Files
learnharness/tests/graph-context-job.test.ts
T
amosblomqvist 0a4a9a11de BYOK provider embeddings (wave 6 chunk B): kill local transformers
Replace the @huggingface/transformers local embedder (~316MB ONNX cache)
with an EmbeddingPort seam: graph.embeddingModel (nullable "provider:id"
slug) selects an OpenRouter/OpenAI/Gemini adapter, resolved fresh per
call from settings + the auth store so key rotations land immediately.

- src/server/embeddings.ts rewritten: slug grammar, injected-fetch
  adapters (OpenRouter input_type, Gemini taskType batching, OpenAI
  index-ordered rows), honest resolution (null = skip-with-info, set
  model with missing key = honest error), embedNewNodes with model-change
  re-embed wipe + ghost pruning + usage steps, federated catalog
  (OpenRouter /api/v1/embeddings/models — VERIFIED live, the inverse
  path 404s; OpenAI text-embedding- filter; Gemini embedContent filter).
- GET /api/models/embeddings: federated catalog, empty when no keys.
- Extraction tail records stages.embedding usage into the run's money
  channel; EMBEDDING_PRICES overlay in core/prices.ts (outside the
  sync-generated block), callCost falls back to it; cost-summary folds
  the fourth stage; graph-context injection resolves its embedder per
  run, fails honestly when unconfigured, records query tokens.
- Settings: GraphSettings.embeddingModel (null factory), section parser
  validates slug shape (id may contain colons — OpenRouter :free
  suffixes, live catalog fact).
- Removal: @huggingface/transformers uninstalled, PATHS.modelCache and
  onnx tracing entries deleted, @huggingface tracing-excludes guard
  added, stale sharp/libvips comments updated to historical.

Live-verified on port 3004: catalog federates 36 rows (33 OpenRouter +
3 OpenAI), embedNewNodes embedded 10 nodes via the free liquid/lfm-2.5
model (dim 1024, 435 prompt tokens, 1 call, $0), settings PUT rejects
bad slugs with 400.

Gates: typecheck, lint, 895/895 tests, build.
2026-09-23 03:53:57 +03:00

318 lines
13 KiB
TypeScript

/**
* Graph context injection — the runner + the wake integration
* (docs/vision-context-injection.md). The trigger gates, the failure
* modes, the one happy delivery (real wake pipeline, fake turn runner,
* scripted embedder), and the SILENT abort (the decided contrast with
* teacher-dispatched sub-agents, which abort with a steer).
*
* Cleanup follows tests/jobs.test.ts: files removed in finally/after.
*/
import assert from "node:assert/strict";
import * as fs from "node:fs";
import * as path from "node:path";
import { after, describe, it } from "node:test";
import { deliverJobResult, setTurnRunner } from "../src/server/jobs.ts";
import { abortJob } from "../src/server/jobs.ts";
import { persistTurn } from "../src/server/turn-service.ts";
import { startGraphContextInjection, runGraphContextJob, type GraphContextDeps, type GraphContextEmbedder } from "../src/agent/subagents/graph-context.ts";
import { chatStore } from "../src/store/chats.ts";
import { jobStore } from "../src/store/jobs.ts";
import { PATHS } from "../config.ts";
import type { EmbeddingsLedger, GraphNode, LedgerEvent } from "../src/core/contracts/graph.ts";
import type { JobRecord, SteerMessage } from "../src/core/contracts.ts";
const createdChats: string[] = [];
const createdJobs: string[] = [];
function trackChat(id: string) {
createdChats.push(id);
}
function trackJob(id: string) {
createdJobs.push(id);
}
after(() => {
for (const id of createdChats) {
try {
fs.unlinkSync(path.join(PATHS.chats, `${id}.json`));
} catch {
/* already gone */
}
}
for (const id of createdJobs) {
try {
fs.unlinkSync(path.join(PATHS.data, "jobs", `${id}.json`));
} catch {
/* already gone */
}
}
});
function waitFor(cond: () => boolean, timeoutMs = 8000, what = "condition"): Promise<void> {
return new Promise((resolve, reject) => {
const started = Date.now();
const tick = () => {
if (cond()) return resolve();
if (Date.now() - started > timeoutMs) return reject(new Error(`timeout waiting for ${what}`));
setTimeout(tick, 25);
};
tick();
});
}
function unit(i: number): number[] {
const v = new Array(8).fill(0);
v[i] = 1;
return v;
}
function node(id: string, statement: string): GraphNode {
return { id, name: id, statement, aliases: [], provenance: [], createdAt: "2026-09-14T00:00:00.000Z" };
}
/** A minimal in-memory graph store — the runner only reads. */
function fakeGraphStore(opts: {
vectors?: Record<string, number[]>;
nodes?: GraphNode[];
events?: LedgerEvent[];
model?: string;
dim?: number;
}): Pick<GraphContextDeps["graphStore"], "readNodes" | "readEvents" | "readEmbeddings"> {
const ledger: EmbeddingsLedger = {
model: opts.model ?? "test-embed",
dim: opts.dim ?? 8,
vectors: opts.vectors ?? {},
clusters: [],
updatedAt: "2026-09-14T00:00:00.000Z",
};
return {
readNodes: () => opts.nodes ?? [],
readEvents: () => opts.events ?? [],
readEmbeddings: () => ledger,
};
}
/** A chat at session start: exactly one typed message (the topic). */
function newTopicChat(label: string, settings?: Record<string, unknown>): { id: string } {
const chat = chatStore.createChat(`Test: ${label}`);
trackChat(chat.id);
chatStore.saveMessages(chat.id, [
{ id: "u1", role: "user", parts: [{ type: "text", text: "the water cycle" }] },
] as never);
if (settings) chatStore.saveSettings(chat.id, settings as never);
return { id: chat.id };
}
/** The scripted embedder: deterministic query vectors, recorded topics.
* Wave 6 shape: the query carries its (absent) prompt-token count; the
* resolver seam wraps the static fake (fresh resolution per run). */
function fakeEmbedder(vec: number[] = unit(0)) {
const topics: string[] = [];
return {
topics,
embedder: {
model: "test-embed",
embedQuery: async (text: string) => {
topics.push(text);
return { vector: vec, promptTokens: undefined };
},
},
};
}
function deps(
graph: Pick<GraphContextDeps["graphStore"], "readNodes" | "readEvents" | "readEmbeddings">,
embedder: GraphContextEmbedder,
deliver: (steer: SteerMessage) => Promise<void>,
): GraphContextDeps {
return { chatStore, jobStore, graphStore: graph, embedder: () => embedder, deliver };
}
describe("startGraphContextInjection — the one-shot gates", () => {
it("starts at session start: job kind graph-context, deterministic toolCallId, runner runs to delivery", async () => {
const { id: chatId } = newTopicChat("injection happy gate");
const graph = fakeGraphStore({
vectors: { n1: unit(0) },
nodes: [node("n1", "Water evaporates from oceans.")],
});
const { embedder, topics } = fakeEmbedder();
const delivered: SteerMessage[] = [];
const d = deps(graph, embedder, async (steer) => {
delivered.push(steer);
});
const job = startGraphContextInjection(d, chatId);
assert.ok(job, "a chat at session start with budget on starts the injection");
trackJob(job.id);
assert.equal(job.kind, "graph-context");
assert.equal(job.toolCallId, `ctx_${chatId}`);
await waitFor(() => delivered.length > 0, 8000, "delivery");
assert.deepEqual(topics, ["the water cycle"], "the topic is the session's only typed message");
const steer = delivered[0]!;
assert.equal(steer.id, `steer_ctx_${chatId}`);
assert.equal(steer.parts.length, 1);
assert.equal(steer.parts[0]!.type, "data-graph-context");
// One shot: a second trigger does nothing (job exists).
assert.equal(startGraphContextInjection(d, chatId), null);
});
it("budget 0 (off) never starts; a session past its start never injects", async () => {
const { id: off } = newTopicChat("injection off", { graphContextTokens: 0 });
const { id: rolling } = (() => {
const chat = chatStore.createChat("Test: two typed messages");
trackChat(chat.id);
chatStore.saveMessages(chat.id, [
{ id: "u1", role: "user", parts: [{ type: "text", text: "topic" }] },
{ id: "u2", role: "user", parts: [{ type: "text", text: "a second message" }] },
] as never);
return { id: chat.id };
})();
const graph = fakeGraphStore({ vectors: { n1: unit(0) }, nodes: [node("n1", "S.")] });
const d = deps(graph, fakeEmbedder().embedder, async () => {});
assert.equal(startGraphContextInjection(d, off), null, "0 budget = off");
assert.equal(startGraphContextInjection(d, rolling), null, "no retroactive injection");
assert.equal(jobStore.listJobs(off).length, 0);
assert.equal(jobStore.listJobs(rolling).length, 0);
assert.equal(startGraphContextInjection(d, "chat_missing"), null, "unknown chat");
});
it("an ERRORED context job still blocks re-injection (one shot means one shot)", async () => {
const { id: chatId } = newTopicChat("injection error one-shot");
const graph = fakeGraphStore({ vectors: {} }); // empty ledger → the run errors
const d = deps(graph, fakeEmbedder().embedder, async () => {});
const job = startGraphContextInjection(d, chatId);
assert.ok(job);
trackJob(job.id);
await waitFor(() => jobStore.getJob(job.id)!.status === "error", 8000, "job errors");
assert.match(jobStore.getJob(job.id)!.error ?? "", /no embeddings yet/);
// Re-trigger with a now-populated ledger: still nothing.
const populated = deps(
fakeGraphStore({ vectors: { n1: unit(0) }, nodes: [node("n1", "S.")] }),
fakeEmbedder().embedder,
async () => {},
);
assert.equal(startGraphContextInjection(populated, chatId), null);
});
});
describe("runGraphContextJob — failure modes are honest errors, never phantom deliveries", () => {
it("a stale ledger (model/dim mismatch) errors with the parity reason", async () => {
const { id: chatId } = newTopicChat("injection stale ledger");
const chat = chatStore.createChat(`Test: ${chatId}`); // placeholder to satisfy lint-free compile
trackChat(chat.id);
const job = jobStore.createJob({ kind: "graph-context", chatId, toolCallId: `ctx_${chatId}` });
trackJob(job.id);
// Ledger stamped with a DIFFERENT model than the embedder (wave 6:
// staleness is the model identity — dim is checked against the
// served vector below).
const d = deps(fakeGraphStore({ vectors: { n1: unit(0) }, model: "other-model" }), fakeEmbedder().embedder, async () => {});
await runGraphContextJob(d, job.id);
const got = jobStore.getJob(job.id)!;
assert.equal(got.status, "error");
assert.match(got.error ?? "", /stale/);
});
it("nothing fitting the budget errors rather than delivering an empty block", async () => {
// Budget below the framing overhead: nothing can fit, ever.
const { id: chatId } = newTopicChat("injection empty selection", { graphContextTokens: 10 });
const job = jobStore.createJob({ kind: "graph-context", chatId, toolCallId: `ctx_${chatId}` });
trackJob(job.id);
// Query orthogonal to every vector; budget can hold nothing.
const graph = fakeGraphStore({ vectors: { n1: unit(7) }, nodes: [node("n1", "A very long statement indeed.")] });
const d = deps(graph, fakeEmbedder(unit(0)).embedder, async () => {});
await runGraphContextJob(d, job.id);
const got = jobStore.getJob(job.id)!;
assert.equal(got.status, "error");
assert.match(got.error ?? "", /nothing relevant fit the budget/);
});
});
describe("the injection + the wake pipeline (end to end, fake turn runner)", () => {
it("delivers through the wake: the record gains the marker steer, the job flips done, the dock kind rides along", async () => {
const { id: chatId } = newTopicChat("injection wake delivery");
const graph = fakeGraphStore({
vectors: { n1: unit(0), n2: unit(0) },
nodes: [node("n1", "Water evaporates from oceans."), node("n2", "Condensation forms clouds.")],
events: [
{ nodeId: "n1", kind: "observation", chatId: "chat_old", at: "2026-09-10T00:00:00Z", note: "solid" },
],
});
const fired: { chatId: string; last: SteerMessage }[] = [];
setTurnRunner(async (cid, messages) => {
// Mimic the real wake turn: write-ahead persistence of the incoming
// messages (the handler does this), then 200.
await persistTurn(chatStore, cid, messages as never, false);
fired.push({ chatId: cid, last: messages[messages.length - 1] as SteerMessage });
return 200;
});
const d = deps(graph, fakeEmbedder().embedder, deliverJobResult);
const job = startGraphContextInjection(d, chatId);
assert.ok(job);
trackJob(job.id);
await waitFor(() => (jobStore.getJob(job.id)?.status ?? "running") === "done", 8000, "wake flipped the job");
const got = jobStore.getJob(job.id)!;
assert.equal(got.status, "done");
assert.equal(got.activity, "delivered");
// The transcript carries the marker steer (audit trail + dedup key).
const record = chatStore.getChat(chatId)!;
const steerMsg = record.messages.find((m) => m.id === `steer_ctx_${chatId}`);
assert.ok(steerMsg, "the steer persisted to the record");
const part = steerMsg.parts[0] as { type: string; data: { propositions?: unknown[] } };
assert.equal(part.type, "data-graph-context");
assert.ok(part.data.propositions!.length >= 1);
// The server-side turn fired once, with the steer as its last input.
assert.equal(fired.length, 1);
assert.equal(fired[0]!.chatId, chatId);
assert.equal(fired[0]!.last.id, `steer_ctx_${chatId}`);
});
it("aborts SILENTLY: the record flips, the teacher is never told (nothing was promised)", async () => {
const { id: chatId } = newTopicChat("injection abort");
// A hanging embedder — killed mid-call, like the research abort test.
let release: (() => void) | null = null;
const hanging = new Promise<void>((resolve) => {
release = resolve;
});
const embedder = {
model: "test-embed",
embedQuery: () => hanging.then(() => ({ vector: unit(0), promptTokens: undefined })),
};
const fired: number[] = [];
setTurnRunner(async () => {
fired.push(1);
return 200;
});
const graph = fakeGraphStore({ vectors: { n1: unit(0) }, nodes: [node("n1", "S.")] });
const d = deps(graph, embedder, deliverJobResult);
const job = startGraphContextInjection(d, chatId);
assert.ok(job);
trackJob(job.id);
await waitFor(() => jobStore.getJob(job.id)!.activity === "embedding topic", 8000, "run started");
const outcome = abortJob(job.id);
assert.ok(outcome.ok);
const got = jobStore.getJob(job.id)!;
assert.equal(got.status, "error");
assert.equal(got.error, "Aborted by learner");
release!(); // unwind the hanging call; the abort check exits silently
await waitFor(() => fired.length >= 0, 50, "settle");
await new Promise((r) => setTimeout(r, 150));
assert.equal(fired.length, 0, "NO abort steer — the decided contrast with sub-agent jobs");
assert.equal(jobStore.getJob(job.id)!.status, "error", "terminal");
// And the chat record never gained a context steer.
const record = chatStore.getChat(chatId)!;
assert.equal(
record.messages.some((m) => m.id === `steer_ctx_${chatId}`),
false,
);
});
});