gooseworks-ai/goose-skills / skills/video/media-proxy
media-proxy
UnverifiedShared helper that routes ALL paid media generation (FAL image/video, ElevenLabs music) through the GooseWorks proxies so every call is charged to your GooseWorks credits — never a provider SDK's default host. Host-swaps the FAL queue URLs, loads the agent token from the sandbox env (GW_MEDIA_PROXY_TOKEN) or ~/.gooseworks/credentials.json, and returns the result CDN URL. Every video-ad media capability imports this; templates never call a provider directly.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.2 KB |
| scripts/media_proxy.py | script | 56.8 KB |
| scripts/resume.py | script | 2.2 KB |
| skill.meta.json | config | 126 B |
| tests/smoke-test.md | markdown | 655 B |
| tests/test_call_query.py | script | 2.9 KB |
| tests/test_media_proxy_policy.py | script | 25.3 KB |
tests/test_call_query.py
View on GitHub"""Custom-video quality tiers: a call's GooseWorks query (shot_scene and the upgrade fields) reaches
the proxy in both transports, and never overrides the proxy's own token or attribution. Free: the
HTTP call and the relay are stubbed, nothing is sent."""
import importlib.util
import json
import os
import pathlib
import tempfile
import unittest
from unittest import mock
SCRIPT = pathlib.Path(__file__).resolve().parents[1] / "scripts" / "media_proxy.py"
QUERY = {"shot_scene": 3, "upgrade_reason": "failed_attempt", "upgrade_attempt": "op-1",
"upgrade_why": "label text garbled at medium", "token": "evil", "project_id": "other"}
def load():
spec = importlib.util.spec_from_file_location("media_proxy_query", SCRIPT)
mod = importlib.util.module_from_spec(spec)
spec.loader.exec_module(mod)
return mod
class Stop(Exception):
pass
class CallQueryTest(unittest.TestCase):
def test_direct_proxy_sends_the_query_beside_its_own_params(self):
mp = load()
seen = {}
def post(url, params=None, **kw):
seen.update(params)
raise Stop()
with mock.patch.object(mp, "relay_mode", return_value=False), \
mock.patch.object(mp, "_cfg", return_value=("https://api.example", "tok", "agent-1")), \
mock.patch.dict(os.environ, {"GW_PROJECT_ID": "proj-1"}), \
mock.patch.object(mp.requests, "post", side_effect=post):
with self.assertRaises(Stop):
mp._fal_run_once("openai/gpt-image-2/edit", {"prompt": "x", "quality": "high"}, 5, 1, False, None, QUERY)
self.assertEqual(seen["shot_scene"], "3")
self.assertEqual(seen["upgrade_reason"], "failed_attempt")
self.assertEqual(seen["upgrade_attempt"], "op-1")
self.assertEqual(seen["upgrade_why"], "label text garbled at medium")
self.assertEqual((seen["token"], seen["agent_id"], seen["project_id"]), ("tok", "agent-1", "proj-1"))
def test_relay_puts_the_query_in_the_data_post_args(self):
mp = load()
seen = {}
def relay(kind, tool, args, then, extra=None, check=None):
seen.update(args)
raise Stop()
with mock.patch.object(mp, "relay_mode", return_value=True), mock.patch.object(mp, "_relay", side_effect=relay):
with self.assertRaises(Stop):
mp._fal_run_once("minimax/h3-max/reference-to-video", {"prompt": "x"}, 5, 1, False, None,
{"shot_scene": "2", "upgrade_reason": "customer_asked", "upgrade_quote": "sharper"})
self.assertEqual(seen["query"], {"shot_scene": "2", "upgrade_reason": "customer_asked", "upgrade_quote": "sharper"})
def test_no_query_sends_nothing_extra(self):
mp = load()
self.assertEqual(mp._call_query(None), {})
self.assertEqual(mp._call_query({"shot_scene": None}), {})
if __name__ == "__main__":
unittest.main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |