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

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,

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 (

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:

plugins/memory/holographic/__init__.py

@@ -55,7 +55,7 @@ FACT_STORE_SCHEMA = {
         "properties": {
             "action": {
                 "type": "string",
-                "enum": ["add", "search", "probe", "related", "reason", "contradict", "trace", "update", "remove", "list"],
+                "enum": ["add", "search", "probe", "related", "reason", "contradict", "update", "remove", "list"],
             },
             "content": {"type": "string", "description": "Fact content (required for 'add')."},
             "query": {"type": "string", "description": "Search query (required for 'search')."},
@@ -67,13 +67,6 @@ FACT_STORE_SCHEMA = {
             "trust_delta": {"type": "number", "description": "Trust adjustment for 'update'."},
             "min_trust": {"type": "number", "description": "Minimum trust filter (default: 0.3)."},
             "limit": {"type": "integer", "description": "Max results (default: 10)."},
-            "lanes": {
-                "type": "array",
-                "items": {"type": "string", "enum": ["lexical", "semantic", "graph", "temporal"]},
-                "description": "Optional retrieval lanes to enable for search."
-            },
-            "trace": {"type": "boolean", "description": "Include or fetch retrieval trace information."},
-            "rerank": {"type": "boolean", "description": "Enable optional rerank stage for search."},
         },
         "required": ["action"],
     },
@@ -126,9 +119,6 @@ class HolographicMemoryProvider(MemoryProvider):
         self._store = None
         self._retriever = None
         self._min_trust = float(self._config.get("min_trust_threshold", 0.3))
-        self._retrieval_lanes = self._parse_retrieval_lanes(self._config.get("retrieval_lanes"))
-        self._enable_rerank = str(self._config.get("enable_rerank", "true")).lower() != "false"
-        self._last_retrieval_trace: dict | None = None
 
     @property
     def name(self) -> str:
@@ -154,14 +144,6 @@ class HolographicMemoryProvider(MemoryProvider):
         except Exception:
             pass
 
-    def _parse_retrieval_lanes(self, value) -> list[str]:
-        if isinstance(value, str):
-            value = [part.strip() for part in value.split(",") if part.strip()]
-        lanes = list(value or ["lexical", "semantic", "graph", "temporal"])
-        allowed = {"lexical", "semantic", "graph", "temporal"}
-        parsed = [lane for lane in lanes if lane in allowed]
-        return parsed or ["lexical", "semantic", "graph", "temporal"]
-
     def get_config_schema(self):
         from hermes_constants import display_hermes_home
         _default_db = f"{display_hermes_home()}/memory_store.db"
@@ -170,10 +152,6 @@ class HolographicMemoryProvider(MemoryProvider):
             {"key": "auto_extract", "description": "Auto-extract facts at session end", "default": "false", "choices": ["true", "false"]},
             {"key": "default_trust", "description": "Default trust score for new facts", "default": "0.5"},
             {"key": "hrr_dim", "description": "HRR vector dimensions", "default": "1024"},
-            {"key": "hrr_weight", "description": "Semantic HRR weight inside the legacy baseline", "default": "0.3"},
-            {"key": "temporal_decay_half_life", "description": "Temporal decay half-life in days (0 disables baseline decay)", "default": "0"},
-            {"key": "retrieval_lanes", "description": "Comma-separated retrieval lanes (lexical,semantic,graph,temporal)", "default": "lexical,semantic,graph,temporal"},
-            {"key": "enable_rerank", "description": "Enable optional local rerank stage", "default": "true", "choices": ["true", "false"]},
         ]
 
     def initialize(self, session_id: str, **kwargs) -> None:
@@ -191,8 +169,6 @@ class HolographicMemoryProvider(MemoryProvider):
         hrr_dim = int(self._config.get("hrr_dim", 1024))
         hrr_weight = float(self._config.get("hrr_weight", 0.3))
         temporal_decay = int(self._config.get("temporal_decay_half_life", 0))
-        self._retrieval_lanes = self._parse_retrieval_lanes(self._config.get("retrieval_lanes", self._retrieval_lanes))
-        self._enable_rerank = str(self._config.get("enable_rerank", self._enable_rerank)).lower() != "false"
 
         self._store = MemoryStore(db_path=db_path, default_trust=default_trust, hrr_dim=hrr_dim)
         self._retriever = FactRetriever(
@@ -200,8 +176,6 @@ class HolographicMemoryProvider(MemoryProvider):
             temporal_decay_half_life=temporal_decay,
             hrr_weight=hrr_weight,
             hrr_dim=hrr_dim,
-            retrieval_lanes=self._retrieval_lanes,
-            enable_rerank=self._enable_rerank,
         )
         self._session_id = session_id
 
@@ -232,23 +206,13 @@ class HolographicMemoryProvider(MemoryProvider):
         if not self._retriever or not query:
             return ""
         try:
-            payload = self._retriever.search_with_trace(
-                query,
-                min_trust=self._min_trust,
-                limit=5,
-                lanes=self._retrieval_lanes,
-                rerank=self._enable_rerank,
-            )
-            self._last_retrieval_trace = payload["trace"]
-            results = payload["results"]
+            results = self._retriever.search(query, min_trust=self._min_trust, limit=5)
             if not results:
                 return ""
             lines = []
             for r in results:
                 trust = r.get("trust_score", r.get("trust", 0))
-                lanes = ",".join(r.get("matched_lanes", []))
-                lane_suffix = f" [{lanes}]" if lanes else ""
-                lines.append(f"- [{trust:.1f}] {r.get('content', '')}{lane_suffix}")
+                lines.append(f"- [{trust:.1f}] {r.get('content', '')}")
             return "## Holographic Memory\n" + "\n".join(lines)
         except Exception as e:
             logger.debug("Holographic prefetch failed: %s", e)
@@ -306,39 +270,14 @@ class HolographicMemoryProvider(MemoryProvider):
                 return json.dumps({"fact_id": fact_id, "status": "added"})
 
             elif action == "search":
-                lanes = args.get("lanes")
-                rerank = args.get("rerank")
-                with_trace = bool(args.get("trace", False))
-                if with_trace:
-                    payload = retriever.search_with_trace(
-                        args["query"],
-                        category=args.get("category"),
-                        min_trust=float(args.get("min_trust", self._min_trust)),
-                        limit=int(args.get("limit", 10)),
-                        lanes=lanes,
-                        rerank=rerank,
-                    )
-                    self._last_retrieval_trace = payload["trace"]
-                    return json.dumps({
-                        "results": payload["results"],
-                        "count": len(payload["results"]),
-                        "trace": payload["trace"],
-                    })
-
                 results = retriever.search(
                     args["query"],
                     category=args.get("category"),
                     min_trust=float(args.get("min_trust", self._min_trust)),
                     limit=int(args.get("limit", 10)),
-                    lanes=lanes,
-                    rerank=rerank,
                 )
-                self._last_retrieval_trace = retriever.last_trace
                 return json.dumps({"results": results, "count": len(results)})
 
-            elif action == "trace":
-                return json.dumps({"trace": self._last_retrieval_trace or retriever.last_trace or {}})
-
             elif action == "probe":
                 results = retriever.probe(
                     args["entity"],
@@ -384,8 +323,7 @@ class HolographicMemoryProvider(MemoryProvider):
                 return json.dumps({"updated": updated})
 
             elif action == "remove":
-                removed = store.remove_fact(int(args["fact_id"])
-                )
+                removed = store.remove_fact(int(args["fact_id"]))
                 return json.dumps({"removed": removed})
 
             elif action == "list":

plugins/memory/holographic/store.py

@@ -83,7 +83,6 @@ _TRUST_MAX       =  1.0
 
 # Entity extraction patterns
 _RE_CAPITALIZED  = re.compile(r'\b([A-Z][a-z]+(?:\s+[A-Z][a-z]+)+)\b')
-_RE_SINGLE_PROPER = re.compile(r'\b([A-Z][A-Za-z0-9_-]{2,})\b')
 _RE_DOUBLE_QUOTE = re.compile(r'"([^"]+)"')
 _RE_SINGLE_QUOTE = re.compile(r"'([^']+)'")
 _RE_AKA          = re.compile(
@@ -415,13 +414,6 @@ class MemoryStore:
         for m in _RE_CAPITALIZED.finditer(text):
             _add(m.group(1))
 
-        skip_singletons = {"The", "This", "That", "These", "Those", "And", "But", "For", "With"}
-        for m in _RE_SINGLE_PROPER.finditer(text):
-            candidate = m.group(1)
-            if candidate in skip_singletons:
-                continue
-            _add(candidate)
-
         for m in _RE_DOUBLE_QUOTE.finditer(text):
             _add(m.group(1))
 

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
 

tests/fixtures/holographic_recall_matrix.json

@@ -1,56 +0,0 @@
-{
-  "facts": [
-    {
-      "content": "Alexander Whitestone aka Rockachopa.",
-      "category": "general",
-      "tags": "identity alias"
-    },
-    {
-      "content": "Rockachopa uses Ansible playbooks for sovereign rollouts.",
-      "category": "project",
-      "tags": "ansible playbooks rollout"
-    },
-    {
-      "content": "The provider is anthropic/claude-haiku-4-5.",
-      "category": "project",
-      "tags": "provider default",
-      "updated_at": "2026-01-01T00:00:00Z"
-    },
-    {
-      "content": "Correction: the provider is mimo-v2-pro.",
-      "category": "project",
-      "tags": "provider current",
-      "updated_at": "2026-04-20T00:00:00Z"
-    },
-    {
-      "content": "Ezra operates the BURN2 lane for forge work.",
-      "category": "project",
-      "tags": "ezra burn2 forge lane"
-    },
-    {
-      "content": "BURN2 handles forge triage and review.",
-      "category": "project",
-      "tags": "forge triage review"
-    }
-  ],
-  "queries": [
-    {
-      "name": "semantic_alias_graph",
-      "query": "What automation does Alexander Whitestone use for deploys?",
-      "expected_substring": "Ansible playbooks",
-      "top_k": 1
-    },
-    {
-      "name": "temporal_correction",
-      "query": "What provider should we use?",
-      "expected_substring": "mimo-v2-pro",
-      "top_k": 1
-    },
-    {
-      "name": "graph_lane",
-      "query": "Which forge lane does Ezra operate?",
-      "expected_substring": "BURN2 lane",
-      "top_k": 1
-    }
-  ]
-}

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"

tests/plugins/memory/test_holographic_retrieval.py

@@ -1,116 +0,0 @@
-"""Tests for multi-path holographic retrieval fusion and traceability."""
-
-from __future__ import annotations
-
-import json
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).resolve().parents[3]))
-
-from plugins.memory.holographic import HolographicMemoryProvider
-from plugins.memory.holographic.retrieval import FactRetriever, format_benchmark_report
-from plugins.memory.holographic.store import MemoryStore
-
-_FIXTURE_PATH = Path(__file__).resolve().parents[2] / "fixtures" / "holographic_recall_matrix.json"
-
-
-def _fixture() -> dict:
-    return json.loads(_FIXTURE_PATH.read_text())
-
-
-def _seed_store(tmp_path) -> MemoryStore:
-    store = MemoryStore(db_path=tmp_path / "memory_store.db")
-    for fact in _fixture()["facts"]:
-        fact_id = store.add_fact(fact["content"], category=fact["category"], tags=fact.get("tags", ""))
-        if fact.get("updated_at"):
-            store._conn.execute(
-                "UPDATE facts SET created_at = ?, updated_at = ? WHERE fact_id = ?",
-                (fact["updated_at"], fact["updated_at"], fact_id),
-            )
-    store._conn.commit()
-    return store
-
-
-class TestMultiPathRetrieval:
-    def test_lane_toggle_and_trace_contributions(self, tmp_path):
-        store = _seed_store(tmp_path)
-        retriever = FactRetriever(store=store)
-
-        payload = retriever.search_with_trace(
-            "Which forge lane does Ezra operate?",
-            limit=3,
-            lanes=["lexical", "graph"],
-        )
-
-        assert payload["trace"]["lanes_run"] == ["lexical", "graph"]
-        assert payload["results"]
-        top = payload["results"][0]
-        assert "BURN2 lane" in top["content"]
-        assert "graph" in top["lane_contributions"]
-        assert set(top["lane_contributions"]).issubset({"lexical", "graph"})
-
-    def test_trace_available_for_failed_recall(self, tmp_path):
-        store = _seed_store(tmp_path)
-        retriever = FactRetriever(store=store)
-
-        payload = retriever.search_with_trace(
-            "nonexistent memory topic xyz123",
-            limit=3,
-            lanes=["lexical", "semantic", "graph", "temporal"],
-        )
-
-        assert payload["results"] == []
-        assert payload["trace"]["fused_count"] == 0
-        assert payload["trace"]["lane_hits"]["lexical"] == 0
-        assert payload["trace"]["lane_hits"]["semantic"] == 0
-
-    def test_benchmark_prompt_matrix_shows_gain_over_baseline(self, tmp_path):
-        store = _seed_store(tmp_path)
-        retriever = FactRetriever(store=store)
-        report = retriever.benchmark_prompt_matrix(_fixture()["queries"], limit=3)
-
-        assert report["fused_top1_hits"] > report["baseline_top1_hits"]
-        assert report["improvement"] > 0
-
-        rendered = format_benchmark_report(report)
-        assert "Prompt matrix benchmark" in rendered
-        assert "semantic_alias_graph" in rendered
-        assert "improvement" in rendered.lower()
-
-
-class TestHolographicProviderTrace:
-    def test_prefetch_records_trace_and_trace_action_returns_it(self, tmp_path):
-        provider = HolographicMemoryProvider(
-            config={
-                "db_path": str(tmp_path / "provider.db"),
-                "retrieval_lanes": ["lexical", "semantic", "graph", "temporal"],
-                "enable_rerank": True,
-            }
-        )
-        provider.initialize("test-session")
-
-        seed_store = _seed_store(tmp_path / "seed")
-        rows = seed_store.list_facts(min_trust=0.0, limit=20)
-        for row in rows:
-            provider._store.add_fact(row["content"], category=row["category"], tags=row.get("tags", ""))
-            if row["content"].startswith("The provider is anthropic"):
-                provider._store._conn.execute(
-                    "UPDATE facts SET created_at = ?, updated_at = ? WHERE content = ?",
-                    ("2026-01-01T00:00:00Z", "2026-01-01T00:00:00Z", row["content"]),
-                )
-            elif row["content"].startswith("Correction: the provider is mimo"):
-                provider._store._conn.execute(
-                    "UPDATE facts SET created_at = ?, updated_at = ? WHERE content = ?",
-                    ("2026-04-20T00:00:00Z", "2026-04-20T00:00:00Z", row["content"]),
-                )
-        provider._store._conn.commit()
-
-        block = provider.prefetch("What provider should we use?")
-        assert "Holographic Memory" in block
-        assert "mimo-v2-pro" in block
-
-        trace_payload = json.loads(provider.handle_tool_call("fact_store", {"action": "trace"}))
-        assert trace_payload["trace"]["query"] == "What provider should we use?"
-        assert trace_payload["trace"]["rerank_applied"] in {True, False}
-        assert trace_payload["trace"]["lane_hits"]["temporal"] >= 1

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