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_model_resolution.py

View on GitHub
"""Public/gateway launch names score consistently without changing launch IDs."""
import unittest

import account_fleet
import auto_bundles
import axis_scores
from model_resolution import family_patterns, provider_name_table, resolve_canonical_model

from router_test_support import isolated_router_state


def setUpModule():
    isolated_router_state(unittest.addModuleCleanup)


class ModelResolutionTests(unittest.TestCase):
    def setUp(self):
        self.accounts = account_fleet.load_accounts(account_fleet.reference_fleet_path())

    def test_decorated_names_aliases_and_family_defaults(self):
        cases = {
            'anthropic/claude-haiku-4-5@20251001': 'claude-haiku-4-5',
            'anthropic/claude-opus-4-6-20260205': 'claude-opus-4-6',
            'claude-sonnet-4-6-latest': 'claude-sonnet-4-6',
            'vendor/claude-opus-future': 'claude-opus-5-5',
            'claude-sonnet-future': 'claude-sonnet-5-5',
            'claude-haiku-future': 'claude-haiku-5-5',
            'claude-fable-future': 'claude-fable-5-2',
            'fable': 'claude-fable-5-2',
            'claude-fable-5': 'claude-fable-5-2',
            'claude-fable-5-2:max': 'claude-fable-5-2',
            'claude-fable-5-1': 'claude-fable-5-1',
            'anthropic/claude-fable-5-1': 'claude-fable-5-1',
            'openai/gpt-6.1-terra:latest': 'gpt-6.1-terra',
            'gpt-6-future': 'gpt-6-astra',
            'gpt-6-future-terra': 'gpt-6.1-terra',
            'gpt-6-future-sol': 'gpt-6.1-sol',
            'gpt-6-future-luna': 'gpt-6-luna',
            'gpt-6-future-pro': 'gpt-6-pro',
            'gpt-6-sol': 'gpt-6-sol',
            'gpt-5.6-sol': 'gpt-5.6-sol',
            'gpt-5.6-terra': 'gpt-5.6-terra',
            'gpt-5.6-luna': 'gpt-5.6-luna',
            'google/gemini-4-pro-preview': 'gemini-4-argon-high',
            'google/gemini-future-pro': 'gemini-4-argon-high',
            'gemini-future-flash': 'gemini-3.8-flash-high',
            'xai/grok-4:free': 'grok-4.7',
            'grok-4.7-latest': 'grok-4.7',
            'grok-future-fast': 'grok-4.7-build-fast',
            'grok-future': 'grok-4.7',
            'deepseek-r-future': 'deepseek-v4-pro',
            'deepseek-v-future': 'deepseek-v4-pro',
            'deepseek-future-flash': 'deepseek-v4.1-flash-free',
            'opencode/deepseek-v4.1-flash-free': 'deepseek-v4.1-flash-free',
            'qwen/Qwen3-Coder-Next:free': 'qwen3-coder-next',
            'qwen-future-coder': 'qwen3-coder-next',
            'qwen-future': 'qwen3.8-max',
            'kimi-future': 'kimi-k3.1-pro',
            'moonshot-future': 'kimi-k3.1-pro',
            'glm-future': 'glm-5.3',
            'opencode/glm-5.3-flash-free': 'glm-5.3-flash-free',
            'minimax-future': 'minimax-m3',
            'minimax-future-flash': 'minimax-m3.1-flash',
            'MiniMax-M3.1-Flash': 'minimax-m3.1-flash',
            'doubao-future': 'doubao-seed-2-1-pro-260628',
            'xiaomi/mimo-future': 'mimo-v2.6-pro',
            'opencode/mimo-v2.6-flash-free': 'mimo-v2.6-flash-free',
            'nvidia/nemotron-future-ultra': 'nemotron-3-ultra-free',
            'nemotron-future-super-vl': 'nemotron-3.5-super-vl-free',
            'nemotron-future-lightning': 'nemotron-3.5-lightning-free',
            'muse-future': 'muse-wonder-1.0',
            'mistral-future': 'mistral-large-4',
            'codestral-future': 'mistral-large-4',
        }
        for raw, expected in cases.items():
            with self.subTest(raw=raw):
                self.assertEqual(account_fleet.canonical(raw, self.accounts), expected)
                resolved = account_fleet.resolve_model(raw, self.accounts)
                spec = account_fleet.model_spec(self.accounts, raw)
                if resolved['source'] == 'family':
                    # A family name carries no row of its own: its scores come from the series conversion in the shipped
                    # five-axis data, never from a copied or default spec.
                    self.assertEqual(spec, {})
                else:
                    self.assertEqual(spec, self.accounts['models'][expected])

    def test_exact_custom_models_aliases_and_existing_calibrations_win(self):
        for name, spec in self.accounts['models'].items():
            if isinstance(spec, dict):
                self.assertEqual(account_fleet.canonical(name, self.accounts), name)
                self.assertIs(account_fleet.model_spec(self.accounts, name), spec)
        for alias, target in self.accounts['aliases'].items():
            self.assertEqual(account_fleet.canonical(alias, self.accounts), target)
        self.accounts['models']['gpt-5-custom'] = {'fast_capable': False}
        self.accounts['aliases']['openai/gpt-5-custom@20251001'] = 'gpt-6.1-sol'
        self.assertEqual(account_fleet.canonical('gpt-5-custom', self.accounts), 'gpt-5-custom')
        self.assertEqual(account_fleet.canonical('openai/gpt-5-custom@20251001', self.accounts), 'gpt-6.1-sol')
        self.assertEqual(account_fleet.canonical('vendor/gpt-5-custom-latest', self.accounts), 'gpt-5-custom')
        # Alias cycles and metadata strings must not become model specifications.
        none = {'defaults': {}, 'rows': {}}
        self.assertIsNone(resolve_canonical_model('loop', {}, {'loop': 'other', 'other': 'loop'}, [], none))
        self.assertIsNone(resolve_canonical_model('basis', self.accounts['models'], {}, family_patterns(self.accounts), none))

    def test_a_document_without_a_families_table_is_a_named_error_not_an_empty_table(self):
        doc = {key: value for key, value in self.accounts.items() if key != 'families'}
        for call in (lambda: account_fleet.resolve_model('claude-opus-6-0', doc),
                     lambda: account_fleet.canonical('claude-opus-6-0', doc),
                     lambda: auto_bundles.series_target('claude-opus-6-0', doc)):
            with self.subTest(call=call), self.assertRaisesRegex(ValueError, 'no families table'):
                call()

    def test_unknown_models_have_no_row_score_or_price(self):
        self.assertEqual(account_fleet.resolve_model('new-vendor/unknown', self.accounts)['source'], 'unknown')
        self.assertEqual(account_fleet.model_spec(self.accounts, 'new-vendor/unknown'), {})
        self.assertNotIn('unmeasured_models', self.accounts)

    def test_obsolete_defaults_are_removed_and_catalog_gaps_stay_explicit(self):
        obsolete = {
            'claude-3-7-sonnet', 'gpt-4.1', 'gpt-4.1-mini', 'o3', 'o3-pro',
            'o4-mini', 'gemini-2.5-pro', 'gemini-2.5-flash', 'grok-3',
            'grok-3-mini', 'deepseek-r1', 'deepseek-v3', 'qwen3-coder',
            'qwen3-235b-a22b', 'kimi-k2', 'glm-4.6', 'minimax-m2',
            'doubao-seed-1.6', 'llama-4-maverick',
        }
        self.assertNotIn('effort_curves', self.accounts)
        for name in obsolete:
            with self.subTest(name=name):
                self.assertNotIn(name, self.accounts['models'])
                self.assertNotIn(name, self.accounts['aliases'])
                self.assertNotIn(name, self.accounts['aliases'].values())
                for rows in self.accounts['dispatch_efforts'].values():
                    self.assertNotIn(name, rows)
        # Catalog did not advertise these speculative launch IDs.
        for name in ['deepseek-r2', 'deepseek-v4.1', 'gemini-3.8-pro',
                     'grok-4.7-mini', 'grok-4.7-fast', 'llama-5']:
            self.assertNotIn(name, self.accounts['models'])
        for name in ['llama-future', 'gpt-4-future', 'unknown-vendor']:
            self.assertIsNone(resolve_canonical_model(name, self.accounts['models'], self.accounts['aliases'],
                                                      family_patterns(self.accounts), provider_name_table(self.accounts)))

    def test_current_frontier_tiers_and_context_windows(self):
        shipped = axis_scores.load_five_axis()['models']
        self.assertEqual(shipped['claude-opus-5-5']['tier']['value'], 0.0)
        sentinels = {
            'claude-opus-5-5': 'arena_overall',
            'gemini-3.8-flash-high': 'arena_overall',
            # Listed only at xHigh/Max on arena.ai Overall, so R2-F2 @High-only tier reads aa.index at High:
            'claude-sonnet-5-5': 'other_overall',
            'gpt-6-astra': 'other_overall',
            'gpt-6.1-sol': 'other_overall',
            'grok-4.7': 'other_overall',
        }
        for name, expected_method in sentinels.items():
            self.assertEqual(shipped[name]['tier']['method'], expected_method, name)
            self.assertIsInstance(shipped[name]['tier']['value'], (int, float), name)
        # Distinct Arena Overall @High models never collapse to the old 3.675 PAV anchor plateau or 'anchor' method
        self.assertEqual(len({shipped[n]['tier']['value'] for n in sentinels}), len(sentinels))
        for name, row in shipped.items():
            self.assertNotEqual((row.get('tier') or {}).get('method'), 'anchor', name)
            self.assertNotEqual((row.get('tier') or {}).get('value'), 3.675, name)
        for name in self.accounts['models']:
            if isinstance(self.accounts['models'][name], dict):
                self.assertIn(name, shipped, name)
        self.assertEqual(self.accounts['models']['gpt-6.1-terra']['context_window'], 500000)


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