Skip to content

amazon-science/ammo / ai_cli_session/.codex/skills/ammo

Profile and optimize GPU kernels for vLLM inference on NVIDIA GPUs. Use when targeting a specific model, hardware, dtype, parallelism, and workload to improve latency.

FileKindSize
RUNTIME.mdmarkdown4.9 KB
SKILL.mdskill md18.5 KB
agents/ammo-auditor.mdmarkdown9.1 KB
agents/ammo-champion.mdmarkdown9.6 KB
agents/ammo-delegate.mdmarkdown3.2 KB
agents/ammo-implementer.mdmarkdown13.8 KB
agents/ammo-investigator.mdmarkdown4.0 KB
agents/ammo-report.mdmarkdown2.9 KB
agents/ammo-researcher.mdmarkdown10.3 KB
agents/ammo-resolver.mdmarkdown4.4 KB
agents/ammo-transcript-monitor.mdmarkdown7.8 KB
agents/openai.yamlexecutablescript313 B
data/ATTRIBUTION.mdmarkdown1.4 KB
data/gsm8k_full.jsonexecutablescript735.5 KB
data/gsm8k_subset.jsonexecutablescript116.8 KB
eval/EVAL-SKILL.mdexecutablescript21.8 KB
eval/agents/transcript_grader.mdexecutablescript18.0 KB
eval/causal/__init__.pyexecutablescript137 B
eval/causal/agents/causal_analyzer.mdexecutablescript10.5 KB
eval/causal/build_dag.pyexecutablescript21.6 KB
eval/causal/diff_versions.pyexecutablescript38.5 KB
eval/causal/extract_events.pyexecutablescript36.3 KB
eval/causal/generate_postmortem.pyexecutablescript17.0 KB
eval/causal/score_nodes.pyexecutablescript21.5 KB
eval/causal/templates/narrative_template.mdexecutablescript472 B
eval/causal/templates/viz_template.htmlexecutablescript9.5 KB
eval/causal/tests/__init__.pyexecutablescript151 B
eval/causal/tests/conftest.pyexecutablescript448 B
eval/causal/tests/fixtures/sample_session.jsonlexecutablescript10.4 KB
eval/causal/tests/fixtures/sample_session_data.jsonexecutablescript3.4 KB
eval/causal/tests/fixtures/sample_snapshot.jsonexecutablescript2.5 KB
eval/causal/tests/test_build_dag.pyexecutablescript2.7 KB
eval/causal/tests/test_diff_versions.pyexecutablescript13.5 KB
eval/causal/tests/test_extract_events.pyexecutablescript3.7 KB
eval/causal/tests/test_generate_postmortem.pyexecutablescript3.1 KB
eval/causal/tests/test_score_nodes.pyexecutablescript3.3 KB
eval/scripts/aggregate_versions.pyexecutablescript15.2 KB
eval/scripts/archive_run.pyexecutablescript9.1 KB
eval/scripts/codex_session.pyexecutablescript10.6 KB
eval/scripts/generate_dashboard.pyexecutablescript5.3 KB
eval/scripts/parse_artifacts.pyexecutablescript48.1 KB
eval/scripts/parse_session_logs.pyexecutablescript51.3 KB
eval/scripts/rescore_archived.pyexecutablescript5.5 KB
eval/scripts/score_campaign.pyexecutablescript43.8 KB
eval/scripts/snapshot_changes.pyexecutablescript11.1 KB
eval/scripts/verify_citations.pyexecutablescript8.8 KB
eval/tests/test_dashboard_bugs.pyexecutablescript8.8 KB
eval/tests/test_parse_session_logs.pyexecutablescript3.9 KB
eval/tests/test_parse_session_logs_round_inference.pyexecutablescript11.0 KB
eval/tests/test_score_campaign_diluted.pyexecutablescript9.4 KB
eval/viewer/dashboard_template.htmlexecutablescript15.1 KB
instrumentation/sitecustomize.pyexecutablescript3.6 KB
orchestration/audit-protocol.mdmarkdown9.3 KB
orchestration/debate-protocol.mdmarkdown11.2 KB
orchestration/integration-logic.mdmarkdown10.3 KB
orchestration/parallel-tracks.mdmarkdown8.9 KB
references/artifact-layout.mdexecutablescript22.4 KB
references/audit-invariants.mdmarkdown10.6 KB
references/champion-common-patterns.mdmarkdown3.4 KB
references/crossover-probing.mdexecutablescript4.7 KB
references/cudagraph-safety.mdmarkdown2.7 KB
references/debate-rules.mdmarkdown4.7 KB
references/debate-scoring-rubric.mdexecutablescript16.7 KB
references/e2e-delta-math.mdexecutablescript17.9 KB
references/e2e-latency-guide.mdexecutablescript9.6 KB
references/fusion-feasibility-heuristics.mdmarkdown5.6 KB
references/gpu-pool.mdexecutablescript5.4 KB
references/impl-track-rules.mdexecutablescript13.8 KB
references/nsys-profiling-guide.mdmarkdown9.8 KB
references/optimization-categories.mdexecutablescript11.0 KB
references/shutdown-protocol.mdexecutablescript3.1 KB
references/technology-selection.mdmarkdown5.0 KB
references/torch-compile-contract.mdmarkdown13.8 KB
references/validation-defaults.mdexecutablescript34.2 KB
references/workload-invocation.mdexecutablescript4.9 KB
references/writing-style.mdexecutablescript6.9 KB
scripts/ammo_state.pyexecutablescript142.0 KB
scripts/artifact_layout.jsonconfig16.3 KB
scripts/check_projection_accuracy.pyexecutablescript11.7 KB
scripts/create_evidence_template.pyexecutablescript9.7 KB
scripts/create_worktree_with_build.shexecutablescript10.2 KB
scripts/generate_validation_report.pyexecutablescript35.7 KB
scripts/gpu_reservation.pyexecutablescript27.1 KB
scripts/hook_cmd_classify.pyscript13.3 KB
scripts/mine_trace.pyscript29.4 KB
scripts/monitor_queue_ack.pyexecutablescript6.1 KB
scripts/ncu_sanity.shexecutablescript5.2 KB
scripts/ncu_sanity_driver.pyexecutablescript8.5 KB
scripts/new_target.pyexecutablescript22.0 KB
scripts/preflight_vllm_api.pyexecutablescript12.3 KB
scripts/reconcile_track_state.pyexecutablescript15.8 KB
scripts/remove_worktree_cleanup.shexecutablescript1.1 KB
scripts/resolve_codex_transcript.pyexecutablescript3.6 KB
scripts/run_vllm_bench_latency_sweep.pyexecutablescript249.6 KB
scripts/transcript_filter.pyexecutablescript38.4 KB
scripts/transitions.jsonexecutablescript1.5 KB
scripts/verify_validation_gates.pyexecutablescript88.8 KB
tests/agents/test-champion.mdexecutablescript20.4 KB
tests/agents/test-impl-champion.mdexecutablescript14.3 KB
tests/agents/test-implementer.mdexecutablescript15.8 KB
tests/agents/test-orchestrator.mdexecutablescript33.8 KB
tests/agents/test-researcher.mdexecutablescript21.0 KB
tests/agents/test-transcript-monitor.mdexecutablescript13.4 KB
tests/fixtures/diluted_pass/legacy_no_phase.golden.mdmarkdown1.1 KB
tests/fixtures/diluted_pass/legacy_no_phase.golden.summary.jsonconfig582 B
tests/fixtures/diluted_pass/legacy_no_phase.jsonconfig400 B
tests/fixtures/diluted_pass/legacy_scalar_phase.golden.mdmarkdown2.0 KB
tests/fixtures/diluted_pass/legacy_scalar_phase.golden.summary.jsonconfig1.0 KB
tests/fixtures/diluted_pass/legacy_scalar_phase.jsonconfig626 B
tests/fixtures/mining/real_campaign_bottleneck_analysis.mdmarkdown20.7 KB
tests/run_all.shexecutablescript1.6 KB
tests/scripts/test_transcript_filter.pyexecutablescript41.1 KB
tests/test_agent_runtime_contracts.pyexecutablescript1.8 KB
tests/test_ammo_state.pyexecutablescript71.7 KB
tests/test_artifact_layout_manifest.pyscript11.6 KB
tests/test_audit_started.pyscript18.2 KB
tests/test_correctness_comparator.pyscript12.6 KB
tests/test_diluted_pass.pyscript24.4 KB
tests/test_drift_compat.pyscript5.1 KB
tests/test_evidence_freshness.pyexecutablescript5.6 KB
tests/test_fail_closed.pyexecutablescript14.7 KB
tests/test_gpu_reservation.pyexecutablescript24.8 KB
tests/test_gpu_reservation_session_id.pyexecutablescript11.2 KB
tests/test_guidance_semantic_contract.pyscript24.9 KB
tests/test_hook_cmd_classify_parity.pyscript11.7 KB
tests/test_hook_semantics.pyexecutablescript95.3 KB
tests/test_mine_trace.pyscript24.2 KB
tests/test_mining_invalidated_schema.pyexecutablescript9.4 KB
tests/test_new_target_dp_ep.pyexecutablescript7.4 KB
tests/test_new_target_v2_scaffold.pyexecutablescript13.1 KB
tests/test_parse_artifacts.pyexecutablescript3.0 KB
tests/test_policy_convergence.pyscript797 B
tests/test_preflight_vllm_api.pyscript13.3 KB
tests/test_projection_accuracy_v2.pyexecutablescript4.1 KB
tests/test_reconcile_track_state.pyexecutablescript18.2 KB
tests/test_resolve_codex_transcript.pyexecutablescript3.1 KB
tests/test_state_schema_semantics.pyexecutablescript7.6 KB
tests/test_status_set_sync.pyexecutablescript9.1 KB
tests/test_sweep_baseline_from_arm.pyscript11.0 KB
tests/test_sweep_decode_capture.pyexecutablescript31.8 KB
tests/test_sweep_dp.pyexecutablescript45.4 KB
tests/test_sweep_fresh_cache.pyscript5.5 KB
tests/test_sweep_profiler_guard.pyscript22.6 KB
tests/test_sweep_real_prompts.pyscript20.1 KB
tests/test_sweep_refactor.pyexecutablescript37.6 KB
tests/test_sweep_round_slot.pyexecutablescript7.4 KB
tests/test_validation_report_phase_triage.pyexecutablescript10.0 KB
tests/test_validation_report_v2.pyexecutablescript6.2 KB
tests/test_verify_validation_gates.pyexecutablescript52.9 KB
tests/test_workload_matrix.pyexecutablescript19.3 KB

tests/test_status_set_sync.py

View on GitHub
#!/usr/bin/env python3
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: CC-BY-NC-4.0
"""Z2-T3 / P4#2: status/verdict set sync-oracle (assertion-only).

This file IS the deliverable — it edits NO production file. It pins the
load-bearing status/verdict sets that are duplicated across four sources and
fails loudly the moment any one of them drifts:

  - schema track `status` enum + `verdict` enum (state.schema.json)
  - transitions.json `track_terminal_statuses` / `track_passing_statuses` /
    `integration_terminal_statuses` / `integration_ship_statuses` /
    `terminal_statuses`
  - ammo_state.py, which must READ those sets from transitions.json and hold no
    inline copy of them
  - generate_validation_report.py's passing-COMPAT tuple
    `("PASS", "GATING_REQUIRED", "GATED_PASS")`

All are located by CONTENT (enum-signature / regex over source), never by line
number, so they survive code motion. The test only READS frozen files; a guard
asserts it never mutates them.

Run: python3 -m pytest tests/test_status_set_sync.py -q
"""

from __future__ import annotations

import json
import re
from pathlib import Path

_HERE = Path(__file__).resolve()
_SCRIPTS_DIR = _HERE.parent.parent / "scripts"
_CODEX_DIR = _HERE.parents[3]  # .../ai_cli_session/.codex
_SCHEMA_PATH = _CODEX_DIR / "schemas" / "state.schema.json"
_TRANSITIONS_PATH = _SCRIPTS_DIR / "transitions.json"
_ENGINE_PATH = _SCRIPTS_DIR / "ammo_state.py"
_REPORT_PATH = _SCRIPTS_DIR / "generate_validation_report.py"


# ─────────────────────────────────────────────
# Content-keyed locators (no line pins)
# ─────────────────────────────────────────────

def _all_enums(node, acc):
    """Recursively collect every `enum` array (as a list) in a JSON-schema dict."""
    if isinstance(node, dict):
        if isinstance(node.get("enum"), list):
            acc.append(node["enum"])
        for v in node.values():
            _all_enums(v, acc)
    elif isinstance(node, list):
        for v in node:
            _all_enums(v, acc)
    return acc


def _schema_status_enum():
    """The track-status enum = the enum array containing BOTH 'IN_PROGRESS' and
    'GPU_BLOCKED' (uniquely identifies parallel_tracks.tracks.*.status)."""
    schema = json.loads(_SCHEMA_PATH.read_text(encoding="utf-8"))
    matches = [set(e) for e in _all_enums(schema, []) if "IN_PROGRESS" in e and "GPU_BLOCKED" in e]
    assert len(matches) == 1, "expected exactly one status enum, found %d" % len(matches)
    return matches[0]


def _schema_verdict_enum():
    """The verdict enum = the enum array containing BOTH 'GATING_REQUIRED' and
    null (None). 'GATING_REQUIRED'+null uniquely separates it from the
    classification enum (lossless/lossy/null, no GATING_REQUIRED) and from the
    status enum (no null)."""
    schema = json.loads(_SCHEMA_PATH.read_text(encoding="utf-8"))
    matches = [set(e) for e in _all_enums(schema, []) if "GATING_REQUIRED" in e and None in e]
    assert len(matches) == 1, "expected exactly one verdict enum, found %d" % len(matches)
    return matches[0]


def _set_from_quoted(text):
    """Pull every double-quoted token out of a matched literal into a set."""
    return set(re.findall(r'"([^"]+)"', text))


# Every status set the engine must read from transitions.json, paired with a
# whitespace-tolerant regex that matches an inline copy of the same members.
_ENGINE_SET_KEYS = {
    "track_terminal_statuses": r'"PASS"\s*,\s*"GATED_PASS"\s*,\s*"FAIL"',
    "track_passing_statuses": r'"PASS"\s*,\s*"GATED_PASS"',
    "terminal_statuses": r'"campaign_complete"\s*,\s*"campaign_exhausted"',
    "integration_terminal_statuses": r'"completed"\s*,\s*"exhausted"\s*,\s*"failed"',
    "integration_ship_statuses": r'"combined"\s*,\s*"single_pass"\s*,\s*"gated_pass"',
}


def _transitions():
    return json.loads(_TRANSITIONS_PATH.read_text(encoding="utf-8"))


def _engine_inline_status_literals():
    """Content-grep ammo_state.py for any inline copy of a transitions status set.
    Returns the offending transitions keys (empty when the engine reads them all)."""
    src = _ENGINE_PATH.read_text(encoding="utf-8")
    return sorted(key for key, pattern in _ENGINE_SET_KEYS.items() if re.search(pattern, src))


def _report_passing_compat_tuple():
    """Content-grep generate_validation_report.py for the passing-COMPAT tuple
    ("PASS", "GATING_REQUIRED", "GATED_PASS") (whitespace-tolerant)."""
    src = _REPORT_PATH.read_text(encoding="utf-8")
    m = re.search(r'\(\s*"PASS"\s*,\s*"GATING_REQUIRED"\s*,\s*"GATED_PASS"\s*\)', src)
    assert m is not None, "report passing-compat tuple not found"
    return _set_from_quoted(m.group(0))


# ─────────────────────────────────────────────
# Tests
# ─────────────────────────────────────────────

def test_schema_status_enum_exact():
    assert _schema_status_enum() == {
        "IN_PROGRESS", "PASS", "GATING_REQUIRED", "GATED_PASS", "FAIL", "GPU_BLOCKED"
    }


def test_schema_verdict_enum_exact():
    assert _schema_verdict_enum() == {
        "PASS", "GATING_REQUIRED", "GATED_PASS", "FAIL", None
    }


def test_transitions_terminal_set_and_subset_of_schema():
    terminal = set(_transitions()["track_terminal_statuses"])
    assert terminal == {"PASS", "GATED_PASS", "FAIL"}
    # terminal ⊆ schema status enum
    assert terminal <= _schema_status_enum()


def test_engine_reads_every_status_set_from_transitions():
    """transitions.json is the SOLE owner: the engine looks every status set up by
    key and keeps no inline literal that can drift out of sync (the gated_pass
    defect, where one semantic change needed three hand edits)."""
    src = _ENGINE_PATH.read_text(encoding="utf-8")
    transitions = _transitions()
    for key in _ENGINE_SET_KEYS:
        assert key in transitions, "transitions.json lost status set %s" % key
        assert '["%s"]' % key in src, "ammo_state.py does not read transitions[%r]" % key
    assert _engine_inline_status_literals() == [], (
        "ammo_state.py hardcodes status sets that transitions.json owns: %s"
        % _engine_inline_status_literals()
    )


def test_report_passing_compat_subset_of_verdict_and_distinct_from_terminal():
    compat = _report_passing_compat_tuple()
    assert compat == {"PASS", "GATING_REQUIRED", "GATED_PASS"}
    # passing-compat ⊆ verdict enum (compare on the string members; verdict enum
    # also carries None, which the tuple legitimately omits)
    verdict_strings = {v for v in _schema_verdict_enum() if isinstance(v, str)}
    assert compat <= verdict_strings
    # explicitly a DIFFERENT set from the terminal set: includes GATING_REQUIRED,
    # excludes FAIL.
    terminal = set(_transitions()["track_terminal_statuses"])
    assert compat != terminal
    assert "GATING_REQUIRED" in compat and "GATING_REQUIRED" not in terminal
    assert "FAIL" in terminal and "FAIL" not in compat


def test_passing_set_subset_of_terminal():
    """transitions track_passing_statuses ⊆ track_terminal_statuses (a passing
    status is always terminal)."""
    transitions = _transitions()
    passing = set(transitions["track_passing_statuses"])
    terminal = set(transitions["track_terminal_statuses"])
    assert passing == {"PASS", "GATED_PASS"}
    assert passing <= terminal


def test_integration_ship_statuses_preserve_lowercase_gated_pass():
    transitions = json.loads(_TRANSITIONS_PATH.read_text(encoding="utf-8"))
    assert set(transitions["integration_ship_statuses"]) == {
        "combined",
        "single_pass",
        "gated_pass",
    }


def test_engine_has_no_operational_claude_primitives():
    source = _ENGINE_PATH.read_text(encoding="utf-8")
    for stale in (
        "SendMessage",
        "shutdown_approved",
        "TeamCreate",
        "TeamDelete",
        ".claude/",
        "close_agent",
        "send_input",
    ):
        assert stale not in source


def test_jsonschema_importable():
    """CI-insurance: the 90+/98 state-validate baseline asserts jsonschema-specific
    error strings, and P4#6 fail-closed is DEFAULT-ON — both silently degrade if
    jsonschema vanishes from the env. This cheap assertion surfaces that loudly."""
    import jsonschema  # noqa: F401


def test_oracle_reads_only_no_writes():
    """Guard: this oracle must never mutate the frozen files it inspects. Snapshot
    (size, mtime_ns) before running every locator, then re-check after."""
    frozen = [_SCHEMA_PATH, _TRANSITIONS_PATH, _ENGINE_PATH, _REPORT_PATH]
    before = {p: (p.stat().st_size, p.stat().st_mtime_ns) for p in frozen}
    # exercise every read path
    _schema_status_enum()
    _schema_verdict_enum()
    _engine_inline_status_literals()
    _report_passing_compat_tuple()
    json.loads(_TRANSITIONS_PATH.read_text(encoding="utf-8"))
    after = {p: (p.stat().st_size, p.stat().st_mtime_ns) for p in frozen}
    assert before == after, "sync-oracle must not modify frozen files"
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall