amosblomqvist
bd9694b0e4
OpenRouter log diagnosis (owner, 2026-09-28): extraction time was
dominated by tool-validation retries. The failing call had the whole
propositions array emitted as ONE JSON-STRING ('propositions.0: must
be object'), a truncated placeholder artifact inside it, and
word-salad statements late in the array — payload-size collapse.
Field audit: 'evidence' was never persisted anywhere and its
faithfulness-checking consumer died with the fully-trusted ruling;
'messages' fed messageId granularity that NOTHING downstream reads,
and the model sent [] anyway (chat-level provenance in practice).
'aliases' stays (optional now): the auditor's find tool globs them.
Schema: propositions = {id, name, statement, aliases?}; edges =
{from, to, type}. Prompts lose the evidence/messages doctrine and
[id]-anchor guidance, gain a compact faithfulness line;
transcriptView renders anchorless. The auditor echo instruction
drops the evidence/messages mention, so its payload halves too.
Heal: healStringifiedArrays on the submit tool's prepareArguments
(pi-agent-core's sanctioned pre-TypeBox shim) parses a stringified
propositions/edges back into arrays — the LaTeX-restore doctrine:
heal weak-model wire behavior at the seam. Test drives the real
agent-loop seam with a stringified submit.
1299 lines
53 KiB
TypeScript
1299 lines
53 KiB
TypeScript
/**
|
||
* The extraction pipeline tests (vision §1 construction, 2026-09-02 redesign;
|
||
* relinked 2026-09-27): extractor → auditor → merger, the sole graph writer —
|
||
* the extractor alone sees the source (whole-session markdown), the auditor
|
||
* never does (identity linking through graph tools), the merger is
|
||
* deterministic.
|
||
*
|
||
* transcriptView — the markdown rendering the extractor sees (pure):
|
||
* id-anchored Teacher/Learner blocks + check blocks
|
||
* pipeline — scripted faux engines drive both agents: findings out,
|
||
* audit verdict (with linkTo identity) in, deterministic
|
||
* merge applied; failure paths checkpoint nothing;
|
||
* single-flight per chat
|
||
*
|
||
* The merger itself (identity verdicts, idempotency) is tested in
|
||
* tests/graph.test.ts directly against mergeFindings — here it is the
|
||
* integration: what one full pipeline run does to the ledgers.
|
||
*
|
||
* Ledger: in-memory (the GraphStore port) — this suite never touches
|
||
* data/graph. Chats: real ChatRecords in the real chat store (created and
|
||
* deleted by this suite).
|
||
*/
|
||
|
||
import assert from "node:assert/strict";
|
||
import * as fs from "node:fs";
|
||
import { after, describe, it } from "node:test";
|
||
import { createFauxCore, fauxAssistantMessage, fauxToolCall, type FauxResponseStep, type ToolCall } from "@earendil-works/pi-ai";
|
||
import type { PiEngine } from "../src/agent/models.ts";
|
||
import type { LhMessage } from "../src/core/native-messages.ts";
|
||
import { newPlanBlockMessage } from "../src/core/native-messages.ts";
|
||
import { projectView as projectNative } from "../src/core/view.ts";
|
||
import type {
|
||
AuditResult,
|
||
CoverageEntry,
|
||
ExtractionRunUsage,
|
||
GraphEdge,
|
||
GraphNode,
|
||
NodeMapping,
|
||
NotesSource,
|
||
SessionCheckpoint,
|
||
SessionFindings,
|
||
} from "../src/core/contracts.ts";
|
||
import type { GraphStore } from "../src/core/ports.ts";
|
||
import { abortExtraction, createExtractionPipeline, extractionStatuses, transcriptView } from "../src/agent/subagents/extraction.ts";
|
||
import { ModelsNotConfiguredError, ProviderKeyMissingError, providerKeyMissing, type ModelSlotName } from "../src/core/settings.ts";
|
||
import { coverageOf, messageViewLines } from "../src/core/coverage.ts";
|
||
import { chatStore } from "../src/store/chats.ts";
|
||
import { PATHS } from "../config.ts";
|
||
|
||
// ─── fixtures ────────────────────────────────────────────────────────────────
|
||
|
||
const createdChats: string[] = [];
|
||
|
||
/** A scripted pi engine (faux provider, docs/pi-engine-swap.md §7): the
|
||
* response queue replaces the old doGenerate turn counter. Usage is
|
||
* ESTIMATED by faux from the prompt/response text (deterministic, > 0) —
|
||
* the tests assert structure and positivity, not flat mock numbers. */
|
||
function fauxEngine(steps: FauxResponseStep[]): PiEngine {
|
||
const faux = createFauxCore({});
|
||
faux.setResponses(steps);
|
||
return { model: faux.getModel(), streamFn: faux.streamSimple };
|
||
}
|
||
|
||
/** An in-memory GraphStore (core/ports.ts) — this suite never touches data/graph. */
|
||
function memoryLedgers() {
|
||
const nodes: GraphNode[] = [];
|
||
const edges: GraphEdge[] = [];
|
||
const mappings: NodeMapping[] = [];
|
||
const checkpoints: SessionCheckpoint[] = [];
|
||
const coverage: CoverageEntry[] = [];
|
||
const sources = new Map<string, NotesSource>();
|
||
const positions = new Map<string, { x: number; y: number }>();
|
||
return {
|
||
appendNode: (n: GraphNode) => void nodes.push(n),
|
||
readNodes: () => nodes.map((n) => ({ ...n })),
|
||
appendEdge: (e: GraphEdge) => void edges.push(e),
|
||
readEdges: () => edges.map((e) => ({ ...e })),
|
||
appendMapping: (m: NodeMapping) => void mappings.push(m),
|
||
readMappings: () => mappings.map((m) => ({ ...m })),
|
||
appendCheckpoint: (c: SessionCheckpoint) => void checkpoints.push(c),
|
||
readCheckpoints: () => checkpoints.map((c) => ({ ...c })),
|
||
// Extraction coverage (vision-extraction-coverage.md) — append-only;
|
||
// the chat pipeline checkpoints one entry per covered message.
|
||
appendCoverage: (e) => void coverage.push({ ...e }),
|
||
readCoverage: () => coverage.map((e) => ({ ...e })),
|
||
upsertSource: (s: NotesSource) => {
|
||
// Mirrors the real store: an upsert KEEPS the existing usage log.
|
||
const prev = sources.get(s.id);
|
||
sources.set(s.id, { ...s, extractions: [...(prev?.extractions ?? [])] });
|
||
},
|
||
readSources: () => [...sources.values()].map((s) => ({ ...s, extractions: [...(s.extractions ?? [])] })),
|
||
appendSourceUsage: (id: string, entry: ExtractionRunUsage) => {
|
||
const source = sources.get(id);
|
||
if (!source) return;
|
||
if (!source.extractions?.some((r) => r.startedAt === entry.startedAt)) {
|
||
source.extractions = [...(source.extractions ?? []), entry];
|
||
}
|
||
},
|
||
// Cluster labelings — mirrors the real store: append dedupes by id.
|
||
// The layout ledger — settleGraphLayout writes it after each merge.
|
||
readPositions: () => Object.fromEntries([...positions].map(([id, p]) => [id, { ...p }])),
|
||
writePositions: (next) => {
|
||
positions.clear();
|
||
for (const [id, p] of Object.entries(next)) positions.set(id, { x: p.x, y: p.y });
|
||
},
|
||
// The destructive seam (wave 6 session deletion) — mirrors the real
|
||
// store: replace the provided ledgers' full contents.
|
||
rewriteLedgers: (next) => {
|
||
if (next.nodes) nodes.splice(0, nodes.length, ...next.nodes.map((n) => ({ ...n, provenance: [...n.provenance], aliases: [...n.aliases] })));
|
||
if (next.edges) edges.splice(0, edges.length, ...next.edges.map((e) => ({ ...e, provenance: [...e.provenance] })));
|
||
if (next.mappings) mappings.splice(0, mappings.length, ...next.mappings.map((m) => ({ ...m })));
|
||
if (next.coverage) coverage.splice(0, coverage.length, ...next.coverage.map((c) => ({ ...c })));
|
||
if (next.checkpoints) checkpoints.splice(0, checkpoints.length, ...next.checkpoints.map((c) => ({ ...c })));
|
||
},
|
||
} satisfies GraphStore;
|
||
}
|
||
|
||
// Native fixture builders (Wave B): the record holds pi-native history —
|
||
// an assistant message with its tool calls + one result message per call;
|
||
// the projection reproduces the part shapes these view tests pin.
|
||
interface NativeCallDesc {
|
||
name: string;
|
||
toolCallId: string;
|
||
input: Record<string, unknown>;
|
||
output: unknown;
|
||
}
|
||
|
||
function user(id: string, text: string): LhMessage {
|
||
return { id, role: "user", content: text, timestamp: Date.now() } as never;
|
||
}
|
||
|
||
function assistant(id: string, items: unknown[]): LhMessage[] {
|
||
const content: unknown[] = [];
|
||
const calls: NativeCallDesc[] = [];
|
||
for (const item of items) {
|
||
const it = item as { type?: string; text?: string };
|
||
if (it && it.type === "text") {
|
||
content.push({ type: "text", text: it.text });
|
||
} else {
|
||
const call = item as NativeCallDesc;
|
||
calls.push(call);
|
||
content.push({ type: "toolCall", id: call.toolCallId, name: call.name, arguments: call.input as never });
|
||
}
|
||
}
|
||
const out: LhMessage[] = [
|
||
{
|
||
id,
|
||
role: "assistant",
|
||
content,
|
||
api: "openai-completions",
|
||
provider: "openrouter",
|
||
model: "test",
|
||
usage: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
||
stopReason: "stop",
|
||
timestamp: Date.now(),
|
||
} as never,
|
||
];
|
||
for (const call of calls) {
|
||
out.push({
|
||
id: `r_${call.toolCallId}`,
|
||
role: "toolResult",
|
||
toolCallId: call.toolCallId,
|
||
toolName: call.name,
|
||
content: [{ type: "text", text: "ok" }],
|
||
details: call.output,
|
||
isError: false,
|
||
timestamp: Date.now(),
|
||
} as never);
|
||
}
|
||
return out;
|
||
}
|
||
|
||
function quizPart(toolCallId: string, input: Record<string, unknown>, output: Record<string, unknown>): NativeCallDesc {
|
||
return { name: "quiz", toolCallId, input, output };
|
||
}
|
||
|
||
function planPart(toolCallId: string, name: string, input: Record<string, unknown>, tree: unknown): NativeCallDesc {
|
||
return { name, toolCallId, input, output: { ok: true, tree } };
|
||
}
|
||
|
||
/** A session-shaped fixture chat: probe → teaching text → check. Tree-blind
|
||
* world: the plan tree is NOT part of extraction — it is noise. */
|
||
function fixtureChat() {
|
||
const chat = chatStore.createChat("Extraction fixture");
|
||
createdChats.push(chat.id);
|
||
chatStore.saveMessages(chat.id, [
|
||
user("u1", "teach me the chain rule"),
|
||
...assistant("a1", [
|
||
quizPart("probe-1", { question: "What is a derivative, roughly?" }, {
|
||
questionId: "probe-1", kind: "quiz", questionText: "What is a derivative, roughly?",
|
||
correct: false, dontKnow: false, answeredAt: "2026-08-22T01:00:00.000Z",
|
||
}),
|
||
]),
|
||
// Distinct TURNS: the native grouping canon merges consecutive
|
||
// assistant messages into one view group, so the fixture separates
|
||
// its turns with learner messages (the real record's shape).
|
||
user("u2", "go on"),
|
||
...assistant("a2", [
|
||
{ type: "text", text: "The derivative measures how fast a function changes." },
|
||
planPart("p1", "plan_init", { nodes: [], edges: [] }, { nodes: [], edges: [], currentNodeId: null, doneNodeIds: [], version: 1 }),
|
||
]),
|
||
user("u3", "check me"),
|
||
...assistant("a3", [
|
||
quizPart("check-1", { question: "Check" }, {
|
||
questionId: "check-1", kind: "quiz", questionText: "Check", correct: true, dontKnow: false,
|
||
answeredAt: "2026-08-22T02:00:00.000Z",
|
||
}),
|
||
]),
|
||
].flat());
|
||
return { chatId: chat.id, record: chatStore.getChat(chat.id)! };
|
||
}
|
||
|
||
after(() => {
|
||
for (const id of createdChats) {
|
||
try {
|
||
fs.unlinkSync(`${PATHS.chats}/${id}.json`);
|
||
} catch {
|
||
/* already gone */
|
||
}
|
||
}
|
||
});
|
||
|
||
/** What the extractor would produce for the fixture session — tree-blind,
|
||
* free-form, with chat-level provenance. */
|
||
const FINDINGS: SessionFindings = {
|
||
propositions: [
|
||
{
|
||
id: "p1",
|
||
name: "Derivative",
|
||
statement: "The derivative measures how fast a function changes",
|
||
aliases: [],
|
||
},
|
||
{
|
||
id: "p2",
|
||
name: "Chain rule",
|
||
statement: "The chain rule differentiates composed functions by multiplying local rates.",
|
||
aliases: [],
|
||
},
|
||
],
|
||
edges: [
|
||
{
|
||
from: "p1",
|
||
to: "p2",
|
||
type: "follows",
|
||
},
|
||
],
|
||
};
|
||
|
||
/** An engine whose ONE response is the `name` tool call with the given
|
||
* input — the whole deliverable; the pipeline stops after a clean submit
|
||
* (shouldStop), so no trailing text step exists anymore. `onCall` fires at
|
||
* the moment of the model call — the observation point for mid-run
|
||
* assertions. */
|
||
function submitModel(name: string, input: unknown, onCall?: () => void): PiEngine {
|
||
return fauxEngine([
|
||
(context) => {
|
||
onCall?.();
|
||
void context;
|
||
return fauxAssistantMessage(
|
||
[fauxToolCall(name, input as ToolCall["arguments"], { id: `${name}-call` })],
|
||
{ stopReason: "toolUse" },
|
||
);
|
||
},
|
||
]);
|
||
}
|
||
|
||
/** A submit model whose single response WAITS on a gate before answering —
|
||
* the timing control for the serialized-audit tests (owner 2026-09-28):
|
||
* the model call has STARTED (onCall fired, the run holds the audit
|
||
* gate) but will not resolve until the test opens the gate. */
|
||
function gatedSubmitModel(name: string, input: unknown, gate: Promise<void>, onCall?: () => void): PiEngine {
|
||
return fauxEngine([
|
||
async () => {
|
||
onCall?.();
|
||
await gate;
|
||
return fauxAssistantMessage(
|
||
[fauxToolCall(name, input as ToolCall["arguments"], { id: `${name}-call` })],
|
||
{ stopReason: "toolUse" },
|
||
);
|
||
},
|
||
]);
|
||
}
|
||
|
||
/** Poll until true — the queued-phase observations need real ticks. */
|
||
async function until(cond: () => boolean, ms = 2000): Promise<void> {
|
||
for (const t0 = Date.now(); !cond(); ) {
|
||
if (Date.now() - t0 > ms) throw new Error("condition never became true in time");
|
||
await new Promise((r) => setTimeout(r, 2));
|
||
}
|
||
}
|
||
|
||
/** An engine whose model call never resolves until its abort signal fires
|
||
* — mimicking a cancelled provider request (the abort path). Like a real
|
||
* provider, an ALREADY-aborted signal resolves immediately (the abort can
|
||
* win the race before the call attaches its listener); the faux stream
|
||
* then sees the aborted signal and ends the message as aborted. */
|
||
function hangingModel(): PiEngine {
|
||
return fauxEngine([
|
||
(_context, options) =>
|
||
new Promise((resolve) => {
|
||
const sig = options?.signal;
|
||
if (sig?.aborted) {
|
||
resolve(fauxAssistantMessage("late"));
|
||
return;
|
||
}
|
||
sig?.addEventListener("abort", () => resolve(fauxAssistantMessage("late")), { once: true });
|
||
}),
|
||
]);
|
||
}
|
||
|
||
/** An engine that never calls a tool (the failure path). */
|
||
function silentModel(): PiEngine {
|
||
return fauxEngine([fauxAssistantMessage("I refuse to use tools"), fauxAssistantMessage("…")]);
|
||
}
|
||
|
||
// ─── transcriptView (pure) ───────────────────────────────────────────────────
|
||
|
||
describe("transcriptView (pure — the shared markdown engine, owner 2026-09-27)", () => {
|
||
it("renders anchorless speaker blocks + check blocks — tree-blind, plan ops folded", () => {
|
||
const { record } = fixtureChat();
|
||
const view = transcriptView(record);
|
||
|
||
// The document header is the session title.
|
||
assert.match(view, /^# Extraction fixture$/m);
|
||
|
||
// Conversation verbatim, each block headed by its speaker only —
|
||
// the [id] anchors are GONE (submit-schema slim, 2026-09-28:
|
||
// propositions no longer report message ids).
|
||
assert.match(view, /### Learner\n\nteach me the chain rule/);
|
||
assert.match(view, /### Teacher\n\nThe derivative measures how fast a function changes\./);
|
||
|
||
// Checks render as readable blocks (question + outcome).
|
||
assert.match(view, /### Quiz\n/);
|
||
assert.match(view, /\*\*Q:\*\* What is a derivative, roughly\?/);
|
||
assert.match(view, /The learner answered incorrectly\./);
|
||
assert.match(view, /The learner answered correctly\./);
|
||
|
||
// TREE-BLIND: no plan tree, no tree edges, no mark_done lines — plan
|
||
// ops fold to the generic one-liner like every other non-quiz tool.
|
||
assert.doesNotMatch(view, /FINAL PLAN TREE/);
|
||
assert.doesNotMatch(view, /TREE EDGES/);
|
||
assert.match(view, /\*plan_init result delivered\*/);
|
||
assert.doesNotMatch(view, /output-available/);
|
||
});
|
||
|
||
it("summarizes job tool results as one line and drops empty text", () => {
|
||
const chat = chatStore.createChat("View noise fixture");
|
||
createdChats.push(chat.id);
|
||
chatStore.saveMessages(chat.id, [
|
||
user("u1", "go"),
|
||
...assistant("a1", [
|
||
{
|
||
name: "research",
|
||
toolCallId: "r1",
|
||
input: { question: "q" },
|
||
output: { brief: "long brief", sources: [] },
|
||
},
|
||
{ type: "text", text: " " },
|
||
]),
|
||
].flat());
|
||
const view = transcriptView(chatStore.getChat(chat.id)!);
|
||
assert.match(view, /\*research result delivered\*/);
|
||
assert.doesNotMatch(view, /long brief/);
|
||
assert.doesNotMatch(view, /### Teacher/);
|
||
});
|
||
});
|
||
|
||
// ─── the pipeline ───────────────────────────────────────────────────────────
|
||
|
||
describe("the extraction pipeline (extractor → auditor → merger)", () => {
|
||
it("stringified-payload heal (owner, 2026-09-28): propositions arriving as ONE JSON string still validate and merge", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
const verdict: AuditResult = { propositions: FINDINGS.propositions, edges: FINDINGS.edges };
|
||
|
||
// The weak-model failure from the OpenRouter log: the whole array
|
||
// emitted as a JSON-STRING ("propositions.0: must be object").
|
||
// pi-agent-core's prepareArguments shim runs BEFORE TypeBox — the
|
||
// heal parses it, validation passes, no retry burned.
|
||
const extractor = submitModel("submit_findings", {
|
||
propositions: JSON.stringify(FINDINGS.propositions),
|
||
edges: FINDINGS.edges,
|
||
});
|
||
|
||
const pipeline = createExtractionPipeline({ chatStore, graphStore: ledgers, extractor, auditor: submitModel("submit_review", verdict) });
|
||
const stats = await pipeline.runExtraction(chatId);
|
||
assert.deepEqual(stats, { nodes: 2, edges: 1 });
|
||
});
|
||
|
||
it("runs end to end: findings → audit verdict (identity) → deterministic merge + checkpoint", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
|
||
// The auditor passes p1 through and LINKS it to a pre-existing node
|
||
// (identity verdict); p2 stays a verdict-free create.
|
||
const existingId = "n_existing";
|
||
ledgers.appendNode({
|
||
id: existingId,
|
||
name: "Derivative",
|
||
statement: "Derivatives measure rates of change",
|
||
aliases: [],
|
||
createdAt: "2026-08-01T00:00:00.000Z",
|
||
provenance: [],
|
||
});
|
||
const verdict: AuditResult = {
|
||
propositions: [
|
||
{ ...FINDINGS.propositions[0]!, linkTo: existingId },
|
||
],
|
||
edges: [],
|
||
};
|
||
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", FINDINGS),
|
||
auditor: submitModel("submit_review", verdict),
|
||
});
|
||
const stats = await pipeline.runExtraction(chatId);
|
||
|
||
// The linked proposition created NO new node.
|
||
assert.deepEqual(stats, { nodes: 0, edges: 0 });
|
||
|
||
// Link-append: the phrasing joined the existing node's aliases and
|
||
// the provenance unioned; no second node line defines a new node.
|
||
assert.equal(ledgers.readNodes().length, 2); // the pre-seeded line + the link line
|
||
assert.deepEqual(ledgers.readMappings(), [{ chatId, sourceId: "p1", graphNodeId: existingId }]);
|
||
|
||
// COVERAGE checkpointed per message (not a whole-chat checkpoint):
|
||
// one entry per transcript message, fingerprinted content each —
|
||
// the same turns are never extracted twice.
|
||
const record = chatStore.getChat(chatId)!;
|
||
const covered = ledgers.readCoverage();
|
||
// Wave D: the coverage unit is the VISIBLE native message — bonded
|
||
// riders with no view lines (a textless call message) are context,
|
||
// never checkpointed.
|
||
const visible = record.messages.filter(
|
||
(m) => messageViewLines(m, m.id).length > 0,
|
||
).length;
|
||
assert.equal(covered.length, visible);
|
||
assert.ok(covered.every((c) => c.chatId === chatId && c.fp.length === 64 && c.tokens > 0));
|
||
assert.equal(ledgers.readCheckpoints().length, 0, "the chat path writes coverage, not the legacy checkpoint");
|
||
|
||
assert.equal(
|
||
coverageOf(record.messages, covered, chatId).uncoveredCount,
|
||
0,
|
||
"every message is now covered",
|
||
);
|
||
});
|
||
|
||
it("BYOK refusal: no stage engines anywhere → the run throws honestly before any stage (owner, 2026-09-22)", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
// No direct engines AND no engineFor — the chain came up empty.
|
||
const pipeline = createExtractionPipeline({ chatStore, graphStore: ledgers });
|
||
await assert.rejects(pipeline.runExtraction(chatId), (err: unknown) => {
|
||
assert.ok(err instanceof ModelsNotConfiguredError);
|
||
assert.deepEqual(err.envelope.missing, ["cheap"]); // extractor + auditor are the cheap tier
|
||
assert.equal(err.envelope.code, "models_not_configured");
|
||
return true;
|
||
});
|
||
// nothing ran: no phase residue, no usage, no coverage writes
|
||
assert.equal(ledgers.readCoverage().length, 0);
|
||
});
|
||
|
||
it("key-presence refusal: a stage engine whose provider key is gone throws before any batch (provider-key interlude, 2026-09-25)", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
const extractor = fauxEngine([]);
|
||
const auditor = fauxEngine([]);
|
||
const seen: Array<[string, ModelSlotName]> = [];
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor,
|
||
auditor,
|
||
providerKeyMissing: (provider, tier) => {
|
||
seen.push([provider, tier]);
|
||
return providerKeyMissing(provider, [tier]);
|
||
},
|
||
});
|
||
await assert.rejects(pipeline.runExtraction(chatId), (err: unknown) => {
|
||
assert.ok(err instanceof ProviderKeyMissingError);
|
||
assert.equal(err.envelope.code, "provider_key_missing");
|
||
assert.equal(err.envelope.provider, extractor.model.provider, "the provider of the keyless engine");
|
||
assert.deepEqual(err.envelope.slots, ["cheap"], "extractor + auditor are the cheap tier");
|
||
return true;
|
||
});
|
||
// FIRST offender surfaces (extractor before auditor) — and nothing
|
||
// ran: the refusal lands before any batch, no coverage writes.
|
||
assert.deepEqual(seen, [[extractor.model.provider, "cheap"]]);
|
||
assert.equal(ledgers.readCoverage().length, 0);
|
||
});
|
||
|
||
it("key-presence pass-through: null from the check lets a stage through — the NEXT keyless stage surfaces (first-offender discipline)", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
let calls = 0;
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: fauxEngine([]),
|
||
auditor: fauxEngine([]),
|
||
providerKeyMissing: (provider, tier) => (calls++ === 0 ? null : providerKeyMissing(provider, [tier])),
|
||
});
|
||
await assert.rejects(pipeline.runExtraction(chatId), (err: unknown) => {
|
||
assert.ok(err instanceof ProviderKeyMissingError, "the auditor's refusal surfaces after the extractor passed");
|
||
return true;
|
||
});
|
||
assert.equal(calls, 2, "both stages were checked, in order");
|
||
assert.equal(ledgers.readCoverage().length, 0);
|
||
});
|
||
|
||
it("the LLM cluster-namer is DEAD (wave 7): a merge mints no naming runs — labels are session names now", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
// Identity-pass verdict: p1 becomes a new node, p2 unlinked.
|
||
const verdict: AuditResult = {
|
||
propositions: [{ ...FINDINGS.propositions[0]! }],
|
||
edges: [],
|
||
};
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", FINDINGS),
|
||
auditor: submitModel("submit_review", verdict),
|
||
});
|
||
const stats = await pipeline.runExtraction(chatId);
|
||
assert.deepEqual(stats, { nodes: 1, edges: 0 });
|
||
// Wave 7 (950ddfd): birth-session clusters carry session-name labels,
|
||
// so the post-merge naming garnish is gone — no model spend, no
|
||
// naming-run records, no label writes.
|
||
});
|
||
|
||
|
||
|
||
it("engineFor fills the stages (model slots wave): the chain replaces config pins", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
const verdict: AuditResult = {
|
||
propositions: FINDINGS.propositions,
|
||
edges: [],
|
||
};
|
||
const consulted: string[] = [];
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
// NO direct values — the stages resolve ENTIRELY through engineFor
|
||
// (the role override → slot → factory-pin chain, read fresh per
|
||
// stage call in production; here, the scripted chain).
|
||
engineFor: (role) => {
|
||
consulted.push(role);
|
||
if (role === "extractor") return submitModel("submit_findings", FINDINGS);
|
||
if (role === "auditor") return submitModel("submit_review", verdict);
|
||
return submitModel("submit_labels", { labels: [] });
|
||
},
|
||
});
|
||
const stats = await pipeline.runExtraction(chatId);
|
||
assert.equal(stats.nodes, 2, "the chain-fed pipeline ran end to end — both propositions merged");
|
||
// The stages were resolved through the chain, in pipeline order (the
|
||
// labeler is fire-and-forget garnish — extractor + auditor are the
|
||
// pinned order).
|
||
assert.equal(consulted[0], "extractor");
|
||
assert.equal(consulted[1], "auditor");
|
||
});
|
||
|
||
it("direct test values still WIN over engineFor (the priority pin)", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
const verdict: AuditResult = {
|
||
propositions: FINDINGS.propositions,
|
||
edges: [],
|
||
};
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", FINDINGS),
|
||
auditor: submitModel("submit_review", verdict),
|
||
// If the direct values did NOT win, this throw would surface.
|
||
engineFor: (role) => {
|
||
throw new Error(`engineFor should not be consulted for ${role} when a direct value is set`);
|
||
},
|
||
});
|
||
const stats = await pipeline.runExtraction(chatId);
|
||
assert.equal(stats.nodes, 2, "the direct-value seams ran, untouched by engineFor");
|
||
});
|
||
|
||
it("checkpoints nothing when a stage fails", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", FINDINGS),
|
||
auditor: silentModel(), // never submits the review
|
||
});
|
||
await assert.rejects(pipeline.runExtraction(chatId), /the auditor never submitted a review/);
|
||
assert.equal(ledgers.readNodes().length, 0);
|
||
assert.equal(ledgers.readCheckpoints().length, 0, "no checkpoint — the next trigger re-runs");
|
||
|
||
const failingExtractor = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: silentModel(),
|
||
auditor: submitModel("submit_review", FINDINGS),
|
||
});
|
||
await assert.rejects(failingExtractor.runExtraction(chatId), /the extractor never submitted findings/);
|
||
assert.equal(ledgers.readCheckpoints().length, 0);
|
||
});
|
||
|
||
it("reports its phase through the status registry while running, and clears it when done", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
const existingId = "n_existing";
|
||
ledgers.appendNode({
|
||
id: existingId,
|
||
name: "Derivative",
|
||
statement: "Derivatives measure rates of change",
|
||
aliases: [],
|
||
createdAt: "2026-08-01T00:00:00.000Z",
|
||
provenance: [],
|
||
});
|
||
const seen: (string | undefined)[] = [];
|
||
const phaseOf = () => extractionStatuses().find((r) => r.chatId === chatId)?.phase;
|
||
const verdict: AuditResult = {
|
||
propositions: [{ ...FINDINGS.propositions[0]!, linkTo: existingId }],
|
||
edges: [],
|
||
};
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
// Each stage's first generate is the observation point: the
|
||
// registry must already carry this chat at the right phase.
|
||
extractor: submitModel("submit_findings", FINDINGS, () => seen.push(phaseOf())),
|
||
auditor: submitModel("submit_review", verdict, () => seen.push(phaseOf())),
|
||
});
|
||
await pipeline.runExtraction(chatId);
|
||
assert.deepEqual(seen, ["extracting", "auditing"]);
|
||
assert.equal(extractionStatuses().length, 0, "the registry clears when the run ends");
|
||
});
|
||
|
||
it("serialized audit (owner 2026-09-28): a second run QUEUES at the gate; its auditor explores the graph only AFTER the first run's merge", async () => {
|
||
const a = fixtureChat();
|
||
const b = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
|
||
const single = (id: string, name: string, statement: string): SessionFindings => ({
|
||
propositions: [{ id, name, statement, aliases: [], }],
|
||
edges: [],
|
||
});
|
||
const findingsA = single("pa", "Alpha claim", "Alpha statement, full precision");
|
||
const findingsB = single("pb", "Beta claim", "Beta statement, full precision");
|
||
|
||
let gateOpen!: () => void;
|
||
const gate = new Promise<void>((resolve) => (gateOpen = resolve));
|
||
let aAuditing = false;
|
||
const pipelineA = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", findingsA),
|
||
auditor: gatedSubmitModel("submit_review", findingsA, gate, () => {
|
||
aAuditing = true;
|
||
}),
|
||
});
|
||
const runA = pipelineA.runExtraction(a.chatId);
|
||
await until(() => extractionStatuses().some((r) => r.chatId === a.chatId && r.phase === "auditing"));
|
||
assert.ok(aAuditing, "run A holds the gate — its audit model call is in flight");
|
||
|
||
let bAuditorCalled = false;
|
||
let bSawAlphasMerge = false;
|
||
const pipelineB = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", findingsB),
|
||
// THE pin: when B's auditor is finally invoked, A's merge must
|
||
// already be in the ledgers — B explores the post-merge graph,
|
||
// which is the entire point of the gate.
|
||
auditor: submitModel("submit_review", findingsB, () => {
|
||
bAuditorCalled = true;
|
||
bSawAlphasMerge = ledgers.readNodes().some((n) => n.name === "Alpha claim");
|
||
}),
|
||
});
|
||
const runB = pipelineB.runExtraction(b.chatId);
|
||
|
||
await until(() => extractionStatuses().some((r) => r.chatId === b.chatId && r.phase === "waiting"));
|
||
assert.ok(!bAuditorCalled, "B's auditor has not been invoked — it queues behind A");
|
||
assert.equal(ledgers.readNodes().filter((n) => n.name === "Beta claim").length, 0, "nothing of B merged yet");
|
||
assert.equal(extractionStatuses().find((r) => r.chatId === a.chatId)?.phase, "auditing", "A still audits while B waits");
|
||
|
||
gateOpen();
|
||
assert.deepEqual(await runA, { nodes: 1, edges: 0 });
|
||
assert.deepEqual(await runB, { nodes: 1, edges: 0 });
|
||
assert.ok(bAuditorCalled);
|
||
assert.ok(bSawAlphasMerge, "B's auditor saw A's merged node — audit serialized after merge");
|
||
assert.equal(extractionStatuses().length, 0, "both runs left the registry");
|
||
});
|
||
|
||
it("serialized audit: a run ABORTED while waiting never audits — and the queue chain stays healthy for successors", async () => {
|
||
const a = fixtureChat();
|
||
const b = fixtureChat();
|
||
const c = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
|
||
const single = (id: string, name: string, statement: string): SessionFindings => ({
|
||
propositions: [{ id, name, statement, aliases: [], }],
|
||
edges: [],
|
||
});
|
||
|
||
let gateOpen!: () => void;
|
||
const gate = new Promise<void>((resolve) => (gateOpen = resolve));
|
||
const pipelineA = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", single("pa", "Alpha claim", "Alpha statement")),
|
||
auditor: gatedSubmitModel("submit_review", single("pa", "Alpha claim", "Alpha statement"), gate),
|
||
});
|
||
const runA = pipelineA.runExtraction(a.chatId);
|
||
await until(() => extractionStatuses().some((r) => r.chatId === a.chatId && r.phase === "auditing"));
|
||
|
||
let bAuditorCalled = false;
|
||
const pipelineB = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", single("pb", "Beta claim", "Beta statement")),
|
||
auditor: submitModel("submit_review", single("pb", "Beta claim", "Beta statement"), () => {
|
||
bAuditorCalled = true;
|
||
}),
|
||
});
|
||
const runB = pipelineB.runExtraction(b.chatId);
|
||
await until(() => extractionStatuses().some((r) => r.chatId === b.chatId && r.phase === "waiting"));
|
||
|
||
// The dock's abort button, pressed while B queues.
|
||
assert.equal(abortExtraction(b.chatId), true);
|
||
assert.deepEqual(await runB, { nodes: 0, edges: 0 }, "aborted before auditing — zero emissions");
|
||
assert.ok(!bAuditorCalled, "B's auditor was never invoked");
|
||
assert.ok(!extractionStatuses().some((r) => r.chatId === b.chatId), "B left the registry");
|
||
assert.equal(ledgers.readCoverage().some((row) => row.chatId === b.chatId), false, "B checkpointed nothing");
|
||
|
||
// The chain link B abandoned still resolved: A finishes, and a
|
||
// THIRD run audits normally — no deadlock residue.
|
||
gateOpen();
|
||
assert.deepEqual(await runA, { nodes: 1, edges: 0 });
|
||
const pipelineC = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", single("pc", "Gamma claim", "Gamma statement")),
|
||
auditor: submitModel("submit_review", single("pc", "Gamma claim", "Gamma statement")),
|
||
});
|
||
assert.deepEqual(await pipelineC.runExtraction(c.chatId), { nodes: 1, edges: 0 });
|
||
});
|
||
|
||
it("captures per-stage usage live, persists the run's usage into the chat record", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
const existingId = "n_existing";
|
||
ledgers.appendNode({
|
||
id: existingId,
|
||
name: "Derivative",
|
||
statement: "Derivatives measure rates of change",
|
||
aliases: [],
|
||
createdAt: "2026-08-01T00:00:00.000Z",
|
||
provenance: [],
|
||
});
|
||
const usageSeen: (number | undefined)[] = [];
|
||
const verdict: AuditResult = {
|
||
propositions: [{ ...FINDINGS.propositions[0]!, linkTo: existingId }],
|
||
edges: [],
|
||
};
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
// During the auditor's generate, the registry must already carry
|
||
// the extractor's fully accumulated live usage (2 steps × 10/5).
|
||
extractor: submitModel("submit_findings", FINDINGS),
|
||
auditor: submitModel("submit_review", verdict, () =>
|
||
usageSeen.push(extractionStatuses().find((r) => r.chatId === chatId)?.usage.extractor?.steps.at(-1)?.inputTokens),
|
||
),
|
||
});
|
||
await pipeline.runExtraction(chatId);
|
||
|
||
// Live: mid-audit the extractor's usage was fully accumulated (faux
|
||
// estimates tokens from the prompt/response text — deterministic,
|
||
// positive, no cache).
|
||
assert.equal(usageSeen.length, 1);
|
||
assert.ok(typeof usageSeen[0] === "number" && usageSeen[0]! > 0, "the extractor's step billed input tokens");
|
||
|
||
// Persisted: the run appended ONE usage entry to the chat's
|
||
// extractions log — per-stage model + steps, with merge stats.
|
||
const record = chatStore.getChat(chatId)!;
|
||
assert.equal(record.extractions?.length, 1);
|
||
const run = record.extractions![0]!;
|
||
assert.equal(run.stats?.nodes, 0); // linked, not created
|
||
// the scripted engine's model, provider-qualified (model slots wave)
|
||
assert.equal(run.stages.extractor.model, "faux:faux-1");
|
||
assert.equal(run.stages.extractor.steps.length, 1); // the submit call — the run STOPS after a clean submit
|
||
const step = run.stages.extractor.steps[0]!;
|
||
assert.ok(step.inputTokens! > 0 && step.outputTokens! > 0, "estimated usage captured");
|
||
assert.equal(step.cacheReadTokens, 0);
|
||
assert.equal(step.cacheWriteTokens, 0);
|
||
assert.equal(step.reasoningTokens, 0);
|
||
assert.equal(run.stages.auditor.steps.length, 1);
|
||
assert.ok(!Number.isNaN(Date.parse(run.at)));
|
||
});
|
||
|
||
it("aborts mid-run: cancels the model call, persists partial usage, checkpoints nothing", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: hangingModel(), // hangs until aborted — no step finishes
|
||
auditor: submitModel("submit_review", { propositions: [], edges: [] }),
|
||
});
|
||
const runPromise = pipeline.runExtraction(chatId);
|
||
|
||
// The registry entry exists synchronously after the call (setPhase
|
||
// runs before the first await); abort is TRUE cancellation.
|
||
assert.equal(abortExtraction(chatId), true);
|
||
const stats = await runPromise;
|
||
|
||
// A deliberate stop, not a failure: zero emissions, no throw.
|
||
assert.deepEqual(stats, { nodes: 0, edges: 0 });
|
||
assert.equal(extractionStatuses().length, 0, "the registry clears");
|
||
assert.equal(ledgers.readNodes().length, 0, "nothing merged");
|
||
assert.equal(ledgers.readCheckpoints().length, 0, "nothing checkpointed — the next trigger re-runs");
|
||
|
||
// Partial usage still persisted (money was spent): stats absent,
|
||
// no completed steps in either stage.
|
||
const record = chatStore.getChat(chatId)!;
|
||
assert.equal(record.extractions?.length, 1);
|
||
const run = record.extractions![0]!;
|
||
assert.equal(run.stats, undefined);
|
||
assert.equal(run.stages.extractor.steps.length, 0);
|
||
assert.equal(run.stages.auditor.steps.length, 0);
|
||
|
||
// Aborting a non-running chat is an idempotent no-op.
|
||
assert.equal(abortExtraction(chatId), false);
|
||
});
|
||
|
||
it("is single-flight per chat — a concurrent second run is a no-op", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
|
||
// The extractor's first call hangs until we release it.
|
||
let release!: () => void;
|
||
const gate = new Promise<void>((resolve) => {
|
||
release = resolve;
|
||
});
|
||
let calls = 0;
|
||
const gatedExtractor = fauxEngine([
|
||
async () => {
|
||
calls++;
|
||
if (calls === 1) await gate;
|
||
return fauxAssistantMessage("…");
|
||
},
|
||
]);
|
||
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: gatedExtractor,
|
||
auditor: silentModel(),
|
||
});
|
||
|
||
const first = pipeline.runExtraction(chatId);
|
||
const second = await pipeline.runExtraction(chatId); // in-flight → zeros
|
||
assert.deepEqual(second, { nodes: 0, edges: 0 });
|
||
|
||
release();
|
||
await assert.rejects(first, /the extractor never submitted findings/);
|
||
});
|
||
|
||
it("registers runs on the process-wide registry (route-instance safety): a second pipeline instance sees the same single-flight state", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
|
||
// Gated extractor: the first call hangs until released, so the run
|
||
// stays registered while we observe it.
|
||
let release!: () => void;
|
||
const gate = new Promise<void>((resolve) => {
|
||
release = resolve;
|
||
});
|
||
let calls = 0;
|
||
const gatedExtractor = fauxEngine([
|
||
async () => {
|
||
calls++;
|
||
if (calls === 1) await gate;
|
||
return fauxAssistantMessage("…");
|
||
},
|
||
]);
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: gatedExtractor,
|
||
auditor: silentModel(),
|
||
});
|
||
// A SECOND instance over DIFFERENT ledgers — the observer a separate
|
||
// route entry's module instance is in dev (the turn-liveness lesson:
|
||
// module instances split; globalThis does not).
|
||
const observer = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: memoryLedgers(),
|
||
extractor: silentModel(),
|
||
auditor: silentModel(),
|
||
});
|
||
|
||
const first = pipeline.runExtraction(chatId);
|
||
// The synchronous prefix (setPhase at batch start) registers BEFORE
|
||
// the first await — the run is visible the moment it starts.
|
||
assert.ok(
|
||
extractionStatuses().some((run) => run.chatId === chatId && run.phase === "extracting"),
|
||
"the run is registered at start",
|
||
);
|
||
const g = globalThis as { __lhExtractionRuns?: { running: Map<string, unknown> } };
|
||
assert.ok(g.__lhExtractionRuns?.running.has(chatId), "the registry lives on globalThis — no module-instance split can hide runs");
|
||
assert.deepEqual(await observer.runExtraction(chatId), { nodes: 0, edges: 0 }, "single-flight spans pipeline instances");
|
||
|
||
release();
|
||
await assert.rejects(first, /the extractor never submitted findings/);
|
||
assert.ok(!extractionStatuses().some((run) => run.chatId === chatId), "the registry entry clears when the run ends (however it ends)");
|
||
assert.ok(!g.__lhExtractionRuns?.running.has(chatId), "nothing leaks into the global registry");
|
||
});
|
||
|
||
it("throws for unknown chats", async () => {
|
||
const ledgers = memoryLedgers();
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: silentModel(),
|
||
auditor: silentModel(),
|
||
});
|
||
await assert.rejects(pipeline.runExtraction("chat_does_not_exist"), /Chat not found/);
|
||
});
|
||
});
|
||
|
||
// ── the notes front door (format-agnostic import) ────────────────────────────
|
||
|
||
/** Raw personal notes — arbitrary format, no session, no message ids. */
|
||
const NOTES_TEXT = `> [!quote] YOU
|
||
> teach me vim
|
||
|
||
> [!abstract] PI
|
||
> Vim always starts in Normal mode — keys are commands, not text.`;
|
||
|
||
/** What the notes-mode extractor submits: same shapes as session findings,
|
||
* messages always empty (the file is the provenance). */
|
||
const NOTES_FINDINGS = {
|
||
propositions: [
|
||
{
|
||
id: "p1",
|
||
name: "Vim normal mode",
|
||
statement: "Vim starts in Normal mode, where keys are commands.",
|
||
aliases: [],
|
||
},
|
||
],
|
||
edges: [],
|
||
} as const;
|
||
|
||
const NOTES_VERDICT = {
|
||
propositions: [NOTES_FINDINGS.propositions[0]],
|
||
edges: [],
|
||
} as const;
|
||
|
||
describe("the notes front door (importNotes — format-agnostic)", () => {
|
||
it("imports raw notes end to end: source record, file-scoped provenance", async () => {
|
||
const ledgers = memoryLedgers();
|
||
const seen: { kind?: string; label?: string }[] = [];
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", NOTES_FINDINGS),
|
||
// During the auditor's call the registry must show the notes run.
|
||
auditor: submitModel("submit_review", NOTES_VERDICT, () => {
|
||
const run = extractionStatuses().find((r) => r.chatId.startsWith("src_"));
|
||
seen.push({ kind: run?.kind, label: run?.label });
|
||
}),
|
||
});
|
||
const stats = await pipeline.importNotes({ filePath: "/vault/learn vim.md", text: NOTES_TEXT });
|
||
|
||
assert.deepEqual(stats, { nodes: 1, edges: 0 });
|
||
// The run surfaced as a NOTES run labeled with the file path.
|
||
assert.deepEqual(seen, [{ kind: "notes", label: "/vault/learn vim.md" }]);
|
||
assert.equal(extractionStatuses().length, 0, "the registry clears when the run ends");
|
||
|
||
// The source record: deterministic src id, the file path, the usage log.
|
||
const source = ledgers.readSources()[0]!;
|
||
assert.match(source.id, /^src_/);
|
||
assert.equal(source.filePath, "/vault/learn vim.md");
|
||
assert.ok(Date.parse(source.importedAt));
|
||
assert.equal(source.extractions?.length, 1, "the run's usage persisted into the source record");
|
||
assert.equal(source.extractions![0]!.stats?.nodes, 1);
|
||
assert.ok(source.extractions![0]!.stages.extractor.steps.length > 0, "faux usage captured");
|
||
|
||
// File-scoped provenance (submit-schema slim, 2026-09-28): the
|
||
// node carries ONE chat-level point — the source key itself, no
|
||
// message anchors.
|
||
const node = ledgers.readNodes()[0]!;
|
||
assert.equal(node.statement, "Vim starts in Normal mode, where keys are commands.");
|
||
assert.deepEqual(node.provenance, [{ chatId: source.id, messageId: "" }]);
|
||
assert.deepEqual(ledgers.readMappings(), [{ chatId: source.id, sourceId: "p1", graphNodeId: node.id }]);
|
||
// The checkpoint stamps the import.
|
||
assert.equal(ledgers.readCheckpoints()[0]!.chatId, source.id);
|
||
});
|
||
|
||
it("re-importing the same file is idempotent: same source identity, refs dedupe, usage history grows", async () => {
|
||
const ledgers = memoryLedgers();
|
||
const mk = () =>
|
||
createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", NOTES_FINDINGS),
|
||
auditor: submitModel("submit_review", NOTES_VERDICT),
|
||
});
|
||
const first = await mk().importNotes({ filePath: "/vault/learn vim.md", text: NOTES_TEXT });
|
||
assert.deepEqual(first, { nodes: 1, edges: 0 });
|
||
|
||
const second = await mk().importNotes({ filePath: "/vault/learn vim.md", text: NOTES_TEXT });
|
||
assert.deepEqual(second, { nodes: 0, edges: 0 }, "the same source id dedupes everything");
|
||
|
||
assert.equal(ledgers.readSources().length, 1, "one source identity — the path hashes to the same id");
|
||
assert.equal(ledgers.readSources()[0]!.extractions?.length, 2, "both runs billed their usage");
|
||
assert.equal(ledgers.readNodes().length, 1, "no duplicate node");
|
||
});
|
||
|
||
it("aborts like a chat run: true cancellation, nothing merged, partial usage in the source record", async () => {
|
||
const ledgers = memoryLedgers();
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: hangingModel(),
|
||
auditor: submitModel("submit_review", NOTES_VERDICT),
|
||
});
|
||
const runPromise = pipeline.importNotes({ filePath: "/vault/learn vim.md", text: NOTES_TEXT });
|
||
|
||
const srcId = extractionStatuses().find((r) => r.chatId.startsWith("src_"))!.chatId;
|
||
assert.equal(abortExtraction(srcId), true);
|
||
assert.deepEqual(await runPromise, { nodes: 0, edges: 0 });
|
||
assert.equal(ledgers.readNodes().length, 0, "nothing merged");
|
||
assert.equal(ledgers.readCheckpoints().length, 0, "nothing checkpointed");
|
||
assert.equal(ledgers.readSources()[0]!.extractions?.length, 1, "partial usage still persisted");
|
||
assert.equal(ledgers.readSources()[0]!.extractions![0]!.stats, undefined, "never merged → no stats");
|
||
});
|
||
});
|
||
|
||
// ── the chunked pipeline (extraction coverage — vision-extraction-coverage.md) ──
|
||
|
||
/** Pull the pipeline's prompt view out of a model call: the pipeline sends
|
||
* the session's markdown document itself as the user turn, so the LAST
|
||
* user message's text IS what the extractor saw. */
|
||
function capturedView(context: unknown): string {
|
||
const messages = (context as { messages?: { role: string; content: string }[] }).messages ?? [];
|
||
const last = [...messages].reverse().find((m) => m.role === "user");
|
||
return typeof last?.content === "string" ? last.content : "";
|
||
}
|
||
|
||
/** An extractor step that submits FINDINGS, optionally capturing its view. */
|
||
function findingsStep(capture?: (view: string) => void): FauxResponseStep {
|
||
return (context) => {
|
||
capture?.(capturedView(context));
|
||
return fauxAssistantMessage(
|
||
[fauxToolCall("submit_findings", FINDINGS as unknown as ToolCall["arguments"], { id: "findings-call" })],
|
||
{ stopReason: "toolUse" },
|
||
);
|
||
};
|
||
}
|
||
|
||
/** An auditor step that passes p1 through (no linkTo — a fresh node), drops p2. */
|
||
function passThroughAuditStep(): FauxResponseStep {
|
||
return () =>
|
||
fauxAssistantMessage(
|
||
[
|
||
fauxToolCall(
|
||
"submit_review",
|
||
{
|
||
propositions: [{ ...FINDINGS.propositions[0]! }],
|
||
edges: [],
|
||
} as unknown as ToolCall["arguments"],
|
||
{ id: "review-call" },
|
||
),
|
||
],
|
||
{ stopReason: "toolUse" },
|
||
);
|
||
}
|
||
|
||
/** A session with UNCOVERED-multiple-batch mass: five long distinct messages
|
||
* (~1200 tok each — 3600+1200 > the factory chunk budget 4096 → batches of
|
||
* [m1,m2,m3] and [m4,m5]). */
|
||
function chunkyChat() {
|
||
const chat = chatStore.createChat("Chunky coverage fixture");
|
||
createdChats.push(chat.id);
|
||
// ~1230 tok per message (chars/4): three fill the 4096 budget, the
|
||
// fourth would overflow — deterministic batches [m1,m2,m3] + [m4,m5].
|
||
chatStore.saveMessages(
|
||
chat.id,
|
||
[1, 2, 3, 4, 5].map((n) => user(`u${n}`, `topic ${n}: ${"detail ".repeat(700)}${n}`)),
|
||
);
|
||
return { chatId: chat.id, record: chatStore.getChat(chat.id)! };
|
||
}
|
||
|
||
describe("the chunked pipeline (extraction coverage)", () => {
|
||
it("extracts uncovered messages in token-budgeted batches, checkpoints coverage per batch, and no-ops once covered", async () => {
|
||
const { chatId, record } = chunkyChat();
|
||
const ledgers = memoryLedgers();
|
||
const views: string[] = [];
|
||
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: fauxEngine([findingsStep((v) => views.push(v)), findingsStep((v) => views.push(v))]),
|
||
auditor: fauxEngine([passThroughAuditStep(), passThroughAuditStep()]),
|
||
});
|
||
const stats = await pipeline.runExtraction(chatId);
|
||
|
||
// Two batches: the first held messages 1-3, the second 4-5 — a
|
||
// message is never split, batches are consecutive oldest-first.
|
||
assert.equal(views.length, 2, "one extractor call per batch");
|
||
assert.ok(views[0]!.includes("### Learner") && views[0]!.includes("topic 1:"));
|
||
assert.ok(!views[0]!.includes("topic 4:"), "the batch stops at the token budget");
|
||
assert.ok(views[1]!.includes("### Learner") && views[1]!.includes("topic 4:"));
|
||
assert.ok(!views[1]!.includes("topic 3:"));
|
||
// The document header is the session title.
|
||
assert.ok(views[0]!.startsWith("# Chunky coverage fixture"));
|
||
|
||
// p1 was a fresh node in batch 1; batch 2's p1 mapped to the same
|
||
// node (chat-scoped mapping).
|
||
assert.deepEqual(stats, { nodes: 1, edges: 0 });
|
||
|
||
// Per-batch coverage: every message checkpointed, nothing legacy.
|
||
const coverage = ledgers.readCoverage();
|
||
assert.equal(coverage.length, record.messages.length);
|
||
assert.equal(ledgers.readCheckpoints().length, 0);
|
||
assert.equal(coverageOf(record.messages, coverage, chatId).uncoveredCount, 0);
|
||
|
||
// A second run is a NO-OP: nothing uncovered → no model calls, no
|
||
// new usage entry (no money spent on covered ground).
|
||
const before = views.length;
|
||
const again = await pipeline.runExtraction(chatId);
|
||
assert.deepEqual(again, { nodes: 0, edges: 0 });
|
||
assert.equal(views.length, before);
|
||
assert.equal(chatStore.getChat(chatId)!.extractions?.length, 1, "the no-op run persists no usage");
|
||
});
|
||
|
||
it("aborting after a merged batch keeps it covered; the re-run extracts only the remainder", async () => {
|
||
const { chatId, record } = chunkyChat();
|
||
const ledgers = memoryLedgers();
|
||
const views: string[] = [];
|
||
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
// Batch 1 submits and merges; batch 2's extractor call HANGS
|
||
// until the abort fires — the dock's abort button, mid-run.
|
||
extractor: fauxEngine([
|
||
findingsStep((v) => views.push(v)),
|
||
(_context, options) =>
|
||
new Promise((resolve) => {
|
||
const sig = options?.signal;
|
||
if (sig?.aborted) {
|
||
resolve(fauxAssistantMessage("late"));
|
||
return;
|
||
}
|
||
sig?.addEventListener("abort", () => resolve(fauxAssistantMessage("late")), { once: true });
|
||
}),
|
||
]),
|
||
auditor: fauxEngine([passThroughAuditStep()]),
|
||
});
|
||
const runPromise = pipeline.runExtraction(chatId);
|
||
// The abort must land while batch 2's extractor hangs. The faux
|
||
// stream only resolves on abort, so wait for the batch-1 merge to
|
||
// show in coverage, then abort.
|
||
await new Promise<void>((resolve) => {
|
||
const check = setInterval(() => {
|
||
if (ledgers.readCoverage().length > 0) {
|
||
clearInterval(check);
|
||
resolve();
|
||
}
|
||
}, 5);
|
||
});
|
||
assert.equal(abortExtraction(chatId), true);
|
||
const stats = await runPromise;
|
||
|
||
// Batch 1's emissions are kept and its messages stay covered.
|
||
assert.deepEqual(stats, { nodes: 1, edges: 0 });
|
||
assert.equal(ledgers.readCoverage().length, 3, "batch 1 checkpointed its three messages");
|
||
const cov = coverageOf(record.messages, ledgers.readCoverage(), chatId);
|
||
assert.equal(cov.uncoveredCount, 2, "the in-flight batch's messages stay uncovered");
|
||
|
||
// The re-run — the manual extract button — picks up ONLY the
|
||
// remainder: one batch, messages 4-5 alone in the prompt.
|
||
const reRunViews: string[] = [];
|
||
const finisher = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: fauxEngine([findingsStep((v) => reRunViews.push(v))]),
|
||
auditor: fauxEngine([passThroughAuditStep()]),
|
||
});
|
||
await finisher.runExtraction(chatId);
|
||
assert.equal(reRunViews.length, 1);
|
||
assert.ok(reRunViews[0]!.includes("### Learner") && reRunViews[0]!.includes("topic 4:"));
|
||
assert.ok(!reRunViews[0]!.includes("### Learner · u1"), "the covered remainder never re-enters the prompt");
|
||
assert.equal(ledgers.readCoverage().length, 5, "the re-run closed the gap");
|
||
});
|
||
|
||
it("a re-opened message re-extracts alone; a data-part attach never re-opens it", async () => {
|
||
// A small session: one batch covers everything, so re-openings are
|
||
// the ONLY thing later runs can see.
|
||
const chat = chatStore.createChat("Re-open fixture");
|
||
createdChats.push(chat.id);
|
||
chatStore.saveMessages(chat.id, [user("s1", "short topic one"), user("s2", "short topic two")]);
|
||
const chatId = chat.id;
|
||
const ledgers = memoryLedgers();
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: fauxEngine([findingsStep()]),
|
||
auditor: fauxEngine([passThroughAuditStep()]),
|
||
});
|
||
await pipeline.runExtraction(chatId);
|
||
// Wave D: the record IS native history — coverage reads it directly.
|
||
const record = () => chatStore.getChat(chatId)!.messages;
|
||
const messages = () => record();
|
||
assert.equal(coverageOf(messages(), ledgers.readCoverage(), chatId).uncoveredCount, 0);
|
||
|
||
// Data parts are invisible to the extraction view — a plan-block
|
||
// marker append (whose data part splices into the projected view)
|
||
// does NOT re-open a covered message.
|
||
chatStore.saveMessages(chatId, [
|
||
...record(),
|
||
newPlanBlockMessage("call_s2", { kind: "full", at: "2026-09-26T00:00:00.000Z", current: null, nodes: [], edges: [] }),
|
||
]);
|
||
const afterAttach = coverageOf(messages(), ledgers.readCoverage(), chatId);
|
||
assert.equal(afterAttach.uncoveredCount, 0, "data parts don't change the fingerprint");
|
||
|
||
// A quiz answer merging into an ASKING message changes its view →
|
||
// exactly that message re-opens, and the next run extracts it alone.
|
||
// (Native: the answer arrives as the call's tool result — the
|
||
// projected group gains the answer line.)
|
||
const mutated = record().map((m) =>
|
||
(m as { id?: string }).id === "s1"
|
||
? ({ ...m, content: [...(m as { content: unknown[] }).content, { type: "text", text: "the answer merged in late" }] } as never)
|
||
: m,
|
||
);
|
||
chatStore.saveMessages(chatId, mutated);
|
||
const afterMerge = coverageOf(messages(), ledgers.readCoverage(), chatId);
|
||
assert.equal(afterMerge.uncoveredCount, 1, "only the mutated message re-opens");
|
||
|
||
const reRunViews: string[] = [];
|
||
const reOpener = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: fauxEngine([findingsStep((v) => reRunViews.push(v))]),
|
||
auditor: fauxEngine([passThroughAuditStep()]),
|
||
});
|
||
await reOpener.runExtraction(chatId);
|
||
assert.equal(reRunViews.length, 1, "one batch: the single re-opened message");
|
||
assert.ok(reRunViews[0]!.includes("### Learner · s1") && !reRunViews[0]!.includes("### Learner · s2"));
|
||
assert.equal(coverageOf(messages(), ledgers.readCoverage(), chatId).uncoveredCount, 0, "re-covered");
|
||
});
|
||
});
|
||
|
||
// ─── session deletion mid-run (wave 6) ─────────────────────────────────────
|
||
|
||
describe("the session-deletion guard (chat deleted mid-run)", () => {
|
||
it("a run whose chat dies mid-extraction aborts at the merge with nothing merged, checkpointed, or billed", async () => {
|
||
const { chatId } = fixtureChat();
|
||
const ledgers = memoryLedgers();
|
||
|
||
// The chat record is deleted DURING the audit model call — the worst
|
||
// window: findings already spent, the merge next.
|
||
const pipeline = createExtractionPipeline({
|
||
chatStore,
|
||
graphStore: ledgers,
|
||
extractor: submitModel("submit_findings", FINDINGS),
|
||
auditor: submitModel("submit_review", { propositions: FINDINGS.propositions, edges: [] }, () => chatStore.deleteChat(chatId)),
|
||
});
|
||
const stats = await pipeline.runExtraction(chatId);
|
||
|
||
// The abort rides the existing abort path: info, not error; zero
|
||
// emissions (stats present but empty — nothing merged).
|
||
assert.ok(stats);
|
||
assert.equal(stats.nodes, 0);
|
||
assert.equal(stats.edges, 0);
|
||
|
||
// Nothing merged, nothing checkpointed — the deleted chat leaves no
|
||
// trace for a later snapshot to resurrect.
|
||
assert.equal(ledgers.readNodes().length, 0);
|
||
assert.equal(ledgers.readEdges().length, 0);
|
||
assert.equal(ledgers.readMappings().length, 0);
|
||
assert.equal(ledgers.readCoverage().length, 0);
|
||
assert.equal(ledgers.readCheckpoints().length, 0);
|
||
|
||
// The run is off the registry (the finally always cleans up).
|
||
assert.equal(extractionStatuses().some((run) => run.chatId === chatId), false);
|
||
// And its partial spend died with the chat — no usage row on a ghost.
|
||
assert.equal(chatStore.getChat(chatId), null);
|
||
});
|
||
});
|