect(ticks).toBeGreaterThan(blocks * 3);
|
||||
// O(blocks): each stabilized block parsed once + the single final whole-text
|
||||
// parse. A small constant absorbs the finalize render and the live-tail block;
|
||||
// the load-bearing claim is the bound below.
|
||||
expect(calls).toBeLessThanOrEqual(blocks + 2);
|
||||
// ≪ ticks — and, non-vacuously, the blocks WERE parsed (not skipped entirely).
|
||||
expect(calls).toBeLessThan(ticks / 3);
|
||||
expect(calls).toBeGreaterThan(blocks / 2);
|
||||
// MUTATION-VERIFY (documented, not run here): dropping the `memo()` wrapper on
|
||||
// MarkdownChunk (so every stable block re-parses each tick) drives `calls`
|
||||
// toward `ticks` (~394), reddening both upper-bound assertions above.
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,112 +0,0 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { render } from "@testing-library/react";
|
||||
import { MantineProvider } from "@mantine/core";
|
||||
import type { UIMessage } from "@ai-sdk/react";
|
||||
|
||||
// Stub react-i18next (the component reads `useTranslation`). Mirrors the other
|
||||
// message-item specs.
|
||||
vi.mock("react-i18next", () => ({
|
||||
useTranslation: () => ({ t: (key: string) => key }),
|
||||
}));
|
||||
|
||||
import MessageItem from "./message-item";
|
||||
import { messageSignature } from "@/features/ai-chat/utils/message-signature.ts";
|
||||
// The REAL canonical renderer (NOT the spy the memo test installs): this file
|
||||
// exercises the actual markdown output so the visual-regression assertions below
|
||||
// compare against genuine HTML (incl. the schema's `<li><p>` wrappers).
|
||||
import { renderChatMarkdown } from "@/features/ai-chat/utils/markdown.ts";
|
||||
import classes from "./ai-chat.module.css";
|
||||
|
||||
const msg = (
|
||||
parts: UIMessage["parts"],
|
||||
extra?: Partial<UIMessage>,
|
||||
): UIMessage =>
|
||||
({ id: "m1", role: "assistant", parts, ...extra }) as UIMessage;
|
||||
|
||||
const renderRow = (message: UIMessage, turnStreaming = false) =>
|
||||
render(
|
||||
<MantineProvider>
|
||||
<MessageItem
|
||||
message={message}
|
||||
signature={messageSignature(message)}
|
||||
turnStreaming={turnStreaming}
|
||||
/>
|
||||
</MantineProvider>,
|
||||
);
|
||||
|
||||
// A rich multi-block answer that exercises headings, a list (the `<li><p>` case
|
||||
// the scoped CSS tightens), inline emphasis, and multiple paragraphs.
|
||||
const ANSWER = [
|
||||
"# Заголовок",
|
||||
"",
|
||||
"Первый абзац с **жирным** и `кодом`.",
|
||||
"",
|
||||
"- пункт один",
|
||||
"- пункт два",
|
||||
"",
|
||||
"Второй абзац.",
|
||||
].join("\n");
|
||||
|
||||
describe("MessageItem final render — visual parity with the canonical pipeline", () => {
|
||||
it("a finalized text part renders exactly renderChatMarkdown(text)", () => {
|
||||
const { container } = renderRow(
|
||||
msg([{ type: "text", text: ANSWER, state: "done" }]),
|
||||
);
|
||||
const block = container.querySelector(`.${classes.markdown}`);
|
||||
expect(block).not.toBeNull();
|
||||
// Byte-for-byte the canonical output (the SAME whole-text pass the pre-#492
|
||||
// MarkdownPart produced), including `<li><p>…</p></li>` wrappers.
|
||||
expect(block!.innerHTML).toBe(renderChatMarkdown(ANSWER, {}));
|
||||
// The list wrapper is really present (guards against a vacuous empty render).
|
||||
expect(container.querySelectorAll("li p").length).toBe(2);
|
||||
});
|
||||
|
||||
it("the streaming incremental view CONVERGES to the canonical render on finish", () => {
|
||||
// Mount mid-stream (live tail) — the DOM here is the incremental view.
|
||||
const { container, rerender } = render(
|
||||
<MantineProvider>
|
||||
<MessageItem
|
||||
message={msg([{ type: "text", text: ANSWER, state: "streaming" }])}
|
||||
signature={messageSignature(
|
||||
msg([{ type: "text", text: ANSWER, state: "streaming" }]),
|
||||
)}
|
||||
turnStreaming
|
||||
/>
|
||||
</MantineProvider>,
|
||||
);
|
||||
// Finish the turn: state flips to done AND the turn is no longer streaming.
|
||||
const done = msg([{ type: "text", text: ANSWER, state: "done" }]);
|
||||
rerender(
|
||||
<MantineProvider>
|
||||
<MessageItem message={done} signature={messageSignature(done)} />
|
||||
</MantineProvider>,
|
||||
);
|
||||
// After finish there is exactly ONE canonical markdown container whose HTML is
|
||||
// the whole-text render — identical to the non-streaming path above.
|
||||
const blocks = container.querySelectorAll(`.${classes.markdown}`);
|
||||
expect(blocks.length).toBe(1);
|
||||
expect(blocks[0].innerHTML).toBe(renderChatMarkdown(ANSWER, {}));
|
||||
});
|
||||
|
||||
it("neutralizeInternalLinks is honored on the finalized render", () => {
|
||||
const linkAnswer = "См. [страницу](/p/abc).";
|
||||
const { container } = render(
|
||||
<MantineProvider>
|
||||
<MessageItem
|
||||
message={msg([{ type: "text", text: linkAnswer, state: "done" }])}
|
||||
signature={messageSignature(
|
||||
msg([{ type: "text", text: linkAnswer, state: "done" }]),
|
||||
)}
|
||||
neutralizeInternalLinks
|
||||
/>
|
||||
</MantineProvider>,
|
||||
);
|
||||
const block = container.querySelector(`.${classes.markdown}`);
|
||||
expect(block!.innerHTML).toBe(
|
||||
renderChatMarkdown(linkAnswer, { neutralizeInternalLinks: true }),
|
||||
);
|
||||
// The internal link was made inert (no href) by the neutralization flag.
|
||||
const a = container.querySelector("a");
|
||||
expect(a?.hasAttribute("href")).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -4,7 +4,6 @@ import { useTranslation } from "react-i18next";
|
||||
import type { UIMessage } from "@ai-sdk/react";
|
||||
import ToolCallCard from "@/features/ai-chat/components/tool-call-card.tsx";
|
||||
import ReasoningBlock from "@/features/ai-chat/components/reasoning-block.tsx";
|
||||
import { StreamingMarkdownText } from "@/features/ai-chat/components/streaming-markdown-text.tsx";
|
||||
import ChatErrorAlert from "@/features/ai-chat/components/chat-error-alert.tsx";
|
||||
import ChatStoppedNotice from "@/features/ai-chat/components/chat-stopped-notice.tsx";
|
||||
import { ToolUiPart, isToolPart } from "@/features/ai-chat/utils/tool-parts.tsx";
|
||||
@@ -87,39 +86,17 @@ interface MessageItemProps {
|
||||
* One assistant text part rendered as sanitized markdown. Memoized on its inputs
|
||||
* so a finalized text part is NOT re-parsed on every streamed delta: during a
|
||||
* turn only the actively-growing tail part changes its `text`, so every earlier
|
||||
* part hits the memo and skips the expensive canonical parse + DOMPurify pass.
|
||||
* Props are primitives, so React.memo's default shallow compare is exactly right
|
||||
* (the `text` string is compared by value).
|
||||
*
|
||||
* Streaming gate (#492) — mirrors ReasoningBlock:
|
||||
* - `streaming` (this is the live, actively-growing tail part of an in-flight
|
||||
* turn): render incrementally via StreamingMarkdownText — the stabilized blocks
|
||||
* go through the canonical pipeline (each parsed ONCE, memoized) and only the
|
||||
* live tail is cheap plain text. This makes the per-tick cost O(new blocks),
|
||||
* not the pre-#492 O(ticks) whole-answer re-parse on every ~20Hz delta.
|
||||
* - finalized (the common case, and the turn-end flip): render the WHOLE text
|
||||
* through ONE canonical pass — byte-identical to the pre-#492 output (visual
|
||||
* parity). The row re-renders on the streaming→done flip because
|
||||
* `messageSignature` tracks each part's `state` (and `turnStreaming` flips at
|
||||
* turn end), so the incremental view always converges to this single render.
|
||||
* part hits the memo and skips the expensive marked + DOMPurify pass. Props are
|
||||
* primitives, so React.memo's default shallow compare is exactly right (the
|
||||
* `text` string is compared by value).
|
||||
*/
|
||||
const MarkdownPart = memo(function MarkdownPart({
|
||||
text,
|
||||
neutralizeInternalLinks,
|
||||
streaming,
|
||||
}: {
|
||||
text: string;
|
||||
neutralizeInternalLinks: boolean;
|
||||
streaming: boolean;
|
||||
}) {
|
||||
if (streaming) {
|
||||
return (
|
||||
<StreamingMarkdownText
|
||||
text={text}
|
||||
neutralizeInternalLinks={neutralizeInternalLinks}
|
||||
/>
|
||||
);
|
||||
}
|
||||
const html = renderChatMarkdown(text, { neutralizeInternalLinks });
|
||||
if (html) {
|
||||
return (
|
||||
@@ -202,10 +179,47 @@ function MessageItem({
|
||||
{resolveAssistantName(assistantName) ?? t("AI agent")}
|
||||
</Text>
|
||||
{message.parts.map((part, index) => {
|
||||
// Tool parts (`tool-*` / `dynamic-tool`) are template-literal kinds, so
|
||||
// they cannot be a `switch` case; the runtime guard handles them, and the
|
||||
// switch below covers every CLOSED (literal-typed) part kind with a
|
||||
// compile-time exhaustiveness check in its default.
|
||||
if (part.type === "reasoning") {
|
||||
// Reasoning ("thinking") -> a collapsible block with its own token
|
||||
// count. Empty/whitespace reasoning with no authoritative count carries
|
||||
// nothing to show, so skip it (avoids an empty 0-token block).
|
||||
const text = (part as { text?: string }).text ?? "";
|
||||
if (!text.trim() && !(reasoningTokens && reasoningTokens > 0))
|
||||
return null;
|
||||
// Absent state (persisted rows) and "done" both mean finalized.
|
||||
// `messageSignature` already includes each part's `state`, so the
|
||||
// streaming→done flip changes the row signature and re-renders this
|
||||
// row — which is what lets ReasoningBlock switch from chunked plain
|
||||
// text to its one-time markdown parse (see reasoning-block.tsx).
|
||||
// ALSO require the turn to be live: a part stranded at
|
||||
// `state:"streaming"` after the turn ended (no `reasoning-end` — see
|
||||
// the `turnStreaming` prop doc) must still finalize and parse.
|
||||
const streaming =
|
||||
turnStreaming && (part as { state?: string }).state === "streaming";
|
||||
return (
|
||||
<ReasoningBlock
|
||||
key={index}
|
||||
text={text}
|
||||
tokens={reasoningTokens}
|
||||
streaming={streaming}
|
||||
/>
|
||||
);
|
||||
}
|
||||
|
||||
if (part.type === "text") {
|
||||
// Skip empty/whitespace-only text parts (a streaming message often
|
||||
// starts with an empty text part before the first token arrives); the
|
||||
// typing indicator covers that gap until real content streams in.
|
||||
if (!part.text.trim()) return null;
|
||||
return (
|
||||
<MarkdownPart
|
||||
key={index}
|
||||
text={part.text}
|
||||
neutralizeInternalLinks={neutralizeInternalLinks}
|
||||
/>
|
||||
);
|
||||
}
|
||||
|
||||
if (isToolPart(part.type)) {
|
||||
return (
|
||||
<ToolCallCard
|
||||
@@ -218,76 +232,7 @@ function MessageItem({
|
||||
);
|
||||
}
|
||||
|
||||
switch (part.type) {
|
||||
case "reasoning": {
|
||||
// Reasoning ("thinking") -> a collapsible block with its own token
|
||||
// count. Empty/whitespace reasoning with no authoritative count
|
||||
// carries nothing to show, so skip it (avoids an empty 0-token block).
|
||||
const text = part.text ?? "";
|
||||
if (!text.trim() && !(reasoningTokens && reasoningTokens > 0))
|
||||
return null;
|
||||
// Absent state (persisted rows) and "done" both mean finalized.
|
||||
// `messageSignature` already includes each part's `state`, so the
|
||||
// streaming→done flip changes the row signature and re-renders this
|
||||
// row — which is what lets ReasoningBlock switch from chunked plain
|
||||
// text to its one-time markdown parse (see reasoning-block.tsx).
|
||||
// ALSO require the turn to be live: a part stranded at
|
||||
// `state:"streaming"` after the turn ended (no `reasoning-end` — see
|
||||
// the `turnStreaming` prop doc) must still finalize and parse.
|
||||
const streaming = turnStreaming && part.state === "streaming";
|
||||
return (
|
||||
<ReasoningBlock
|
||||
key={index}
|
||||
text={text}
|
||||
tokens={reasoningTokens}
|
||||
streaming={streaming}
|
||||
/>
|
||||
);
|
||||
}
|
||||
|
||||
case "text": {
|
||||
// Skip empty/whitespace-only text parts (a streaming message often
|
||||
// starts with an empty text part before the first token arrives); the
|
||||
// typing indicator covers that gap until real content streams in.
|
||||
if (!part.text.trim()) return null;
|
||||
// The live, actively-growing tail part of the in-flight turn renders
|
||||
// incrementally (see MarkdownPart); a finalized part (persisted, or
|
||||
// the turn-end flip) renders the whole text through one canonical
|
||||
// pass. Same liveness rule as the reasoning branch above.
|
||||
const streaming = turnStreaming && part.state === "streaming";
|
||||
return (
|
||||
<MarkdownPart
|
||||
key={index}
|
||||
text={part.text}
|
||||
neutralizeInternalLinks={neutralizeInternalLinks}
|
||||
streaming={streaming}
|
||||
/>
|
||||
);
|
||||
}
|
||||
|
||||
case "source-url":
|
||||
case "source-document":
|
||||
case "file":
|
||||
case "step-start":
|
||||
// Not surfaced in the chat bubble (v1) — same as the pre-#492 default.
|
||||
return null;
|
||||
|
||||
default: {
|
||||
// Compile-time exhaustiveness over the CLOSED union members: every
|
||||
// literal-typed part kind is handled above, so the only kinds that
|
||||
// can reach here are the OPEN template-literal ones (`tool-*` — caught
|
||||
// by the guard at runtime — and `data-*`) plus `dynamic-tool`. Adding
|
||||
// a NEW closed part kind to UIMessagePart makes this assignment fail
|
||||
// to compile, forcing it to be handled instead of silently ignored
|
||||
// (this replaces the pre-#492 fall-through `return null` + WARNING).
|
||||
const _exhaustive:
|
||||
| `tool-${string}`
|
||||
| "dynamic-tool"
|
||||
| `data-${string}` = part.type;
|
||||
void _exhaustive;
|
||||
return null;
|
||||
}
|
||||
}
|
||||
return null;
|
||||
})}
|
||||
{/* A persisted turn error (server stored it in metadata.error). Rendered
|
||||
here so it survives a thread remount and shows in reopened history. */}
|
||||
|
||||
@@ -1,96 +0,0 @@
|
||||
import { memo, useMemo } from "react";
|
||||
import { splitPlainChunks } from "@/features/ai-chat/components/streaming-plain-text.tsx";
|
||||
import { renderChatMarkdown } from "@/features/ai-chat/utils/markdown.ts";
|
||||
import classes from "@/features/ai-chat/components/ai-chat.module.css";
|
||||
|
||||
/**
|
||||
* One STABILIZED markdown block, rendered through the canonical pipeline and
|
||||
* memoized on its string prop. During streaming only the TAIL chunk grows (the
|
||||
* `splitPlainChunks` append-only invariant guarantees every earlier chunk is
|
||||
* byte-identical across deltas), so React skips every stable block and each one
|
||||
* is parsed by `renderChatMarkdown` EXACTLY ONCE — turning the pre-#492
|
||||
* "re-parse the whole accumulated answer on every ~20Hz tick" (O(ticks)) into
|
||||
* O(number of blocks). The markup is DOMPurify-sanitized inside renderChatMarkdown
|
||||
* before it reaches `dangerouslySetInnerHTML`.
|
||||
*
|
||||
* NOTE (transient streaming-only artifact): a safe cut is a blank-line boundary,
|
||||
* so a construct that legitimately contains a blank line (e.g. a fenced code block
|
||||
* with an empty line) can be split across chunks and render oddly WHILE it is still
|
||||
* streaming. This is cosmetic and self-heals: the moment the part finalizes,
|
||||
* MarkdownPart renders the WHOLE text through one canonical pass (visual parity
|
||||
* with the pre-#492 output). The reasoning path makes the same trade (plain text
|
||||
* while streaming, one markdown parse at the end).
|
||||
*/
|
||||
const MarkdownChunk = memo(function MarkdownChunk({
|
||||
text,
|
||||
neutralizeInternalLinks,
|
||||
}: {
|
||||
text: string;
|
||||
neutralizeInternalLinks: boolean;
|
||||
}) {
|
||||
const html = renderChatMarkdown(text, { neutralizeInternalLinks });
|
||||
if (html) {
|
||||
return (
|
||||
<div
|
||||
className={classes.markdown}
|
||||
// Sanitized by renderChatMarkdown (DOMPurify) before insertion.
|
||||
dangerouslySetInnerHTML={{ __html: html }}
|
||||
/>
|
||||
);
|
||||
}
|
||||
// Malformed/unsupported markdown could not render synchronously: raw text.
|
||||
return (
|
||||
<div className={classes.markdown} style={{ whiteSpace: "pre-wrap" }}>
|
||||
{text}
|
||||
</div>
|
||||
);
|
||||
});
|
||||
|
||||
/**
|
||||
* The cheap streaming-time stand-in for the finalized answer's one-time markdown
|
||||
* parse (see MarkdownPart in message-item.tsx). Mirrors StreamingPlainText's
|
||||
* chunked-memo pattern but renders the STABILIZED prefix as real markdown (each
|
||||
* block parsed once, memoized) and only the LIVE tail as flat plain text — so the
|
||||
* user sees formatted output for everything up to the last safe cut, and the not-
|
||||
* yet-stable tail (which markdown-parsing every tick would make O(ticks)) stays a
|
||||
* single cheap escaped text node until it stabilizes into a new block.
|
||||
*
|
||||
* `splitPlainChunks` yields chunks where, under append-only growth, every chunk
|
||||
* except the LAST is immutable; the last chunk is the live tail. Index keys are
|
||||
* therefore stable (a given index never changes to a different chunk's content).
|
||||
*/
|
||||
export function StreamingMarkdownText({
|
||||
text,
|
||||
neutralizeInternalLinks,
|
||||
}: {
|
||||
text: string;
|
||||
neutralizeInternalLinks: boolean;
|
||||
}) {
|
||||
const chunks = useMemo(() => splitPlainChunks(text), [text]);
|
||||
return (
|
||||
<>
|
||||
{chunks.map((chunk, index) =>
|
||||
index < chunks.length - 1 ? (
|
||||
<MarkdownChunk
|
||||
key={index}
|
||||
text={chunk}
|
||||
neutralizeInternalLinks={neutralizeInternalLinks}
|
||||
/>
|
||||
) : (
|
||||
// The live tail: flat, React-escaped plain text (no markdown parse, no
|
||||
// sanitizer, no innerHTML). `pre-wrap` preserves its newlines; trailing
|
||||
// separator newlines are dropped at display time so the block gap comes
|
||||
// from the markdown margins, not a doubled empty line (mirrors
|
||||
// PlainChunk in streaming-plain-text.tsx).
|
||||
<div
|
||||
key={index}
|
||||
className={classes.markdown}
|
||||
style={{ whiteSpace: "pre-wrap" }}
|
||||
>
|
||||
{chunk.replace(/\n+$/, "")}
|
||||
</div>
|
||||
),
|
||||
)}
|
||||
</>
|
||||
);
|
||||
}
|
||||
@@ -35,7 +35,6 @@ import {
|
||||
import { PaginationOptions } from '@docmost/db/pagination/pagination-options';
|
||||
import { AiChatRepo } from '@docmost/db/repos/ai-chat/ai-chat.repo';
|
||||
import { AiChatMessageRepo } from '@docmost/db/repos/ai-chat/ai-chat-message.repo';
|
||||
import { AiChatRunStepRepo } from '@docmost/db/repos/ai-chat/ai-chat-run-step.repo';
|
||||
import { PageRepo } from '@docmost/db/repos/page/page.repo';
|
||||
import { UserThrottlerGuard } from '../../integrations/throttle/user-throttler.guard';
|
||||
import { AI_CHAT_THROTTLER } from '../../integrations/throttle/throttler-names';
|
||||
@@ -44,8 +43,6 @@ import {
|
||||
AiChatRunHooks,
|
||||
AiChatService,
|
||||
AiChatStreamBody,
|
||||
rowHasInlineParts,
|
||||
hydrateAssistantParts,
|
||||
} from './ai-chat.service';
|
||||
import { AiChatRunService } from './ai-chat-run.service';
|
||||
import { AiTranscriptionService } from './ai-transcription.service';
|
||||
@@ -132,39 +129,8 @@ export class AiChatController {
|
||||
// production. Only touched on the resumable-stream (flag-on) path.
|
||||
private readonly streamRegistry?: AiChatStreamRegistryService,
|
||||
private readonly environment?: EnvironmentService,
|
||||
// #492: reconstruct a #492 mid-run record's parts from the steps table before
|
||||
// returning rows to the client / export. OPTIONAL so positional controller
|
||||
// specs compile unchanged; when absent, hydration is skipped (old-era rows
|
||||
// already carry inline parts, so nothing to reconstruct).
|
||||
private readonly aiChatRunStepRepo?: AiChatRunStepRepo,
|
||||
) {}
|
||||
|
||||
/**
|
||||
* Reconstruct parts for any assistant rows that don't carry them INLINE — a
|
||||
* #492 mid-run record whose per-step parts live in `ai_chat_run_steps` (the
|
||||
* append-persist backend). Every FINISHED row (old-era + #492) and every old-era
|
||||
* streaming snapshot already has inline `metadata.parts`, so the common path
|
||||
* fetches NOTHING and returns the rows untouched; only an actively-streaming
|
||||
* new-style row triggers the batch step fetch. Consumers (seed/poll/export) read
|
||||
* `metadata.parts` off the returned rows exactly as before — the era switch is
|
||||
* invisible to them (reconstructRunParts contract).
|
||||
*/
|
||||
private async withReconstructedParts(
|
||||
rows: AiChatMessage[],
|
||||
workspaceId: string,
|
||||
): Promise<AiChatMessage[]> {
|
||||
if (!this.aiChatRunStepRepo) return rows;
|
||||
const needy = rows.filter(
|
||||
(r) => r.role === 'assistant' && !rowHasInlineParts(r),
|
||||
);
|
||||
if (needy.length === 0) return rows;
|
||||
const stepsByMessage = await this.aiChatRunStepRepo.findByMessageIds(
|
||||
needy.map((r) => r.id),
|
||||
workspaceId,
|
||||
);
|
||||
return hydrateAssistantParts(rows, stepsByMessage);
|
||||
}
|
||||
|
||||
/** List the requesting user's chats in this workspace (paginated). */
|
||||
@HttpCode(HttpStatus.OK)
|
||||
@Post('chats')
|
||||
@@ -218,17 +184,11 @@ export class AiChatController {
|
||||
@AuthWorkspace() workspace: Workspace,
|
||||
) {
|
||||
await this.assertOwnedChat(dto.chatId, user, workspace);
|
||||
const page = await this.aiChatMessageRepo.findByChat(
|
||||
return this.aiChatMessageRepo.findByChat(
|
||||
dto.chatId,
|
||||
workspace.id,
|
||||
pagination,
|
||||
);
|
||||
// #492: reconstruct parts for any active new-style row so the client seed sees
|
||||
// `metadata.parts` unchanged (a no-op for the finished rows that fill a page).
|
||||
return {
|
||||
...page,
|
||||
items: await this.withReconstructedParts(page.items, workspace.id),
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -265,10 +225,7 @@ export class AiChatController {
|
||||
workspace.id,
|
||||
);
|
||||
return {
|
||||
// #492: the delta of an actively-streaming new-style row carries its parts
|
||||
// reconstructed from the steps table, so the degraded poll shows persisted
|
||||
// progress exactly as the pre-#492 full-row snapshot did.
|
||||
rows: await this.withReconstructedParts(rows, workspace.id),
|
||||
rows,
|
||||
cursor,
|
||||
run: run ? { id: run.id, status: run.status } : null,
|
||||
};
|
||||
@@ -290,10 +247,8 @@ export class AiChatController {
|
||||
@AuthWorkspace() workspace: Workspace,
|
||||
): Promise<{ markdown: string }> {
|
||||
const chat = await this.assertOwnedChat(dto.chatId, user, workspace);
|
||||
const rows = await this.withReconstructedParts(
|
||||
await this.aiChatMessageRepo.findAllByChat(dto.chatId, workspace.id),
|
||||
// #492: an interrupted-but-still-active turn exports its persisted steps
|
||||
// (reconstructed from the steps table) just like the pre-#492 full row did.
|
||||
const rows = await this.aiChatMessageRepo.findAllByChat(
|
||||
dto.chatId,
|
||||
workspace.id,
|
||||
);
|
||||
const markdown = buildChatMarkdown({
|
||||
@@ -333,13 +288,7 @@ export class AiChatController {
|
||||
workspace.id,
|
||||
)
|
||||
: undefined;
|
||||
// #492: reconnect to an IN-FLIGHT run reconstructs the projection row's parts
|
||||
// from the steps table (the row itself carries only the step marker mid-run);
|
||||
// a finished run's row already has inline parts, so this is a no-op.
|
||||
const [hydrated] = message
|
||||
? await this.withReconstructedParts([message], workspace.id)
|
||||
: [undefined];
|
||||
return { run, message: hydrated ?? null };
|
||||
return { run, message: message ?? null };
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -370,10 +370,12 @@ describe('AiChatService.stream — abortSignal wiring (#184 F3)', () => {
|
||||
);
|
||||
});
|
||||
|
||||
// #490 reactive branch: a provider CONTEXT-OVERFLOW 400 in onError is classified,
|
||||
// records a distinguishable cause, and stamps metadata.replayOverflow so the NEXT
|
||||
// turn's budgeter trims aggressively (the recovery that un-bricks the chat).
|
||||
it('#490: a context-overflow 400 stamps replayOverflow on the finalized row', async () => {
|
||||
// #490/#520 reactive branch: a provider CONTEXT-OVERFLOW 400 in onError is
|
||||
// classified, records a distinguishable cause, and stamps the consecutive-overflow
|
||||
// COUNTER (metadata.replayOverflowCount) so the NEXT turn's budgeter trims with
|
||||
// escalating aggression (the recovery that un-bricks the chat). This is a fresh
|
||||
// chat (empty history -> prior streak 0), so the first overflow stamps count 1.
|
||||
it('#490/#520: a context-overflow 400 stamps replayOverflowCount=1 on the finalized row', async () => {
|
||||
jest
|
||||
.spyOn(Logger.prototype, 'error')
|
||||
.mockImplementation(() => undefined as never);
|
||||
@@ -397,11 +399,14 @@ describe('AiChatService.stream — abortSignal wiring (#184 F3)', () => {
|
||||
metadata: Record<string, unknown>;
|
||||
};
|
||||
expect(patch.status).toBe('error');
|
||||
expect(patch.metadata.replayOverflow).toBe(true);
|
||||
// First overflow on a fresh chat -> k = prior(0) + 1 = 1.
|
||||
expect(patch.metadata.replayOverflowCount).toBe(1);
|
||||
// The legacy boolean is no longer written (the counter supersedes it).
|
||||
expect('replayOverflow' in patch.metadata).toBe(false);
|
||||
expect(patch.metadata.error).toContain('контекстное окно');
|
||||
});
|
||||
|
||||
it('#490: a non-overflow error does NOT stamp replayOverflow', async () => {
|
||||
it('#490/#520: a non-overflow error does NOT stamp the overflow counter', async () => {
|
||||
jest
|
||||
.spyOn(Logger.prototype, 'error')
|
||||
.mockImplementation(() => undefined as never);
|
||||
@@ -412,6 +417,7 @@ describe('AiChatService.stream — abortSignal wiring (#184 F3)', () => {
|
||||
status: string;
|
||||
metadata: Record<string, unknown>;
|
||||
};
|
||||
expect('replayOverflowCount' in patch.metadata).toBe(false);
|
||||
expect('replayOverflow' in patch.metadata).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -30,13 +30,16 @@ import {
|
||||
STEP_LIMIT_NO_ANSWER_MARKER,
|
||||
OUTPUT_DEGENERATION_ERROR,
|
||||
lastAssistantContextTokens,
|
||||
lastAssistantReplayOverflow,
|
||||
lastAssistantReplayOverflowCount,
|
||||
seedActivatedTools,
|
||||
} from './ai-chat.service';
|
||||
import type { AiChatMessage, Workspace } from '@docmost/db/types/entity.types';
|
||||
import { buildSystemPrompt } from './ai-chat.prompt';
|
||||
import type { McpClientsService } from './external-mcp/mcp-clients.service';
|
||||
import { resolveEffectiveReplayThreshold } from './history-budget';
|
||||
import {
|
||||
resolveEffectiveReplayThreshold,
|
||||
REPLAY_MIN_FLOOR_TOKENS,
|
||||
} from './history-budget';
|
||||
|
||||
/**
|
||||
* Unit tests for compactToolOutput: the pure helper that shrinks tool outputs
|
||||
@@ -554,49 +557,123 @@ describe('seedActivatedTools', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('lastAssistantReplayOverflow', () => {
|
||||
describe('lastAssistantReplayOverflowCount', () => {
|
||||
const row = (
|
||||
role: string,
|
||||
metadata: Record<string, unknown> | null,
|
||||
): AiChatMessage => ({ role, metadata }) as unknown as AiChatMessage;
|
||||
|
||||
it('is true only when the LAST assistant turn overflowed', () => {
|
||||
it('reads the consecutive-overflow count from the LAST assistant turn', () => {
|
||||
expect(
|
||||
lastAssistantReplayOverflow([
|
||||
row('assistant', { replayOverflow: true }),
|
||||
lastAssistantReplayOverflowCount([
|
||||
row('assistant', { replayOverflowCount: 3 }),
|
||||
row('user', null),
|
||||
]),
|
||||
).toBe(true);
|
||||
// A recovered (later, non-overflow) assistant turn clears it.
|
||||
).toBe(3);
|
||||
// A recovered (later, non-overflow) assistant turn resets it to 0 — the read
|
||||
// stops at the most recent assistant row, which carries no count.
|
||||
expect(
|
||||
lastAssistantReplayOverflow([
|
||||
row('assistant', { replayOverflow: true }),
|
||||
lastAssistantReplayOverflowCount([
|
||||
row('assistant', { replayOverflowCount: 3 }),
|
||||
row('user', null),
|
||||
row('assistant', { contextTokens: 5 }),
|
||||
]),
|
||||
).toBe(false);
|
||||
expect(lastAssistantReplayOverflow([])).toBe(false);
|
||||
).toBe(0);
|
||||
expect(lastAssistantReplayOverflowCount([])).toBe(0);
|
||||
});
|
||||
|
||||
// #490 reactive recovery: a prior turn stamped `replayOverflow` must make the
|
||||
// NEXT turn's effective budget the AGGRESSIVE 0.5x cut — that harder trim is
|
||||
// what un-bricks a chat that just 400'd on the context window. This exercises
|
||||
// the exact wiring the service uses: read the stamp, then scale the threshold.
|
||||
it('#490: a prior replayOverflow drives the next turn to the 0.5x aggressive budget', () => {
|
||||
// BACK-COMPAT (#520): an in-flight row written by the pre-#520 boolean stamp
|
||||
// (`replayOverflow: true`, no count) reads as k=1 — the old single 0.5× behavior —
|
||||
// so a chat mid-recovery across the deploy does not regress.
|
||||
it('#520 back-compat: a legacy boolean replayOverflow reads as k=1', () => {
|
||||
expect(
|
||||
lastAssistantReplayOverflowCount([
|
||||
row('assistant', { replayOverflow: true }),
|
||||
row('user', null),
|
||||
]),
|
||||
).toBe(1);
|
||||
// A legacy row with the flag absent/false is k=0.
|
||||
expect(
|
||||
lastAssistantReplayOverflowCount([row('assistant', { contextTokens: 5 })]),
|
||||
).toBe(0);
|
||||
});
|
||||
|
||||
// A corrupt/negative persisted count never yields a negative k.
|
||||
it('clamps a corrupt negative count to 0', () => {
|
||||
expect(
|
||||
lastAssistantReplayOverflowCount([
|
||||
row('assistant', { replayOverflowCount: -4 }),
|
||||
]),
|
||||
).toBe(0);
|
||||
});
|
||||
|
||||
// #490/#520 reactive recovery: the prior consecutive-overflow count `k` drives
|
||||
// the next turn's effective budget to an ESCALATING cut (0.5**k) — each further
|
||||
// consecutive 400 tightens it, which is what un-bricks a chat that keeps
|
||||
// overflowing. This exercises the exact wiring the service uses: read the count,
|
||||
// then scale the threshold.
|
||||
it('#490/#520: the prior count drives the next turn to the escalating aggressive budget', () => {
|
||||
const history = [
|
||||
row('assistant', { replayOverflow: true }),
|
||||
row('assistant', { replayOverflowCount: 1 }),
|
||||
row('user', null),
|
||||
];
|
||||
const priorOverflowed = lastAssistantReplayOverflow(history);
|
||||
expect(priorOverflowed).toBe(true);
|
||||
// Base budget 100k -> aggressive recovery halves it to 50k this turn.
|
||||
expect(resolveEffectiveReplayThreshold(100_000, priorOverflowed)).toBe(50_000);
|
||||
const k = lastAssistantReplayOverflowCount(history);
|
||||
expect(k).toBe(1);
|
||||
// Base budget 100k -> first-overflow recovery halves it to 50k this turn.
|
||||
expect(resolveEffectiveReplayThreshold(100_000, k)).toBe(50_000);
|
||||
// A second consecutive overflow (k=2) quarters it.
|
||||
expect(resolveEffectiveReplayThreshold(100_000, 2)).toBe(25_000);
|
||||
// Odd base floors, not rounds.
|
||||
expect(resolveEffectiveReplayThreshold(99_999, true)).toBe(49_999);
|
||||
// No prior overflow -> the base budget is used verbatim (no aggressive cut).
|
||||
expect(resolveEffectiveReplayThreshold(100_000, false)).toBe(100_000);
|
||||
expect(resolveEffectiveReplayThreshold(99_999, 1)).toBe(49_999);
|
||||
// No prior overflow (k=0) -> the base budget is used verbatim (no cut).
|
||||
expect(resolveEffectiveReplayThreshold(100_000, 0)).toBe(100_000);
|
||||
// An explicit off-switch (null) is never overridden, even on recovery.
|
||||
expect(resolveEffectiveReplayThreshold(null, true)).toBeNull();
|
||||
expect(resolveEffectiveReplayThreshold(null, 3)).toBeNull();
|
||||
});
|
||||
|
||||
// #520 escalation table + convergence: the cut deepens each consecutive overflow
|
||||
// and is CLAMPED at the floor so it converges (un-bricks even against a small
|
||||
// real window), instead of the old fixed single 0.5× that stuck at 50k forever.
|
||||
it('#520: escalates and converges to the floor, un-bricking a small real window', () => {
|
||||
const base = 100_000;
|
||||
expect(resolveEffectiveReplayThreshold(base, 0)).toBe(base);
|
||||
expect(resolveEffectiveReplayThreshold(base, 1)).toBe(50_000);
|
||||
expect(resolveEffectiveReplayThreshold(base, 2)).toBe(25_000);
|
||||
expect(resolveEffectiveReplayThreshold(base, 3)).toBe(12_500);
|
||||
|
||||
// Residual-brick regression (#520): with the flat-default base (100k) and a real
|
||||
// model window of ~40k, the OLD fixed 0.5× stuck at 50k forever (> 40k -> 400s
|
||||
// again, never recovers). The escalating cut drops BELOW 40k after enough
|
||||
// consecutive overflows -> the history finally fits -> the chat un-bricks.
|
||||
const realWindow = 40_000;
|
||||
// k=1 (50k) still exceeds the window — the old behavior's terminal state.
|
||||
expect(resolveEffectiveReplayThreshold(base, 1)).toBeGreaterThan(realWindow);
|
||||
// But escalation converges under the window within a couple more turns.
|
||||
const converged = [2, 3, 4, 5].some(
|
||||
(k) => (resolveEffectiveReplayThreshold(base, k) as number) < realWindow,
|
||||
);
|
||||
expect(converged).toBe(true);
|
||||
|
||||
// Convergence is bounded BELOW by the floor: a large k never trims below it.
|
||||
for (const k of [4, 8, 20, 100]) {
|
||||
expect(resolveEffectiveReplayThreshold(base, k)).toBe(REPLAY_MIN_FLOOR_TOKENS);
|
||||
expect(
|
||||
resolveEffectiveReplayThreshold(base, k) as number,
|
||||
).toBeGreaterThanOrEqual(REPLAY_MIN_FLOOR_TOKENS);
|
||||
}
|
||||
});
|
||||
|
||||
// The floor never RAISES a legitimately small configured budget above itself —
|
||||
// that would re-overflow the very window it was configured for.
|
||||
it('#520: never inflates a small configured budget above itself', () => {
|
||||
const small = 5_000; // below the floor
|
||||
expect(resolveEffectiveReplayThreshold(small, 0)).toBe(small);
|
||||
// Even under escalation the effective threshold never exceeds the base.
|
||||
for (const k of [1, 2, 3, 10]) {
|
||||
expect(
|
||||
resolveEffectiveReplayThreshold(small, k) as number,
|
||||
).toBeLessThanOrEqual(small);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
@@ -930,21 +1007,29 @@ describe('flushAssistant', () => {
|
||||
expect(flushed.metadata.error).toBe('boom');
|
||||
});
|
||||
|
||||
// #490 observability: the replay budgeter's decision is stamped on the turn.
|
||||
it('records replayTrimmedToTokens + replayOverflow when provided', () => {
|
||||
// #490/#520 observability: the replay budgeter's decision is stamped on the turn,
|
||||
// now including the consecutive-overflow COUNTER (#520) the next turn escalates on.
|
||||
it('records replayTrimmedToTokens + replayOverflowCount when provided', () => {
|
||||
const f = flushAssistant([], '', 'error', {
|
||||
error: 'ctx',
|
||||
replayTrimmedToTokens: 42_000,
|
||||
replayOverflow: true,
|
||||
replayOverflowCount: 2,
|
||||
});
|
||||
expect(f.metadata.replayTrimmedToTokens).toBe(42_000);
|
||||
expect(f.metadata.replayOverflow).toBe(true);
|
||||
expect(f.metadata.replayOverflowCount).toBe(2);
|
||||
});
|
||||
|
||||
it('omits the replay metadata when not provided', () => {
|
||||
const f = flushAssistant([], '', 'completed', { finishReason: 'stop' });
|
||||
expect('replayTrimmedToTokens' in f.metadata).toBe(false);
|
||||
expect('replayOverflow' in f.metadata).toBe(false);
|
||||
expect('replayOverflowCount' in f.metadata).toBe(false);
|
||||
});
|
||||
|
||||
// A clean finalize (no overflow -> count 0/omitted) leaves NO counter, which the
|
||||
// next turn reads as k=0 — the reset that ends a recovery streak.
|
||||
it('omits replayOverflowCount for a zero/absent count (reset semantics)', () => {
|
||||
const zero = flushAssistant([], '', 'completed', { replayOverflowCount: 0 });
|
||||
expect('replayOverflowCount' in zero.metadata).toBe(false);
|
||||
});
|
||||
|
||||
// #274 observability: the page-change diff the agent saw this turn is persisted
|
||||
|
||||
@@ -22,7 +22,6 @@ import { AiSettingsService } from '../../integrations/ai/ai-settings.service';
|
||||
import { describeProviderError } from '../../integrations/ai/ai-error.util';
|
||||
import { AiChatRepo } from '@docmost/db/repos/ai-chat/ai-chat.repo';
|
||||
import { AiChatMessageRepo } from '@docmost/db/repos/ai-chat/ai-chat-message.repo';
|
||||
import { AiChatRunStepRepo } from '@docmost/db/repos/ai-chat/ai-chat-run-step.repo';
|
||||
import { AiChatPageSnapshotRepo } from '@docmost/db/repos/ai-chat/ai-chat-page-snapshot.repo';
|
||||
import { AiAgentRoleRepo } from '@docmost/db/repos/ai-agent-roles/ai-agent-roles.repo';
|
||||
import { PageRepo } from '@docmost/db/repos/page/page.repo';
|
||||
@@ -141,9 +140,10 @@ const OUTPUT_DEGENERATION_ERROR =
|
||||
|
||||
// Prefix recorded on the assistant row when the provider rejected the turn for
|
||||
// CONTEXT OVERFLOW (#490): the replayed history exceeded the model's window. The
|
||||
// row is ALSO stamped `metadata.replayOverflow` so the NEXT turn's budgeter trims
|
||||
// aggressively (the reactive recovery — the overflowing turn had no usage signal
|
||||
// to trigger preventive trimming, so the classified 400 is what un-bricks it).
|
||||
// row is ALSO stamped `metadata.replayOverflowCount` (the consecutive-overflow
|
||||
// counter, #520) so the NEXT turn's budgeter trims with escalating aggression (the
|
||||
// reactive recovery — the overflowing turn had no usage signal to trigger
|
||||
// preventive trimming, so the classified 400 is what un-bricks it).
|
||||
export const CONTEXT_OVERFLOW_ERROR_PREFIX =
|
||||
'Диалог превысил контекстное окно модели; история будет агрессивно ' +
|
||||
'сокращена на следующем ходу.';
|
||||
@@ -190,11 +190,10 @@ export function stepBudgetWarning(stepNumber: number): string {
|
||||
//
|
||||
// `system` is the in-scope system prompt; we CONCATENATE so the original
|
||||
// persona/context is preserved — a bare `system` override would REPLACE the
|
||||
// whole system prompt for the step. `activatedTools` is a closure Set grown by
|
||||
// loadTools and owned by the streaming loop; the caller seeds it from and
|
||||
// persists it to the chat's metadata across turns (#490), but this function only
|
||||
// READS the Set it is handed, so it stays a pure function of its arguments (not
|
||||
// module-global).
|
||||
// whole system prompt for the step. `activatedTools` is PER-TURN mutable state
|
||||
// owned by the streaming loop (a closure Set grown by loadTools); it is passed
|
||||
// in (not module-global, not persisted) so this stays a pure function of its
|
||||
// arguments.
|
||||
//
|
||||
// NOTE: at AI SDK v7 the per-step `system` field is renamed to `instructions`.
|
||||
// On v6 (`^6.0.134`) `system` is the correct field — adjust when bumping.
|
||||
@@ -519,12 +518,6 @@ export class AiChatService implements OnModuleInit, OnModuleDestroy {
|
||||
// constructions compile unchanged; Nest always injects the real singleton, so
|
||||
// reconcile sees the SAME in-memory active/zombie maps the runner mutates.
|
||||
private readonly aiChatRunService?: AiChatRunService,
|
||||
// #492 append-persist: per-step INSERT into the lightweight steps table (the
|
||||
// O(Σ steps) replacement for the O(n²) full-row `metadata.parts` rewrite).
|
||||
// OPTIONAL so existing positional constructions (int-specs) compile unchanged;
|
||||
// Nest injects the real singleton. When ABSENT the per-step path falls back to
|
||||
// the pre-#492 full-row flush (no regression, only no WAL win).
|
||||
private readonly aiChatRunStepRepo?: AiChatRunStepRepo,
|
||||
) {}
|
||||
|
||||
// #487: periodic reconcile timer (single-process phase 1). Started in
|
||||
@@ -1121,34 +1114,8 @@ export class AiChatService implements OnModuleInit, OnModuleDestroy {
|
||||
chatId,
|
||||
workspace.id,
|
||||
);
|
||||
// #492: HYDRATE needy assistant rows from the steps table BEFORE the replay
|
||||
// map. A #492 mid-run assistant row carries only a step marker
|
||||
// (metadata.parts:[]); its real per-step parts live in `ai_chat_run_steps`.
|
||||
// The graceful terminal callbacks (onFinish/onError/onAbort -> flushAssistant)
|
||||
// assemble the full inline parts, so a normally-ended turn already has them.
|
||||
// But a HARD crash mid-run (SIGKILL/OOM) fires NO terminal callback, so the
|
||||
// row stays parts:[]; without this, rowToUiMessage falls back to an empty
|
||||
// text part and the partial tool-calls/results/text — durable in the steps
|
||||
// table — would DROP OUT of the model's replay context (regressing #183
|
||||
// step-granular durability for the model consumer). Mirrors the controller's
|
||||
// withReconstructedParts EXACTLY (same needy predicate + hydration helper).
|
||||
// Guarded on the optional repo: absent (positional test builds) degrades to
|
||||
// the current behavior rather than crashing.
|
||||
let replayHistory = oldHistory;
|
||||
if (this.aiChatRunStepRepo) {
|
||||
const needy = oldHistory.filter(
|
||||
(r) => r.role === 'assistant' && !rowHasInlineParts(r),
|
||||
);
|
||||
if (needy.length > 0) {
|
||||
const stepsByMessage = await this.aiChatRunStepRepo.findByMessageIds(
|
||||
needy.map((r) => r.id),
|
||||
workspace.id,
|
||||
);
|
||||
replayHistory = hydrateAssistantParts(oldHistory, stepsByMessage);
|
||||
}
|
||||
}
|
||||
const uiMessages: Array<Omit<UIMessage, 'id'> & { id: string }> = [
|
||||
...replayHistory.map(rowToUiMessage),
|
||||
...oldHistory.map(rowToUiMessage),
|
||||
{
|
||||
id: 'pending-user',
|
||||
role: 'user',
|
||||
@@ -1187,9 +1154,7 @@ export class AiChatService implements OnModuleInit, OnModuleDestroy {
|
||||
// hint — confirm it against the persisted history (the preceding assistant
|
||||
// turn must really be aborted/streaming) so a spoofed flag cannot inject the
|
||||
// interrupt note onto an ordinary turn. The partial output the model needs is
|
||||
// already in `messages`: a #492 mid-run row's per-step parts live only in the
|
||||
// `ai_chat_run_steps` table and were hydrated into the replay history above,
|
||||
// so the aborted assistant turn replays WITH its partial parts intact.
|
||||
// already in `messages` (the aborted assistant row replays via findRecent).
|
||||
// Append the new user turn (shape-only) so index -2 is the prior assistant.
|
||||
const interrupted = isInterruptResume(
|
||||
[...oldHistory, { role: 'user', status: null, metadata: null }],
|
||||
@@ -1228,19 +1193,23 @@ export class AiChatService implements OnModuleInit, OnModuleDestroy {
|
||||
}
|
||||
// Last turn's provider-reported context size (authoritative when present).
|
||||
const priorContextTokens = lastAssistantContextTokens(oldHistory);
|
||||
// Reactive recovery (#490): if the LAST turn was rejected for context
|
||||
// overflow (stamped by onError), trim AGGRESSIVELY this turn — the
|
||||
// overflowing turn produced no usage signal, so a normal-threshold trim may
|
||||
// not shrink enough to fit. This is what un-bricks a chat that just 400'd.
|
||||
const priorOverflowed = lastAssistantReplayOverflow(oldHistory);
|
||||
// Reactive recovery (#490/#520): `k` = how many CONSECUTIVE preceding turns
|
||||
// were rejected for context overflow (stamped by onError). Each consecutive
|
||||
// overflow trims MORE aggressively (resolveEffectiveReplayThreshold scales the
|
||||
// budget by 0.5**k, clamped at the floor) so recovery ESCALATES until the
|
||||
// history fits — the overflowing turn produced no usage signal, so a single
|
||||
// fixed cut may not shrink enough when the real model window is small. This is
|
||||
// what un-bricks a chat that keeps 400'ing on the context window.
|
||||
const priorOverflowCount = lastAssistantReplayOverflowCount(oldHistory);
|
||||
const effectiveThreshold = resolveEffectiveReplayThreshold(
|
||||
replayBudget.thresholdTokens,
|
||||
priorOverflowed,
|
||||
priorOverflowCount,
|
||||
);
|
||||
if (priorOverflowed) {
|
||||
if (priorOverflowCount > 0) {
|
||||
this.logger.warn(
|
||||
`AI chat (chat ${chatId}): previous turn hit context overflow; ` +
|
||||
`applying aggressive replay budget (${effectiveThreshold} tokens).`,
|
||||
`AI chat (chat ${chatId}): ${priorOverflowCount} consecutive context ` +
|
||||
`overflow(s); applying escalated aggressive replay budget ` +
|
||||
`(${effectiveThreshold} tokens).`,
|
||||
);
|
||||
}
|
||||
const preTrim = trimHistoryForReplay(
|
||||
@@ -1248,7 +1217,7 @@ export class AiChatService implements OnModuleInit, OnModuleDestroy {
|
||||
effectiveThreshold,
|
||||
// A prior OVERFLOW means the provider count is stale/absent — force the
|
||||
// char-estimate path by ignoring priorContextTokens on recovery.
|
||||
priorOverflowed ? undefined : priorContextTokens,
|
||||
priorOverflowCount > 0 ? undefined : priorContextTokens,
|
||||
);
|
||||
messages = preTrim.messages;
|
||||
// Observability (#490): record the budgeter's decision on the turn so the UI
|
||||
@@ -1446,11 +1415,10 @@ export class AiChatService implements OnModuleInit, OnModuleDestroy {
|
||||
const baseTools = { ...external.tools, ...docmostTools };
|
||||
|
||||
// Deferred tool loading state (#332), scoped to THIS streaming loop:
|
||||
// - `activatedTools` is a fresh closure Set per streamText call (not
|
||||
// module-global), SEEDED from the chat's persisted metadata.activatedTools
|
||||
// (#490, just below) so activation carries across turns. loadTools.execute
|
||||
// adds to it; prepareAgentStep reads it to widen `activeTools` on the NEXT
|
||||
// step; turn end persists it back.
|
||||
// - `activatedTools` is per-TURN mutable state — a fresh closure Set created
|
||||
// per streamText call, NOT module-global and NOT persisted, so a new turn
|
||||
// starts cold. loadTools.execute adds to it; prepareAgentStep reads it to
|
||||
// widen `activeTools` on the NEXT step.
|
||||
// - `validDeferredNames` = every tool that is NOT core (the in-app deferred
|
||||
// tools + ALL external MCP tools), computed from the ACTUAL toolset so an
|
||||
// external tool is loadable by its namespaced name. loadTools rejects any
|
||||
@@ -1594,57 +1562,17 @@ export class AiChatService implements OnModuleInit, OnModuleDestroy {
|
||||
// connection when finalize runs, so the SQL `WHERE status='streaming'`
|
||||
// (not this flag) is what prevents it clobbering the terminal row.
|
||||
if (finalized) return null;
|
||||
// The count derives from capturedSteps.length at THIS instant, so the
|
||||
// returned value is EXACTLY the persisted `stepsPersisted` the ring rotates
|
||||
// on (whether we take the append-persist path or the legacy fallback).
|
||||
const stepsPersisted = capturedSteps.length;
|
||||
// Build the flush ONCE so the returned count is EXACTLY the persisted
|
||||
// `stepsPersisted` (both derive from capturedSteps.length at this instant).
|
||||
const flushed = flushAssistant(capturedSteps, '', 'streaming', {
|
||||
pageChanged,
|
||||
partsCache,
|
||||
});
|
||||
const stepsPersisted = flushed.metadata.stepsPersisted as number;
|
||||
try {
|
||||
if (this.aiChatRunStepRepo) {
|
||||
// #492 APPEND-PERSIST: write only THIS finished step's parts to the
|
||||
// steps table (O(step) WAL), then bump the row's CHEAP step marker —
|
||||
// NO growing `metadata.parts` blob (that O(n²) full-row rewrite is
|
||||
// exactly what this removes). The full `metadata.parts` is assembled
|
||||
// once at finalize; a mid-run resume seed is reconstructed from the
|
||||
// step rows (reconstructRunParts). The INSERT is idempotent
|
||||
// (ON CONFLICT DO NOTHING), so a re-fired step never doubles the parts.
|
||||
const index = stepsPersisted - 1;
|
||||
if (index >= 0) {
|
||||
const stepParts = assistantParts(
|
||||
[capturedSteps[index]],
|
||||
'',
|
||||
partsCache,
|
||||
);
|
||||
await this.aiChatRunStepRepo.insertStep(
|
||||
assistantId,
|
||||
workspace.id,
|
||||
index,
|
||||
stepParts,
|
||||
);
|
||||
}
|
||||
// Marker UPDATE: advance stepsPersisted + keep the toolTrace era marker
|
||||
// (bumps updatedAt so the delta poll observes the step, and carries the
|
||||
// frontier a resuming client attaches from). Scoped onlyIfStreaming so a
|
||||
// late marker never clobbers the terminal finalize.
|
||||
await this.aiChatMessageRepo.update(
|
||||
assistantId,
|
||||
workspace.id,
|
||||
{ metadata: stepMarkerMetadata(stepsPersisted) },
|
||||
{ onlyIfStreaming: true },
|
||||
);
|
||||
} else {
|
||||
// Legacy fallback (no steps table wired — positional test builds): the
|
||||
// pre-#492 full-row flush, so parts still land inline on the row.
|
||||
const flushed = flushAssistant(capturedSteps, '', 'streaming', {
|
||||
pageChanged,
|
||||
partsCache,
|
||||
});
|
||||
await this.aiChatMessageRepo.update(
|
||||
assistantId,
|
||||
workspace.id,
|
||||
flushed,
|
||||
{ onlyIfStreaming: true },
|
||||
);
|
||||
}
|
||||
await this.aiChatMessageRepo.update(assistantId, workspace.id, flushed, {
|
||||
onlyIfStreaming: true,
|
||||
});
|
||||
return stepsPersisted;
|
||||
} catch (err) {
|
||||
this.logger.warn(
|
||||
@@ -1981,7 +1909,12 @@ export class AiChatService implements OnModuleInit, OnModuleDestroy {
|
||||
pageChanged,
|
||||
partsCache,
|
||||
replayTrimmedToTokens,
|
||||
replayOverflow: overflow || undefined,
|
||||
// #520: escalate the consecutive-overflow counter so the NEXT turn
|
||||
// trims MORE aggressively (0.5**k). k grows by 1 each consecutive
|
||||
// overflow; a clean finalize omits the field, resetting it to 0.
|
||||
replayOverflowCount: overflow
|
||||
? priorOverflowCount + 1
|
||||
: undefined,
|
||||
}),
|
||||
);
|
||||
// #184: settle the RUN as failed, carrying the provider/transport cause.
|
||||
@@ -2413,22 +2346,39 @@ export function seedActivatedTools(
|
||||
}
|
||||
|
||||
/**
|
||||
* Whether the most recent assistant turn was rejected for CONTEXT OVERFLOW
|
||||
* (#490): its row carries `metadata.replayOverflow` (stamped by the stream's
|
||||
* onError). The next turn's budgeter reads this to trim aggressively — the
|
||||
* reactive recovery. Only the LAST assistant turn matters (an older overflow was
|
||||
* already recovered), so we stop at the first assistant row scanning backwards.
|
||||
* How many CONSECUTIVE recent turns were rejected for CONTEXT OVERFLOW (#490/#520):
|
||||
* `k`, read from the most recent assistant row's `metadata.replayOverflowCount`
|
||||
* (stamped by the stream's onError, incremented each consecutive overflow and reset
|
||||
* to 0 on any clean finalize). The next turn's budgeter feeds this to
|
||||
* {@link resolveEffectiveReplayThreshold} to trim with ESCALATING aggression — the
|
||||
* reactive recovery. Only the LAST assistant turn matters (its count already carries
|
||||
* the consecutive streak; an older overflow followed by a clean turn was recovered),
|
||||
* so we stop at the first assistant row scanning backwards.
|
||||
*
|
||||
* BACK-COMPAT: a row written by the pre-#520 boolean stamp (`replayOverflow: true`,
|
||||
* no count) is read as k=1 — the old single 0.5× behavior — so in-flight chats do
|
||||
* not regress across the deploy.
|
||||
*/
|
||||
export function lastAssistantReplayOverflow(
|
||||
export function lastAssistantReplayOverflowCount(
|
||||
history: ReadonlyArray<AiChatMessage>,
|
||||
): boolean {
|
||||
): number {
|
||||
for (let i = history.length - 1; i >= 0; i--) {
|
||||
const row = history[i];
|
||||
if (row.role !== 'assistant') continue;
|
||||
const meta = (row.metadata ?? {}) as { replayOverflow?: unknown };
|
||||
return meta.replayOverflow === true;
|
||||
const meta = (row.metadata ?? {}) as {
|
||||
replayOverflowCount?: unknown;
|
||||
replayOverflow?: unknown;
|
||||
};
|
||||
if (typeof meta.replayOverflowCount === 'number') {
|
||||
// Guard against a corrupt/negative persisted value.
|
||||
return meta.replayOverflowCount > 0
|
||||
? Math.floor(meta.replayOverflowCount)
|
||||
: 0;
|
||||
}
|
||||
// Back-compat: legacy boolean stamp -> one overflow (0.5× cut).
|
||||
return meta.replayOverflow === true ? 1 : 0;
|
||||
}
|
||||
return false;
|
||||
return 0;
|
||||
}
|
||||
|
||||
/** The last message with role 'user' from a useChat payload, if any. */
|
||||
@@ -2824,122 +2774,6 @@ export function rowToUiMessage(row: AiChatMessage): Omit<UIMessage, 'id'> & {
|
||||
return { id: row.id, role, parts: parts as UIMessage['parts'] };
|
||||
}
|
||||
|
||||
/**
|
||||
* Cheap step-marker metadata for the #492 per-step UPDATE. Advances
|
||||
* `stepsPersisted` (the resume attach frontier) and keeps the `toolTraceVersion`
|
||||
* era marker, WITHOUT the growing `parts` blob (those live in the steps table
|
||||
* now; the full `metadata.parts` is assembled once at finalize by flushAssistant).
|
||||
* `parts: []` is kept for shape stability — it reads as an empty inline-parts row,
|
||||
* which is exactly the discriminator that routes reconstruction to the steps table.
|
||||
*/
|
||||
export function stepMarkerMetadata(
|
||||
stepsPersisted: number,
|
||||
): Record<string, unknown> {
|
||||
return { parts: [], toolTraceVersion: 2, stepsPersisted };
|
||||
}
|
||||
|
||||
/**
|
||||
* Whether an assistant row already carries its full UI parts INLINE on the row
|
||||
* (`metadata.parts`). TRUE for every FINISHED row — old-era rows AND #492 rows,
|
||||
* whose full parts are assembled once at finalize — and for old-era streaming
|
||||
* snapshots (the pre-#492 per-step full-row flush). FALSE for a #492 MID-RUN
|
||||
* record, whose per-step parts live in the `ai_chat_run_steps` table. This is the
|
||||
* era discriminator the reconstruct seam branches on — no schema flag needed.
|
||||
*/
|
||||
export function rowHasInlineParts(row: { metadata?: unknown }): boolean {
|
||||
const meta = (row.metadata ?? {}) as { parts?: unknown };
|
||||
return Array.isArray(meta.parts) && meta.parts.length > 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Concatenate persisted per-step parts (in `stepIndex` order) into the turn's UI
|
||||
* parts (#492). Reproduces EXACTLY what flushAssistant → assistantParts would have
|
||||
* written to `metadata.parts` for those finished steps, since each step row stored
|
||||
* `assistantParts([step])` at persist time.
|
||||
*/
|
||||
export function assembleStepParts(
|
||||
stepRows: ReadonlyArray<{ stepIndex: number; parts: unknown }>,
|
||||
): UIMessage['parts'] {
|
||||
const parts: Array<Record<string, unknown>> = [];
|
||||
for (const step of [...stepRows].sort((a, b) => a.stepIndex - b.stepIndex)) {
|
||||
if (Array.isArray(step.parts)) {
|
||||
parts.push(...(step.parts as Array<Record<string, unknown>>));
|
||||
}
|
||||
}
|
||||
return parts as UIMessage['parts'];
|
||||
}
|
||||
|
||||
/**
|
||||
* reconstructRunParts (#492) — the single backend-switch seam. Given an assistant
|
||||
* ROW and its persisted step rows, return the turn's UI `parts` + the persisted
|
||||
* step count, reading from the ROW when it already carries inline parts (old-era
|
||||
* records AND every finished record) and from the STEPS TABLE otherwise (a #492
|
||||
* mid-run record). The higher-level consumers (attach seed, delta poll, export)
|
||||
* route their row→parts through this / {@link hydrateAssistantParts}, so old and
|
||||
* new records reconstruct identically WITHOUT the consumers branching on the era.
|
||||
*/
|
||||
export function reconstructRunParts(
|
||||
row: { metadata?: unknown; content?: string | null },
|
||||
stepRows: ReadonlyArray<{ stepIndex: number; parts: unknown }>,
|
||||
): { parts: UIMessage['parts']; stepsPersisted: number } {
|
||||
if (rowHasInlineParts(row)) {
|
||||
const meta = row.metadata as {
|
||||
parts: UIMessage['parts'];
|
||||
stepsPersisted?: number;
|
||||
};
|
||||
return {
|
||||
parts: meta.parts,
|
||||
stepsPersisted:
|
||||
typeof meta.stepsPersisted === 'number'
|
||||
? meta.stepsPersisted
|
||||
: stepRows.length,
|
||||
};
|
||||
}
|
||||
if (stepRows.length > 0) {
|
||||
return {
|
||||
parts: assembleStepParts(stepRows),
|
||||
stepsPersisted: stepRows.length,
|
||||
};
|
||||
}
|
||||
// No inline parts and no step rows: an old-era seed / empty streaming row. Fall
|
||||
// back to a single text part from `content` (mirrors rowToUiMessage).
|
||||
return {
|
||||
parts: textPart(row.content ?? '') as UIMessage['parts'],
|
||||
stepsPersisted: 0,
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Fill each assistant row's `metadata.parts` from its step rows when the row does
|
||||
* not already carry them inline (a #492 mid-run record), so a consumer that reads
|
||||
* `metadata.parts` off the RAW row (the client seed/poll, the Markdown export)
|
||||
* sees the reconstructed parts with NO change to itself. Rows that already have
|
||||
* inline parts (old-era + finished) and non-assistant rows pass through untouched.
|
||||
* Pure: returns new row objects, never mutates the inputs.
|
||||
*/
|
||||
export function hydrateAssistantParts<
|
||||
T extends { id: string; role?: string; metadata?: unknown },
|
||||
>(
|
||||
rows: ReadonlyArray<T>,
|
||||
stepsByMessage: Map<
|
||||
string,
|
||||
ReadonlyArray<{ stepIndex: number; parts: unknown }>
|
||||
>,
|
||||
): T[] {
|
||||
return rows.map((row) => {
|
||||
if (row.role !== 'assistant' || rowHasInlineParts(row)) return row;
|
||||
const steps = stepsByMessage.get(row.id);
|
||||
if (!steps || steps.length === 0) return row;
|
||||
return {
|
||||
...row,
|
||||
metadata: {
|
||||
...((row.metadata ?? {}) as Record<string, unknown>),
|
||||
parts: assembleStepParts(steps),
|
||||
},
|
||||
};
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* The persisted-row patch shape produced by {@link flushAssistant}. It is the
|
||||
* SAME shape the assistant repo insert/update consume (content + toolCalls +
|
||||
@@ -3084,9 +2918,11 @@ export function flushAssistant(
|
||||
// the (estimated) token size it trimmed to — the UI can show "replay truncated
|
||||
// at N tokens". Omitted when nothing was trimmed.
|
||||
replayTrimmedToTokens?: number;
|
||||
// #490 reactive branch: set when the provider rejected this turn for context
|
||||
// overflow. Stamped into metadata so the NEXT turn's budgeter trims aggressively.
|
||||
replayOverflow?: boolean;
|
||||
// #490/#520 reactive branch: the consecutive context-overflow count for THIS
|
||||
// turn (prior streak + 1) when the provider rejected it for context overflow.
|
||||
// Stamped into metadata so the NEXT turn's budgeter trims with escalating
|
||||
// aggression (0.5**k). Omitted (undefined) on a clean turn, which resets k to 0.
|
||||
replayOverflowCount?: number;
|
||||
},
|
||||
): AssistantFlush {
|
||||
const finished = capturedSteps ?? [];
|
||||
@@ -3139,7 +2975,8 @@ export function flushAssistant(
|
||||
metadata.maxContextTokens = extra.maxContextTokens;
|
||||
if (extra?.replayTrimmedToTokens)
|
||||
metadata.replayTrimmedToTokens = extra.replayTrimmedToTokens;
|
||||
if (extra?.replayOverflow) metadata.replayOverflow = true;
|
||||
if (extra?.replayOverflowCount && extra.replayOverflowCount > 0)
|
||||
metadata.replayOverflowCount = extra.replayOverflowCount;
|
||||
if (extra?.error) metadata.error = extra.error;
|
||||
// Persist the page-change diff the agent saw this turn (#274 observability),
|
||||
// so history / the Markdown export can show what the user changed. Only when
|
||||
|
||||
@@ -1,6 +1,11 @@
|
||||
import { randomBytes } from 'crypto';
|
||||
import { Client } from 'pg';
|
||||
import { flushAssistant, serializeSteps } from './ai-chat.service';
|
||||
import {
|
||||
flushAssistant,
|
||||
serializeSteps,
|
||||
lastAssistantReplayOverflowCount,
|
||||
} from './ai-chat.service';
|
||||
import type { AiChatMessage } from '@docmost/db/types/entity.types';
|
||||
|
||||
/**
|
||||
* #490 write-volume regression — an OBSERVABLE-PROPERTY test on a LIVE Postgres,
|
||||
@@ -207,3 +212,111 @@ describe('#490 write-volume on a live Postgres (pg_current_wal_lsn delta)', () =
|
||||
expect(v2).toBeLessThan(v1 * 0.75);
|
||||
}, 120_000);
|
||||
});
|
||||
|
||||
/**
|
||||
* #520 reactive-recovery COUNTER lifecycle on a LIVE Postgres — proves the
|
||||
* consecutive-overflow count survives a real jsonb metadata round-trip (the persist
|
||||
* path), not just an in-memory object. flushAssistant BUILDS the row metadata, we
|
||||
* WRITE it to a jsonb column, READ it back, then reconstruct the assistant row and
|
||||
* run lastAssistantReplayOverflowCount over it — exactly the read the next turn does.
|
||||
*
|
||||
* The lifecycle proven end-to-end through pg:
|
||||
* - consecutive overflows INCREMENT k (1 -> 2 -> 3);
|
||||
* - a CLEAN finalize omits the field, which the reader treats as a RESET to 0;
|
||||
* - a legacy boolean row (`replayOverflow: true`) reads back as k=1 (back-compat).
|
||||
*/
|
||||
describe('#520 overflow-counter lifecycle on a live Postgres (jsonb round-trip)', () => {
|
||||
let client: Client | undefined;
|
||||
let available = false;
|
||||
|
||||
beforeAll(async () => {
|
||||
try {
|
||||
client = new Client(CONN);
|
||||
await client.connect();
|
||||
await client.query('SELECT 1');
|
||||
available = true;
|
||||
} catch {
|
||||
available = false;
|
||||
client = undefined;
|
||||
}
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await client?.end().catch(() => undefined);
|
||||
});
|
||||
|
||||
// Round-trip an arbitrary metadata object through a real jsonb column and read it
|
||||
// back as the reconstructed assistant row the next turn would load.
|
||||
async function roundTrip(
|
||||
c: Client,
|
||||
metadata: unknown,
|
||||
): Promise<AiChatMessage> {
|
||||
await c.query('UPDATE _wal_counter SET metadata=$1 WHERE id=1', [
|
||||
JSON.stringify(metadata),
|
||||
]);
|
||||
const back = (await c.query('SELECT metadata FROM _wal_counter WHERE id=1'))
|
||||
.rows[0].metadata as Record<string, unknown>;
|
||||
return { role: 'assistant', metadata: back } as unknown as AiChatMessage;
|
||||
}
|
||||
|
||||
it('increments across consecutive overflows, resets on a clean turn, and honors the legacy boolean', async () => {
|
||||
if (!available || !client) {
|
||||
console.warn('SKIP: gitmost-test-pg not reachable; skipping counter test.');
|
||||
return;
|
||||
}
|
||||
const c = client;
|
||||
await c.query('DROP TABLE IF EXISTS _wal_counter');
|
||||
await c.query('CREATE TABLE _wal_counter(id int primary key, metadata jsonb)');
|
||||
await c.query("INSERT INTO _wal_counter VALUES (1, '{}'::jsonb)");
|
||||
|
||||
// Turn 1 overflow: prior streak 0 -> stamp k=1 (as the service does: prior+1).
|
||||
let prior = lastAssistantReplayOverflowCount([]); // fresh chat
|
||||
expect(prior).toBe(0);
|
||||
let row = await roundTrip(
|
||||
c,
|
||||
flushAssistant([], '', 'error', {
|
||||
error: 'ctx',
|
||||
replayOverflowCount: prior + 1,
|
||||
}).metadata,
|
||||
);
|
||||
prior = lastAssistantReplayOverflowCount([row]);
|
||||
expect(prior).toBe(1);
|
||||
|
||||
// Turn 2 overflow: prior 1 -> stamp k=2.
|
||||
row = await roundTrip(
|
||||
c,
|
||||
flushAssistant([], '', 'error', {
|
||||
error: 'ctx',
|
||||
replayOverflowCount: prior + 1,
|
||||
}).metadata,
|
||||
);
|
||||
prior = lastAssistantReplayOverflowCount([row]);
|
||||
expect(prior).toBe(2);
|
||||
|
||||
// Turn 3 overflow: prior 2 -> stamp k=3.
|
||||
row = await roundTrip(
|
||||
c,
|
||||
flushAssistant([], '', 'error', {
|
||||
error: 'ctx',
|
||||
replayOverflowCount: prior + 1,
|
||||
}).metadata,
|
||||
);
|
||||
prior = lastAssistantReplayOverflowCount([row]);
|
||||
expect(prior).toBe(3);
|
||||
|
||||
// Turn 4 CLEAN finalize: no overflow -> the field is omitted -> reset to 0.
|
||||
row = await roundTrip(
|
||||
c,
|
||||
flushAssistant([], 'all good', 'completed', { finishReason: 'stop' })
|
||||
.metadata,
|
||||
);
|
||||
expect('replayOverflowCount' in (row.metadata as object)).toBe(false);
|
||||
expect(lastAssistantReplayOverflowCount([row])).toBe(0);
|
||||
|
||||
// Back-compat: a row persisted by the pre-#520 boolean stamp reads back as k=1.
|
||||
row = await roundTrip(c, { replayOverflow: true });
|
||||
expect(lastAssistantReplayOverflowCount([row])).toBe(1);
|
||||
|
||||
await c.query('DROP TABLE IF EXISTS _wal_counter');
|
||||
}, 60_000);
|
||||
});
|
||||
|
||||
@@ -1,14 +1,79 @@
|
||||
import type { ModelMessage } from 'ai';
|
||||
import {
|
||||
resolveReplayBudget,
|
||||
resolveEffectiveReplayThreshold,
|
||||
isContextOverflowError,
|
||||
estimateMessagesTokens,
|
||||
trimHistoryForReplay,
|
||||
REPLAY_BUDGET_DEFAULT_TOKENS,
|
||||
REPLAY_MIN_FLOOR_TOKENS,
|
||||
REPLAY_TRUNCATION_MARKER,
|
||||
REPLAY_TURN_COLLAPSED_MARKER,
|
||||
} from './history-budget';
|
||||
|
||||
describe('resolveEffectiveReplayThreshold (#520 iterative escalation)', () => {
|
||||
// The escalation table: each consecutive overflow (k) deepens the cut by 0.5×.
|
||||
it('scales the base by 0.5**k, flooring (not rounding) fractional tokens', () => {
|
||||
const base = 100_000;
|
||||
expect(resolveEffectiveReplayThreshold(base, 0)).toBe(base); // k=0: unchanged
|
||||
expect(resolveEffectiveReplayThreshold(base, 1)).toBe(50_000); // 0.5×
|
||||
expect(resolveEffectiveReplayThreshold(base, 2)).toBe(25_000); // 0.25×
|
||||
expect(resolveEffectiveReplayThreshold(base, 3)).toBe(12_500); // 0.125×
|
||||
// Floors, not rounds.
|
||||
expect(resolveEffectiveReplayThreshold(99_999, 1)).toBe(49_999);
|
||||
});
|
||||
|
||||
it('passes a null base (trimming OFF) through unchanged for any k', () => {
|
||||
for (const k of [0, 1, 2, 5, 100]) {
|
||||
expect(resolveEffectiveReplayThreshold(null, k)).toBeNull();
|
||||
}
|
||||
});
|
||||
|
||||
// The crux of #520: convergence. A large k is clamped at REPLAY_MIN_FLOOR_TOKENS,
|
||||
// so the escalation CONVERGES to a small-but-usable budget instead of trimming to
|
||||
// zero — and, unlike the old fixed 0.5× that stuck at 50k, it drops far enough to
|
||||
// fit a small real model window.
|
||||
it('clamps a large k at the floor (converges, never below)', () => {
|
||||
const base = 100_000;
|
||||
for (const k of [4, 6, 10, 50, 200]) {
|
||||
const t = resolveEffectiveReplayThreshold(base, k) as number;
|
||||
expect(t).toBe(REPLAY_MIN_FLOOR_TOKENS);
|
||||
expect(t).toBeGreaterThanOrEqual(REPLAY_MIN_FLOOR_TOKENS);
|
||||
}
|
||||
});
|
||||
|
||||
// Residual-brick regression (#520): flat-default base 100k, real window ~40k. The
|
||||
// OLD fixed single 0.5× stuck at 50k > 40k forever (re-overflows every turn — the
|
||||
// brick). The iterative cut drops BELOW 40k after a couple more consecutive
|
||||
// overflows, so the history finally fits and the chat un-bricks.
|
||||
it('un-bricks: escalation drops below a small real window the fixed 0.5× never could', () => {
|
||||
const base = 100_000;
|
||||
const realWindow = 40_000;
|
||||
// The old terminal state: 0.5× = 50k, still above the window.
|
||||
expect(resolveEffectiveReplayThreshold(base, 1)).toBeGreaterThan(realWindow);
|
||||
// Escalation converges under the window.
|
||||
const converged = [2, 3, 4, 5].some(
|
||||
(k) => (resolveEffectiveReplayThreshold(base, k) as number) < realWindow,
|
||||
);
|
||||
expect(converged).toBe(true);
|
||||
// MUTATION SENTINEL: reverting `** k` to `** 1` (fixed 0.5×) makes every k yield
|
||||
// 50k, so `converged` above would be FALSE and this test reddens. Removing the
|
||||
// floor reddens the clamp test instead.
|
||||
});
|
||||
|
||||
// The floor never RAISES a legitimately small configured budget above itself
|
||||
// (min(floor, base)); doing so would re-overflow the very small window it was set
|
||||
// for. So a base BELOW the floor is passed through unchanged and never inflated.
|
||||
it('never inflates a small configured budget above itself', () => {
|
||||
const small = 5_000; // below REPLAY_MIN_FLOOR_TOKENS
|
||||
expect(resolveEffectiveReplayThreshold(small, 0)).toBe(small);
|
||||
for (const k of [1, 2, 3, 10]) {
|
||||
const t = resolveEffectiveReplayThreshold(small, k) as number;
|
||||
expect(t).toBeLessThanOrEqual(small);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe('resolveReplayBudget', () => {
|
||||
it('uses floor(0.7 x window) for a configured window (no cap)', () => {
|
||||
// 0.7 x 60k = 42k
|
||||
|
||||
@@ -22,10 +22,25 @@ export const REPLAY_BUDGET_DEFAULT_TOKENS = 100_000;
|
||||
/** Fraction of a configured context window used as the budget. */
|
||||
export const REPLAY_BUDGET_WINDOW_FRACTION = 0.7;
|
||||
/**
|
||||
* Fraction of the normal budget used for the REACTIVE re-trim after a provider
|
||||
* context-overflow 400 — the preventive estimate under-counted, so cut harder.
|
||||
* Per-step fraction of the normal budget applied on the REACTIVE re-trim after a
|
||||
* provider context-overflow 400 — the preventive estimate under-counted, so cut
|
||||
* harder. This is now applied ITERATIVELY: with `k` consecutive overflow turns the
|
||||
* budget is scaled by `fraction ** k` (k=1 -> 0.5×, k=2 -> 0.25×, …), so recovery
|
||||
* ESCALATES turn over turn until the replayed history finally fits, instead of the
|
||||
* old single fixed 0.5× cut that could never un-brick a chat whose real model
|
||||
* window is smaller than 0.5 × the (unconfigured, flat-default) base budget (#520).
|
||||
*/
|
||||
export const REPLAY_AGGRESSIVE_FRACTION = 0.5;
|
||||
/**
|
||||
* Lower bound (tokens) on the escalating reactive budget: the iterative cut is
|
||||
* clamped here so it CONVERGES (a fixed floor, not an ever-shrinking value that
|
||||
* would eventually trim everything). Rationale: below ~8k tokens a chat cannot
|
||||
* carry meaningful recent context, and even a small real model window comfortably
|
||||
* fits this much — keep-recent-turns still applies on top, so a handful of recent
|
||||
* turns survive. It is never applied so as to RAISE a legitimately small configured
|
||||
* budget (that would re-overflow a tiny window); see resolveEffectiveReplayThreshold.
|
||||
*/
|
||||
export const REPLAY_MIN_FLOOR_TOKENS = 8_000;
|
||||
/**
|
||||
* Turns (a user message + its assistant/tool replies) kept FULL at the tail,
|
||||
* including the current one — never trimmed. Older turns are compacted first.
|
||||
@@ -85,22 +100,34 @@ export function resolveReplayBudget(rawContextWindow: unknown): ReplayBudget {
|
||||
}
|
||||
|
||||
/**
|
||||
* The effective replay threshold for THIS turn, given the base budget and whether
|
||||
* the PREVIOUS turn hit a context-overflow 400 (the reactive-recovery signal,
|
||||
* `metadata.replayOverflow`). On recovery the base budget is scaled down by
|
||||
* {@link REPLAY_AGGRESSIVE_FRACTION}: the overflowing turn produced no usage
|
||||
* signal, so the preventive estimate under-counted and a normal-threshold trim may
|
||||
* not shrink enough to fit — this harder cut is what un-bricks the chat.
|
||||
* The effective replay threshold for THIS turn, given the base budget and `k` — the
|
||||
* number of CONSECUTIVE preceding turns that hit a context-overflow 400 (the
|
||||
* reactive-recovery signal `metadata.replayOverflowCount`, read from the last
|
||||
* assistant row). On recovery the base budget is scaled down ITERATIVELY by
|
||||
* {@link REPLAY_AGGRESSIVE_FRACTION} ** k and clamped at {@link REPLAY_MIN_FLOOR_TOKENS}:
|
||||
* - k=0 -> base unchanged (no overflow: nothing to recover from).
|
||||
* - k=1 -> floor(0.5 × base); k=2 -> floor(0.25 × base); … each further consecutive
|
||||
* overflow tightens the cut, so recovery ESCALATES until the history fits.
|
||||
* - the escalation is clamped at the floor so it CONVERGES — this is what un-bricks
|
||||
* a chat whose real model window is smaller than a single 0.5× cut of the base
|
||||
* (e.g. an unconfigured window: flat-default base 100k, real window <50k) (#520).
|
||||
*
|
||||
* The overflowing turn produced no usage signal, so the preventive estimate
|
||||
* under-counted and a normal-threshold (or single fixed 0.5×) trim may not shrink
|
||||
* enough to fit; the escalating cut is what recovers such a chat.
|
||||
*
|
||||
* A `null` base budget (trimming OFF) is passed through unchanged: an explicit
|
||||
* off-switch is never overridden by the recovery path.
|
||||
* off-switch is never overridden by the recovery path. The floor is applied as
|
||||
* `min(floor, base)` so it never RAISES a legitimately small configured budget
|
||||
* above itself (which would re-overflow the same small window it was set for).
|
||||
*/
|
||||
export function resolveEffectiveReplayThreshold(
|
||||
thresholdTokens: number | null,
|
||||
priorOverflowed: boolean,
|
||||
k: number,
|
||||
): number | null {
|
||||
if (!priorOverflowed || thresholdTokens == null) return thresholdTokens;
|
||||
return Math.floor(thresholdTokens * REPLAY_AGGRESSIVE_FRACTION);
|
||||
if (thresholdTokens == null || k <= 0) return thresholdTokens;
|
||||
const scaled = Math.floor(thresholdTokens * REPLAY_AGGRESSIVE_FRACTION ** k);
|
||||
return Math.max(scaled, Math.min(REPLAY_MIN_FLOOR_TOKENS, thresholdTokens));
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -32,7 +32,6 @@ import { TemplateRepo } from '@docmost/db/repos/template/template.repo';
|
||||
import { AiChatRepo } from '@docmost/db/repos/ai-chat/ai-chat.repo';
|
||||
import { AiChatMessageRepo } from '@docmost/db/repos/ai-chat/ai-chat-message.repo';
|
||||
import { AiChatRunRepo } from '@docmost/db/repos/ai-chat/ai-chat-run.repo';
|
||||
import { AiChatRunStepRepo } from '@docmost/db/repos/ai-chat/ai-chat-run-step.repo';
|
||||
import { AiChatPageSnapshotRepo } from '@docmost/db/repos/ai-chat/ai-chat-page-snapshot.repo';
|
||||
import { AiProviderCredentialsRepo } from '@docmost/db/repos/ai-chat/ai-provider-credentials.repo';
|
||||
import { AiMcpServerRepo } from '@docmost/db/repos/ai-chat/ai-mcp-server.repo';
|
||||
@@ -126,7 +125,6 @@ import { firstSqlToken } from '../integrations/metrics/metrics.constants';
|
||||
AiChatRepo,
|
||||
AiChatMessageRepo,
|
||||
AiChatRunRepo,
|
||||
AiChatRunStepRepo,
|
||||
AiChatPageSnapshotRepo,
|
||||
AiProviderCredentialsRepo,
|
||||
AiMcpServerRepo,
|
||||
@@ -163,7 +161,6 @@ import { firstSqlToken } from '../integrations/metrics/metrics.constants';
|
||||
AiChatRepo,
|
||||
AiChatMessageRepo,
|
||||
AiChatRunRepo,
|
||||
AiChatRunStepRepo,
|
||||
AiChatPageSnapshotRepo,
|
||||
AiProviderCredentialsRepo,
|
||||
AiMcpServerRepo,
|
||||
|
||||
@@ -1,70 +0,0 @@
|
||||
import { type Kysely, sql } from 'kysely';
|
||||
|
||||
/**
|
||||
* `ai_chat_run_steps` — append-only per-step persistence for an assistant turn
|
||||
* (#492 wave C). Each finished agent step's UI `parts` (its text part + a part
|
||||
* per tool call, WITH the tool output) is INSERTed as its own lightweight row the
|
||||
* moment the step ends, instead of REWRITING the whole assistant row's growing
|
||||
* `metadata.parts` jsonb on every `onStepFinish`.
|
||||
*
|
||||
* WHY a separate table + INSERT (not a jsonb `||` append on the message row): a
|
||||
* Postgres jsonb UPDATE rewrites the ENTIRE TOASTed row version under MVCC, so
|
||||
* re-persisting a growing `metadata.parts` on every step is O(n²) write volume
|
||||
* (a 50-step run with ~100 KB tool outputs wrote hundreds of MB of WAL / dead
|
||||
* tuples per turn, hammering autovacuum). `||` would only shave the network
|
||||
* payload — the WAL/TOAST rewrite harm remains. An INSERT into a per-step table
|
||||
* writes ONLY that step's bytes, so the per-turn write volume is O(Σ steps).
|
||||
*
|
||||
* The full `metadata.parts` on the message row is assembled ONCE at finalize (the
|
||||
* terminal completed/error/aborted write). Mid-run, a resuming client's seed is
|
||||
* reconstructed by concatenating these step rows in `step_index` order — which
|
||||
* reproduces exactly what the old per-step full-row rewrite persisted. Records
|
||||
* written the OLD way (full `metadata.parts` on the row, no step rows) still
|
||||
* reconstruct from the row unchanged; the two eras are distinguished by whether
|
||||
* the row already carries non-empty `metadata.parts` (see reconstructRunParts /
|
||||
* assembleStepParts in ai-chat.service.ts).
|
||||
*
|
||||
* ON DELETE CASCADE on `message_id`: the step rows are a derived projection of the
|
||||
* assistant message; they must vanish with it (or with its workspace).
|
||||
*/
|
||||
export async function up(db: Kysely<any>): Promise<void> {
|
||||
await db.schema
|
||||
.createTable('ai_chat_run_steps')
|
||||
.ifNotExists()
|
||||
.addColumn('id', 'uuid', (col) =>
|
||||
col.primaryKey().defaultTo(sql`gen_uuid_v7()`),
|
||||
)
|
||||
// The assistant message row this step belongs to (the #183 projection). The
|
||||
// step rows are a derived, per-step slice of that message, so they cascade.
|
||||
.addColumn('message_id', 'uuid', (col) =>
|
||||
col.references('ai_chat_messages.id').onDelete('cascade').notNull(),
|
||||
)
|
||||
.addColumn('workspace_id', 'uuid', (col) =>
|
||||
col.references('workspaces.id').onDelete('cascade').notNull(),
|
||||
)
|
||||
// 0-based index of the finished step within the turn. Ordering key for
|
||||
// reconstruction; unique per message (idempotent step re-persist).
|
||||
.addColumn('step_index', 'integer', (col) => col.notNull())
|
||||
// The step's UI parts (text part + a `tool-*` part per call, WITH output).
|
||||
// Concatenated in step order to rebuild the turn's `metadata.parts`.
|
||||
.addColumn('parts', 'jsonb', (col) => col.notNull())
|
||||
.addColumn('created_at', 'timestamptz', (col) =>
|
||||
col.notNull().defaultTo(sql`now()`),
|
||||
)
|
||||
.execute();
|
||||
|
||||
// Idempotent per-step persist: a retried INSERT of the same (message, step)
|
||||
// is a no-op (the service uses ON CONFLICT DO NOTHING). This also serves the
|
||||
// reconstruction read (WHERE message_id ORDER BY step_index).
|
||||
await db.schema
|
||||
.createIndex('ai_chat_run_steps_message_step_uidx')
|
||||
.ifNotExists()
|
||||
.on('ai_chat_run_steps')
|
||||
.columns(['message_id', 'step_index'])
|
||||
.unique()
|
||||
.execute();
|
||||
}
|
||||
|
||||
export async function down(db: Kysely<any>): Promise<void> {
|
||||
await db.schema.dropTable('ai_chat_run_steps').ifExists().execute();
|
||||
}
|
||||
@@ -1,95 +0,0 @@
|
||||
import { Injectable } from '@nestjs/common';
|
||||
import { InjectKysely } from 'nestjs-kysely';
|
||||
import { KyselyDB, KyselyTransaction } from '../../types/kysely.types';
|
||||
import { dbOrTx } from '../../utils';
|
||||
import { AiChatRunStep } from '@docmost/db/types/entity.types';
|
||||
|
||||
/**
|
||||
* Append-only per-step persistence for an assistant turn (#492). Each finished
|
||||
* agent step's UI `parts` (its text part + a `tool-*` part per call, WITH the
|
||||
* tool output) is INSERTed as its own lightweight row the moment the step ends —
|
||||
* instead of REWRITING the assistant row's growing `metadata.parts` jsonb on every
|
||||
* `onStepFinish` (a Postgres jsonb UPDATE rewrites the whole TOASTed row version
|
||||
* under MVCC, so that was O(n²) WAL/dead-tuple churn per turn).
|
||||
*
|
||||
* The full `metadata.parts` on the message row is assembled ONCE at finalize;
|
||||
* mid-run, a resuming client's seed is rebuilt from these rows in `stepIndex`
|
||||
* order (see `assembleStepParts` / the reconstruct seam in ai-chat.service.ts).
|
||||
* Every method is workspace-scoped as defense-in-depth.
|
||||
*/
|
||||
@Injectable()
|
||||
export class AiChatRunStepRepo {
|
||||
constructor(@InjectKysely() private readonly db: KyselyDB) {}
|
||||
|
||||
/**
|
||||
* Append one finished step's parts. Idempotent: a retried persist of the SAME
|
||||
* (message, stepIndex) is a no-op via ON CONFLICT DO NOTHING — the per-step
|
||||
* writes are fired fire-and-forget + serialized, and a duplicate must never
|
||||
* throw into the stream or double the parts. Returns whether a NEW row landed
|
||||
* (false = the step was already persisted).
|
||||
*/
|
||||
async insertStep(
|
||||
messageId: string,
|
||||
workspaceId: string,
|
||||
stepIndex: number,
|
||||
parts: unknown,
|
||||
trx?: KyselyTransaction,
|
||||
): Promise<boolean> {
|
||||
const db = dbOrTx(this.db, trx);
|
||||
const inserted = await db
|
||||
.insertInto('aiChatRunSteps')
|
||||
.values({
|
||||
messageId,
|
||||
workspaceId,
|
||||
stepIndex,
|
||||
// jsonb column: cast through never (same pattern as the message repo).
|
||||
parts: parts as never,
|
||||
})
|
||||
.onConflict((oc) => oc.columns(['messageId', 'stepIndex']).doNothing())
|
||||
.returning('id')
|
||||
.executeTakeFirst();
|
||||
return inserted !== undefined;
|
||||
}
|
||||
|
||||
/** All persisted steps for ONE assistant message, in step order. */
|
||||
async findByMessage(
|
||||
messageId: string,
|
||||
workspaceId: string,
|
||||
): Promise<AiChatRunStep[]> {
|
||||
return this.db
|
||||
.selectFrom('aiChatRunSteps')
|
||||
.selectAll('aiChatRunSteps')
|
||||
.where('messageId', '=', messageId)
|
||||
.where('workspaceId', '=', workspaceId)
|
||||
.orderBy('stepIndex', 'asc')
|
||||
.execute();
|
||||
}
|
||||
|
||||
/**
|
||||
* All persisted steps for a SET of assistant messages, grouped by messageId
|
||||
* (each group in step order). One query for the batch — the hydration seam
|
||||
* (getMessages / delta / export) calls this only for the rows that actually
|
||||
* need reconstruction (an active new-style row whose `metadata.parts` is still
|
||||
* empty), which is usually none, so this is skipped on the common path.
|
||||
*/
|
||||
async findByMessageIds(
|
||||
messageIds: string[],
|
||||
workspaceId: string,
|
||||
): Promise<Map<string, AiChatRunStep[]>> {
|
||||
const byMessage = new Map<string, AiChatRunStep[]>();
|
||||
if (messageIds.length === 0) return byMessage;
|
||||
const rows = await this.db
|
||||
.selectFrom('aiChatRunSteps')
|
||||
.selectAll('aiChatRunSteps')
|
||||
.where('messageId', 'in', messageIds)
|
||||
.where('workspaceId', '=', workspaceId)
|
||||
.orderBy('stepIndex', 'asc')
|
||||
.execute();
|
||||
for (const row of rows) {
|
||||
const list = byMessage.get(row.messageId);
|
||||
if (list) list.push(row);
|
||||
else byMessage.set(row.messageId, [row]);
|
||||
}
|
||||
return byMessage;
|
||||
}
|
||||
}
|
||||
-17
@@ -692,22 +692,6 @@ export interface AiChatRuns {
|
||||
updatedAt: Generated<Timestamp>;
|
||||
}
|
||||
|
||||
// Append-only per-step persistence for an assistant turn (#492). Mirrors
|
||||
// migration 20260708T120000-ai-chat-run-steps.ts. Each finished agent step's UI
|
||||
// `parts` are INSERTed as their own row (instead of rewriting the message row's
|
||||
// growing `metadata.parts` jsonb every step — an O(n²) WAL/TOAST churn). The full
|
||||
// `metadata.parts` is assembled once at finalize; mid-run a resuming client's seed
|
||||
// is rebuilt by concatenating these rows in `stepIndex` order. Cascades with the
|
||||
// assistant message row it projects.
|
||||
export interface AiChatRunSteps {
|
||||
id: Generated<string>;
|
||||
messageId: string;
|
||||
workspaceId: string;
|
||||
stepIndex: number;
|
||||
parts: Json;
|
||||
createdAt: Generated<Timestamp>;
|
||||
}
|
||||
|
||||
// Per-(chat,page) snapshot of the open page's Markdown at the END of the agent's
|
||||
// previous turn (#274). Mirrors migration 20260702T120000-ai-chat-page-snapshot.ts.
|
||||
// The next turn diffs the CURRENT Markdown against `contentMd` to surface edits a
|
||||
@@ -745,7 +729,6 @@ export interface DB {
|
||||
aiChats: AiChats;
|
||||
aiChatMessages: AiChatMessages;
|
||||
aiChatRuns: AiChatRuns;
|
||||
aiChatRunSteps: AiChatRunSteps;
|
||||
aiChatPageSnapshots: AiChatPageSnapshots;
|
||||
apiKeys: ApiKeys;
|
||||
attachments: Attachments;
|
||||
|
||||
@@ -4,7 +4,6 @@ import {
|
||||
AiChats,
|
||||
AiChatMessages,
|
||||
AiChatRuns,
|
||||
AiChatRunSteps,
|
||||
AiChatPageSnapshots,
|
||||
Attachments,
|
||||
Comments,
|
||||
@@ -65,12 +64,6 @@ export type InsertableAiChatMessage = Omit<Insertable<AiChatMessages>, 'tsv'>;
|
||||
export type AiChatRun = Selectable<AiChatRuns>;
|
||||
export type InsertableAiChatRun = Insertable<AiChatRuns>;
|
||||
|
||||
// AI Chat Run Step (#492): append-only per-step parts persistence. Each finished
|
||||
// agent step's UI parts are stored as their own row; the full turn's parts are
|
||||
// assembled from these (in stepIndex order) for a mid-run resume seed.
|
||||
export type AiChatRunStep = Selectable<AiChatRunSteps>;
|
||||
export type InsertableAiChatRunStep = Insertable<AiChatRunSteps>;
|
||||
|
||||
// AI Chat Page Snapshot (#274): per-(chat,page) Markdown snapshot taken at the
|
||||
// end of the agent's previous turn, diffed against the current page next turn to
|
||||
// detect human edits made between turns.
|
||||
|
||||
@@ -1,412 +0,0 @@
|
||||
import * as http from 'node:http';
|
||||
import { Kysely } from 'kysely';
|
||||
import { tool } from 'ai';
|
||||
import { z } from 'zod';
|
||||
import { MockLanguageModelV3, convertArrayToReadableStream } from 'ai/test';
|
||||
import { AiChatRepo } from '@docmost/db/repos/ai-chat/ai-chat.repo';
|
||||
import { AiChatMessageRepo } from '@docmost/db/repos/ai-chat/ai-chat-message.repo';
|
||||
import { AiChatRunStepRepo } from '@docmost/db/repos/ai-chat/ai-chat-run-step.repo';
|
||||
import {
|
||||
AiChatService,
|
||||
assembleStepParts,
|
||||
assistantParts,
|
||||
rowHasInlineParts,
|
||||
stepMarkerMetadata,
|
||||
} from 'src/core/ai-chat/ai-chat.service';
|
||||
import {
|
||||
getTestDb,
|
||||
destroyTestDb,
|
||||
createWorkspace,
|
||||
createUser,
|
||||
createChat,
|
||||
createMessage,
|
||||
} from './db';
|
||||
|
||||
/**
|
||||
* #492 append-persist — the REAL onStep WRITE path (F2) and the model-REPLAY
|
||||
* hydration path (F1), driven through `AiChatService.stream` against a LIVE
|
||||
* Postgres with a REAL `AiChatRunStepRepo` INJECTED. The existing append-persist
|
||||
* int-specs hand-roll the insert+marker cycle via the repos directly and build
|
||||
* the service with `aiChatRunStepRepo: undefined` (only the legacy-fallback branch
|
||||
* is covered), so an off-by-one on `stepsPersisted-1`, a wrong `capturedSteps`
|
||||
* slice, or a broken marker payload would pass all of them. These tests exercise
|
||||
* the actual `updateStreaming` append-persist branch end to end.
|
||||
*
|
||||
* The seam is the injected `model` (a seeded `MockLanguageModelV3` from `ai/test`)
|
||||
* plus a REAL Node `ServerResponse` as the hijacked socket — mirrors
|
||||
* ai-chat-stream.int-spec.ts.
|
||||
*/
|
||||
|
||||
const sleep = (ms: number) => new Promise((r) => setTimeout(r, ms));
|
||||
|
||||
async function waitFor(
|
||||
cond: () => Promise<boolean> | boolean,
|
||||
{ timeoutMs = 15_000, stepMs = 25 } = {},
|
||||
): Promise<void> {
|
||||
const start = Date.now();
|
||||
while (Date.now() - start < timeoutMs) {
|
||||
if (await cond()) return;
|
||||
await sleep(stepMs);
|
||||
}
|
||||
throw new Error('waitFor: condition not met within timeout');
|
||||
}
|
||||
|
||||
// A real Node ServerResponse wired to a live socket (identical helper to the
|
||||
// stream int-spec) so the SDK's pipe/heartbeat writes behave as in prod.
|
||||
function makeRealResponse(): Promise<{
|
||||
res: http.ServerResponse;
|
||||
cleanup: () => Promise<void>;
|
||||
}> {
|
||||
return new Promise((resolve) => {
|
||||
const server = http.createServer((_req, res) => {
|
||||
resolve({
|
||||
res,
|
||||
cleanup: () =>
|
||||
new Promise<void>((done) => {
|
||||
try {
|
||||
if (!res.writableEnded) res.end();
|
||||
} catch {
|
||||
/* socket already gone */
|
||||
}
|
||||
server.close(() => done());
|
||||
}),
|
||||
});
|
||||
});
|
||||
server.listen(0, () => {
|
||||
const port = (server.address() as any).port;
|
||||
const creq = http.request({ port, method: 'GET' }, (cres) => {
|
||||
cres.resume();
|
||||
});
|
||||
creq.on('error', () => undefined);
|
||||
creq.end();
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
// Stream parts for a normal, successful single-step turn.
|
||||
function successStream() {
|
||||
return convertArrayToReadableStream([
|
||||
{ type: 'stream-start', warnings: [] },
|
||||
{ type: 'text-start', id: 't1' },
|
||||
{ type: 'text-delta', id: 't1', delta: 'Hello' },
|
||||
{ type: 'text-delta', id: 't1', delta: ' there' },
|
||||
{ type: 'text-end', id: 't1' },
|
||||
{
|
||||
type: 'finish',
|
||||
finishReason: 'stop',
|
||||
usage: { inputTokens: 10, outputTokens: 5, totalTokens: 15 },
|
||||
},
|
||||
] as any);
|
||||
}
|
||||
|
||||
// A THREE-step turn: steps 0 and 1 each emit text + an `echo` tool call (the SDK
|
||||
// runs the tool and continues); step 2 answers and stops. Three steps is
|
||||
// deliberate: the LAST finished step's append-persist write races the terminal
|
||||
// finalize (which writes the full inline parts anyway, so a lost last-step row is
|
||||
// by design), but the NON-final steps 0 and 1 always drain to the steps table
|
||||
// before finalize — so those are what the test asserts on deterministically.
|
||||
function threeStepModel(): MockLanguageModelV3 {
|
||||
let step = 0;
|
||||
const toolStep = (i: number) => ({
|
||||
stream: convertArrayToReadableStream([
|
||||
{ type: 'stream-start', warnings: [] },
|
||||
{ type: 'text-start', id: `s${i}` },
|
||||
{ type: 'text-delta', id: `s${i}`, delta: `step ${i} ` },
|
||||
{ type: 'text-end', id: `s${i}` },
|
||||
{
|
||||
type: 'tool-call',
|
||||
toolCallId: `c${i}`,
|
||||
toolName: 'echo',
|
||||
input: JSON.stringify({ msg: `m${i}` }),
|
||||
},
|
||||
{
|
||||
type: 'finish',
|
||||
finishReason: 'tool-calls',
|
||||
usage: { inputTokens: 5, outputTokens: 3, totalTokens: 8 },
|
||||
},
|
||||
] as any),
|
||||
});
|
||||
return new MockLanguageModelV3({
|
||||
doStream: async () => {
|
||||
const n = step++;
|
||||
// Realistic inter-step latency. A real model spends seconds per step, so the
|
||||
// fire-and-forget per-step write chain drains to the steps table BETWEEN
|
||||
// steps; the mock otherwise collapses all steps into microseconds and the
|
||||
// terminal finalize wins the race before any but the first step persists.
|
||||
if (n > 0) await sleep(200);
|
||||
if (n < 2) return toolStep(n);
|
||||
return {
|
||||
stream: convertArrayToReadableStream([
|
||||
{ type: 'stream-start', warnings: [] },
|
||||
{ type: 'text-start', id: 's2' },
|
||||
{ type: 'text-delta', id: 's2', delta: 'final answer' },
|
||||
{ type: 'text-end', id: 's2' },
|
||||
{
|
||||
type: 'finish',
|
||||
finishReason: 'stop',
|
||||
usage: { inputTokens: 6, outputTokens: 4, totalTokens: 10 },
|
||||
},
|
||||
] as any),
|
||||
};
|
||||
},
|
||||
} as any);
|
||||
}
|
||||
|
||||
describe('#492 append-persist service paths [integration]', () => {
|
||||
let db: Kysely<any>;
|
||||
let aiChatRepo: AiChatRepo;
|
||||
let msgRepo: AiChatMessageRepo;
|
||||
let stepRepo: AiChatRunStepRepo;
|
||||
let workspaceId: string;
|
||||
let userId: string;
|
||||
|
||||
let closeCalls: number;
|
||||
const mcpClients = {
|
||||
toolsFor: async () => ({
|
||||
tools: {},
|
||||
clients: [
|
||||
{
|
||||
close: async () => {
|
||||
closeCalls += 1;
|
||||
},
|
||||
},
|
||||
],
|
||||
outcomes: [],
|
||||
instructions: [],
|
||||
}),
|
||||
};
|
||||
|
||||
// Build the service WITH a REAL AiChatRunStepRepo injected (the property under
|
||||
// test) — unlike the legacy-fallback harness that passes it as undefined.
|
||||
const echoTool = tool({
|
||||
description: 'echo the message back',
|
||||
inputSchema: z.object({ msg: z.string() }),
|
||||
execute: async ({ msg }) => ({ echoed: msg }),
|
||||
});
|
||||
|
||||
function buildService(): AiChatService {
|
||||
return new AiChatService(
|
||||
{ getChatModel: async () => null } as any,
|
||||
aiChatRepo,
|
||||
msgRepo,
|
||||
{} as any, // aiChatPageSnapshotRepo
|
||||
{ resolve: async () => null } as any, // aiSettings
|
||||
{ forUser: async () => ({ echo: echoTool }) } as any, // tools
|
||||
mcpClients as any,
|
||||
{} as any, // aiAgentRoleRepo
|
||||
{} as any, // pageRepo
|
||||
{} as any, // pageAccess
|
||||
{
|
||||
isAiChatDeferredToolsEnabled: () => false,
|
||||
isAiChatFinalStepLockdownEnabled: () => false,
|
||||
} as any, // environment (deferred OFF -> all tools active every step)
|
||||
undefined, // streamRegistry
|
||||
undefined, // aiChatRunService
|
||||
stepRepo, // #492 aiChatRunStepRepo — the append-persist backend
|
||||
);
|
||||
}
|
||||
|
||||
function userUiMessage(text: string) {
|
||||
return {
|
||||
id: `u-${Math.random()}`,
|
||||
role: 'user',
|
||||
parts: [{ type: 'text', text }],
|
||||
};
|
||||
}
|
||||
|
||||
async function runStream(opts: {
|
||||
model: MockLanguageModelV3;
|
||||
chatId: string;
|
||||
body: any;
|
||||
}): Promise<void> {
|
||||
closeCalls = 0;
|
||||
const service = buildService();
|
||||
const { res, cleanup } = await makeRealResponse();
|
||||
try {
|
||||
await service.stream({
|
||||
user: { id: userId, workspaceId } as any,
|
||||
workspace: { id: workspaceId, name: 'WS' } as any,
|
||||
sessionId: 'sess-1',
|
||||
body: opts.body,
|
||||
res: { raw: res } as any,
|
||||
signal: new AbortController().signal,
|
||||
model: opts.model as any,
|
||||
role: null,
|
||||
} as any);
|
||||
await waitFor(async () => {
|
||||
const rows = await msgRepo.findAllByChat(opts.chatId, workspaceId);
|
||||
return rows.some(
|
||||
(r) =>
|
||||
r.role === 'assistant' &&
|
||||
['completed', 'error', 'aborted'].includes(r.status as string),
|
||||
);
|
||||
});
|
||||
await waitFor(() => closeCalls > 0, { timeoutMs: 5_000 });
|
||||
} finally {
|
||||
await cleanup();
|
||||
}
|
||||
}
|
||||
|
||||
beforeAll(async () => {
|
||||
db = getTestDb();
|
||||
aiChatRepo = new AiChatRepo(db as any);
|
||||
msgRepo = new AiChatMessageRepo(db as any);
|
||||
stepRepo = new AiChatRunStepRepo(db as any);
|
||||
workspaceId = (await createWorkspace(db)).id;
|
||||
userId = (await createUser(db, workspaceId)).id;
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await destroyTestDb();
|
||||
});
|
||||
|
||||
// --- F2: the real onStep append-persist WRITE branch -----------------------
|
||||
it('drives steps through the real onStep path: per-step rows + marker match a single-row flush', async () => {
|
||||
const chatId = (await createChat(db, { workspaceId, creatorId: userId })).id;
|
||||
const model = threeStepModel();
|
||||
|
||||
// Capture the mid-run step-marker UPDATEs the append-persist branch writes on
|
||||
// the assistant row (a { parts: [], toolTraceVersion, stepsPersisted } patch).
|
||||
const updateSpy = jest.spyOn(msgRepo, 'update');
|
||||
try {
|
||||
await runStream({
|
||||
model,
|
||||
chatId,
|
||||
body: { chatId, messages: [userUiMessage('call the tool then answer')] },
|
||||
});
|
||||
|
||||
const rows = await msgRepo.findAllByChat(chatId, workspaceId);
|
||||
const assistant = rows.find((r) => r.role === 'assistant')!;
|
||||
expect(assistant).toBeDefined();
|
||||
expect(assistant.status).toBe('completed');
|
||||
// The turn finalizes with the FULL inline parts assembled by a single-row
|
||||
// flush (assistantParts over every step) — the baseline the per-step slices
|
||||
// must reproduce.
|
||||
expect(rowHasInlineParts(assistant)).toBe(true);
|
||||
const finalParts = (assistant.metadata as { parts: any[] }).parts;
|
||||
|
||||
// The two NON-final finished steps each landed their own row, in stepIndex
|
||||
// order. (The fire-and-forget write chain drains before the next step, so
|
||||
// poll until both are on disk; the LAST step's write may lose the finalize
|
||||
// race, which is by design — its parts are already in `finalParts`.)
|
||||
await waitFor(async () => {
|
||||
const s = await stepRepo.findByMessage(assistant.id, workspaceId);
|
||||
return s.length >= 2;
|
||||
});
|
||||
const steps = await stepRepo.findByMessage(assistant.id, workspaceId);
|
||||
expect(steps[0].stepIndex).toBe(0);
|
||||
expect(steps[1].stepIndex).toBe(1);
|
||||
|
||||
// Each per-step row carries a NON-trivial slice: this step's text part + its
|
||||
// paired tool part (guards a mutation that persists empty/whole-turn parts).
|
||||
const s0 = steps[0].parts as any[];
|
||||
expect(s0).toContainEqual({ type: 'text', text: 'step 0 ' });
|
||||
expect(s0.some((p) => p.type === 'tool-echo')).toBe(true);
|
||||
|
||||
// The per-step slices are EXACTLY the corresponding prefix of the single-row
|
||||
// flush: assembleStepParts([step0, step1]) === finalParts[0 .. len0+len1].
|
||||
// This is what an off-by-one on `stepsPersisted-1` (a wrong `capturedSteps`
|
||||
// slice) or a shifted stepIndex breaks — the prefix no longer aligns.
|
||||
const prefixLen =
|
||||
(steps[0].parts as any[]).length + (steps[1].parts as any[]).length;
|
||||
expect(assembleStepParts([steps[0], steps[1]] as any)).toEqual(
|
||||
finalParts.slice(0, prefixLen),
|
||||
);
|
||||
|
||||
// The mid-run step markers advanced 1 -> 2 -> ... (the resume frontier), each
|
||||
// a shape-stable empty-parts marker equal to a single-row flush's marker.
|
||||
const markerCounts = updateSpy.mock.calls
|
||||
.map((c) => (c[2] as any)?.metadata)
|
||||
.filter(
|
||||
(m) =>
|
||||
m &&
|
||||
Array.isArray(m.parts) &&
|
||||
m.parts.length === 0 &&
|
||||
typeof m.stepsPersisted === 'number',
|
||||
)
|
||||
.map((m) => m.stepsPersisted);
|
||||
// Monotonic from 1, covering at least the two non-final steps.
|
||||
expect(markerCounts.slice(0, 2)).toEqual([1, 2]);
|
||||
expect(
|
||||
updateSpy.mock.calls
|
||||
.map((c) => (c[2] as any)?.metadata)
|
||||
.find((m) => m && m.stepsPersisted === 2),
|
||||
).toEqual(stepMarkerMetadata(2));
|
||||
} finally {
|
||||
updateSpy.mockRestore();
|
||||
}
|
||||
}, 60_000);
|
||||
|
||||
// --- F1: model-REPLAY hydrates a hard-crashed mid-run turn from the steps table
|
||||
it('replays a hard-crashed mid-run turn WITH its partial steps hydrated from the steps table', async () => {
|
||||
const chatId = (await createChat(db, { workspaceId, creatorId: userId })).id;
|
||||
|
||||
// Prior turn: a genuine user question...
|
||||
await createMessage(db, {
|
||||
workspaceId,
|
||||
chatId,
|
||||
userId,
|
||||
role: 'user',
|
||||
content: 'What is in the design doc?',
|
||||
createdAt: new Date(Date.now() - 3000),
|
||||
});
|
||||
// ...and an assistant row that a HARD crash (SIGKILL/OOM) left mid-run: only a
|
||||
// step marker on the row (metadata.parts:[] , content:''), NO terminal
|
||||
// callback ever fired, so its real parts live ONLY in ai_chat_run_steps.
|
||||
const crashed = await createMessage(db, {
|
||||
workspaceId,
|
||||
chatId,
|
||||
role: 'assistant',
|
||||
content: '',
|
||||
status: 'aborted',
|
||||
metadata: stepMarkerMetadata(1),
|
||||
createdAt: new Date(Date.now() - 2000),
|
||||
});
|
||||
// The durable partial step: some reasoning text + a completed getPage tool
|
||||
// call (input + output), exactly what #183 step-granular durability preserves.
|
||||
await stepRepo.insertStep(
|
||||
crashed.id,
|
||||
workspaceId,
|
||||
0,
|
||||
assistantParts(
|
||||
[
|
||||
{
|
||||
text: 'HYDRATED_PARTIAL_STEP the doc says',
|
||||
toolCalls: [
|
||||
{ toolCallId: 'g1', toolName: 'getPage', input: { id: 'p1' } },
|
||||
],
|
||||
toolResults: [
|
||||
{
|
||||
toolCallId: 'g1',
|
||||
toolName: 'getPage',
|
||||
output: { id: 'p1', body: 'PARTIAL_TOOL_OUTPUT budget section' },
|
||||
},
|
||||
],
|
||||
} as any,
|
||||
],
|
||||
'',
|
||||
),
|
||||
);
|
||||
|
||||
// The NEXT turn: the model just answers. The service must REPLAY the crashed
|
||||
// assistant turn with its partial parts hydrated from the steps table.
|
||||
const model = new MockLanguageModelV3({
|
||||
doStream: async () => ({ stream: successStream() }),
|
||||
} as any);
|
||||
await runStream({
|
||||
model,
|
||||
chatId,
|
||||
body: { chatId, messages: [userUiMessage('Continue please')] },
|
||||
});
|
||||
|
||||
expect(model.doStreamCalls.length).toBeGreaterThan(0);
|
||||
const prompt = JSON.stringify(model.doStreamCalls[0].prompt);
|
||||
// The partial step's TEXT reached the model context (it would be an empty text
|
||||
// part without hydration — rowToUiMessage falls back to `content:''`).
|
||||
expect(prompt).toContain('HYDRATED_PARTIAL_STEP');
|
||||
// The partial TOOL RESULT survived too (durable in the steps table, replayed).
|
||||
expect(prompt).toContain('PARTIAL_TOOL_OUTPUT');
|
||||
// The genuine prior user turn is present as well (sanity: real history replay).
|
||||
expect(prompt).toContain('What is in the design doc?');
|
||||
}, 60_000);
|
||||
});
|
||||
@@ -1,173 +0,0 @@
|
||||
import { randomBytes } from 'crypto';
|
||||
import { Kysely, sql } from 'kysely';
|
||||
import { AiChatRunStepRepo } from '@docmost/db/repos/ai-chat/ai-chat-run-step.repo';
|
||||
import { AiChatMessageRepo } from '@docmost/db/repos/ai-chat/ai-chat-message.repo';
|
||||
import {
|
||||
assistantParts,
|
||||
flushAssistant,
|
||||
stepMarkerMetadata,
|
||||
} from '../../src/core/ai-chat/ai-chat.service';
|
||||
import {
|
||||
getTestDb,
|
||||
destroyTestDb,
|
||||
createWorkspace,
|
||||
createUser,
|
||||
createChat,
|
||||
} from './db';
|
||||
|
||||
/**
|
||||
* #492 append-persist — WRITE-VOLUME regression on a LIVE Postgres, measured via
|
||||
* the `pg_current_wal_lsn()` delta around a realistic multi-step run driven through
|
||||
* the REAL repos (not a mock — a mock cannot observe MVCC/TOAST rewrite volume, the
|
||||
* whole point). Proves the core claim:
|
||||
*
|
||||
* NEW (per-step INSERT into ai_chat_run_steps + a CHEAP step-marker UPDATE on the
|
||||
* message row) writes O(Σ steps) of WAL — each step writes only its own bytes.
|
||||
*
|
||||
* OLD (the pre-#492 full-row rewrite: re-persist the GROWING metadata.parts on
|
||||
* every onStepFinish) writes O(n²) — step k rewrites the whole TOASTed jsonb of
|
||||
* all k prior outputs.
|
||||
*
|
||||
* The OLD path here IS the reverted behavior, so this doubles as the mutation
|
||||
* check: swapping the new path back to `flushAssistant` full-row UPDATEs reddens
|
||||
* the assertion (OLD is many times larger).
|
||||
*/
|
||||
type Step = {
|
||||
text: string;
|
||||
toolCalls: Array<{ toolCallId: string; toolName: string; input: unknown }>;
|
||||
toolResults: Array<{ toolCallId: string; toolName: string; output: unknown }>;
|
||||
};
|
||||
|
||||
// ~100 KB INCOMPRESSIBLE output per step (a page read). Random base64 so TOAST
|
||||
// cannot compress it away and hide the real write volume.
|
||||
function makeStep(i: number, outputBytes = 100_000): Step {
|
||||
const body = randomBytes(Math.ceil(outputBytes * 0.75)).toString('base64');
|
||||
return {
|
||||
text: `step ${i} reasoning`,
|
||||
toolCalls: [
|
||||
{ toolCallId: `c${i}`, toolName: 'getPage', input: { id: `p${i}` } },
|
||||
],
|
||||
toolResults: [
|
||||
{
|
||||
toolCallId: `c${i}`,
|
||||
toolName: 'getPage',
|
||||
output: { id: `p${i}`, title: `Page ${i}`, body },
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
|
||||
async function walDelta(
|
||||
db: Kysely<any>,
|
||||
fn: () => Promise<void>,
|
||||
): Promise<number> {
|
||||
const before = (
|
||||
await sql<{ l: string }>`select pg_current_wal_lsn() as l`.execute(db)
|
||||
).rows[0].l;
|
||||
await fn();
|
||||
// NOTE: no pg_switch_wal() — a segment switch pads the LSN to the next 16 MB
|
||||
// boundary and would swamp the delta. The raw LSN advances by the WAL bytes.
|
||||
const after = (
|
||||
await sql<{ l: string }>`select pg_current_wal_lsn() as l`.execute(db)
|
||||
).rows[0].l;
|
||||
return Number(
|
||||
(
|
||||
await sql<{
|
||||
d: string;
|
||||
}>`select pg_wal_lsn_diff(${after}::pg_lsn, ${before}::pg_lsn) as d`.execute(
|
||||
db,
|
||||
)
|
||||
).rows[0].d,
|
||||
);
|
||||
}
|
||||
|
||||
describe('#492 append-persist write volume (pg_current_wal_lsn delta) [integration]', () => {
|
||||
let db: Kysely<any>;
|
||||
let stepRepo: AiChatRunStepRepo;
|
||||
let msgRepo: AiChatMessageRepo;
|
||||
let workspaceId: string;
|
||||
let userId: string;
|
||||
let chatId: string;
|
||||
|
||||
beforeAll(async () => {
|
||||
db = getTestDb();
|
||||
stepRepo = new AiChatRunStepRepo(db as any);
|
||||
msgRepo = new AiChatMessageRepo(db as any);
|
||||
workspaceId = (await createWorkspace(db)).id;
|
||||
userId = (await createUser(db, workspaceId)).id;
|
||||
chatId = (await createChat(db, { workspaceId, creatorId: userId })).id;
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await destroyTestDb();
|
||||
});
|
||||
|
||||
const seedRow = () =>
|
||||
msgRepo.insert({
|
||||
chatId,
|
||||
workspaceId,
|
||||
userId,
|
||||
role: 'assistant',
|
||||
content: '',
|
||||
status: 'streaming',
|
||||
metadata: stepMarkerMetadata(0) as never,
|
||||
});
|
||||
|
||||
const STEPS = 40;
|
||||
|
||||
it('NEW per-step INSERT is O(Σ steps); OLD full-row rewrite is O(n²)', async () => {
|
||||
const steps: Step[] = [];
|
||||
for (let i = 0; i < STEPS; i++) steps.push(makeStep(i));
|
||||
|
||||
// NEW: per-step INSERT of THIS step's parts + a cheap marker UPDATE.
|
||||
const newRow = await seedRow();
|
||||
const newWal = await walDelta(db, async () => {
|
||||
for (let i = 0; i < STEPS; i++) {
|
||||
await stepRepo.insertStep(
|
||||
newRow.id,
|
||||
workspaceId,
|
||||
i,
|
||||
assistantParts([steps[i]], ''),
|
||||
);
|
||||
await msgRepo.update(
|
||||
newRow.id,
|
||||
workspaceId,
|
||||
{ metadata: stepMarkerMetadata(i + 1) },
|
||||
{ onlyIfStreaming: true },
|
||||
);
|
||||
}
|
||||
});
|
||||
|
||||
// OLD (the pre-#492 revert): re-persist the GROWING metadata.parts on the
|
||||
// message row on every step.
|
||||
const oldRow = await seedRow();
|
||||
const oldWal = await walDelta(db, async () => {
|
||||
const acc: Step[] = [];
|
||||
for (let i = 0; i < STEPS; i++) {
|
||||
acc.push(steps[i]);
|
||||
await msgRepo.update(
|
||||
oldRow.id,
|
||||
workspaceId,
|
||||
flushAssistant(acc as never, '', 'streaming'),
|
||||
{ onlyIfStreaming: true },
|
||||
);
|
||||
}
|
||||
});
|
||||
|
||||
// eslint-disable-next-line no-console
|
||||
console.log(
|
||||
`[#492 WAL] ${STEPS} steps ×100KB: new=${(newWal / 1e6).toFixed(1)}MB ` +
|
||||
`old=${(oldWal / 1e6).toFixed(1)}MB (${(oldWal / newWal).toFixed(
|
||||
1,
|
||||
)}x smaller)`,
|
||||
);
|
||||
|
||||
// O(Σ steps): ~STEPS × (100KB output + marker) of WAL. 40 × ~100KB parts plus
|
||||
// 40 tiny markers is a few tens of MB at most — bounded, linear in step count.
|
||||
expect(newWal).toBeLessThan(30_000_000);
|
||||
// O(n²): step k rewrites ~k × 100KB. Σ over 40 steps ≈ 80+ MB — far larger.
|
||||
expect(oldWal).toBeGreaterThan(30_000_000);
|
||||
// The load-bearing claim: the new path writes a small FRACTION of the old.
|
||||
expect(newWal).toBeLessThan(oldWal * 0.35);
|
||||
}, 120_000);
|
||||
});
|
||||
@@ -1,169 +0,0 @@
|
||||
import { Kysely } from 'kysely';
|
||||
import { AiChatController } from 'src/core/ai-chat/ai-chat.controller';
|
||||
import {
|
||||
assembleStepParts,
|
||||
assistantParts,
|
||||
stepMarkerMetadata,
|
||||
} from 'src/core/ai-chat/ai-chat.service';
|
||||
import { AiChatRepo } from '@docmost/db/repos/ai-chat/ai-chat.repo';
|
||||
import { AiChatMessageRepo } from '@docmost/db/repos/ai-chat/ai-chat-message.repo';
|
||||
import { AiChatRunStepRepo } from '@docmost/db/repos/ai-chat/ai-chat-run-step.repo';
|
||||
import type { User, Workspace } from '@docmost/db/types/entity.types';
|
||||
import {
|
||||
getTestDb,
|
||||
destroyTestDb,
|
||||
createWorkspace,
|
||||
createUser,
|
||||
createChat,
|
||||
createMessage,
|
||||
} from './db';
|
||||
|
||||
/**
|
||||
* #492 controller hydration (crash-before-finalize RESUME) on a LIVE Postgres.
|
||||
* `AiChatController.withReconstructedParts` is wired into getMessages/delta/export/
|
||||
* run, but `aiChatRunStepRepo` is OPTIONAL and every controller unit spec passes it
|
||||
* as `undefined`, so the hydration branch early-returns and NEVER executes in those
|
||||
* tests. This drives the real read path — a mid-run streaming row (marker only,
|
||||
* empty inline parts) PLUS its `ai_chat_run_steps` rows — through getMessages WITH
|
||||
* the repo present, exercising the `role==='assistant' && !rowHasInlineParts`
|
||||
* needy predicate, the workspace-scoped batch step fetch, and the endpoint binding.
|
||||
*/
|
||||
describe('#492 controller hydration read path [integration]', () => {
|
||||
let db: Kysely<any>;
|
||||
let aiChatRepo: AiChatRepo;
|
||||
let msgRepo: AiChatMessageRepo;
|
||||
let stepRepo: AiChatRunStepRepo;
|
||||
let workspaceId: string;
|
||||
let otherWorkspaceId: string;
|
||||
let userId: string;
|
||||
|
||||
// Build the controller WITH a real AiChatRunStepRepo injected (position 9), the
|
||||
// seam the unit specs leave undefined. Only the read-path deps are real.
|
||||
function buildController(): AiChatController {
|
||||
return new AiChatController(
|
||||
{} as any, // aiChatService
|
||||
{} as any, // aiChatRunService
|
||||
aiChatRepo,
|
||||
msgRepo,
|
||||
{} as any, // aiTranscription
|
||||
{} as any, // pageRepo
|
||||
undefined, // streamRegistry
|
||||
undefined, // environment
|
||||
stepRepo, // #492 aiChatRunStepRepo
|
||||
);
|
||||
}
|
||||
|
||||
beforeAll(async () => {
|
||||
db = getTestDb();
|
||||
aiChatRepo = new AiChatRepo(db as any);
|
||||
msgRepo = new AiChatMessageRepo(db as any);
|
||||
stepRepo = new AiChatRunStepRepo(db as any);
|
||||
workspaceId = (await createWorkspace(db)).id;
|
||||
otherWorkspaceId = (await createWorkspace(db)).id;
|
||||
userId = (await createUser(db, workspaceId)).id;
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await destroyTestDb();
|
||||
});
|
||||
|
||||
it('getMessages reconstructs a mid-run row from the steps table (finished rows untouched)', async () => {
|
||||
const chatId = (
|
||||
await createChat(db, { workspaceId, creatorId: userId })
|
||||
).id;
|
||||
const user = { id: userId } as User;
|
||||
const workspace = { id: workspaceId } as Workspace;
|
||||
|
||||
// A prior FINISHED assistant row that already carries inline parts — the needy
|
||||
// predicate must SKIP it (no step fetch), returned untouched.
|
||||
const finishedParts = assistantParts(
|
||||
[{ text: 'done earlier', toolCalls: [], toolResults: [] } as any],
|
||||
'',
|
||||
);
|
||||
await createMessage(db, {
|
||||
workspaceId,
|
||||
chatId,
|
||||
role: 'assistant',
|
||||
content: 'done earlier',
|
||||
status: 'completed',
|
||||
metadata: { parts: finishedParts, toolTraceVersion: 2, stepsPersisted: 1 },
|
||||
createdAt: new Date(Date.now() - 3000),
|
||||
});
|
||||
|
||||
// The mid-run row a crash-before-finalize left behind: a step marker only
|
||||
// (parts:[] , content:''), status 'streaming'. Its real parts live ONLY in the
|
||||
// steps table.
|
||||
const midRun = await createMessage(db, {
|
||||
workspaceId,
|
||||
chatId,
|
||||
role: 'assistant',
|
||||
content: '',
|
||||
status: 'streaming',
|
||||
metadata: stepMarkerMetadata(2),
|
||||
createdAt: new Date(Date.now() - 1000),
|
||||
});
|
||||
|
||||
const step0 = assistantParts(
|
||||
[
|
||||
{
|
||||
text: 'reasoning about the page',
|
||||
toolCalls: [
|
||||
{ toolCallId: 'g1', toolName: 'getPage', input: { id: 'p1' } },
|
||||
],
|
||||
toolResults: [
|
||||
{ toolCallId: 'g1', toolName: 'getPage', output: { id: 'p1', body: 'B' } },
|
||||
],
|
||||
} as any,
|
||||
],
|
||||
'',
|
||||
);
|
||||
const step1 = assistantParts(
|
||||
[{ text: 'partial synthesis so far', toolCalls: [], toolResults: [] } as any],
|
||||
'',
|
||||
);
|
||||
await stepRepo.insertStep(midRun.id, workspaceId, 0, step0);
|
||||
await stepRepo.insertStep(midRun.id, workspaceId, 1, step1);
|
||||
|
||||
// Workspace-scoping guard: a step row for the SAME message id under a DIFFERENT
|
||||
// workspace must NEVER leak into this workspace's reconstruction.
|
||||
await stepRepo.insertStep(midRun.id, otherWorkspaceId, 99, [
|
||||
{ type: 'text', text: 'FOREIGN_WORKSPACE_LEAK' },
|
||||
]);
|
||||
|
||||
const res = await buildController().getMessages(
|
||||
{ chatId } as any,
|
||||
{ limit: 50 } as any,
|
||||
user,
|
||||
workspace,
|
||||
);
|
||||
|
||||
const items = res.items as any[];
|
||||
const finished = items.find((r) => r.status === 'completed');
|
||||
const reconstructed = items.find((r) => r.id === midRun.id);
|
||||
|
||||
// The finished row passed through with its inline parts unchanged.
|
||||
expect(finished.metadata.parts).toEqual(finishedParts);
|
||||
|
||||
// The mid-run row's parts were reconstructed from the two step rows, in order,
|
||||
// exactly as assembleStepParts concatenates them — the client seed sees the
|
||||
// persisted progress with no change to itself.
|
||||
const expected = assembleStepParts([
|
||||
{ stepIndex: 0, parts: step0 },
|
||||
{ stepIndex: 1, parts: step1 },
|
||||
] as any);
|
||||
expect(reconstructed.metadata.parts).toEqual(expected);
|
||||
// The foreign-workspace step row did NOT leak in.
|
||||
expect(JSON.stringify(reconstructed.metadata.parts)).not.toContain(
|
||||
'FOREIGN_WORKSPACE_LEAK',
|
||||
);
|
||||
// Sanity: reconstruction produced real content (text + the paired tool part +
|
||||
// the second step's text), not an empty fallback.
|
||||
expect(reconstructed.metadata.parts).toContainEqual({
|
||||
type: 'text',
|
||||
text: 'reasoning about the page',
|
||||
});
|
||||
expect(
|
||||
(reconstructed.metadata.parts as any[]).some((p) => p.type === 'tool-getPage'),
|
||||
).toBe(true);
|
||||
}, 60_000);
|
||||
});
|
||||
@@ -1,163 +0,0 @@
|
||||
import { randomBytes } from 'crypto';
|
||||
import { Kysely } from 'kysely';
|
||||
import { AiChatRunStepRepo } from '@docmost/db/repos/ai-chat/ai-chat-run-step.repo';
|
||||
import { AiChatMessageRepo } from '@docmost/db/repos/ai-chat/ai-chat-message.repo';
|
||||
import {
|
||||
assistantParts,
|
||||
reconstructRunParts,
|
||||
hydrateAssistantParts,
|
||||
stepMarkerMetadata,
|
||||
rowHasInlineParts,
|
||||
} from '../../src/core/ai-chat/ai-chat.service';
|
||||
import {
|
||||
getTestDb,
|
||||
destroyTestDb,
|
||||
createWorkspace,
|
||||
createUser,
|
||||
createChat,
|
||||
} from './db';
|
||||
|
||||
/**
|
||||
* #492 append-persist — the reconstruct CONTRACT on a live Postgres. Proves that a
|
||||
* turn persisted the NEW way (per-step rows in `ai_chat_run_steps`, only a step
|
||||
* marker on the message row) reconstructs to the SAME UI parts as a turn persisted
|
||||
* the OLD way (full `metadata.parts` inline on the row, no step rows) — so the
|
||||
* era-switch is invisible to attach / delta-poll / export. Real repos + real jsonb
|
||||
* roundtrip, not a mock (a mock cannot prove the parts survive the jsonb column
|
||||
* byte-identical).
|
||||
*/
|
||||
type Step = {
|
||||
text: string;
|
||||
toolCalls: Array<{ toolCallId: string; toolName: string; input: unknown }>;
|
||||
toolResults: Array<{ toolCallId: string; toolName: string; output: unknown }>;
|
||||
};
|
||||
|
||||
// A realistic step: some text + a getPage tool call whose ~100 KB body is
|
||||
// INCOMPRESSIBLE random base64 (a 'x'.repeat filler would TOAST away and hide the
|
||||
// real bytes). Under MAX_TOOL_OUTPUT_BYTES (200 KB) it is stored uncompacted.
|
||||
function makeStep(i: number, outputBytes = 4_000): Step {
|
||||
const body = randomBytes(Math.ceil(outputBytes * 0.75)).toString('base64');
|
||||
return {
|
||||
text: `step ${i} text`,
|
||||
toolCalls: [
|
||||
{ toolCallId: `c${i}`, toolName: 'getPage', input: { id: `p${i}` } },
|
||||
],
|
||||
toolResults: [
|
||||
{
|
||||
toolCallId: `c${i}`,
|
||||
toolName: 'getPage',
|
||||
output: { id: `p${i}`, title: `Page ${i}`, body },
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
|
||||
describe('AiChatRunStepRepo + reconstruct contract [integration]', () => {
|
||||
let db: Kysely<any>;
|
||||
let stepRepo: AiChatRunStepRepo;
|
||||
let msgRepo: AiChatMessageRepo;
|
||||
let workspaceId: string;
|
||||
let userId: string;
|
||||
let chatId: string;
|
||||
|
||||
beforeAll(async () => {
|
||||
db = getTestDb();
|
||||
stepRepo = new AiChatRunStepRepo(db as any);
|
||||
msgRepo = new AiChatMessageRepo(db as any);
|
||||
workspaceId = (await createWorkspace(db)).id;
|
||||
userId = (await createUser(db, workspaceId)).id;
|
||||
chatId = (await createChat(db, { workspaceId, creatorId: userId })).id;
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await destroyTestDb();
|
||||
});
|
||||
|
||||
const seedRow = (metadata: unknown, status: string) =>
|
||||
msgRepo.insert({
|
||||
chatId,
|
||||
workspaceId,
|
||||
userId,
|
||||
role: 'assistant',
|
||||
content: '',
|
||||
status,
|
||||
metadata: metadata as never,
|
||||
});
|
||||
|
||||
it('insertStep is idempotent per (message, stepIndex) and reads back in order', async () => {
|
||||
const row = await seedRow(stepMarkerMetadata(0), 'streaming');
|
||||
const parts0 = assistantParts([makeStep(0)], '');
|
||||
const parts1 = assistantParts([makeStep(1)], '');
|
||||
|
||||
expect(await stepRepo.insertStep(row.id, workspaceId, 0, parts0)).toBe(true);
|
||||
expect(await stepRepo.insertStep(row.id, workspaceId, 1, parts1)).toBe(true);
|
||||
// A retried persist of the SAME step is a no-op (ON CONFLICT DO NOTHING).
|
||||
expect(await stepRepo.insertStep(row.id, workspaceId, 0, parts0)).toBe(
|
||||
false,
|
||||
);
|
||||
|
||||
const steps = await stepRepo.findByMessage(row.id, workspaceId);
|
||||
expect(steps.map((s) => s.stepIndex)).toEqual([0, 1]);
|
||||
|
||||
// Batch fetch groups by message id in step order.
|
||||
const map = await stepRepo.findByMessageIds([row.id], workspaceId);
|
||||
expect(map.get(row.id)!.map((s) => s.stepIndex)).toEqual([0, 1]);
|
||||
});
|
||||
|
||||
it('a NEW-style (step-table) run reconstructs identically to an OLD-style (inline) run', async () => {
|
||||
const steps = [makeStep(10), makeStep(11)];
|
||||
// The inline parts the OLD full-row flush would have written.
|
||||
const fullParts = assistantParts(steps, '');
|
||||
|
||||
// OLD-style record: full parts inline on the row, NO step rows.
|
||||
const oldRow = await seedRow(
|
||||
{ parts: fullParts, toolTraceVersion: 2, stepsPersisted: 2 },
|
||||
'completed',
|
||||
);
|
||||
|
||||
// NEW-style record: only a step marker on the row + per-step rows.
|
||||
const newRow = await seedRow(stepMarkerMetadata(2), 'streaming');
|
||||
for (let i = 0; i < steps.length; i++) {
|
||||
await stepRepo.insertStep(
|
||||
newRow.id,
|
||||
workspaceId,
|
||||
i,
|
||||
assistantParts([steps[i]], ''),
|
||||
);
|
||||
}
|
||||
|
||||
// Re-read both from the DB (proves the jsonb roundtrip).
|
||||
const oldFetched = await msgRepo.findById(oldRow.id, workspaceId);
|
||||
const newFetched = await msgRepo.findById(newRow.id, workspaceId);
|
||||
const oldSteps = await stepRepo.findByMessage(oldRow.id, workspaceId);
|
||||
const newSteps = await stepRepo.findByMessage(newRow.id, workspaceId);
|
||||
|
||||
// The discriminator: the old row carries inline parts, the new one does not.
|
||||
expect(rowHasInlineParts(oldFetched!)).toBe(true);
|
||||
expect(rowHasInlineParts(newFetched!)).toBe(false);
|
||||
expect(oldSteps).toHaveLength(0);
|
||||
expect(newSteps).toHaveLength(2);
|
||||
|
||||
const oldRecon = reconstructRunParts(oldFetched!, oldSteps);
|
||||
const newRecon = reconstructRunParts(newFetched!, newSteps);
|
||||
|
||||
// Both reconstruct to the SAME parts + step count — the era is invisible.
|
||||
expect(newRecon.parts).toEqual(fullParts);
|
||||
expect(oldRecon.parts).toEqual(fullParts);
|
||||
expect(newRecon.parts).toEqual(oldRecon.parts);
|
||||
expect(newRecon.stepsPersisted).toBe(2);
|
||||
expect(oldRecon.stepsPersisted).toBe(2);
|
||||
|
||||
// hydrateAssistantParts fills the new row's metadata.parts to match the old
|
||||
// row's inline parts — so a consumer reading `metadata.parts` off the raw row
|
||||
// (the client seed/poll, export) is unchanged across the era.
|
||||
const map = await stepRepo.findByMessageIds([newRow.id], workspaceId);
|
||||
const [hydrated] = hydrateAssistantParts([newFetched!], map);
|
||||
expect((hydrated.metadata as { parts: unknown }).parts).toEqual(fullParts);
|
||||
// A row that already has inline parts passes through untouched (same ref-shape).
|
||||
const [oldPassThrough] = hydrateAssistantParts([oldFetched!], map);
|
||||
expect((oldPassThrough.metadata as { parts: unknown }).parts).toEqual(
|
||||
fullParts,
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -1,63 +0,0 @@
|
||||
import { Kysely, sql } from 'kysely';
|
||||
import {
|
||||
up,
|
||||
down,
|
||||
} from '../../src/database/migrations/20260708T120000-ai-chat-run-steps';
|
||||
import { getTestDb, destroyTestDb } from './db';
|
||||
|
||||
/**
|
||||
* #492 migration up/down roundtrip on a LIVE Postgres. global-setup already
|
||||
* migrated docmost_test to latest (so the table exists at start); this drives the
|
||||
* migration's own down()/up() and asserts the table presence toggles, then leaves
|
||||
* it PRESENT (up) so the shared test DB is intact for any spec that runs after.
|
||||
*/
|
||||
async function tableExists(db: Kysely<any>): Promise<boolean> {
|
||||
const row = (
|
||||
await sql<{ t: string | null }>`select to_regclass('ai_chat_run_steps') as t`.execute(
|
||||
db,
|
||||
)
|
||||
).rows[0];
|
||||
return row.t !== null;
|
||||
}
|
||||
|
||||
async function uniqueIndexExists(db: Kysely<any>): Promise<boolean> {
|
||||
const row = (
|
||||
await sql<{
|
||||
t: string | null;
|
||||
}>`select to_regclass('ai_chat_run_steps_message_step_uidx') as t`.execute(db)
|
||||
).rows[0];
|
||||
return row.t !== null;
|
||||
}
|
||||
|
||||
describe('20260708 ai_chat_run_steps migration roundtrip [integration]', () => {
|
||||
let db: Kysely<any>;
|
||||
|
||||
beforeAll(() => {
|
||||
db = getTestDb();
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
// Belt-and-suspenders: guarantee the table is present for later specs even if
|
||||
// an assertion threw mid-roundtrip.
|
||||
if (!(await tableExists(db))) await up(db);
|
||||
await destroyTestDb();
|
||||
});
|
||||
|
||||
it('down() drops the table+index and up() recreates them (idempotent)', async () => {
|
||||
// Starts applied (global-setup migrated to latest).
|
||||
expect(await tableExists(db)).toBe(true);
|
||||
expect(await uniqueIndexExists(db)).toBe(true);
|
||||
|
||||
await down(db);
|
||||
expect(await tableExists(db)).toBe(false);
|
||||
expect(await uniqueIndexExists(db)).toBe(false);
|
||||
|
||||
await up(db);
|
||||
expect(await tableExists(db)).toBe(true);
|
||||
expect(await uniqueIndexExists(db)).toBe(true);
|
||||
|
||||
// up() is idempotent (ifNotExists) — a second run is a harmless no-op.
|
||||
await expect(up(db)).resolves.not.toThrow();
|
||||
expect(await tableExists(db)).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -322,21 +322,20 @@ describe('AiChatService.stream [integration]', () => {
|
||||
});
|
||||
|
||||
/**
|
||||
* #332 + #490 deferred tool loading, the ON path. Turn 1 starts COLD (CORE +
|
||||
* loadTools only) and activates a deferred tool via loadTools; that activation
|
||||
* is PERSISTED into the chat's metadata.activatedTools (#490) so the NEXT turn
|
||||
* SEEDS from it and the tool is active from the fresh turn's FIRST step — the
|
||||
* model never re-runs loadTools to re-activate the same tool. The unit tests
|
||||
* only exercise pure prepareAgentStep with hand-fed Sets; this pins the real
|
||||
* wiring end-to-end (loadTools.execute -> activatedTools -> persist -> next-turn
|
||||
* seed -> prepareStep -> per-step activeTools) against the real streamText loop.
|
||||
* We drive a MockLanguageModelV3 whose step 1 calls loadTools(['createPage'])
|
||||
* and assert, via the model's recorded per-step CallOptions.tools (the AI SDK
|
||||
* filters the provider tool list by activeTools), that the deferred tool becomes
|
||||
* active on the SAME turn's next step AND, seeded from metadata, on the next
|
||||
* turn's first step.
|
||||
* #332 deferred tool loading, the ON path. The riskiest property is that the
|
||||
* per-turn `activatedTools` Set is created FRESH inside each stream() call, so a
|
||||
* tool a previous turn activated via loadTools is NOT still active when the next
|
||||
* turn starts — the new turn begins "cold" (CORE + loadTools only). The unit
|
||||
* tests only exercise pure prepareAgentStep with hand-fed Sets; this pins the
|
||||
* real wiring end-to-end (loadTools.execute -> activatedTools -> prepareStep ->
|
||||
* per-step activeTools) against the real streamText loop, and proves there is no
|
||||
* cross-turn leak. We drive a MockLanguageModelV3 whose step 1 calls
|
||||
* loadTools(['createPage']) and assert, via the model's recorded per-step
|
||||
* CallOptions.tools (the AI SDK filters the provider tool list by activeTools),
|
||||
* that the deferred tool becomes active on the SAME turn's next step but NOT on a
|
||||
* fresh turn's first step.
|
||||
*/
|
||||
describe('deferred tool loading ON — cross-turn activation persistence (#332 + #490)', () => {
|
||||
describe('deferred tool loading ON — per-turn activation, no leak (#332)', () => {
|
||||
// A stub deferred (non-core) tool the agent can activate. Its execute is never
|
||||
// called — the model only needs to SEE it become active — but it must be a
|
||||
// valid AI-SDK tool so the SDK includes it in a step's tool list once active.
|
||||
@@ -452,7 +451,7 @@ describe('AiChatService.stream [integration]', () => {
|
||||
} as any);
|
||||
}
|
||||
|
||||
it('activates a deferred tool for the SAME turn, and a NEW turn SEEDS it from persisted chat metadata (#490)', async () => {
|
||||
it('activates a deferred tool for the SAME turn, and a NEW turn starts cold (no leak)', async () => {
|
||||
const chatId = (await createChat(db, { workspaceId, creatorId: userId })).id;
|
||||
|
||||
// --- Turn 1: loadTools(createPage) on step 1, then answer on step 2. ---
|
||||
@@ -475,7 +474,7 @@ describe('AiChatService.stream [integration]', () => {
|
||||
// Step 2 of the SAME turn sees the just-activated deferred tool.
|
||||
expect(step2Tools).toContain('createPage');
|
||||
|
||||
// --- Turn 2 on the SAME chat: seeds the persisted activation (#490). ---
|
||||
// --- Turn 2 on the SAME chat: must start cold again. ---
|
||||
const model2 = new MockLanguageModelV3({
|
||||
doStream: async () => ({ stream: successStream() }),
|
||||
} as any);
|
||||
@@ -486,10 +485,9 @@ describe('AiChatService.stream [integration]', () => {
|
||||
|
||||
const nextTurnFirstStep = toolNames(model2.doStreamCalls[0]);
|
||||
expect(nextTurnFirstStep).toContain('loadTools');
|
||||
// #490: activation PERSISTS across turns — turn 1 wrote createPage into the
|
||||
// chat's metadata.activatedTools, so the next turn seeds from it and the
|
||||
// deferred tool is active from the FIRST step (no need to re-run loadTools).
|
||||
expect(nextTurnFirstStep).toContain('createPage');
|
||||
// The activated set is per-turn: the prior turn's createPage did NOT leak,
|
||||
// so the fresh turn's first step sees it deferred again.
|
||||
expect(nextTurnFirstStep).not.toContain('createPage');
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user