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_auto_bundles.py

View on GitHub
import json
from pathlib import Path
import unittest

import auto_bundles as ab
import allocator
import account_fleet
import quota_pools

from router_test_support import isolated_router_state


def setUpModule():
    isolated_router_state(unittest.addModuleCleanup)

REAL = json.loads(account_fleet.reference_fleet_path().read_text(encoding='utf-8-sig'))
NOW = 2_000_000_000.0


def public(accounts):
    return {'models': REAL['models'], 'aliases': REAL.get('aliases', {}), 'superseded': REAL.get('superseded', {}),
            'families': REAL['families'], 'provider_names': REAL['provider_names'], 'accounts': accounts}


def proxy_accounts():
    acc = public({
        'llmproxy': {'billing': 'metered', 'backend_kind': 'metered_usd', 'family': 'codex',
                     'windows': {'balance': {}}, 'bundles': {}}})
    return acc


def catalog(provider, ids, ok=True, checked=NOW):
    return {'providers': {provider: {'ok': ok, 'type': 'openai_compatible', 'checked_at': checked,
                                     'models': [{'id': i} for i in ids]}}}


class DefaultProfile(unittest.TestCase):
    def test_a_name_resolves_to_a_calibrated_row_a_series_or_nothing(self):
        for model, source, canonical, target in (
            ('claude-opus-5-5-high', 'calibrated', 'claude-opus-5-5', 'claude-opus-5-5'),
            ('qwen3.7-max', 'calibrated', 'qwen3.7-max', 'qwen3.7-max'),
            ('qwen3.5-max', 'family', 'qwen3.5-max', 'qwen3.8-max'),
            # Alibaba documents `qwen-flash` as the Qwen3 Flash 2025-07-28 snapshot: an alias to its row
            ('qwen-flash', 'calibrated', 'qwen3-flash-2025-07-28', 'qwen3-flash-2025-07-28'),
            ('deepseek-flash', 'calibrated', 'deepseek-v4.1-flash-free', 'deepseek-v4.1-flash-free'),
            ('zzz-unknown-9', 'unmeasured', 'zzz-unknown-9', None),
        ):
            with self.subTest(model=model):
                profile = ab.default_profile(model, REAL)
                self.assertEqual((profile['source'], profile['model'], profile['target']), (source, canonical, target))
                self.assertNotIn('spec', profile)       # no score row is supplied for a name the data does not carry

    def test_a_name_without_a_row_or_a_series_has_no_scores(self):
        for name in ('opencode/big-pickle', 'pulse-alpha-free'):
            profile = ab.default_profile(name, REAL)
            self.assertEqual((profile['source'], profile['target']), ('unmeasured', None), name)

    def test_split_effort(self):
        self.assertEqual(ab.split_effort('claude-opus-5-5-xhigh'), ('claude-opus-5-5', 'xhigh'))
        self.assertEqual(ab.split_effort('gpt-6.1-sol'), ('gpt-6.1-sol', None))


class Derive(unittest.TestCase):
    def test_proxy_metered_latest_checked_and_non_chat_excluded(self):
        # Checked is not routed: metered stays a last resort in candidate_eval.evaluate_bundle.
        out = ab.derive(proxy_accounts(), catalog('llmproxy', ['gpt-6.1-sol', 'kimi-k3', 'gemini-embedding-001', 'qwen-flash', 'zzz-proxy-model']), NOW)
        rows = out['bundles']['llmproxy']
        self.assertTrue(all(not b['disabled'] and b['billing'] == 'metered' for b in rows.values()))
        self.assertIn('auto:llmproxy:codex:gpt-6.1-sol@high', rows)
        self.assertEqual(rows['auto:llmproxy:codex:kimi-k3.1-pro@high']['compatibility'] if 'auto:llmproxy:codex:kimi-k3.1-pro@high' in rows
                         else rows['auto:llmproxy:codex:kimi-k3@high']['compatibility'], 'unverified')
        self.assertEqual([e['model'] for e in out['excluded']], ['gemini-embedding-001'])
        # `qwen-flash` resolves (alias) to the Qwen3 Flash snapshot row it serves
        self.assertEqual(rows['auto:llmproxy:codex:qwen3-flash-2025-07-28@high']['draws'], ['balance'])
        self.assertEqual(rows['auto:llmproxy:codex:zzz-proxy-model@high']['score_source'], 'unmeasured')

    def test_user_checkbox_overrides_default_both_ways(self):
        latest, old = 'auto:llmproxy:codex:gpt-6.1-sol@high', 'auto:llmproxy:codex:gpt-5.6-sol@high'
        ids = ['gpt-6.1-sol', 'gpt-5.6-sol']
        rows = ab.derive(proxy_accounts(), catalog('llmproxy', ids), NOW)['bundles']['llmproxy']
        self.assertEqual((rows[latest]['disabled'], rows[old]['disabled']), (False, True))
        prefs = {'accounts': {'llmproxy': {'bundles': {latest: {'disabled': True}, old: {'disabled': False}}}}}
        rows = ab.derive(proxy_accounts(), catalog('llmproxy', ids), NOW, overrides=prefs)['bundles']['llmproxy']
        self.assertEqual((rows[latest]['disabled'], rows[old]['disabled']), (True, False))

    def test_extra_effort_of_latest_model_is_checked(self):
        agy = REAL['accounts']['antigravity']
        acc = public({'antigravity': agy})
        provider = next(iter(agy['bundles'].values())).get('provider', 'antigravity')
        ids = ['claude-opus-5-5-low', 'claude-opus-5-5-high', 'claude-opus-5-5-xhigh', 'gemini-4-argon-high']
        out = ab.derive(acc, catalog(provider, ids), NOW)
        rows = out['bundles'].get('antigravity', {})
        self.assertEqual(list(rows), ['auto:antigravity:antigravity-resilient:claude-opus-5-5@xhigh'])
        bundle = rows['auto:antigravity:antigravity-resilient:claude-opus-5-5@xhigh']
        self.assertFalse(bundle['disabled'])  # another effort of the latest model is the same model
        self.assertEqual(bundle['draws'], agy['bundles']['agy_opus55_high']['draws'])

    def test_stale_then_expired(self):
        acc = proxy_accounts()
        bid = 'auto:llmproxy:codex:gpt-6.1-sol@high'
        failed = catalog('llmproxy', ['gpt-6.1-sol'], ok=False, checked=NOW - 3600)
        self.assertEqual(ab.derive(acc, failed, NOW, seen={bid: NOW - 3600})['bundles']['llmproxy'][bid]['availability'], 'stale')
        old = ab.derive(acc, failed, NOW, seen={bid: NOW - 8 * 86400})['bundles']['llmproxy'][bid]
        self.assertEqual(old['availability'], 'expired')
        self.assertTrue(old['disabled'])

    def test_superseded_unchecked_latest_and_unknown_checked(self):
        spec = REAL['accounts']['claude']
        provider = next(iter(spec['bundles'].values())).get('provider', 'claude')
        ids = ['claude-haiku-4-5', 'claude-haiku-5-5', 'claude-opus-4-8', 'claude-opus-9-1', 'claude-sonnet-5-5-xhigh']
        rows = ab.derive(public({'claude': spec}), catalog(provider, ids), NOW)['bundles']['claude']
        state = {b['launch_model']: b['disabled'] for b in rows.values()}
        self.assertEqual(state, {'claude-haiku-4-5': True, 'claude-opus-4-8': True,          # superseded in public data
                                 'claude-haiku-5-5': False, 'claude-sonnet-5-5-xhigh': False,  # latest
                                 'claude-opus-9-1': False})                                  # newer than the data
        self.assertFalse([key for b in rows.values() for key in b if 'reason' in key and 'compatibility' not in key])

    def test_default_comes_from_data_not_names(self):
        spec = REAL['accounts']['claude']
        provider = next(iter(spec['bundles'].values())).get('provider', 'claude')
        without = {**public({'claude': spec}), 'superseded': {}}
        rows = ab.derive(without, catalog(provider, ['claude-haiku-4-5']), NOW)['bundles']['claude']
        self.assertFalse(rows['auto:claude:claude:claude-haiku-4-5@high']['disabled'])
        marked = {**without, 'superseded': {'claude-haiku-5-5': {'by': 'x', 'basis': 'test'}}}
        rows = ab.derive(marked, catalog(provider, ['claude-haiku-5-5']), NOW)['bundles']['claude']
        self.assertTrue(rows['auto:claude:claude:claude-haiku-5-5@high']['disabled'])

    def test_superseded_data_points_at_latest_known_models(self):
        table = json.loads((account_fleet.REFERENCES / 'accounts.json').read_text(encoding='utf-8'))
        known = set(table['models']) | set(table['aliases'])
        for old, entry in table['superseded'].items():
            with self.subTest(old=old):
                self.assertEqual(set(entry), {'by', 'basis'})
                self.assertIn(entry['by'], known)
                self.assertNotIn(entry['by'], table['superseded'])
                self.assertTrue(entry['basis'].strip())
        self.assertEqual(table['superseded'], REAL['superseded'])

    def test_merge_feeds_allocator(self):
        out = ab.derive(proxy_accounts(), catalog('llmproxy', ['zzz-unknown-9']), NOW)
        merged = ab.merge_into(proxy_accounts(), out)
        flat = account_fleet.bundles(merged)
        bid = 'auto:llmproxy:codex:zzz-unknown-9@high'
        self.assertIn(bid, flat)
        self.assertEqual(quota_pools.bundle_pools(flat[bid], merged), ['balance'])
        self.assertNotIn('zzz-unknown-9', merged['models'])     # no row is invented for an unmeasured name


class SeenPersistence(unittest.TestCase):
    def test_seen_roundtrip_and_prune(self):
        import tempfile
        with tempfile.TemporaryDirectory() as d:
            path = Path(d) / 'sub/seen.json'
            self.assertEqual(ab.read_seen(path), {})
            ab.write_seen(path, {'a': NOW, 'old': NOW - 40 * 86400}, now=NOW)
            self.assertEqual(ab.read_seen(path), {'a': NOW})
            path.write_text('not json')
            self.assertEqual(ab.read_seen(path), {})


class SharedHooks(unittest.TestCase):
    def test_disabled_bundle_gives_neutral_exclusion(self):
        # String `disabled` values are rejected at load (test_router_data_models); a boolean one excludes neutrally.
        from datetime import datetime, timezone
        merged = json.loads(json.dumps(REAL))
        owner, bid = next((o, b) for o, s in merged['accounts'].items() for b in (s.get('bundles') or {}))
        merged['accounts'][owner]['bundles'][bid].update(disabled=True, discovery_unavailable=True)
        task = {'work_kind': 'code_implementation', 'difficulty': 'routine', 'needs': {'local_only': True}}
        row = next(c for c in allocator.plan(task, {'read_ok': True, 'accounts': {}}, datetime.now(timezone.utc),
                                             accounts=merged)['ranking'] if c['id'] == bid)
        self.assertIn('unchecked in model management', row['excluded'])
        self.assertTrue(all(isinstance(e, str) for e in row['excluded']))

    def test_harness_visual_capability(self):
        # File-based visual work (the router's only kind) reaches multimodal models on agy via read_file (probe 2026-10-28).
        self.assertTrue(account_fleet.harness_accepts_visual('antigravity-resilient', 'claude-opus-5-5'))
        self.assertTrue(account_fleet.harness_accepts_visual('antigravity-resilient', 'gemini-4-argon-high'))
        self.assertFalse(account_fleet.harness_accepts_visual('antigravity', 'claude-opus-5-5', needs_attachment=True))
        self.assertTrue(account_fleet.harness_accepts_visual('claude', 'claude-opus-5-5', needs_attachment=True))
        # Non-multimodal models are excluded by their own model row, not the harness.
        self.assertFalse(account_fleet.models_table(account_fleet.load_accounts()).get('gpt-oss-120b', {}).get('visual'))


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