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:

optional-skills/dogfood/adversarial-ux-test/SKILL.md

@@ -1,190 +0,0 @@
----
-name: adversarial-ux-test
-description: Roleplay the most difficult, tech-resistant user for your product. Browse the app as that persona, find every UX pain point, then filter complaints through a pragmatism layer to separate real problems from noise. Creates actionable tickets from genuine issues only.
-version: 1.0.0
-author: Omni @ Comelse
-license: MIT
-metadata:
-  hermes:
-    tags: [qa, ux, testing, adversarial, dogfood, personas, user-testing]
-    related_skills: [dogfood]
----
-
-# Adversarial UX Test
-
-Roleplay the worst-case user for your product — the person who hates technology, doesn't want your software, and will find every reason to complain. Then filter their feedback through a pragmatism layer to separate real UX problems from "I hate computers" noise.
-
-Think of it as an automated "mom test" — but angry.
-
-## Why This Works
-
-Most QA finds bugs. This finds **friction**. A technically correct app can still be unusable for real humans. The adversarial persona catches:
-- Confusing terminology that makes sense to developers but not users
-- Too many steps to accomplish basic tasks
-- Missing onboarding or "aha moments"
-- Accessibility issues (font size, contrast, click targets)
-- Cold-start problems (empty states, no demo content)
-- Paywall/signup friction that kills conversion
-
-The **pragmatism filter** (Phase 3) is what makes this useful instead of just entertaining. Without it, you'd add a "print this page" button to every screen because Grandpa can't figure out PDFs.
-
-## How to Use
-
-Tell the agent:
-```
-"Run an adversarial UX test on [URL]"
-"Be a grumpy [persona type] and test [app name]"
-"Do an asshole user test on my staging site"
-```
-
-You can provide a persona or let the agent generate one based on your product's target audience.
-
-## Step 1: Define the Persona
-
-If no persona is provided, generate one by answering:
-
-1. **Who is the HARDEST user for this product?** (age 50+, non-technical role, decades of experience doing it "the old way")
-2. **What is their tech comfort level?** (the lower the better — WhatsApp-only, paper notebooks, wife set up their email)
-3. **What is the ONE thing they need to accomplish?** (their core job, not your feature list)
-4. **What would make them give up?** (too many clicks, jargon, slow, confusing)
-5. **How do they talk when frustrated?** (blunt, sweary, dismissive, sighing)
-
-### Good Persona Example
-> **"Big Mick" McAllister** — 58-year-old S&C coach. Uses WhatsApp and that's it. His "spreadsheet" is a paper notebook. "If I can't figure it out in 10 seconds I'm going back to my notebook." Needs to log session results for 25 players. Hates small text, jargon, and passwords.
-
-### Bad Persona Example
-> "A user who doesn't like the app" — too vague, no constraints, no voice.
-
-The persona must be **specific enough to stay in character** for 20 minutes of testing.
-
-## Step 2: Become the Asshole (Browse as the Persona)
-
-1. Read any available project docs for app context and URLs
-2. **Fully inhabit the persona** — their frustrations, limitations, goals
-3. Navigate to the app using browser tools
-4. **Attempt the persona's ACTUAL TASKS** (not a feature tour):
-   - Can they do what they came to do?
-   - How many clicks/screens to accomplish it?
-   - What confuses them?
-   - What makes them angry?
-   - Where do they get lost?
-   - What would make them give up and go back to their old way?
-
-5. Test these friction categories:
-   - **First impression** — would they even bother past the landing page?
-   - **Core workflow** — the ONE thing they need to do most often
-   - **Error recovery** — what happens when they do something wrong?
-   - **Readability** — text size, contrast, information density
-   - **Speed** — does it feel faster than their current method?
-   - **Terminology** — any jargon they wouldn't understand?
-   - **Navigation** — can they find their way back? do they know where they are?
-
-6. Take screenshots of every pain point
-7. Check browser console for JS errors on every page
-
-## Step 3: The Rant (Write Feedback in Character)
-
-Write the feedback AS THE PERSONA — in their voice, with their frustrations. This is not a bug report. This is a real human venting.
-
-```
-[PERSONA NAME]'s Review of [PRODUCT]
-
-Overall: [Would they keep using it? Yes/No/Maybe with conditions]
-
-THE GOOD (grudging admission):
-- [things even they have to admit work]
-
-THE BAD (legitimate UX issues):
-- [real problems that would stop them from using the product]
-
-THE UGLY (showstoppers):
-- [things that would make them uninstall/cancel immediately]
-
-SPECIFIC COMPLAINTS:
-1. [Page/feature]: "[quote in persona voice]" — [what happened, expected]
-2. ...
-
-VERDICT: "[one-line persona quote summarizing their experience]"
-```
-
-## Step 4: The Pragmatism Filter (Critical — Do Not Skip)
-
-Step OUT of the persona. Evaluate each complaint as a product person:
-
-- **RED: REAL UX BUG** — Any user would have this problem, not just grumpy ones. Fix it.
-- **YELLOW: VALID BUT LOW PRIORITY** — Real issue but only for extreme users. Note it.
-- **WHITE: PERSONA NOISE** — "I hate computers" talking, not a product problem. Skip it.
-- **GREEN: FEATURE REQUEST** — Good idea hidden in the complaint. Consider it.
-
-### Filter Criteria
-1. Would a 35-year-old competent-but-busy user have the same complaint? → RED
-2. Is this a genuine accessibility issue (font size, contrast, click targets)? → RED
-3. Is this "I want it to work like paper" resistance to digital? → WHITE
-4. Is this a real workflow inefficiency the persona stumbled on? → YELLOW or RED
-5. Would fixing this add complexity for the 80% who are fine? → WHITE
-6. Does the complaint reveal a missing onboarding moment? → GREEN
-
-**This filter is MANDATORY.** Never ship raw persona complaints as tickets.
-
-## Step 5: Create Tickets
-
-For **RED** and **GREEN** items only:
-- Clear, actionable title
-- Include the persona's verbatim quote (entertaining + memorable)
-- The real UX issue underneath (objective)
-- A suggested fix (actionable)
-- Tag/label: "ux-review"
-
-For **YELLOW** items: one catch-all ticket with all notes.
-
-**WHITE** items appear in the report only. No tickets.
-
-**Max 10 tickets per session** — focus on the worst issues.
-
-## Step 6: Report
-
-Deliver:
-1. The persona rant (Step 3) — entertaining and visceral
-2. The filtered assessment (Step 4) — pragmatic and actionable
-3. Tickets created (Step 5) — with links
-4. Screenshots of key issues
-
-## Tips
-
-- **One persona per session.** Don't mix perspectives.
-- **Stay in character during Steps 2-3.** Break character only at Step 4.
-- **Test the CORE WORKFLOW first.** Don't get distracted by settings pages.
-- **Empty states are gold.** New user experience reveals the most friction.
-- **The best findings are RED items the persona found accidentally** while trying to do something else.
-- **If the persona has zero complaints, your persona is too tech-savvy.** Make them older, less patient, more set in their ways.
-- **Run this before demos, launches, or after shipping a batch of features.**
-- **Register as a NEW user when possible.** Don't use pre-seeded admin accounts — the cold start experience is where most friction lives.
-- **Zero WHITE items is a signal, not a failure.** If the pragmatism filter finds no noise, your product has real UX problems, not just a grumpy persona.
-- **Check known issues in project docs AFTER the test.** If the persona found a bug that's already in the known issues list, that's actually the most damning finding — it means the team knew about it but never felt the user's pain.
-- **Subscription/paywall testing is critical.** Test with expired accounts, not just active ones. The "what happens when you can't pay" experience reveals whether the product respects users or holds their data hostage.
-- **Count the clicks to accomplish the persona's ONE task.** If it's more than 5, that's almost always a RED finding regardless of persona tech level.
-
-## Example Personas by Industry
-
-These are starting points — customize for your specific product:
-
-| Product Type | Persona | Age | Key Trait |
-|-------------|---------|-----|-----------|
-| CRM | Retirement home director | 68 | Filing cabinet is the current CRM |
-| Photography SaaS | Rural wedding photographer | 62 | Books clients by phone, invoices on paper |
-| AI/ML Tool | Department store buyer | 55 | Burned by 3 failed tech startups |
-| Fitness App | Old-school gym coach | 58 | Paper notebook, thick fingers, bad eyes |
-| Accounting | Family bakery owner | 64 | Shoebox of receipts, hates subscriptions |
-| E-commerce | Market stall vendor | 60 | Cash only, smartphone is for calls |
-| Healthcare | Senior GP | 63 | Dictates notes, nurse handles the computer |
-| Education | Veteran teacher | 57 | Chalk and talk, worksheets in ring binders |
-
-## Rules
-
-- Stay in character during Steps 2-3
-- Be genuinely mean but fair — find real problems, not manufactured ones
-- The pragmatism filter (Step 4) is **MANDATORY**
-- Screenshots required for every complaint
-- Max 10 tickets per session
-- Test on staging/deployed app, not local dev
-- One persona, one session, one report

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/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/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

tests/test_optional_adversarial_ux_skill_catalog.py

@@ -1,25 +0,0 @@
-from pathlib import Path
-
-from tools.skills_hub import OptionalSkillSource
-
-
-REPO_ROOT = Path(__file__).resolve().parents[1]
-
-
-def test_optional_skill_source_scans_adversarial_ux_test():
-    source = OptionalSkillSource()
-    metas = {meta.identifier: meta for meta in source._scan_all()}
-
-    assert "official/dogfood/adversarial-ux-test" in metas
-    assert metas["official/dogfood/adversarial-ux-test"].name == "adversarial-ux-test"
-    assert "tech-resistant user" in metas["official/dogfood/adversarial-ux-test"].description
-
-
-def test_optional_skill_catalog_docs_list_adversarial_ux_test():
-    optional_catalog = (REPO_ROOT / "website" / "docs" / "reference" / "optional-skills-catalog.md").read_text(encoding="utf-8")
-    bundled_catalog = (REPO_ROOT / "website" / "docs" / "reference" / "skills-catalog.md").read_text(encoding="utf-8")
-
-    assert "**adversarial-ux-test**" in optional_catalog
-    assert "official/dogfood/adversarial-ux-test" in optional_catalog
-    assert "`adversarial-ux-test`" in bundled_catalog
-    assert "dogfood/adversarial-ux-test" in bundled_catalog

website/docs/reference/optional-skills-catalog.md

@@ -16,7 +16,6 @@ For example:
 
 ```bash
 hermes skills install official/blockchain/solana
-hermes skills install official/dogfood/adversarial-ux-test
 hermes skills install official/mlops/flash-attention
 ```
 
@@ -57,12 +56,6 @@ hermes skills uninstall <skill-name>
 | **blender-mcp** | Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. |
 | **meme-generation** | Generate real meme images by picking a template and overlaying text with Pillow. Produces actual `.png` meme files. |
 
-## Dogfood
-
-| Skill | Description |
-|-------|-------------|
-| **adversarial-ux-test** | Roleplay the most difficult, tech-resistant user for a product — browse in-persona, rant, then filter through a RED/YELLOW/WHITE/GREEN pragmatism layer so only real UX friction becomes tickets. |
-
 ## DevOps
 
 | Skill | Description |

website/docs/reference/skills-catalog.md

@@ -59,12 +59,9 @@ DevOps and infrastructure automation skills.
 
 ## dogfood
 
-Internal dogfooding and QA skills used to test Hermes Agent itself.
-
 | Skill | Description | Path |
 |-------|-------------|------|
 | `dogfood` | Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports. | `dogfood/dogfood` |
-| `adversarial-ux-test` | Roleplay the most difficult, tech-resistant user for a product — browse in-persona, rant, then filter through a RED/YELLOW/WHITE/GREEN pragmatism layer so only real UX friction becomes tickets. | `dogfood/adversarial-ux-test` |
 | `hermes-agent-setup` | Help users configure Hermes Agent — CLI usage, setup wizard, model/provider selection, tools, skills, voice/STT/TTS, gateway, and troubleshooting. | `dogfood/hermes-agent-setup` |
 
 ## email