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/model_latch.py

View on GitHub
"""Models a launch reported as not existing, latched out of routing until they are seen again.

Contract: a definitive Paseo create failure whose structured error code (`failure_code`, the provider's own
`ProviderActionError` code as the daemon recorded it) says the model does not exist latches that account's model in
<state dir>/model-unavailable.json. Only the code decides; no error text is read or stored. A latch holds until the
first of:
  - a worker on that account and model starts after the latch (registry observe),
  - discovery (the tray's model-catalog.json) lists the model in a probe newer than the latch,
  - RETRY_HOURS pass, after which the next roll may pick the model again and so re-probes it,
  - the user clears it (`model_latch.py --clear <account>/<model>`).
Settings never hold a latch: the user's model checkboxes stay as they were.
"""
from datetime import datetime, timedelta, timezone
import json
import os
from pathlib import Path

import account_state
import override_store

# The same re-probe period as a latched account (account_state.LATCH_RETRY_HOURS).
RETRY_HOURS = account_state.LATCH_RETRY_HOURS
# Provider error codes that mean "this model does not exist on this provider", compared case-insensitively.
# INVALID_MODEL: paseo-antigravity-resilient's ProviderActionError when agy does not recognize the model.
MODEL_UNAVAILABLE_CODES = frozenset(('invalid_model', 'model_not_found', 'unknown_model', 'unsupported_model'))
FILE = 'model-unavailable.json'


def enabled():
    return os.environ.get('ROUTER_MODEL_LATCH', '').strip().lower() != 'off'


def store_path():
    override = os.environ.get('ROUTER_MODEL_LATCH', '').strip()
    if override and override.lower() != 'off':
        return Path(override)
    return Path(os.environ.get('ROUTER_STATE_DIR') or Path.home() / '.agent-compass') / FILE


def catalog_path():
    return Path(os.environ.get('ROUTER_STATE_DIR') or Path.home() / '.agent-compass') / 'model-catalog.json'


def _time(value):
    try:
        moment = datetime.fromisoformat(str(value).replace('Z', '+00:00'))
    except (TypeError, ValueError):
        return None
    return moment if moment.tzinfo else moment.replace(tzinfo=timezone.utc)


def _read(path):
    try:
        doc = json.loads(override_store.retry_denied(lambda: Path(path).read_text(encoding='utf-8')))
    except (FileNotFoundError, ValueError):
        return {'models': {}}
    return doc if isinstance(doc, dict) and isinstance(doc.get('models'), dict) else {'models': {}}


def launch_model(bundle):
    return (bundle or {}).get('launch_model') or (bundle or {}).get('model')


def key(account, model):
    return f'{account}/{model}'


def means_unavailable(code):
    return isinstance(code, str) and code.strip().lower() in MODEL_UNAVAILABLE_CODES


def record(bundle, code, *, at=None, source=None, path=None):
    """Latch the bundle's model when `code` says it does not exist. Returns the entry, or None."""
    account, model = (bundle or {}).get('account'), launch_model(bundle)
    if not enabled() or not means_unavailable(code) or not isinstance(account, str) or not isinstance(model, str):
        return None
    at = at or datetime.now(timezone.utc)
    path = path or store_path()
    entry = {'account': account, 'provider': bundle.get('provider') or account, 'model': model,
             'code': code.strip(), 'observed_at': at.isoformat(), 'source': source}
    with override_store.locked(path):
        doc = _read(path)
        doc['models'][key(account, model)] = entry
        override_store.write(path, doc)
    return entry


def retry_at(entry):
    observed = _time((entry or {}).get('observed_at'))
    return observed + timedelta(hours=RETRY_HOURS) if observed else None


def redetected(entry, catalog):
    """Discovery listed the model in a probe made after the latch."""
    observed = _time(entry.get('observed_at'))
    probe = ((catalog or {}).get('providers') or {}).get(entry.get('provider'))
    if not observed or not isinstance(probe, dict) or not probe.get('ok') or probe.get('type') == 'static':
        return False
    checked = probe.get('checked_at')
    if not isinstance(checked, (int, float)) or isinstance(checked, bool) or checked <= observed.timestamp():
        return False
    return any((m.get('id') if isinstance(m, dict) else m) == entry.get('model') for m in probe.get('models') or [])


def _catalog():
    try:
        doc = json.loads(catalog_path().read_text(encoding='utf-8'))
    except (OSError, ValueError):
        return {}
    return doc if isinstance(doc, dict) else {}


def active(*, now=None, path=None, catalog=None):
    """Latches still in effect, keyed `account/model`. Reading never writes: an outlived latch is only ignored."""
    if not enabled():
        return {}
    now = now or datetime.now(timezone.utc)
    path = path or store_path()
    if not path.exists():
        return {}
    try:
        entries = _read(path)['models']
    except PermissionError:
        return {}
    catalog = _catalog() if catalog is None else catalog
    return {k: v for k, v in entries.items()
            if isinstance(v, dict) and (retry_at(v) or now) > now and not redetected(v, catalog)}


def entry_for(bundle, entries):
    if not entries:
        return None
    return entries.get(key((bundle or {}).get('account'), launch_model(bundle)))


def retry_text(entry):
    when = retry_at(entry)
    return when.isoformat(timespec='minutes') if when else f'after {RETRY_HOURS:g}h'


def reason(bundle, entries):
    """Exclusion text for a latched bundle, else None."""
    entry = entry_for(bundle, entries)
    if not entry:
        return None
    return (f"model launch failed: unavailable ({entry.get('code')}); next retry at {retry_text(entry)}, "
            f"or clear with `model_latch.py --clear {key(entry.get('account'), entry.get('model'))}`")


def warnings(entries, allowed=None):
    """One `plan`/`roll` line per latched model. `allowed(account)` skips accounts this host does not use."""
    return [f"{k}: model launch failed: unavailable ({v.get('code')}); excluded from dispatch until "
            f"{retry_text(v)}, a successful start, or discovery lists it again"
            for k, v in sorted((entries or {}).items()) if allowed is None or allowed(v.get('account'))]


def clear(account, model=None, *, launched_at=None, path=None):
    """Drop latches on `account` (one `model`, or all). With `launched_at`, only latches older than that launch: a
    start that began before the failure says nothing about it. No write when there is nothing to drop."""
    path = path or store_path()
    if not enabled() or not isinstance(account, str) or not path.exists():
        return False
    launched = _time(launched_at) if launched_at is not None else None
    with override_store.locked(path):
        doc = _read(path)
        keys = [k for k, v in doc['models'].items() if isinstance(v, dict) and v.get('account') == account
                and (model is None or v.get('model') == model)
                and (launched_at is None or (launched and (_time(v.get('observed_at')) or launched) < launched))]
        if not keys:
            return False
        for k in keys:
            doc['models'].pop(k)
        override_store.write(path, doc)
    return True


if __name__ == '__main__':
    import argparse
    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
    parser.add_argument('--clear', metavar='ACCOUNT/MODEL', help='Clear one latched model (or ACCOUNT for all) by hand')
    args = parser.parse_args()
    if args.clear:
        account, _, model = args.clear.partition('/')
        clear(account, model or None)
    print(json.dumps(_read(store_path())['models'], ensure_ascii=False, indent=2))
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