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_state_schema_semantics.py

View on GitHub
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: CC-BY-NC-4.0
"""Task-2 regressions for the merged Codex AMMO state schema."""

from __future__ import annotations

import json
from pathlib import Path

from jsonschema import Draft202012Validator


SCHEMA_PATH = Path(__file__).resolve().parents[3] / "schemas" / "state.schema.json"


def _schema() -> dict:
    return json.loads(SCHEMA_PATH.read_text(encoding="utf-8"))


def _campaign_properties() -> dict:
    return _schema()["properties"]["campaign"]["properties"]


def _round_properties() -> dict:
    return _campaign_properties()["rounds"]["items"]["properties"]


def _track_properties() -> dict:
    return _round_properties()["parallel_tracks"]["properties"]["tracks"]["additionalProperties"]["properties"]


def _audit_gate_properties(stage: str) -> dict:
    return _round_properties()["audit"]["properties"][stage]


def test_new_campaign_floor_is_half_percent_without_deflation_contract():
    assert "4.2" in _campaign_properties()["schema_version"]["enum"]
    config = _campaign_properties()["config"]
    assert config["properties"]["min_e2e_improvement_pct"]["default"] == 0.5
    assert "lossless_e2e_deflation_factor" not in config["required"]
    assert "lossy_quant_e2e_deflation_factor" not in config["required"]
    assert "lossless_e2e_deflation_factor" not in config["properties"]
    assert "lossy_quant_e2e_deflation_factor" not in config["properties"]
    legacy_floor = config["properties"]["debate_elimination_score_floor"]["description"]
    assert "LEGACY" in legacy_floor
    assert "EV_pct < min_e2e_improvement_pct" in legacy_floor
    assert "backward compatibility" in legacy_floor


def test_round_schema_adds_mining_invalidation_and_diluted_rollup():
    props = _round_properties()
    assert props["mining_invalidated"]["type"] == "boolean"
    assert props["mining_invalidated_reason"]["type"] == ["string", "null"]
    diluted_tracks = props["diluted_tracks"]
    assert diluted_tracks["type"] == ["array", "null"]
    assert diluted_tracks["items"]["properties"]["op_id"]["type"] == "string"


def test_track_schema_preserves_codex_fields_and_adds_diluted_marker():
    props = _track_properties()
    assert props["diluted"]["type"] == ["boolean", "null"]
    assert "SKIPPED" in props["gate_5_1a"]["enum"]
    assert "SKIPPED" in props["gate_5_2"]["enum"]
    for field in (
        "gate_5_1a_skip_reason",
        "gate_5_2_skip_reason",
        "branch",
        "worktree_path",
        "evidence_path",
        "kill_criteria_results",
        "completed_at",
        "implementer_agent",
        "implementer_rollout_id",
        "monitor_agent",
        "monitor_evidence_path",
        "monitor_offsets_path",
        "monitor_summary_path",
    ):
        assert field in props
    tracks = _round_properties()["parallel_tracks"]["properties"]["tracks"]
    assert tracks["propertyNames"]["pattern"] == "^[A-Za-z0-9_-]+$"
    boundary = props["gate_5_2_boundary"]
    assert "e2e_equivalent_improvement_pct" in boundary["required"]


def test_selected_candidate_preserves_winning_proposal_locator():
    selected = _round_properties()["debate"]["properties"]["selected_candidates"]["items"]

    assert "proposal_file" in selected["properties"]
    assert "rounds/{N}/debate/proposals/" in selected["properties"]["proposal_file"][
        "description"
    ]
    assert "proposal_file" in selected["required"]


def test_selected_candidate_carries_optional_display_name():
    """The lead mints a short display name with each op_id; the op_id stays the
    key. Optional for back-compat: pre-4.2 selected_candidates omit it."""
    selected = _round_properties()["debate"]["properties"]["selected_candidates"]["items"]

    name = selected["properties"]["name"]
    assert name["type"] == "string"
    assert name["minLength"] == 1
    assert "name" not in selected["required"]


def test_selected_candidate_supports_typed_contingent_host_spike():
    selected = _round_properties()["debate"]["properties"]["selected_candidates"][
        "items"
    ]

    assert selected["properties"]["selection_mode"]["enum"] == [
        "ordinary",
        "contingent_host_spike",
    ]
    obligations = selected["properties"]["stage_4_validation_obligations"]
    assert "production_boundary_spike" in obligations["items"]["enum"]


def test_mining_schema_distinguishes_f_e2e_from_f_decode():
    mining = _round_properties()["bottleneck_mining"]["properties"]

    assert "decode wall time" in mining["top_f_decode_pct"]["description"]
    assert "total E2E wall time" in mining["top_f_e2e_pct"]["description"]
    assert "Stage 7 stop check" in mining["top_addressable_e2e_pct"]["description"]


def test_shipped_optimization_can_record_diluted():
    item = _campaign_properties()["shipped_optimizations"]["items"]
    assert item["properties"]["diluted"]["type"] == ["boolean", "null"]


def test_completed_mining_is_not_globally_deadlocking_schema():
    mining = _round_properties()["bottleneck_mining"]
    assert "allOf" not in mining


def test_auditor_escalation_accepts_track_array_scope():
    spec = _campaign_properties()["auditor_escalation"]
    payload = {
        "stage": "4_5_parallel_tracks",
        "round": 2,
        "reason": "three audit cycles exhausted",
        "verdict_files": ["rounds/2/audits/stage_45.md"],
        "scope": ["op001", "op007"],
        "resumable_task": "fix and re-audit quarantined tracks",
    }
    assert list(Draft202012Validator(spec).iter_errors(payload)) == []


def test_auditor_escalation_accepts_campaign_scope_and_rejects_other_string():
    spec = _campaign_properties()["auditor_escalation"]
    payload = {
        "stage": "6_integration",
        "round": 3,
        "reason": "campaign-wide invariant failed",
        "verdict_files": ["rounds/3/audits/stage_67.md"],
        "scope": "campaign",
        "resumable_task": "resolve the campaign blocker and re-audit",
    }
    validator = Draft202012Validator(spec)
    assert list(validator.iter_errors(payload)) == []
    payload["scope"] = "op001"
    assert list(validator.iter_errors(payload))


def test_schema_version_enum_is_unchanged_by_the_audit_start_fields():
    # started_at/cycle are additive on the existing 4.2 gate objects. A new
    # version entry would force every consumer to learn a version it does not
    # need.
    assert _campaign_properties()["schema_version"]["enum"] == [
        "3.0", "4.0", "4.1", "4.2"
    ]


def test_audit_gates_carry_optional_started_at_and_cycle():
    for stage in ("stage_2", "stage_67"):
        gate = _audit_gate_properties(stage)
        props = gate["properties"]

        started = props["started_at"]
        assert started["type"] == ["string", "null"]
        assert started["format"] == "date-time"
        assert "ammo-audit-start-stamp.sh" in started["description"]

        cycle = props["cycle"]
        assert cycle["type"] == ["integer", "null"]
        assert cycle["minimum"] == 1

        # Optional: a legacy gate that carries only passed_at still validates
        # against the schema. The 4.2 backstop lives in ammo_state.py, not here.
        assert "started_at" not in gate.get("required", [])
        assert "cycle" not in gate.get("required", [])


def test_audit_gate_accepts_the_stamped_shape_and_rejects_cycle_zero():
    spec = _audit_gate_properties("stage_45")
    validator = Draft202012Validator(spec)
    stamped = {
        "started_at": "2026-08-04T12:00:00Z",
        "cycle": 2,
        "passed_at": "2026-08-04T12:31:00Z",
        "verdict_file": "rounds/1/audits/stage_45_cycle_2.md",
    }
    assert list(validator.iter_errors(stamped)) == []
    assert list(validator.iter_errors({"cycle": 0}))
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