feat(runner): add experimental two-way OpenAI Dot provider

scripts/__tests__/run-vitest-stable-shard.test.mjs

@@ -273,6 +273,7 @@ test("the real shard partition is duration-balanced", () => {
 const chatSuitePath = "server/src/__tests__/chat-channels.integration.test.ts";
 const nativeRunnerSuitePath =
   "server/src/services/native-runtime/native-codex-runner.integration.test.ts";
+const dotRunnerSuitePath = "server/src/__tests__/dot-runner.test.ts";
 
 // Mirrors pr-trusted.yml (12 shards, called by pr.yml so GITHUB_WORKFLOW is
 // "PR"): the chat suite runs in its dedicated lanes and the cargo-dependent
@@ -288,7 +289,8 @@ test("12 PR without-chat shards plus the dedicated chat and native-runner lanes
   const files = shards.flatMap((shard) => shard.selectedGeneralServerSuites);
   assert.ok(!files.includes(chatSuitePath));
   assert.ok(!files.includes(nativeRunnerSuitePath));
-  assert.deepEqual([...files, chatSuitePath, nativeRunnerSuitePath].sort(), full.selectedGeneralServerSuites.sort());
+  assert.ok(!files.includes(dotRunnerSuitePath));
+  assert.deepEqual([...files, chatSuitePath, nativeRunnerSuitePath, dotRunnerSuitePath].sort(), full.selectedGeneralServerSuites.sort());
   assert.equal(new Set(files).size, files.length);
   const defaultRun = dryRunJson([], prEnv);
   assert.ok(defaultRun.generalServerSuiteCount === full.generalServerSuiteCount);
@@ -307,6 +309,7 @@ for (const [caller, envOverrides] of [["Release", { GITHUB_WORKFLOW: "Release" }
     const files = shards.flatMap((shard) => shard.selectedGeneralServerSuites);
     assert.ok(!files.includes(chatSuitePath));
     assert.ok(files.includes(nativeRunnerSuitePath));
+    assert.ok(files.includes(dotRunnerSuitePath));
     assert.deepEqual([...files, chatSuitePath].sort(), full.selectedGeneralServerSuites.sort());
     assert.equal(new Set(files).size, files.length);
   });
@@ -316,6 +319,7 @@ test("the native-runner lane runs exactly the cargo-dependent vertical-slice sui
   const lane = dryRunJson(["--mode", "general", "--group", "general-server-native-runner"]);
   assert.deepEqual(lane.selectedGeneralServerSuites, [
     "server/src/services/native-runtime/native-codex-runner.integration.test.ts",
+    dotRunnerSuitePath,
   ]);
 });
 

scripts/run-vitest-stable.mjs

@@ -76,8 +76,10 @@ const chatSuite = "server/src/__tests__/chat-channels.integration.test.ts";
 // Inside the PR workflow's plain server shards, which carry no Rust cache,
 // that build was a ~4m30s cold compile of every third-party crate on each run
 // (277s of a 291s shard vitest step, actions run 35246999382, 2026-09-17).
-const nativeRunnerSuite =
-  "server/src/services/native-runtime/native-codex-runner.integration.test.ts";
+const nativeRunnerSuites = [
+  "server/src/services/native-runtime/native-codex-runner.integration.test.ts",
+  "server/src/__tests__/dot-runner.test.ts",
+];
 // In the PR workflow (pr.yml, the caller of pr-trusted.yml — reusable
 // workflows inherit the caller's GITHUB_WORKFLOW), the last Verify Paperclip
 // Runner vitest shard runs the native-runner group instead, because those
@@ -90,7 +92,7 @@ const nativeRunnerSuite =
 const prWorkflowName = "PR";
 const nativeRunnerSuiteRunsInRustCachedLane = process.env.GITHUB_WORKFLOW === prWorkflowName;
 const withoutChatExcludedSuites = nativeRunnerSuiteRunsInRustCachedLane
-  ? [chatSuite, nativeRunnerSuite]
+  ? [chatSuite, ...nativeRunnerSuites]
   : [chatSuite];
 const generalWorkspacesAGroupName = "general-workspaces-a";
 const generalWorkspacesBGroupName = "general-workspaces-b";
@@ -383,7 +385,7 @@ function runGeneralGroup(routeTests, groupName, shardIndex = null, shardCount =
   }
   if (groupName === generalServerNativeRunnerGroupName) {
     runVitest(
-      ["--project", "@paperclipai/server", ...serializedServerVitestArgs, nativeRunnerSuite],
+      ["--project", "@paperclipai/server", ...serializedServerVitestArgs, ...nativeRunnerSuites],
       "native runner vertical-slice suite",
     );
     return;
@@ -517,7 +519,7 @@ if (options.dryRun) {
         generalServerSuiteCount: generalServerTestFiles.length,
         selectedGeneralServerSuites:
           options.mode === generalModeName && options.group === generalServerNativeRunnerGroupName
-            ? [nativeRunnerSuite]
+            ? nativeRunnerSuites
             : options.mode === generalModeName &&
                 [generalServerGroupName, generalServerWithoutChatGroupName].includes(options.group) &&
                 options.shardCount !== null