fix(gemini-cli): surface MODEL_CAPACITY_EXHAUSTED cleanly + drop retired gemma-4-26b (#11833)

Google-side 429 Code Assist errors now flow through Hermes' normal rate-limit
path (status_code on the exception, Retry-After preserved via error.response)
instead of being opaque RuntimeErrors. User sees a one-line capacity message
instead of a 500-char JSON dump.

Changes
- CodeAssistError grows status_code / response / retry_after / details attrs.
  _extract_status_code in error_classifier picks up status_code and classifies
  429 as FailoverReason.rate_limit, so fallback_providers triggers the same
  way it does for SDK errors. run_agent.py line ~10428 already walks
  error.response.headers for Retry-After — preserving the response means that
  path just works.
- _gemini_http_error parses the Google error envelope (error.status +
  error.details[].reason from google.rpc.ErrorInfo, retryDelay from
  google.rpc.RetryInfo). MODEL_CAPACITY_EXHAUSTED / RESOURCE_EXHAUSTED / 404
  model-not-found each produce a human-readable message; unknown shapes fall
  back to the previous raw-body format.
- Drop gemma-4-26b-it from hermes_cli/models.py, hermes_cli/setup.py, and
  agent/model_metadata.py — Google returned 404 for it today in local repro.
  Kept gemma-4-31b-it (capacity-constrained but not retired).

Validation
|                           | Before                         | After                                     |
|---------------------------|--------------------------------|-------------------------------------------|
| Error message             | 'Code Assist returned HTTP 429: {500 chars JSON}' | 'Gemini capacity exhausted for gemini-2.5-pro (Google-side throttle...)' |
| status_code on error      | None (opaque RuntimeError)     | 429                                       |
| Classifier reason         | unknown (string-match fallback) | FailoverReason.rate_limit                |
| Retry-After honored       | ignored                        | extracted from RetryInfo or header        |
| gemma-4-26b-it picker     | advertised (404s on Google)    | removed                                   |

Unit + E2E tests cover non-streaming 429, streaming 429, 404 model-not-found,
Retry-After header fallback, malformed body, and classifier integration.
Targeted suites: tests/agent/test_gemini_cloudcode.py (81 tests), full
tests/hermes_cli (2203 tests) green.

Co-authored-by: teknium1 <teknium@nousresearch.com>

tests/agent/test_gemini_cloudcode.py

@@ -826,6 +826,160 @@ class TestGeminiCloudCodeClient:
         finally:
             client.close()
 
+
+class TestGeminiHttpErrorParsing:
+    """Regression coverage for _gemini_http_error Google-envelope parsing.
+
+    These are the paths that users actually hit during Google-side throttling
+    (April 2026: gemini-2.5-pro MODEL_CAPACITY_EXHAUSTED, gemma-4-26b-it
+    returning 404).  The error needs to carry status_code + response so the
+    main loop's error_classifier and Retry-After logic work.
+    """
+
+    @staticmethod
+    def _fake_response(status: int, body: dict | str = "", headers=None):
+        """Minimal httpx.Response stand-in (duck-typed for _gemini_http_error)."""
+        class _FakeResponse:
+            def __init__(self):
+                self.status_code = status
+                if isinstance(body, dict):
+                    self.text = json.dumps(body)
+                else:
+                    self.text = body
+                self.headers = headers or {}
+        return _FakeResponse()
+
+    def test_model_capacity_exhausted_produces_friendly_message(self):
+        from agent.gemini_cloudcode_adapter import _gemini_http_error
+
+        body = {
+            "error": {
+                "code": 429,
+                "message": "Resource has been exhausted (e.g. check quota).",
+                "status": "RESOURCE_EXHAUSTED",
+                "details": [
+                    {
+                        "@type": "type.googleapis.com/google.rpc.ErrorInfo",
+                        "reason": "MODEL_CAPACITY_EXHAUSTED",
+                        "domain": "googleapis.com",
+                        "metadata": {"model": "gemini-2.5-pro"},
+                    },
+                    {
+                        "@type": "type.googleapis.com/google.rpc.RetryInfo",
+                        "retryDelay": "30s",
+                    },
+                ],
+            }
+        }
+        err = _gemini_http_error(self._fake_response(429, body))
+        assert err.status_code == 429
+        assert err.code == "code_assist_capacity_exhausted"
+        assert err.retry_after == 30.0
+        assert err.details["reason"] == "MODEL_CAPACITY_EXHAUSTED"
+        # Message must be user-friendly, not a raw JSON dump.
+        message = str(err)
+        assert "gemini-2.5-pro" in message
+        assert "capacity exhausted" in message.lower()
+        assert "30s" in message
+        # response attr is preserved for run_agent's Retry-After header path.
+        assert err.response is not None
+
+    def test_resource_exhausted_without_reason(self):
+        from agent.gemini_cloudcode_adapter import _gemini_http_error
+
+        body = {
+            "error": {
+                "code": 429,
+                "message": "Quota exceeded for requests per minute.",
+                "status": "RESOURCE_EXHAUSTED",
+            }
+        }
+        err = _gemini_http_error(self._fake_response(429, body))
+        assert err.status_code == 429
+        assert err.code == "code_assist_rate_limited"
+        message = str(err)
+        assert "quota" in message.lower()
+
+    def test_404_model_not_found_produces_model_retired_message(self):
+        from agent.gemini_cloudcode_adapter import _gemini_http_error
+
+        body = {
+            "error": {
+                "code": 404,
+                "message": "models/gemma-4-26b-it is not found for API version v1internal",
+                "status": "NOT_FOUND",
+            }
+        }
+        err = _gemini_http_error(self._fake_response(404, body))
+        assert err.status_code == 404
+        message = str(err)
+        assert "not available" in message.lower() or "retired" in message.lower()
+        # Error message should reference the actual model text from Google.
+        assert "gemma-4-26b-it" in message
+
+    def test_unauthorized_preserves_status_code(self):
+        from agent.gemini_cloudcode_adapter import _gemini_http_error
+
+        err = _gemini_http_error(self._fake_response(
+            401, {"error": {"code": 401, "message": "Invalid token", "status": "UNAUTHENTICATED"}},
+        ))
+        assert err.status_code == 401
+        assert err.code == "code_assist_unauthorized"
+
+    def test_retry_after_header_fallback(self):
+        """If the body has no RetryInfo detail, fall back to Retry-After header."""
+        from agent.gemini_cloudcode_adapter import _gemini_http_error
+
+        resp = self._fake_response(
+            429,
+            {"error": {"code": 429, "message": "Rate limited", "status": "RESOURCE_EXHAUSTED"}},
+            headers={"Retry-After": "45"},
+        )
+        err = _gemini_http_error(resp)
+        assert err.retry_after == 45.0
+
+    def test_malformed_body_still_produces_structured_error(self):
+        """Non-JSON body must not swallow status_code — we still want the classifier path."""
+        from agent.gemini_cloudcode_adapter import _gemini_http_error
+
+        err = _gemini_http_error(self._fake_response(500, "<html>internal error</html>"))
+        assert err.status_code == 500
+        # Raw body snippet must still be there for debugging.
+        assert "500" in str(err)
+
+    def test_status_code_flows_through_error_classifier(self):
+        """End-to-end: CodeAssistError from a 429 must classify as rate_limit.
+
+        This is the whole point of adding status_code to CodeAssistError —
+        _extract_status_code must see it and FailoverReason.rate_limit must
+        fire, so the main loop triggers fallback_providers.
+        """
+        from agent.gemini_cloudcode_adapter import _gemini_http_error
+        from agent.error_classifier import classify_api_error, FailoverReason
+
+        body = {
+            "error": {
+                "code": 429,
+                "message": "Resource has been exhausted",
+                "status": "RESOURCE_EXHAUSTED",
+                "details": [
+                    {
+                        "@type": "type.googleapis.com/google.rpc.ErrorInfo",
+                        "reason": "MODEL_CAPACITY_EXHAUSTED",
+                        "metadata": {"model": "gemini-2.5-pro"},
+                    }
+                ],
+            }
+        }
+        err = _gemini_http_error(self._fake_response(429, body))
+
+        classified = classify_api_error(
+            err, provider="google-gemini-cli", model="gemini-2.5-pro",
+        )
+        assert classified.status_code == 429
+        assert classified.reason == FailoverReason.rate_limit
+
+
 # =============================================================================
 # Provider registration
 # =============================================================================