fix: restore /usage account limits (#958)

agent/account_usage.py

@@ -0,0 +1,326 @@
+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

cli.py

@@ -13,6 +13,7 @@ Usage:
     python cli.py --list-tools             # List available tools and exit
 """
 
+import concurrent.futures
 import logging
 import os
 import shutil
@@ -63,6 +64,7 @@ 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 = ("⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏")
@@ -6471,6 +6473,29 @@ 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'):

docs/review_packets/hermes-harness-2026-04-21.md

@@ -1,387 +0,0 @@
-# Morning Review Packet
-
-Source epic: [EPIC: Morning review packet — Hermes harness features landed 2026-04-21](https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/949)
-
-## Epic context
-
-EPIC: Morning review packet — Hermes harness features landed 2026-04-21
-
-Source: git log on upstream/main since 2026-04-21 00:00 EDT, plus the current local branch `burn/921-poka-yoke-hardcoded-paths` for the branch-only path-guard work.
-
-Important review note:
-- Validate upstream-landed features on `upstream/main` or a synced branch.
-- Validate the path-guard work on `burn/921-poka-yoke-hardcoded-paths`.
-
-This epic is a morning-review packet: one QA issue per feature cluster, each with concrete acceptance criteria and targeted tests or manual checks.
-
-## Success criteria
-- [ ] Every issue has a clear PASS / FAIL outcome.
-- [ ] Test output or manual evidence is attached to each issue.
-- [ ] Any drift between upstream/main and forge/main is called out explicitly.
-
-## Sub-issues
-### Upstream/main features landed 2026-04-21
-- [ ] #950 [QA] Verify AI Gateway provider UX + attribution headers
-- [ ] #951 [QA] Verify transport abstraction + AnthropicTransport wiring
-- [ ] #952 [QA] Verify CLI voice beep toggle
-- [ ] #953 [QA] Verify bundled skill scripts run out of the box
-- [ ] #954 [QA] Verify maps skill guest_house / camp_site / bakery expansion
-- [ ] #955 [QA] Verify KittenTTS local provider end-to-end
-- [ ] #956 [QA] Verify numbered keyboard shortcuts for approval + clarify prompts
-- [ ] #957 [QA] Verify optional adversarial-ux-test skill catalog flow
-- [ ] #958 [QA] Verify /usage account limits in CLI + gateway
-- [ ] #959 [QA] Verify OpenCode-Go curated catalog additions
-- [ ] #960 [QA] Verify patch 'did you mean?' suggestions
-- [ ] #961 [QA] Verify web dashboard update/restart action buttons
-
-### Local branch-only work
-- [ ] #962 [QA] Verify hardcoded-home path guard on burn/921 branch
-
-## Summary
-
-| Issue | State | Commits | Tests |
-| --- | --- | --- | --- |
-| #950 | open | 5 | 2 |
-| #951 | open | 2 | 2 |
-| #952 | open | 1 | 1 |
-| #953 | open | 1 | 2 |
-| #954 | open | 1 | 0 |
-| #955 | open | 2 | 1 |
-| #956 | open | 1 | 0 |
-| #957 | open | 1 | 0 |
-| #958 | open | 2 | 2 |
-| #959 | open | 1 | 1 |
-| #960 | open | 2 | 1 |
-| #961 | closed | 1 | 0 |
-| #962 | closed | 1 | 1 |
-
-## #950 — [QA] Verify AI Gateway provider UX + attribution headers
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/950
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `b11753879` — attribution default_headers for ai-gateway provider
-- `700437440` — curated picker with live pricing
-- `ac26a460f` — promote ai-gateway in provider picker ordering
-- `5bb2d11b0` — auto-promote free Moonshot models
-- `29f57ec95` — Vercel deep-link for API key creation
-
-### Targeted tests
-- `tests/hermes_cli/test_ai_gateway_models.py`
-- `tests/run_agent/test_provider_attribution_headers.py`
-
-### Tasks
-- [ ] Open `hermes model` and verify `ai-gateway` appears near the top.
-- [ ] Verify live pricing appears in the picker.
-- [ ] Verify free Moonshot models are promoted.
-- [ ] Trigger API-key setup flow and verify the Vercel deep link.
-- [ ] Send one ai-gateway request and verify attribution headers are attached.
-
-### Acceptance criteria
-- [ ] UI ordering and pricing match the landed behavior.
-- [ ] Attribution headers are present on ai-gateway requests.
-- [ ] Targeted tests pass.
-
-## #951 — [QA] Verify transport abstraction + AnthropicTransport wiring
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/951
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `7ab5eebd0` — transport types + Anthropic normalize migration
-- `731f4fbae` — transport ABC + AnthropicTransport wired to all paths
-
-### Targeted tests
-- `tests/agent/transports/test_types.py`
-- `tests/agent/test_anthropic_normalize_v2.py`
-
-### Tasks
-- [ ] Verify plain-text Anthropic responses normalize correctly.
-- [ ] Verify tool-call responses preserve IDs, names, and arguments.
-- [ ] Verify reasoning/thinking is preserved separately from visible content.
-- [ ] Verify finish_reason mapping remains correct across paths.
-
-### Acceptance criteria
-- [ ] Normalized response shape is stable.
-- [ ] Tool-call and reasoning payloads survive normalization.
-- [ ] Targeted tests pass.
-
-## #952 — [QA] Verify CLI voice beep toggle
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/952
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `b48ea41d2` — voice: add CLI beep toggle
-
-### Targeted tests
-- `tests/tools/test_voice_cli_integration.py`
-
-### Tasks
-- [ ] Enable the beep option in config and confirm voice mode emits the beep.
-- [ ] Disable the option and confirm the same path is silent.
-- [ ] Verify voice mode still strips markdown before speech output.
-- [ ] Verify voice mode does not pollute conversation history with TTS-only text.
-
-### Acceptance criteria
-- [ ] Beep behavior is actually toggled by config.
-- [ ] Existing voice/TTS integration behavior is not regressed.
-- [ ] Targeted tests pass.
-
-## #953 — [QA] Verify bundled skill scripts run out of the box
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/953
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `328223576` — make bundled skill scripts runnable out of the box
-
-### Targeted tests
-- `tests/agent/test_skill_commands.py`
-- `tests/tools/test_local_shell_init.py`
-
-### Tasks
-- [ ] Pick a bundled skill that ships a script and run it without manual chmod/PATH surgery.
-- [ ] Verify local terminal execution resolves the installed skill script correctly.
-- [ ] Verify local shell init still behaves correctly.
-
-### Acceptance criteria
-- [ ] Bundled skill scripts execute from the installed skill location with no manual prep.
-- [ ] Local shell init remains healthy.
-- [ ] Targeted tests pass.
-
-## #954 — [QA] Verify maps skill guest_house / camp_site / bakery expansion
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/954
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `c5a814b23` — maps: add guest_house, camp_site, and dual-key bakery lookup
-
-### Tasks
-- [ ] Use the maps skill to search for a guest house in a known populated area.
-- [ ] Use the maps skill to search for a camp site in a known populated area.
-- [ ] Use the maps skill to search for a bakery and verify both supported keys resolve correctly.
-- [ ] Confirm results are sensible and non-empty.
-
-### Acceptance criteria
-- [ ] All three place types resolve correctly.
-- [ ] Bakery lookup works through both supported keys.
-- [ ] Manual evidence is attached in the issue.
-
-## #955 — [QA] Verify KittenTTS local provider end-to-end
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/955
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `1830ebfc5` — add KittenTTS provider
-- `2d7ff9c5b` — complete KittenTTS integration across tools/setup/docs/tests
-
-### Targeted tests
-- `tests/tools/test_tts_kittentts.py`
-
-### Tasks
-- [ ] Configure TTS to use `kittentts`.
-- [ ] Generate speech to `.wav` and verify playable output.
-- [ ] Verify voice / speed / cleaned text are passed correctly.
-- [ ] Generate repeated requests and verify model caching behavior.
-- [ ] Generate a non-wav output and verify ffmpeg conversion path.
-- [ ] Verify missing-package behavior returns a helpful error.
-
-### Acceptance criteria
-- [ ] KittenTTS works end-to-end when installed.
-- [ ] Failure mode is operator-friendly when not installed.
-- [ ] Targeted tests pass.
-
-## #956 — [QA] Verify numbered keyboard shortcuts for approval + clarify prompts
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/956
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `d1ed6f4fb` — CLI: add numbered keyboard shortcuts to approval and clarify prompts
-
-### Tasks
-- [ ] Trigger an approval prompt and choose an option with number keys.
-- [ ] Trigger a clarify prompt and choose an option with number keys.
-- [ ] Verify the correct option is submitted both times.
-- [ ] Verify normal keyboard navigation still works.
-
-### Acceptance criteria
-- [ ] Number-key selection works for both prompt types.
-- [ ] Legacy keyboard navigation is not broken.
-- [ ] Manual evidence is attached in the issue.
-
-## #957 — [QA] Verify optional adversarial-ux-test skill catalog flow
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/957
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `e50e7f11b` — skills: add adversarial-ux-test optional skill
-
-### Tasks
-- [ ] Verify the optional skill appears in the optional skill catalog.
-- [ ] Install or enable the skill.
-- [ ] Load it successfully through Hermes.
-- [ ] Disable or remove it and verify catalog state updates cleanly.
-
-### Acceptance criteria
-- [ ] Catalog listing is correct.
-- [ ] Install / load / disable lifecycle works cleanly.
-- [ ] Manual evidence is attached in the issue.
-
-## #958 — [QA] Verify /usage account limits in CLI + gateway
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/958
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `8a11b0a20` — per-provider account limits module
-- `bcc5d7b67` — append account limits section in CLI and gateway
-
-### Targeted tests
-- `tests/test_account_usage.py`
-- `tests/gateway/test_usage_command.py`
-
-### Tasks
-- [ ] Run `/usage` in CLI for a provider with account limits.
-- [ ] Verify provider, remaining quota, total limit, and reset window render correctly.
-- [ ] Run `/usage` through the gateway and verify the same section appears.
-- [ ] Verify zero-value cache read/write sections stay hidden when appropriate.
-
-### Acceptance criteria
-- [ ] CLI and gateway both show the landed account-limits section correctly.
-- [ ] Targeted tests pass.
-
-## #959 — [QA] Verify OpenCode-Go curated catalog additions
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/959
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `4fea1769d` — opencode-go: add Kimi K2.6 and Qwen3.5/3.6 Plus to curated catalog
-
-### Targeted tests
-- `tests/hermes_cli/test_opencode_go_in_model_list.py`
-
-### Tasks
-- [ ] With valid OpenCode-Go credentials, open `hermes model`.
-- [ ] Verify Kimi K2.6 appears.
-- [ ] Verify Qwen 3.5 Plus and 3.6 Plus appear.
-- [ ] Unset credentials and verify the provider/catalog hides correctly.
-
-### Acceptance criteria
-- [ ] New curated models are present when credentials exist.
-- [ ] Catalog visibility still respects credential gating.
-- [ ] Targeted tests pass.
-
-## #960 — [QA] Verify patch 'did you mean?' suggestions
-
-State: open
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/960
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `15abf4ed8` — add `did you mean?` feedback when patch fails to match
-- `5e6427a42` — gate it to true no-match cases and extend to v4a / skill_manage
-
-### Targeted tests
-- `tests/tools/test_fuzzy_match.py`
-
-### Tasks
-- [ ] Intentionally run a replace/patch with a near-miss `old_string`.
-- [ ] Verify the tool suggests a useful nearby line/context.
-- [ ] Verify suggestions only appear on true no-match failures.
-- [ ] Verify the behavior also works via file tools, v4a patching, and skill_manage.
-
-### Acceptance criteria
-- [ ] Suggestion quality is helpful, not noisy.
-- [ ] Suggestions are correctly gated to no-match cases.
-- [ ] Targeted tests pass.
-
-## #961 — [QA] Verify web dashboard update/restart action buttons
-
-State: closed
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/961
-
-### Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-### Commits
-- `fc21c1420` — add buttons to update Hermes and restart gateway
-
-### Files touched
-- `web/src/pages/StatusPage.tsx`
-- `web/src/lib/api.ts`
-- `web/src/i18n/en.ts`
-
-### Tasks
-- [ ] Open the Web UI status page and verify both buttons are present.
-- [ ] Click Restart Gateway in a safe environment and verify running/output/success-or-failure states render.
-- [ ] Click Update Hermes and verify the same action lifecycle.
-- [ ] Verify the page remains responsive while actions are running.
-
-### Acceptance criteria
-- [ ] Both action buttons are present and wired.
-- [ ] Action status polling and result rendering work end-to-end.
-- [ ] Manual evidence is attached in the issue.
-
-## #962 — [QA] Verify hardcoded-home path guard on burn/921 branch
-
-State: closed
-URL: https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent/issues/962
-
-### Branch / checkout
-- Validate specifically on `burn/921-poka-yoke-hardcoded-paths` (not upstream/main).
-
-### Commits
-- `5dcb90531` — Poka-yoke: prevent hardcoded home-directory paths
-
-### Targeted tests
-- `tests/test_path_guard.py`
-
-### Tasks
-- [ ] Verify hardcoded `/Users/...` paths are rejected.
-- [ ] Verify hardcoded `~/.hermes/...` paths are rejected in guarded contexts.
-- [ ] Verify valid relative paths still pass.
-- [ ] Verify appropriate absolute paths still pass where intended.
-- [ ] Verify linting catches violations in non-test files.
-
-### Acceptance criteria
-- [ ] Guard blocks the dangerous patterns and preserves allowed ones.
-- [ ] Targeted tests pass.

gateway/run.py

@@ -28,6 +28,8 @@ 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.
@@ -6481,6 +6483,38 @@ 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 = []
 
@@ -6538,6 +6572,10 @@ 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
@@ -6547,12 +6585,18 @@ 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)
-            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)_"
-            )
+            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 "No usage data available for this session."
 
     async def _handle_insights_command(self, event: MessageEvent) -> str:

scripts/morning_review_packet.py

@@ -1,301 +0,0 @@
-#!/usr/bin/env python3
-"""Build a morning review packet from a Gitea epic and its child QA issues.
-
-This script fetches a parent epic plus its sub-issues, extracts the structured
-sections from each QA issue body, and renders a single markdown packet suitable
-for morning review.
-
-Usage:
-    python scripts/morning_review_packet.py --epic-number 949
-    python scripts/morning_review_packet.py --epic-number 949 --children 950-962
-    python scripts/morning_review_packet.py --epic-number 949 --output docs/review_packets/hermes-harness-2026-04-21.md
-"""
-
-from __future__ import annotations
-
-import argparse
-import json
-import os
-import re
-import urllib.request
-from dataclasses import dataclass, field
-from pathlib import Path
-from typing import Iterable
-
-DEFAULT_BASE_URL = "https://forge.alexanderwhitestone.com"
-DEFAULT_OWNER = "Timmy_Foundation"
-DEFAULT_REPO = "hermes-agent"
-DEFAULT_TOKEN_PATH = Path.home() / ".config" / "gitea" / "token"
-
-
-@dataclass(frozen=True)
-class CommitEvidence:
-    sha: str
-    summary: str
-
-
-@dataclass
-class ReviewIssue:
-    number: int
-    title: str
-    state: str
-    url: str
-    comments: int = 0
-    parent_issue: int | None = None
-    checkout_notes: list[str] = field(default_factory=list)
-    commits: list[CommitEvidence] = field(default_factory=list)
-    targeted_tests: list[str] = field(default_factory=list)
-    files_touched: list[str] = field(default_factory=list)
-    tasks: list[str] = field(default_factory=list)
-    acceptance_criteria: list[str] = field(default_factory=list)
-
-
-def parse_issue_number_spec(spec: str) -> list[int]:
-    """Parse a comma-separated issue list like ``950-952,955,962``."""
-    numbers: list[int] = []
-    seen: set[int] = set()
-    for chunk in (part.strip() for part in spec.split(",")):
-        if not chunk:
-            continue
-        if "-" in chunk:
-            start_str, end_str = (part.strip() for part in chunk.split("-", 1))
-            start = int(start_str)
-            end = int(end_str)
-            if end < start:
-                raise ValueError(f"Invalid descending issue range: {chunk}")
-            for number in range(start, end + 1):
-                if number not in seen:
-                    numbers.append(number)
-                    seen.add(number)
-        else:
-            number = int(chunk)
-            if number not in seen:
-                numbers.append(number)
-                seen.add(number)
-    return numbers
-
-
-def _parse_sections(body: str) -> dict[str, list[str]]:
-    sections: dict[str, list[str]] = {}
-    current: str | None = None
-    for raw_line in body.splitlines():
-        line = raw_line.rstrip()
-        if line.startswith("## "):
-            current = line[3:].strip()
-            sections[current] = []
-            continue
-        if current is not None:
-            sections[current].append(line)
-    return sections
-
-
-def _clean_bullet(line: str) -> str | None:
-    stripped = line.strip()
-    if not stripped:
-        return None
-    stripped = re.sub(r"^-\s*\[(?: |x|X)\]\s*", "", stripped)
-    stripped = re.sub(r"^-\s*", "", stripped)
-    return stripped.strip() or None
-
-
-def _extract_bullets(lines: Iterable[str]) -> list[str]:
-    items: list[str] = []
-    for line in lines:
-        cleaned = _clean_bullet(line)
-        if cleaned:
-            items.append(cleaned)
-    return items
-
-
-def _extract_parent_issue(body: str, sections: dict[str, list[str]]) -> int | None:
-    parent_lines = sections.get("Parent", [])
-    for line in parent_lines:
-        match = re.search(r"#(\d+)", line)
-        if match:
-            return int(match.group(1))
-    match = re.search(r"Linked to Epic\s+#(\d+)", body, flags=re.IGNORECASE)
-    if match:
-        return int(match.group(1))
-    return None
-
-
-def _extract_commits(lines: Iterable[str]) -> list[CommitEvidence]:
-    commits: list[CommitEvidence] = []
-    for item in _extract_bullets(lines):
-        match = re.match(r"`([^`]+)`\s*(.*)", item)
-        if match:
-            commits.append(CommitEvidence(sha=match.group(1).strip(), summary=match.group(2).strip()))
-        else:
-            commits.append(CommitEvidence(sha="", summary=item))
-    return commits
-
-
-def _strip_backticks(items: Iterable[str]) -> list[str]:
-    cleaned: list[str] = []
-    for item in items:
-        cleaned.append(item.replace("`", "").strip())
-    return cleaned
-
-
-def discover_child_issue_numbers(epic_body: str) -> list[int]:
-    """Discover sub-issue numbers from an epic body."""
-    sections = _parse_sections(epic_body)
-    sub_lines = sections.get("Sub-issues")
-    if not sub_lines:
-        return []
-    numbers: list[int] = []
-    seen: set[int] = set()
-    for line in sub_lines:
-        for match in re.finditer(r"#(\d+)", line):
-            number = int(match.group(1))
-            if number not in seen:
-                numbers.append(number)
-                seen.add(number)
-    return numbers
-
-
-def parse_child_issue(issue: dict) -> ReviewIssue:
-    body = issue.get("body") or ""
-    sections = _parse_sections(body)
-    commit_lines = sections.get("Commits landed today", []) or sections.get("Commit landed today", [])
-
-    return ReviewIssue(
-        number=int(issue["number"]),
-        title=issue.get("title") or "",
-        state=(issue.get("state") or "unknown").lower(),
-        url=issue.get("html_url") or issue.get("url") or "",
-        comments=int(issue.get("comments") or 0),
-        parent_issue=_extract_parent_issue(body, sections),
-        checkout_notes=_extract_bullets(sections.get("Branch / checkout", [])),
-        commits=_extract_commits(commit_lines),
-        targeted_tests=_strip_backticks(_extract_bullets(sections.get("Targeted tests", []))),
-        files_touched=_strip_backticks(_extract_bullets(sections.get("Files touched", []))),
-        tasks=_extract_bullets(sections.get("Tasks", [])),
-        acceptance_criteria=_extract_bullets(sections.get("Acceptance Criteria", [])),
-    )
-
-
-def build_packet_markdown(epic_issue: dict, child_issues: list[ReviewIssue]) -> str:
-    title = epic_issue.get("title") or f"Epic #{epic_issue.get('number')}"
-    url = epic_issue.get("html_url") or epic_issue.get("url") or ""
-    body = epic_issue.get("body") or ""
-    children = sorted(child_issues, key=lambda item: item.number)
-
-    lines: list[str] = []
-    lines.append("# Morning Review Packet")
-    lines.append("")
-    lines.append(f"Source epic: [{title}]({url})")
-    lines.append("")
-    lines.append("## Epic context")
-    lines.append("")
-    lines.append(title)
-    lines.append("")
-    for line in body.splitlines():
-        if line.strip():
-            lines.append(line)
-        else:
-            lines.append("")
-    lines.append("")
-    lines.append("## Summary")
-    lines.append("")
-    lines.append("| Issue | State | Commits | Tests |")
-    lines.append("| --- | --- | --- | --- |")
-    for child in children:
-        lines.append(
-            f"| #{child.number} | {child.state} | {len(child.commits)} | {len(child.targeted_tests)} |"
-        )
-    lines.append("")
-
-    for child in children:
-        lines.append(f"## #{child.number} — {child.title}")
-        lines.append("")
-        lines.append(f"State: {child.state}")
-        lines.append(f"URL: {child.url}")
-        lines.append("")
-        if child.checkout_notes:
-            lines.append("### Branch / checkout")
-            for note in child.checkout_notes:
-                lines.append(f"- {note}")
-            lines.append("")
-        if child.commits:
-            lines.append("### Commits")
-            for commit in child.commits:
-                if commit.sha:
-                    lines.append(f"- `{commit.sha}` — {commit.summary}")
-                else:
-                    lines.append(f"- {commit.summary}")
-            lines.append("")
-        if child.targeted_tests:
-            lines.append("### Targeted tests")
-            for test_path in child.targeted_tests:
-                lines.append(f"- `{test_path}`")
-            lines.append("")
-        if child.files_touched:
-            lines.append("### Files touched")
-            for file_path in child.files_touched:
-                lines.append(f"- `{file_path}`")
-            lines.append("")
-        if child.tasks:
-            lines.append("### Tasks")
-            for task in child.tasks:
-                lines.append(f"- [ ] {task}")
-            lines.append("")
-        if child.acceptance_criteria:
-            lines.append("### Acceptance criteria")
-            for item in child.acceptance_criteria:
-                lines.append(f"- [ ] {item}")
-            lines.append("")
-
-    return "\n".join(lines).rstrip() + "\n"
-
-
-def _resolve_token(explicit_token: str | None = None) -> str:
-    if explicit_token:
-        return explicit_token.strip()
-    env_token = os.getenv("GITEA_TOKEN")
-    if env_token:
-        return env_token.strip()
-    if DEFAULT_TOKEN_PATH.exists():
-        return DEFAULT_TOKEN_PATH.read_text().strip()
-    raise FileNotFoundError(f"No Gitea token found. Set GITEA_TOKEN or create {DEFAULT_TOKEN_PATH}")
-
-
-def fetch_issue(base_url: str, owner: str, repo: str, number: int, token: str) -> dict:
-    url = f"{base_url.rstrip('/')}/api/v1/repos/{owner}/{repo}/issues/{number}"
-    request = urllib.request.Request(url, headers={"Authorization": f"token {token}"})
-    with urllib.request.urlopen(request, timeout=30) as response:
-        return json.loads(response.read().decode())
-
-
-def collect_child_issues(base_url: str, owner: str, repo: str, epic_issue: dict, token: str, children_spec: str | None = None) -> list[dict]:
-    numbers = parse_issue_number_spec(children_spec) if children_spec else discover_child_issue_numbers(epic_issue.get("body") or "")
-    return [fetch_issue(base_url, owner, repo, number, token) for number in numbers]
-
-
-def main(argv: list[str] | None = None) -> int:
-    parser = argparse.ArgumentParser(description="Build a markdown morning review packet from a Gitea epic")
-    parser.add_argument("--base-url", default=DEFAULT_BASE_URL)
-    parser.add_argument("--owner", default=DEFAULT_OWNER)
-    parser.add_argument("--repo", default=DEFAULT_REPO)
-    parser.add_argument("--epic-number", type=int, required=True)
-    parser.add_argument("--children", help="Explicit issue list/ranges, e.g. 950-962")
-    parser.add_argument("--token", help="Gitea token (defaults to GITEA_TOKEN or ~/.config/gitea/token)")
-    parser.add_argument("--output", help="Write markdown packet to this path instead of stdout")
-    args = parser.parse_args(argv)
-
-    token = _resolve_token(args.token)
-    epic_issue = fetch_issue(args.base_url, args.owner, args.repo, args.epic_number, token)
-    child_issue_dicts = collect_child_issues(args.base_url, args.owner, args.repo, epic_issue, token, args.children)
-    packet = build_packet_markdown(epic_issue, [parse_child_issue(issue) for issue in child_issue_dicts])
-
-    if args.output:
-        output_path = Path(args.output)
-        output_path.parent.mkdir(parents=True, exist_ok=True)
-        output_path.write_text(packet)
-    else:
-        print(packet, end="")
-    return 0
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

tests/gateway/test_usage_command.py

@@ -175,3 +175,79 @@ 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

tests/test_account_usage.py

@@ -0,0 +1,203 @@
+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

tests/test_morning_review_packet.py

@@ -1,162 +0,0 @@
-from pathlib import Path
-import sys
-
-SCRIPT_DIR = Path(__file__).resolve().parents[1] / "scripts"
-sys.path.insert(0, str(SCRIPT_DIR))
-
-import morning_review_packet as mrp
-
-
-EPIC_BODY = """Source: git log on upstream/main since 2026-04-21 00:00 EDT.
-
-## Success criteria
-- [ ] Every issue has a clear PASS / FAIL outcome.
-
-## Sub-issues
-- [ ] #950 [QA] Verify AI Gateway provider UX + attribution headers
-- [ ] #951 [QA] Verify transport abstraction + AnthropicTransport wiring
-- [x] #962 [QA] Verify hardcoded-home path guard on burn/921 branch
-"""
-
-
-CHILD_BODY_PLURAL = """## Parent
-#949
-
-## Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-## Commits landed today
-- `b11753879` attribution default_headers for ai-gateway provider
-- `700437440` curated picker with live pricing
-
-## Targeted tests
-- `tests/hermes_cli/test_ai_gateway_models.py`
-- `tests/run_agent/test_provider_attribution_headers.py`
-
-## Tasks
-- [ ] Verify the picker ordering.
-- [ ] Verify attribution headers.
-
-## Acceptance Criteria
-- [ ] Picker shows AI Gateway prominently.
-- [ ] Headers appear on OpenRouter calls.
-"""
-
-
-CHILD_BODY_SINGULAR = """## Parent
-#949
-
-## Branch / checkout
-- Validate on `upstream/main` or an equivalent synced checkout.
-
-## Commit landed today
-- `fc21c1420` add buttons to update Hermes and restart gateway
-
-## Files touched
-- `web/src/pages/StatusPage.tsx`
-- `web/src/lib/api.ts`
-- `web/src/i18n/en.ts`
-
-## Tasks
-- [ ] Open the Web UI status page and verify both buttons are present.
-- [ ] Click Restart Gateway in a safe environment.
-"""
-
-
-def test_discover_child_issue_numbers_from_epic_body():
-    assert mrp.discover_child_issue_numbers(EPIC_BODY) == [950, 951, 962]
-
-
-def test_parse_issue_number_spec_supports_ranges_and_lists():
-    assert mrp.parse_issue_number_spec("950-952,955,962") == [950, 951, 952, 955, 962]
-
-
-def test_parse_child_issue_extracts_structured_sections():
-    issue = {
-        "number": 950,
-        "title": "[QA] Verify AI Gateway provider UX + attribution headers",
-        "state": "open",
-        "html_url": "https://forge.example/950",
-        "comments": 0,
-        "body": CHILD_BODY_PLURAL,
-    }
-
-    parsed = mrp.parse_child_issue(issue)
-
-    assert parsed.number == 950
-    assert parsed.parent_issue == 949
-    assert parsed.checkout_notes == ["Validate on `upstream/main` or an equivalent synced checkout."]
-    assert [c.sha for c in parsed.commits] == ["b11753879", "700437440"]
-    assert parsed.targeted_tests == [
-        "tests/hermes_cli/test_ai_gateway_models.py",
-        "tests/run_agent/test_provider_attribution_headers.py",
-    ]
-    assert parsed.tasks == [
-        "Verify the picker ordering.",
-        "Verify attribution headers.",
-    ]
-    assert parsed.acceptance_criteria == [
-        "Picker shows AI Gateway prominently.",
-        "Headers appear on OpenRouter calls.",
-    ]
-
-
-def test_parse_child_issue_handles_singular_commit_heading_and_files_touched():
-    issue = {
-        "number": 961,
-        "title": "[QA] Verify web dashboard update/restart action buttons",
-        "state": "closed",
-        "html_url": "https://forge.example/961",
-        "comments": 16,
-        "body": CHILD_BODY_SINGULAR,
-    }
-
-    parsed = mrp.parse_child_issue(issue)
-
-    assert [c.sha for c in parsed.commits] == ["fc21c1420"]
-    assert parsed.files_touched == [
-        "web/src/pages/StatusPage.tsx",
-        "web/src/lib/api.ts",
-        "web/src/i18n/en.ts",
-    ]
-    assert parsed.tasks == [
-        "Open the Web UI status page and verify both buttons are present.",
-        "Click Restart Gateway in a safe environment.",
-    ]
-
-
-def test_build_packet_markdown_renders_summary_and_details():
-    epic_issue = {
-        "number": 949,
-        "title": "EPIC: Morning review packet — Hermes harness features landed 2026-04-21",
-        "state": "open",
-        "html_url": "https://forge.example/949",
-        "body": EPIC_BODY,
-    }
-    child_a = mrp.parse_child_issue({
-        "number": 950,
-        "title": "[QA] Verify AI Gateway provider UX + attribution headers",
-        "state": "open",
-        "html_url": "https://forge.example/950",
-        "comments": 0,
-        "body": CHILD_BODY_PLURAL,
-    })
-    child_b = mrp.parse_child_issue({
-        "number": 961,
-        "title": "[QA] Verify web dashboard update/restart action buttons",
-        "state": "closed",
-        "html_url": "https://forge.example/961",
-        "comments": 16,
-        "body": CHILD_BODY_SINGULAR,
-    })
-
-    markdown = mrp.build_packet_markdown(epic_issue, [child_a, child_b])
-
-    assert "# Morning Review Packet" in markdown
-    assert "EPIC: Morning review packet — Hermes harness features landed 2026-04-21" in markdown
-    assert "| #950 | open | 2 | 2 |" in markdown
-    assert "| #961 | closed | 1 | 0 |" in markdown
-    assert "## #950 — [QA] Verify AI Gateway provider UX + attribution headers" in markdown
-    assert "## #961 — [QA] Verify web dashboard update/restart action buttons" in markdown
-    assert "`b11753879` — attribution default_headers for ai-gateway provider" in markdown
-    assert "`web/src/pages/StatusPage.tsx`" in markdown