File size: 8,458 Bytes
be4122e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 | """Rate limit tracking for inference API responses.
Captures x-ratelimit-* headers from provider responses and provides
formatted display for the /usage slash command. Currently supports
the Nous Portal header format (also used by OpenRouter and OpenAI-compatible
APIs that follow the same convention).
Header schema (12 headers total):
x-ratelimit-limit-requests RPM cap
x-ratelimit-limit-requests-1h RPH cap
x-ratelimit-limit-tokens TPM cap
x-ratelimit-limit-tokens-1h TPH cap
x-ratelimit-remaining-requests requests left in minute window
x-ratelimit-remaining-requests-1h requests left in hour window
x-ratelimit-remaining-tokens tokens left in minute window
x-ratelimit-remaining-tokens-1h tokens left in hour window
x-ratelimit-reset-requests seconds until minute request window resets
x-ratelimit-reset-requests-1h seconds until hour request window resets
x-ratelimit-reset-tokens seconds until minute token window resets
x-ratelimit-reset-tokens-1h seconds until hour token window resets
"""
from __future__ import annotations
import time
from dataclasses import dataclass, field
from typing import Any, Mapping, Optional
@dataclass
class RateLimitBucket:
"""One rate-limit window (e.g. requests per minute)."""
limit: int = 0
remaining: int = 0
reset_seconds: float = 0.0
captured_at: float = 0.0 # time.time() when this was captured
@property
def used(self) -> int:
return max(0, self.limit - self.remaining)
@property
def usage_pct(self) -> float:
if self.limit <= 0:
return 0.0
return (self.used / self.limit) * 100.0
@property
def remaining_seconds_now(self) -> float:
"""Estimated seconds remaining until reset, adjusted for elapsed time."""
elapsed = time.time() - self.captured_at
return max(0.0, self.reset_seconds - elapsed)
@dataclass
class RateLimitState:
"""Full rate-limit state parsed from response headers."""
requests_min: RateLimitBucket = field(default_factory=RateLimitBucket)
requests_hour: RateLimitBucket = field(default_factory=RateLimitBucket)
tokens_min: RateLimitBucket = field(default_factory=RateLimitBucket)
tokens_hour: RateLimitBucket = field(default_factory=RateLimitBucket)
captured_at: float = 0.0 # when the headers were captured
provider: str = ""
@property
def has_data(self) -> bool:
return self.captured_at > 0
@property
def age_seconds(self) -> float:
if not self.has_data:
return float("inf")
return time.time() - self.captured_at
def _safe_int(value: Any, default: int = 0) -> int:
try:
return int(float(value))
except (TypeError, ValueError):
return default
def _safe_float(value: Any, default: float = 0.0) -> float:
try:
return float(value)
except (TypeError, ValueError):
return default
def parse_rate_limit_headers(
headers: Mapping[str, str],
provider: str = "",
) -> Optional[RateLimitState]:
"""Parse x-ratelimit-* headers into a RateLimitState.
Returns None if no rate limit headers are present.
"""
# Normalize to lowercase so lookups work regardless of how the server
# capitalises headers (HTTP header names are case-insensitive per RFC 7230).
lowered = {k.lower(): v for k, v in headers.items()}
# Quick check: at least one rate limit header must exist
has_any = any(k.startswith("x-ratelimit-") for k in lowered)
if not has_any:
return None
now = time.time()
def _bucket(resource: str, suffix: str = "") -> RateLimitBucket:
# e.g. resource="requests", suffix="" -> per-minute
# resource="tokens", suffix="-1h" -> per-hour
tag = f"{resource}{suffix}"
return RateLimitBucket(
limit=_safe_int(lowered.get(f"x-ratelimit-limit-{tag}")),
remaining=_safe_int(lowered.get(f"x-ratelimit-remaining-{tag}")),
reset_seconds=_safe_float(lowered.get(f"x-ratelimit-reset-{tag}")),
captured_at=now,
)
return RateLimitState(
requests_min=_bucket("requests"),
requests_hour=_bucket("requests", "-1h"),
tokens_min=_bucket("tokens"),
tokens_hour=_bucket("tokens", "-1h"),
captured_at=now,
provider=provider,
)
# ── Formatting ──────────────────────────────────────────────────────────
def _fmt_count(n: int) -> str:
"""Human-friendly number: 7999856 -> '8.0M', 33599 -> '33.6K', 799 -> '799'."""
if n >= 1_000_000:
return f"{n / 1_000_000:.1f}M"
if n >= 10_000:
return f"{n / 1_000:.1f}K"
if n >= 1_000:
return f"{n / 1_000:.1f}K"
return str(n)
def _fmt_seconds(seconds: float) -> str:
"""Seconds -> human-friendly duration: '58s', '2m 14s', '58m 57s', '1h 2m'."""
s = max(0, int(seconds))
if s < 60:
return f"{s}s"
if s < 3600:
m, sec = divmod(s, 60)
return f"{m}m {sec}s" if sec else f"{m}m"
h, remainder = divmod(s, 3600)
m = remainder // 60
return f"{h}h {m}m" if m else f"{h}h"
def _bar(pct: float, width: int = 20) -> str:
"""ASCII progress bar: [████████░░░░░░░░░░░░] 40%."""
filled = int(pct / 100.0 * width)
filled = max(0, min(width, filled))
empty = width - filled
return f"[{'█' * filled}{'░' * empty}]"
def _bucket_line(label: str, bucket: RateLimitBucket, label_width: int = 14) -> str:
"""Format one bucket as a single line."""
if bucket.limit <= 0:
return f" {label:<{label_width}} (no data)"
pct = bucket.usage_pct
used = _fmt_count(bucket.used)
limit = _fmt_count(bucket.limit)
remaining = _fmt_count(bucket.remaining)
reset = _fmt_seconds(bucket.remaining_seconds_now)
bar = _bar(pct)
return f" {label:<{label_width}} {bar} {pct:5.1f}% {used}/{limit} used ({remaining} left, resets in {reset})"
def format_rate_limit_display(state: RateLimitState) -> str:
"""Format rate limit state for terminal/chat display."""
if not state.has_data:
return "No rate limit data yet — make an API request first."
age = state.age_seconds
if age < 5:
freshness = "just now"
elif age < 60:
freshness = f"{int(age)}s ago"
else:
freshness = f"{_fmt_seconds(age)} ago"
provider_label = state.provider.title() if state.provider else "Provider"
lines = [
f"{provider_label} Rate Limits (captured {freshness}):",
"",
_bucket_line("Requests/min", state.requests_min),
_bucket_line("Requests/hr", state.requests_hour),
"",
_bucket_line("Tokens/min", state.tokens_min),
_bucket_line("Tokens/hr", state.tokens_hour),
]
# Add warnings if any bucket is getting hot
warnings = []
for label, bucket in [
("requests/min", state.requests_min),
("requests/hr", state.requests_hour),
("tokens/min", state.tokens_min),
("tokens/hr", state.tokens_hour),
]:
if bucket.limit > 0 and bucket.usage_pct >= 80:
reset = _fmt_seconds(bucket.remaining_seconds_now)
warnings.append(f" ⚠ {label} at {bucket.usage_pct:.0f}% — resets in {reset}")
if warnings:
lines.append("")
lines.extend(warnings)
return "\n".join(lines)
def format_rate_limit_compact(state: RateLimitState) -> str:
"""One-line compact summary for status bars / gateway messages."""
if not state.has_data:
return "No rate limit data."
rm = state.requests_min
tm = state.tokens_min
rh = state.requests_hour
th = state.tokens_hour
parts = []
if rm.limit > 0:
parts.append(f"RPM: {rm.remaining}/{rm.limit}")
if rh.limit > 0:
parts.append(f"RPH: {_fmt_count(rh.remaining)}/{_fmt_count(rh.limit)} (resets {_fmt_seconds(rh.remaining_seconds_now)})")
if tm.limit > 0:
parts.append(f"TPM: {_fmt_count(tm.remaining)}/{_fmt_count(tm.limit)}")
if th.limit > 0:
parts.append(f"TPH: {_fmt_count(th.remaining)}/{_fmt_count(th.limit)} (resets {_fmt_seconds(th.remaining_seconds_now)})")
return " | ".join(parts)
|