feat: verify AI Gateway provider UX and attribution headers (#950 )

Closes #950 - promote Vercel AI Gateway near the top of the provider picker - add dedicated AI Gateway model flow with Vercel API-key deep link and live pricing - use curated AI Gateway catalog refresh with free Moonshot auto-promotion - apply AI Gateway attribution headers on runtime clients - add targeted QA tests for provider UX and attribution headers
wip: add failing AI Gateway QA tests (#950 )
2026-04-22 11:40:49 -04:00 · 2026-04-22 11:30:05 -04:00
11 changed files with 534 additions and 295 deletions
--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
@@ -1,4 +1,4 @@
-from agent.telemetry_logger import log_token_usage\n"""Shared auxiliary client router for side tasks.
+"""Shared auxiliary client router for side tasks.

 Provides a single resolution chain so every consumer (context compression,
 session search, web extraction, vision analysis, browser vision) picks up
@@ -38,6 +38,7 @@ import json
 import logging
 import os
 import threading
+from agent.telemetry_logger import log_token_usage
 import time
 from pathlib import Path  # noqa: F401 — used by test mocks
 from types import SimpleNamespace
@@ -122,6 +123,16 @@ _OR_HEADERS = {
    "X-OpenRouter-Categories": "productivity,cli-agent",
 }

+# Vercel AI Gateway app attribution headers. HTTP-Referer maps to
+# referrerUrl and X-Title maps to appName in the gateway analytics.
+from hermes_cli import __version__ as _HERMES_VERSION
+
+_AI_GATEWAY_HEADERS = {
+    "HTTP-Referer": "https://hermes-agent.nousresearch.com",
+    "X-Title": "Hermes Agent",
+    "User-Agent": f"HermesAgent/{_HERMES_VERSION}",
+}
+
 # Nous Portal extra_body for product attribution.
 # Callers should pass this as extra_body in chat.completions.create()
 # when the auxiliary client is backed by Nous Portal.
@@ -396,7 +407,8 @@ class _CodexCompletionsAdapter:
                    prompt_tokens=getattr(resp_usage, "input_tokens", 0),
                    completion_tokens=getattr(resp_usage, "output_tokens", 0),
                    total_tokens=getattr(resp_usage, "total_tokens", 0),
-                )\n        log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
+                )
+                log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
        except Exception as exc:
            logger.debug("Codex auxiliary Responses API call failed: %s", exc)
            raise
@@ -529,7 +541,8 @@ class _AnthropicCompletionsAdapter:
                prompt_tokens=prompt_tokens,
                completion_tokens=completion_tokens,
                total_tokens=total_tokens,
-            )\n    log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)
+            )
+            log_token_usage(usage.prompt_tokens, usage.completion_tokens, model)

        choice = SimpleNamespace(
            index=0,
--- a/hermes_cli/main.py
+++ b/hermes_cli/main.py
@@ -168,7 +168,7 @@ import time as _time
 from datetime import datetime

 from hermes_cli import __version__, __release_date__
-from hermes_constants import OPENROUTER_BASE_URL
+from hermes_constants import AI_GATEWAY_BASE_URL, OPENROUTER_BASE_URL

 logger = logging.getLogger(__name__)

@@ -1112,6 +1112,8 @@ def select_provider_and_model(args=None):
    # Step 2: Provider-specific setup + model selection
    if selected_provider == "openrouter":
        _model_flow_openrouter(config, current_model)
+    elif selected_provider == "ai-gateway":
+        _model_flow_ai_gateway(config, current_model)
    elif selected_provider == "nous":
        _model_flow_nous(config, current_model, args=args)
    elif selected_provider == "openai-codex":
@@ -1267,6 +1269,55 @@ def _model_flow_openrouter(config, current_model=""):
        print("No change.")


+def _model_flow_ai_gateway(config, current_model=""):
+    """Vercel AI Gateway provider: ensure API key, then pick model with pricing."""
+    from hermes_cli.auth import _prompt_model_selection, _save_model_choice, deactivate_provider
+    from hermes_cli.config import get_env_value, save_env_value
+    from hermes_cli.models import ai_gateway_model_ids, get_pricing_for_provider
+
+    api_key = get_env_value("AI_GATEWAY_API_KEY")
+    if not api_key:
+        print("No Vercel AI Gateway API key configured.")
+        print("Create API key here: https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai-gateway&title=AI+Gateway")
+        print("Add a payment method to get $5 in free credits.")
+        print()
+        try:
+            import getpass
+            key = getpass.getpass("AI Gateway API key (or Enter to cancel): ").strip()
+        except (KeyboardInterrupt, EOFError):
+            print()
+            return
+        if not key:
+            print("Cancelled.")
+            return
+        save_env_value("AI_GATEWAY_API_KEY", key)
+        print("API key saved.")
+        print()
+
+    models_list = ai_gateway_model_ids(force_refresh=True)
+    pricing = get_pricing_for_provider("ai-gateway", force_refresh=True)
+
+    selected = _prompt_model_selection(models_list, current_model=current_model, pricing=pricing)
+    if selected:
+        _save_model_choice(selected)
+
+        from hermes_cli.config import load_config, save_config
+
+        cfg = load_config()
+        model = cfg.get("model")
+        if not isinstance(model, dict):
+            model = {"default": model} if model else {}
+            cfg["model"] = model
+        model["provider"] = "ai-gateway"
+        model["base_url"] = AI_GATEWAY_BASE_URL
+        model["api_mode"] = "chat_completions"
+        save_config(cfg)
+        deactivate_provider()
+        print(f"Default model set to: {selected} (via Vercel AI Gateway)")
+    else:
+        print("No change.")
+
+
 def _model_flow_nous(config, current_model="", args=None):
    """Nous Portal provider: ensure logged in, then pick model."""
    from hermes_cli.auth import (
--- a/hermes_cli/models.py
+++ b/hermes_cli/models.py
@@ -58,6 +58,28 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [

 _openrouter_catalog_cache: list[tuple[str, str]] | None = None

+# Fallback Vercel AI Gateway snapshot used when the live catalog is unavailable.
+# OSS / open-weight models prioritized first, then closed-source by family.
+VERCEL_AI_GATEWAY_MODELS: list[tuple[str, str]] = [
+    ("moonshotai/kimi-k2.6", "recommended"),
+    ("alibaba/qwen3.6-plus", ""),
+    ("zai/glm-5.1", ""),
+    ("minimax/minimax-m2.7", ""),
+    ("anthropic/claude-sonnet-4.6", ""),
+    ("anthropic/claude-opus-4.7", ""),
+    ("anthropic/claude-opus-4.6", ""),
+    ("anthropic/claude-haiku-4.5", ""),
+    ("openai/gpt-5.4", ""),
+    ("openai/gpt-5.4-mini", ""),
+    ("openai/gpt-5.3-codex", ""),
+    ("google/gemini-3.1-pro-preview", ""),
+    ("google/gemini-3-flash", ""),
+    ("google/gemini-3.1-flash-lite-preview", ""),
+    ("xai/grok-4.20-reasoning", ""),
+]
+
+_ai_gateway_catalog_cache: list[tuple[str, str]] | None = None
+

 def _codex_curated_models() -> list[str]:
    """Derive the openai-codex curated list from codex_models.py.
@@ -258,18 +280,21 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
        "minimax-m2.5",
    ],
    "ai-gateway": [
-        "anthropic/claude-opus-4.6",
+        "moonshotai/kimi-k2.6",
+        "alibaba/qwen3.6-plus",
+        "zai/glm-5.1",
+        "minimax/minimax-m2.7",
        "anthropic/claude-sonnet-4.6",
-        "anthropic/claude-sonnet-4.5",
+        "anthropic/claude-opus-4.7",
+        "anthropic/claude-opus-4.6",
        "anthropic/claude-haiku-4.5",
-        "openai/gpt-5",
-        "openai/gpt-4.1",
-        "openai/gpt-4.1-mini",
-        "google/gemini-3-pro-preview",
+        "openai/gpt-5.4",
+        "openai/gpt-5.4-mini",
+        "openai/gpt-5.3-codex",
+        "google/gemini-3.1-pro-preview",
        "google/gemini-3-flash",
-        "google/gemini-2.5-pro",
-        "google/gemini-2.5-flash",
-        "deepseek/deepseek-v3.2",
+        "google/gemini-3.1-flash-lite-preview",
+        "xai/grok-4.20-reasoning",
    ],
    "kilocode": [
        "anthropic/claude-opus-4.6",
@@ -516,6 +541,7 @@ class ProviderEntry(NamedTuple):
 CANONICAL_PROVIDERS: list[ProviderEntry] = [
    ProviderEntry("nous",           "Nous Portal",              "Nous Portal (Nous Research subscription)"),
    ProviderEntry("openrouter",     "OpenRouter",               "OpenRouter (100+ models, pay-per-use)"),
+    ProviderEntry("ai-gateway",     "Vercel AI Gateway",        "Vercel AI Gateway (200+ models, $5 free credit, no markup)"),
    ProviderEntry("anthropic",      "Anthropic",                "Anthropic (Claude models — API key or Claude Code)"),
    ProviderEntry("openai-codex",   "OpenAI Codex",             "OpenAI Codex"),
    ProviderEntry("xiaomi",         "Xiaomi MiMo",              "Xiaomi MiMo (MiMo-V2 models — pro, omni, flash)"),
@@ -536,7 +562,6 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
    ProviderEntry("kilocode",       "Kilo Code",                "Kilo Code (Kilo Gateway API)"),
    ProviderEntry("opencode-zen",   "OpenCode Zen",             "OpenCode Zen (35+ curated models, pay-as-you-go)"),
    ProviderEntry("opencode-go",    "OpenCode Go",              "OpenCode Go (open models, $10/month subscription)"),
-    ProviderEntry("ai-gateway",     "Vercel AI Gateway",        "Vercel AI Gateway (200+ models, pay-per-use)"),
 ]

 # Derived dicts — used throughout the codebase
@@ -679,6 +704,90 @@ def model_ids(*, force_refresh: bool = False) -> list[str]:



+def _ai_gateway_model_is_free(pricing: Any) -> bool:
+    """Return True if an AI Gateway model has $0 input AND output pricing."""
+    if not isinstance(pricing, dict):
+        return False
+    try:
+        return float(pricing.get("input", "0")) == 0 and float(pricing.get("output", "0")) == 0
+    except (TypeError, ValueError):
+        return False
+
+
+def fetch_ai_gateway_models(
+    timeout: float = 8.0,
+    *,
+    force_refresh: bool = False,
+) -> list[tuple[str, str]]:
+    """Return the curated AI Gateway picker list, refreshed from the live catalog when possible."""
+    global _ai_gateway_catalog_cache
+
+    if _ai_gateway_catalog_cache is not None and not force_refresh:
+        return list(_ai_gateway_catalog_cache)
+
+    from hermes_constants import AI_GATEWAY_BASE_URL
+
+    fallback = list(VERCEL_AI_GATEWAY_MODELS)
+    preferred_ids = [mid for mid, _ in fallback]
+
+    try:
+        req = urllib.request.Request(
+            f"{AI_GATEWAY_BASE_URL.rstrip('/')}/models",
+            headers={"Accept": "application/json"},
+        )
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            payload = json.loads(resp.read().decode())
+    except Exception:
+        return list(_ai_gateway_catalog_cache or fallback)
+
+    live_items = payload.get("data", [])
+    if not isinstance(live_items, list):
+        return list(_ai_gateway_catalog_cache or fallback)
+
+    live_by_id: dict[str, dict[str, Any]] = {}
+    for item in live_items:
+        if not isinstance(item, dict):
+            continue
+        mid = str(item.get("id") or "").strip()
+        if not mid:
+            continue
+        live_by_id[mid] = item
+
+    curated: list[tuple[str, str]] = []
+    for preferred_id in preferred_ids:
+        live_item = live_by_id.get(preferred_id)
+        if live_item is None:
+            continue
+        desc = "free" if _ai_gateway_model_is_free(live_item.get("pricing")) else ""
+        curated.append((preferred_id, desc))
+
+    if not curated:
+        return list(_ai_gateway_catalog_cache or fallback)
+
+    free_moonshot = next(
+        (
+            mid
+            for mid, item in live_by_id.items()
+            if mid.startswith("moonshotai/") and _ai_gateway_model_is_free(item.get("pricing"))
+        ),
+        None,
+    )
+    if free_moonshot:
+        curated = [(mid, desc) for mid, desc in curated if mid != free_moonshot]
+        curated.insert(0, (free_moonshot, "recommended"))
+    else:
+        first_id, _ = curated[0]
+        curated[0] = (first_id, "recommended")
+
+    _ai_gateway_catalog_cache = curated
+    return list(curated)
+
+
+def ai_gateway_model_ids(*, force_refresh: bool = False) -> list[str]:
+    """Return just the AI Gateway model-id strings."""
+    return [mid for mid, _ in fetch_ai_gateway_models(force_refresh=force_refresh)]
+
+
 # ---------------------------------------------------------------------------
 # Pricing helpers — fetch live pricing from OpenRouter-compatible /v1/models
 # ---------------------------------------------------------------------------
@@ -821,6 +930,51 @@ def fetch_models_with_pricing(
    return result


+def fetch_ai_gateway_pricing(
+    timeout: float = 8.0,
+    *,
+    force_refresh: bool = False,
+) -> dict[str, dict[str, str]]:
+    """Fetch Vercel AI Gateway /v1/models and return Hermes-shaped pricing."""
+    from hermes_constants import AI_GATEWAY_BASE_URL
+
+    cache_key = AI_GATEWAY_BASE_URL.rstrip("/")
+    if not force_refresh and cache_key in _pricing_cache:
+        return _pricing_cache[cache_key]
+
+    try:
+        req = urllib.request.Request(
+            f"{cache_key}/models",
+            headers={"Accept": "application/json"},
+        )
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            payload = json.loads(resp.read().decode())
+    except Exception:
+        _pricing_cache[cache_key] = {}
+        return {}
+
+    result: dict[str, dict[str, str]] = {}
+    for item in payload.get("data", []):
+        if not isinstance(item, dict):
+            continue
+        mid = item.get("id")
+        pricing = item.get("pricing")
+        if not (mid and isinstance(pricing, dict)):
+            continue
+        entry: dict[str, str] = {
+            "prompt": str(pricing.get("input", "")),
+            "completion": str(pricing.get("output", "")),
+        }
+        if pricing.get("input_cache_read"):
+            entry["input_cache_read"] = str(pricing["input_cache_read"])
+        if pricing.get("input_cache_write"):
+            entry["input_cache_write"] = str(pricing["input_cache_write"])
+        result[mid] = entry
+
+    _pricing_cache[cache_key] = result
+    return result
+
+
 def _resolve_openrouter_api_key() -> str:
    """Best-effort OpenRouter API key for pricing fetch."""
    return os.getenv("OPENROUTER_API_KEY", "").strip()
@@ -839,7 +993,7 @@ def _resolve_nous_pricing_credentials() -> tuple[str, str]:


 def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> dict[str, dict[str, str]]:
-    """Return live pricing for providers that support it (openrouter, nous)."""
+    """Return live pricing for providers that support it (openrouter, ai-gateway, nous)."""
    normalized = normalize_provider(provider)
    if normalized == "openrouter":
        return fetch_models_with_pricing(
@@ -847,11 +1001,11 @@ def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> d
            base_url="https://openrouter.ai/api",
            force_refresh=force_refresh,
        )
+    if normalized == "ai-gateway":
+        return fetch_ai_gateway_pricing(force_refresh=force_refresh)
    if normalized == "nous":
        api_key, base_url = _resolve_nous_pricing_credentials()
        if base_url:
-            # Nous base_url typically looks like https://inference-api.nousresearch.com/v1
-            # We need the part before /v1 for our fetch function
            stripped = base_url.rstrip("/")
            if stripped.endswith("/v1"):
                stripped = stripped[:-3]
@@ -1253,9 +1407,7 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
        if live:
            return live
    if normalized == "ai-gateway":
-        live = _fetch_ai_gateway_models()
-        if live:
-            return live
+        return ai_gateway_model_ids()
    if normalized == "custom":
        base_url = _get_custom_base_url()
        if base_url:
--- a/hermes_cli/tools_config.py
+++ b/hermes_cli/tools_config.py
@@ -57,7 +57,7 @@ CONFIGURABLE_TOOLSETS = [
    ("moa",             "🧠 Mixture of Agents",         "mixture_of_agents"),
    ("tts",             "🔊 Text-to-Speech",            "text_to_speech"),
    ("skills",          "📚 Skills",                    "list, view, manage"),
-    ("todo",            "📋 Task Planning",             "todo, ultraplan"),
+    ("todo",            "📋 Task Planning",             "todo"),
    ("memory",          "💾 Memory",                    "persistent memory across sessions"),
    ("session_search",  "🔎 Session Search",            "search past conversations"),
    ("clarify",         "❓ Clarifying Questions",      "clarify"),
--- a/run_agent.py
+++ b/run_agent.py
@@ -908,6 +908,10 @@ class AIAgent:
                        "X-OpenRouter-Title": "Hermes Agent",
                        "X-OpenRouter-Categories": "productivity,cli-agent",
                    }
+                elif "ai-gateway.vercel.sh" in effective_base.lower():
+                    from agent.auxiliary_client import _AI_GATEWAY_HEADERS
+
+                    client_kwargs["default_headers"] = dict(_AI_GATEWAY_HEADERS)
                elif "api.githubcopilot.com" in effective_base.lower():
                    from hermes_cli.models import copilot_default_headers

@@ -4667,11 +4671,13 @@ class AIAgent:
        return True

    def _apply_client_headers_for_base_url(self, base_url: str) -> None:
-        from agent.auxiliary_client import _OR_HEADERS
+        from agent.auxiliary_client import _AI_GATEWAY_HEADERS, _OR_HEADERS

        normalized = (base_url or "").lower()
        if "openrouter" in normalized:
            self._client_kwargs["default_headers"] = dict(_OR_HEADERS)
+        elif "ai-gateway.vercel.sh" in normalized:
+            self._client_kwargs["default_headers"] = dict(_AI_GATEWAY_HEADERS)
        elif "api.githubcopilot.com" in normalized:
            from hermes_cli.models import copilot_default_headers

--- a/tests/hermes_cli/test_ai_gateway_models.py
+++ b/tests/hermes_cli/test_ai_gateway_models.py
@@ -0,0 +1,222 @@
+"""AI Gateway provider UX, live pricing, and model promotion tests."""
+
+from __future__ import annotations
+
+import json
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from hermes_cli import models as models_module
+from hermes_cli.models import (
+    CANONICAL_PROVIDERS,
+    VERCEL_AI_GATEWAY_MODELS,
+    _ai_gateway_model_is_free,
+    ai_gateway_model_ids,
+    fetch_ai_gateway_models,
+    fetch_ai_gateway_pricing,
+    get_pricing_for_provider,
+)
+
+
+def _mock_urlopen(payload):
+    resp = MagicMock()
+    resp.read.return_value = json.dumps(payload).encode()
+    ctx = MagicMock()
+    ctx.__enter__.return_value = resp
+    ctx.__exit__.return_value = False
+    return ctx
+
+
+def _reset_caches():
+    models_module._ai_gateway_catalog_cache = None
+    models_module._pricing_cache.clear()
+
+
+@pytest.fixture
+def config_home(tmp_path, monkeypatch):
+    home = tmp_path / "hermes"
+    home.mkdir()
+    (home / "config.yaml").write_text("model: some-old-model\n")
+    (home / ".env").write_text("")
+    monkeypatch.setenv("HERMES_HOME", str(home))
+    monkeypatch.delenv("AI_GATEWAY_API_KEY", raising=False)
+    monkeypatch.delenv("AI_GATEWAY_BASE_URL", raising=False)
+    return home
+
+
+def test_ai_gateway_provider_is_promoted_near_top_of_picker():
+    slugs = [entry.slug for entry in CANONICAL_PROVIDERS]
+    assert "ai-gateway" in slugs[:3]
+
+
+def test_ai_gateway_pricing_translates_input_output_to_prompt_completion():
+    _reset_caches()
+    payload = {
+        "data": [
+            {
+                "id": "moonshotai/kimi-k2.5",
+                "type": "language",
+                "pricing": {
+                    "input": "0.0000006",
+                    "output": "0.0000025",
+                    "input_cache_read": "0.00000015",
+                    "input_cache_write": "0.0000006",
+                },
+            }
+        ]
+    }
+    with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
+        result = fetch_ai_gateway_pricing(force_refresh=True)
+
+    entry = result["moonshotai/kimi-k2.5"]
+    assert entry["prompt"] == "0.0000006"
+    assert entry["completion"] == "0.0000025"
+    assert entry["input_cache_read"] == "0.00000015"
+    assert entry["input_cache_write"] == "0.0000006"
+
+
+def test_get_pricing_for_provider_supports_ai_gateway():
+    _reset_caches()
+    payload = {
+        "data": [
+            {
+                "id": "moonshotai/kimi-k2.5",
+                "type": "language",
+                "pricing": {"input": "0.0001", "output": "0.0002"},
+            }
+        ]
+    }
+    with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
+        result = get_pricing_for_provider("ai-gateway", force_refresh=True)
+    assert result["moonshotai/kimi-k2.5"] == {"prompt": "0.0001", "completion": "0.0002"}
+
+
+def test_ai_gateway_pricing_returns_empty_on_fetch_failure():
+    _reset_caches()
+    with patch("urllib.request.urlopen", side_effect=OSError("network down")):
+        result = fetch_ai_gateway_pricing(force_refresh=True)
+    assert result == {}
+
+
+def test_ai_gateway_pricing_skips_entries_without_pricing_dict():
+    _reset_caches()
+    payload = {
+        "data": [
+            {"id": "x/y", "pricing": None},
+            {"id": "a/b", "pricing": {"input": "0", "output": "0"}},
+        ]
+    }
+    with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
+        result = fetch_ai_gateway_pricing(force_refresh=True)
+    assert "x/y" not in result
+    assert result["a/b"] == {"prompt": "0", "completion": "0"}
+
+
+def test_ai_gateway_free_detector():
+    assert _ai_gateway_model_is_free({"input": "0", "output": "0"}) is True
+    assert _ai_gateway_model_is_free({"input": "0", "output": "0.01"}) is False
+    assert _ai_gateway_model_is_free({"input": "0.01", "output": "0"}) is False
+    assert _ai_gateway_model_is_free(None) is False
+    assert _ai_gateway_model_is_free({"input": "not a number"}) is False
+
+
+def test_fetch_ai_gateway_models_filters_against_live_catalog():
+    _reset_caches()
+    preferred = [mid for mid, _ in VERCEL_AI_GATEWAY_MODELS]
+    live_ids = preferred[:3]
+    payload = {
+        "data": [
+            {"id": mid, "pricing": {"input": "0.001", "output": "0.002"}}
+            for mid in live_ids
+        ]
+    }
+    with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
+        result = fetch_ai_gateway_models(force_refresh=True)
+
+    assert [mid for mid, _ in result] == live_ids
+    assert result[0][1] == "recommended"
+    assert ai_gateway_model_ids(force_refresh=False) == live_ids
+
+
+def test_fetch_ai_gateway_models_tags_free_models():
+    _reset_caches()
+    first_id = VERCEL_AI_GATEWAY_MODELS[0][0]
+    second_id = VERCEL_AI_GATEWAY_MODELS[1][0]
+    payload = {
+        "data": [
+            {"id": first_id, "pricing": {"input": "0.001", "output": "0.002"}},
+            {"id": second_id, "pricing": {"input": "0", "output": "0"}},
+        ]
+    }
+    with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
+        result = fetch_ai_gateway_models(force_refresh=True)
+
+    by_id = dict(result)
+    assert by_id[first_id] == "recommended"
+    assert by_id[second_id] == "free"
+
+
+def test_free_moonshot_model_auto_promoted_to_top_even_if_not_curated():
+    _reset_caches()
+    first_curated = VERCEL_AI_GATEWAY_MODELS[0][0]
+    unlisted_free_moonshot = "moonshotai/kimi-coder-free-preview"
+    payload = {
+        "data": [
+            {"id": first_curated, "pricing": {"input": "0.001", "output": "0.002"}},
+            {"id": unlisted_free_moonshot, "pricing": {"input": "0", "output": "0"}},
+        ]
+    }
+    with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
+        result = fetch_ai_gateway_models(force_refresh=True)
+
+    assert result[0] == (unlisted_free_moonshot, "recommended")
+    assert any(mid == first_curated for mid, _ in result)
+
+
+def test_paid_moonshot_does_not_get_auto_promoted():
+    _reset_caches()
+    first_curated = VERCEL_AI_GATEWAY_MODELS[0][0]
+    payload = {
+        "data": [
+            {"id": first_curated, "pricing": {"input": "0.001", "output": "0.002"}},
+            {"id": "moonshotai/some-paid-variant", "pricing": {"input": "0.001", "output": "0.002"}},
+        ]
+    }
+    with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
+        result = fetch_ai_gateway_models(force_refresh=True)
+
+    assert result[0][0] == first_curated
+
+
+def test_fetch_ai_gateway_models_falls_back_on_error():
+    _reset_caches()
+    with patch("urllib.request.urlopen", side_effect=OSError("network")):
+        result = fetch_ai_gateway_models(force_refresh=True)
+    assert result == list(VERCEL_AI_GATEWAY_MODELS)
+
+
+def test_ai_gateway_setup_flow_shows_deeplink_and_passes_pricing(config_home, monkeypatch, capsys):
+    from hermes_cli.main import _model_flow_ai_gateway
+    from hermes_cli.config import load_config
+
+    pricing = {"moonshotai/kimi-k2.6": {"prompt": "0", "completion": "0"}}
+    monkeypatch.setenv("HERMES_HOME", str(config_home))
+
+    with patch("getpass.getpass", return_value="vercel-key"), \
+         patch("hermes_cli.models.ai_gateway_model_ids", return_value=["moonshotai/kimi-k2.6"]), \
+         patch("hermes_cli.models.get_pricing_for_provider", return_value=pricing), \
+         patch("hermes_cli.auth._prompt_model_selection", return_value="moonshotai/kimi-k2.6") as prompt_selection, \
+         patch("hermes_cli.auth.deactivate_provider"):
+        _model_flow_ai_gateway(load_config(), "")
+
+    out = capsys.readouterr().out
+    assert "vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai-gateway&title=AI+Gateway" in out
+    assert "free credits" in out.lower()
+    assert prompt_selection.call_args.kwargs["pricing"] == pricing
+
+    import yaml
+    config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
+    model = config["model"]
+    assert model["provider"] == "ai-gateway"
+    assert model["api_mode"] == "chat_completions"
--- a/tests/run_agent/test_provider_attribution_headers.py
+++ b/tests/run_agent/test_provider_attribution_headers.py
@@ -0,0 +1,62 @@
+"""Attribution default_headers applied per provider via base-URL detection."""
+
+from unittest.mock import MagicMock, patch
+
+from run_agent import AIAgent
+
+
+@patch("run_agent.OpenAI")
+def test_openrouter_base_url_applies_or_headers(mock_openai):
+    mock_openai.return_value = MagicMock()
+    agent = AIAgent(
+        api_key="test-key",
+        base_url="https://openrouter.ai/api/v1",
+        model="test/model",
+        quiet_mode=True,
+        skip_context_files=True,
+        skip_memory=True,
+    )
+
+    agent._apply_client_headers_for_base_url("https://openrouter.ai/api/v1")
+
+    headers = agent._client_kwargs["default_headers"]
+    assert headers["HTTP-Referer"] == "https://hermes-agent.nousresearch.com"
+    assert headers["X-OpenRouter-Title"] == "Hermes Agent"
+
+
+@patch("run_agent.OpenAI")
+def test_ai_gateway_base_url_applies_attribution_headers(mock_openai):
+    mock_openai.return_value = MagicMock()
+    agent = AIAgent(
+        api_key="test-key",
+        base_url="https://openrouter.ai/api/v1",
+        model="test/model",
+        quiet_mode=True,
+        skip_context_files=True,
+        skip_memory=True,
+    )
+
+    agent._apply_client_headers_for_base_url("https://ai-gateway.vercel.sh/v1")
+
+    headers = agent._client_kwargs["default_headers"]
+    assert headers["HTTP-Referer"] == "https://hermes-agent.nousresearch.com"
+    assert headers["X-Title"] == "Hermes Agent"
+    assert headers["User-Agent"].startswith("HermesAgent/")
+
+
+@patch("run_agent.OpenAI")
+def test_unknown_base_url_clears_default_headers(mock_openai):
+    mock_openai.return_value = MagicMock()
+    agent = AIAgent(
+        api_key="test-key",
+        base_url="https://openrouter.ai/api/v1",
+        model="test/model",
+        quiet_mode=True,
+        skip_context_files=True,
+        skip_memory=True,
+    )
+    agent._client_kwargs["default_headers"] = {"X-Stale": "yes"}
+
+    agent._apply_client_headers_for_base_url("https://api.example.com/v1")
+
+    assert "default_headers" not in agent._client_kwargs
--- a/tests/tools/test_registry.py
+++ b/tests/tools/test_registry.py
@@ -294,32 +294,22 @@ class TestBuiltinDiscovery:
            "tools.browser_tool",
            "tools.clarify_tool",
            "tools.code_execution_tool",
-            "tools.crisis_tool",
            "tools.cronjob_tools",
            "tools.delegate_tool",
            "tools.file_tools",
            "tools.homeassistant_tool",
            "tools.image_generation_tool",
-            "tools.local_inference_tool",
            "tools.memory_tool",
            "tools.mixture_of_agents_tool",
            "tools.process_registry",
            "tools.rl_training_tool",
-            "tools.scavenger_fixer",
            "tools.send_message_tool",
            "tools.session_search_tool",
            "tools.skill_manager_tool",
            "tools.skills_tool",
-            "tools.sovereign_router",
-            "tools.sovereign_scavenger",
-            "tools.sovereign_teleport",
-            "tools.static_analyzer",
-            "tools.symbolic_verify",
            "tools.terminal_tool",
            "tools.todo_tool",
            "tools.tts_tool",
-            "tools.ultraplan",
-            "tools.verify_tool",
            "tools.vision_tools",
            "tools.web_tools",
        }
--- a/tests/tools/test_ultraplan_tool.py
+++ b/tests/tools/test_ultraplan_tool.py
@@ -1,81 +0,0 @@
-import json
-from pathlib import Path
-
-from toolsets import resolve_toolset
-from tools.registry import registry
-
-
-def test_create_action_saves_markdown_and_json(tmp_path):
-    from tools.ultraplan import ultraplan_tool
-
-    result = json.loads(
-        ultraplan_tool(
-            action="create",
-            mission="Daily autonomous planning",
-            streams=[
-                {
-                    "id": "A",
-                    "name": "Backlog burn",
-                    "phases": [
-                        {"id": "A1", "name": "Triage", "artifact": "issue list"},
-                        {"id": "A2", "name": "Ship", "dependencies": ["A1"], "artifact": "PR"},
-                    ],
-                }
-            ],
-            base_dir=str(tmp_path),
-        )
-    )
-
-    assert result["success"] is True
-    assert Path(result["file_path"]).exists()
-    assert Path(result["json_path"]).exists()
-    assert "Work Streams" in Path(result["file_path"]).read_text(encoding="utf-8")
-
-
-def test_load_action_returns_saved_plan(tmp_path):
-    from tools.ultraplan import ultraplan_tool
-
-    created = json.loads(
-        ultraplan_tool(
-            action="create",
-            date="20260422",
-            mission="Mission from saved plan",
-            base_dir=str(tmp_path),
-        )
-    )
-    loaded = json.loads(
-        ultraplan_tool(
-            action="load",
-            date="20260422",
-            base_dir=str(tmp_path),
-        )
-    )
-
-    assert created["success"] is True
-    assert loaded["success"] is True
-    assert loaded["plan"]["mission"] == "Mission from saved plan"
-    assert loaded["file_path"].endswith("ultraplan_20260422.md")
-
-
-def test_cron_spec_returns_daily_schedule_and_prompt():
-    from tools.ultraplan import ultraplan_tool
-
-    result = json.loads(ultraplan_tool(action="cron_spec"))
-
-    assert result["success"] is True
-    assert result["schedule"] == "0 6 * * *"
-    assert "Ultraplan" in result["prompt"]
-    assert "ultraplan_YYYYMMDD.md" in result["prompt"]
-
-
-def test_registry_registers_ultraplan_tool():
-    import tools.ultraplan  # noqa: F401
-
-    entry = registry.get_entry("ultraplan")
-    assert entry is not None
-    assert entry.toolset == "todo"
-
-
-def test_default_toolsets_include_ultraplan():
-    assert "ultraplan" in resolve_toolset("todo")
-    assert "ultraplan" in resolve_toolset("hermes-cli")
--- a/tools/ultraplan.py
+++ b/tools/ultraplan.py
@@ -290,9 +290,6 @@ def load_ultraplan(date: str, base_dir: Path = None) -> Optional[Ultraplan]:
        return None


-DEFAULT_ULTRAPLAN_SCHEDULE = "0 6 * * *"
-
-
 def generate_daily_cron_prompt() -> str:
    """Generate the prompt for the daily ultraplan cron job."""
    return """Generate today's Ultraplan.
@@ -301,9 +298,9 @@ Steps:
 1. Check open Gitea issues assigned to you
 2. Check open PRs needing review
 3. Check fleet health status
-4. Decompose work into parallel streams with concrete phases and artifacts
-5. Use the ultraplan tool to save ~/.timmy/cron/ultraplan_YYYYMMDD.md and the matching JSON sidecar
-6. Optionally file a Gitea issue with the plan summary
+4. Decompose work into parallel streams
+5. Generate ultraplan_YYYYMMDD.md
+6. File Gitea issue with the plan

 Output format:
 - Mission statement
@@ -311,176 +308,3 @@ Output format:
 - Dependency map
 - Success metrics
 """
-
-
-def generate_daily_cron_job_spec(schedule: str = DEFAULT_ULTRAPLAN_SCHEDULE) -> Dict[str, str]:
-    """Return a reusable cron job spec for daily Ultraplan generation."""
-    return {
-        "name": "Daily Ultraplan",
-        "schedule": schedule,
-        "prompt": generate_daily_cron_prompt(),
-        "path_pattern": "~/.timmy/cron/ultraplan_YYYYMMDD.md",
-    }
-
-
-def _resolve_base_dir(base_dir: Optional[str | Path]) -> Path:
-    """Normalize the requested Ultraplan base directory."""
-    if base_dir is None:
-        return Path.home() / ".timmy" / "cron"
-    return Path(base_dir).expanduser()
-
-
-def ultraplan_tool(
-    action: str,
-    date: Optional[str] = None,
-    mission: str = "",
-    streams: Optional[List[Dict[str, Any]]] = None,
-    metrics: Optional[Dict[str, Any]] = None,
-    notes: str = "",
-    base_dir: Optional[str] = None,
-) -> str:
-    """Create/load Ultraplan artifacts and expose a daily cron spec."""
-    from tools.registry import tool_error, tool_result
-
-    action = (action or "").strip().lower()
-    resolved_base_dir = _resolve_base_dir(base_dir)
-
-    try:
-        if action == "create":
-            plan = create_ultraplan(date=date, mission=mission, streams=streams or [])
-            if metrics:
-                plan.metrics = metrics
-            if notes:
-                plan.notes = notes
-            md_path = save_ultraplan(plan, base_dir=resolved_base_dir)
-            json_path = resolved_base_dir / f"ultraplan_{plan.date}.json"
-            return tool_result(
-                success=True,
-                action="create",
-                date=plan.date,
-                file_path=str(md_path),
-                json_path=str(json_path),
-                plan=plan.to_dict(),
-            )
-
-        if action == "load":
-            plan_date = date or datetime.now().strftime("%Y%m%d")
-            plan = load_ultraplan(plan_date, base_dir=resolved_base_dir)
-            if plan is None:
-                return tool_error(
-                    f"No Ultraplan found for {plan_date}",
-                    success=False,
-                    action="load",
-                    date=plan_date,
-                )
-            return tool_result(
-                success=True,
-                action="load",
-                date=plan.date,
-                file_path=str(resolved_base_dir / f"ultraplan_{plan.date}.md"),
-                json_path=str(resolved_base_dir / f"ultraplan_{plan.date}.json"),
-                plan=plan.to_dict(),
-                markdown=plan.to_markdown(),
-            )
-
-        if action == "cron_spec":
-            spec = generate_daily_cron_job_spec()
-            return tool_result(success=True, action="cron_spec", **spec)
-
-        return tool_error(
-            f"Unknown Ultraplan action: {action}",
-            success=False,
-            action=action,
-        )
-    except Exception as e:
-        return tool_error(f"Ultraplan {action or 'tool'} failed: {e}", success=False, action=action)
-
-
-ULTRAPLAN_SCHEMA = {
-    "name": "ultraplan",
-    "description": (
-        "Create or load daily Ultraplan planning artifacts under ~/.timmy/cron/ and "
-        "return a reusable cron spec for autonomous planning. Use this when you want "
-        "a concrete markdown/json plan file with streams, phases, dependencies, and metrics."
-    ),
-    "parameters": {
-        "type": "object",
-        "properties": {
-            "action": {
-                "type": "string",
-                "enum": ["create", "load", "cron_spec"],
-                "description": "Operation to perform",
-            },
-            "date": {
-                "type": "string",
-                "description": "Plan date as YYYYMMDD. Defaults to today for create/load.",
-            },
-            "mission": {
-                "type": "string",
-                "description": "High-level mission statement for today's plan.",
-            },
-            "streams": {
-                "type": "array",
-                "description": "Optional work streams with phases/artifacts/dependencies for create.",
-                "items": {
-                    "type": "object",
-                    "properties": {
-                        "id": {"type": "string"},
-                        "name": {"type": "string"},
-                        "phases": {
-                            "type": "array",
-                            "items": {
-                                "type": "object",
-                                "properties": {
-                                    "id": {"type": "string"},
-                                    "name": {"type": "string"},
-                                    "description": {"type": "string"},
-                                    "artifact": {"type": "string"},
-                                    "dependencies": {
-                                        "type": "array",
-                                        "items": {"type": "string"},
-                                    },
-                                },
-                                "required": ["name"],
-                            },
-                        },
-                    },
-                    "required": ["name"],
-                },
-            },
-            "metrics": {
-                "type": "object",
-                "description": "Optional success metrics to store on the plan.",
-                "additionalProperties": True,
-            },
-            "notes": {
-                "type": "string",
-                "description": "Optional free-form notes appended to the saved plan.",
-            },
-            "base_dir": {
-                "type": "string",
-                "description": "Optional override for the Ultraplan storage directory.",
-            },
-        },
-        "required": ["action"],
-    },
-}
-
-
-from tools.registry import registry
-
-registry.register(
-    name="ultraplan",
-    toolset="todo",
-    schema=ULTRAPLAN_SCHEMA,
-    handler=lambda args, **_kw: ultraplan_tool(
-        action=args.get("action", ""),
-        date=args.get("date"),
-        mission=args.get("mission", ""),
-        streams=args.get("streams"),
-        metrics=args.get("metrics"),
-        notes=args.get("notes", ""),
-        base_dir=args.get("base_dir"),
-    ),
-    emoji="🗺️",
-)
--- a/toolsets.py
+++ b/toolsets.py
@@ -47,7 +47,7 @@ _HERMES_CORE_TOOLS = [
    # Text-to-speech
    "text_to_speech",
    # Planning & memory
-    "todo", "ultraplan", "memory",
+    "todo", "memory",
    # Session history search
    "session_search",
    # Clarifying questions
@@ -157,8 +157,8 @@ TOOLSETS = {
    },
    
    "todo": {
-        "description": "Task planning and tracking for multi-step work, including daily Ultraplan artifacts",
-        "tools": ["todo", "ultraplan"],
+        "description": "Task planning and tracking for multi-step work",
+        "tools": ["todo"],
        "includes": []
    },