Merge branch 'main' of github.com:NousResearch/hermes-agent into bb/gui

tests/agent/test_auxiliary_client.py

@@ -40,6 +40,16 @@ def _clean_env(monkeypatch):
         "ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN", "CLAUDE_CODE_OAUTH_TOKEN",
     ):
         monkeypatch.delenv(key, raising=False)
+    # Module-level unhealthy cache (10-min TTL) leaks between tests;
+    # earlier tests that call _mark_provider_unhealthy() poison the
+    # cache for later ones, causing _resolve_auto to skip providers
+    # that the test patched to return valid clients.
+    import agent.auxiliary_client as _aux_mod
+    _aux_mod._aux_unhealthy_until.clear()
+    _aux_mod._aux_unhealthy_logged_at.clear()
+    yield
+    _aux_mod._aux_unhealthy_until.clear()
+    _aux_mod._aux_unhealthy_logged_at.clear()
 
 
 @pytest.fixture
@@ -461,6 +471,17 @@ class TestExpiredCodexFallback:
         import base64
         import time as _time
 
+        # Belt-and-suspenders: _try_openrouter marks openrouter unhealthy
+        # when OPENROUTER_API_KEY is absent (which the preceding test in
+        # this class exercises).  The file-level _clean_env autouse fixture
+        # clears the cache, but fixture ordering with the conftest
+        # _hermetic_environment autouse can leave a narrow window where
+        # the mark reappears.  Explicitly clear here so this test is
+        # independent of run order.
+        import agent.auxiliary_client as _aux_mod
+        _aux_mod._aux_unhealthy_until.clear()
+        _aux_mod._aux_unhealthy_logged_at.clear()
+
         header = base64.urlsafe_b64encode(b'{"alg":"RS256","typ":"JWT"}').rstrip(b"=").decode()
         payload_data = json.dumps({"exp": int(_time.time()) - 3600}).encode()
         payload = base64.urlsafe_b64encode(payload_data).rstrip(b"=").decode()
@@ -1047,6 +1068,20 @@ class TestGetProviderChain:
 class TestTryPaymentFallback:
     """_try_payment_fallback skips the failed provider and tries alternatives."""
 
+    @pytest.fixture(autouse=True)
+    def _clear_unhealthy_cache(self):
+        """Earlier tests in this file call _mark_provider_unhealthy() which
+        pollutes the module-level ``_aux_unhealthy_until`` dict (10-min TTL).
+        Without this cleanup the fallback chain skips providers we've patched
+        to return valid clients — the patched function is never called.
+        """
+        from agent.auxiliary_client import _aux_unhealthy_until, _aux_unhealthy_logged_at
+        _aux_unhealthy_until.clear()
+        _aux_unhealthy_logged_at.clear()
+        yield
+        _aux_unhealthy_until.clear()
+        _aux_unhealthy_logged_at.clear()
+
     def test_skips_failed_provider(self):
         mock_client = MagicMock()
         with patch("agent.auxiliary_client._try_openrouter", return_value=(None, None)), \

tests/agent/test_custom_provider_extra_body.py

@@ -0,0 +1,93 @@
+from types import SimpleNamespace
+
+from agent.agent_init import _merge_custom_provider_extra_body
+
+
+def test_custom_provider_extra_body_merges_into_request_overrides():
+    agent = SimpleNamespace(
+        provider="custom",
+        model="google/gemma-4-31b-it",
+        base_url="https://example.test/v1",
+        request_overrides={"service_tier": "priority"},
+    )
+
+    _merge_custom_provider_extra_body(
+        agent,
+        [
+            {
+                "name": "gemma",
+                "base_url": "https://example.test/v1/",
+                "model": "google/gemma-4-31b-it",
+                "extra_body": {
+                    "enable_thinking": True,
+                    "reasoning_effort": "high",
+                },
+            }
+        ],
+    )
+
+    assert agent.request_overrides == {
+        "service_tier": "priority",
+        "extra_body": {
+            "enable_thinking": True,
+            "reasoning_effort": "high",
+        },
+    }
+
+
+def test_custom_provider_extra_body_preserves_caller_override():
+    agent = SimpleNamespace(
+        provider="custom",
+        model="google/gemma-4-31b-it",
+        base_url="https://example.test/v1",
+        request_overrides={
+            "extra_body": {
+                "reasoning_effort": "low",
+                "caller_only": True,
+            }
+        },
+    )
+
+    _merge_custom_provider_extra_body(
+        agent,
+        [
+            {
+                "name": "gemma",
+                "base_url": "https://example.test/v1",
+                "model": "google/gemma-4-31b-it",
+                "extra_body": {
+                    "enable_thinking": True,
+                    "reasoning_effort": "high",
+                },
+            }
+        ],
+    )
+
+    assert agent.request_overrides["extra_body"] == {
+        "enable_thinking": True,
+        "reasoning_effort": "low",
+        "caller_only": True,
+    }
+
+
+def test_custom_provider_extra_body_ignores_other_custom_models():
+    agent = SimpleNamespace(
+        provider="custom",
+        model="other-model",
+        base_url="https://example.test/v1",
+        request_overrides={},
+    )
+
+    _merge_custom_provider_extra_body(
+        agent,
+        [
+            {
+                "name": "gemma",
+                "base_url": "https://example.test/v1",
+                "model": "google/gemma-4-31b-it",
+                "extra_body": {"enable_thinking": True},
+            }
+        ],
+    )
+
+    assert agent.request_overrides == {}

tests/agent/test_image_routing.py

@@ -9,8 +9,11 @@ from unittest.mock import patch
 import pytest
 
 from agent.image_routing import (
+    _coerce_capability_bool,
     _coerce_mode,
     _explicit_aux_vision_override,
+    _lookup_supports_vision,
+    _supports_vision_override,
     build_native_content_parts,
     decide_image_input_mode,
 )
@@ -125,6 +128,168 @@ class TestDecideImageInputMode:
             assert decide_image_input_mode("xiaomi", "mimo-v2.5-pro", {}) == "text"
 
 
+# ─── _coerce_capability_bool ─────────────────────────────────────────────────
+
+
+class TestCoerceCapabilityBool:
+    def test_real_bool_passes_through(self):
+        assert _coerce_capability_bool(True) is True
+        assert _coerce_capability_bool(False) is False
+
+    def test_int_0_and_1(self):
+        assert _coerce_capability_bool(1) is True
+        assert _coerce_capability_bool(0) is False
+
+    def test_other_ints_return_none(self):
+        assert _coerce_capability_bool(2) is None
+        assert _coerce_capability_bool(-1) is None
+
+    def test_yaml_true_tokens(self):
+        for s in ("true", "TRUE", "True", "yes", "on", "1", "  true  "):
+            assert _coerce_capability_bool(s) is True
+
+    def test_yaml_false_tokens(self):
+        for s in ("false", "FALSE", "False", "no", "off", "0", "  false  "):
+            assert _coerce_capability_bool(s) is False
+
+    def test_quoted_false_does_not_silently_become_true(self):
+        # Regression: bool("false") is True in Python. A user writing
+        # supports_vision: "false" must NOT enable native vision routing.
+        assert _coerce_capability_bool("false") is False
+
+    def test_unrecognised_strings_return_none(self):
+        # None == fall through to models.dev, not a silent truthy.
+        assert _coerce_capability_bool("maybe") is None
+        assert _coerce_capability_bool("") is None
+        assert _coerce_capability_bool("definitely") is None
+
+    def test_other_types_return_none(self):
+        assert _coerce_capability_bool(None) is None
+        assert _coerce_capability_bool([]) is None
+        assert _coerce_capability_bool({}) is None
+        assert _coerce_capability_bool(1.5) is None
+
+
+# ─── _supports_vision_override ───────────────────────────────────────────────
+
+
+class TestSupportsVisionOverride:
+    def test_no_cfg_returns_none(self):
+        assert _supports_vision_override(None, "custom", "my-llava") is None
+        assert _supports_vision_override({}, "custom", "my-llava") is None
+
+    def test_top_level_shortcut_wins(self):
+        cfg = {"model": {"supports_vision": True}}
+        assert _supports_vision_override(cfg, "custom", "my-llava") is True
+
+    def test_top_level_false_propagates(self):
+        cfg = {"model": {"supports_vision": False}}
+        assert _supports_vision_override(cfg, "custom", "my-llava") is False
+
+    def test_per_provider_per_model_via_runtime_name(self):
+        cfg = {
+            "providers": {
+                "custom": {"models": {"my-llava": {"supports_vision": True}}},
+            },
+        }
+        assert _supports_vision_override(cfg, "custom", "my-llava") is True
+
+    def test_per_provider_per_model_via_config_name(self):
+        # Named custom provider — runtime self.provider == "custom", config
+        # holds the original name under model.provider.
+        cfg = {
+            "model": {"provider": "my-vllm"},
+            "providers": {
+                "my-vllm": {"models": {"my-llava": {"supports_vision": True}}},
+            },
+        }
+        assert _supports_vision_override(cfg, "custom", "my-llava") is True
+
+    def test_quoted_false_string_in_yaml_does_not_enable(self):
+        # Real-world: user writes supports_vision: "false" (quoted).
+        cfg = {"model": {"supports_vision": "false"}}
+        assert _supports_vision_override(cfg, "custom", "my-llava") is False
+
+    def test_unrecognised_value_falls_through(self):
+        cfg = {"model": {"supports_vision": "maybe"}}
+        assert _supports_vision_override(cfg, "custom", "my-llava") is None
+
+    def test_no_override_returns_none(self):
+        cfg = {"model": {"default": "my-llava"}}
+        assert _supports_vision_override(cfg, "custom", "my-llava") is None
+
+    def test_malformed_sections_are_ignored(self):
+        # User accidentally wrote a string where a section was expected —
+        # don't blow up, just fall through.
+        cfg = {"model": "some-string", "providers": ["not-a-dict"]}
+        assert _supports_vision_override(cfg, "custom", "my-llava") is None
+
+
+# ─── _lookup_supports_vision (override-aware) ────────────────────────────────
+
+
+class TestLookupSupportsVisionOverride:
+    def test_config_override_short_circuits_models_dev(self):
+        # Config says True, models.dev says None — config wins.
+        cfg = {"model": {"supports_vision": True}}
+        with patch("agent.models_dev.get_model_capabilities", return_value=None):
+            assert _lookup_supports_vision("custom", "my-llava", cfg) is True
+
+    def test_config_override_false_beats_vision_capable_models_dev(self):
+        # User explicitly disables vision on a models.dev-vision-capable model.
+        fake_caps = type("Caps", (), {"supports_vision": True})()
+        cfg = {"model": {"supports_vision": False}}
+        with patch("agent.models_dev.get_model_capabilities", return_value=fake_caps):
+            assert _lookup_supports_vision("anthropic", "claude-sonnet-4", cfg) is False
+
+    def test_no_override_falls_back_to_models_dev(self):
+        fake_caps = type("Caps", (), {"supports_vision": True})()
+        with patch("agent.models_dev.get_model_capabilities", return_value=fake_caps):
+            assert _lookup_supports_vision("anthropic", "claude-sonnet-4", {}) is True
+
+    def test_no_override_no_models_dev_entry_returns_none(self):
+        with patch("agent.models_dev.get_model_capabilities", return_value=None):
+            assert _lookup_supports_vision("custom", "my-llava", {}) is None
+
+    def test_cfg_none_falls_back_to_models_dev(self):
+        # Caller didn't pass cfg at all — old call sites must still work.
+        with patch("agent.models_dev.get_model_capabilities", return_value=None):
+            assert _lookup_supports_vision("openrouter", "x", None) is None
+
+
+# ─── decide_image_input_mode with auto + override ────────────────────────────
+
+
+class TestAutoModeRespectsOverride:
+    def test_auto_native_for_custom_with_supports_vision_true(self):
+        # The motivating bug: Qwen3.6 on local llama.cpp via provider=custom.
+        # Without the override, auto falls back to text. With it, auto picks
+        # native — no need to also set agent.image_input_mode: native.
+        cfg = {"model": {"supports_vision": True}}
+        with patch("agent.models_dev.get_model_capabilities", return_value=None):
+            assert decide_image_input_mode("custom", "qwen3.6-35b", cfg) == "native"
+
+    def test_auto_text_for_custom_with_supports_vision_false(self):
+        cfg = {"model": {"supports_vision": False}}
+        with patch("agent.models_dev.get_model_capabilities", return_value=None):
+            assert decide_image_input_mode("custom", "some-text-only", cfg) == "text"
+
+    def test_auto_text_for_custom_with_no_override(self):
+        # Unchanged baseline: unknown custom model → text.
+        with patch("agent.models_dev.get_model_capabilities", return_value=None):
+            assert decide_image_input_mode("custom", "unknown", {}) == "text"
+
+    def test_explicit_aux_vision_override_still_wins(self):
+        # If the user has configured a dedicated vision aux backend, respect
+        # it even when supports_vision: true is also set.
+        cfg = {
+            "model": {"supports_vision": True},
+            "auxiliary": {"vision": {"provider": "openrouter", "model": "gemini-2.5-pro"}},
+        }
+        with patch("agent.models_dev.get_model_capabilities", return_value=None):
+            assert decide_image_input_mode("custom", "qwen3.6-35b", cfg) == "text"
+
+
 # ─── build_native_content_parts ──────────────────────────────────────────────
 
 

tests/agent/test_skill_commands.py

@@ -556,10 +556,11 @@ Generate some audio.
             raising=False,
         )
 
-        with patch.dict(
-            os.environ, {"HERMES_SESSION_PLATFORM": "telegram"}, clear=False
-        ):
-            with patch("tools.skills_tool.SKILLS_DIR", tmp_path):
+        with patch("tools.skills_tool.SKILLS_DIR", tmp_path):
+            from gateway.session_context import clear_session_vars, set_session_vars
+
+            tokens = set_session_vars(platform="telegram")
+            try:
                 _make_skill(
                     tmp_path,
                     "test-skill",
@@ -571,6 +572,8 @@ Generate some audio.
                 )
                 scan_skill_commands()
                 msg = build_skill_invocation_message("/test-skill", "do stuff")
+            finally:
+                clear_session_vars(tokens)
 
         assert msg is not None
         assert "local cli" in msg.lower()

tests/agent/transports/test_codex_transport.py

@@ -196,14 +196,13 @@ class TestCodexBuildKwargs:
         )
         # xAI Responses receives reasoning.effort on the allowlisted models.
         assert kw.get("reasoning") == {"effort": "high"}
-        # As of May 2026 we deliberately do NOT request
-        # reasoning.encrypted_content back from xAI — the OAuth/SuperGrok
-        # surface rejects replayed encrypted reasoning items on turn 2+
-        # (the multi-turn "Expected to have received response.created
-        # before error" failure).  Grok still reasons natively each turn;
-        # we just don't try to thread the prior turn's encrypted blob back
-        # in.  See tests/run_agent/test_codex_xai_oauth_recovery.py.
-        assert "reasoning.encrypted_content" not in kw.get("include", [])
+        # As of May 2026 (post-revert of PR #26644) we DO request
+        # reasoning.encrypted_content back from xAI so we can replay it
+        # across turns for cross-turn coherence — xAI explicitly relies
+        # on this for their partnership integration.  See
+        # tests/run_agent/test_codex_xai_oauth_recovery.py for the
+        # full history.
+        assert "reasoning.encrypted_content" in kw.get("include", [])
 
     def test_xai_reasoning_disabled_no_reasoning_key(self, transport):
         messages = [{"role": "user", "content": "Hi"}]
@@ -229,9 +228,9 @@ class TestCodexBuildKwargs:
     # api.x.ai 400s with "Model X does not support parameter reasoningEffort"
     # on grok-4 / grok-4-fast / grok-3 / grok-code-fast / grok-4.20-0309-*.
     # Those models reason natively but don't expose the dial. The transport
-    # must omit the `reasoning` key for them.  As of May 2026 we also no
-    # longer request ``reasoning.encrypted_content`` back from xAI on ANY
-    # model — see test_xai_reasoning_effort_passed for the rationale.
+    # must omit the `reasoning` key for them.  As of May 2026 we DO request
+    # ``reasoning.encrypted_content`` back from xAI on every model —
+    # see test_xai_reasoning_effort_passed for the rationale.
 
     def test_xai_grok_4_omits_reasoning_effort(self, transport):
         """grok-4 / grok-4-0709 reject reasoning.effort with HTTP 400."""
@@ -245,9 +244,9 @@ class TestCodexBuildKwargs:
             assert "reasoning" not in kw, (
                 f"{model} must not receive a reasoning key (xAI rejects it)"
             )
-            # We no longer ask xAI for encrypted_content back (see comment
-            # above) — verify the include list is empty.
-            assert "reasoning.encrypted_content" not in kw.get("include", [])
+            # Even without the effort dial we still ask xAI to echo back
+            # encrypted reasoning content so it can be replayed next turn.
+            assert "reasoning.encrypted_content" in kw.get("include", [])
 
     def test_xai_grok_4_fast_omits_reasoning_effort(self, transport):
         """grok-4-fast and grok-4-1-fast variants reject reasoning.effort."""