Files
OmniRoute/tests/unit/playground-model-qualify.test.ts
Will Gordon 4795825513 fix(sse): make Claude effort/no-think catalog variants dispatchable on every provider (#9006)
* fix(executors): route Claude-via-Vertex through native rawPredict with real streaming

Claude models on Vertex AI were being sent through the generic OpenAI-
compatible partner endpoint, which 404s/errors for Claude on at least
some projects. Route them through Vertex's native Anthropic Messages
API (publishers/anthropic/.../rawPredict) instead, stripping the
body-level model field rawPredict rejects and injecting the required
anthropic_version field.

rawPredict only ever returns a complete JSON body, never real SSE
framing, so streaming requests now get a genuine Anthropic-format SSE
stream synthesized from that JSON (message_start/content_block_*/
message_delta/message_stop), which the existing claude-to-openai
response translator already knows how to parse.

Also fixes two response-format resolution bugs that silently dropped
a custom model's DB-stored targetFormat override whenever the model
id also existed in the static provider registry (as claude-sonnet-4-6
and claude-opus-4-7 do under vertex): resolveModelOrError had its own
ad-hoc resolution that never consulted the override, and even once
fixed, executeChatWithBreaker discarded the correctly-resolved format
before handleChatCore's own resolution ran a second time.

* docs: add changelog fragment for #8909

* refactor(sse): extract shared Claude effort-model predicate

* fix(sse): strip Claude effort-suffix ids for any provider serving a real Claude model

* fix(sse): keep no-think and CC-discovery catalog variant roots unprefixed

* fix(dashboard): re-qualify no-think playground model ids correctly

* fix(sse): scope Vertex 404s to a per-model lockout via passthroughModels

* docs: add changelog fragment for the Claude catalog/dispatch fix

* fix(sse): align regex naming and changelog formatting

* fix(sse): clarify effort-variant strip comment and add cross-module drift guard

* fix(sse): disambiguate Vertex connection-wide vs per-model 403s

* docs: document Vertex 403 disambiguation in changelog fragment

* fix(sse): correlate reason and resource within the same ErrorInfo detail

* fix(sse): extract Vertex error classifier and rebaseline frozen file sizes

* test: register vertex-passthrough-model-lockout in stryker tap.testFiles

* fix(sse): reconciles rebase-onto-tip drift for 9006

Two categories of inherited base-branch breakage surfaced when
rebasing onto release/v3.8.50's latest tip, both confirmed unrelated
to this PR's own diff:

- check:file-size: base.ts and chat.ts drifted further past their
  frozen caps via already-merged commits (7163081f5 and others) that
  didn't rebaseline after growing them. Documented and bumped in
  file-size-baseline.json.
- chat-helpers.test.ts: two gpt-5.5 routing assertions predate #9275
  (fix(routing): bare model ids route to codex first), which
  deliberately made gpt-5.5 route to codex unconditionally, regardless
  of which other providers are active. Confirmed via #9275's own
  commit message and code comments this is intentional, not a
  regression; verified reproducible on the raw base tip alone, with
  no changes from this PR involved. Updated both assertions and their
  names to match the new, intentional default.

* ci: re-trigger checks after GitHub Actions incident (2026-08-07, resolved)

* ci: re-trigger checks (previous push event was dropped)

* fix(quality): rebaseline combo-routing-engine.test.ts own-comment growth

The ALL_ACCOUNTS_INACTIVE->ALL_TARGETS_SKIPPED fix (a32aed738) added explanatory comments (+7 lines), pushing the file past its frozen 3457 cap. CI's PR-mode check:file-size caught it; local check-file-size.mjs was not re-run after that specific commit.
2026-08-11 10:02:48 -03:00

74 lines
3.4 KiB
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
const { qualifyPlaygroundModel } =
await import("../../src/app/(dashboard)/dashboard/media-providers/components/LlmChatCard.tsx");
// #3050 — vendor-namespaced model ids already contain a "/", so the old
// `.includes("/")` heuristic skipped the provider prefix and the request was
// rejected with "Ambiguous model 'moonshotai/kimi-k2.6'".
test("qualifyPlaygroundModel prefixes a vendor-namespaced model with providerId (#3050)", () => {
assert.equal(qualifyPlaygroundModel("moonshotai/kimi-k2.6", "nim"), "nim/moonshotai/kimi-k2.6");
assert.equal(
qualifyPlaygroundModel("nvidia/zyphra/zamba2-7b-instruct", "nim"),
"nim/nvidia/zyphra/zamba2-7b-instruct"
);
});
test("qualifyPlaygroundModel prefixes a bare model", () => {
assert.equal(qualifyPlaygroundModel("gpt-4o", "openai"), "openai/gpt-4o");
});
test("qualifyPlaygroundModel does not double-prefix an already-qualified model", () => {
assert.equal(
qualifyPlaygroundModel("nim/moonshotai/kimi-k2.6", "nim"),
"nim/moonshotai/kimi-k2.6"
);
assert.equal(qualifyPlaygroundModel("nim", "nim"), "nim");
});
test("qualifyPlaygroundModel returns the model unchanged without a providerId", () => {
assert.equal(qualifyPlaygroundModel("moonshotai/kimi-k2.6", ""), "moonshotai/kimi-k2.6");
assert.equal(qualifyPlaygroundModel("", "nim"), "");
});
test("OpenCode Free playground uses its routing alias instead of the reserved provider id", async () => {
const { getProviderAlias } = await import("../../src/shared/constants/providers.ts");
assert.equal(getProviderAlias("opencode"), "oc");
assert.equal(qualifyPlaygroundModel("big-pickle", getProviderAlias("opencode")), "oc/big-pickle");
});
test("qualifyPlaygroundModel inserts the provider after the no-think prefix, not before it", () => {
assert.equal(
qualifyPlaygroundModel("no-think/claude-sonnet-5", "vertex"),
"no-think/vertex/claude-sonnet-5"
);
});
test("qualifyPlaygroundModel does not double-qualify an already-qualified no-think id", () => {
assert.equal(
qualifyPlaygroundModel("no-think/vertex/claude-sonnet-5", "vertex"),
"no-think/vertex/claude-sonnet-5"
);
});
test("qualifyPlaygroundModel does not mistake a provider-name-prefix collision for already-qualified", () => {
// routingPrefix "vertex" must not match "vertex-eu/..." as already-qualified just because
// it starts with the same characters — the check requires an exact "vertex/" segment
// boundary. A naive `inner.startsWith(routingPrefix)` (no slash) would wrongly skip
// qualification here and leave the provider segment un-inserted.
assert.equal(
qualifyPlaygroundModel("no-think/vertex-eu/claude-sonnet-5", "vertex"),
"no-think/vertex/vertex-eu/claude-sonnet-5"
);
});
test("LlmChatCard's local NO_THINKING_PREFIX literal matches the canonical constant", async () => {
// Drift guard: LlmChatCard.tsx deliberately hardcodes "no-think/" as a literal instead
// of importing NO_THINKING_PREFIX from open-sse/utils/noThinkingAlias.ts (avoids pulling
// server-side catalog modules into the client bundle — see Step 1). This test file is not
// client-bundled, so it can safely import the real constant and assert they never drift.
const { NO_THINKING_PREFIX } = await import("../../open-sse/utils/noThinkingAlias.ts");
assert.equal(NO_THINKING_PREFIX, "no-think/");
});