Merge remote-tracking branch 'origin/main' into feat/dashboard-chat

tests/hermes_cli/test_api_key_providers.py

@@ -15,6 +15,8 @@ from hermes_cli.auth import (
     get_auth_status,
     AuthError,
     KIMI_CODE_BASE_URL,
+    STEPFUN_STEP_PLAN_INTL_BASE_URL,
+    STEPFUN_STEP_PLAN_CN_BASE_URL,
     _resolve_kimi_base_url,
 )
 from hermes_cli.copilot_auth import _try_gh_cli_token
@@ -35,6 +37,7 @@ class TestProviderRegistry:
         ("xai", "xAI", "api_key"),
         ("nvidia", "NVIDIA NIM", "api_key"),
         ("kimi-coding", "Kimi / Moonshot", "api_key"),
+        ("stepfun", "StepFun Step Plan", "api_key"),
         ("minimax", "MiniMax", "api_key"),
         ("minimax-cn", "MiniMax (China)", "api_key"),
         ("ai-gateway", "Vercel AI Gateway", "api_key"),
@@ -71,7 +74,11 @@ class TestProviderRegistry:
 
     def test_kimi_env_vars(self):
         pconfig = PROVIDER_REGISTRY["kimi-coding"]
-        assert pconfig.api_key_env_vars == ("KIMI_API_KEY",)
+        # KIMI_API_KEY is the primary env var; KIMI_CODING_API_KEY is a
+        # secondary fallback for Kimi Code sk-kimi- keys so users don't
+        # have to overload the same variable.
+        assert "KIMI_API_KEY" in pconfig.api_key_env_vars
+        assert "KIMI_CODING_API_KEY" in pconfig.api_key_env_vars
         assert pconfig.base_url_env_var == "KIMI_BASE_URL"
 
     def test_minimax_env_vars(self):
@@ -79,6 +86,11 @@ class TestProviderRegistry:
         assert pconfig.api_key_env_vars == ("MINIMAX_API_KEY",)
         assert pconfig.base_url_env_var == "MINIMAX_BASE_URL"
 
+    def test_stepfun_env_vars(self):
+        pconfig = PROVIDER_REGISTRY["stepfun"]
+        assert pconfig.api_key_env_vars == ("STEPFUN_API_KEY",)
+        assert pconfig.base_url_env_var == "STEPFUN_BASE_URL"
+
     def test_minimax_cn_env_vars(self):
         pconfig = PROVIDER_REGISTRY["minimax-cn"]
         assert pconfig.api_key_env_vars == ("MINIMAX_CN_API_KEY",)
@@ -104,6 +116,7 @@ class TestProviderRegistry:
         assert PROVIDER_REGISTRY["copilot-acp"].inference_base_url == "acp://copilot"
         assert PROVIDER_REGISTRY["zai"].inference_base_url == "https://api.z.ai/api/paas/v4"
         assert PROVIDER_REGISTRY["kimi-coding"].inference_base_url == "https://api.moonshot.ai/v1"
+        assert PROVIDER_REGISTRY["stepfun"].inference_base_url == STEPFUN_STEP_PLAN_INTL_BASE_URL
         assert PROVIDER_REGISTRY["minimax"].inference_base_url == "https://api.minimax.io/anthropic"
         assert PROVIDER_REGISTRY["minimax-cn"].inference_base_url == "https://api.minimaxi.com/anthropic"
         assert PROVIDER_REGISTRY["ai-gateway"].inference_base_url == "https://ai-gateway.vercel.sh/v1"
@@ -126,7 +139,8 @@ PROVIDER_ENV_VARS = (
     "OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN",
     "CLAUDE_CODE_OAUTH_TOKEN",
     "GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY",
-    "KIMI_API_KEY", "KIMI_BASE_URL", "MINIMAX_API_KEY", "MINIMAX_CN_API_KEY",
+    "KIMI_API_KEY", "KIMI_BASE_URL", "STEPFUN_API_KEY", "STEPFUN_BASE_URL",
+    "MINIMAX_API_KEY", "MINIMAX_CN_API_KEY",
     "AI_GATEWAY_API_KEY", "AI_GATEWAY_BASE_URL",
     "KILOCODE_API_KEY", "KILOCODE_BASE_URL",
     "DASHSCOPE_API_KEY", "OPENCODE_ZEN_API_KEY", "OPENCODE_GO_API_KEY",
@@ -152,6 +166,9 @@ class TestResolveProvider:
     def test_explicit_kimi_coding(self):
         assert resolve_provider("kimi-coding") == "kimi-coding"
 
+    def test_explicit_stepfun(self):
+        assert resolve_provider("stepfun") == "stepfun"
+
     def test_explicit_minimax(self):
         assert resolve_provider("minimax") == "minimax"
 
@@ -176,6 +193,9 @@ class TestResolveProvider:
     def test_alias_moonshot(self):
         assert resolve_provider("moonshot") == "kimi-coding"
 
+    def test_alias_step(self):
+        assert resolve_provider("step") == "stepfun"
+
     def test_alias_minimax_underscore(self):
         assert resolve_provider("minimax_cn") == "minimax-cn"
 
@@ -244,6 +264,10 @@ class TestResolveProvider:
         monkeypatch.setenv("KIMI_API_KEY", "test-kimi-key")
         assert resolve_provider("auto") == "kimi-coding"
 
+    def test_auto_detects_stepfun_key(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "test-stepfun-key")
+        assert resolve_provider("auto") == "stepfun"
+
     def test_auto_detects_minimax_key(self, monkeypatch):
         monkeypatch.setenv("MINIMAX_API_KEY", "test-mm-key")
         assert resolve_provider("auto") == "minimax"
@@ -308,6 +332,13 @@ class TestApiKeyProviderStatus:
         status = get_api_key_provider_status("kimi-coding")
         assert status["base_url"] == "https://custom.kimi.example/v1"
 
+    def test_stepfun_status_uses_configured_base_url(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-key")
+        monkeypatch.setenv("STEPFUN_BASE_URL", STEPFUN_STEP_PLAN_CN_BASE_URL)
+        status = get_api_key_provider_status("stepfun")
+        assert status["configured"] is True
+        assert status["base_url"] == STEPFUN_STEP_PLAN_CN_BASE_URL
+
     def test_copilot_status_uses_gh_cli_token(self, monkeypatch):
         monkeypatch.setattr("hermes_cli.copilot_auth._try_gh_cli_token", lambda: "gho_gh_cli_token")
         status = get_api_key_provider_status("copilot")
@@ -425,6 +456,19 @@ class TestResolveApiKeyProviderCredentials:
         assert creds["api_key"] == "kimi-secret-key"
         assert creds["base_url"] == "https://api.moonshot.ai/v1"
 
+    def test_resolve_stepfun_with_key(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-secret-key")
+        creds = resolve_api_key_provider_credentials("stepfun")
+        assert creds["provider"] == "stepfun"
+        assert creds["api_key"] == "stepfun-secret-key"
+        assert creds["base_url"] == STEPFUN_STEP_PLAN_INTL_BASE_URL
+
+    def test_resolve_stepfun_custom_base_url(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-secret-key")
+        monkeypatch.setenv("STEPFUN_BASE_URL", STEPFUN_STEP_PLAN_CN_BASE_URL)
+        creds = resolve_api_key_provider_credentials("stepfun")
+        assert creds["base_url"] == STEPFUN_STEP_PLAN_CN_BASE_URL
+
     def test_resolve_minimax_with_key(self, monkeypatch):
         monkeypatch.setenv("MINIMAX_API_KEY", "mm-secret-key")
         creds = resolve_api_key_provider_credentials("minimax")
@@ -515,6 +559,16 @@ class TestRuntimeProviderResolution:
         assert result["api_mode"] == "chat_completions"
         assert result["api_key"] == "kimi-key"
 
+    def test_runtime_stepfun(self, monkeypatch):
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-key")
+        monkeypatch.setenv("STEPFUN_BASE_URL", STEPFUN_STEP_PLAN_CN_BASE_URL)
+        from hermes_cli.runtime_provider import resolve_runtime_provider
+        result = resolve_runtime_provider(requested="stepfun")
+        assert result["provider"] == "stepfun"
+        assert result["api_mode"] == "chat_completions"
+        assert result["api_key"] == "stepfun-key"
+        assert result["base_url"] == STEPFUN_STEP_PLAN_CN_BASE_URL
+
     def test_runtime_minimax(self, monkeypatch):
         monkeypatch.setenv("MINIMAX_API_KEY", "mm-key")
         from hermes_cli.runtime_provider import resolve_runtime_provider

tests/hermes_cli/test_at_context_completion_filter.py

@@ -0,0 +1,90 @@
+"""Regression test: `@folder:` completion must only surface directories and
+`@file:` must only surface regular files.
+
+Reported during TUI v2 blitz testing: typing `@folder:` showed .dockerignore,
+.env, .gitignore, etc. alongside the actual directories because the path-
+completion branch yielded every entry regardless of the explicit prefix, and
+auto-switched the completion kind based on `is_dir`. That defeated the user's
+explicit choice and rendered the `@folder:` / `@file:` prefixes useless for
+filtering.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Iterable
+
+from hermes_cli.commands import SlashCommandCompleter
+
+
+def _run(tmp_path: Path, word: str) -> list[tuple[str, str]]:
+    (tmp_path / "readme.md").write_text("x")
+    (tmp_path / ".env").write_text("x")
+    (tmp_path / "src").mkdir()
+    (tmp_path / "docs").mkdir()
+
+    completer = SlashCommandCompleter.__new__(SlashCommandCompleter)
+    completions: Iterable = completer._context_completions(word)
+
+    return [(c.text, c.display_meta) for c in completions if c.text.startswith(("@file:", "@folder:"))]
+
+
+def test_at_folder_only_yields_directories(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+
+    texts = [t for t, _ in _run(tmp_path, "@folder:")]
+
+    assert all(t.startswith("@folder:") for t in texts), texts
+    assert any(t == "@folder:src/" for t in texts)
+    assert any(t == "@folder:docs/" for t in texts)
+    assert not any(t == "@folder:readme.md" for t in texts)
+    assert not any(t == "@folder:.env" for t in texts)
+
+
+def test_at_file_only_yields_files(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+
+    texts = [t for t, _ in _run(tmp_path, "@file:")]
+
+    assert all(t.startswith("@file:") for t in texts), texts
+    assert any(t == "@file:readme.md" for t in texts)
+    assert any(t == "@file:.env" for t in texts)
+    assert not any(t == "@file:src/" for t in texts)
+    assert not any(t == "@file:docs/" for t in texts)
+
+
+def test_at_folder_preserves_prefix_on_empty_match(tmp_path, monkeypatch):
+    """User typed `@folder:` (no partial) — completion text must keep the
+    `@folder:` prefix even though the previous implementation auto-rewrote
+    it to `@file:` for non-dir entries.
+    """
+    monkeypatch.chdir(tmp_path)
+
+    texts = [t for t, _ in _run(tmp_path, "@folder:")]
+
+    assert texts, "expected at least one directory completion"
+    for t in texts:
+        assert t.startswith("@folder:"), f"prefix leaked: {t}"
+
+
+def test_at_folder_bare_without_colon_lists_directories(tmp_path, monkeypatch):
+    """Typing `@folder` alone (no colon yet) should surface directories so
+    users don't need to first accept the static `@folder:` hint before
+    seeing what they're picking from.
+    """
+    monkeypatch.chdir(tmp_path)
+
+    texts = [t for t, _ in _run(tmp_path, "@folder")]
+
+    assert any(t == "@folder:src/" for t in texts), texts
+    assert any(t == "@folder:docs/" for t in texts), texts
+    assert not any(t == "@folder:readme.md" for t in texts)
+
+
+def test_at_file_bare_without_colon_lists_files(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+
+    texts = [t for t, _ in _run(tmp_path, "@file")]
+
+    assert any(t == "@file:readme.md" for t in texts), texts
+    assert not any(t == "@file:src/" for t in texts)

tests/hermes_cli/test_auth_commands.py

@@ -1011,3 +1011,466 @@ def test_seed_from_singletons_respects_codex_suppression(tmp_path, monkeypatch):
     # Verify the auth store was NOT modified (no auto-import happened)
     after = json.loads((hermes_home / "auth.json").read_text())
     assert "openai-codex" not in after.get("providers", {})
+
+
+def test_auth_remove_env_seeded_suppresses_shell_exported_var(tmp_path, monkeypatch, capsys):
+    """`hermes auth remove xai 1` must stick even when the env var is exported
+    by the shell (not written into ~/.hermes/.env).  Before PR for #13371 the
+    removal silently restored on next load_pool() because _seed_from_env()
+    re-read os.environ.  Now env:<VAR> is suppressed in auth.json.
+    """
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    # Simulate shell export (NOT written to .env)
+    monkeypatch.setenv("XAI_API_KEY", "sk-xai-shell-export")
+    (hermes_home / ".env").write_text("")
+
+    _write_auth_store(
+        tmp_path,
+        {
+            "version": 1,
+            "credential_pool": {
+                "xai": [{
+                    "id": "env-1",
+                    "label": "XAI_API_KEY",
+                    "auth_type": "api_key",
+                    "priority": 0,
+                    "source": "env:XAI_API_KEY",
+                    "access_token": "sk-xai-shell-export",
+                    "base_url": "https://api.x.ai/v1",
+                }]
+            },
+        },
+    )
+
+    from types import SimpleNamespace
+    from hermes_cli.auth_commands import auth_remove_command
+    auth_remove_command(SimpleNamespace(provider="xai", target="1"))
+
+    # Suppression marker written
+    after = json.loads((hermes_home / "auth.json").read_text())
+    assert "env:XAI_API_KEY" in after.get("suppressed_sources", {}).get("xai", [])
+
+    # Diagnostic printed pointing at the shell
+    out = capsys.readouterr().out
+    assert "still set in your shell environment" in out
+    assert "Cleared XAI_API_KEY from .env" not in out  # wasn't in .env
+
+    # Fresh simulation: shell re-exports, reload pool
+    monkeypatch.setenv("XAI_API_KEY", "sk-xai-shell-export")
+    from agent.credential_pool import load_pool
+    pool = load_pool("xai")
+    assert not pool.has_credentials(), "pool must stay empty — env:XAI_API_KEY suppressed"
+
+
+def test_auth_remove_env_seeded_dotenv_only_no_shell_hint(tmp_path, monkeypatch, capsys):
+    """When the env var lives only in ~/.hermes/.env (not the shell), the
+    shell-hint should NOT be printed — avoid scaring the user about a
+    non-existent shell export.
+    """
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    # Key ONLY in .env, shell must not have it
+    monkeypatch.delenv("DEEPSEEK_API_KEY", raising=False)
+    (hermes_home / ".env").write_text("DEEPSEEK_API_KEY=sk-ds-only\n")
+    # Mimic load_env() populating os.environ
+    monkeypatch.setenv("DEEPSEEK_API_KEY", "sk-ds-only")
+
+    _write_auth_store(
+        tmp_path,
+        {
+            "version": 1,
+            "credential_pool": {
+                "deepseek": [{
+                    "id": "env-1",
+                    "label": "DEEPSEEK_API_KEY",
+                    "auth_type": "api_key",
+                    "priority": 0,
+                    "source": "env:DEEPSEEK_API_KEY",
+                    "access_token": "sk-ds-only",
+                }]
+            },
+        },
+    )
+
+    from types import SimpleNamespace
+    from hermes_cli.auth_commands import auth_remove_command
+    auth_remove_command(SimpleNamespace(provider="deepseek", target="1"))
+
+    out = capsys.readouterr().out
+    assert "Cleared DEEPSEEK_API_KEY from .env" in out
+    assert "still set in your shell environment" not in out
+    assert (hermes_home / ".env").read_text().strip() == ""
+
+
+def test_auth_add_clears_env_suppression_for_provider(tmp_path, monkeypatch):
+    """Re-adding a credential via `hermes auth add <provider>` clears any
+    env:<VAR> suppression marker — strong signal the user wants auth back.
+    Matches the Codex device_code re-link behaviour.
+    """
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+    monkeypatch.delenv("XAI_API_KEY", raising=False)
+
+    _write_auth_store(
+        tmp_path,
+        {
+            "version": 1,
+            "providers": {},
+            "suppressed_sources": {"xai": ["env:XAI_API_KEY"]},
+        },
+    )
+
+    from types import SimpleNamespace
+    from hermes_cli.auth import is_source_suppressed
+    from hermes_cli.auth_commands import auth_add_command
+
+    assert is_source_suppressed("xai", "env:XAI_API_KEY") is True
+    auth_add_command(SimpleNamespace(
+        provider="xai", auth_type="api_key",
+        api_key="sk-xai-manual", label="manual",
+    ))
+    assert is_source_suppressed("xai", "env:XAI_API_KEY") is False
+
+
+def test_seed_from_env_respects_env_suppression(tmp_path, monkeypatch):
+    """_seed_from_env() must skip env:<VAR> sources that the user suppressed
+    via `hermes auth remove`.  This is the gate that prevents shell-exported
+    keys from resurrecting removed credentials.
+    """
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+    monkeypatch.setenv("XAI_API_KEY", "sk-xai-shell-export")
+
+    (hermes_home / "auth.json").write_text(json.dumps({
+        "version": 1,
+        "providers": {},
+        "suppressed_sources": {"xai": ["env:XAI_API_KEY"]},
+    }))
+
+    from agent.credential_pool import _seed_from_env
+
+    entries = []
+    changed, active = _seed_from_env("xai", entries)
+    assert changed is False
+    assert entries == []
+    assert active == set()
+
+
+def test_seed_from_env_respects_openrouter_suppression(tmp_path, monkeypatch):
+    """OpenRouter is the special-case branch in _seed_from_env; verify it
+    honours suppression too.
+    """
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+    monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-shell-export")
+
+    (hermes_home / "auth.json").write_text(json.dumps({
+        "version": 1,
+        "providers": {},
+        "suppressed_sources": {"openrouter": ["env:OPENROUTER_API_KEY"]},
+    }))
+
+    from agent.credential_pool import _seed_from_env
+
+    entries = []
+    changed, active = _seed_from_env("openrouter", entries)
+    assert changed is False
+    assert entries == []
+    assert active == set()
+
+
+# =============================================================================
+# Unified credential-source stickiness — every source Hermes reads from has a
+# registered RemovalStep in agent.credential_sources, and every seeding path
+# gates on is_source_suppressed.  Below: one test per source proving remove
+# sticks across a fresh load_pool() call.
+# =============================================================================
+
+
+def test_seed_from_singletons_respects_nous_suppression(tmp_path, monkeypatch):
+    """nous device_code must not re-seed from auth.json when suppressed."""
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    (hermes_home / "auth.json").write_text(json.dumps({
+        "version": 1,
+        "providers": {"nous": {"access_token": "tok", "refresh_token": "r", "expires_at": 9999999999}},
+        "suppressed_sources": {"nous": ["device_code"]},
+    }))
+
+    from agent.credential_pool import _seed_from_singletons
+    entries = []
+    changed, active = _seed_from_singletons("nous", entries)
+    assert changed is False
+    assert entries == []
+    assert active == set()
+
+
+def test_seed_from_singletons_respects_copilot_suppression(tmp_path, monkeypatch):
+    """copilot gh_cli must not re-seed when suppressed."""
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    (hermes_home / "auth.json").write_text(json.dumps({
+        "version": 1,
+        "providers": {},
+        "suppressed_sources": {"copilot": ["gh_cli"]},
+    }))
+
+    # Stub resolve_copilot_token to return a live token
+    import hermes_cli.copilot_auth as ca
+    monkeypatch.setattr(ca, "resolve_copilot_token", lambda: ("ghp_fake", "gh auth token"))
+
+    from agent.credential_pool import _seed_from_singletons
+    entries = []
+    changed, active = _seed_from_singletons("copilot", entries)
+    assert changed is False
+    assert entries == []
+    assert active == set()
+
+
+def test_seed_from_singletons_respects_qwen_suppression(tmp_path, monkeypatch):
+    """qwen-oauth qwen-cli must not re-seed from ~/.qwen/oauth_creds.json when suppressed."""
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    (hermes_home / "auth.json").write_text(json.dumps({
+        "version": 1,
+        "providers": {},
+        "suppressed_sources": {"qwen-oauth": ["qwen-cli"]},
+    }))
+
+    import hermes_cli.auth as ha
+    monkeypatch.setattr(ha, "resolve_qwen_runtime_credentials", lambda **kw: {
+        "api_key": "tok", "source": "qwen-cli", "base_url": "https://q",
+    })
+
+    from agent.credential_pool import _seed_from_singletons
+    entries = []
+    changed, active = _seed_from_singletons("qwen-oauth", entries)
+    assert changed is False
+    assert entries == []
+    assert active == set()
+
+
+def test_seed_from_singletons_respects_hermes_pkce_suppression(tmp_path, monkeypatch):
+    """anthropic hermes_pkce must not re-seed from ~/.hermes/.anthropic_oauth.json when suppressed."""
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    import yaml
+    (hermes_home / "config.yaml").write_text(yaml.dump({"model": {"provider": "anthropic", "model": "claude"}}))
+    (hermes_home / "auth.json").write_text(json.dumps({
+        "version": 1,
+        "providers": {},
+        "suppressed_sources": {"anthropic": ["hermes_pkce"]},
+    }))
+
+    # Stub the readers so only hermes_pkce is "available"; claude_code returns None
+    import agent.anthropic_adapter as aa
+    monkeypatch.setattr(aa, "read_hermes_oauth_credentials", lambda: {
+        "accessToken": "tok", "refreshToken": "r", "expiresAt": 9999999999000,
+    })
+    monkeypatch.setattr(aa, "read_claude_code_credentials", lambda: None)
+
+    from agent.credential_pool import _seed_from_singletons
+    entries = []
+    changed, active = _seed_from_singletons("anthropic", entries)
+    # hermes_pkce suppressed, claude_code returns None → nothing should be seeded
+    assert entries == []
+    assert "hermes_pkce" not in active
+
+
+def test_seed_custom_pool_respects_config_suppression(tmp_path, monkeypatch):
+    """Custom provider config:<name> source must not re-seed when suppressed."""
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    import yaml
+    (hermes_home / "config.yaml").write_text(yaml.dump({
+        "model": {},
+        "custom_providers": [
+            {"name": "my", "base_url": "https://c.example.com", "api_key": "sk-custom"},
+        ],
+    }))
+
+    from agent.credential_pool import _seed_custom_pool, get_custom_provider_pool_key
+    pool_key = get_custom_provider_pool_key("https://c.example.com")
+
+    (hermes_home / "auth.json").write_text(json.dumps({
+        "version": 1,
+        "providers": {},
+        "suppressed_sources": {pool_key: ["config:my"]},
+    }))
+
+    entries = []
+    changed, active = _seed_custom_pool(pool_key, entries)
+    assert changed is False
+    assert entries == []
+    assert "config:my" not in active
+
+
+def test_credential_sources_registry_has_expected_steps():
+    """Sanity check — the registry contains the expected RemovalSteps.
+
+    Guards against accidentally dropping a step during future refactors.
+    If you add a new credential source, add it to the expected set below.
+    """
+    from agent.credential_sources import _REGISTRY
+
+    descriptions = {step.description for step in _REGISTRY}
+    expected = {
+        "gh auth token / COPILOT_GITHUB_TOKEN / GH_TOKEN",
+        "Any env-seeded credential (XAI_API_KEY, DEEPSEEK_API_KEY, etc.)",
+        "~/.claude/.credentials.json",
+        "~/.hermes/.anthropic_oauth.json",
+        "auth.json providers.nous",
+        "auth.json providers.openai-codex + ~/.codex/auth.json",
+        "~/.qwen/oauth_creds.json",
+        "Custom provider config.yaml api_key field",
+    }
+    assert descriptions == expected, f"Registry mismatch. Got: {descriptions}"
+
+
+def test_credential_sources_find_step_returns_none_for_manual():
+    """Manual entries have nothing external to clean up — no step registered."""
+    from agent.credential_sources import find_removal_step
+    assert find_removal_step("openrouter", "manual") is None
+    assert find_removal_step("xai", "manual") is None
+
+
+def test_credential_sources_find_step_copilot_before_generic_env(tmp_path, monkeypatch):
+    """copilot env:GH_TOKEN must dispatch to the copilot step, not the
+    generic env-var step.  The copilot step handles the duplicate-source
+    problem (same token seeded as both gh_cli and env:<VAR>); the generic
+    env step would only suppress one of the variants.
+    """
+    from agent.credential_sources import find_removal_step
+
+    step = find_removal_step("copilot", "env:GH_TOKEN")
+    assert step is not None
+    assert "copilot" in step.description.lower() or "gh" in step.description.lower()
+
+    # Generic step still matches any other provider's env var
+    step = find_removal_step("xai", "env:XAI_API_KEY")
+    assert step is not None
+    assert "env-seeded" in step.description.lower()
+
+
+def test_auth_remove_copilot_suppresses_all_variants(tmp_path, monkeypatch):
+    """Removing any copilot source must suppress gh_cli + all env:* variants
+    so the duplicate-seed paths don't resurrect the credential.
+    """
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    _write_auth_store(
+        tmp_path,
+        {
+            "version": 1,
+            "credential_pool": {
+                "copilot": [{
+                    "id": "c1",
+                    "label": "gh auth token",
+                    "auth_type": "api_key",
+                    "priority": 0,
+                    "source": "gh_cli",
+                    "access_token": "ghp_fake",
+                }]
+            },
+        },
+    )
+
+    from types import SimpleNamespace
+    from hermes_cli.auth import is_source_suppressed
+    from hermes_cli.auth_commands import auth_remove_command
+
+    auth_remove_command(SimpleNamespace(provider="copilot", target="1"))
+
+    assert is_source_suppressed("copilot", "gh_cli")
+    assert is_source_suppressed("copilot", "env:COPILOT_GITHUB_TOKEN")
+    assert is_source_suppressed("copilot", "env:GH_TOKEN")
+    assert is_source_suppressed("copilot", "env:GITHUB_TOKEN")
+
+
+def test_auth_add_clears_all_suppressions_including_non_env(tmp_path, monkeypatch):
+    """Re-adding a credential via `hermes auth add <provider>` clears ALL
+    suppression markers for the provider, not just env:*.  This matches
+    the single "re-engage" semantic — the user wants auth back, period.
+    """
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    _write_auth_store(
+        tmp_path,
+        {
+            "version": 1,
+            "providers": {},
+            "suppressed_sources": {
+                "copilot": ["gh_cli", "env:GH_TOKEN", "env:COPILOT_GITHUB_TOKEN"],
+            },
+        },
+    )
+
+    from types import SimpleNamespace
+    from hermes_cli.auth import is_source_suppressed
+    from hermes_cli.auth_commands import auth_add_command
+
+    auth_add_command(SimpleNamespace(
+        provider="copilot", auth_type="api_key",
+        api_key="ghp-manual", label="m",
+    ))
+
+    assert not is_source_suppressed("copilot", "gh_cli")
+    assert not is_source_suppressed("copilot", "env:GH_TOKEN")
+    assert not is_source_suppressed("copilot", "env:COPILOT_GITHUB_TOKEN")
+
+
+def test_auth_remove_codex_manual_device_code_suppresses_canonical(tmp_path, monkeypatch):
+    """Removing a manual:device_code entry (from `hermes auth add openai-codex`)
+    must suppress the canonical ``device_code`` key, not ``manual:device_code``.
+    The re-seed gate in _seed_from_singletons checks ``device_code``.
+    """
+    hermes_home = tmp_path / "hermes"
+    hermes_home.mkdir(parents=True, exist_ok=True)
+    monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+    _write_auth_store(
+        tmp_path,
+        {
+            "version": 1,
+            "providers": {"openai-codex": {"tokens": {"access_token": "t", "refresh_token": "r"}}},
+            "credential_pool": {
+                "openai-codex": [{
+                    "id": "cdx",
+                    "label": "manual-codex",
+                    "auth_type": "oauth",
+                    "priority": 0,
+                    "source": "manual:device_code",
+                    "access_token": "t",
+                }]
+            },
+        },
+    )
+
+    from types import SimpleNamespace
+    from hermes_cli.auth import is_source_suppressed
+    from hermes_cli.auth_commands import auth_remove_command
+
+    auth_remove_command(SimpleNamespace(provider="openai-codex", target="1"))
+    assert is_source_suppressed("openai-codex", "device_code")

tests/hermes_cli/test_auth_nous_provider.py

@@ -376,7 +376,6 @@ class TestLoginNousSkipKeepsCurrent:
             lambda *a, **kw: prompt_returns,
         )
         monkeypatch.setattr(models_mod, "get_pricing_for_provider", lambda p: {})
-        monkeypatch.setattr(models_mod, "filter_nous_free_models", lambda ids, p: ids)
         monkeypatch.setattr(models_mod, "check_nous_free_tier", lambda: None)
         monkeypatch.setattr(
             models_mod, "partition_nous_models_by_tier",

tests/hermes_cli/test_commands.py

@@ -1208,3 +1208,119 @@ class TestDiscordSkillCommandsByCategory:
         assert "axolotl" in names
         assert "vllm" in names
         assert len(uncategorized) == 0
+
+
+# ---------------------------------------------------------------------------
+# Plugin slash command integration
+# ---------------------------------------------------------------------------
+
+class TestPluginCommandEnumeration:
+    """Plugin commands registered via ctx.register_command() must be surfaced
+    by every gateway enumerator (Telegram menu, Slack subcommand map, etc.).
+    """
+
+    def _patch_plugin_commands(self, monkeypatch, commands):
+        """Monkeypatch hermes_cli.plugins.get_plugin_commands() to a fixed dict."""
+        from hermes_cli import plugins as _plugins_mod
+
+        monkeypatch.setattr(
+            _plugins_mod, "get_plugin_commands", lambda: dict(commands)
+        )
+
+    def test_plugin_command_appears_in_telegram_menu(self, monkeypatch):
+        """/metricas registered by a plugin must appear in Telegram BotCommand menu."""
+        self._patch_plugin_commands(monkeypatch, {
+            "metricas": {
+                "handler": lambda _a: "ok",
+                "description": "Metrics dashboard",
+                "args_hint": "dias:7",
+                "plugin": "metrics-plugin",
+            }
+        })
+        names = {name for name, _desc in telegram_bot_commands()}
+        assert "metricas" in names
+
+    def test_plugin_command_appears_in_slack_subcommand_map(self, monkeypatch):
+        """/hermes metricas must route through the Slack subcommand map."""
+        self._patch_plugin_commands(monkeypatch, {
+            "metricas": {
+                "handler": lambda _a: "ok",
+                "description": "Metrics",
+                "args_hint": "",
+                "plugin": "metrics-plugin",
+            }
+        })
+        mapping = slack_subcommand_map()
+        assert mapping.get("metricas") == "/metricas"
+
+    def test_plugin_command_does_not_shadow_builtin_in_slack(self, monkeypatch):
+        """If a plugin registers a name that collides with a built-in, the built-in mapping wins."""
+        self._patch_plugin_commands(monkeypatch, {
+            "status": {
+                "handler": lambda _a: "plugin-status",
+                "description": "Plugin status",
+                "args_hint": "",
+                "plugin": "shadow-plugin",
+            }
+        })
+        mapping = slack_subcommand_map()
+        # Built-in /status must still be present and not overwritten.
+        assert mapping.get("status") == "/status"
+
+    def test_plugin_command_with_hyphens_sanitized_for_telegram(self, monkeypatch):
+        """Plugin names containing hyphens must be underscore-normalized for Telegram."""
+        self._patch_plugin_commands(monkeypatch, {
+            "my-plugin-cmd": {
+                "handler": lambda _a: "ok",
+                "description": "desc",
+                "args_hint": "",
+                "plugin": "p",
+            }
+        })
+        names = {name for name, _desc in telegram_bot_commands()}
+        assert "my_plugin_cmd" in names
+        assert "my-plugin-cmd" not in names
+
+    def test_is_gateway_known_command_recognizes_plugin_commands(self, monkeypatch):
+        """is_gateway_known_command() must return True for plugin commands."""
+        from hermes_cli.commands import is_gateway_known_command
+
+        self._patch_plugin_commands(monkeypatch, {
+            "metricas": {
+                "handler": lambda _a: "ok",
+                "description": "Metrics",
+                "args_hint": "",
+                "plugin": "p",
+            }
+        })
+        assert is_gateway_known_command("metricas") is True
+        assert is_gateway_known_command("definitely-not-registered") is False
+
+    def test_is_gateway_known_command_still_recognizes_builtins(self, monkeypatch):
+        """Built-in commands must remain known even when plugin discovery fails."""
+        from hermes_cli import plugins as _plugins_mod
+        from hermes_cli.commands import is_gateway_known_command
+
+        def _boom():
+            raise RuntimeError("plugin system down")
+
+        monkeypatch.setattr(_plugins_mod, "get_plugin_commands", _boom)
+
+        assert is_gateway_known_command("status") is True
+        assert is_gateway_known_command(None) is False
+        assert is_gateway_known_command("") is False
+
+    def test_plugin_enumerator_handles_missing_plugin_manager(self, monkeypatch):
+        """Enumerators must never raise when plugin discovery raises."""
+        from hermes_cli import plugins as _plugins_mod
+
+        def _boom():
+            raise RuntimeError("plugin system down")
+
+        monkeypatch.setattr(_plugins_mod, "get_plugin_commands", _boom)
+
+        # Both calls should succeed and just return the built-in set.
+        tg_names = {name for name, _desc in telegram_bot_commands()}
+        slack_names = set(slack_subcommand_map())
+        assert "status" in tg_names
+        assert "status" in slack_names

tests/hermes_cli/test_config_drift.py

@@ -0,0 +1,36 @@
+"""Regression tests for removed dead config keys.
+
+This file guards against accidental re-introduction of config keys that were
+documented or declared at some point but never actually wired up to read code.
+Future dead-config regressions can accumulate here.
+"""
+
+import inspect
+
+
+def test_delegation_default_toolsets_removed_from_cli_config():
+    """delegation.default_toolsets was dead config — never read by
+    _load_config() or anywhere else. Removed.
+
+    Guards against accidental re-introduction in cli.py's CLI_CONFIG default
+    dict. If this test fails, someone re-added the key without wiring it up
+    to _load_config() in tools/delegate_tool.py.
+
+    We inspect the source of load_cli_config() instead of asserting on the
+    runtime CLI_CONFIG dict because CLI_CONFIG is populated by deep-merging
+    the user's ~/.hermes/config.yaml over the defaults (cli.py:359-366).
+    A contributor who still has the legacy key set in their own config
+    would cause a false failure, and HERMES_HOME patching via conftest
+    doesn't help because cli._hermes_home is frozen at module import time
+    (cli.py:76) — before any autouse fixture can fire. Source inspection
+    sidesteps all of that: it tests the defaults literal directly.
+    """
+    from cli import load_cli_config
+
+    source = inspect.getsource(load_cli_config)
+    assert '"default_toolsets"' not in source, (
+        "delegation.default_toolsets was removed because it was never read. "
+        "Do not re-add it to cli.py's CLI_CONFIG default dict; "
+        "use tools/delegate_tool.py's DEFAULT_TOOLSETS module constant or "
+        "wire a new config key through _load_config()."
+    )

tests/hermes_cli/test_debug.py

@@ -137,50 +137,105 @@ class TestUploadToPastebin:
 # Log reading
 # ---------------------------------------------------------------------------
 
-class TestReadFullLog:
-    """Test _read_full_log for standalone log uploads."""
+class TestCaptureLogSnapshot:
+    """Test _capture_log_snapshot for log reading and truncation."""
 
     def test_reads_small_file(self, hermes_home):
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
-        content = _read_full_log("agent")
-        assert content is not None
-        assert "session started" in content
+        snap = _capture_log_snapshot("agent", tail_lines=10)
+        assert snap.full_text is not None
+        assert "session started" in snap.full_text
+        assert "session started" in snap.tail_text
 
     def test_returns_none_for_missing(self, tmp_path, monkeypatch):
         home = tmp_path / ".hermes"
         home.mkdir()
         monkeypatch.setenv("HERMES_HOME", str(home))
 
-        from hermes_cli.debug import _read_full_log
-        assert _read_full_log("agent") is None
+        from hermes_cli.debug import _capture_log_snapshot
+        snap = _capture_log_snapshot("agent", tail_lines=10)
+        assert snap.full_text is None
+        assert snap.tail_text == "(file not found)"
 
-    def test_returns_none_for_empty(self, hermes_home):
-        # Truncate agent.log to empty
+    def test_empty_primary_reports_file_empty(self, hermes_home):
+        """Empty primary (no .1 fallback) surfaces as '(file empty)', not missing."""
         (hermes_home / "logs" / "agent.log").write_text("")
 
-        from hermes_cli.debug import _read_full_log
-        assert _read_full_log("agent") is None
+        from hermes_cli.debug import _capture_log_snapshot
+        snap = _capture_log_snapshot("agent", tail_lines=10)
+        assert snap.full_text is None
+        assert snap.tail_text == "(file empty)"
+
+    def test_race_truncate_after_resolve_reports_empty(self, hermes_home, monkeypatch):
+        """If the log is truncated between resolve and stat, say 'empty', not 'missing'."""
+        log_path = hermes_home / "logs" / "agent.log"
+        from hermes_cli import debug
+
+        monkeypatch.setattr(debug, "_resolve_log_path", lambda _name: log_path)
+        log_path.write_text("")
+
+        snap = debug._capture_log_snapshot("agent", tail_lines=10)
+        assert snap.path == log_path
+        assert snap.full_text is None
+        assert snap.tail_text == "(file empty)"
 
     def test_truncates_large_file(self, hermes_home):
         """Files larger than max_bytes get tail-truncated."""
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
         # Write a file larger than 1KB
         big_content = "x" * 100 + "\n"
         (hermes_home / "logs" / "agent.log").write_text(big_content * 200)
 
-        content = _read_full_log("agent", max_bytes=1024)
-        assert content is not None
-        assert "truncated" in content
+        snap = _capture_log_snapshot("agent", tail_lines=10, max_bytes=1024)
+        assert snap.full_text is not None
+        assert "truncated" in snap.full_text
+
+    def test_keeps_first_line_when_truncation_on_boundary(self, hermes_home):
+        """When truncation lands on a line boundary, keep the first full line."""
+        from hermes_cli.debug import _capture_log_snapshot
+
+        # File must exceed the initial chunk_size (8192) used by the
+        # backward-reading loop so the truncation path actually fires.
+        line = "A" * 99 + "\n"  # 100 bytes per line
+        num_lines = 200  # 20000 bytes
+        (hermes_home / "logs" / "agent.log").write_text(line * num_lines)
+
+        # max_bytes = 1000 = 100 * 10 → cut at byte 20000 - 1000 = 19000,
+        # and byte 19000 - 1 is '\n'.  Boundary hit → keep all 10 lines.
+        snap = _capture_log_snapshot("agent", tail_lines=5, max_bytes=1000)
+        assert snap.full_text is not None
+        assert "truncated" in snap.full_text
+        raw = snap.full_text.split("\n", 1)[1]
+        kept = [l for l in raw.strip().splitlines() if l.startswith("A")]
+        assert len(kept) == 10
+
+    def test_drops_partial_when_truncation_mid_line(self, hermes_home):
+        """When truncation lands mid-line, drop the partial fragment."""
+        from hermes_cli.debug import _capture_log_snapshot
+
+        line = "A" * 99 + "\n"  # 100 bytes per line
+        num_lines = 200  # 20000 bytes
+        (hermes_home / "logs" / "agent.log").write_text(line * num_lines)
+
+        # max_bytes = 950 doesn't divide evenly into 100 → mid-line cut.
+        snap = _capture_log_snapshot("agent", tail_lines=5, max_bytes=950)
+        assert snap.full_text is not None
+        assert "truncated" in snap.full_text
+        raw = snap.full_text.split("\n", 1)[1]
+        kept = [l for l in raw.strip().splitlines() if l.startswith("A")]
+        # 950 / 100 = 9.5 → 9 complete lines after dropping partial
+        assert len(kept) == 9
 
     def test_unknown_log_returns_none(self, hermes_home):
-        from hermes_cli.debug import _read_full_log
-        assert _read_full_log("nonexistent") is None
+        from hermes_cli.debug import _capture_log_snapshot
+        snap = _capture_log_snapshot("nonexistent", tail_lines=10)
+        assert snap.full_text is None
 
     def test_falls_back_to_rotated_file(self, hermes_home):
         """When gateway.log doesn't exist, falls back to gateway.log.1."""
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
         logs_dir = hermes_home / "logs"
         # Remove the primary (if any) and create a .1 rotation
@@ -189,33 +244,33 @@ class TestReadFullLog:
             "2026-04-12 10:00:00 INFO gateway.run: rotated content\n"
         )
 
-        content = _read_full_log("gateway")
-        assert content is not None
-        assert "rotated content" in content
+        snap = _capture_log_snapshot("gateway", tail_lines=10)
+        assert snap.full_text is not None
+        assert "rotated content" in snap.full_text
 
     def test_prefers_primary_over_rotated(self, hermes_home):
         """Primary log is used when it exists, even if .1 also exists."""
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
         logs_dir = hermes_home / "logs"
         (logs_dir / "gateway.log").write_text("primary content\n")
         (logs_dir / "gateway.log.1").write_text("rotated content\n")
 
-        content = _read_full_log("gateway")
-        assert "primary content" in content
-        assert "rotated" not in content
+        snap = _capture_log_snapshot("gateway", tail_lines=10)
+        assert "primary content" in snap.full_text
+        assert "rotated" not in snap.full_text
 
     def test_falls_back_when_primary_empty(self, hermes_home):
         """Empty primary log falls back to .1 rotation."""
-        from hermes_cli.debug import _read_full_log
+        from hermes_cli.debug import _capture_log_snapshot
 
         logs_dir = hermes_home / "logs"
         (logs_dir / "agent.log").write_text("")
         (logs_dir / "agent.log.1").write_text("rotated agent data\n")
 
-        content = _read_full_log("agent")
-        assert content is not None
-        assert "rotated agent data" in content
+        snap = _capture_log_snapshot("agent", tail_lines=10)
+        assert snap.full_text is not None
+        assert "rotated agent data" in snap.full_text
 
 
 # ---------------------------------------------------------------------------
@@ -283,6 +338,44 @@ class TestCollectDebugReport:
 class TestRunDebugShare:
     """Test the run_debug_share CLI handler."""
 
+    def test_share_sweeps_expired_pastes(self, hermes_home, capsys):
+        """Slash-command path should sweep old pending deletes before uploading."""
+        from hermes_cli.debug import run_debug_share
+
+        args = MagicMock()
+        args.lines = 50
+        args.expire = 7
+        args.local = False
+
+        with patch("hermes_cli.dump.run_dump"), \
+             patch("hermes_cli.debug._sweep_expired_pastes", return_value=(0, 0)) as mock_sweep, \
+             patch("hermes_cli.debug.upload_to_pastebin",
+                    return_value="https://paste.rs/test"):
+            run_debug_share(args)
+
+        mock_sweep.assert_called_once()
+        assert "Debug report uploaded" in capsys.readouterr().out
+
+    def test_share_survives_sweep_failure(self, hermes_home, capsys):
+        """Expired-paste cleanup is best-effort and must not block sharing."""
+        from hermes_cli.debug import run_debug_share
+
+        args = MagicMock()
+        args.lines = 50
+        args.expire = 7
+        args.local = False
+
+        with patch("hermes_cli.dump.run_dump"), \
+             patch(
+                 "hermes_cli.debug._sweep_expired_pastes",
+                 side_effect=RuntimeError("offline"),
+             ), \
+             patch("hermes_cli.debug.upload_to_pastebin",
+                    return_value="https://paste.rs/test"):
+            run_debug_share(args)
+
+        assert "https://paste.rs/test" in capsys.readouterr().out
+
     def test_local_flag_prints_full_logs(self, hermes_home, capsys):
         """--local prints the report plus full log contents."""
         from hermes_cli.debug import run_debug_share
@@ -340,6 +433,55 @@ class TestRunDebugShare:
         assert "--- hermes dump ---" in gateway_paste
         assert "--- full gateway.log ---" in gateway_paste
 
+    def test_share_keeps_report_and_full_log_on_same_snapshot(self, hermes_home, capsys):
+        """A mid-run rotation must not make full agent.log older than the report."""
+        from hermes_cli.debug import run_debug_share, collect_debug_report as real_collect_debug_report
+
+        logs_dir = hermes_home / "logs"
+        (logs_dir / "agent.log").write_text(
+            "2026-04-22 12:00:00 INFO agent: newest line\n"
+        )
+        (logs_dir / "agent.log.1").write_text(
+            "2026-04-10 12:00:00 INFO agent: old rotated line\n"
+        )
+
+        args = MagicMock()
+        args.lines = 50
+        args.expire = 7
+        args.local = False
+
+        uploaded_content = []
+
+        def _mock_upload(content, expiry_days=7):
+            uploaded_content.append(content)
+            return f"https://paste.rs/paste{len(uploaded_content)}"
+
+        def _wrapped_collect_debug_report(*, log_lines=200, dump_text="", log_snapshots=None):
+            report = real_collect_debug_report(
+                log_lines=log_lines,
+                dump_text=dump_text,
+                log_snapshots=log_snapshots,
+            )
+            # Simulate the live log rotating after the report is built but
+            # before the old implementation would have re-read agent.log for
+            # standalone upload.
+            (logs_dir / "agent.log").write_text("")
+            (logs_dir / "agent.log.1").write_text(
+                "2026-04-10 12:00:00 INFO agent: old rotated line\n"
+            )
+            return report
+
+        with patch("hermes_cli.dump.run_dump"), \
+             patch("hermes_cli.debug.collect_debug_report", side_effect=_wrapped_collect_debug_report), \
+             patch("hermes_cli.debug.upload_to_pastebin", side_effect=_mock_upload):
+            run_debug_share(args)
+
+        report_paste = uploaded_content[0]
+        agent_paste = uploaded_content[1]
+        assert "2026-04-22 12:00:00 INFO agent: newest line" in report_paste
+        assert "2026-04-22 12:00:00 INFO agent: newest line" in agent_paste
+        assert "old rotated line" not in agent_paste
+
     def test_share_skips_missing_logs(self, tmp_path, monkeypatch, capsys):
         """Only uploads logs that exist."""
         home = tmp_path / ".hermes"

tests/hermes_cli/test_env_loader.py

@@ -33,6 +33,25 @@ def test_project_env_overrides_stale_shell_values_when_user_env_missing(tmp_path
     assert os.getenv("OPENAI_BASE_URL") == "https://project.example/v1"
 
 
+def test_project_env_is_sanitized_before_loading(tmp_path, monkeypatch):
+    home = tmp_path / "hermes"
+    project_env = tmp_path / ".env"
+    project_env.write_text(
+        "TELEGRAM_BOT_TOKEN=8356550917:AAGGEkzg06Hrc3Hjb3Sa1jkGVDOdU_lYy2Q"
+        "ANTHROPIC_API_KEY=sk-ant-test123\n",
+        encoding="utf-8",
+    )
+
+    monkeypatch.delenv("TELEGRAM_BOT_TOKEN", raising=False)
+    monkeypatch.delenv("ANTHROPIC_API_KEY", raising=False)
+
+    loaded = load_hermes_dotenv(hermes_home=home, project_env=project_env)
+
+    assert loaded == [project_env]
+    assert os.getenv("TELEGRAM_BOT_TOKEN") == "8356550917:AAGGEkzg06Hrc3Hjb3Sa1jkGVDOdU_lYy2Q"
+    assert os.getenv("ANTHROPIC_API_KEY") == "sk-ant-test123"
+
+
 def test_user_env_takes_precedence_over_project_env(tmp_path, monkeypatch):
     home = tmp_path / "hermes"
     home.mkdir()

tests/hermes_cli/test_gateway.py

@@ -121,6 +121,12 @@ def test_systemd_status_warns_when_linger_disabled(monkeypatch, tmp_path, capsys
             return SimpleNamespace(returncode=0, stdout="", stderr="")
         if cmd[:3] == ["systemctl", "--user", "is-active"]:
             return SimpleNamespace(returncode=0, stdout="active\n", stderr="")
+        if cmd[:3] == ["systemctl", "--user", "show"]:
+            return SimpleNamespace(
+                returncode=0,
+                stdout="ActiveState=active\nSubState=running\nResult=success\nExecMainStatus=0\n",
+                stderr="",
+            )
         raise AssertionError(f"Unexpected command: {cmd}")
 
     monkeypatch.setattr(gateway.subprocess, "run", fake_run)
@@ -352,3 +358,24 @@ class TestWaitForGatewayExit:
 
         assert killed == 2
         assert calls == [(11, True), (22, True)]
+
+
+class TestStopProfileGateway:
+    def test_stop_profile_gateway_keeps_pid_file_when_process_still_running(self, monkeypatch):
+        calls = {"kill": 0, "remove": 0}
+
+        monkeypatch.setattr("gateway.status.get_running_pid", lambda: 12345)
+        monkeypatch.setattr(
+            gateway.os,
+            "kill",
+            lambda pid, sig: calls.__setitem__("kill", calls["kill"] + 1),
+        )
+        monkeypatch.setattr("time.sleep", lambda _: None)
+        monkeypatch.setattr(
+            "gateway.status.remove_pid_file",
+            lambda: calls.__setitem__("remove", calls["remove"] + 1),
+        )
+
+        assert gateway.stop_profile_gateway() is True
+        assert calls["kill"] == 21
+        assert calls["remove"] == 0

tests/hermes_cli/test_gateway_service.py

@@ -77,8 +77,10 @@ class TestSystemdServiceRefresh:
         gateway_cli.systemd_restart()
 
         assert unit_path.read_text(encoding="utf-8") == "new unit\n"
-        assert calls[:2] == [
+        assert calls[:4] == [
             ["systemctl", "--user", "daemon-reload"],
+            ["systemctl", "--user", "show", gateway_cli.get_service_name(), "--no-pager", "--property", "ActiveState,SubState,Result,ExecMainStatus"],
+            ["systemctl", "--user", "reset-failed", gateway_cli.get_service_name()],
             ["systemctl", "--user", "reload-or-restart", gateway_cli.get_service_name()],
         ]
 
@@ -474,13 +476,21 @@ class TestGatewaySystemServiceRouting:
                 raise ProcessLookupError()
         monkeypatch.setattr(os, "kill", fake_kill)
 
-        # Simulate systemctl is-active returning "active" with a new PID
+        # Simulate systemctl reset-failed/start followed by an active unit
         new_pid = [None]
         def fake_subprocess_run(cmd, **kwargs):
-            if "is-active" in cmd:
-                result = SimpleNamespace(stdout="active\n", returncode=0)
-                new_pid[0] = 999  # new PID
-                return result
+            if "reset-failed" in cmd:
+                calls.append(("reset-failed", cmd))
+                return SimpleNamespace(stdout="", returncode=0)
+            if "start" in cmd:
+                calls.append(("start", cmd))
+                return SimpleNamespace(stdout="", returncode=0)
+            if "show" in cmd:
+                new_pid[0] = 999
+                return SimpleNamespace(
+                    stdout="ActiveState=active\nSubState=running\nResult=success\nExecMainStatus=0\n",
+                    returncode=0,
+                )
             raise AssertionError(f"Unexpected systemctl call: {cmd}")
 
         monkeypatch.setattr(gateway_cli.subprocess, "run", fake_subprocess_run)
@@ -494,9 +504,131 @@ class TestGatewaySystemServiceRouting:
         gateway_cli.systemd_restart()
 
         assert ("self", 654) in calls
+        assert any(call[0] == "reset-failed" for call in calls)
+        assert any(call[0] == "start" for call in calls)
         out = capsys.readouterr().out.lower()
         assert "restarted" in out
 
+    def test_systemd_restart_recovers_failed_planned_restart(self, monkeypatch, capsys):
+        monkeypatch.setattr(gateway_cli, "_select_systemd_scope", lambda system=False: False)
+        monkeypatch.setattr(gateway_cli, "refresh_systemd_unit_if_needed", lambda system=False: None)
+        monkeypatch.setattr(
+            "gateway.status.read_runtime_status",
+            lambda: {"restart_requested": True, "gateway_state": "stopped"},
+        )
+        monkeypatch.setattr(gateway_cli, "_request_gateway_self_restart", lambda pid: False)
+
+        calls = []
+        started = {"value": False}
+
+        def fake_subprocess_run(cmd, **kwargs):
+            if "show" in cmd:
+                if not started["value"]:
+                    return SimpleNamespace(
+                        stdout=(
+                            "ActiveState=failed\n"
+                            "SubState=failed\n"
+                            "Result=exit-code\n"
+                            f"ExecMainStatus={GATEWAY_SERVICE_RESTART_EXIT_CODE}\n"
+                        ),
+                        returncode=0,
+                    )
+                return SimpleNamespace(
+                    stdout="ActiveState=active\nSubState=running\nResult=success\nExecMainStatus=0\n",
+                    returncode=0,
+                )
+            if "reset-failed" in cmd:
+                calls.append(("reset-failed", cmd))
+                return SimpleNamespace(stdout="", returncode=0)
+            if "start" in cmd:
+                started["value"] = True
+                calls.append(("start", cmd))
+                return SimpleNamespace(stdout="", returncode=0)
+            raise AssertionError(f"Unexpected command: {cmd}")
+
+        monkeypatch.setattr(gateway_cli.subprocess, "run", fake_subprocess_run)
+        monkeypatch.setattr(
+            "gateway.status.get_running_pid",
+            lambda: 999 if started["value"] else None,
+        )
+
+        gateway_cli.systemd_restart()
+
+        assert any(call[0] == "reset-failed" for call in calls)
+        assert any(call[0] == "start" for call in calls)
+        out = capsys.readouterr().out.lower()
+        assert "restarted" in out
+
+    def test_systemd_status_surfaces_planned_restart_failure(self, monkeypatch, capsys):
+        unit = SimpleNamespace(exists=lambda: True)
+        monkeypatch.setattr(gateway_cli, "_select_systemd_scope", lambda system=False: False)
+        monkeypatch.setattr(gateway_cli, "get_systemd_unit_path", lambda system=False: unit)
+        monkeypatch.setattr(gateway_cli, "has_conflicting_systemd_units", lambda: False)
+        monkeypatch.setattr(gateway_cli, "has_legacy_hermes_units", lambda: False)
+        monkeypatch.setattr(gateway_cli, "systemd_unit_is_current", lambda system=False: True)
+        monkeypatch.setattr(gateway_cli, "_runtime_health_lines", lambda: ["⚠ Last shutdown reason: Gateway restart requested"])
+        monkeypatch.setattr(gateway_cli, "get_systemd_linger_status", lambda: (True, ""))
+        monkeypatch.setattr(gateway_cli, "_read_systemd_unit_properties", lambda system=False: {
+            "ActiveState": "failed",
+            "SubState": "failed",
+            "Result": "exit-code",
+            "ExecMainStatus": str(GATEWAY_SERVICE_RESTART_EXIT_CODE),
+        })
+
+        calls = []
+
+        def fake_run_systemctl(args, **kwargs):
+            calls.append(args)
+            if args[:2] == ["status", gateway_cli.get_service_name()]:
+                return SimpleNamespace(returncode=0, stdout="", stderr="")
+            if args[:2] == ["is-active", gateway_cli.get_service_name()]:
+                return SimpleNamespace(returncode=3, stdout="failed\n", stderr="")
+            raise AssertionError(f"Unexpected args: {args}")
+
+        monkeypatch.setattr(gateway_cli, "_run_systemctl", fake_run_systemctl)
+
+        gateway_cli.systemd_status()
+
+        out = capsys.readouterr().out
+        assert "Planned restart is stuck in systemd failed state" in out
+
+    def test_gateway_status_dispatches_full_flag(self, monkeypatch):
+        user_unit = SimpleNamespace(exists=lambda: True)
+        system_unit = SimpleNamespace(exists=lambda: False)
+
+        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
+        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
+        monkeypatch.setattr(
+            gateway_cli,
+            "get_systemd_unit_path",
+            lambda system=False: system_unit if system else user_unit,
+        )
+        monkeypatch.setattr(
+            gateway_cli,
+            "get_gateway_runtime_snapshot",
+            lambda system=False: gateway_cli.GatewayRuntimeSnapshot(
+                manager="systemd (user)",
+                service_installed=True,
+                service_running=False,
+                gateway_pids=(),
+                service_scope="user",
+            ),
+        )
+
+        calls = []
+        monkeypatch.setattr(
+            gateway_cli,
+            "systemd_status",
+            lambda deep=False, system=False, full=False: calls.append((deep, system, full)),
+        )
+
+        gateway_cli.gateway_command(
+            SimpleNamespace(gateway_command="status", deep=False, system=False, full=True)
+        )
+
+        assert calls == [(False, False, True)]
+
     def test_gateway_install_passes_system_flags(self, monkeypatch):
         monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
@@ -547,11 +679,15 @@ class TestGatewaySystemServiceRouting:
         )
 
         calls = []
-        monkeypatch.setattr(gateway_cli, "systemd_status", lambda deep=False, system=False: calls.append((deep, system)))
+        monkeypatch.setattr(
+            gateway_cli,
+            "systemd_status",
+            lambda deep=False, system=False, full=False: calls.append((deep, system, full)),
+        )
 
         gateway_cli.gateway_command(SimpleNamespace(gateway_command="status", deep=False, system=False))
 
-        assert calls == [(False, False)]
+        assert calls == [(False, False, False)]
 
     def test_gateway_status_reports_manual_process_when_service_is_stopped(self, monkeypatch, capsys):
         user_unit = SimpleNamespace(exists=lambda: True)
@@ -565,7 +701,11 @@ class TestGatewaySystemServiceRouting:
             "get_systemd_unit_path",
             lambda system=False: system_unit if system else user_unit,
         )
-        monkeypatch.setattr(gateway_cli, "systemd_status", lambda deep=False, system=False: print("service stopped"))
+        monkeypatch.setattr(
+            gateway_cli,
+            "systemd_status",
+            lambda deep=False, system=False, full=False: print("service stopped"),
+        )
         monkeypatch.setattr(
             gateway_cli,
             "get_gateway_runtime_snapshot",
@@ -1570,6 +1710,23 @@ class TestMigrateLegacyCommand:
 
         assert called == {"interactive": False, "dry_run": False}
 
+
+class TestGatewayStatusParser:
+    def test_gateway_status_subparser_accepts_full_flag(self):
+        import subprocess
+        import sys
+
+        result = subprocess.run(
+            [sys.executable, "-m", "hermes_cli.main", "gateway", "status", "-l", "--help"],
+            cwd=str(gateway_cli.PROJECT_ROOT),
+            capture_output=True,
+            text=True,
+            timeout=15,
+        )
+
+        assert result.returncode == 0
+        assert "unrecognized arguments" not in result.stderr
+
     def test_gateway_command_migrate_legacy_dry_run_passes_through(
         self, monkeypatch
     ):

tests/hermes_cli/test_image_gen_picker.py

@@ -0,0 +1,174 @@
+"""Tests for plugin image_gen providers injecting themselves into the picker.
+
+Covers `_plugin_image_gen_providers`, `_visible_providers`, and
+`_toolset_needs_configuration_prompt` handling of plugin providers.
+"""
+
+from __future__ import annotations
+
+import pytest
+
+from agent import image_gen_registry
+from agent.image_gen_provider import ImageGenProvider
+
+
+class _FakeProvider(ImageGenProvider):
+    def __init__(self, name: str, available: bool = True, schema=None, models=None):
+        self._name = name
+        self._available = available
+        self._schema = schema or {
+            "name": name.title(),
+            "badge": "test",
+            "tag": f"{name} test tag",
+            "env_vars": [{"key": f"{name.upper()}_API_KEY", "prompt": f"{name} key"}],
+        }
+        self._models = models or [
+            {"id": f"{name}-model-v1", "display": f"{name} v1",
+             "speed": "~5s", "strengths": "test", "price": "$"},
+        ]
+
+    @property
+    def name(self) -> str:
+        return self._name
+
+    def is_available(self) -> bool:
+        return self._available
+
+    def list_models(self):
+        return list(self._models)
+
+    def default_model(self):
+        return self._models[0]["id"] if self._models else None
+
+    def get_setup_schema(self):
+        return dict(self._schema)
+
+    def generate(self, prompt, aspect_ratio="landscape", **kw):
+        return {"success": True, "image": f"{self._name}://{prompt}"}
+
+
+@pytest.fixture(autouse=True)
+def _reset_registry():
+    image_gen_registry._reset_for_tests()
+    yield
+    image_gen_registry._reset_for_tests()
+
+
+class TestPluginPickerInjection:
+    def test_plugin_providers_returns_registered(self, monkeypatch):
+        from hermes_cli import tools_config
+
+        image_gen_registry.register_provider(_FakeProvider("myimg"))
+
+        rows = tools_config._plugin_image_gen_providers()
+        names = [r["name"] for r in rows]
+        plugin_names = [r.get("image_gen_plugin_name") for r in rows]
+
+        assert "Myimg" in names
+        assert "myimg" in plugin_names
+
+    def test_fal_skipped_to_avoid_duplicate(self, monkeypatch):
+        from hermes_cli import tools_config
+
+        # Simulate a FAL plugin being registered — the picker already has
+        # hardcoded FAL rows in TOOL_CATEGORIES, so plugin-FAL must be
+        # skipped to avoid showing FAL twice.
+        image_gen_registry.register_provider(_FakeProvider("fal"))
+        image_gen_registry.register_provider(_FakeProvider("openai"))
+
+        rows = tools_config._plugin_image_gen_providers()
+        names = [r.get("image_gen_plugin_name") for r in rows]
+        assert "fal" not in names
+        assert "openai" in names
+
+    def test_visible_providers_includes_plugins_for_image_gen(self, monkeypatch):
+        from hermes_cli import tools_config
+
+        image_gen_registry.register_provider(_FakeProvider("someimg"))
+
+        cat = tools_config.TOOL_CATEGORIES["image_gen"]
+        visible = tools_config._visible_providers(cat, {})
+        plugin_names = [p.get("image_gen_plugin_name") for p in visible if p.get("image_gen_plugin_name")]
+        assert "someimg" in plugin_names
+
+    def test_visible_providers_does_not_inject_into_other_categories(self, monkeypatch):
+        from hermes_cli import tools_config
+
+        image_gen_registry.register_provider(_FakeProvider("someimg"))
+
+        # Browser category must NOT see image_gen plugins.
+        browser = tools_config.TOOL_CATEGORIES["browser"]
+        visible = tools_config._visible_providers(browser, {})
+        assert all(p.get("image_gen_plugin_name") is None for p in visible)
+
+
+class TestPluginCatalog:
+    def test_plugin_catalog_returns_models(self):
+        from hermes_cli import tools_config
+
+        image_gen_registry.register_provider(_FakeProvider("catimg"))
+
+        catalog, default = tools_config._plugin_image_gen_catalog("catimg")
+        assert "catimg-model-v1" in catalog
+        assert default == "catimg-model-v1"
+
+    def test_plugin_catalog_empty_for_unknown(self):
+        from hermes_cli import tools_config
+
+        catalog, default = tools_config._plugin_image_gen_catalog("does-not-exist")
+        assert catalog == {}
+        assert default is None
+
+
+class TestConfigPrompt:
+    def test_image_gen_satisfied_by_plugin_provider(self, monkeypatch, tmp_path):
+        """When a plugin provider reports is_available(), the picker should
+        not force a setup prompt on the user."""
+        from hermes_cli import tools_config
+
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        monkeypatch.delenv("FAL_KEY", raising=False)
+
+        image_gen_registry.register_provider(_FakeProvider("avail-img", available=True))
+
+        assert tools_config._toolset_needs_configuration_prompt("image_gen", {}) is False
+
+    def test_image_gen_still_prompts_when_nothing_available(self, monkeypatch, tmp_path):
+        from hermes_cli import tools_config
+
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        monkeypatch.delenv("FAL_KEY", raising=False)
+
+        image_gen_registry.register_provider(_FakeProvider("unavail-img", available=False))
+
+        assert tools_config._toolset_needs_configuration_prompt("image_gen", {}) is True
+
+
+class TestConfigWriting:
+    def test_picking_plugin_provider_writes_provider_and_model(self, monkeypatch, tmp_path):
+        """When a user picks a plugin-backed image_gen provider with no
+        env vars needed, ``_configure_provider`` should write both
+        ``image_gen.provider`` and ``image_gen.model``."""
+        from hermes_cli import tools_config
+
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+        image_gen_registry.register_provider(_FakeProvider("noenv", schema={
+            "name": "NoEnv",
+            "badge": "free",
+            "tag": "",
+            "env_vars": [],
+        }))
+
+        # Stub out the interactive model picker — no TTY in tests.
+        monkeypatch.setattr(tools_config, "_prompt_choice", lambda *a, **kw: 0)
+
+        config: dict = {}
+        provider_row = {
+            "name": "NoEnv",
+            "env_vars": [],
+            "image_gen_plugin_name": "noenv",
+        }
+        tools_config._configure_provider(provider_row, config)
+
+        assert config["image_gen"]["provider"] == "noenv"
+        assert config["image_gen"]["model"] == "noenv-model-v1"

tests/hermes_cli/test_model_provider_persistence.py

@@ -32,6 +32,8 @@ def config_home(tmp_path, monkeypatch):
     monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
     monkeypatch.delenv("OPENAI_API_KEY", raising=False)
     monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
+    monkeypatch.delenv("STEPFUN_API_KEY", raising=False)
+    monkeypatch.delenv("STEPFUN_BASE_URL", raising=False)
     return home
 
 
@@ -330,3 +332,33 @@ class TestBaseUrlValidation:
 
         saved = get_env_value("GLM_BASE_URL") or ""
         assert saved == "", "Empty input should not save a base URL"
+
+    def test_stepfun_provider_saved_with_selected_region(self, config_home, monkeypatch):
+        from hermes_cli.main import _model_flow_stepfun
+        from hermes_cli.config import load_config, get_env_value
+
+        monkeypatch.setenv("STEPFUN_API_KEY", "stepfun-test-key")
+
+        with patch(
+            "hermes_cli.main._prompt_provider_choice",
+            return_value=1,
+        ), patch(
+            "hermes_cli.models.fetch_api_models",
+            return_value=["step-3.5-flash", "step-3-agent-lite"],
+        ), patch(
+            "hermes_cli.auth._prompt_model_selection",
+            return_value="step-3-agent-lite",
+        ), patch(
+            "hermes_cli.auth.deactivate_provider",
+        ):
+            _model_flow_stepfun(load_config(), "old-model")
+
+        import yaml
+
+        config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
+        model = config.get("model")
+        assert isinstance(model, dict)
+        assert model.get("provider") == "stepfun"
+        assert model.get("default") == "step-3-agent-lite"
+        assert model.get("base_url") == "https://api.stepfun.com/step_plan/v1"
+        assert get_env_value("STEPFUN_BASE_URL") == "https://api.stepfun.com/step_plan/v1"

tests/hermes_cli/test_model_validation.py

@@ -63,6 +63,11 @@ class TestParseModelInput:
         assert provider == "zai"
         assert model == "glm-5"
 
+    def test_stepfun_alias_resolved(self):
+        provider, model = parse_model_input("step:step-3.5-flash", "openrouter")
+        assert provider == "stepfun"
+        assert model == "step-3.5-flash"
+
     def test_no_slash_no_colon_keeps_provider(self):
         provider, model = parse_model_input("gpt-5.4", "openrouter")
         assert provider == "openrouter"
@@ -154,6 +159,7 @@ class TestNormalizeProvider:
         assert normalize_provider("glm") == "zai"
         assert normalize_provider("kimi") == "kimi-coding"
         assert normalize_provider("moonshot") == "kimi-coding"
+        assert normalize_provider("step") == "stepfun"
         assert normalize_provider("github-copilot") == "copilot"
 
     def test_case_insensitive(self):
@@ -164,6 +170,7 @@ class TestProviderLabel:
     def test_known_labels_and_auto(self):
         assert provider_label("anthropic") == "Anthropic"
         assert provider_label("kimi") == "Kimi / Kimi Coding Plan"
+        assert provider_label("stepfun") == "StepFun Step Plan"
         assert provider_label("copilot") == "GitHub Copilot"
         assert provider_label("copilot-acp") == "GitHub Copilot ACP"
         assert provider_label("auto") == "Auto"
@@ -193,6 +200,16 @@ class TestProviderModelIds:
     def test_zai_returns_glm_models(self):
         assert "glm-5" in provider_model_ids("zai")
 
+    def test_stepfun_prefers_live_catalog(self):
+        with patch(
+            "hermes_cli.auth.resolve_api_key_provider_credentials",
+            return_value={"api_key": "***", "base_url": "https://api.stepfun.com/step_plan/v1"},
+        ), patch(
+            "hermes_cli.models.fetch_api_models",
+            return_value=["step-3.5-flash", "step-3-agent-lite"],
+        ):
+            assert provider_model_ids("stepfun") == ["step-3.5-flash", "step-3-agent-lite"]
+
     def test_copilot_prefers_live_catalog(self):
         with patch("hermes_cli.auth.resolve_api_key_provider_credentials", return_value={"api_key": "gh-token"}), \
              patch("hermes_cli.models._fetch_github_models", return_value=["gpt-5.4", "claude-sonnet-4.6"]):
@@ -457,29 +474,62 @@ class TestValidateApiNotFound:
         assert "not found" in result["message"]
 
 
-# -- validate — API unreachable — reject with guidance ----------------
+# -- validate — API unreachable — soft-accept via catalog or warning --------
 
 class TestValidateApiFallback:
-    def test_any_model_rejected_when_api_down(self):
-        result = _validate("anthropic/claude-opus-4.6", api_models=None)
-        assert result["accepted"] is False
-        assert result["persist"] is False
+    """When /models is unreachable, the validator must accept the model (with
+    a warning) rather than reject it outright — otherwise provider switches
+    fail in the gateway for any provider whose /models endpoint is down or
+    doesn't exist (e.g. opencode-go returns 404 HTML).
 
-    def test_unknown_model_also_rejected_when_api_down(self):
-        result = _validate("anthropic/claude-next-gen", api_models=None)
-        assert result["accepted"] is False
-        assert result["persist"] is False
-        assert "could not reach" in result["message"].lower()
+    Two paths:
+      1. Provider has a curated catalog (``_PROVIDER_MODELS`` / live fetch):
+         validate against it (recognized=True for known models,
+         recognized=False with 'Note:' for unknown).
+      2. Provider has no catalog: accept with a generic 'Note:' warning.
 
-    def test_zai_model_rejected_when_api_down(self):
+    In both cases ``accepted`` and ``persist`` must be True so the gateway can
+    write the ``_session_model_overrides`` entry.
+    """
+
+    def test_known_model_accepted_via_catalog_when_api_down(self):
+        # Force the openrouter catalog lookup to return a deterministic list.
+        with patch(
+            "hermes_cli.models.provider_model_ids",
+            return_value=["anthropic/claude-opus-4.6", "openai/gpt-5.4"],
+        ):
+            result = _validate("anthropic/claude-opus-4.6", api_models=None)
+        assert result["accepted"] is True
+        assert result["persist"] is True
+        assert result["recognized"] is True
+
+    def test_unknown_model_accepted_with_note_when_api_down(self):
+        with patch(
+            "hermes_cli.models.provider_model_ids",
+            return_value=["anthropic/claude-opus-4.6", "openai/gpt-5.4"],
+        ):
+            result = _validate("anthropic/claude-next-gen", api_models=None)
+        assert result["accepted"] is True
+        assert result["persist"] is True
+        assert result["recognized"] is False
+        # Message flags it as unverified against the catalog.
+        assert "not found" in result["message"].lower() or "note" in result["message"].lower()
+
+    def test_zai_known_model_accepted_via_catalog_when_api_down(self):
+        # glm-5 is in the zai curated catalog (_PROVIDER_MODELS["zai"]).
         result = _validate("glm-5", provider="zai", api_models=None)
-        assert result["accepted"] is False
-        assert result["persist"] is False
+        assert result["accepted"] is True
+        assert result["persist"] is True
+        assert result["recognized"] is True
 
-    def test_unknown_provider_rejected_when_api_down(self):
-        result = _validate("some-model", provider="totally-unknown", api_models=None)
-        assert result["accepted"] is False
-        assert result["persist"] is False
+    def test_unknown_provider_soft_accepted_when_api_down(self):
+        # No catalog for unknown providers — soft-accept with a Note.
+        with patch("hermes_cli.models.provider_model_ids", return_value=[]):
+            result = _validate("some-model", provider="totally-unknown", api_models=None)
+        assert result["accepted"] is True
+        assert result["persist"] is True
+        assert result["recognized"] is False
+        assert "note" in result["message"].lower()
 
     def test_custom_endpoint_warns_with_probed_url_and_v1_hint(self):
         with patch(

tests/hermes_cli/test_models.py

@@ -4,7 +4,6 @@ from unittest.mock import patch, MagicMock
 
 from hermes_cli.models import (
     OPENROUTER_MODELS, fetch_openrouter_models, model_ids, detect_provider_for_model,
-    filter_nous_free_models, _NOUS_ALLOWED_FREE_MODELS,
     is_nous_free_tier, partition_nous_models_by_tier,
     check_nous_free_tier, _FREE_TIER_CACHE_TTL,
 )
@@ -88,6 +87,131 @@ class TestFetchOpenRouterModels:
 
         assert models == OPENROUTER_MODELS
 
+    def test_filters_out_models_without_tool_support(self, monkeypatch):
+        """Models whose supported_parameters omits 'tools' must not appear in the picker.
+
+        hermes-agent is tool-calling-first — surfacing a non-tool model leads to
+        immediate runtime failures when the user selects it. Ported from
+        Kilo-Org/kilocode#9068.
+        """
+        class _Resp:
+            def __enter__(self):
+                return self
+
+            def __exit__(self, exc_type, exc, tb):
+                return False
+
+            def read(self):
+                # opus-4.6 advertises tools → kept
+                # nano-image has explicit supported_parameters that OMITS tools → dropped
+                # qwen3.6-plus advertises tools → kept
+                return (
+                    b'{"data":['
+                    b'{"id":"anthropic/claude-opus-4.6","pricing":{"prompt":"0.000015","completion":"0.000075"},'
+                    b'"supported_parameters":["temperature","tools","tool_choice"]},'
+                    b'{"id":"google/gemini-3-pro-image-preview","pricing":{"prompt":"0.00001","completion":"0.00003"},'
+                    b'"supported_parameters":["temperature","response_format"]},'
+                    b'{"id":"qwen/qwen3.6-plus","pricing":{"prompt":"0.000000325","completion":"0.00000195"},'
+                    b'"supported_parameters":["tools","temperature"]}'
+                    b']}'
+                )
+
+        # Include the image-only id in the curated list so it has a chance to be surfaced.
+        monkeypatch.setattr(
+            _models_mod,
+            "OPENROUTER_MODELS",
+            [
+                ("anthropic/claude-opus-4.6", ""),
+                ("google/gemini-3-pro-image-preview", ""),
+                ("qwen/qwen3.6-plus", ""),
+            ],
+        )
+        monkeypatch.setattr(_models_mod, "_openrouter_catalog_cache", None)
+        with patch("hermes_cli.models.urllib.request.urlopen", return_value=_Resp()):
+            models = fetch_openrouter_models(force_refresh=True)
+
+        ids = [mid for mid, _ in models]
+        assert "anthropic/claude-opus-4.6" in ids
+        assert "qwen/qwen3.6-plus" in ids
+        # Image-only model advertised supported_parameters WITHOUT tools → must be dropped.
+        assert "google/gemini-3-pro-image-preview" not in ids
+
+    def test_permissive_when_supported_parameters_missing(self, monkeypatch):
+        """Models missing the supported_parameters field keep appearing in the picker.
+
+        Some OpenRouter-compatible gateways (Nous Portal, private mirrors, older
+        catalog snapshots) don't populate supported_parameters. Treating missing
+        as 'unknown → allow' prevents the picker from silently emptying on
+        those gateways.
+        """
+        class _Resp:
+            def __enter__(self):
+                return self
+
+            def __exit__(self, exc_type, exc, tb):
+                return False
+
+            def read(self):
+                # No supported_parameters field at all on either entry.
+                return (
+                    b'{"data":['
+                    b'{"id":"anthropic/claude-opus-4.6","pricing":{"prompt":"0.000015","completion":"0.000075"}},'
+                    b'{"id":"qwen/qwen3.6-plus","pricing":{"prompt":"0.000000325","completion":"0.00000195"}}'
+                    b']}'
+                )
+
+        monkeypatch.setattr(_models_mod, "_openrouter_catalog_cache", None)
+        with patch("hermes_cli.models.urllib.request.urlopen", return_value=_Resp()):
+            models = fetch_openrouter_models(force_refresh=True)
+
+        ids = [mid for mid, _ in models]
+        assert "anthropic/claude-opus-4.6" in ids
+        assert "qwen/qwen3.6-plus" in ids
+
+
+class TestOpenRouterToolSupportHelper:
+    """Unit tests for _openrouter_model_supports_tools (Kilo port #9068)."""
+
+    def test_tools_in_supported_parameters(self):
+        from hermes_cli.models import _openrouter_model_supports_tools
+        assert _openrouter_model_supports_tools(
+            {"id": "x", "supported_parameters": ["temperature", "tools"]}
+        ) is True
+
+    def test_tools_missing_from_supported_parameters(self):
+        from hermes_cli.models import _openrouter_model_supports_tools
+        assert _openrouter_model_supports_tools(
+            {"id": "x", "supported_parameters": ["temperature", "response_format"]}
+        ) is False
+
+    def test_supported_parameters_absent_is_permissive(self):
+        """Missing field → allow (so older / non-OR gateways still work)."""
+        from hermes_cli.models import _openrouter_model_supports_tools
+        assert _openrouter_model_supports_tools({"id": "x"}) is True
+
+    def test_supported_parameters_none_is_permissive(self):
+        from hermes_cli.models import _openrouter_model_supports_tools
+        assert _openrouter_model_supports_tools({"id": "x", "supported_parameters": None}) is True
+
+    def test_supported_parameters_malformed_is_permissive(self):
+        """Malformed (non-list) value → allow rather than silently drop."""
+        from hermes_cli.models import _openrouter_model_supports_tools
+        assert _openrouter_model_supports_tools(
+            {"id": "x", "supported_parameters": "tools,temperature"}
+        ) is True
+
+    def test_non_dict_item_is_permissive(self):
+        from hermes_cli.models import _openrouter_model_supports_tools
+        assert _openrouter_model_supports_tools(None) is True
+        assert _openrouter_model_supports_tools("anthropic/claude-opus-4.6") is True
+
+    def test_empty_supported_parameters_list_drops_model(self):
+        """Explicit empty list → no tools → drop."""
+        from hermes_cli.models import _openrouter_model_supports_tools
+        assert _openrouter_model_supports_tools(
+            {"id": "x", "supported_parameters": []}
+        ) is False
+
 
 class TestFindOpenrouterSlug:
     def test_exact_match(self):
@@ -168,89 +292,6 @@ class TestDetectProviderForModel:
         assert result[0] not in ("nous",)  # nous has claude models but shouldn't be suggested
 
 
-class TestFilterNousFreeModels:
-    """Tests for filter_nous_free_models — Nous Portal free-model policy."""
-
-    _PAID = {"prompt": "0.000003", "completion": "0.000015"}
-    _FREE = {"prompt": "0", "completion": "0"}
-
-    def test_paid_models_kept(self):
-        """Regular paid models pass through unchanged."""
-        models = ["anthropic/claude-opus-4.6", "openai/gpt-5.4"]
-        pricing = {m: self._PAID for m in models}
-        assert filter_nous_free_models(models, pricing) == models
-
-    def test_free_non_allowlist_models_removed(self):
-        """Free models NOT in the allowlist are filtered out."""
-        models = ["anthropic/claude-opus-4.6", "arcee-ai/trinity-large-preview:free"]
-        pricing = {
-            "anthropic/claude-opus-4.6": self._PAID,
-            "arcee-ai/trinity-large-preview:free": self._FREE,
-        }
-        result = filter_nous_free_models(models, pricing)
-        assert result == ["anthropic/claude-opus-4.6"]
-
-    def test_allowlist_model_kept_when_free(self):
-        """Allowlist models are kept when they report as free."""
-        models = ["anthropic/claude-opus-4.6", "xiaomi/mimo-v2-pro"]
-        pricing = {
-            "anthropic/claude-opus-4.6": self._PAID,
-            "xiaomi/mimo-v2-pro": self._FREE,
-        }
-        result = filter_nous_free_models(models, pricing)
-        assert result == ["anthropic/claude-opus-4.6", "xiaomi/mimo-v2-pro"]
-
-    def test_allowlist_model_removed_when_paid(self):
-        """Allowlist models are removed when they are NOT free."""
-        models = ["anthropic/claude-opus-4.6", "xiaomi/mimo-v2-pro"]
-        pricing = {
-            "anthropic/claude-opus-4.6": self._PAID,
-            "xiaomi/mimo-v2-pro": self._PAID,
-        }
-        result = filter_nous_free_models(models, pricing)
-        assert result == ["anthropic/claude-opus-4.6"]
-
-    def test_no_pricing_returns_all(self):
-        """When pricing data is unavailable, all models pass through."""
-        models = ["anthropic/claude-opus-4.6", "nvidia/nemotron-3-super-120b-a12b:free"]
-        assert filter_nous_free_models(models, {}) == models
-
-    def test_model_with_no_pricing_entry_treated_as_paid(self):
-        """A model missing from the pricing dict is kept (assumed paid)."""
-        models = ["anthropic/claude-opus-4.6", "openai/gpt-5.4"]
-        pricing = {"anthropic/claude-opus-4.6": self._PAID}  # gpt-5.4 not in pricing
-        result = filter_nous_free_models(models, pricing)
-        assert result == models
-
-    def test_mixed_scenario(self):
-        """End-to-end: mix of paid, free-allowed, free-disallowed, allowlist-not-free."""
-        models = [
-            "anthropic/claude-opus-4.6",       # paid, not allowlist → keep
-            "nvidia/nemotron-3-super-120b-a12b:free",  # free, not allowlist → drop
-            "xiaomi/mimo-v2-pro",              # free, allowlist → keep
-            "xiaomi/mimo-v2-omni",             # paid, allowlist → drop
-            "openai/gpt-5.4",                  # paid, not allowlist → keep
-        ]
-        pricing = {
-            "anthropic/claude-opus-4.6": self._PAID,
-            "nvidia/nemotron-3-super-120b-a12b:free": self._FREE,
-            "xiaomi/mimo-v2-pro": self._FREE,
-            "xiaomi/mimo-v2-omni": self._PAID,
-            "openai/gpt-5.4": self._PAID,
-        }
-        result = filter_nous_free_models(models, pricing)
-        assert result == [
-            "anthropic/claude-opus-4.6",
-            "xiaomi/mimo-v2-pro",
-            "openai/gpt-5.4",
-        ]
-
-    def test_allowlist_contains_expected_models(self):
-        """Sanity: the allowlist has the models we expect."""
-        assert "xiaomi/mimo-v2-pro" in _NOUS_ALLOWED_FREE_MODELS
-        assert "xiaomi/mimo-v2-omni" in _NOUS_ALLOWED_FREE_MODELS
-
-
 class TestIsNousFreeTier:
     """Tests for is_nous_free_tier — account tier detection."""
 
@@ -376,3 +417,190 @@ class TestCheckNousFreeTierCache:
     def test_cache_ttl_is_short(self):
         """TTL should be short enough to catch upgrades quickly (<=5 min)."""
         assert _FREE_TIER_CACHE_TTL <= 300
+
+
+class TestNousRecommendedModels:
+    """Tests for fetch_nous_recommended_models + get_nous_recommended_aux_model."""
+
+    _SAMPLE_PAYLOAD = {
+        "paidRecommendedModels": [],
+        "freeRecommendedModels": [],
+        "paidRecommendedCompactionModel": None,
+        "paidRecommendedVisionModel": None,
+        "freeRecommendedCompactionModel": {
+            "modelName": "google/gemini-3-flash-preview",
+            "displayName": "Google: Gemini 3 Flash Preview",
+        },
+        "freeRecommendedVisionModel": {
+            "modelName": "google/gemini-3-flash-preview",
+            "displayName": "Google: Gemini 3 Flash Preview",
+        },
+    }
+
+    def setup_method(self):
+        _models_mod._nous_recommended_cache.clear()
+
+    def teardown_method(self):
+        _models_mod._nous_recommended_cache.clear()
+
+    def _mock_urlopen(self, payload):
+        """Return a context-manager mock mimicking urllib.request.urlopen()."""
+        import json as _json
+        response = MagicMock()
+        response.read.return_value = _json.dumps(payload).encode()
+        cm = MagicMock()
+        cm.__enter__.return_value = response
+        cm.__exit__.return_value = False
+        return cm
+
+    def test_fetch_caches_per_portal_url(self):
+        from hermes_cli.models import fetch_nous_recommended_models
+        mock_cm = self._mock_urlopen(self._SAMPLE_PAYLOAD)
+        with patch("urllib.request.urlopen", return_value=mock_cm) as mock_urlopen:
+            a = fetch_nous_recommended_models("https://portal.example.com")
+            b = fetch_nous_recommended_models("https://portal.example.com")
+        assert a == self._SAMPLE_PAYLOAD
+        assert b == self._SAMPLE_PAYLOAD
+        assert mock_urlopen.call_count == 1  # second call served from cache
+
+    def test_fetch_cache_is_keyed_per_portal(self):
+        from hermes_cli.models import fetch_nous_recommended_models
+        mock_cm = self._mock_urlopen(self._SAMPLE_PAYLOAD)
+        with patch("urllib.request.urlopen", return_value=mock_cm) as mock_urlopen:
+            fetch_nous_recommended_models("https://portal.example.com")
+            fetch_nous_recommended_models("https://portal.staging-nousresearch.com")
+        assert mock_urlopen.call_count == 2  # different portals → separate fetches
+
+    def test_fetch_returns_empty_on_network_failure(self):
+        from hermes_cli.models import fetch_nous_recommended_models
+        with patch("urllib.request.urlopen", side_effect=OSError("boom")):
+            result = fetch_nous_recommended_models("https://portal.example.com")
+        assert result == {}
+
+    def test_fetch_force_refresh_bypasses_cache(self):
+        from hermes_cli.models import fetch_nous_recommended_models
+        mock_cm = self._mock_urlopen(self._SAMPLE_PAYLOAD)
+        with patch("urllib.request.urlopen", return_value=mock_cm) as mock_urlopen:
+            fetch_nous_recommended_models("https://portal.example.com")
+            fetch_nous_recommended_models("https://portal.example.com", force_refresh=True)
+        assert mock_urlopen.call_count == 2
+
+    def test_get_aux_model_returns_vision_recommendation(self):
+        from hermes_cli.models import get_nous_recommended_aux_model
+        with patch(
+            "hermes_cli.models.fetch_nous_recommended_models",
+            return_value=self._SAMPLE_PAYLOAD,
+        ):
+            # Free tier → free vision recommendation.
+            model = get_nous_recommended_aux_model(vision=True, free_tier=True)
+        assert model == "google/gemini-3-flash-preview"
+
+    def test_get_aux_model_returns_compaction_recommendation(self):
+        from hermes_cli.models import get_nous_recommended_aux_model
+        payload = dict(self._SAMPLE_PAYLOAD)
+        payload["freeRecommendedCompactionModel"] = {"modelName": "minimax/minimax-m2.7"}
+        with patch(
+            "hermes_cli.models.fetch_nous_recommended_models",
+            return_value=payload,
+        ):
+            model = get_nous_recommended_aux_model(vision=False, free_tier=True)
+        assert model == "minimax/minimax-m2.7"
+
+    def test_get_aux_model_returns_none_when_field_null(self):
+        from hermes_cli.models import get_nous_recommended_aux_model
+        payload = dict(self._SAMPLE_PAYLOAD)
+        payload["freeRecommendedCompactionModel"] = None
+        with patch(
+            "hermes_cli.models.fetch_nous_recommended_models",
+            return_value=payload,
+        ):
+            model = get_nous_recommended_aux_model(vision=False, free_tier=True)
+        assert model is None
+
+    def test_get_aux_model_returns_none_on_empty_payload(self):
+        from hermes_cli.models import get_nous_recommended_aux_model
+        with patch("hermes_cli.models.fetch_nous_recommended_models", return_value={}):
+            assert get_nous_recommended_aux_model(vision=False, free_tier=True) is None
+            assert get_nous_recommended_aux_model(vision=True, free_tier=False) is None
+
+    def test_get_aux_model_returns_none_when_modelname_blank(self):
+        from hermes_cli.models import get_nous_recommended_aux_model
+        payload = {"freeRecommendedCompactionModel": {"modelName": "  "}}
+        with patch(
+            "hermes_cli.models.fetch_nous_recommended_models",
+            return_value=payload,
+        ):
+            assert get_nous_recommended_aux_model(vision=False, free_tier=True) is None
+
+    def test_paid_tier_prefers_paid_recommendation(self):
+        """Paid-tier users should get the paid model when it's populated."""
+        from hermes_cli.models import get_nous_recommended_aux_model
+        payload = {
+            "paidRecommendedCompactionModel": {"modelName": "anthropic/claude-opus-4.7"},
+            "freeRecommendedCompactionModel": {"modelName": "google/gemini-3-flash-preview"},
+            "paidRecommendedVisionModel": {"modelName": "openai/gpt-5.4"},
+            "freeRecommendedVisionModel": {"modelName": "google/gemini-3-flash-preview"},
+        }
+        with patch("hermes_cli.models.fetch_nous_recommended_models", return_value=payload):
+            text = get_nous_recommended_aux_model(vision=False, free_tier=False)
+            vision = get_nous_recommended_aux_model(vision=True, free_tier=False)
+        assert text == "anthropic/claude-opus-4.7"
+        assert vision == "openai/gpt-5.4"
+
+    def test_paid_tier_falls_back_to_free_when_paid_is_null(self):
+        """If the Portal returns null for the paid field, fall back to free."""
+        from hermes_cli.models import get_nous_recommended_aux_model
+        payload = {
+            "paidRecommendedCompactionModel": None,
+            "freeRecommendedCompactionModel": {"modelName": "google/gemini-3-flash-preview"},
+            "paidRecommendedVisionModel": None,
+            "freeRecommendedVisionModel": {"modelName": "google/gemini-3-flash-preview"},
+        }
+        with patch("hermes_cli.models.fetch_nous_recommended_models", return_value=payload):
+            text = get_nous_recommended_aux_model(vision=False, free_tier=False)
+            vision = get_nous_recommended_aux_model(vision=True, free_tier=False)
+        assert text == "google/gemini-3-flash-preview"
+        assert vision == "google/gemini-3-flash-preview"
+
+    def test_free_tier_never_uses_paid_recommendation(self):
+        """Free-tier users must not get paid-only recommendations."""
+        from hermes_cli.models import get_nous_recommended_aux_model
+        payload = {
+            "paidRecommendedCompactionModel": {"modelName": "anthropic/claude-opus-4.7"},
+            "freeRecommendedCompactionModel": None,  # no free recommendation
+        }
+        with patch("hermes_cli.models.fetch_nous_recommended_models", return_value=payload):
+            model = get_nous_recommended_aux_model(vision=False, free_tier=True)
+        # Free tier must return None — never leak the paid model.
+        assert model is None
+
+    def test_auto_detects_tier_when_not_supplied(self):
+        """Default behaviour: call check_nous_free_tier() to pick the tier."""
+        from hermes_cli.models import get_nous_recommended_aux_model
+        payload = {
+            "paidRecommendedCompactionModel": {"modelName": "paid-model"},
+            "freeRecommendedCompactionModel": {"modelName": "free-model"},
+        }
+        with (
+            patch("hermes_cli.models.fetch_nous_recommended_models", return_value=payload),
+            patch("hermes_cli.models.check_nous_free_tier", return_value=True),
+        ):
+            assert get_nous_recommended_aux_model(vision=False) == "free-model"
+        with (
+            patch("hermes_cli.models.fetch_nous_recommended_models", return_value=payload),
+            patch("hermes_cli.models.check_nous_free_tier", return_value=False),
+        ):
+            assert get_nous_recommended_aux_model(vision=False) == "paid-model"
+
+    def test_tier_detection_error_defaults_to_paid(self):
+        """If tier detection raises, assume paid so we don't downgrade silently."""
+        from hermes_cli.models import get_nous_recommended_aux_model
+        payload = {
+            "paidRecommendedCompactionModel": {"modelName": "paid-model"},
+            "freeRecommendedCompactionModel": {"modelName": "free-model"},
+        }
+        with (
+            patch("hermes_cli.models.fetch_nous_recommended_models", return_value=payload),
+            patch("hermes_cli.models.check_nous_free_tier", side_effect=RuntimeError("boom")),
+        ):
+            assert get_nous_recommended_aux_model(vision=False) == "paid-model"

tests/hermes_cli/test_models_dev_preferred_merge.py

@@ -0,0 +1,124 @@
+"""Tests for the models.dev-preferred merge behavior in provider_model_ids
+and list_authenticated_providers.
+
+These guard the contract:
+
+  * For providers in ``_MODELS_DEV_PREFERRED`` (opencode-go, opencode-zen,
+    xiaomi, deepseek, smaller inference providers), both the CLI model
+    picker path (``provider_model_ids``) and the gateway ``/model`` picker
+    path (``list_authenticated_providers``) merge fresh models.dev entries
+    on top of the curated static list.
+  * OpenRouter and Nous Portal are NEVER merged — they keep their curated
+    (OpenRouter) or live-Portal (Nous) semantics.
+  * If models.dev is unreachable (offline / CI), the curated list is the
+    fallback — no crash, no empty list.
+
+Merging is what lets new models (e.g. ``mimo-v2.5-pro`` on opencode-go)
+appear in ``/model`` without a Hermes release.
+"""
+
+import os
+from unittest.mock import patch
+
+import pytest
+
+from hermes_cli.models import (
+    _MODELS_DEV_PREFERRED,
+    _merge_with_models_dev,
+    provider_model_ids,
+)
+
+
+class TestMergeHelper:
+    def test_merge_empty_mdev_returns_curated(self):
+        """When models.dev returns nothing, curated list is preserved verbatim."""
+        with patch("agent.models_dev.list_agentic_models", return_value=[]):
+            out = _merge_with_models_dev("opencode-go", ["mimo-v2-pro", "kimi-k2.6"])
+        assert out == ["mimo-v2-pro", "kimi-k2.6"]
+
+    def test_merge_mdev_raises_returns_curated(self):
+        """Offline / broken models.dev must not break the catalog path."""
+        def boom(_provider):
+            raise RuntimeError("network down")
+
+        with patch("agent.models_dev.list_agentic_models", side_effect=boom):
+            out = _merge_with_models_dev("opencode-go", ["mimo-v2-pro"])
+        assert out == ["mimo-v2-pro"]
+
+    def test_merge_mdev_first_then_curated_extras(self):
+        """models.dev entries come first; curated-only entries are appended."""
+        mdev = ["mimo-v2.5-pro", "mimo-v2-pro", "kimi-k2.6"]
+        curated = ["kimi-k2.6", "kimi-k2.5", "mimo-v2-pro"]  # kimi-k2.5 is curated-only
+        with patch("agent.models_dev.list_agentic_models", return_value=mdev):
+            out = _merge_with_models_dev("opencode-go", curated)
+        # models.dev entries first (in order), then curated-only entries
+        assert out == ["mimo-v2.5-pro", "mimo-v2-pro", "kimi-k2.6", "kimi-k2.5"]
+
+    def test_merge_case_insensitive_dedup(self):
+        """Dedup is case-insensitive but preserves the first occurrence's casing."""
+        mdev = ["MiniMax-M2.7"]
+        curated = ["minimax-m2.7", "minimax-m2.5"]
+        with patch("agent.models_dev.list_agentic_models", return_value=mdev):
+            out = _merge_with_models_dev("minimax", curated)
+        # models.dev casing wins since it came first
+        assert out == ["MiniMax-M2.7", "minimax-m2.5"]
+
+
+class TestProviderModelIdsPreferred:
+    def test_opencode_go_is_preferred(self):
+        assert "opencode-go" in _MODELS_DEV_PREFERRED
+
+    def test_opencode_go_includes_fresh_models_dev_entries(self):
+        """provider_model_ids('opencode-go') adds models.dev entries on top."""
+        mdev = ["mimo-v2.5-pro", "mimo-v2.5", "mimo-v2-pro", "kimi-k2.6"]
+        with patch("agent.models_dev.list_agentic_models", return_value=mdev):
+            out = provider_model_ids("opencode-go")
+        # Fresh models must surface (this is exactly the reported bug fix:
+        # mimo-v2.5-pro should be pickable on opencode-go).
+        assert "mimo-v2.5-pro" in out
+        assert "mimo-v2.5" in out
+        # Curated entries are still present.
+        assert "mimo-v2-pro" in out
+        assert "kimi-k2.6" in out
+
+    def test_opencode_go_offline_falls_back_to_curated(self):
+        """Offline models.dev → curated-only list, no crash."""
+        with patch("agent.models_dev.list_agentic_models", return_value=[]):
+            out = provider_model_ids("opencode-go")
+        # Curated floor (see hermes_cli/models.py _PROVIDER_MODELS["opencode-go"])
+        assert "mimo-v2-pro" in out
+        assert "kimi-k2.6" in out
+
+    def test_opencode_zen_includes_fresh_models(self):
+        """opencode-zen follows the same pattern as opencode-go."""
+        assert "opencode-zen" in _MODELS_DEV_PREFERRED
+        mdev = ["claude-opus-4-7", "kimi-k2.6", "glm-5.1"]
+        with patch("agent.models_dev.list_agentic_models", return_value=mdev):
+            out = provider_model_ids("opencode-zen")
+        assert "claude-opus-4-7" in out
+        assert "kimi-k2.6" in out
+
+
+class TestOpenRouterAndNousUnchanged:
+    """Per Teknium: openrouter and nous are NEVER merged with models.dev."""
+
+    def test_openrouter_not_in_preferred_set(self):
+        assert "openrouter" not in _MODELS_DEV_PREFERRED
+
+    def test_nous_not_in_preferred_set(self):
+        assert "nous" not in _MODELS_DEV_PREFERRED
+
+    def test_openrouter_does_not_call_merge(self):
+        """openrouter takes its own live path — merge helper must NOT run."""
+        with patch(
+            "hermes_cli.models._merge_with_models_dev",
+            side_effect=AssertionError("merge should not be called for openrouter"),
+        ):
+            # Even if model_ids() fails for some other reason, we just care
+            # that the merge path isn't invoked.
+            try:
+                provider_model_ids("openrouter")
+            except AssertionError:
+                raise
+            except Exception:
+                pass  # model_ids() may fail in the hermetic test env — that's fine.

tests/hermes_cli/test_opencode_go_in_model_list.py

@@ -6,16 +6,41 @@ from unittest.mock import patch
 from hermes_cli.model_switch import list_authenticated_providers
 
 
+# Minimum set of models that must be present for opencode-go no matter
+# whether the picker sourced its list from curated-only or curated+models.dev.
+# The curated list in hermes_cli/models.py defines the floor; models.dev only
+# ever adds names on top of it via _merge_with_models_dev.
+_OPENCODE_GO_REQUIRED = {
+    "kimi-k2.6",
+    "kimi-k2.5",
+    "glm-5.1",
+    "glm-5",
+    "mimo-v2-pro",
+    "mimo-v2-omni",
+    "minimax-m2.7",
+    "minimax-m2.5",
+}
+
+
 @patch.dict(os.environ, {"OPENCODE_GO_API_KEY": "test-key"}, clear=False)
 def test_opencode_go_appears_when_api_key_set():
     """opencode-go should appear in list_authenticated_providers when OPENCODE_GO_API_KEY is set."""
-    providers = list_authenticated_providers(current_provider="openrouter")
-    
+    providers = list_authenticated_providers(current_provider="openrouter", max_models=50)
+
     # Find opencode-go in results
     opencode_go = next((p for p in providers if p["slug"] == "opencode-go"), None)
-    
+
     assert opencode_go is not None, "opencode-go should appear when OPENCODE_GO_API_KEY is set"
-    assert opencode_go["models"] == ["kimi-k2.5", "glm-5.1", "glm-5", "mimo-v2-pro", "mimo-v2-omni", "minimax-m2.7", "minimax-m2.5"]
+    # Behavior check: the curated floor must be present. The list may also
+    # include extra models.dev entries (e.g. mimo-v2.5-pro) when the registry
+    # is reachable — that's the whole point of the models.dev-preferred merge
+    # introduced for opencode-go, so don't pin to an exact list here.
+    present = set(opencode_go["models"])
+    missing = _OPENCODE_GO_REQUIRED - present
+    assert not missing, (
+        f"opencode-go picker should include the curated floor; missing: {sorted(missing)}. "
+        f"Got: {opencode_go['models']}"
+    )
     # opencode-go can appear as "built-in" (from PROVIDER_TO_MODELS_DEV when
     # models.dev is reachable) or "hermes" (from HERMES_OVERLAYS fallback when
     # the API is unavailable, e.g. in CI).
@@ -26,10 +51,10 @@ def test_opencode_go_not_appears_when_no_creds():
     """opencode-go should NOT appear when no credentials are set."""
     # Ensure OPENCODE_GO_API_KEY is not set
     env_without_key = {k: v for k, v in os.environ.items() if k != "OPENCODE_GO_API_KEY"}
-    
+
     with patch.dict(os.environ, env_without_key, clear=True):
         providers = list_authenticated_providers(current_provider="openrouter")
-        
+
         # opencode-go should not be in results
         opencode_go = next((p for p in providers if p["slug"] == "opencode-go"), None)
         assert opencode_go is None, "opencode-go should not appear without credentials"

tests/hermes_cli/test_opencode_go_validation_fallback.py

@@ -0,0 +1,133 @@
+"""Tests for the static-catalog fallback in validate_requested_model.
+
+OpenCode Go and OpenCode Zen publish an OpenAI-compatible API at paths that do
+NOT expose ``/models`` (the path returns the marketing site's HTML 404).  This
+caused ``validate_requested_model`` to return ``accepted=False`` for every
+model on those providers, which in turn made ``switch_model()`` fail and the
+gateway's ``/model <name> --provider opencode-go`` command never write to
+``_session_model_overrides``.
+
+These tests cover the catalog-fallback path: when ``fetch_api_models`` returns
+``None``, the validator must consult ``provider_model_ids()`` for the provider
+(populated from ``_PROVIDER_MODELS``) rather than rejecting outright.
+"""
+
+from unittest.mock import patch
+
+from hermes_cli.models import validate_requested_model
+
+
+_UNREACHABLE_PROBE = {
+    "models": None,
+    "probed_url": "https://opencode.ai/zen/go/v1/models",
+    "resolved_base_url": "https://opencode.ai/zen/go/v1",
+    "suggested_base_url": None,
+    "used_fallback": False,
+}
+
+
+def _patched(func):
+    """Decorator: force fetch_api_models / probe_api_models to simulate an
+    unreachable /models endpoint, proving the catalog path is used."""
+    def wrapper(*args, **kwargs):
+        with patch("hermes_cli.models.fetch_api_models", return_value=None), \
+             patch("hermes_cli.models.probe_api_models", return_value=_UNREACHABLE_PROBE):
+            return func(*args, **kwargs)
+    wrapper.__name__ = func.__name__
+    return wrapper
+
+
+# ---------------------------------------------------------------------------
+# opencode-go: curated catalog in _PROVIDER_MODELS
+# ---------------------------------------------------------------------------
+
+
+@_patched
+def test_opencode_go_known_model_accepted():
+    """A model present in the opencode-go curated catalog must be accepted
+    even when /models is unreachable."""
+    result = validate_requested_model("kimi-k2.6", "opencode-go")
+    assert result["accepted"] is True
+    assert result["persist"] is True
+    assert result["recognized"] is True
+    assert result["message"] is None
+
+
+@_patched
+def test_opencode_go_known_model_case_insensitive():
+    """Catalog lookup is case-insensitive."""
+    result = validate_requested_model("KIMI-K2.6", "opencode-go")
+    assert result["accepted"] is True
+    assert result["recognized"] is True
+
+
+@_patched
+def test_opencode_go_typo_auto_corrected():
+    """A close typo (>= 0.9 similarity) is auto-corrected to the catalog
+    entry."""
+    # 'kimi-k2.55' vs 'kimi-k2.5' ratio ≈ 0.95 — within the 0.9 cutoff.
+    result = validate_requested_model("kimi-k2.55", "opencode-go")
+    assert result["accepted"] is True
+    assert result["recognized"] is True
+    assert result.get("corrected_model") == "kimi-k2.5"
+
+
+@_patched
+def test_opencode_go_unknown_model_accepted_with_suggestion():
+    """An unknown model that has a medium-similarity match (>= 0.5 but < 0.9)
+    is accepted with recognized=False and a 'similar models' hint.  The key
+    invariant: the gateway MUST be able to persist this override, so
+    accepted/persist must both be True."""
+    # 'kimi-k3-preview' vs 'kimi-k2.6' — similar enough to suggest, not to auto-correct.
+    result = validate_requested_model("kimi-k3-preview", "opencode-go")
+    assert result["accepted"] is True
+    assert result["persist"] is True
+    assert result["recognized"] is False
+    assert "kimi-k3-preview" in result["message"]
+    assert "curated catalog" in result["message"]
+
+
+@_patched
+def test_opencode_go_totally_unknown_model_still_accepted():
+    """A model with zero similarity to the catalog is still accepted (no
+    suggestion line) so the user can try a model that hasn't made it into the
+    curated list yet."""
+    result = validate_requested_model("some-brand-new-model", "opencode-go")
+    assert result["accepted"] is True
+    assert result["persist"] is True
+    assert result["recognized"] is False
+    # No suggestion text (no close matches)
+    assert "Similar models" not in result["message"]
+    assert "opencode" in result["message"].lower() or "opencode go" in result["message"].lower()
+
+
+# ---------------------------------------------------------------------------
+# opencode-zen: same pattern as opencode-go
+# ---------------------------------------------------------------------------
+
+
+@_patched
+def test_opencode_zen_known_model_accepted():
+    """opencode-zen also uses _PROVIDER_MODELS; kimi-k2 is in its catalog."""
+    result = validate_requested_model("kimi-k2", "opencode-zen")
+    assert result["accepted"] is True
+    assert result["recognized"] is True
+
+
+# ---------------------------------------------------------------------------
+# Unknown provider with no catalog: soft-accept (honors the comment's intent)
+# ---------------------------------------------------------------------------
+
+
+@_patched
+def test_provider_without_catalog_accepts_with_warning():
+    """When a provider has no entry in _PROVIDER_MODELS and /models is
+    unreachable, accept the model with a 'Note:' warning rather than reject.
+    This matches the in-code comment: 'Accept and persist, but warn so typos
+    don't silently break things.'"""
+    # Use a made-up provider name that won't resolve to any catalog.
+    result = validate_requested_model("some-model", "provider-that-does-not-exist")
+    assert result["accepted"] is True
+    assert result["persist"] is True
+    assert result["recognized"] is False
+    assert "Note:" in result["message"]

tests/hermes_cli/test_plugin_scanner_recursion.py

@@ -0,0 +1,357 @@
+"""Tests for PR1 pluggable image gen: scanner recursion, kinds, path keys.
+
+Covers ``_scan_directory`` recursion into category namespaces
+(``plugins/image_gen/openai/``), ``kind`` parsing, path-derived registry
+keys, and the new gate logic (bundled backends auto-load; user backends
+still opt-in; exclusive kind skipped; unknown kinds → standalone warning).
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, Dict
+
+import pytest
+import yaml
+
+from hermes_cli.plugins import PluginManager, PluginManifest
+
+
+# ── Helpers ────────────────────────────────────────────────────────────────
+
+
+def _write_plugin(
+    root: Path,
+    segments: list[str],
+    *,
+    manifest_extra: Dict[str, Any] | None = None,
+    register_body: str = "pass",
+) -> Path:
+    """Create a plugin dir at ``root/<segments...>/`` with plugin.yaml + __init__.py.
+
+    ``segments`` lets tests build both flat (``["my-plugin"]``) and
+    category-namespaced (``["image_gen", "openai"]``) layouts.
+    """
+    plugin_dir = root
+    for seg in segments:
+        plugin_dir = plugin_dir / seg
+    plugin_dir.mkdir(parents=True, exist_ok=True)
+
+    manifest = {
+        "name": segments[-1],
+        "version": "0.1.0",
+        "description": f"Test plugin {'/'.join(segments)}",
+    }
+    if manifest_extra:
+        manifest.update(manifest_extra)
+    (plugin_dir / "plugin.yaml").write_text(yaml.dump(manifest))
+    (plugin_dir / "__init__.py").write_text(
+        f"def register(ctx):\n    {register_body}\n"
+    )
+    return plugin_dir
+
+
+def _enable(hermes_home: Path, name: str) -> None:
+    """Append ``name`` to ``plugins.enabled`` in ``<hermes_home>/config.yaml``."""
+    cfg_path = hermes_home / "config.yaml"
+    cfg: dict = {}
+    if cfg_path.exists():
+        try:
+            cfg = yaml.safe_load(cfg_path.read_text()) or {}
+        except Exception:
+            cfg = {}
+    plugins_cfg = cfg.setdefault("plugins", {})
+    enabled = plugins_cfg.setdefault("enabled", [])
+    if isinstance(enabled, list) and name not in enabled:
+        enabled.append(name)
+    cfg_path.write_text(yaml.safe_dump(cfg))
+
+
+# ── Scanner recursion ──────────────────────────────────────────────────────
+
+
+class TestCategoryNamespaceRecursion:
+    def test_category_namespace_discovered(self, tmp_path, monkeypatch):
+        """``<root>/image_gen/openai/plugin.yaml`` is discovered with key
+        ``image_gen/openai`` when the ``image_gen`` parent has no manifest."""
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        user_plugins = hermes_home / "plugins"
+
+        _write_plugin(user_plugins, ["image_gen", "openai"])
+        _enable(hermes_home, "image_gen/openai")
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert "image_gen/openai" in mgr._plugins
+        loaded = mgr._plugins["image_gen/openai"]
+        assert loaded.manifest.key == "image_gen/openai"
+        assert loaded.manifest.name == "openai"
+        assert loaded.enabled is True
+
+    def test_flat_plugin_key_matches_name(self, tmp_path, monkeypatch):
+        """Flat plugins keep their bare name as the key (back-compat)."""
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        user_plugins = hermes_home / "plugins"
+
+        _write_plugin(user_plugins, ["my-plugin"])
+        _enable(hermes_home, "my-plugin")
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert "my-plugin" in mgr._plugins
+        assert mgr._plugins["my-plugin"].manifest.key == "my-plugin"
+
+    def test_depth_cap_two(self, tmp_path, monkeypatch):
+        """Plugins nested three levels deep are not discovered.
+
+        ``<root>/a/b/c/plugin.yaml`` should NOT be picked up — cap is
+        two segments.
+        """
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        user_plugins = hermes_home / "plugins"
+
+        _write_plugin(user_plugins, ["a", "b", "c"])
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        non_bundled = [
+            k for k, p in mgr._plugins.items()
+            if p.manifest.source != "bundled"
+        ]
+        assert non_bundled == []
+
+    def test_category_dir_with_manifest_is_leaf(self, tmp_path, monkeypatch):
+        """If ``image_gen/plugin.yaml`` exists, ``image_gen`` itself IS the
+        plugin and its children are ignored."""
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        user_plugins = hermes_home / "plugins"
+
+        # parent has a manifest → stop recursing
+        _write_plugin(user_plugins, ["image_gen"])
+        # child also has a manifest — should NOT be found because we stop
+        # at the parent.
+        _write_plugin(user_plugins, ["image_gen", "openai"])
+        _enable(hermes_home, "image_gen")
+        _enable(hermes_home, "image_gen/openai")
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        # The bundled plugins/image_gen/openai/ exists in the repo — filter
+        # it out so we're only asserting on the user-dir layout.
+        user_plugins_in_registry = {
+            k for k, p in mgr._plugins.items() if p.manifest.source != "bundled"
+        }
+        assert "image_gen" in user_plugins_in_registry
+        assert "image_gen/openai" not in user_plugins_in_registry
+
+
+# ── Kind parsing ───────────────────────────────────────────────────────────
+
+
+class TestKindField:
+    def test_default_kind_is_standalone(self, tmp_path, monkeypatch):
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        _write_plugin(hermes_home / "plugins", ["p1"])
+        _enable(hermes_home, "p1")
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert mgr._plugins["p1"].manifest.kind == "standalone"
+
+    @pytest.mark.parametrize("kind", ["backend", "exclusive", "standalone"])
+    def test_valid_kinds_parsed(self, kind, tmp_path, monkeypatch):
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        _write_plugin(
+            hermes_home / "plugins",
+            ["p1"],
+            manifest_extra={"kind": kind},
+        )
+        # Not all kinds auto-load, but manifest should parse.
+        _enable(hermes_home, "p1")
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert "p1" in mgr._plugins
+        assert mgr._plugins["p1"].manifest.kind == kind
+
+    def test_unknown_kind_falls_back_to_standalone(self, tmp_path, monkeypatch, caplog):
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        _write_plugin(
+            hermes_home / "plugins",
+            ["p1"],
+            manifest_extra={"kind": "bogus"},
+        )
+        _enable(hermes_home, "p1")
+
+        with caplog.at_level("WARNING"):
+            mgr = PluginManager()
+            mgr.discover_and_load()
+
+        assert mgr._plugins["p1"].manifest.kind == "standalone"
+        assert any(
+            "unknown kind" in rec.getMessage() for rec in caplog.records
+        )
+
+
+# ── Gate logic ─────────────────────────────────────────────────────────────
+
+
+class TestBackendGate:
+    def test_user_backend_still_gated_by_enabled(self, tmp_path, monkeypatch):
+        """User-installed ``kind: backend`` plugins still require opt-in —
+        they're not trusted by default."""
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        user_plugins = hermes_home / "plugins"
+
+        _write_plugin(
+            user_plugins,
+            ["image_gen", "fancy"],
+            manifest_extra={"kind": "backend"},
+        )
+        # Do NOT opt in.
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        loaded = mgr._plugins["image_gen/fancy"]
+        assert loaded.enabled is False
+        assert "not enabled" in (loaded.error or "")
+
+    def test_user_backend_loads_when_enabled(self, tmp_path, monkeypatch):
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        user_plugins = hermes_home / "plugins"
+
+        _write_plugin(
+            user_plugins,
+            ["image_gen", "fancy"],
+            manifest_extra={"kind": "backend"},
+        )
+        _enable(hermes_home, "image_gen/fancy")
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert mgr._plugins["image_gen/fancy"].enabled is True
+
+    def test_exclusive_kind_skipped(self, tmp_path, monkeypatch):
+        """``kind: exclusive`` plugins are recorded but not loaded — the
+        category's own discovery system handles them (memory today)."""
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        _write_plugin(
+            hermes_home / "plugins",
+            ["some-backend"],
+            manifest_extra={"kind": "exclusive"},
+        )
+        _enable(hermes_home, "some-backend")
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        loaded = mgr._plugins["some-backend"]
+        assert loaded.enabled is False
+        assert "exclusive" in (loaded.error or "")
+
+
+# ── Bundled backend auto-load (integration with real bundled plugin) ────────
+
+
+class TestBundledBackendAutoLoad:
+    def test_bundled_image_gen_openai_autoloads(self, tmp_path, monkeypatch):
+        """The bundled ``plugins/image_gen/openai/`` plugin loads without
+        any opt-in — it's ``kind: backend`` and shipped in-repo."""
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert "image_gen/openai" in mgr._plugins
+        loaded = mgr._plugins["image_gen/openai"]
+        assert loaded.manifest.source == "bundled"
+        assert loaded.manifest.kind == "backend"
+        assert loaded.enabled is True, f"error: {loaded.error}"
+
+
+# ── PluginContext.register_image_gen_provider ───────────────────────────────
+
+
+class TestRegisterImageGenProvider:
+    def test_accepts_valid_provider(self, tmp_path, monkeypatch):
+        from agent import image_gen_registry
+        from agent.image_gen_provider import ImageGenProvider
+
+        image_gen_registry._reset_for_tests()
+
+        class FakeProvider(ImageGenProvider):
+            @property
+            def name(self) -> str:
+                return "fake-test"
+
+            def generate(self, prompt, aspect_ratio="landscape", **kw):
+                return {"success": True, "image": "test://fake"}
+
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        plugin_dir = _write_plugin(
+            hermes_home / "plugins",
+            ["my-img-plugin"],
+            register_body=(
+                "from agent.image_gen_provider import ImageGenProvider\n"
+                "    class P(ImageGenProvider):\n"
+                "        @property\n"
+                "        def name(self): return 'fake-ctx'\n"
+                "        def generate(self, prompt, aspect_ratio='landscape', **kw):\n"
+                "            return {'success': True, 'image': 'x://y'}\n"
+                "    ctx.register_image_gen_provider(P())"
+            ),
+        )
+        _enable(hermes_home, "my-img-plugin")
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert mgr._plugins["my-img-plugin"].enabled is True
+        assert image_gen_registry.get_provider("fake-ctx") is not None
+
+        image_gen_registry._reset_for_tests()
+
+    def test_rejects_non_provider(self, tmp_path, monkeypatch, caplog):
+        from agent import image_gen_registry
+
+        image_gen_registry._reset_for_tests()
+
+        import os
+        hermes_home = Path(os.environ["HERMES_HOME"])  # set by hermetic conftest fixture
+        _write_plugin(
+            hermes_home / "plugins",
+            ["bad-img-plugin"],
+            register_body="ctx.register_image_gen_provider('not a provider')",
+        )
+        _enable(hermes_home, "bad-img-plugin")
+
+        with caplog.at_level("WARNING"):
+            mgr = PluginManager()
+            mgr.discover_and_load()
+
+        # Plugin loaded (register returned normally) but nothing was
+        # registered in the provider registry.
+        assert mgr._plugins["bad-img-plugin"].enabled is True
+        assert image_gen_registry.get_provider("not a provider") is None
+
+        image_gen_registry._reset_for_tests()

tests/hermes_cli/test_plugins.py

@@ -250,6 +250,73 @@ class TestPluginLoading:
 
         assert "hermes_plugins.ns_plugin" in sys.modules
 
+    def test_user_memory_plugin_auto_coerced_to_exclusive(self, tmp_path, monkeypatch):
+        """User-installed memory plugins must NOT be loaded by the general
+        PluginManager — they belong to plugins/memory discovery.
+
+        Regression test for the mempalace crash:
+            'PluginContext' object has no attribute 'register_memory_provider'
+
+        A plugin that calls ``ctx.register_memory_provider`` in its
+        ``__init__.py`` should be auto-detected and treated as
+        ``kind: exclusive`` so the general loader records the manifest but
+        does not import/register() it. The real activation happens through
+        ``plugins/memory/__init__.py`` via ``memory.provider`` config.
+        """
+        plugins_dir = tmp_path / "hermes_test" / "plugins"
+        plugin_dir = plugins_dir / "mempalace"
+        plugin_dir.mkdir(parents=True)
+        # No explicit `kind:` — the heuristic should kick in.
+        (plugin_dir / "plugin.yaml").write_text(yaml.dump({"name": "mempalace"}))
+        (plugin_dir / "__init__.py").write_text(
+            "class MemPalaceProvider:\n"
+            "    pass\n"
+            "def register(ctx):\n"
+            "    ctx.register_memory_provider('mempalace', MemPalaceProvider)\n"
+        )
+        # Even if the user explicitly enables it in config, the loader
+        # should still treat it as exclusive and skip general loading.
+        hermes_home = tmp_path / "hermes_test"
+        (hermes_home / "config.yaml").write_text(
+            yaml.safe_dump({"plugins": {"enabled": ["mempalace"]}})
+        )
+        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert "mempalace" in mgr._plugins
+        entry = mgr._plugins["mempalace"]
+        assert entry.manifest.kind == "exclusive", (
+            f"Expected auto-coerced kind='exclusive', got {entry.manifest.kind}"
+        )
+        # Not loaded by general manager (no register() call, no AttributeError).
+        assert not entry.enabled
+        assert entry.module is None
+        assert "exclusive" in (entry.error or "").lower()
+
+    def test_explicit_standalone_kind_not_coerced(self, tmp_path, monkeypatch):
+        """If a plugin explicitly declares ``kind: standalone`` in its
+        manifest, the memory-provider heuristic must NOT override it —
+        even if the source happens to mention ``MemoryProvider``.
+        """
+        plugins_dir = tmp_path / "hermes_test" / "plugins"
+        plugin_dir = plugins_dir / "not_memory"
+        plugin_dir.mkdir(parents=True)
+        (plugin_dir / "plugin.yaml").write_text(
+            yaml.dump({"name": "not_memory", "kind": "standalone"})
+        )
+        (plugin_dir / "__init__.py").write_text(
+            "# This plugin inspects MemoryProvider docs but isn't one.\n"
+            "def register(ctx):\n    pass\n"
+        )
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path / "hermes_test"))
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert mgr._plugins["not_memory"].manifest.kind == "standalone"
+
 
 # ── TestPluginHooks ────────────────────────────────────────────────────────
 
@@ -720,6 +787,33 @@ class TestPluginCommands:
         assert entry["handler"] is handler
         assert entry["description"] == "My custom command"
         assert entry["plugin"] == "test-plugin"
+        # args_hint defaults to empty string when not passed.
+        assert entry["args_hint"] == ""
+
+    def test_register_command_with_args_hint(self):
+        """args_hint is stored and surfaced for gateway-native UI registration."""
+        mgr = PluginManager()
+        manifest = PluginManifest(name="test-plugin", source="user")
+        ctx = PluginContext(manifest, mgr)
+
+        ctx.register_command(
+            "metricas",
+            lambda a: a,
+            description="Metrics dashboard",
+            args_hint="dias:7 formato:json",
+        )
+
+        entry = mgr._plugin_commands["metricas"]
+        assert entry["args_hint"] == "dias:7 formato:json"
+
+    def test_register_command_args_hint_whitespace_trimmed(self):
+        """args_hint leading/trailing whitespace is stripped."""
+        mgr = PluginManager()
+        manifest = PluginManifest(name="test-plugin", source="user")
+        ctx = PluginContext(manifest, mgr)
+
+        ctx.register_command("foo", lambda a: a, args_hint="  <file>  ")
+        assert mgr._plugin_commands["foo"]["args_hint"] == "<file>"
 
     def test_register_command_normalizes_name(self):
         """Names are lowercased, stripped, and leading slashes removed."""

tests/hermes_cli/test_runtime_provider_resolution.py

@@ -1412,3 +1412,90 @@ def test_named_custom_runtime_no_model_when_absent(monkeypatch):
 
     resolved = rp.resolve_runtime_provider(requested="my-server")
     assert "model" not in resolved
+
+
+# ---------------------------------------------------------------------------
+# GHSA-76xc-57q6-vm5m — Ollama URL substring leak
+#
+# Same bug class as the previously-fixed GHSA-xf8p-v2cg-h7h5 (OpenRouter).
+# _resolve_openrouter_runtime's custom-endpoint branch selects OLLAMA_API_KEY
+# when the base_url "looks like" ollama.com. Previous implementation used
+# raw substring match; a custom base_url whose PATH or look-alike host
+# merely contained "ollama.com" leaked OLLAMA_API_KEY to that endpoint.
+# Fix: use base_url_host_matches (same helper as the OpenRouter sweep).
+# ---------------------------------------------------------------------------
+
+class TestOllamaUrlSubstringLeak:
+    """Call-site regression tests for the fix in _resolve_openrouter_runtime."""
+
+    def _make_cfg(self, base_url):
+        return {"base_url": base_url, "api_key": "", "provider": "custom"}
+
+    def test_ollama_key_not_leaked_to_path_injection(self, monkeypatch):
+        """http://127.0.0.1:9000/ollama.com/v1 — attacker endpoint with
+        ollama.com in PATH. Must resolve to OPENAI_API_KEY, not OLLAMA_API_KEY."""
+        monkeypatch.setenv("OPENAI_API_KEY", "oa-secret")
+        monkeypatch.setenv("OPENROUTER_API_KEY", "or-secret")
+        monkeypatch.setenv("OLLAMA_API_KEY", "ol-SECRET-should-not-leak")
+        monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "custom")
+        monkeypatch.setattr(rp, "_get_model_config", lambda: self._make_cfg(
+            "http://127.0.0.1:9000/ollama.com/v1"
+        ))
+        monkeypatch.setattr(rp, "load_pool", lambda provider: None)
+        monkeypatch.setattr(rp, "_try_resolve_from_custom_pool", lambda *a, **k: None)
+
+        resolved = rp.resolve_runtime_provider(requested="custom")
+
+        assert "ol-SECRET" not in resolved["api_key"], (
+            "OLLAMA_API_KEY must not be sent to an endpoint whose "
+            "hostname is not ollama.com (GHSA-76xc-57q6-vm5m)"
+        )
+        assert resolved["api_key"] == "oa-secret"
+
+    def test_ollama_key_not_leaked_to_lookalike_host(self, monkeypatch):
+        """ollama.com.attacker.test — look-alike host. OLLAMA_API_KEY
+        must not be sent."""
+        monkeypatch.setenv("OPENAI_API_KEY", "oa-secret")
+        monkeypatch.setenv("OLLAMA_API_KEY", "ol-SECRET-should-not-leak")
+        monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "custom")
+        monkeypatch.setattr(rp, "_get_model_config", lambda: self._make_cfg(
+            "http://ollama.com.attacker.test:9000/v1"
+        ))
+        monkeypatch.setattr(rp, "load_pool", lambda provider: None)
+        monkeypatch.setattr(rp, "_try_resolve_from_custom_pool", lambda *a, **k: None)
+
+        resolved = rp.resolve_runtime_provider(requested="custom")
+
+        assert "ol-SECRET" not in resolved["api_key"]
+        assert resolved["api_key"] == "oa-secret"
+
+    def test_ollama_key_sent_to_genuine_ollama_com(self, monkeypatch):
+        """https://ollama.com/v1 — legit Ollama Cloud. OLLAMA_API_KEY
+        should be used."""
+        monkeypatch.setenv("OPENAI_API_KEY", "oa-secret")
+        monkeypatch.setenv("OLLAMA_API_KEY", "ol-legit-key")
+        monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "custom")
+        monkeypatch.setattr(rp, "_get_model_config", lambda: self._make_cfg(
+            "https://ollama.com/v1"
+        ))
+        monkeypatch.setattr(rp, "load_pool", lambda provider: None)
+        monkeypatch.setattr(rp, "_try_resolve_from_custom_pool", lambda *a, **k: None)
+
+        resolved = rp.resolve_runtime_provider(requested="custom")
+
+        assert resolved["api_key"] == "ol-legit-key"
+
+    def test_ollama_key_sent_to_ollama_subdomain(self, monkeypatch):
+        """https://api.ollama.com/v1 — legit subdomain."""
+        monkeypatch.setenv("OPENAI_API_KEY", "oa-secret")
+        monkeypatch.setenv("OLLAMA_API_KEY", "ol-legit-key")
+        monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "custom")
+        monkeypatch.setattr(rp, "_get_model_config", lambda: self._make_cfg(
+            "https://api.ollama.com/v1"
+        ))
+        monkeypatch.setattr(rp, "load_pool", lambda provider: None)
+        monkeypatch.setattr(rp, "_try_resolve_from_custom_pool", lambda *a, **k: None)
+
+        resolved = rp.resolve_runtime_provider(requested="custom")
+
+        assert resolved["api_key"] == "ol-legit-key"

tests/hermes_cli/test_skin_engine.py

@@ -268,7 +268,6 @@ class TestCliBrandingHelpers:
 
     def test_prompt_toolkit_style_overrides_cover_tui_classes(self):
         from hermes_cli.skin_engine import set_active_skin, get_prompt_toolkit_style_overrides
-
         set_active_skin("ares")
         overrides = get_prompt_toolkit_style_overrides()
         required = {
@@ -277,6 +276,13 @@ class TestCliBrandingHelpers:
             "prompt",
             "prompt-working",
             "hint",
+            "status-bar",
+            "status-bar-strong",
+            "status-bar-dim",
+            "status-bar-good",
+            "status-bar-warn",
+            "status-bar-bad",
+            "status-bar-critical",
             "input-rule",
             "image-badge",
             "completion-menu",
@@ -325,6 +331,15 @@ class TestCliBrandingHelpers:
         overrides = get_prompt_toolkit_style_overrides()
         assert overrides["prompt"] == skin.get_color("prompt")
         assert overrides["input-rule"] == skin.get_color("input_rule")
+        assert overrides["status-bar"] == (
+            f"bg:{skin.get_color('status_bar_bg')} {skin.get_color('status_bar_text')}"
+        )
+        assert overrides["status-bar-strong"] == (
+            f"bg:{skin.get_color('status_bar_bg')} {skin.get_color('status_bar_strong')} bold"
+        )
+        assert overrides["status-bar-critical"] == (
+            f"bg:{skin.get_color('status_bar_bg')} {skin.get_color('status_bar_critical')} bold"
+        )
         assert overrides["clarify-title"] == f"{skin.get_color('banner_title')} bold"
         assert overrides["sudo-prompt"] == f"{skin.get_color('ui_error')} bold"
         assert overrides["approval-title"] == f"{skin.get_color('ui_warn')} bold"

tests/hermes_cli/test_web_server.py

@@ -706,6 +706,7 @@ class TestNewEndpoints:
         assert "skills" in data
         assert isinstance(data["daily"], list)
         assert "total_sessions" in data["totals"]
+        assert "total_api_calls" in data["totals"]
         assert data["skills"] == {
             "summary": {
                 "total_skill_loads": 0,

tests/hermes_cli/test_web_server_host_header.py

@@ -0,0 +1,148 @@
+"""Tests for GHSA-ppp5-vxwm-4cf7 — Host-header validation.
+
+DNS rebinding defence: a victim browser that has the dashboard open
+could be tricked into fetching from an attacker-controlled hostname
+that TTL-flips to 127.0.0.1. Same-origin / CORS checks won't help —
+the browser now treats the attacker origin as same-origin. Validating
+the Host header at the application layer rejects the attack.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import pytest
+
+_repo = str(Path(__file__).resolve().parents[1])
+if _repo not in sys.path:
+    sys.path.insert(0, _repo)
+
+
+class TestHostHeaderValidator:
+    """Unit test the _is_accepted_host helper directly — cheaper and
+    more thorough than spinning up the full FastAPI app."""
+
+    def test_loopback_bind_accepts_loopback_names(self):
+        from hermes_cli.web_server import _is_accepted_host
+
+        for bound in ("127.0.0.1", "localhost", "::1"):
+            for host_header in (
+                "127.0.0.1", "127.0.0.1:9119",
+                "localhost", "localhost:9119",
+                "[::1]", "[::1]:9119",
+            ):
+                assert _is_accepted_host(host_header, bound), (
+                    f"bound={bound} must accept host={host_header}"
+                )
+
+    def test_loopback_bind_rejects_attacker_hostnames(self):
+        """The core rebinding defence: attacker-controlled hosts that
+        TTL-flip to 127.0.0.1 must be rejected."""
+        from hermes_cli.web_server import _is_accepted_host
+
+        for bound in ("127.0.0.1", "localhost"):
+            for attacker in (
+                "evil.example",
+                "evil.example:9119",
+                "rebind.attacker.test:80",
+                "localhost.attacker.test",  # subdomain trick
+                "127.0.0.1.evil.test",  # lookalike IP prefix
+                "",  # missing Host
+            ):
+                assert not _is_accepted_host(attacker, bound), (
+                    f"bound={bound} must reject attacker host={attacker!r}"
+                )
+
+    def test_zero_zero_bind_accepts_anything(self):
+        """0.0.0.0 means operator explicitly opted into all-interfaces
+        (requires --insecure). No Host-layer defence is possible — rely
+        on operator network controls."""
+        from hermes_cli.web_server import _is_accepted_host
+
+        for host in ("10.0.0.5", "evil.example", "my-server.corp.net"):
+            assert _is_accepted_host(host, "0.0.0.0")
+            assert _is_accepted_host(host + ":9119", "0.0.0.0")
+
+    def test_explicit_non_loopback_bind_requires_exact_match(self):
+        """If the operator bound to a specific non-loopback hostname,
+        the Host header must match exactly."""
+        from hermes_cli.web_server import _is_accepted_host
+
+        assert _is_accepted_host("my-server.corp.net", "my-server.corp.net")
+        assert _is_accepted_host("my-server.corp.net:9119", "my-server.corp.net")
+        # Different host — reject
+        assert not _is_accepted_host("evil.example", "my-server.corp.net")
+        # Loopback — reject (we bound to a specific non-loopback name)
+        assert not _is_accepted_host("localhost", "my-server.corp.net")
+
+    def test_case_insensitive_comparison(self):
+        """Host headers are case-insensitive per RFC — accept variations."""
+        from hermes_cli.web_server import _is_accepted_host
+
+        assert _is_accepted_host("LOCALHOST", "127.0.0.1")
+        assert _is_accepted_host("LocalHost:9119", "127.0.0.1")
+
+
+class TestHostHeaderMiddleware:
+    """End-to-end test via the FastAPI app — verify the middleware
+    rejects bad Host headers with 400."""
+
+    def test_rebinding_request_rejected(self):
+        from fastapi.testclient import TestClient
+        from hermes_cli.web_server import app
+
+        # Simulate start_server having set the bound_host
+        app.state.bound_host = "127.0.0.1"
+        try:
+            client = TestClient(app)
+            # The TestClient sends Host: testserver by default — which is
+            # NOT a loopback alias, so the middleware must reject it.
+            resp = client.get(
+                "/api/status",
+                headers={"Host": "evil.example"},
+            )
+            assert resp.status_code == 400
+            assert "Invalid Host header" in resp.json()["detail"]
+        finally:
+            # Clean up so other tests don't inherit the bound_host
+            if hasattr(app.state, "bound_host"):
+                del app.state.bound_host
+
+    def test_legit_loopback_request_accepted(self):
+        from fastapi.testclient import TestClient
+        from hermes_cli.web_server import app
+
+        app.state.bound_host = "127.0.0.1"
+        try:
+            client = TestClient(app)
+            # /api/status is in _PUBLIC_API_PATHS — passes auth — so the
+            # only thing that can reject is the host header middleware
+            resp = client.get(
+                "/api/status",
+                headers={"Host": "localhost:9119"},
+            )
+            # Either 200 (endpoint served) or some other non-400 —
+            # just not the host-rejection 400
+            assert resp.status_code != 400 or (
+                "Invalid Host header" not in resp.json().get("detail", "")
+            )
+        finally:
+            if hasattr(app.state, "bound_host"):
+                del app.state.bound_host
+
+    def test_no_bound_host_skips_validation(self):
+        """If app.state.bound_host isn't set (e.g. running under test
+        infra without calling start_server), middleware must pass through
+        rather than crash."""
+        from fastapi.testclient import TestClient
+        from hermes_cli.web_server import app
+
+        # Make sure bound_host isn't set
+        if hasattr(app.state, "bound_host"):
+            del app.state.bound_host
+
+        client = TestClient(app)
+        resp = client.get("/api/status")
+        # Should get through to the status endpoint, not a 400
+        assert resp.status_code != 400