mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-09-18 21:02:50 +03:00
65e81158ab
Landed with the design call resolved per the owner's pick — **option 1**: the synced store is now endpoint-agnostic (persistDiscoveredModels and managedModelImport no longer drop non-chat models at write time), and chat selectability moved to read time (auto-pool expansion in autoStrategy applies filterChatSelectableModels; the models-route projection already had its chatOnly filter). Your discovery test now passes end-to-end (3/3): /api/show capabilities persist per connection and image/embedding requests route through the advertising host. Reconciliation notes: conflicted areas merged onto the current tip (adobe discovery import, requestedModel preflight signature, resolvedProvider fast-path coexists with the synced-route override — explicit resolution wins); carried base-red drains (#10055 memoization, #11071 test variants) dropped as already-landed; the managed-model-import exclusion test was propagated to the new contract (image/video models persist; the read filter still hides them from chat pickers — pinned by a new assertion). Full battery: 205/206 focused (the one red is a confirmed periodic-timer timing flake on the loaded devbox — 20/20 isolated), autoCombo vitest 30/30, combo suites 46/46, gates + typecheck clean. Thank you @yourspraveen — the capability probe + routing design was right; it just needed the store contract opened up. Fixes #11087.
97 lines
4.2 KiB
TypeScript
97 lines
4.2 KiB
TypeScript
/**
|
|
* Regression test for #8189 — "auto" claudeClassifierCompat mode was over-broad.
|
|
*
|
|
* shouldDefaultAllowClassifier() previously treated `stop_sequences` containing the
|
|
* literal token `</block>` as sufficient PROOF of a Claude Code classifier request in
|
|
* "auto" mode, with no correlation to the classifier's system-prompt marker. Any
|
|
* unrelated Claude-format (/v1/messages) request that merely happened to set
|
|
* stop_sequences=["</block>"] (e.g. an app generating markup with a stop token) was
|
|
* silently short-circuited with a synthetic ALLOW response — WITHOUT ever calling the
|
|
* configured provider.
|
|
*
|
|
* Fix: in "auto" mode, the SECURITY_MONITOR_MARKER system-prompt text is now a
|
|
* necessary condition. `stop_sequences` alone is no longer sufficient.
|
|
*
|
|
* Follow-up (#9276): "always" mode previously short-circuited EVERY Claude-format
|
|
* request unconditionally, regardless of signal shape. That let a normal chat
|
|
* request through /v1/messages be silently swallowed by an operator's "always"
|
|
* opt-in. The unconditional `if (mode === "always") return true` branch was
|
|
* removed — "always" now requires the same SECURITY_MONITOR_MARKER as "auto".
|
|
*/
|
|
|
|
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import { shouldDefaultAllowClassifier } from "../../open-sse/handlers/chatCore/claudeClassifierCompat.ts";
|
|
import { FORMATS } from "../../open-sse/translator/formats.ts";
|
|
|
|
test("issue #8189: 'auto' mode fires on stop_sequences alone, with NO security-monitor marker present — over-broad trigger", () => {
|
|
const body = {
|
|
model: "aug/claude-sonnet-4.6",
|
|
max_tokens: 20,
|
|
stop_sequences: ["</block>"],
|
|
system: "You are a helpful assistant that writes CMS page templates.",
|
|
messages: [{ role: "user", content: "Write a <block>...</block> template" }],
|
|
};
|
|
const result = shouldDefaultAllowClassifier(FORMATS.CLAUDE, body, "auto");
|
|
assert.equal(
|
|
result,
|
|
false,
|
|
"auto mode must not short-circuit a request that merely happens to set stop_sequences=['</block>'] for unrelated reasons and carries no security-monitor marker"
|
|
);
|
|
});
|
|
|
|
test("issue #8189: 'auto' mode still short-circuits when the security-monitor marker is present, even without stop_sequences", () => {
|
|
const body = {
|
|
system: [
|
|
{
|
|
type: "text",
|
|
text: "You are a security monitor for autonomous AI coding agents. Evaluate the following action.",
|
|
},
|
|
],
|
|
stop_sequences: [],
|
|
messages: [{ role: "user", content: "<transcript>Bash rm -rf /</transcript>" }],
|
|
};
|
|
assert.equal(
|
|
shouldDefaultAllowClassifier(FORMATS.CLAUDE, body, "auto"),
|
|
true,
|
|
"marker-present must still short-circuit even without stop_sequences"
|
|
);
|
|
});
|
|
|
|
test("issue #9276: 'always' mode does NOT short-circuit without the security-monitor marker (narrowed to match 'auto')", () => {
|
|
const body = {
|
|
system: "You are a helpful assistant that writes CMS page templates.",
|
|
stop_sequences: ["</block>"],
|
|
messages: [{ role: "user", content: "hello" }],
|
|
};
|
|
assert.equal(
|
|
shouldDefaultAllowClassifier(FORMATS.CLAUDE, body, "always"),
|
|
false,
|
|
"mode='always' must NOT short-circuit a request with no security-monitor marker, even " +
|
|
"with stop_sequences=['</block>'] — #9276 removed the unconditional always-mode return"
|
|
);
|
|
});
|
|
|
|
test("issue #9276: 'always' mode still short-circuits when the security-monitor marker is present (operator opted in)", () => {
|
|
const body = {
|
|
system:
|
|
"You are a security monitor for autonomous AI coding agents. Evaluate the following action.",
|
|
stop_sequences: [],
|
|
messages: [{ role: "user", content: "<transcript>Bash rm -rf /</transcript>" }],
|
|
};
|
|
assert.equal(
|
|
shouldDefaultAllowClassifier(FORMATS.CLAUDE, body, "always"),
|
|
true,
|
|
"mode='always' must still short-circuit when the security-monitor marker is present"
|
|
);
|
|
});
|
|
|
|
test("issue #8189: 'off' mode (shipped default) never short-circuits", () => {
|
|
const body = {
|
|
system: [{ type: "text", text: "You are a security monitor for autonomous AI coding agents." }],
|
|
stop_sequences: ["</block>"],
|
|
};
|
|
assert.equal(shouldDefaultAllowClassifier(FORMATS.CLAUDE, body, "off"), false);
|
|
assert.equal(shouldDefaultAllowClassifier(FORMATS.CLAUDE, body, undefined), false);
|
|
});
|