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'):

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:

plugins/memory/holographic/__init__.py

@@ -26,7 +26,6 @@ from agent.memory_provider import MemoryProvider
 from tools.registry import tool_error
 from .store import MemoryStore
 from .retrieval import FactRetriever
-from .observations import ObservationSynthesizer
 
 logger = logging.getLogger(__name__)
 
@@ -38,29 +37,28 @@ logger = logging.getLogger(__name__)
 FACT_STORE_SCHEMA = {
     "name": "fact_store",
     "description": (
-        "Deep structured memory with algebraic reasoning and grounded observation synthesis. "
+        "Deep structured memory with algebraic reasoning. "
         "Use alongside the memory tool — memory for always-on context, "
-        "fact_store for deep recall, compositional queries, and higher-order observations.\n\n"
+        "fact_store for deep recall and compositional queries.\n\n"
         "ACTIONS (simple → powerful):\n"
         "• add — Store a fact the user would expect you to remember.\n"
         "• search — Keyword lookup ('editor config', 'deploy process').\n"
         "• probe — Entity recall: ALL facts about a person/thing.\n"
         "• related — What connects to an entity? Structural adjacency.\n"
         "• reason — Compositional: facts connected to MULTIPLE entities simultaneously.\n"
-        "• observe — Synthesized higher-order observations backed by supporting facts.\n"
         "• contradict — Memory hygiene: find facts making conflicting claims.\n"
         "• update/remove/list — CRUD operations.\n\n"
-        "IMPORTANT: Before answering questions about the user, ALWAYS probe/reason/observe first."
+        "IMPORTANT: Before answering questions about the user, ALWAYS probe or reason first."
     ),
     "parameters": {
         "type": "object",
         "properties": {
             "action": {
                 "type": "string",
-                "enum": ["add", "search", "probe", "related", "reason", "observe", "contradict", "update", "remove", "list"],
+                "enum": ["add", "search", "probe", "related", "reason", "contradict", "update", "remove", "list"],
             },
             "content": {"type": "string", "description": "Fact content (required for 'add')."},
-            "query": {"type": "string", "description": "Search query (required for 'search'/'observe')."},
+            "query": {"type": "string", "description": "Search query (required for 'search')."},
             "entity": {"type": "string", "description": "Entity name for 'probe'/'related'."},
             "entities": {"type": "array", "items": {"type": "string"}, "description": "Entity names for 'reason'."},
             "fact_id": {"type": "integer", "description": "Fact ID for 'update'/'remove'."},
@@ -68,12 +66,6 @@ FACT_STORE_SCHEMA = {
             "tags": {"type": "string", "description": "Comma-separated tags."},
             "trust_delta": {"type": "number", "description": "Trust adjustment for 'update'."},
             "min_trust": {"type": "number", "description": "Minimum trust filter (default: 0.3)."},
-            "min_confidence": {"type": "number", "description": "Minimum observation confidence (default: 0.6)."},
-            "observation_type": {
-                "type": "string",
-                "enum": ["recurring_preference", "stable_direction", "behavioral_pattern"],
-                "description": "Optional observation type filter for 'observe'.",
-            },
             "limit": {"type": "integer", "description": "Max results (default: 10)."},
         },
         "required": ["action"],
@@ -126,9 +118,7 @@ class HolographicMemoryProvider(MemoryProvider):
         self._config = config or _load_plugin_config()
         self._store = None
         self._retriever = None
-        self._observation_synth = None
         self._min_trust = float(self._config.get("min_trust_threshold", 0.3))
-        self._observation_min_confidence = float(self._config.get("observation_min_confidence", 0.6))
 
     @property
     def name(self) -> str:
@@ -187,7 +177,6 @@ class HolographicMemoryProvider(MemoryProvider):
             hrr_weight=hrr_weight,
             hrr_dim=hrr_dim,
         )
-        self._observation_synth = ObservationSynthesizer(self._store)
         self._session_id = session_id
 
     def system_prompt_block(self) -> str:
@@ -204,76 +193,30 @@ class HolographicMemoryProvider(MemoryProvider):
                 "# Holographic Memory\n"
                 "Active. Empty fact store — proactively add facts the user would expect you to remember.\n"
                 "Use fact_store(action='add') to store durable structured facts about people, projects, preferences, decisions.\n"
-                "Use fact_store(action='observe') to synthesize higher-order observations with evidence.\n"
                 "Use fact_feedback to rate facts after using them (trains trust scores)."
             )
         return (
             f"# Holographic Memory\n"
             f"Active. {total} facts stored with entity resolution and trust scoring.\n"
-            f"Use fact_store to search, probe entities, reason across entities, or synthesize observations.\n"
+            f"Use fact_store to search, probe entities, reason across entities, or add facts.\n"
             f"Use fact_feedback to rate facts after using them (trains trust scores)."
         )
 
     def prefetch(self, query: str, *, session_id: str = "") -> str:
-        if not query:
+        if not self._retriever or not query:
             return ""
-
-        parts = []
-        raw_results = []
         try:
-            if self._retriever:
-                raw_results = self._retriever.search(query, min_trust=self._min_trust, limit=5)
-        except Exception as e:
-            logger.debug("Holographic prefetch fact search failed: %s", e)
-            raw_results = []
-
-        observations = []
-        try:
-            if self._observation_synth:
-                observations = self._observation_synth.observe(
-                    query,
-                    min_confidence=self._observation_min_confidence,
-                    limit=3,
-                    refresh=True,
-                )
-        except Exception as e:
-            logger.debug("Holographic prefetch observation search failed: %s", e)
-            observations = []
-
-        if not raw_results and observations:
-            seen_fact_ids = set()
-            evidence_backfill = []
-            for observation in observations:
-                for evidence in observation.get("evidence", []):
-                    fact_id = evidence.get("fact_id")
-                    if fact_id in seen_fact_ids:
-                        continue
-                    seen_fact_ids.add(fact_id)
-                    evidence_backfill.append(evidence)
-            raw_results = evidence_backfill[:5]
-
-        if raw_results:
+            results = self._retriever.search(query, min_trust=self._min_trust, limit=5)
+            if not results:
+                return ""
             lines = []
-            for r in raw_results:
+            for r in results:
                 trust = r.get("trust_score", r.get("trust", 0))
                 lines.append(f"- [{trust:.1f}] {r.get('content', '')}")
-            parts.append("## Holographic Memory\n" + "\n".join(lines))
-
-        if observations:
-            lines = []
-            for observation in observations:
-                evidence_ids = ", ".join(
-                    f"#{item['fact_id']}" for item in observation.get("evidence", [])[:3]
-                ) or "none"
-                lines.append(
-                    f"- [{observation.get('confidence', 0.0):.2f}] "
-                    f"{observation.get('observation_type', 'observation')}: "
-                    f"{observation.get('summary', '')} "
-                    f"(evidence: {evidence_ids})"
-                )
-            parts.append("## Holographic Observations\n" + "\n".join(lines))
-
-        return "\n\n".join(parts)
+            return "## Holographic Memory\n" + "\n".join(lines)
+        except Exception as e:
+            logger.debug("Holographic prefetch failed: %s", e)
+            return ""
 
     def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
         # Holographic memory stores explicit facts via tools, not auto-sync.
@@ -309,7 +252,6 @@ class HolographicMemoryProvider(MemoryProvider):
     def shutdown(self) -> None:
         self._store = None
         self._retriever = None
-        self._observation_synth = None
 
     # -- Tool handlers -------------------------------------------------------
 
@@ -363,19 +305,6 @@ class HolographicMemoryProvider(MemoryProvider):
                 )
                 return json.dumps({"results": results, "count": len(results)})
 
-            elif action == "observe":
-                synthesizer = self._observation_synth
-                if not synthesizer:
-                    return tool_error("Observation synthesizer is not initialized")
-                observations = synthesizer.observe(
-                    args.get("query", ""),
-                    observation_type=args.get("observation_type"),
-                    min_confidence=float(args.get("min_confidence", self._observation_min_confidence)),
-                    limit=int(args.get("limit", 10)),
-                    refresh=True,
-                )
-                return json.dumps({"observations": observations, "count": len(observations)})
-
             elif action == "contradict":
                 results = retriever.contradict(
                     category=args.get("category"),

plugins/memory/holographic/observations.py

@@ -1,249 +0,0 @@
-"""Higher-order observation synthesis for holographic memory.
-
-Builds grounded observations from accumulated facts and keeps them in a
-separate retrieval layer with explicit evidence links back to supporting facts.
-"""
-
-from __future__ import annotations
-
-import re
-from typing import Any
-
-from .store import MemoryStore
-
-_TOKEN_RE = re.compile(r"[a-z0-9_]+")
-_HIGHER_ORDER_CUES = {
-    "prefer",
-    "preference",
-    "preferences",
-    "style",
-    "pattern",
-    "patterns",
-    "behavior",
-    "behaviour",
-    "habit",
-    "habits",
-    "workflow",
-    "direction",
-    "trajectory",
-    "strategy",
-    "tend",
-    "usually",
-}
-
-_OBSERVATION_PATTERNS = [
-    {
-        "observation_type": "recurring_preference",
-        "subject": "communication_style",
-        "categories": {"user_pref", "general"},
-        "labels": {
-            "concise": ["concise", "terse", "brief", "short", "no fluff"],
-            "result_first": ["result-only", "result only", "outcome only", "quick", "quickly"],
-            "silent_ops": ["silent", "no status", "no repetitive status", "no questions"],
-        },
-        "summary_prefix": "Recurring preference",
-    },
-    {
-        "observation_type": "stable_direction",
-        "subject": "project_direction",
-        "categories": {"project", "general", "tool"},
-        "labels": {
-            "local_first": ["local-first", "local first", "local-only", "local only", "ollama", "own hardware"],
-            "gitea_first": ["gitea-first", "gitea first", "forge", "pull request", "pr flow", "issue flow"],
-            "ansible": ["ansible", "playbook", "role", "deploy via ansible"],
-        },
-        "summary_prefix": "Stable direction",
-    },
-    {
-        "observation_type": "behavioral_pattern",
-        "subject": "operator_workflow",
-        "categories": {"general", "project", "tool", "user_pref"},
-        "labels": {
-            "commit_early": ["commit early", "commits early", "commit after", "wip commit"],
-            "pr_first": ["open pr", "push a pr", "pull request", "pr immediately", "create pr"],
-            "dedup_guard": ["no dupes", "no duplicates", "avoid duplicate", "existing pr"],
-        },
-        "summary_prefix": "Behavioral pattern",
-    },
-]
-
-_TYPE_QUERY_HINTS = {
-    "recurring_preference": {"prefer", "preference", "style", "communication", "likes", "wants"},
-    "stable_direction": {"direction", "trajectory", "strategy", "project", "roadmap", "moving"},
-    "behavioral_pattern": {"pattern", "behavior", "workflow", "habit", "operator", "agent", "usually"},
-}
-
-
-class ObservationSynthesizer:
-    """Synthesizes grounded observations from facts and retrieves them by query."""
-
-    def __init__(self, store: MemoryStore):
-        self.store = store
-
-    def synthesize(
-        self,
-        *,
-        persist: bool = True,
-        min_confidence: float = 0.6,
-        limit: int = 10,
-    ) -> list[dict[str, Any]]:
-        facts = self.store.list_facts(min_trust=0.0, limit=1000)
-        observations: list[dict[str, Any]] = []
-
-        for pattern in _OBSERVATION_PATTERNS:
-            candidate = self._build_candidate(pattern, facts, min_confidence=min_confidence)
-            if not candidate:
-                continue
-
-            if persist:
-                candidate["observation_id"] = self.store.upsert_observation(
-                    candidate["observation_type"],
-                    candidate["subject"],
-                    candidate["summary"],
-                    candidate["confidence"],
-                    candidate["evidence_fact_ids"],
-                    metadata=candidate["metadata"],
-                )
-
-            candidate["evidence"] = self._expand_evidence(candidate["evidence_fact_ids"])
-            candidate["evidence_count"] = len(candidate["evidence"])
-            candidate.pop("evidence_fact_ids", None)
-            observations.append(candidate)
-
-        observations.sort(
-            key=lambda item: (item["confidence"], item.get("evidence_count", 0)),
-            reverse=True,
-        )
-        return observations[:limit]
-
-    def observe(
-        self,
-        query: str = "",
-        *,
-        observation_type: str | None = None,
-        min_confidence: float = 0.6,
-        limit: int = 10,
-        refresh: bool = True,
-    ) -> list[dict[str, Any]]:
-        if refresh:
-            self.synthesize(persist=True, min_confidence=min_confidence, limit=limit)
-
-        observations = self.store.list_observations(
-            observation_type=observation_type,
-            min_confidence=min_confidence,
-            limit=max(limit * 4, 20),
-        )
-        if not observations:
-            return []
-
-        if not query:
-            return observations[:limit]
-
-        query_tokens = self._tokenize(query)
-        is_higher_order = bool(query_tokens & _HIGHER_ORDER_CUES)
-        ranked: list[dict[str, Any]] = []
-
-        for item in observations:
-            searchable = " ".join(
-                [
-                    item.get("summary", ""),
-                    item.get("subject", ""),
-                    item.get("observation_type", ""),
-                    " ".join(item.get("metadata", {}).get("labels", [])),
-                ]
-            )
-            overlap = self._overlap_score(query_tokens, self._tokenize(searchable))
-            type_bonus = self._type_bonus(query_tokens, item.get("observation_type", ""))
-            if overlap <= 0 and type_bonus <= 0 and not is_higher_order:
-                continue
-            ranked_item = dict(item)
-            ranked_item["score"] = round(item.get("confidence", 0.0) + overlap + type_bonus, 3)
-            ranked.append(ranked_item)
-
-        if not ranked and is_higher_order:
-            ranked = [
-                {**item, "score": round(float(item.get("confidence", 0.0)), 3)}
-                for item in observations
-            ]
-
-        ranked.sort(
-            key=lambda item: (item.get("score", 0.0), item.get("confidence", 0.0), item.get("evidence_count", 0)),
-            reverse=True,
-        )
-        return ranked[:limit]
-
-    def _build_candidate(
-        self,
-        pattern: dict[str, Any],
-        facts: list[dict[str, Any]],
-        *,
-        min_confidence: float,
-    ) -> dict[str, Any] | None:
-        matched_fact_ids: set[int] = set()
-        matched_labels: dict[str, set[int]] = {label: set() for label in pattern["labels"]}
-
-        for fact in facts:
-            if fact.get("category") not in pattern["categories"]:
-                continue
-            haystack = f"{fact.get('content', '')} {fact.get('tags', '')}".lower()
-            local_match = False
-            for label, keywords in pattern["labels"].items():
-                if any(keyword in haystack for keyword in keywords):
-                    matched_labels[label].add(int(fact["fact_id"]))
-                    local_match = True
-            if local_match:
-                matched_fact_ids.add(int(fact["fact_id"]))
-
-        if len(matched_fact_ids) < 2:
-            return None
-
-        active_labels = sorted(label for label, ids in matched_labels.items() if ids)
-        confidence = min(0.95, 0.35 + 0.12 * len(matched_fact_ids) + 0.08 * len(active_labels))
-        confidence = round(confidence, 3)
-        if confidence < min_confidence:
-            return None
-
-        label_summary = ", ".join(label.replace("_", "-") for label in active_labels)
-        subject_text = pattern["subject"].replace("_", " ")
-        summary = (
-            f"{pattern['summary_prefix']}: {subject_text} trends toward {label_summary} "
-            f"based on {len(matched_fact_ids)} supporting facts."
-        )
-        return {
-            "observation_type": pattern["observation_type"],
-            "subject": pattern["subject"],
-            "summary": summary,
-            "confidence": confidence,
-            "metadata": {
-                "labels": active_labels,
-                "evidence_count": len(matched_fact_ids),
-            },
-            "evidence_fact_ids": sorted(matched_fact_ids),
-        }
-
-    def _expand_evidence(self, fact_ids: list[int]) -> list[dict[str, Any]]:
-        facts_by_id = {
-            fact["fact_id"]: fact
-            for fact in self.store.list_facts(min_trust=0.0, limit=1000)
-        }
-        return [facts_by_id[fact_id] for fact_id in fact_ids if fact_id in facts_by_id]
-
-    @staticmethod
-    def _tokenize(text: str) -> set[str]:
-        return set(_TOKEN_RE.findall(text.lower()))
-
-    @staticmethod
-    def _overlap_score(query_tokens: set[str], text_tokens: set[str]) -> float:
-        if not query_tokens or not text_tokens:
-            return 0.0
-        overlap = query_tokens & text_tokens
-        if not overlap:
-            return 0.0
-        return round(len(overlap) / max(len(query_tokens), 1), 3)
-
-    @staticmethod
-    def _type_bonus(query_tokens: set[str], observation_type: str) -> float:
-        hints = _TYPE_QUERY_HINTS.get(observation_type, set())
-        if not hints:
-            return 0.0
-        return 0.25 if query_tokens & hints else 0.0

plugins/memory/holographic/store.py

@@ -3,7 +3,6 @@ SQLite-backed fact store with entity resolution and trust scoring.
 Single-user Hermes memory store plugin.
 """
 
-import json
 import re
 import sqlite3
 import threading
@@ -74,28 +73,6 @@ CREATE TABLE IF NOT EXISTS memory_banks (
     fact_count INTEGER DEFAULT 0,
     updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
 );
-
-CREATE TABLE IF NOT EXISTS observations (
-    observation_id   INTEGER PRIMARY KEY AUTOINCREMENT,
-    observation_type TEXT NOT NULL,
-    subject          TEXT NOT NULL,
-    summary          TEXT NOT NULL,
-    confidence       REAL DEFAULT 0.0,
-    metadata_json    TEXT DEFAULT '{}',
-    created_at       TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
-    updated_at       TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
-    UNIQUE(observation_type, subject)
-);
-
-CREATE TABLE IF NOT EXISTS observation_evidence (
-    observation_id INTEGER REFERENCES observations(observation_id) ON DELETE CASCADE,
-    fact_id        INTEGER REFERENCES facts(fact_id) ON DELETE CASCADE,
-    evidence_weight REAL DEFAULT 1.0,
-    PRIMARY KEY (observation_id, fact_id)
-);
-
-CREATE INDEX IF NOT EXISTS idx_observations_type ON observations(observation_type);
-CREATE INDEX IF NOT EXISTS idx_observations_confidence ON observations(confidence DESC);
 """
 
 # Trust adjustment constants
@@ -151,7 +128,6 @@ class MemoryStore:
     def _init_db(self) -> None:
         """Create tables, indexes, and triggers if they do not exist. Enable WAL mode."""
         self._conn.execute("PRAGMA journal_mode=WAL")
-        self._conn.execute("PRAGMA foreign_keys=ON")
         self._conn.executescript(_SCHEMA)
         # Migrate: add hrr_vector column if missing (safe for existing databases)
         columns = {row[1] for row in self._conn.execute("PRAGMA table_info(facts)").fetchall()}
@@ -370,115 +346,6 @@ class MemoryStore:
             rows = self._conn.execute(sql, params).fetchall()
             return [self._row_to_dict(r) for r in rows]
 
-    def upsert_observation(
-        self,
-        observation_type: str,
-        subject: str,
-        summary: str,
-        confidence: float,
-        evidence_fact_ids: list[int],
-        metadata: dict | None = None,
-    ) -> int:
-        """Create or update a synthesized observation and its evidence links."""
-        with self._lock:
-            metadata_json = json.dumps(metadata or {}, sort_keys=True)
-            self._conn.execute(
-                """
-                INSERT INTO observations (
-                    observation_type, subject, summary, confidence, metadata_json
-                )
-                VALUES (?, ?, ?, ?, ?)
-                ON CONFLICT(observation_type, subject) DO UPDATE SET
-                    summary = excluded.summary,
-                    confidence = excluded.confidence,
-                    metadata_json = excluded.metadata_json,
-                    updated_at = CURRENT_TIMESTAMP
-                """,
-                (observation_type, subject, summary, confidence, metadata_json),
-            )
-            row = self._conn.execute(
-                """
-                SELECT observation_id
-                FROM observations
-                WHERE observation_type = ? AND subject = ?
-                """,
-                (observation_type, subject),
-            ).fetchone()
-            observation_id = int(row["observation_id"])
-
-            self._conn.execute(
-                "DELETE FROM observation_evidence WHERE observation_id = ?",
-                (observation_id,),
-            )
-            unique_fact_ids = sorted({int(fid) for fid in evidence_fact_ids})
-            if unique_fact_ids:
-                self._conn.executemany(
-                    """
-                    INSERT OR IGNORE INTO observation_evidence (observation_id, fact_id)
-                    VALUES (?, ?)
-                    """,
-                    [(observation_id, fact_id) for fact_id in unique_fact_ids],
-                )
-            self._conn.commit()
-            return observation_id
-
-    def list_observations(
-        self,
-        observation_type: str | None = None,
-        min_confidence: float = 0.0,
-        limit: int = 50,
-    ) -> list[dict]:
-        """List synthesized observations with expanded supporting evidence."""
-        with self._lock:
-            params: list = [min_confidence]
-            observation_clause = ""
-            if observation_type is not None:
-                observation_clause = "AND observation_type = ?"
-                params.append(observation_type)
-            params.append(limit)
-            rows = self._conn.execute(
-                f"""
-                SELECT observation_id, observation_type, subject, summary, confidence,
-                       metadata_json, created_at, updated_at,
-                       (
-                           SELECT COUNT(*)
-                           FROM observation_evidence oe
-                           WHERE oe.observation_id = observations.observation_id
-                       ) AS evidence_count
-                FROM observations
-                WHERE confidence >= ?
-                  {observation_clause}
-                ORDER BY confidence DESC, updated_at DESC
-                LIMIT ?
-                """,
-                params,
-            ).fetchall()
-
-            results = []
-            for row in rows:
-                item = dict(row)
-                try:
-                    item["metadata"] = json.loads(item.pop("metadata_json") or "{}")
-                except json.JSONDecodeError:
-                    item["metadata"] = {}
-                item["evidence"] = self._get_observation_evidence(int(item["observation_id"]))
-                results.append(item)
-            return results
-
-    def _get_observation_evidence(self, observation_id: int) -> list[dict]:
-        rows = self._conn.execute(
-            """
-            SELECT f.fact_id, f.content, f.category, f.tags, f.trust_score,
-                   f.retrieval_count, f.helpful_count, f.created_at, f.updated_at
-            FROM observation_evidence oe
-            JOIN facts f ON f.fact_id = oe.fact_id
-            WHERE oe.observation_id = ?
-            ORDER BY f.trust_score DESC, f.updated_at DESC
-            """,
-            (observation_id,),
-        ).fetchall()
-        return [self._row_to_dict(row) for row in rows]
-
     def record_feedback(self, fact_id: int, helpful: bool) -> dict:
         """Record user feedback and adjust trust asymmetrically.
 

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/plugins/memory/test_holographic_observations.py

@@ -1,96 +0,0 @@
-import json
-
-import pytest
-
-from plugins.memory.holographic import HolographicMemoryProvider
-from plugins.memory.holographic.store import MemoryStore
-
-
-@pytest.fixture()
-def store(tmp_path):
-    db_path = tmp_path / "memory.db"
-    s = MemoryStore(db_path=str(db_path), default_trust=0.5)
-    yield s
-    s.close()
-
-
-@pytest.fixture()
-def provider(tmp_path):
-    p = HolographicMemoryProvider(
-        config={
-            "db_path": str(tmp_path / "memory.db"),
-            "default_trust": 0.5,
-        }
-    )
-    p.initialize(session_id="test-session")
-    yield p
-    if p._store:
-        p._store.close()
-
-
-class TestObservationSynthesis:
-    def test_observe_action_persists_observation_with_evidence_links(self, provider):
-        fact_ids = [
-            provider._store.add_fact('User prefers concise status updates', category='user_pref'),
-            provider._store.add_fact('User wants result-only replies with no fluff', category='user_pref'),
-        ]
-
-        result = json.loads(
-            provider.handle_tool_call(
-                'fact_store',
-                {
-                    'action': 'observe',
-                    'query': 'What communication style does the user prefer?',
-                    'limit': 5,
-                },
-            )
-        )
-
-        assert result['count'] == 1
-        observation = result['observations'][0]
-        assert observation['observation_type'] == 'recurring_preference'
-        assert observation['confidence'] >= 0.6
-        assert sorted(item['fact_id'] for item in observation['evidence']) == sorted(fact_ids)
-
-        stored = provider._store.list_observations(limit=10)
-        assert len(stored) == 1
-        assert stored[0]['observation_type'] == 'recurring_preference'
-        assert stored[0]['evidence_count'] == 2
-        assert len(provider._store.list_facts(limit=10)) == 2
-
-    def test_observe_action_synthesizes_three_observation_types(self, provider):
-        provider._store.add_fact('User prefers concise updates', category='user_pref')
-        provider._store.add_fact('User wants result-only communication', category='user_pref')
-        provider._store.add_fact('Project is moving to a local-first deployment model', category='project')
-        provider._store.add_fact('Project direction stays Gitea-first for issue and PR flow', category='project')
-        provider._store.add_fact('Operator always commits early before moving on', category='general')
-        provider._store.add_fact('Operator pushes a PR immediately after each meaningful fix', category='general')
-
-        result = json.loads(provider.handle_tool_call('fact_store', {'action': 'observe', 'limit': 10}))
-        types = {item['observation_type'] for item in result['observations']}
-
-        assert {'recurring_preference', 'stable_direction', 'behavioral_pattern'} <= types
-
-    def test_single_fact_does_not_create_overconfident_observation(self, provider):
-        provider._store.add_fact('User prefers concise updates', category='user_pref')
-
-        result = json.loads(
-            provider.handle_tool_call(
-                'fact_store',
-                {'action': 'observe', 'query': 'What does the user prefer?', 'limit': 5},
-            )
-        )
-
-        assert result['count'] == 0
-        assert provider._store.list_observations(limit=10) == []
-
-    def test_prefetch_surfaces_observations_as_separate_layer(self, provider):
-        provider._store.add_fact('User prefers concise updates', category='user_pref')
-        provider._store.add_fact('User wants result-only communication', category='user_pref')
-
-        prefetch = provider.prefetch('What communication style does the user prefer?')
-
-        assert '## Holographic Observations' in prefetch
-        assert '## Holographic Memory' in prefetch
-        assert 'recurring_preference' in prefetch
-        assert 'evidence' in prefetch.lower()

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