Add Fireworks balance usage panel (#6488)
* Add a Fireworks balance collector and teach the agents panel prepaid ledgers The omarchy-agent-usage-fireworks collector reads serverless token usage from the Fireworks billing API, grouped by day and model for the last 30 days, and reshapes it into the shared record contract. Fireworks does not expose its prepaid ledger through the documented API, so the record carries an estimated balance instead of rate limits: credits configured in ~/.config/omarchy/agents/fireworks.json minus rated account costs since the funding date. Credentials come from FIREWORKS_API_KEY/FIREWORKS_ACCOUNT_ID, the auth.ini that firectl set-api-key writes, or — last, so an explicit login wins — the key opencode stores for its fireworks-ai provider. The panel gains two generic capabilities any agent record can use: a balance object draws a BALANCE section — remaining credit, a fuel-gauge meter that drains toward empty and lights the bar alarm below 10%, and funded-versus-spent detail — and hasPromptStats: false keeps prompt and session counts out of today's tooltip for agents whose billing API only ever reports tokens, on this machine and through synced snapshots. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Feed Claude and Codex usage from pi, omp, and opencode sessions A subscription burned entirely through another coding agent leaves no native Claude Code transcripts and no Codex session files, so the panel showed nothing for it. pi and omp write compatible JSONL sessions, and opencode records per-message provider, model, and token usage in its message database; the claude and codex collectors now scan all three — filtered to Anthropic and OpenAI providers respectively — and merge those numbers into their local stats. Fireworks stays out on purpose: its billing API already sees that traffic server-side, and a local scan would count the same tokens twice. The collector tests pin XDG_DATA_HOME so a developer's real opencode history cannot leak into fixture runs. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
David Heinemeier Hansson
co-authored by
Claude Fable 5
Claude Fable 5
parent
b85ae70ebd
commit
77cf58ccfe
+111
-60
@@ -4,9 +4,10 @@
|
||||
# omarchy:hidden=true
|
||||
"""Collect Codex usage into one display-ready JSON record.
|
||||
|
||||
Local stats come from native Codex CLI session files (and pi sessions that
|
||||
ran through openai-codex); rate limits and the plan come from the Codex
|
||||
app-server RPC. The agents panel only ever reads the JSON this prints.
|
||||
Local stats come from native Codex CLI session files, pi/omp sessions that
|
||||
ran through openai-codex, and opencode sessions that ran on an OpenAI
|
||||
provider; rate limits and the plan come from the Codex app-server RPC. The agents
|
||||
panel only ever reads the JSON this prints.
|
||||
"""
|
||||
|
||||
import argparse
|
||||
@@ -14,6 +15,7 @@ import json
|
||||
import os
|
||||
import select
|
||||
import shutil
|
||||
import sqlite3
|
||||
import subprocess
|
||||
import time
|
||||
from datetime import datetime, timedelta, timezone
|
||||
@@ -122,69 +124,117 @@ def add_usage(day, session_key, model, input_tokens, output_tokens, cache_read,
|
||||
|
||||
|
||||
def scan_pi_sessions():
|
||||
root = Path.home() / ".pi" / "agent" / "sessions"
|
||||
if not root.exists():
|
||||
return
|
||||
try:
|
||||
rg = find_command("rg") or "rg"
|
||||
proc = subprocess.Popen(
|
||||
[rg, "--json", "-e", '"provider":"openai-codex"', "-e", '"api":"openai-codex"', str(root)],
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.DEVNULL,
|
||||
text=True,
|
||||
errors="replace",
|
||||
env=ENV,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
return
|
||||
|
||||
assert proc.stdout is not None
|
||||
for raw in proc.stdout:
|
||||
roots = [
|
||||
Path.home() / ".pi" / "agent" / "sessions",
|
||||
Path.home() / ".omp" / "agent" / "sessions",
|
||||
]
|
||||
rg = find_command("rg") or "rg"
|
||||
for root in roots:
|
||||
if not root.exists():
|
||||
continue
|
||||
try:
|
||||
event = json.loads(raw)
|
||||
if event.get("type") != "match":
|
||||
proc = subprocess.Popen(
|
||||
[rg, "--json", "-e", r'"provider"\s*:\s*"openai-codex"', "-e", r'"api"\s*:\s*"openai-codex', str(root)],
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.DEVNULL,
|
||||
text=True,
|
||||
errors="replace",
|
||||
env=ENV,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
return
|
||||
|
||||
assert proc.stdout is not None
|
||||
for raw in proc.stdout:
|
||||
try:
|
||||
event = json.loads(raw)
|
||||
if event.get("type") != "match":
|
||||
continue
|
||||
line = event.get("data", {}).get("lines", {}).get("text", "")
|
||||
path = event.get("data", {}).get("path", {}).get("text", "pi-session")
|
||||
entry = json.loads(line)
|
||||
except Exception:
|
||||
continue
|
||||
line = event.get("data", {}).get("lines", {}).get("text", "")
|
||||
path = event.get("data", {}).get("path", {}).get("text", "pi-session")
|
||||
entry = json.loads(line)
|
||||
|
||||
if entry.get("type") != "message":
|
||||
continue
|
||||
message_key = path + ":" + str(entry.get("id") or "")
|
||||
if message_key in seen_pi_messages:
|
||||
continue
|
||||
seen_pi_messages.add(message_key)
|
||||
message = entry.get("message") or {}
|
||||
if message.get("role") != "assistant":
|
||||
continue
|
||||
provider = str(message.get("provider") or "")
|
||||
api = str(message.get("api") or "")
|
||||
if provider != "openai-codex" and not api.startswith("openai-codex"):
|
||||
continue
|
||||
|
||||
usage = message.get("usage") or {}
|
||||
if not usage:
|
||||
continue
|
||||
total = number(usage.get("totalTokens"))
|
||||
input_tokens = number(usage.get("input"))
|
||||
output_tokens = number(usage.get("output"))
|
||||
cache_read = number(usage.get("cacheRead"))
|
||||
cache_write = number(usage.get("cacheWrite"))
|
||||
if total and not (input_tokens or output_tokens or cache_read or cache_write):
|
||||
input_tokens = total
|
||||
if not (input_tokens or output_tokens or cache_read or cache_write):
|
||||
continue
|
||||
|
||||
day = local_day(entry.get("timestamp") or message.get("timestamp"))
|
||||
session_key = path
|
||||
add_usage(day, session_key, model_name(message.get("model")), input_tokens, output_tokens, cache_read, cache_write)
|
||||
|
||||
try:
|
||||
proc.wait(timeout=1)
|
||||
except Exception:
|
||||
continue
|
||||
proc.kill()
|
||||
|
||||
if entry.get("type") != "message":
|
||||
continue
|
||||
message_key = path + ":" + str(entry.get("id") or "")
|
||||
if message_key in seen_pi_messages:
|
||||
continue
|
||||
seen_pi_messages.add(message_key)
|
||||
message = entry.get("message") or {}
|
||||
if message.get("role") != "assistant":
|
||||
continue
|
||||
provider = str(message.get("provider") or "")
|
||||
api = str(message.get("api") or "")
|
||||
if provider != "openai-codex" and not api.startswith("openai-codex"):
|
||||
continue
|
||||
|
||||
usage = message.get("usage") or {}
|
||||
if not usage:
|
||||
continue
|
||||
total = number(usage.get("totalTokens"))
|
||||
input_tokens = number(usage.get("input"))
|
||||
output_tokens = number(usage.get("output"))
|
||||
cache_read = number(usage.get("cacheRead"))
|
||||
cache_write = number(usage.get("cacheWrite"))
|
||||
if total and not (input_tokens or output_tokens or cache_read or cache_write):
|
||||
input_tokens = total
|
||||
if not (input_tokens or output_tokens or cache_read or cache_write):
|
||||
continue
|
||||
|
||||
day = local_day(entry.get("timestamp") or message.get("timestamp"))
|
||||
session_key = path
|
||||
add_usage(day, session_key, model_name(message.get("model")), input_tokens, output_tokens, cache_read, cache_write)
|
||||
|
||||
def scan_opencode_sessions():
|
||||
# A subscription burned entirely through opencode leaves no native session
|
||||
# files, but opencode records per-message provider, model, and token usage
|
||||
# in its own database. Read-only: opencode may be writing right now.
|
||||
db = Path(os.environ.get("XDG_DATA_HOME") or (Path.home() / ".local" / "share")) / "opencode" / "opencode.db"
|
||||
if not db.is_file():
|
||||
return
|
||||
try:
|
||||
proc.wait(timeout=1)
|
||||
except Exception:
|
||||
proc.kill()
|
||||
conn = sqlite3.connect(db.resolve().as_uri() + "?mode=ro", uri=True, timeout=2)
|
||||
except sqlite3.Error:
|
||||
return
|
||||
try:
|
||||
conn.execute("PRAGMA query_only = ON")
|
||||
for session_id, raw in conn.execute("SELECT session_id, data FROM message"):
|
||||
# One malformed row must not abort the scan, so every shape assumption
|
||||
# lives inside the try.
|
||||
try:
|
||||
entry = json.loads(raw)
|
||||
# Exact match: opencode provider ids are free-form, and a custom
|
||||
# "openai-local" gateway is not this subscription.
|
||||
if not isinstance(entry, dict) or entry.get("role") != "assistant":
|
||||
continue
|
||||
if str(entry.get("providerID") or "") != "openai":
|
||||
continue
|
||||
tokens = entry.get("tokens") or {}
|
||||
cache = tokens.get("cache") or {}
|
||||
input_tokens = number(tokens.get("input"))
|
||||
# opencode keeps thinking tokens out of output; both are generated.
|
||||
output_tokens = number(tokens.get("output")) + number(tokens.get("reasoning"))
|
||||
cache_read = number(cache.get("read"))
|
||||
cache_write = number(cache.get("write"))
|
||||
if not (input_tokens or output_tokens or cache_read or cache_write):
|
||||
continue
|
||||
day = local_day((entry.get("time") or {}).get("created"))
|
||||
model = model_name(str(entry.get("modelID") or "").rstrip("/").split("/")[-1])
|
||||
except Exception:
|
||||
continue
|
||||
add_usage(day, "opencode:" + str(session_id), model, input_tokens, output_tokens, cache_read, cache_write)
|
||||
except sqlite3.Error:
|
||||
pass
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
|
||||
def scan_native_codex_sessions():
|
||||
@@ -349,6 +399,7 @@ def main():
|
||||
|
||||
scan_pi_sessions()
|
||||
scan_native_codex_sessions()
|
||||
scan_opencode_sessions()
|
||||
rpc = fetch_codex_rpc()
|
||||
|
||||
record = {
|
||||
|
||||
Reference in New Issue
Block a user