Files
OmniRoute/tests/unit/chatcore-client-usage-buffer.test.ts
NOXX - Commiter 7a68a7961c fix(notion-web): production-ready labels, multi-workspace, inference, usage (FINAL) (#7768)
* fix(notion-web): use real picker labels as primary model ids

Catalog /v1/models now surfaces web-picker names (fable-5, gpt-5.6-sol)
instead of Notion food codenames (acai-budino-high, orange-mousse).
Food codenames stay internal via notionCodename + resolveNotionCodename
for runInferenceTranscript. Legacy codename requests still work; responses
echo the client-facing id.

Also points discovery/inference at app.notion.com (same host as the AI picker).

Follow-up to #7696.

* fix(notion-web): explain plan-locked models like Fable 5

Notion returns Fable 5 (acai-budino-high) with isDisabled=true and
disabledReason=business_or_enterprise_plan_required. Keep it out of the
enabled catalog (requests would fail) but surface a discovery warning so
operators know why it is missing. Also warn when space_id is resolved via
getSpaces instead of the cookie.

* feat(notion-web): auto-detect workspace without pasting space_id

Operators only need the raw token_v2 value. When space_id is omitted:
- getSpaces loads all workspaces (browser-like headers + user id)
- each workspace is probed via getAvailableModels
- the richest AI catalog wins

Also softens auth hints so they no longer demand a cookie blob with =.

* fix(notion-web): pick Business workspace so Fable 5 is listed

Probe ALL workspaces instead of early-exiting on the first catalog with
>=8 models. Prefer spaces where Fable is enabled over personal spaces
where Notion returns isDisabled=business_or_enterprise_plan_required.
Cache the chosen spaceId for inference when cookie has no space_id.

* fix(notion-web): working inference + honest token estimates

- runInferenceTranscript: createThread+threadId, config/context/user
  transcript, space/user headers (fixes ValidationError 400)
- Parse modern NDJSON patch/record-map; strip lang tags
- Estimate usage from text (Notion has no metering); mark estimated
- Treat all-zero usage as missing; skip USAGE_TOKEN_BUFFER on estimated
- Keep estimated flag through response sanitizer (was stripped -> flat 2000)

Verified live: fable-5/gpt-5.6-sol chat 200; usage 7 / 65 not constant 2000.

* refactor(notion-web): extract helpers to keep discoverNotionWebModels/execute under the complexity cap

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
Co-authored-by: artickc <artickc@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
2026-07-19 16:21:18 -03:00

91 lines
3.8 KiB
TypeScript

// Characterization of applyClientUsageBuffer — the non-streaming usage buffer/estimate block
// extracted from handleChatCore (chatCore god-file decomposition, #3501). Deps are injected so the
// buffer-vs-estimate branch and the in-place mutation of translatedResponse.usage are observable.
// Locks: usage present → buffer+filter; usage absent → estimate from content length; empty content
// (length 2 from JSON.stringify("")) still estimates; the mutation target is translatedResponse.
import { test } from "node:test";
import assert from "node:assert/strict";
const { applyClientUsageBuffer } = await import(
"../../open-sse/handlers/chatCore/clientUsageBuffer.ts"
);
function makeDeps(overrides: Record<string, unknown> = {}) {
const calls = { buffer: [] as unknown[], estimate: [] as unknown[], filter: [] as unknown[] };
const deps = {
addBufferToUsage: (u: unknown) => {
calls.buffer.push(u);
return { ...(u as object), _buffered: true };
},
estimateUsage: (...a: unknown[]) => {
calls.estimate.push(a);
return { _estimated: true };
},
filterUsageForFormat: (u: unknown, _fmt: unknown) => {
calls.filter.push(u);
return { ...(u as object), _filtered: true };
},
...overrides,
} as Parameters<typeof applyClientUsageBuffer>[3];
return { deps, calls };
}
test("usage present → buffer then filter, mutates in place", () => {
const { deps, calls } = makeDeps();
const resp: Record<string, unknown> = { usage: { prompt_tokens: 5 } };
applyClientUsageBuffer(resp, { messages: [] }, "openai", deps);
assert.equal(calls.buffer.length, 1);
assert.equal(calls.estimate.length, 0);
assert.equal((resp.usage as Record<string, unknown>)._buffered, true);
assert.equal((resp.usage as Record<string, unknown>)._filtered, true);
});
test("all-zero usage stub → estimate (not constant buffer-only 2000)", () => {
const { deps, calls } = makeDeps();
const resp: Record<string, unknown> = {
usage: { prompt_tokens: 0, completion_tokens: 0, total_tokens: 0 },
choices: [{ message: { content: "PONG" } }],
};
applyClientUsageBuffer(resp, { messages: [{ role: "user", content: "hi" }] }, "openai", deps);
assert.equal(calls.buffer.length, 0, "must not buffer zeros into USAGE_TOKEN_BUFFER");
assert.equal(calls.estimate.length, 1);
assert.equal((resp.usage as Record<string, unknown>)._estimated, true);
});
test("no usage but content present → estimate then filter", () => {
const { deps, calls } = makeDeps();
const resp: Record<string, unknown> = {
choices: [{ message: { content: "hello world" } }],
};
applyClientUsageBuffer(resp, { messages: [] }, "openai", deps);
assert.equal(calls.buffer.length, 0);
assert.equal(calls.estimate.length, 1);
assert.equal((resp.usage as Record<string, unknown>)._estimated, true);
assert.equal((resp.usage as Record<string, unknown>)._filtered, true);
// estimateUsage receives (body, contentLength, format)
const args = calls.estimate[0] as unknown[];
assert.equal(args[2], "openai");
assert.equal(typeof args[1], "number");
});
test("empty content → JSON.stringify('') length 2 > 0 still estimates", () => {
const { deps, calls } = makeDeps();
const resp: Record<string, unknown> = {};
applyClientUsageBuffer(resp, {}, "claude", deps);
// content "" → JSON.stringify("") = '""' length 2 → contentLength 2 > 0
assert.equal(calls.estimate.length, 1);
const args = calls.estimate[0] as unknown[];
assert.equal(args[1], 2);
});
test("content length is computed from choices[0].message.content", () => {
const { deps, calls } = makeDeps();
const resp: Record<string, unknown> = {
choices: [{ message: { content: "abc" } }],
};
applyClientUsageBuffer(resp, {}, "openai", deps);
// JSON.stringify("abc") = '"abc"' → length 5
const args = calls.estimate[0] as unknown[];
assert.equal(args[1], 5);
});