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_reconcile_track_state.py

View on GitHub
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: CC-BY-NC-4.0
"""Regression tests for AMMO track state reconciliation."""

from __future__ import annotations

import importlib.util
import json
import sys
from pathlib import Path


_SCRIPT = Path(__file__).resolve().parents[1] / "scripts" / "reconcile_track_state.py"
_spec = importlib.util.spec_from_file_location("reconcile_track_state", str(_SCRIPT))
reconcile_track_state = importlib.util.module_from_spec(_spec)
sys.modules["reconcile_track_state"] = reconcile_track_state
_spec.loader.exec_module(reconcile_track_state)


def _write_artifact(tmp_path: Path, evidence: dict) -> Path:
    artifact_dir = tmp_path / "artifacts"
    track_dir = artifact_dir / "rounds" / "1" / "tracks" / "op001"
    track_dir.mkdir(parents=True)
    (artifact_dir / "state.json").write_text(
        json.dumps(
            {
                "campaign": {
                    "current_round": 1,
                    "rounds": [
                        {
                            "round_id": 1,
                            "parallel_tracks": {"tracks": {"op001": {"status": "IN_PROGRESS"}}},
                        }
                    ],
                }
            }
        ),
        encoding="utf-8",
    )
    (track_dir / "evidence.json").write_text(json.dumps(evidence), encoding="utf-8")
    return artifact_dir


def _component_pass_evidence(**extra: dict) -> dict:
    evidence = {
        "correctness": {"status": "PASS"},
        "kernel_bench": {"status": "PASS"},
        "e2e": {"status": "PASS"},
    }
    evidence.update(extra)
    return evidence


def _generated_diluted_evidence(**extra: dict) -> dict:
    evidence = {
        "verdict": "FAIL",
        "diluted": False,
        "correctness": {"status": "PASS"},
        "kernel_bench": {"status": "PASS"},
        "e2e": {
            "status": "PASS",
            "admissibility": {"status": "PASS"},
            "fastpath_proof": {"status": "PASS", "hits": 1},
        },
        "kill_criteria": {"e2e_threshold": {"status": "PASS"}},
    }
    evidence.update(extra)
    return evidence


def _enable_binding_diluted_gates(artifact_dir: Path, **track_updates: object) -> None:
    state_path = artifact_dir / "state.json"
    state = json.loads(state_path.read_text(encoding="utf-8"))
    track = state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]
    track.update(
        {
            "correctness": True,
            "gate_5_1a": "PASS",
            "gate_5_2": "PASS",
            **track_updates,
        }
    )
    state_path.write_text(json.dumps(state), encoding="utf-8")


def _write_diluted_summary(artifact_dir: Path, gate: dict | None = None) -> None:
    summary_path = artifact_dir / "rounds" / "1" / "tracks" / "op001" / "validation_summary.json"
    summary_path.write_text(
        json.dumps(
            {
                "e2e_gate": gate
                or {"track_verdict": "PASS", "diluted_pass": {"eligible": True}}
            }
        ),
        encoding="utf-8",
    )


def test_inferred_pass_requires_nonempty_kill_criteria(tmp_path):
    artifact_dir = _write_artifact(tmp_path, _component_pass_evidence(kill_criteria={}))

    try:
        reconcile_track_state.reconcile_track_state(artifact_dir, "op001")
    except ValueError as exc:
        assert "track verdict" in str(exc)
    else:
        raise AssertionError("empty kill_criteria must not infer PASS")


def test_inferred_pass_requires_kill_criteria_field(tmp_path):
    artifact_dir = _write_artifact(tmp_path, _component_pass_evidence())

    try:
        reconcile_track_state.reconcile_track_state(artifact_dir, "op001")
    except ValueError as exc:
        assert "track verdict" in str(exc)
    else:
        raise AssertionError("missing kill_criteria must not infer PASS")


def test_inferred_pass_with_kill_criteria_updates_round_scoped_state(tmp_path):
    artifact_dir = _write_artifact(
        tmp_path,
        _component_pass_evidence(kill_criteria={"e2e_threshold": {"status": "PASS"}}),
    )

    result = reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))
    track = state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]

    assert result.verdict == "PASS"
    assert track["status"] == "PASS"
    assert track["evidence_path"] == "rounds/1/tracks/op001/evidence.json"
    assert track["kill_criteria_results"] == {"e2e_threshold": "PASS"}
    assert "completed_at" in track


def test_contingent_boundary_arithmetic_reconciles_to_track_state(tmp_path):
    boundary = {
        "baseline_duration_us": 100.0,
        "optimized_duration_us": 90.0,
        "occurrence_count": 1000,
        "baseline_e2e_us": 2_000_000.0,
        "e2e_equivalent_improvement_pct": 0.5,
        "campaign_floor_pct": 0.5,
        "meets_floor": True,
    }
    artifact_dir = _write_artifact(
        tmp_path,
        _component_pass_evidence(
            kernel_bench={"status": "PASS", "boundary_ab": boundary},
            kill_criteria={"e2e_threshold": {"status": "PASS"}},
        ),
    )

    reconcile_track_state.reconcile_track_state(
        artifact_dir, "op001", write=True
    )
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))
    track = state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]
    assert track["gate_5_2_boundary"] == boundary


def test_diluted_pass_marker_reconciles_to_track_state(tmp_path):
    artifact_dir = _write_artifact(
        tmp_path,
        _component_pass_evidence(
            verdict="PASS",
            diluted=True,
            kill_criteria={"e2e_threshold": {"status": "PASS"}},
        ),
    )

    reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))

    assert state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]["diluted"] is True
    assert state["campaign"]["rounds"][0]["diluted_tracks"] == [
        {
            "op_id": "op001",
            "tpot_improvement_pct": None,
            "decode_share_of_e2e": None,
        }
    ]


def test_diluted_true_cannot_reconcile_with_fail_verdict(tmp_path):
    artifact_dir = _write_artifact(tmp_path, {"verdict": "FAIL", "diluted": True})

    try:
        reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    except ValueError as exc:
        assert "requires verdict PASS" in str(exc)
    else:
        raise AssertionError("diluted=true must never persist on a FAIL track")


def test_explicit_false_clears_stale_diluted_marker(tmp_path):
    artifact_dir = _write_artifact(
        tmp_path,
        _component_pass_evidence(
            verdict="PASS",
            diluted=False,
            kill_criteria={"e2e_threshold": {"status": "PASS"}},
        ),
    )
    state_path = artifact_dir / "state.json"
    state = json.loads(state_path.read_text(encoding="utf-8"))
    state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]["diluted"] = True
    state_path.write_text(json.dumps(state), encoding="utf-8")

    reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads(state_path.read_text(encoding="utf-8"))

    assert state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]["diluted"] is False


def test_non_boolean_diluted_evidence_is_rejected(tmp_path):
    artifact_dir = _write_artifact(tmp_path, {"verdict": "PASS", "diluted": "true"})

    try:
        reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    except ValueError as exc:
        assert "must be boolean" in str(exc)
    else:
        raise AssertionError("non-boolean diluted evidence must be rejected")


def test_generated_diluted_summary_overrides_template_false(tmp_path):
    artifact_dir = _write_artifact(tmp_path, _generated_diluted_evidence())
    _enable_binding_diluted_gates(artifact_dir)
    _write_diluted_summary(artifact_dir)

    reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))

    assert state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]["diluted"] is True


def test_generated_diluted_summary_overrides_only_e2e_floor_failure(tmp_path):
    artifact_dir = _write_artifact(tmp_path, _generated_diluted_evidence())
    _enable_binding_diluted_gates(artifact_dir)
    _write_diluted_summary(artifact_dir)

    result = reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))
    track = state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]

    assert result.verdict == "PASS"
    assert track["status"] == "PASS"
    assert track["diluted"] is True


def test_generated_diluted_summary_cannot_waive_binding_vetoes(tmp_path):
    cases = (
        ({"correctness": {"status": "FAIL"}}, {}, "correctness"),
        ({"kernel_bench": {"status": "FAIL"}}, {}, "kernel"),
        ({"e2e": {"status": "FAIL", "admissibility": {"status": "FAIL"}, "fastpath_proof": {"status": "PASS", "hits": 1}}}, {}, "admissibility"),
        ({"e2e": {"status": "FAIL", "admissibility": {"status": "PASS"}, "fastpath_proof": {"status": "FAIL", "hits": 0}}}, {}, "fast-path"),
        ({"kill_criteria": {"threshold": {"status": "FAIL"}}}, {}, "kill"),
        ({}, {"gate_5_1a": "FAIL"}, "Gate 5.1a"),
        ({}, {"correctness": False}, "Gate 5.1b"),
    )
    for index, (evidence_updates, track_updates, expected) in enumerate(cases):
        artifact_dir = _write_artifact(
            tmp_path / str(index), _generated_diluted_evidence(**evidence_updates)
        )
        _enable_binding_diluted_gates(artifact_dir, **track_updates)
        _write_diluted_summary(artifact_dir)
        original = (artifact_dir / "state.json").read_text(encoding="utf-8")

        try:
            reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
        except ValueError as exc:
            assert expected in str(exc)
        else:
            raise AssertionError(f"generated diluted PASS must not waive {expected}")
        assert (artifact_dir / "state.json").read_text(encoding="utf-8") == original


def test_generated_diluted_summary_cannot_promote_untouched_template(tmp_path):
    artifact_dir = _write_artifact(
        tmp_path,
        {
            "verdict": "FAIL",
            "diluted": False,
            "correctness": {"status": "FAIL"},
            "kernel_bench": {"status": "FAIL"},
            "e2e": {
                "status": "FAIL",
                "admissibility": {"status": "FAIL"},
                "fastpath_proof": {"status": "FAIL", "hits": 0},
            },
            "kill_criteria": {},
        },
    )
    _write_diluted_summary(artifact_dir)

    try:
        reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    except ValueError as exc:
        assert "cannot waive binding validation gates" in str(exc)
    else:
        raise AssertionError("untouched evidence template must never reconcile to diluted PASS")


def test_generated_diluted_summary_requires_eligible_true_and_pass_verdict(tmp_path):
    gates = (
        {"track_verdict": "PASS", "diluted_pass": {"eligible": False}},
        {"track_verdict": "FAIL", "diluted_pass": {"eligible": True}},
        {"track_verdict": "PASS", "diluted_pass": True},
    )
    for index, gate in enumerate(gates):
        artifact_dir = _write_artifact(tmp_path / str(index), {"verdict": "PASS"})
        summary_path = artifact_dir / "rounds" / "1" / "tracks" / "op001" / "validation_summary.json"
        summary_path.write_text(json.dumps({"e2e_gate": gate}), encoding="utf-8")
        try:
            reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
        except ValueError as exc:
            assert "diluted_pass" in str(exc)
        else:
            raise AssertionError("contradictory generated diluted summary must fail closed")


def test_diluted_rollup_reconcile_preserves_populated_metrics(tmp_path):
    artifact_dir = _write_artifact(tmp_path, {"verdict": "PASS", "diluted": True})
    state_path = artifact_dir / "state.json"
    state = json.loads(state_path.read_text(encoding="utf-8"))
    state["campaign"]["rounds"][0]["diluted_tracks"] = [
        {
            "op_id": "op001",
            "tpot_improvement_pct": 3.25,
            "decode_share_of_e2e": 0.8,
        }
    ]
    state_path.write_text(json.dumps(state), encoding="utf-8")

    reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads(state_path.read_text(encoding="utf-8"))

    assert state["campaign"]["rounds"][0]["diluted_tracks"] == [
        {
            "op_id": "op001",
            "tpot_improvement_pct": 3.25,
            "decode_share_of_e2e": 0.8,
        }
    ]


def test_generated_plain_summary_clears_stale_explicit_true(tmp_path):
    artifact_dir = _write_artifact(
        tmp_path,
        _component_pass_evidence(
            verdict="PASS",
            diluted=True,
            kill_criteria={"e2e_threshold": {"status": "PASS"}},
        ),
    )
    summary_path = artifact_dir / "rounds" / "1" / "tracks" / "op001" / "validation_summary.json"
    summary_path.write_text(
        json.dumps({"e2e_gate": {"track_verdict": "PASS"}}),
        encoding="utf-8",
    )

    reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))

    assert state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]["diluted"] is False


def test_gpu_blocked_reconciles_without_completed_at(tmp_path):
    artifact_dir = _write_artifact(tmp_path, {"verdict": "GPU_BLOCKED"})

    result = reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))
    track = state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]

    assert result.verdict == "GPU_BLOCKED"
    assert track["status"] == "GPU_BLOCKED"
    assert track["verdict"] is None
    assert "completed_at" not in track


def test_gpu_blocked_reconciliation_clears_stale_completed_at(tmp_path):
    artifact_dir = _write_artifact(tmp_path, {"verdict": "GPU_BLOCKED"})
    state_path = artifact_dir / "state.json"
    state = json.loads(state_path.read_text(encoding="utf-8"))
    track = state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]
    track["status"] = "PASS"
    track["completed_at"] = "2026-05-11T00:00:00Z"
    state_path.write_text(json.dumps(state), encoding="utf-8")

    reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads(state_path.read_text(encoding="utf-8"))
    track = state["campaign"]["rounds"][0]["parallel_tracks"]["tracks"]["op001"]

    assert track["status"] == "GPU_BLOCKED"
    assert "completed_at" not in track


def test_v2_missing_current_round_evidence_does_not_use_legacy_track_path(tmp_path):
    artifact_dir = _write_artifact(tmp_path, {"verdict": "PASS"})
    current = artifact_dir / "rounds" / "1" / "tracks" / "op001" / "evidence.json"
    legacy = artifact_dir / "tracks" / "op001" / "evidence.json"
    legacy.parent.mkdir(parents=True)
    legacy.write_text(current.read_text(encoding="utf-8"), encoding="utf-8")
    current.unlink()

    try:
        reconcile_track_state.reconcile_track_state(artifact_dir, "op001")
    except FileNotFoundError as exc:
        assert "rounds/1" in str(exc).replace("\\", "/")
    else:
        raise AssertionError("V2 reconciliation must not consume legacy-root evidence")


def test_true_legacy_reconciliation_keeps_flat_layout(tmp_path):
    artifact_dir = tmp_path / "legacy"
    track_dir = artifact_dir / "tracks" / "op001"
    track_dir.mkdir(parents=True)
    (artifact_dir / "state.json").write_text(
        json.dumps({"parallel_tracks": {"op001": {"status": "IN_PROGRESS"}}}),
        encoding="utf-8",
    )
    (track_dir / "evidence.json").write_text(json.dumps({"verdict": "PASS"}), encoding="utf-8")

    result = reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    state = json.loads((artifact_dir / "state.json").read_text(encoding="utf-8"))

    assert result.verdict == "PASS"
    assert state["parallel_tracks"]["op001"]["evidence_path"] == "tracks/op001/evidence.json"


def test_reconcile_rejects_track_id_path_traversal(tmp_path):
    artifact_dir = _write_artifact(tmp_path, {"verdict": "PASS"})

    try:
        reconcile_track_state.reconcile_track_state(artifact_dir, "../../../tracks/op", write=True)
    except ValueError as exc:
        assert "Invalid track id" in str(exc)
    else:
        raise AssertionError("track id traversal must be rejected")


def test_reconcile_rejects_boolean_current_round(tmp_path):
    artifact_dir = _write_artifact(tmp_path, {"verdict": "PASS"})
    state_path = artifact_dir / "state.json"
    state = json.loads(state_path.read_text(encoding="utf-8"))
    state["campaign"]["current_round"] = True
    state_path.write_text(json.dumps(state), encoding="utf-8")

    try:
        reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    except ValueError as exc:
        assert "current-round track container" in str(exc)
    else:
        raise AssertionError("boolean current_round must fail closed")


def test_partial_v2_campaign_cannot_reconcile_flat_legacy_track(tmp_path):
    artifact_dir = tmp_path / "partial"
    track_dir = artifact_dir / "tracks" / "op001"
    track_dir.mkdir(parents=True)
    state_path = artifact_dir / "state.json"
    original = {
        "campaign": {"status": "active"},
        "parallel_tracks": {"op001": {"status": "IN_PROGRESS"}},
    }
    state_path.write_text(json.dumps(original), encoding="utf-8")
    (track_dir / "evidence.json").write_text(json.dumps({"verdict": "PASS"}), encoding="utf-8")

    try:
        reconcile_track_state.reconcile_track_state(artifact_dir, "op001", write=True)
    except ValueError as exc:
        assert "current-round track container" in str(exc)
    else:
        raise AssertionError("partial V2 campaign must not reconcile legacy-root evidence")
    assert json.loads(state_path.read_text(encoding="utf-8")) == original
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