Skip to content

akiiwa-games/AgentCompass / skills/agent-compass

agent-compass

Flagged

Choose owner, model and effort, outbound authorization, advisor use, and continuation for delegated work. Reads local usage and effective account policy, profiles the task with the configured System-One scorer, then allocates a compatible worker. Use for independent worker or advisor work; ordinary local execution needs no routing.

FileKindSize
SKILL.mdskill md5.5 KB
agents/openai.yamlconfig427 B
calibration/README.mdmarkdown55.2 KB
calibration/arena_capture.pyscript14.0 KB
calibration/community.pyscript25.2 KB
calibration/five_axis.pyscript196.4 KB
calibration/measurements.pyscript68.4 KB
calibration/refresh.pyscript48.6 KB
calibration/series.pyscript10.2 KB
calibration/sources.pyscript24.1 KB
calibration/tiers.pyscript14.6 KB
grok-bot/.gitignoreother47 B
grok-bot/dependency_patch.pyscript4.5 KB
grok-bot/install_cli.pyscript3.6 KB
grok-bot/test-recovery.mjsscript8.6 KB
grok-bot/test_install_cli.pyscript4.1 KB
grok-bot/upstream.jsonconfig3.4 KB
references/accounts.jsonconfig155.9 KB
references/classifier-cases.jsonconfig21.5 KB
references/dispatch-lifecycle.mdmarkdown28.9 KB
references/dispatch-rules.mdmarkdown11.3 KB
references/effort-matching.mdmarkdown5.1 KB
references/fast-modes.mdmarkdown3.5 KB
references/five-axis-scores.jsonconfig3.1 MB
references/gemini-decisions-api.mdmarkdown2.9 KB
references/grok-bot.mdmarkdown13.0 KB
references/herdr.mdmarkdown5.1 KB
references/jev-api.mdmarkdown1.6 KB
references/level-3-conversion.jsonconfig2.4 KB
references/model-capabilities.jsonconfig3.6 KB
references/model-capabilities.mdmarkdown14.6 KB
references/parent-address-gate.mdmarkdown10.1 KB
references/plan-templates.jsonconfig13.2 KB
references/provider-discovery.mdmarkdown11.5 KB
references/provider-usage.mdmarkdown4.1 KB
references/public-data.jsonconfig816 B
references/public-measurements.jsonconfig1.3 MB
references/roll-reference.mdmarkdown26.7 KB
references/router-internals.mdmarkdown93.7 KB
references/task-classifier.mdmarkdown6.1 KB
references/user-scores.jsonconfig6.8 KB
references/work-kinds.mdmarkdown4.7 KB
references/worker-communication.mdmarkdown2.1 KB
scripts/account_fleet.pyscript32.9 KB
scripts/account_state.pyscript22.2 KB
scripts/accounts_override.pyscript14.8 KB
scripts/allocator.pyscript19.8 KB
scripts/antigravity_plan.pyscript18.7 KB
scripts/antigravity_telemetry.pyscript5.1 KB
scripts/auto_bundles.pyscript31.3 KB
scripts/axis_scores.pyscript40.3 KB
scripts/caller_input.pyscript3.0 KB
scripts/candidate_eval.pyscript54.0 KB
scripts/candidate_ranking.pyscript9.5 KB
scripts/capability_catalog.pyscript8.0 KB
scripts/check_router_contract.pyscript2.8 KB
scripts/conftest.pyscript2.5 KB
scripts/cwd_policy.pyscript1.5 KB
scripts/data_age.pyscript1.5 KB
scripts/decision_ledger.pyscript18.9 KB
scripts/demo_plan.pyscript6.3 KB
scripts/dispatch_fallback.pyscript40.3 KB
scripts/dispatch_flow.pyscript58.7 KB
scripts/dispatch_ground_truth.pyscript43.5 KB
scripts/dispatch_registry.pyscript113.7 KB
scripts/entry.pyscript1.7 KB
scripts/env_vars.pyscript580 B
scripts/fast_modes.pyscript2.5 KB
scripts/fixtures/grok-api-responses.jsonconfig907 B
scripts/fixtures/reference-accounts.jsonconfig26.9 KB
scripts/grok_bot_paths.pyscript1005 B
scripts/host_herdr.pyscript16.8 KB
scripts/host_placement.pyscript9.4 KB
scripts/host_policy.pyscript10.1 KB
scripts/launch_failures.pyscript5.9 KB
scripts/launch_values.pyscript12.3 KB
scripts/ledger_snapshot.pyscript11.1 KB
scripts/live_models.pyscript21.1 KB
scripts/model_latch.pyscript7.6 KB
scripts/model_resolution.pyscript18.0 KB
scripts/override_store.pyscript2.2 KB
scripts/plan_state_residue.pyscript5.0 KB
scripts/provider_inventory.pyscript128.2 KB
scripts/provider_retry.pyscript34.6 KB
scripts/public_data.pyscript59.2 KB
scripts/quota_economy.pyscript38.0 KB
scripts/quota_exhaustion.pyscript5.9 KB
scripts/quota_overrides.pyscript25.6 KB
scripts/quota_pools.pyscript29.8 KB
scripts/reference_provenance.pyscript32.3 KB
scripts/released_names.pyscript3.8 KB
scripts/roll.pyscript106.3 KB
scripts/route_judge.pyscript83.4 KB
scripts/route_simulation.pyscript26.3 KB
scripts/router_test_support.pyscript6.7 KB
scripts/run_grok_bot.pyscript18.8 KB
scripts/scorer_client.pyscript55.2 KB
scripts/stage_help.pyscript5.8 KB
scripts/state_upgrade.pyscript24.0 KB
scripts/subscription_cli.pyscript3.6 KB
scripts/task_intake.pyscript33.6 KB
scripts/test_account_identity.pyscript7.1 KB
scripts/test_account_state.pyscript63.3 KB
scripts/test_accounts_override.pyscript30.1 KB
scripts/test_allocator.pyscript94.2 KB
scripts/test_antigravity_plan.pyscript13.2 KB
scripts/test_applicable_quota.pyscript9.1 KB
scripts/test_auto_bundles.pyscript10.8 KB
scripts/test_billing_routing_policy.pyscript9.9 KB
scripts/test_cadence_count.pyscript32.2 KB
scripts/test_calibration_units.pyscript27.0 KB
scripts/test_capability_catalog.pyscript5.0 KB
scripts/test_decision_ledger.pyscript8.5 KB
scripts/test_demo_plan.pyscript3.4 KB
scripts/test_derived_state.pyscript21.6 KB
scripts/test_dispatch.pyscript322.3 KB
scripts/test_dispatch_answers.pyscript14.8 KB
scripts/test_dispatch_fallback.pyscript53.2 KB
scripts/test_entry.pyscript1.6 KB
scripts/test_fast_modes.pyscript9.9 KB
scripts/test_five_axis.pyscript290.1 KB
scripts/test_five_axis_economy.pyscript105.0 KB
scripts/test_fleet_parity.pyscript15.6 KB
scripts/test_grok_bot.pyscript47.7 KB
scripts/test_ground_truth_recording.pyscript68.8 KB
scripts/test_herdr.pyscript14.1 KB
scripts/test_host_policy.pyscript24.6 KB
scripts/test_launch_values.pyscript8.0 KB
scripts/test_metered_usd.pyscript60.4 KB
scripts/test_model_resolution.pyscript9.2 KB
scripts/test_named_route_facts.pyscript28.6 KB
scripts/test_native_hosts.pyscript6.0 KB
scripts/test_new_user_fleet.pyscript3.3 KB
scripts/test_no_hardcode_classification.pyscript75.1 KB
scripts/test_no_legacy_scoring.pyscript6.5 KB
scripts/test_override_store.pyscript2.3 KB
scripts/test_plan_says_why.pyscript44.9 KB
scripts/test_provider_inventory.pyscript83.2 KB
scripts/test_provider_names.pyscript126.0 KB
scripts/test_provider_pools.pyscript14.2 KB
scripts/test_public_data.pyscript93.5 KB
scripts/test_quota_exhaustion.pyscript5.6 KB
scripts/test_rate_limit_windows.pyscript6.3 KB
scripts/test_record_says_why.pyscript26.5 KB
scripts/test_reference_provenance.pyscript16.7 KB
scripts/test_refresh_entry.pyscript110.7 KB
scripts/test_released_names.pyscript4.1 KB
scripts/test_reset_priority.pyscript4.8 KB
scripts/test_roll_answers.pyscript44.7 KB
scripts/test_roll_notifications.pyscript10.4 KB
scripts/test_route_judge.pyscript99.8 KB
scripts/test_route_simulation.pyscript7.0 KB
scripts/test_routing_parity.pyscript32.3 KB
scripts/test_routing_review.pyscript25.1 KB
scripts/test_setup_discovery_parity.pyscript9.5 KB
scripts/test_stage_help.pyscript2.0 KB
scripts/test_state_upgrade.pyscript13.8 KB
scripts/test_turn_refusal.pyscript16.7 KB
scripts/test_usage_cache.pyscript4.9 KB
scripts/test_usage_collector.pyscript21.4 KB
scripts/test_usage_core_claude_accounts.pyscript1.8 KB
scripts/test_usage_core_grok_cli_billing.pyscript15.6 KB
scripts/test_usage_core_magpie.pyscript5.4 KB
scripts/test_usage_core_magpie_pool.pyscript10.8 KB
scripts/test_usage_core_safety.pyscript24.4 KB
scripts/test_user_scores.pyscript102.3 KB
scripts/test_venice_usage.pyscript1.3 KB
scripts/test_window_scope.pyscript5.5 KB
scripts/turn_refusal.pyscript10.7 KB
scripts/usage_cache.pyscript4.7 KB
scripts/usage_collector.pyscript7.4 KB
scripts/usage_core.pyscript142.0 KB
scripts/usage_magpie.pyscript10.6 KB
scripts/usage_reading.pyscript17.1 KB
scripts/user_scores.pyscript72.8 KB
scripts/venice_usage.pyscript2.6 KB
scripts/window_scope.pyscript3.2 KB
scripts/worker_context.pyscript8.9 KB
scripts/worker_sessions.pyscript10.9 KB

scripts/test_billing_routing_policy.py

View on GitHub
"""Contract: only subscription accounts join automatic routing.

Metered (API) and unknown billing stay recognized and launchable. A checked metered
bundle is a last resort: chosen by an explicit selection, task.metered_ok, or when no
subscription bundle can take the work. The model-management checkbox is eligibility,
not consent to outrank subscriptions. Unknown billing stays explicit selection only.
Oh My Pi (Paseo's built-in `omp` provider) is the first metered Paseo launcher.
"""
from datetime import datetime, timezone
import json
import unittest
from unittest.mock import patch

import accounts_override
import allocator
import account_fleet
import dispatch_registry
import host_policy
import provider_inventory as inventory

from router_test_support import isolated_router_state, temporary_root, usage_windows

BUNDLE = 'venice_glm52_high'
TASK = {
    'objective': 'Reply with exactly OK',
    'hours': 0.1,
    'profile': {
        'work_kind': 'text_processing', 'primary_level': 1, 'secondary_kind': 'none', 'secondary_level': 0,
        'needs_visual': False, 'needs_gui': False, 'local_only': False, 'wants_fast': False,
        'read_only_review': False, 'access': 'read-only', 'expected_hours': 0.1,
        'multi_task': False, 'task_count': '1',
        'axis_demand': {'creativity': 0, 'coding': 0, 'aesthetics': 0, 'tool_operation': 0},
    },
}
NOW = datetime(2026, 11, 11, tzinfo=timezone.utc)
# One current reading per window that can price spend: the subscription's own and the metered account's prepaid budget.
USAGE = usage_windows(NOW, {'codex': [('usage', 90, 100)], 'omp': [('weekly', 90, 100)]})


def setUpModule():
    isolated_router_state(unittest.addModuleCleanup, discovery=False, policy=False)


def omp_accounts(billing='metered', subscription=True):
    accounts = account_fleet.load_accounts(account_fleet.REFERENCES / 'accounts.json')
    accounts['accounts']['codex'].update(verified=subscription, plan='Pro')  # one launchable subscription account
    spec = accounts['accounts']['omp']
    # A metered account states its own prepaid budget: community capacity data measures subscription plans only.
    spec.update(billing=billing, verified=True, windows={'weekly': {'hours': 168}}, capacity_usd={'weekly': 200.0})
    spec.pop('capacity_status', None)
    # GLM-5.2's Arena rows are listed at Max only and it has no multi-effort AA curve, so F2 scores only 'max'; run the
    # fixture bundle at 'max' where both its five-axis scores and its Arena duration fit exist (its id is only a label).
    spec['bundles'][BUNDLE]['effort'] = 'max'
    if billing is None:
        spec.pop('billing')  # an account entry alone is not consent to automatic routing
    return accounts


def omp_row(decision):
    return next(row for row in decision['ranking'] if row['id'] == BUNDLE)


class AutomaticRoutingTests(unittest.TestCase):
    def plan(self, accounts, constraints=None):
        return allocator.plan({**TASK, 'constraints': constraints or {}}, USAGE, NOW, accounts=accounts, overrides=[],
                              host_policy_config=None)

    def test_metered_and_unknown_billing_are_not_automatic(self):
        for billing, reason in (('metered', 'metered access is a last resort'),
                                ('unknown', 'unknown billing: explicit selection only'),
                                (None, 'unknown billing: explicit selection only')):
            with self.subTest(billing=billing):
                decision = self.plan(omp_accounts(billing))
                self.assertNotEqual(decision['choice'], BUNDLE)
                self.assertIn(reason, omp_row(decision)['excluded'])

    def test_explicit_model_selects_metered_omp_bundle(self):
        for model in ('glm-5.2', 'venice-api/zai-org-glm-5-2', BUNDLE):
            with self.subTest(model=model):
                decision = self.plan(omp_accounts(), {'model': model})
                self.assertEqual(decision['choice'], BUNDLE)
                self.assertEqual(decision['selected_bundle']['launch_model'], 'venice-api/zai-org-glm-5-2')

    def test_checked_metered_bundle_stays_last_resort(self):
        for billing, reason in (('metered', 'metered access is a last resort'),
                                ('unknown', 'unknown billing: explicit selection only')):
            with self.subTest(billing=billing):
                accounts = omp_accounts(billing)
                accounts_override.apply(accounts, {'accounts': {'omp': {'bundles': {BUNDLE: {'disabled': False}}}}})
                bundle = accounts['accounts']['omp']['bundles'][BUNDLE]
                self.assertEqual({k for k in bundle if 'enabled' in k}, set())  # the checkbox writes only `disabled`
                decision = self.plan(accounts)
                # The fixture's one launchable subscription account takes the work, whichever of its bundles wins.
                self.assertEqual(decision['selected_bundle']['account'], 'codex')
                self.assertIn(reason, omp_row(decision)['excluded'])
                self.assertNotIn('metered_fallback', decision['decision']['task'])

    def test_metered_used_when_no_subscription_can_take_the_work(self):
        decision = self.plan(omp_accounts(subscription=False))
        self.assertEqual(decision['choice'], BUNDLE)
        self.assertTrue(decision['decision']['task']['metered_fallback'])
        unchecked = omp_accounts(subscription=False)
        unchecked['accounts']['omp']['bundles'][BUNDLE]['disabled'] = True
        self.assertEqual(self.plan(unchecked)['choice'], 'none')  # unchecked is never a fallback
        self.assertEqual(self.plan(omp_accounts('unknown', subscription=False))['choice'], 'none')

    def test_task_metered_ok_admits_checked_metered_bundle(self):
        decision = allocator.plan({**TASK, 'metered_ok': True}, USAGE, NOW, accounts=omp_accounts(), overrides=[],
                                  host_policy_config=None)
        self.assertFalse([r for r in omp_row(decision)['excluded'] if 'metered' in r])

    def test_subscription_accounts_are_unchanged(self):
        decision = self.plan(omp_accounts('subscription'))
        self.assertFalse([r for r in omp_row(decision)['excluded'] if 'billing' in r or 'metered' in r])

    def test_dispatch_recheck_keeps_explicit_selection_for_pinned_bundle(self):
        # dispatch_registry.prepare re-plans a user_override with pinned_bundle and no model
        # constraint; the explicit choice must survive that recheck end to end.
        decision = allocator.plan(TASK, USAGE, NOW, accounts=omp_accounts(), overrides=[], route={'pinned_bundle': BUNDLE},
                                  host_policy_config=None)
        self.assertFalse([r for r in omp_row(decision)['excluded'] if 'metered' in r or 'billing' in r])
        other = allocator.plan(TASK, USAGE, NOW, accounts=omp_accounts(), overrides=[], route={'pinned_bundle': 'sol_high'},
                               host_policy_config=None)
        self.assertIn('metered access is a last resort', omp_row(other)['excluded'])


class OmpLaunchTests(unittest.TestCase):
    def test_paseo_launch_request_uses_omp_provider_mode_and_thinking(self):
        bundle = omp_accounts()['accounts']['omp']['bundles'][BUNDLE]
        request = dispatch_registry.launch_request(bundle, {'title': 't', 'initialPrompt': 'p'})
        self.assertEqual(request['provider'], 'omp/venice-api/zai-org-glm-5-2')
        self.assertEqual(request['settings'], {'modeId': 'full', 'thinkingOptionId': bundle['effort']})


class DiscoveryTests(unittest.TestCase):
    def setUp(self):
        self.home = temporary_root(self.addCleanup)
        self.now = datetime(2026, 10, 30, 12, tzinfo=timezone.utc)

    def discover(self, providers, omp_installed):
        path = self.home / '.paseo/config.json'
        path.parent.mkdir(parents=True, exist_ok=True)
        path.write_text(json.dumps({'agents': {'providers': providers}}), encoding='utf-8')
        with patch.object(inventory.shutil, 'which',
                          side_effect=lambda name, **kwargs: 'omp.exe' if omp_installed and name == 'omp' else None):
            return inventory.discover(self.home, {'PATH': ''}, self.now)

    def test_omp_is_metered_and_follows_paseo_switch(self):
        for label, providers, installed, status in (
            ('not configured', {}, True, 'disabled'),
            ('disabled', {'omp': {'enabled': False}}, True, 'disabled'),
            ('enabled, installed', {'omp': {'enabled': True}}, True, 'ready'),
            ('enabled, missing', {'omp': {'enabled': True}}, False, 'missing_client'),
        ):
            with self.subTest(case=label):
                row = self.discover(providers, installed)['accounts']['omp']
                self.assertEqual((row['family'], row['billing'], row['status']), ('omp', 'metered', status))

    def test_paseo_builtins_are_recognized_without_invented_models(self):
        snapshot = self.discover({'copilot': {'enabled': False}, 'muse': {'enabled': True}}, False)
        self.assertEqual(snapshot['accounts']['copilot']['status'], 'disabled')
        muse = snapshot['accounts']['muse']
        self.assertEqual((muse['family'], muse['billing'], muse['status']), ('muse', 'unknown', 'ready'))
        self.assertNotIn('models', muse)
        accounts = inventory.apply(account_fleet.load_accounts(account_fleet.reference_fleet_path()), snapshot)
        self.assertFalse((accounts['accounts'].get('muse') or {}).get('bundles'))

    def test_metered_ready_account_is_not_auto_enrolled_by_host_policy(self):
        policy = self.home / 'host-policy.json'
        policy.write_text(json.dumps({'allowed_accounts': ['codex'], 'known_accounts': ['codex']}), encoding='utf-8')
        accounts = omp_accounts()
        accounts['_discovery'] = {'accounts': {'omp': {'status': 'ready', 'family': 'omp'}}}
        with patch.dict(inventory.os.environ, {'ROUTER_HOST_POLICY': str(policy)}):
            self.assertEqual(host_policy.sync_discovered(accounts)['added'], [])
            self.assertFalse(host_policy.account_allowed(host_policy.load_policy(), 'omp'))


if __name__ == '__main__':
    unittest.main()
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall