refactor(model-routing): centralize explicit foreground fallback policy (#6020)

* refactor(model-routing): centralize explicit foreground fallback policy Make foreground fallback an explicit per-user, availability-only policy shared by streaming Chat, non-stream Chat, and Agent runs. Preserve strict defaults, owner/model and credential boundaries, pinned Agent routes, and truthful per-round provenance/accounting. Carry provider-reported model identifiers through native streaming adapters, non-stream responses, and caches, and keep legacy default_model_fallbacks as tombstoned raw storage that generic settings APIs and agent tools cannot expose or mutate. * fix(agent-loop): restore rebase-dropped qwen routing, workspace prompt, and temperature clamp * fix(model-routing): thread selected endpoint identity, fix cost classification and fallback eligibility * fix(chat): restore stream helpers and harden run stop lifecycle * fix(model-routing): let numeric provider codes win over symbolic rate-limit statuses * fix(agent-loop): apply qwen temperature and notes-tool clamps per fallback candidate * fix(chat): honor queued stop across resend and reload canonical terminal on EOF * fix(chat): track stop queue and cleanup ownership by per-send generation * fix(agent-loop): preserve requested temperature for non-qwen fallback candidates * fix(chat): reserve send ownership before any await and scope stop to the current send * fix(chat): clear the previous run identity at send reservation --------- Co-authored-by: RaresKeY <158580472+RaresKeY@users.noreply.github.com> Co-authored-by: StressTestor <212606152+StressTestor@users.noreply.github.com>
2026-09-25 01:22:19 +02:00 · 2026-08-14 08:10:30 +01:00
parent b52296471b
commit c4369305f0
46 changed files with 11418 additions and 1006 deletions
@@ -0,0 +1,47 @@
+"""Execute terminal stream-error classification under Node."""
+
+import json
+import shutil
+import subprocess
+from pathlib import Path
+
+import pytest
+
+
+_REPO = Path(__file__).resolve().parents[1]
+_MODULE = (_REPO / "static" / "js" / "chatStreamErrors.js").as_uri()
+
+
+def test_terminal_provider_errors_preserve_text_and_never_auto_retry():
+    if not shutil.which("node"):
+        pytest.skip("node is not installed")
+
+    script = f"""
+      import {{ createTerminalStreamError, isRecoverableStreamError }} from {json.dumps(_MODULE)};
+      const stringError = createTerminalStreamError({{ status: 401, error: 'invalid key' }});
+      const objectError = createTerminalStreamError({{ status: 404, error: {{ message: 'model missing' }} }});
+      console.log(JSON.stringify({{
+        stringMessage: stringError.message,
+        objectMessage: objectError.message,
+        terminalRecoverable: isRecoverableStreamError(stringError),
+        eofRecoverable: isRecoverableStreamError(new Error('Stream closed before completion')),
+        networkRecoverable: isRecoverableStreamError(new TypeError('fetch failed')),
+      }}));
+    """
+    result = subprocess.run(
+        ["node", "--input-type=module"],
+        input=script,
+        capture_output=True,
+        text=True,
+        cwd=_REPO,
+        timeout=30,
+    )
+
+    assert result.returncode == 0, result.stderr
+    assert json.loads(result.stdout) == {
+        "stringMessage": "invalid key",
+        "objectMessage": "model missing",
+        "terminalRecoverable": False,
+        "eofRecoverable": True,
+        "networkRecoverable": True,
+    }