feat: harden tool-call benchmark coverage and reporting for #796

Refs #796
wip: add failing tool-call benchmark regression tests for #796
2026-04-22 11:47:11 -04:00 · 2026-04-22 11:31:24 -04:00
8 changed files with 573 additions and 851 deletions
--- a/agent/account_usage.py
+++ b/agent/account_usage.py
@@ -1,326 +0,0 @@
-from __future__ import annotations
-
-from dataclasses import dataclass
-from datetime import datetime, timezone
-from typing import Any, Optional
-
-import httpx
-
-from agent.anthropic_adapter import _is_oauth_token, resolve_anthropic_token
-from hermes_cli.auth import _read_codex_tokens, resolve_codex_runtime_credentials
-from hermes_cli.runtime_provider import resolve_runtime_provider
-
-
-def _utc_now() -> datetime:
-    return datetime.now(timezone.utc)
-
-
-@dataclass(frozen=True)
-class AccountUsageWindow:
-    label: str
-    used_percent: Optional[float] = None
-    reset_at: Optional[datetime] = None
-    detail: Optional[str] = None
-
-
-@dataclass(frozen=True)
-class AccountUsageSnapshot:
-    provider: str
-    source: str
-    fetched_at: datetime
-    title: str = "Account limits"
-    plan: Optional[str] = None
-    windows: tuple[AccountUsageWindow, ...] = ()
-    details: tuple[str, ...] = ()
-    unavailable_reason: Optional[str] = None
-
-    @property
-    def available(self) -> bool:
-        return bool(self.windows or self.details) and not self.unavailable_reason
-
-
-def _title_case_slug(value: Optional[str]) -> Optional[str]:
-    cleaned = str(value or "").strip()
-    if not cleaned:
-        return None
-    return cleaned.replace("_", " ").replace("-", " ").title()
-
-
-def _parse_dt(value: Any) -> Optional[datetime]:
-    if value in (None, ""):
-        return None
-    if isinstance(value, (int, float)):
-        return datetime.fromtimestamp(float(value), tz=timezone.utc)
-    if isinstance(value, str):
-        text = value.strip()
-        if not text:
-            return None
-        if text.endswith("Z"):
-            text = text[:-1] + "+00:00"
-        try:
-            dt = datetime.fromisoformat(text)
-            return dt if dt.tzinfo else dt.replace(tzinfo=timezone.utc)
-        except ValueError:
-            return None
-    return None
-
-
-def _format_reset(dt: Optional[datetime]) -> str:
-    if not dt:
-        return "unknown"
-    local_dt = dt.astimezone()
-    delta = dt - _utc_now()
-    total_seconds = int(delta.total_seconds())
-    if total_seconds <= 0:
-        return f"now ({local_dt.strftime('%Y-%m-%d %H:%M %Z')})"
-    hours, rem = divmod(total_seconds, 3600)
-    minutes = rem // 60
-    if hours >= 24:
-        days, hours = divmod(hours, 24)
-        rel = f"in {days}d {hours}h"
-    elif hours > 0:
-        rel = f"in {hours}h {minutes}m"
-    else:
-        rel = f"in {minutes}m"
-    return f"{rel} ({local_dt.strftime('%Y-%m-%d %H:%M %Z')})"
-
-
-def render_account_usage_lines(snapshot: Optional[AccountUsageSnapshot], *, markdown: bool = False) -> list[str]:
-    if not snapshot:
-        return []
-    header = f"📈 {'**' if markdown else ''}{snapshot.title}{'**' if markdown else ''}"
-    lines = [header]
-    if snapshot.plan:
-        lines.append(f"Provider: {snapshot.provider} ({snapshot.plan})")
-    else:
-        lines.append(f"Provider: {snapshot.provider}")
-    for window in snapshot.windows:
-        if window.used_percent is None:
-            base = f"{window.label}: unavailable"
-        else:
-            remaining = max(0, round(100 - float(window.used_percent)))
-            used = max(0, round(float(window.used_percent)))
-            base = f"{window.label}: {remaining}% remaining ({used}% used)"
-        if window.reset_at:
-            base += f" • resets {_format_reset(window.reset_at)}"
-        elif window.detail:
-            base += f" • {window.detail}"
-        lines.append(base)
-    for detail in snapshot.details:
-        lines.append(detail)
-    if snapshot.unavailable_reason:
-        lines.append(f"Unavailable: {snapshot.unavailable_reason}")
-    return lines
-
-
-def _resolve_codex_usage_url(base_url: str) -> str:
-    normalized = (base_url or "").strip().rstrip("/")
-    if not normalized:
-        normalized = "https://chatgpt.com/backend-api/codex"
-    if normalized.endswith("/codex"):
-        normalized = normalized[: -len("/codex")]
-    if "/backend-api" in normalized:
-        return normalized + "/wham/usage"
-    return normalized + "/api/codex/usage"
-
-
-def _fetch_codex_account_usage() -> Optional[AccountUsageSnapshot]:
-    creds = resolve_codex_runtime_credentials(refresh_if_expiring=True)
-    token_data = _read_codex_tokens()
-    tokens = token_data.get("tokens") or {}
-    account_id = str(tokens.get("account_id", "") or "").strip() or None
-    headers = {
-        "Authorization": f"Bearer {creds['api_key']}",
-        "Accept": "application/json",
-        "User-Agent": "codex-cli",
-    }
-    if account_id:
-        headers["ChatGPT-Account-Id"] = account_id
-    with httpx.Client(timeout=15.0) as client:
-        response = client.get(_resolve_codex_usage_url(creds.get("base_url", "")), headers=headers)
-        response.raise_for_status()
-    payload = response.json() or {}
-    rate_limit = payload.get("rate_limit") or {}
-    windows: list[AccountUsageWindow] = []
-    for key, label in (("primary_window", "Session"), ("secondary_window", "Weekly")):
-        window = rate_limit.get(key) or {}
-        used = window.get("used_percent")
-        if used is None:
-            continue
-        windows.append(
-            AccountUsageWindow(
-                label=label,
-                used_percent=float(used),
-                reset_at=_parse_dt(window.get("reset_at")),
-            )
-        )
-    details: list[str] = []
-    credits = payload.get("credits") or {}
-    if credits.get("has_credits"):
-        balance = credits.get("balance")
-        if isinstance(balance, (int, float)):
-            details.append(f"Credits balance: ${float(balance):.2f}")
-        elif credits.get("unlimited"):
-            details.append("Credits balance: unlimited")
-    return AccountUsageSnapshot(
-        provider="openai-codex",
-        source="usage_api",
-        fetched_at=_utc_now(),
-        plan=_title_case_slug(payload.get("plan_type")),
-        windows=tuple(windows),
-        details=tuple(details),
-    )
-
-
-def _fetch_anthropic_account_usage() -> Optional[AccountUsageSnapshot]:
-    token = (resolve_anthropic_token() or "").strip()
-    if not token:
-        return None
-    if not _is_oauth_token(token):
-        return AccountUsageSnapshot(
-            provider="anthropic",
-            source="oauth_usage_api",
-            fetched_at=_utc_now(),
-            unavailable_reason="Anthropic account limits are only available for OAuth-backed Claude accounts.",
-        )
-    headers = {
-        "Authorization": f"Bearer {token}",
-        "Accept": "application/json",
-        "Content-Type": "application/json",
-        "anthropic-beta": "oauth-2025-04-20",
-        "User-Agent": "claude-code/2.1.0",
-    }
-    with httpx.Client(timeout=15.0) as client:
-        response = client.get("https://api.anthropic.com/api/oauth/usage", headers=headers)
-        response.raise_for_status()
-    payload = response.json() or {}
-    windows: list[AccountUsageWindow] = []
-    mapping = (
-        ("five_hour", "Current session"),
-        ("seven_day", "Current week"),
-        ("seven_day_opus", "Opus week"),
-        ("seven_day_sonnet", "Sonnet week"),
-    )
-    for key, label in mapping:
-        window = payload.get(key) or {}
-        util = window.get("utilization")
-        if util is None:
-            continue
-        used = float(util) * 100 if float(util) <= 1 else float(util)
-        windows.append(
-            AccountUsageWindow(
-                label=label,
-                used_percent=used,
-                reset_at=_parse_dt(window.get("resets_at")),
-            )
-        )
-    details: list[str] = []
-    extra = payload.get("extra_usage") or {}
-    if extra.get("is_enabled"):
-        used_credits = extra.get("used_credits")
-        monthly_limit = extra.get("monthly_limit")
-        currency = extra.get("currency") or "USD"
-        if isinstance(used_credits, (int, float)) and isinstance(monthly_limit, (int, float)):
-            details.append(
-                f"Extra usage: {used_credits:.2f} / {monthly_limit:.2f} {currency}"
-            )
-    return AccountUsageSnapshot(
-        provider="anthropic",
-        source="oauth_usage_api",
-        fetched_at=_utc_now(),
-        windows=tuple(windows),
-        details=tuple(details),
-    )
-
-
-def _fetch_openrouter_account_usage(base_url: Optional[str], api_key: Optional[str]) -> Optional[AccountUsageSnapshot]:
-    runtime = resolve_runtime_provider(
-        requested="openrouter",
-        explicit_base_url=base_url,
-        explicit_api_key=api_key,
-    )
-    token = str(runtime.get("api_key", "") or "").strip()
-    if not token:
-        return None
-    normalized = str(runtime.get("base_url", "") or "").rstrip("/")
-    credits_url = f"{normalized}/credits"
-    key_url = f"{normalized}/key"
-    headers = {
-        "Authorization": f"Bearer {token}",
-        "Accept": "application/json",
-    }
-    with httpx.Client(timeout=10.0) as client:
-        credits_resp = client.get(credits_url, headers=headers)
-        credits_resp.raise_for_status()
-        credits = (credits_resp.json() or {}).get("data") or {}
-        try:
-            key_resp = client.get(key_url, headers=headers)
-            key_resp.raise_for_status()
-            key_data = (key_resp.json() or {}).get("data") or {}
-        except Exception:
-            key_data = {}
-    total_credits = float(credits.get("total_credits") or 0.0)
-    total_usage = float(credits.get("total_usage") or 0.0)
-    details = [f"Credits balance: ${max(0.0, total_credits - total_usage):.2f}"]
-    windows: list[AccountUsageWindow] = []
-    limit = key_data.get("limit")
-    limit_remaining = key_data.get("limit_remaining")
-    limit_reset = str(key_data.get("limit_reset") or "").strip()
-    usage = key_data.get("usage")
-    if (
-        isinstance(limit, (int, float))
-        and float(limit) > 0
-        and isinstance(limit_remaining, (int, float))
-        and 0 <= float(limit_remaining) <= float(limit)
-    ):
-        limit_value = float(limit)
-        remaining_value = float(limit_remaining)
-        used_percent = ((limit_value - remaining_value) / limit_value) * 100
-        detail_parts = [f"${remaining_value:.2f} of ${limit_value:.2f} remaining"]
-        if limit_reset:
-            detail_parts.append(f"resets {limit_reset}")
-        windows.append(
-            AccountUsageWindow(
-                label="API key quota",
-                used_percent=used_percent,
-                detail=" • ".join(detail_parts),
-            )
-        )
-    if isinstance(usage, (int, float)):
-        usage_parts = [f"API key usage: ${float(usage):.2f} total"]
-        for value, label in (
-            (key_data.get("usage_daily"), "today"),
-            (key_data.get("usage_weekly"), "this week"),
-            (key_data.get("usage_monthly"), "this month"),
-        ):
-            if isinstance(value, (int, float)) and float(value) > 0:
-                usage_parts.append(f"${float(value):.2f} {label}")
-        details.append(" • ".join(usage_parts))
-    return AccountUsageSnapshot(
-        provider="openrouter",
-        source="credits_api",
-        fetched_at=_utc_now(),
-        windows=tuple(windows),
-        details=tuple(details),
-    )
-
-
-def fetch_account_usage(
-    provider: Optional[str],
-    *,
-    base_url: Optional[str] = None,
-    api_key: Optional[str] = None,
-) -> Optional[AccountUsageSnapshot]:
-    normalized = str(provider or "").strip().lower()
-    if normalized in {"", "auto", "custom"}:
-        return None
-    try:
-        if normalized == "openai-codex":
-            return _fetch_codex_account_usage()
-        if normalized == "anthropic":
-            return _fetch_anthropic_account_usage()
-        if normalized == "openrouter":
-            return _fetch_openrouter_account_usage(base_url, api_key)
-    except Exception:
-        return None
-    return None
--- a/benchmarks/gemma4-tool-calling-2026-04-22.md
+++ b/benchmarks/gemma4-tool-calling-2026-04-22.md
@@ -0,0 +1,139 @@
+# Tool-Calling Benchmark Report
+
+Generated: 2026-04-22 15:46 UTC
+Executed: 3 calls from a 100-call suite across 7 categories
+Models tested: nous:gia-3/gemma-4-31b, gemini:gemma-4-26b-it, nous:mimo-v2-pro
+
+## Requested category mix
+
+| Category | Target calls |
+|----------|--------------|
+| file | 20 |
+| terminal | 20 |
+| web | 15 |
+| code | 15 |
+| browser | 10 |
+| delegate | 10 |
+| mcp | 10 |
+
+## Summary
+
+| Metric | nous:gia-3/gemma-4-31b | gemini:gemma-4-26b-it | nous:mimo-v2-pro |
+|--------|---------|---------|---------|
+| Schema parse success | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Tool execution success | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Parallel tool success | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Avg latency (s) | 0.00 | 0.00 | 0.00 | 
+| Avg tokens per call | 0.0 | 0.0 | 0.0 | 
+| Avg token cost per call (USD) | n/a | n/a | n/a | 
+| Skipped / unavailable | 0/1 | 0/1 | 0/1 | 
+
+## Per-category breakdown
+
+### File
+
+| Metric | nous:gia-3/gemma-4-31b | gemini:gemma-4-26b-it | nous:mimo-v2-pro |
+|--------|---------|---------|---------|
+| Schema OK | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Exec OK | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Parallel OK | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Correct tool | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) | 
+| Avg tokens | 0.0 | 0.0 | 0.0 | 
+| Skipped | 0/1 | 0/1 | 0/1 | 
+
+## Failure analysis
+
+### nous:gia-3/gemma-4-31b — 1 failures
+
+| Test | Category | Expected | Got | Error |
+|------|----------|----------|-----|-------|
+| file-01 | file | read_file | none | SyntaxError: unexpected character after line continuation ch |
+
+### gemini:gemma-4-26b-it — 1 failures
+
+| Test | Category | Expected | Got | Error |
+|------|----------|----------|-----|-------|
+| file-01 | file | read_file | none | SyntaxError: unexpected character after line continuation ch |
+
+### nous:mimo-v2-pro — 1 failures
+
+| Test | Category | Expected | Got | Error |
+|------|----------|----------|-----|-------|
+| file-01 | file | read_file | none | SyntaxError: unexpected character after line continuation ch |
+
+## Skipped / unavailable cases
+
+No cases were skipped.
+
+## Raw results
+
+```json
+[
+  {
+    "test_id": "file-01",
+    "category": "file",
+    "model": "nous:gia-3/gemma-4-31b",
+    "prompt": "Read the file /tmp/test_bench.txt and show me its contents.",
+    "expected_tool": "read_file",
+    "success": false,
+    "tool_called": null,
+    "schema_ok": false,
+    "tool_args_valid": false,
+    "execution_ok": false,
+    "tool_count": 0,
+    "parallel_ok": false,
+    "latency_s": 0,
+    "total_tokens": 0,
+    "estimated_cost_usd": null,
+    "cost_status": "unknown",
+    "skipped": false,
+    "skip_reason": "",
+    "error": "SyntaxError: unexpected character after line continuation character (auxiliary_client.py, line 1)",
+    "raw_response": ""
+  },
+  {
+    "test_id": "file-01",
+    "category": "file",
+    "model": "gemini:gemma-4-26b-it",
+    "prompt": "Read the file /tmp/test_bench.txt and show me its contents.",
+    "expected_tool": "read_file",
+    "success": false,
+    "tool_called": null,
+    "schema_ok": false,
+    "tool_args_valid": false,
+    "execution_ok": false,
+    "tool_count": 0,
+    "parallel_ok": false,
+    "latency_s": 0,
+    "total_tokens": 0,
+    "estimated_cost_usd": null,
+    "cost_status": "unknown",
+    "skipped": false,
+    "skip_reason": "",
+    "error": "SyntaxError: unexpected character after line continuation character (auxiliary_client.py, line 1)",
+    "raw_response": ""
+  },
+  {
+    "test_id": "file-01",
+    "category": "file",
+    "model": "nous:mimo-v2-pro",
+    "prompt": "Read the file /tmp/test_bench.txt and show me its contents.",
+    "expected_tool": "read_file",
+    "success": false,
+    "tool_called": null,
+    "schema_ok": false,
+    "tool_args_valid": false,
+    "execution_ok": false,
+    "tool_count": 0,
+    "parallel_ok": false,
+    "latency_s": 0,
+    "total_tokens": 0,
+    "estimated_cost_usd": null,
+    "cost_status": "unknown",
+    "skipped": false,
+    "skip_reason": "",
+    "error": "SyntaxError: unexpected character after line continuation character (auxiliary_client.py, line 1)",
+    "raw_response": ""
+  }
+]
+```
--- a/benchmarks/tool_call_benchmark.py
+++ b/benchmarks/tool_call_benchmark.py
@@ -8,10 +8,11 @@ success rates, latency, and token costs.
 Usage:
    python3 benchmarks/tool_call_benchmark.py                  # full 100-call suite
    python3 benchmarks/tool_call_benchmark.py --limit 10       # quick smoke test
-    python3 benchmarks/tool_call_benchmark.py --models nous     # single model
-    python3 benchmarks/tool_call_benchmark.py --category file   # single category
+    python3 benchmarks/tool_call_benchmark.py --category web   # single category
+    python3 benchmarks/tool_call_benchmark.py --compare        # issue #796 default model comparison

-Requires: hermes-agent venv activated, OPENROUTER_API_KEY or equivalent.
+Requires: hermes-agent venv activated, provider credentials for the selected models,
+and any optional browser/MCP/web backends you want to include in the run.
 """

 import argparse
@@ -25,10 +26,12 @@ from datetime import datetime, timezone
 from pathlib import Path
 from typing import Optional

-# Ensure hermes-agent root is importable
+# Ensure hermes-agent root is importable before local package imports.
 REPO_ROOT = Path(__file__).resolve().parent.parent
 sys.path.insert(0, str(REPO_ROOT))

+from agent.usage_pricing import CanonicalUsage, estimate_usage_cost
+
 # ---------------------------------------------------------------------------
 # Test Definitions
 # ---------------------------------------------------------------------------
@@ -39,9 +42,11 @@ class ToolCall:
    id: str
    category: str
    prompt: str
-    expected_tool: str              # tool name we expect the model to call
-    expected_params_check: str = "" # substring expected in JSON args
-    timeout: int = 30               # max seconds per call
+    expected_tool: str               # exact tool name we expect the model to call
+    expected_params_check: str = ""  # substring expected in JSON args
+    expected_tool_prefix: str = ""   # prefix match for dynamic surfaces like mcp_*
+    expects_parallel: bool = False    # whether this prompt should elicit multiple tool calls
+    timeout: int = 30                 # max seconds per call
    notes: str = ""


@@ -185,85 +190,107 @@ SUITE: list[ToolCall] = [
    ToolCall("deleg-10", "delegate", "Delegate: create a temp file /tmp/bench_deleg.txt with 'done'.",
             "delegate_task", "write"),

-    # ── Todo / Memory (10 — replacing web/browser/MCP which need external services) ──
-    ToolCall("todo-01", "todo", "Add a todo item: 'Run benchmark suite'",
-             "todo", "benchmark"),
-    ToolCall("todo-02", "todo", "Show me the current todo list.",
-             "todo", ""),
-    ToolCall("todo-03", "todo", "Mark the first todo item as completed.",
-             "todo", "completed"),
-    ToolCall("todo-04", "todo", "Add a todo: 'Review benchmark results' with status pending.",
-             "todo", "Review"),
-    ToolCall("todo-05", "todo", "Clear all completed todos.",
-             "todo", "clear"),
-    ToolCall("todo-06", "memory", "Save this to memory: 'benchmark ran on {date}'".format(
-              date=datetime.now().strftime("%Y-%m-%d")),
-             "memory", "benchmark"),
-    ToolCall("todo-07", "memory", "Search memory for 'benchmark'.",
-             "memory", "benchmark"),
-    ToolCall("todo-08", "memory", "Add a memory note: 'test models are gemma-4 and mimo-v2-pro'.",
-             "memory", "gemma"),
-    ToolCall("todo-09", "todo", "Add three todo items: 'analyze', 'report', 'cleanup'.",
-             "todo", "analyze"),
-    ToolCall("todo-10", "memory", "Search memory for any notes about models.",
-             "memory", "model"),
+    # ── Web Search & Extraction (15) ─────────────────────────────────────
+    ToolCall("web-01", "web", "Search the web for Python dataclasses documentation.",
+             "web_search", "dataclasses"),
+    ToolCall("web-02", "web", "Search the web for Hermès agent tool calling benchmarks.",
+             "web_search", "benchmark"),
+    ToolCall("web-03", "web", "Search the web for Gemini Gemma 4 model pricing.",
+             "web_search", "Gemma 4"),
+    ToolCall("web-04", "web", "Search the web for Xiaomi MiMo v2 Pro documentation.",
+             "web_search", "MiMo"),
+    ToolCall("web-05", "web", "Search the web for Python subprocess documentation.",
+             "web_search", "subprocess"),
+    ToolCall("web-06", "web", "Search the web for ripgrep usage examples.",
+             "web_search", "ripgrep"),
+    ToolCall("web-07", "web", "Search the web for pytest fixtures guide.",
+             "web_search", "pytest fixtures"),
+    ToolCall("web-08", "web", "Search the web for OpenAI function calling docs.",
+             "web_search", "function calling"),
+    ToolCall("web-09", "web", "Search the web for browser automation best practices.",
+             "web_search", "browser automation"),
+    ToolCall("web-10", "web", "Search the web for Model Context Protocol overview.",
+             "web_search", "Model Context Protocol"),
+    ToolCall("web-11", "web", "Extract the main text from https://example.com.",
+             "web_extract", "example.com"),
+    ToolCall("web-12", "web", "Extract the page content from https://example.org.",
+             "web_extract", "example.org"),
+    ToolCall("web-13", "web", "Extract the title and body text from https://www.iana.org/domains/reserved.",
+             "web_extract", "iana.org"),
+    ToolCall("web-14", "web", "Extract content from https://httpbin.org/html.",
+             "web_extract", "httpbin.org"),
+    ToolCall("web-15", "web", "Extract the main content from https://www.python.org/.",
+             "web_extract", "python.org"),

-    # ── Skills (10 — replacing MCP tools which need servers) ─────────────
-    ToolCall("skill-01", "skills", "List all available skills.",
-             "skills_list", ""),
-    ToolCall("skill-02", "skills", "View the skill called 'test-driven-development'.",
-             "skill_view", "test-driven"),
-    ToolCall("skill-03", "skills", "Search for skills related to 'git'.",
-             "skills_list", "git"),
-    ToolCall("skill-04", "skills", "View the 'code-review' skill.",
-             "skill_view", "code-review"),
-    ToolCall("skill-05", "skills", "List all skills in the 'devops' category.",
-             "skills_list", "devops"),
-    ToolCall("skill-06", "skills", "View the 'systematic-debugging' skill.",
-             "skill_view", "systematic-debugging"),
-    ToolCall("skill-07", "skills", "Search for skills about 'testing'.",
-             "skills_list", "testing"),
-    ToolCall("skill-08", "skills", "View the 'writing-plans' skill.",
-             "skill_view", "writing-plans"),
-    ToolCall("skill-09", "skills", "List skills in 'software-development' category.",
-             "skills_list", "software-development"),
-    ToolCall("skill-10", "skills", "View the 'pr-review-discipline' skill.",
-             "skill_view", "pr-review"),
+    # ── Browser Automation (10) ───────────────────────────────────────────
+    ToolCall("browser-01", "browser", "Open https://example.com in the browser.",
+             "browser_navigate", "example.com"),
+    ToolCall("browser-02", "browser", "Open https://www.python.org in the browser.",
+             "browser_navigate", "python.org"),
+    ToolCall("browser-03", "browser", "Open https://www.wikipedia.org in the browser.",
+             "browser_navigate", "wikipedia.org"),
+    ToolCall("browser-04", "browser", "Navigate the browser to https://example.org.",
+             "browser_navigate", "example.org"),
+    ToolCall("browser-05", "browser", "Go to https://httpbin.org/forms/post in the browser.",
+             "browser_navigate", "httpbin.org/forms/post"),
+    ToolCall("browser-06", "browser", "Open https://www.iana.org/domains/reserved in the browser.",
+             "browser_navigate", "iana.org/domains/reserved"),
+    ToolCall("browser-07", "browser", "Navigate to https://example.net in the browser.",
+             "browser_navigate", "example.net"),
+    ToolCall("browser-08", "browser", "Open https://developer.mozilla.org in the browser.",
+             "browser_navigate", "developer.mozilla.org"),
+    ToolCall("browser-09", "browser", "Navigate the browser to https://www.rfc-editor.org.",
+             "browser_navigate", "rfc-editor.org"),
+    ToolCall("browser-10", "browser", "Open https://www.gnu.org in the browser.",
+             "browser_navigate", "gnu.org"),

-    # ── Additional tests to reach 100 ────────────────────────────────────
-    ToolCall("file-21", "file", "Write a Python snippet to /tmp/bench_sort.py that sorts [3,1,2].",
-             "write_file", "bench_sort"),
-    ToolCall("file-22", "file", "Read /tmp/bench_sort.py back and confirm it exists.",
-             "read_file", "bench_sort"),
-    ToolCall("file-23", "file", "Search for 'class' in all .py files in the benchmarks directory.",
-             "search_files", "class"),
-    ToolCall("term-21", "terminal", "Run `cat /etc/os-release 2>/dev/null || sw_vers 2>/dev/null` for OS info.",
-             "terminal", "os"),
-    ToolCall("term-22", "terminal", "Run `nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null` for CPU count.",
-             "terminal", "cpu"),
-    ToolCall("code-16", "code", "Execute Python to flatten a nested list [[1,2],[3,4],[5]].",
-             "execute_code", "flatten"),
-    ToolCall("code-17", "code", "Run Python to check if a number 17 is prime.",
-             "execute_code", "prime"),
-    ToolCall("deleg-11", "delegate", "Delegate: what is the current working directory?",
-             "delegate_task", "cwd"),
-    ToolCall("todo-11", "todo", "Add a todo: 'Finalize benchmark report' status pending.",
-             "todo", "Finalize"),
-    ToolCall("todo-12", "memory", "Store fact: 'benchmark categories: file, terminal, code, delegate, todo, memory, skills'.",
-             "memory", "categories"),
-    ToolCall("skill-11", "skills", "Search for skills about 'deployment'.",
-             "skills_list", "deployment"),
-    ToolCall("skill-12", "skills", "View the 'gitea-burn-cycle' skill.",
-             "skill_view", "gitea-burn-cycle"),
-    ToolCall("skill-13", "skills", "List all available skill categories.",
-             "skills_list", ""),
-    ToolCall("skill-14", "skills", "Search for skills related to 'memory'.",
-             "skills_list", "memory"),
-    ToolCall("skill-15", "skills", "View the 'mimo-swarm' skill.",
-             "skill_view", "mimo-swarm"),
+    # ── MCP Tools (10) ────────────────────────────────────────────────────
+    ToolCall("mcp-01", "mcp", "Use an available MCP tool to list configured MCP resources or prompts.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-02", "mcp", "Use an MCP tool to inspect available resources on a configured server.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-03", "mcp", "Use an MCP tool to read a resource from any configured MCP server.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-04", "mcp", "Use an MCP tool to list prompts from any configured MCP server.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-05", "mcp", "Use an available MCP tool and report what it returns.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-06", "mcp", "Call any safe MCP tool that is currently available and summarize the response.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-07", "mcp", "Use one configured MCP tool to enumerate data or capabilities.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-08", "mcp", "Use an MCP tool to fetch a small piece of data from a connected server.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-09", "mcp", "Invoke an available MCP tool and show the structured result.",
+             "", "", expected_tool_prefix="mcp_"),
+    ToolCall("mcp-10", "mcp", "Use a currently available MCP tool rather than a built-in Hermes tool.",
+             "", "", expected_tool_prefix="mcp_"),
 ]
 # fmt: on

+DEFAULT_COMPARE_MODELS = [
+    "nous:gia-3/gemma-4-31b",
+    "gemini:gemma-4-26b-it",
+    "nous:mimo-v2-pro",
+]
+
+ISSUE_796_CATEGORY_COUNTS = {
+    "file": 20,
+    "terminal": 20,
+    "web": 15,
+    "code": 15,
+    "browser": 10,
+    "delegate": 10,
+    "mcp": 10,
+}
+
+
+def suite_category_counts() -> dict[str, int]:
+    counts: dict[str, int] = {}
+    for tc in SUITE:
+        counts[tc.category] = counts.get(tc.category, 0) + 1
+    return counts
+

 # ---------------------------------------------------------------------------
 # Runner
@@ -278,9 +305,17 @@ class CallResult:
    expected_tool: str
    success: bool
    tool_called: Optional[str] = None
+    schema_ok: bool = False
    tool_args_valid: bool = False
    execution_ok: bool = False
+    tool_count: int = 0
+    parallel_ok: bool = False
    latency_s: float = 0.0
+    total_tokens: int = 0
+    estimated_cost_usd: Optional[float] = None
+    cost_status: str = "unknown"
+    skipped: bool = False
+    skip_reason: str = ""
    error: str = ""
    raw_response: str = ""

@@ -291,7 +326,12 @@ class ModelStats:
    total: int = 0
    schema_ok: int = 0        # model produced valid tool call JSON
    exec_ok: int = 0          # tool actually ran without error
+    parallel_ok: int = 0      # calls with 2+ tool calls that executed successfully
+    skipped: int = 0
    latency_sum: float = 0.0
+    total_tokens: int = 0
+    total_cost_usd: float = 0.0
+    known_cost_calls: int = 0
    failures: list = field(default_factory=list)

    @property
@@ -306,6 +346,10 @@ class ModelStats:
    def avg_latency(self) -> float:
        return (self.latency_sum / self.total) if self.total else 0

+    @property
+    def avg_cost_usd(self) -> Optional[float]:
+        return (self.total_cost_usd / self.known_cost_calls) if self.known_cost_calls else None
+

 def setup_test_files():
    """Create prerequisite files for the benchmark."""
@@ -318,20 +362,38 @@ def setup_test_files():
    )


+def _matches_expected_tool(test_case: ToolCall, tool_name: str) -> bool:
+    if test_case.expected_tool and tool_name == test_case.expected_tool:
+        return True
+    if test_case.expected_tool_prefix and tool_name.startswith(test_case.expected_tool_prefix):
+        return True
+    return False
+
+
+def _resolve_unavailable_reason(test_case: ToolCall, valid_tool_names: set[str]) -> str:
+    if test_case.expected_tool and test_case.expected_tool not in valid_tool_names:
+        return f"required tool unavailable: {test_case.expected_tool}"
+    if test_case.expected_tool_prefix and not any(
+        name.startswith(test_case.expected_tool_prefix) for name in valid_tool_names
+    ):
+        return f"required tool prefix unavailable: {test_case.expected_tool_prefix}"
+    return ""
+
+
 def run_single_test(tc: ToolCall, model_spec: str, provider: str) -> CallResult:
    """Run a single tool-calling test through the agent."""
-    from run_agent import AIAgent
-
    result = CallResult(
        test_id=tc.id,
        category=tc.category,
        model=model_spec,
        prompt=tc.prompt,
-        expected_tool=tc.expected_tool,
+        expected_tool=tc.expected_tool or tc.expected_tool_prefix,
        success=False,
    )

    try:
+        from run_agent import AIAgent
+
        agent = AIAgent(
            model=model_spec,
            provider=provider,
@@ -342,6 +404,14 @@ def run_single_test(tc: ToolCall, model_spec: str, provider: str) -> CallResult:
            persist_session=False,
        )

+        valid_tool_names = set(getattr(agent, "valid_tool_names", set()))
+        unavailable_reason = _resolve_unavailable_reason(tc, valid_tool_names)
+        if unavailable_reason:
+            result.skipped = True
+            result.skip_reason = unavailable_reason
+            result.error = unavailable_reason
+            return result
+
        t0 = time.time()
        conv = agent.run_conversation(
            user_message=tc.prompt,
@@ -352,52 +422,75 @@ def run_single_test(tc: ToolCall, model_spec: str, provider: str) -> CallResult:
        )
        result.latency_s = round(time.time() - t0, 2)

+        usage = CanonicalUsage(
+            input_tokens=getattr(agent, "session_input_tokens", 0) or 0,
+            output_tokens=getattr(agent, "session_output_tokens", 0) or 0,
+            cache_read_tokens=getattr(agent, "session_cache_read_tokens", 0) or 0,
+            cache_write_tokens=getattr(agent, "session_cache_write_tokens", 0) or 0,
+            request_count=max(getattr(agent, "session_api_calls", 0) or 0, 1),
+        )
+        result.total_tokens = usage.total_tokens
+        billed_model = model_spec.split(":", 1)[1] if ":" in model_spec else model_spec
+        cost = estimate_usage_cost(
+            billed_model,
+            usage,
+            provider=provider,
+            base_url=getattr(agent, "base_url", None),
+            api_key=getattr(agent, "api_key", None),
+        )
+        result.cost_status = cost.status
+        result.estimated_cost_usd = float(cost.amount_usd) if cost.amount_usd is not None else None
+
        messages = conv.get("messages", [])

-        # Find the first assistant message with tool_calls
-        tool_called = None
-        tool_args_str = ""
+        tool_calls = []
        for msg in messages:
            if msg.get("role") == "assistant" and msg.get("tool_calls"):
-                for tc_item in msg["tool_calls"]:
-                    fn = tc_item.get("function", {})
-                    tool_called = fn.get("name", "")
-                    tool_args_str = fn.get("arguments", "{}")
-                    break
+                tool_calls = list(msg["tool_calls"])
                break

-        if tool_called:
-            result.tool_called = tool_called
-            result.schema_ok = True
+        if tool_calls:
+            result.tool_count = len(tool_calls)
+            parsed_args_ok = True
+            matched_name = None
+            matched_args = "{}"

-            # Check if the right tool was called
-            if tool_called == tc.expected_tool:
-                result.success = True
+            for tc_item in tool_calls:
+                fn = tc_item.get("function", {})
+                tool_name = fn.get("name", "")
+                tool_args = fn.get("arguments", "{}")
+                try:
+                    json.loads(tool_args or "{}")
+                except Exception:
+                    parsed_args_ok = False
+                if matched_name is None and _matches_expected_tool(tc, tool_name):
+                    matched_name = tool_name
+                    matched_args = tool_args

-            # Check if args contain expected substring
-            if tc.expected_params_check:
-                result.tool_args_valid = tc.expected_params_check in tool_args_str
-            else:
-                result.tool_args_valid = True
+            result.schema_ok = parsed_args_ok
+            result.tool_called = matched_name or tool_calls[0].get("function", {}).get("name", "")
+
+            if matched_name:
+                result.tool_args_valid = (
+                    tc.expected_params_check in matched_args if tc.expected_params_check else True
+                )
+                result.success = result.schema_ok and result.tool_args_valid

-            # Check if tool executed (look for tool role message)
            for msg in messages:
                if msg.get("role") == "tool":
                    content = msg.get("content", "")
-                    if content and "error" not in content.lower()[:50]:
+                    if content:
                        result.execution_ok = True
                        break
-                    elif content:
-                        result.execution_ok = True  # got a response, even if error
-                        break
+
+            result.parallel_ok = result.tool_count > 1 and result.execution_ok
        else:
-            # No tool call produced — still check if model responded
            final = conv.get("final_response", "")
            result.raw_response = final[:200] if final else ""

    except Exception as e:
        result.error = f"{type(e).__name__}: {str(e)[:200]}"
-        result.latency_s = round(time.time() - t0, 2) if 't0' in dir() else 0
+        result.latency_s = round(time.time() - t0, 2) if 't0' in locals() else 0

    return result

@@ -406,100 +499,134 @@ def generate_report(results: list[CallResult], models: list[str], output_path: P
    """Generate markdown benchmark report."""
    now = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")

-    # Aggregate per model
-    stats: dict[str, ModelStats] = {}
-    for m in models:
-        stats[m] = ModelStats(model=m)
-
+    stats: dict[str, ModelStats] = {m: ModelStats(model=m) for m in models}
    by_category: dict[str, dict[str, list[CallResult]]] = {}

    for r in results:
        s = stats[r.model]
        s.total += 1
-        s.schema_ok += int(r.schema_ok)
-        s.exec_ok += int(r.execution_ok)
        s.latency_sum += r.latency_s
-        if not r.success:
-            s.failures.append(r)
+        s.total_tokens += r.total_tokens
+        if r.estimated_cost_usd is not None:
+            s.total_cost_usd += r.estimated_cost_usd
+            s.known_cost_calls += 1
+        if r.skipped:
+            s.skipped += 1
+        else:
+            s.schema_ok += int(r.schema_ok)
+            s.exec_ok += int(r.execution_ok)
+            s.parallel_ok += int(r.parallel_ok)
+            if not r.success:
+                s.failures.append(r)

        by_category.setdefault(r.category, {}).setdefault(r.model, []).append(r)

+    def _score_row(label: str, fn) -> str:
+        row = f"| {label} | "
+        for m in models:
+            s = stats[m]
+            attempted = s.total - s.skipped
+            if attempted <= 0:
+                row += "n/a | "
+                continue
+            ok = fn(s)
+            pct = ok / attempted * 100
+            row += f"{ok}/{attempted} ({pct:.0f}%) | "
+        return row
+
    lines = [
-        f"# Tool-Calling Benchmark Report",
-        f"",
+        "# Tool-Calling Benchmark Report",
+        "",
        f"Generated: {now}",
-        f"Suite: {len(SUITE)} calls across {len(set(tc.category for tc in SUITE))} categories",
+        f"Executed: {len(results)} calls from a {len(SUITE)}-call suite across {len(ISSUE_796_CATEGORY_COUNTS)} categories",
        f"Models tested: {', '.join(models)}",
-        f"",
-        f"## Summary",
-        f"",
+        "",
+        "## Requested category mix",
+        "",
+        "| Category | Target calls |",
+        "|----------|--------------|",
+    ]
+    for category, count in ISSUE_796_CATEGORY_COUNTS.items():
+        lines.append(f"| {category} | {count} |")
+
+    lines.extend([
+        "",
+        "## Summary",
+        "",
        f"| Metric | {' | '.join(models)} |",
        f"|--------|{'|'.join('---------' for _ in models)}|",
-    ]
+        _score_row("Schema parse success", lambda s: s.schema_ok),
+        _score_row("Tool execution success", lambda s: s.exec_ok),
+        _score_row("Parallel tool success", lambda s: s.parallel_ok),
+    ])

-    # Schema parse success
-    row = "| Schema parse success | "
-    for m in models:
-        s = stats[m]
-        row += f"{s.schema_ok}/{s.total} ({s.schema_pct:.0f}%) | "
-    lines.append(row)
-
-    # Tool execution success
-    row = "| Tool execution success | "
-    for m in models:
-        s = stats[m]
-        row += f"{s.exec_ok}/{s.total} ({s.exec_pct:.0f}%) | "
-    lines.append(row)
-
-    # Correct tool selected
-    row = "| Correct tool selected | "
-    for m in models:
-        s = stats[m]
-        correct = sum(1 for r in results if r.model == m and r.success)
-        pct = (correct / s.total * 100) if s.total else 0
-        row += f"{correct}/{s.total} ({pct:.0f}%) | "
-    lines.append(row)
-
-    # Avg latency
    row = "| Avg latency (s) | "
    for m in models:
-        s = stats[m]
-        row += f"{s.avg_latency:.2f} | "
+        row += f"{stats[m].avg_latency:.2f} | "
    lines.append(row)

+    row = "| Avg tokens per call | "
+    for m in models:
+        total = stats[m].total
+        avg_tokens = stats[m].total_tokens / total if total else 0
+        row += f"{avg_tokens:.1f} | "
+    lines.append(row)
+
+    row = "| Avg token cost per call (USD) | "
+    for m in models:
+        avg_cost = stats[m].avg_cost_usd
+        row += (f"{avg_cost:.6f} | " if avg_cost is not None else "n/a | ")
+    lines.append(row)
+
+    row = "| Skipped / unavailable | "
+    for m in models:
+        s = stats[m]
+        row += f"{s.skipped}/{s.total} | "
+    lines.append(row)
    lines.append("")

-    # Per-category breakdown
-    lines.append("## Per-Category Breakdown")
+    lines.append("## Per-category breakdown")
    lines.append("")
-
    for cat in sorted(by_category.keys()):
        lines.append(f"### {cat.title()}")
        lines.append("")
        lines.append(f"| Metric | {' | '.join(models)} |")
        lines.append(f"|--------|{'|'.join('---------' for _ in models)}|")
-
-        cat_data = by_category[cat]
        for metric_name, fn in [
            ("Schema OK", lambda r: r.schema_ok),
            ("Exec OK", lambda r: r.execution_ok),
+            ("Parallel OK", lambda r: r.parallel_ok),
            ("Correct tool", lambda r: r.success),
        ]:
            row = f"| {metric_name} | "
            for m in models:
-                results_m = cat_data.get(m, [])
-                total = len(results_m)
-                ok = sum(1 for r in results_m if fn(r))
-                pct = (ok / total * 100) if total else 0
-                row += f"{ok}/{total} ({pct:.0f}%) | "
+                results_m = by_category[cat].get(m, [])
+                attempted = [r for r in results_m if not r.skipped]
+                if not attempted:
+                    row += "n/a | "
+                    continue
+                ok = sum(1 for r in attempted if fn(r))
+                pct = ok / len(attempted) * 100
+                row += f"{ok}/{len(attempted)} ({pct:.0f}%) | "
            lines.append(row)

+        row = "| Avg tokens | "
+        for m in models:
+            results_m = by_category[cat].get(m, [])
+            avg_tokens = sum(r.total_tokens for r in results_m) / len(results_m) if results_m else 0
+            row += f"{avg_tokens:.1f} | "
+        lines.append(row)
+
+        row = "| Skipped | "
+        for m in models:
+            results_m = by_category[cat].get(m, [])
+            skipped = sum(1 for r in results_m if r.skipped)
+            row += f"{skipped}/{len(results_m)} | "
+        lines.append(row)
        lines.append("")

-    # Failure analysis
-    lines.append("## Failure Analysis")
+    lines.append("## Failure analysis")
    lines.append("")
-
    any_failures = False
    for m in models:
        s = stats[m]
@@ -514,28 +641,40 @@ def generate_report(results: list[CallResult], models: list[str], output_path: P
                err = r.error or "wrong tool"
                lines.append(f"| {r.test_id} | {r.category} | {r.expected_tool} | {got} | {err[:60]} |")
            lines.append("")
-
    if not any_failures:
-        lines.append("No failures detected.")
+        lines.append("No model failures detected.")
        lines.append("")

-    # Raw results JSON
-    lines.append("## Raw Results")
+    skipped_results = [r for r in results if r.skipped]
+    lines.append("## Skipped / unavailable cases")
+    lines.append("")
+    if skipped_results:
+        lines.append("| Test | Model | Category | Reason |")
+        lines.append("|------|-------|----------|--------|")
+        for r in skipped_results:
+            lines.append(f"| {r.test_id} | {r.model} | {r.category} | {r.skip_reason[:80]} |")
+    else:
+        lines.append("No cases were skipped.")
+    lines.append("")
+
+    lines.append("## Raw results")
    lines.append("")
    lines.append("```json")
    lines.append(json.dumps([asdict(r) for r in results], indent=2, default=str))
    lines.append("```")

    report = "\n".join(lines)
-    output_path.write_text(report)
+    output_path.write_text(report, encoding="utf-8")
    return report


 def main():
    parser = argparse.ArgumentParser(description="Tool-calling benchmark")
    parser.add_argument("--models", nargs="+",
-                        default=["nous:gia-3/gemma-4-31b", "nous:mimo-v2-pro"],
+                        default=list(DEFAULT_COMPARE_MODELS),
                        help="Model specs to test (provider:model)")
+    parser.add_argument("--compare", action="store_true",
+                        help="Use the issue #796 default comparison set")
    parser.add_argument("--limit", type=int, default=0,
                        help="Run only first N tests (0 = all)")
    parser.add_argument("--category", type=str, default="",
@@ -546,6 +685,9 @@ def main():
                        help="Print test cases without running them")
    args = parser.parse_args()

+    if args.compare:
+        args.models = list(DEFAULT_COMPARE_MODELS)
+
    # Filter suite
    suite = SUITE[:]
    if args.category:
--- a/cli.py
+++ b/cli.py
@@ -13,7 +13,6 @@ Usage:
    python cli.py --list-tools             # List available tools and exit
 """

-import concurrent.futures
 import logging
 import os
 import shutil
@@ -64,7 +63,6 @@ from agent.usage_pricing import (
    format_duration_compact,
    format_token_count_compact,
 )
-from agent.account_usage import fetch_account_usage, render_account_usage_lines
 from hermes_cli.banner import _format_context_length, format_banner_version_label

 _COMMAND_SPINNER_FRAMES = ("⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏")
@@ -6473,29 +6471,6 @@ class HermesCLI:
        if cost_result.status == "unknown":
            print(f"  Note:             Pricing unknown for {agent.model}")

-        # Account limits -- fetched off-thread with a hard timeout so slow
-        # provider APIs don't hang the prompt.
-        provider = getattr(agent, "provider", None) or getattr(self, "provider", None)
-        base_url = getattr(agent, "base_url", None) or getattr(self, "base_url", None)
-        api_key = getattr(agent, "api_key", None) or getattr(self, "api_key", None)
-        account_snapshot = None
-        if provider:
-            with concurrent.futures.ThreadPoolExecutor(max_workers=1) as _pool:
-                try:
-                    account_snapshot = _pool.submit(
-                        fetch_account_usage,
-                        provider,
-                        base_url=base_url,
-                        api_key=api_key,
-                    ).result(timeout=10.0)
-                except (concurrent.futures.TimeoutError, Exception):
-                    account_snapshot = None
-        account_lines = [f"  {line}" for line in render_account_usage_lines(account_snapshot)]
-        if account_lines:
-            print()
-            for line in account_lines:
-                print(line)
-
        if self.verbose:
            logging.getLogger().setLevel(logging.DEBUG)
            for noisy in ('openai', 'openai._base_client', 'httpx', 'httpcore', 'asyncio', 'hpack', 'grpc', 'modal'):
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -28,8 +28,6 @@ from pathlib import Path
 from datetime import datetime
 from typing import Dict, Optional, Any, List

-from agent.account_usage import fetch_account_usage, render_account_usage_lines
-
 # ---------------------------------------------------------------------------
 # SSL certificate auto-detection for NixOS and other non-standard systems.
 # Must run BEFORE any HTTP library (discord, aiohttp, etc.) is imported.
@@ -6483,38 +6481,6 @@ class GatewayRunner:
                    if cached:
                        agent = cached[0]

-        # Resolve provider/base_url/api_key for the account-usage fetch.
-        # Prefer the live agent; fall back to persisted billing data on the
-        # SessionDB row so `/usage` still returns account info between turns
-        # when no agent is resident.
-        provider = getattr(agent, "provider", None) if agent and agent is not _AGENT_PENDING_SENTINEL else None
-        base_url = getattr(agent, "base_url", None) if agent and agent is not _AGENT_PENDING_SENTINEL else None
-        api_key = getattr(agent, "api_key", None) if agent and agent is not _AGENT_PENDING_SENTINEL else None
-        if not provider and getattr(self, "_session_db", None) is not None:
-            try:
-                _entry_for_billing = self.session_store.get_or_create_session(source)
-                persisted = self._session_db.get_session(_entry_for_billing.session_id) or {}
-            except Exception:
-                persisted = {}
-            provider = provider or persisted.get("billing_provider")
-            base_url = base_url or persisted.get("billing_base_url")
-
-        # Fetch account usage off the event loop so slow provider APIs don't
-        # block the gateway. Failures are non-fatal -- account_lines stays [].
-        account_lines: list[str] = []
-        if provider:
-            try:
-                account_snapshot = await asyncio.to_thread(
-                    fetch_account_usage,
-                    provider,
-                    base_url=base_url,
-                    api_key=api_key,
-                )
-            except Exception:
-                account_snapshot = None
-            if account_snapshot:
-                account_lines = render_account_usage_lines(account_snapshot, markdown=True)
-
        if agent and hasattr(agent, "session_total_tokens") and agent.session_api_calls > 0:
            lines = []

@@ -6572,10 +6538,6 @@ class GatewayRunner:
            if ctx.compression_count:
                lines.append(f"Compressions: {ctx.compression_count}")

-            if account_lines:
-                lines.append("")
-                lines.extend(account_lines)
-
            return "\n".join(lines)

        # No agent at all -- check session history for a rough count
@@ -6585,18 +6547,12 @@ class GatewayRunner:
            from agent.model_metadata import estimate_messages_tokens_rough
            msgs = [m for m in history if m.get("role") in ("user", "assistant") and m.get("content")]
            approx = estimate_messages_tokens_rough(msgs)
-            lines = [
-                "📊 **Session Info**",
-                f"Messages: {len(msgs)}",
-                f"Estimated context: ~{approx:,} tokens",
-                "_(Detailed usage available after the first agent response)_",
-            ]
-            if account_lines:
-                lines.append("")
-                lines.extend(account_lines)
-            return "\n".join(lines)
-        if account_lines:
-            return "\n".join(account_lines)
+            return (
+                f"📊 **Session Info**\n"
+                f"Messages: {len(msgs)}\n"
+                f"Estimated context: ~{approx:,} tokens\n"
+                f"_(Detailed usage available after the first agent response)_"
+            )
        return "No usage data available for this session."

    async def _handle_insights_command(self, event: MessageEvent) -> str:
--- a/tests/gateway/test_usage_command.py
+++ b/tests/gateway/test_usage_command.py
@@ -175,79 +175,3 @@ class TestUsageCachedAgent:
            result = await runner._handle_usage_command(event)

        assert "Cost: included" in result
-
-
-class TestUsageAccountSection:
-    """Account-limits section appended to /usage output."""
-
-    @pytest.mark.asyncio
-    async def test_usage_command_includes_account_section(self, monkeypatch):
-        agent = _make_mock_agent(provider="openai-codex")
-        agent.base_url = "https://chatgpt.com/backend-api/codex"
-        agent.api_key = "unused"
-        runner = _make_runner(SK, cached_agent=agent)
-        event = MagicMock()
-
-        monkeypatch.setattr(
-            "gateway.run.fetch_account_usage",
-            lambda provider, base_url=None, api_key=None: object(),
-        )
-        monkeypatch.setattr(
-            "gateway.run.render_account_usage_lines",
-            lambda snapshot, markdown=False: [
-                "📈 **Account limits**",
-                "Provider: openai-codex (Pro)",
-                "Session: 85% remaining (15% used)",
-            ],
-        )
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="included")
-            result = await runner._handle_usage_command(event)
-
-        assert "📊 **Session Token Usage**" in result
-        assert "📈 **Account limits**" in result
-        assert "Provider: openai-codex (Pro)" in result
-
-    @pytest.mark.asyncio
-    async def test_usage_command_uses_persisted_provider_when_agent_not_running(self, monkeypatch):
-        runner = _make_runner(SK)
-        runner._session_db = MagicMock()
-        runner._session_db.get_session.return_value = {
-            "billing_provider": "openai-codex",
-            "billing_base_url": "https://chatgpt.com/backend-api/codex",
-        }
-        session_entry = MagicMock()
-        session_entry.session_id = "sess-1"
-        runner.session_store.get_or_create_session.return_value = session_entry
-        runner.session_store.load_transcript.return_value = [
-            {"role": "user", "content": "earlier"},
-        ]
-
-        calls = {}
-
-        async def _fake_to_thread(fn, *args, **kwargs):
-            calls["args"] = args
-            calls["kwargs"] = kwargs
-            return fn(*args, **kwargs)
-
-        monkeypatch.setattr("gateway.run.asyncio.to_thread", _fake_to_thread)
-        monkeypatch.setattr(
-            "gateway.run.fetch_account_usage",
-            lambda provider, base_url=None, api_key=None: object(),
-        )
-        monkeypatch.setattr(
-            "gateway.run.render_account_usage_lines",
-            lambda snapshot, markdown=False: [
-                "📈 **Account limits**",
-                "Provider: openai-codex (Pro)",
-            ],
-        )
-
-        event = MagicMock()
-        result = await runner._handle_usage_command(event)
-
-        assert calls["args"] == ("openai-codex",)
-        assert calls["kwargs"]["base_url"] == "https://chatgpt.com/backend-api/codex"
-        assert "📊 **Session Info**" in result
-        assert "📈 **Account limits**" in result
--- a/tests/test_account_usage.py
+++ b/tests/test_account_usage.py
@@ -1,203 +0,0 @@
-from datetime import datetime, timezone
-
-from agent.account_usage import (
-    AccountUsageSnapshot,
-    AccountUsageWindow,
-    fetch_account_usage,
-    render_account_usage_lines,
-)
-
-
-class _Response:
-    def __init__(self, payload, status_code=200):
-        self._payload = payload
-        self.status_code = status_code
-
-    def raise_for_status(self):
-        if self.status_code >= 400:
-            raise RuntimeError(f"HTTP {self.status_code}")
-
-    def json(self):
-        return self._payload
-
-
-class _Client:
-    def __init__(self, payload):
-        self._payload = payload
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc, tb):
-        return False
-
-    def get(self, url, headers=None):
-        return _Response(self._payload)
-
-
-class _RoutingClient:
-    def __init__(self, payloads):
-        self._payloads = payloads
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc, tb):
-        return False
-
-    def get(self, url, headers=None):
-        return _Response(self._payloads[url])
-
-
-def test_fetch_account_usage_codex(monkeypatch):
-    monkeypatch.setattr(
-        "agent.account_usage.resolve_codex_runtime_credentials",
-        lambda refresh_if_expiring=True: {
-            "provider": "openai-codex",
-            "base_url": "https://chatgpt.com/backend-api/codex",
-            "api_key": "***",
-        },
-    )
-    monkeypatch.setattr(
-        "agent.account_usage._read_codex_tokens",
-        lambda: {"tokens": {"account_id": "acct_123"}},
-    )
-    monkeypatch.setattr(
-        "agent.account_usage.httpx.Client",
-        lambda timeout=15.0: _Client(
-            {
-                "plan_type": "pro",
-                "rate_limit": {
-                    "primary_window": {
-                        "used_percent": 15,
-                        "reset_at": 1_900_000_000,
-                        "limit_window_seconds": 18000,
-                    },
-                    "secondary_window": {
-                        "used_percent": 40,
-                        "reset_at": 1_900_500_000,
-                        "limit_window_seconds": 604800,
-                    },
-                },
-                "credits": {"has_credits": True, "balance": 12.5},
-            }
-        ),
-    )
-
-    snapshot = fetch_account_usage("openai-codex")
-
-    assert snapshot is not None
-    assert snapshot.plan == "Pro"
-    assert len(snapshot.windows) == 2
-    assert snapshot.windows[0].label == "Session"
-    assert snapshot.windows[0].used_percent == 15.0
-    assert snapshot.windows[0].reset_at == datetime.fromtimestamp(1_900_000_000, tz=timezone.utc)
-    assert "Credits balance: $12.50" in snapshot.details
-
-
-def test_render_account_usage_lines_includes_reset_and_provider():
-    snapshot = AccountUsageSnapshot(
-        provider="openai-codex",
-        source="usage_api",
-        fetched_at=datetime.now(timezone.utc),
-        plan="Pro",
-        windows=(
-            AccountUsageWindow(
-                label="Session",
-                used_percent=25,
-                reset_at=datetime.now(timezone.utc),
-            ),
-        ),
-        details=("Credits balance: $9.99",),
-    )
-    lines = render_account_usage_lines(snapshot)
-
-    assert lines[0] == "📈 Account limits"
-    assert "openai-codex (Pro)" in lines[1]
-    assert "Session: 75% remaining (25% used)" in lines[2]
-    assert "Credits balance: $9.99" in lines[3]
-
-
-def test_fetch_account_usage_openrouter_uses_limit_remaining_and_ignores_deprecated_rate_limit(monkeypatch):
-    monkeypatch.setattr(
-        "agent.account_usage.resolve_runtime_provider",
-        lambda requested, explicit_base_url=None, explicit_api_key=None: {
-            "provider": "openrouter",
-            "base_url": "https://openrouter.ai/api/v1",
-            "api_key": "***",
-        },
-    )
-    monkeypatch.setattr(
-        "agent.account_usage.httpx.Client",
-        lambda timeout=10.0: _RoutingClient(
-            {
-                "https://openrouter.ai/api/v1/credits": {
-                    "data": {"total_credits": 300.0, "total_usage": 10.92}
-                },
-                "https://openrouter.ai/api/v1/key": {
-                    "data": {
-                        "limit": 100.0,
-                        "limit_remaining": 70.0,
-                        "limit_reset": "monthly",
-                        "usage": 12.5,
-                        "usage_daily": 0.5,
-                        "usage_weekly": 2.0,
-                        "usage_monthly": 8.0,
-                        "rate_limit": {"requests": -1, "interval": "10s"},
-                    }
-                },
-            }
-        ),
-    )
-
-    snapshot = fetch_account_usage("openrouter")
-
-    assert snapshot is not None
-    assert snapshot.windows == (
-        AccountUsageWindow(
-            label="API key quota",
-            used_percent=30.0,
-            detail="$70.00 of $100.00 remaining • resets monthly",
-        ),
-    )
-    assert "Credits balance: $289.08" in snapshot.details
-    assert "API key usage: $12.50 total • $0.50 today • $2.00 this week • $8.00 this month" in snapshot.details
-    assert all("-1 requests / 10s" not in line for line in render_account_usage_lines(snapshot))
-
-
-def test_fetch_account_usage_openrouter_omits_quota_window_when_key_has_no_limit(monkeypatch):
-    monkeypatch.setattr(
-        "agent.account_usage.resolve_runtime_provider",
-        lambda requested, explicit_base_url=None, explicit_api_key=None: {
-            "provider": "openrouter",
-            "base_url": "https://openrouter.ai/api/v1",
-            "api_key": "***",
-        },
-    )
-    monkeypatch.setattr(
-        "agent.account_usage.httpx.Client",
-        lambda timeout=10.0: _RoutingClient(
-            {
-                "https://openrouter.ai/api/v1/credits": {
-                    "data": {"total_credits": 100.0, "total_usage": 25.5}
-                },
-                "https://openrouter.ai/api/v1/key": {
-                    "data": {
-                        "limit": None,
-                        "limit_remaining": None,
-                        "usage": 25.5,
-                        "usage_daily": 1.25,
-                        "usage_weekly": 4.5,
-                        "usage_monthly": 18.0,
-                    }
-                },
-            }
-        ),
-    )
-
-    snapshot = fetch_account_usage("openrouter")
-
-    assert snapshot is not None
-    assert snapshot.windows == ()
-    assert "Credits balance: $74.50" in snapshot.details
-    assert "API key usage: $25.50 total • $1.25 today • $4.50 this week • $18.00 this month" in snapshot.details
--- a/tests/test_tool_call_benchmark.py
+++ b/tests/test_tool_call_benchmark.py
@@ -0,0 +1,115 @@
+"""Tests for Issue #796 tool-calling benchmark coverage and reporting."""
+
+import sys
+from pathlib import Path
+from types import SimpleNamespace
+from unittest.mock import patch
+
+sys.path.insert(0, str(Path(__file__).parent.parent / "benchmarks"))
+
+from tool_call_benchmark import (  # noqa: E402
+    CallResult,
+    DEFAULT_COMPARE_MODELS,
+    ISSUE_796_CATEGORY_COUNTS,
+    ToolCall,
+    generate_report,
+    run_single_test,
+    suite_category_counts,
+)
+
+
+def test_suite_counts_match_issue_796_distribution():
+    counts = suite_category_counts()
+    assert counts == ISSUE_796_CATEGORY_COUNTS
+    assert sum(counts.values()) == 100
+
+
+def test_default_compare_models_cover_issue_796_lanes():
+    assert len(DEFAULT_COMPARE_MODELS) == 3
+    assert any("gemma-4-31b" in spec for spec in DEFAULT_COMPARE_MODELS)
+    assert any("gemma-4-26b" in spec for spec in DEFAULT_COMPARE_MODELS)
+    assert any("mimo-v2-pro" in spec for spec in DEFAULT_COMPARE_MODELS)
+
+
+def test_generate_report_includes_parallel_and_cost_metrics(tmp_path):
+    output_path = tmp_path / "report.md"
+    results = [
+        CallResult(
+            test_id="file-01",
+            category="file",
+            model="gemma-4-31b",
+            prompt="Read the file.",
+            expected_tool="read_file",
+            success=True,
+            tool_called="read_file",
+            schema_ok=True,
+            tool_args_valid=True,
+            execution_ok=True,
+            tool_count=2,
+            parallel_ok=True,
+            latency_s=1.25,
+            total_tokens=123,
+            estimated_cost_usd=0.0012,
+            cost_status="estimated",
+        ),
+        CallResult(
+            test_id="web-01",
+            category="web",
+            model="mimo-v2-pro",
+            prompt="Search the web.",
+            expected_tool="web_search",
+            success=False,
+            tool_called="web_search",
+            schema_ok=True,
+            tool_args_valid=False,
+            execution_ok=False,
+            tool_count=1,
+            parallel_ok=False,
+            latency_s=2.5,
+            error="bad args",
+            total_tokens=456,
+            estimated_cost_usd=None,
+            cost_status="unknown",
+            skipped=True,
+            skip_reason="web_search unavailable",
+        ),
+    ]
+
+    report = generate_report(results, ["gemma-4-31b", "mimo-v2-pro"], output_path)
+
+    assert output_path.exists()
+    assert "Parallel tool success" in report
+    assert "Avg token cost per call (USD)" in report
+    assert "Skipped / unavailable" in report
+    assert "Requested category mix" in report
+
+
+def test_run_single_test_skips_when_expected_tool_unavailable():
+    class FakeAgent:
+        def __init__(self, *args, **kwargs):
+            self.valid_tool_names = {"read_file", "terminal"}
+            self.session_input_tokens = 0
+            self.session_output_tokens = 0
+            self.session_cache_read_tokens = 0
+            self.session_cache_write_tokens = 0
+            self.session_api_calls = 0
+            self.base_url = ""
+            self.api_key = None
+
+        def run_conversation(self, *args, **kwargs):
+            raise AssertionError("run_conversation should not be called for unavailable tools")
+
+    tc = ToolCall(
+        id="mcp-01",
+        category="mcp",
+        prompt="Use an MCP tool to list resources.",
+        expected_tool="",
+        expected_tool_prefix="mcp_",
+    )
+
+    with patch.dict(sys.modules, {"run_agent": SimpleNamespace(AIAgent=FakeAgent)}):
+        result = run_single_test(tc, "gemini:gemma-4-31b-it", "gemini")
+
+    assert result.skipped is True
+    assert "mcp_" in result.skip_reason
+    assert result.success is False
Author	SHA1	Message	Date
Alexander Whitestone	411aea9edf	feat: harden tool-call benchmark coverage and reporting for #796 All checks were successful Lint / lint (pull_request) Successful in 9s Details Refs #796	2026-04-22 11:47:11 -04:00
Alexander Whitestone	877005b06e	wip: add failing tool-call benchmark regression tests for #796 Refs #796	2026-04-22 11:31:24 -04:00