Skip to content

fix: salvage partial L3 abstraction drafts #2054

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
RerankerGuo wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

fix: salvage partial L3 abstraction drafts #2054

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
132 changes: 99 additions & 33 deletions apps/memos-local-plugin/core/memory/l3/abstract.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,30 +102,11 @@ export async function abstractDraft(
temperature: 0.15,
malformedRetries: 1,
schemaHint: `{"title":"...","domain_tags":["..."],"environment":[{"label":"...","description":"...","evidenceIds":["..."]}],"inference":[...],"constraints":[...],"body":"markdown","confidence":0..1,"supersedes_world_ids":[]}`,
validate: (v) => {
const o = v as Record<string, unknown>;
if (typeof o.title !== "string" || !(o.title as string).trim()) {
throw new MemosError(
ERROR_CODES.LLM_OUTPUT_MALFORMED,
"l3.abstraction: 'title' must be a non-empty string",
{ got: o.title },
);
}
const triple = ["environment", "inference", "constraints"];
for (const k of triple) {
if (!Array.isArray(o[k])) {
throw new MemosError(
ERROR_CODES.LLM_OUTPUT_MALFORMED,
`l3.abstraction: '${k}' must be an array`,
{ got: o[k] },
);
}
}
},
},
);

const draft = normaliseDraft(rsp.value);
assertDraftMinimallyUsable(draft);
if (deps.validate) deps.validate(draft);
return { ok: true, draft };
} catch (err) {
Expand Down Expand Up @@ -260,13 +241,15 @@ function packPolicy(

function normaliseDraft(value: Record<string, unknown>): L3AbstractionDraft {
const triple = pickTriple(value);
const domainTags = normaliseTags(value.domain_tags);
const body = typeof value.body === "string" ? sanitizeDerivedMarkdown(value.body) : "";
return {
title: sanitizeDerivedText(value.title),
domainTags: normaliseTags(value.domain_tags),
title: deriveTitle(value.title, triple, body, domainTags),
domainTags,
environment: triple.environment,
inference: triple.inference,
constraints: triple.constraints,
body: typeof value.body === "string" ? sanitizeDerivedMarkdown(value.body) : "",
body,
confidence: clamp01(typeof value.confidence === "number" ? value.confidence : 0.5),
supersedesWorldIds: Array.isArray(value.supersedes_world_ids)
? (value.supersedes_world_ids as unknown[])
Expand All @@ -289,17 +272,27 @@ function pickTriple(value: Record<string, unknown>): {
}

function toEntries(raw: unknown): L3AbstractionDraftEntry[] {
if (!Array.isArray(raw)) return [];
return raw
const items = Array.isArray(raw) ? raw : raw == null ? [] : [raw];
return items
.map((r): L3AbstractionDraftEntry | null => {
if (typeof r === "string") {
const description = sanitizeDerivedMarkdown(r);
return description ? { label: "", description, evidenceIds: undefined } : null;
}
if (!r || typeof r !== "object") return null;
const o = r as Record<string, unknown>;
const label = typeof o.label === "string" ? sanitizeDerivedText(o.label) : "";
const description = typeof o.description === "string" ? sanitizeDerivedMarkdown(o.description) : "";
const label = firstText(o, ["label", "name", "title", "heading", "key"]);
const description = firstMarkdown(o, [
"description",
"body",
"text",
"content",
"detail",
"summary",
"value",
]);
if (!label && !description) return null;
const evidenceIds = Array.isArray(o.evidenceIds)
? (o.evidenceIds as unknown[]).filter((s): s is string => typeof s === "string")
: undefined;
const evidenceIds = normaliseEvidenceIds(o.evidenceIds ?? o.evidence_ids ?? o.evidence);
return { label, description, evidenceIds };
})
.filter((e): e is L3AbstractionDraftEntry => e !== null)
Expand Down Expand Up @@ -328,15 +321,88 @@ function buildBody(draft: L3AbstractionDraft): string {
}

function normaliseTags(raw: unknown): string[] {
if (!Array.isArray(raw)) return [];
const values = Array.isArray(raw)
? raw
: typeof raw === "string"
? raw.split(/[,;\n]/)
: raw == null
? []
: [raw];
return dedupeStrings(
(raw as unknown[])
.filter((s): s is string => typeof s === "string")
values
.map((value) => {
if (typeof value === "string") return value;
if (value && typeof value === "object") {
return firstText(value as Record<string, unknown>, ["label", "name", "tag", "value", "key"]);
}
return "";
})
.map((s) => s.trim().toLowerCase())
.filter((s) => s.length > 0 && s.length < 24),
).slice(0, 6);
}

function firstText(o: Record<string, unknown>, keys: readonly string[]): string {
for (const key of keys) {
const cleaned = sanitizeDerivedText(o[key]);
if (cleaned) return cleaned;
}
return "";
}

function firstMarkdown(o: Record<string, unknown>, keys: readonly string[]): string {
for (const key of keys) {
const cleaned = sanitizeDerivedMarkdown(o[key]);
if (cleaned) return cleaned;
}
return "";
}

function normaliseEvidenceIds(raw: unknown): string[] | undefined {
const values = Array.isArray(raw)
? raw
: typeof raw === "string"
? raw.split(/[,;\n]/)
: [];
const ids = values
.map((value) => sanitizeDerivedText(value))
.filter((value) => value.length > 0);
return ids.length > 0 ? dedupeStrings(ids) : undefined;
}

function deriveTitle(
rawTitle: unknown,
triple: ReturnType<typeof pickTriple>,
body: string,
domainTags: readonly string[],
): string {
const title = sanitizeDerivedText(rawTitle);
if (title) return title.slice(0, 160);
for (const bucket of [triple.inference, triple.environment, triple.constraints]) {
for (const entry of bucket) {
const candidate = entry.label || entry.description;
if (candidate) return sanitizeDerivedText(candidate).slice(0, 160);
}
}
const bodyLine = body
.split(/\r?\n/)
.map((line) => sanitizeDerivedText(line.replace(/^#+\s*/, "")))
.find((line) => line.length > 0);
if (bodyLine) return bodyLine.slice(0, 160);
return domainTags.join(" ").slice(0, 160);
}

function assertDraftMinimallyUsable(draft: L3AbstractionDraft): void {
const hasEntries =
draft.environment.length > 0 || draft.inference.length > 0 || draft.constraints.length > 0;
if (draft.title || draft.body || draft.domainTags.length > 0 || hasEntries) return;
throw new MemosError(
ERROR_CODES.LLM_OUTPUT_MALFORMED,
"l3.abstraction: empty draft after normalisation",
{},
);
}

function dedupeStrings(arr: readonly string[]): string[] {
return Array.from(new Set(arr));
}
Expand Down
72 changes: 68 additions & 4 deletions apps/memos-local-plugin/tests/unit/memory/l3/abstract.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
* - happy path → ok + draft with normalised tags + triple
* - LLM disabled → llm_disabled
* - LLM throws → llm_failed (no uncaught throw)
* - malformed JSON (missing environment[]) → llm_failed
* - salvageable JSON drafts are normalised before persistence
*/

import { describe, expect, it } from "vitest";
Expand Down Expand Up @@ -180,7 +180,7 @@ describe("memory/l3/abstract", () => {
expect(res.detail).toContain("boom");
});

it("returns llm_failed when the LLM returns missing triple", async () => {
it("salvages a draft with missing triple arrays", async () => {
const llm = fakeLlm({
completeJson: {
[OP]: {
Expand All @@ -193,10 +193,75 @@ describe("memory/l3/abstract", () => {
{ cluster: mkCluster(), evidenceByPolicy: new Map() },
{ llm, log, config: cfg() },
);
expect(res.ok).toBe(true);
if (!res.ok) return;
expect(res.draft.title).toBe("missing triple");
expect(res.draft.environment).toEqual([]);
expect(res.draft.inference).toEqual([]);
expect(res.draft.constraints).toEqual([]);
});

it("normalises salvageable string/object entries and tag strings", async () => {
const llm = fakeLlm({
completeJson: {
[OP]: {
title: "",
domain_tags: "Docker, Alpine; pip\nWheels",
environment: "Alpine uses musl libc.",
inference: [{ body: "Binary wheels often fail on musl.", name: "Wheel mismatch" }],
constraints: ["Install system headers before pip."],
confidence: 0.8,
},
},
});

const res = await abstractDraft(
{ cluster: mkCluster(), evidenceByPolicy: new Map() },
{ llm, log, config: cfg() },
);

expect(res.ok).toBe(true);
if (!res.ok) return;
expect(res.draft.title).toBe("Wheel mismatch");
expect(res.draft.domainTags).toEqual(["docker", "alpine", "pip", "wheels"]);
expect(res.draft.environment).toEqual([
{ label: "", description: "Alpine uses musl libc.", evidenceIds: undefined },
]);
expect(res.draft.inference).toEqual([
{
label: "Wheel mismatch",
description: "Binary wheels often fail on musl.",
evidenceIds: undefined,
},
]);
expect(res.draft.constraints).toEqual([
{ label: "", description: "Install system headers before pip.", evidenceIds: undefined },
]);
});

it("still rejects drafts with no usable content after normalisation", async () => {
const llm = fakeLlm({
completeJson: {
[OP]: {
title: "",
domain_tags: "",
environment: [],
inference: [],
constraints: [],
body: "",
},
},
});

const res = await abstractDraft(
{ cluster: mkCluster(), evidenceByPolicy: new Map() },
{ llm, log, config: cfg() },
);

expect(res.ok).toBe(false);
if (res.ok) return;
expect(res.reason).toBe("llm_failed");
expect(res.detail ?? "").toMatch(/environment|inference|constraints/);
expect(res.detail ?? "").toContain("empty draft");
});

it("buildWorldModelRow wires draft + cluster into a persist-ready row", () => {
Expand Down Expand Up @@ -227,4 +292,3 @@ describe("memory/l3/abstract", () => {
expect(row.body).toContain("Environment");
});
});