Extract Yao CLI test helpers

reports/adaptation_proposals.json

@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-16T13:40:09Z",
   "skill_dir": ".",
   "source_patterns": "reports/user_patterns.json",
   "pattern_count": 5,

reports/adaptation_proposals.md

@@ -1,6 +1,6 @@
 # Adaptation Proposals
 
-- Generated at: `2026-06-16`
+- Generated at: `2026-06-16T13:40:09Z`
 - Pattern report: `reports/user_patterns.json`
 - Proposal only: `true`
 - Writes repository files: `false`

reports/architecture_maintainability.json

@@ -4,9 +4,9 @@
   "generated_at": "2026-06-16",
   "skill_dir": ".",
   "summary": {
-    "python_file_count": 202,
+    "python_file_count": 203,
     "script_file_count": 131,
-    "test_file_count": 71,
+    "test_file_count": 72,
     "internal_module_count": 48,
     "cli_script_count": 85,
     "command_handler_count": 68,
@@ -16,7 +16,7 @@
     "watch_line_threshold": 720,
     "block_line_threshold": 1500,
     "largest_file_lines": 852,
-    "watchlist_count": 2,
+    "watchlist_count": 1,
     "hotspot_count": 0,
     "blocker_count": 0,
     "decision": "pass"
@@ -29,13 +29,6 @@
       "severity": "pass",
       "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
     },
-    {
-      "path": "tests/verify_yao_cli.py",
-      "lines": 787,
-      "kind": "test",
-      "severity": "pass",
-      "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
-    },
     {
       "path": "scripts/trust_check.py",
       "lines": 714,
@@ -57,6 +50,13 @@
       "severity": "pass",
       "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
     },
+    {
+      "path": "tests/verify_yao_cli.py",
+      "lines": 696,
+      "kind": "test",
+      "severity": "pass",
+      "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
+    },
     {
       "path": "scripts/world_class_evidence_contract.py",
       "lines": 686,
@@ -114,13 +114,6 @@
       "kind": "test",
       "severity": "pass",
       "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
-    },
-    {
-      "path": "tests/verify_yao_cli.py",
-      "lines": 787,
-      "kind": "test",
-      "severity": "pass",
-      "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
     }
   ],
   "hotspots": [],

reports/architecture_maintainability.md

@@ -5,9 +5,9 @@ Generated at: `2026-06-16`
 ## Summary
 
 - decision: `pass`
-- python files: `202`
+- python files: `203`
 - scripts: `131`
-- tests: `71`
+- tests: `72`
 - internal modules: `48`
 - CLI scripts: `85`
 - Yao CLI command handlers: `68`
@@ -15,7 +15,7 @@ Generated at: `2026-06-16`
 - command modules: `6`
 - largest file lines: `852`
 - watch threshold lines: `720`
-- watchlist: `2`
+- watchlist: `1`
 - hotspots: `0`
 - blockers: `0`
 
@@ -30,17 +30,16 @@ No file-size hotspots found.
 | File | Lines | Kind | Recommended next split |
 | --- | ---: | --- | --- |
 | `tests/verify_review_studio.py` | `852` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
-| `tests/verify_yao_cli.py` | `787` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
 
 ## Largest Files
 
 | File | Lines | Kind | Severity |
 | --- | ---: | --- | --- |
 | `tests/verify_review_studio.py` | `852` | `test` | `pass` |
-| `tests/verify_yao_cli.py` | `787` | `test` | `pass` |
 | `scripts/trust_check.py` | `714` | `internal-module` | `pass` |
 | `scripts/review_studio_gates.py` | `707` | `internal-module` | `pass` |
 | `scripts/apply_adaptation.py` | `706` | `cli-script` | `pass` |
+| `tests/verify_yao_cli.py` | `696` | `test` | `pass` |
 | `scripts/world_class_evidence_contract.py` | `686` | `internal-module` | `pass` |
 | `scripts/render_review_viewer.py` | `685` | `cli-script` | `pass` |
 | `scripts/skill_report_model.py` | `665` | `internal-module` | `pass` |

reports/context_budget.json

@@ -6,9 +6,9 @@
     "context_budget_tier": "production",
     "context_budget_limit": 1000,
     "skill_body_tokens": 797,
-    "other_text_tokens": 1052655,
+    "other_text_tokens": 1052729,
     "estimated_initial_load_tokens": 990,
-    "estimated_total_text_tokens": 1053452,
+    "estimated_total_text_tokens": 1053526,
     "deferred_resource_tokens": 487270,
     "deferred_resource_warn_threshold": 120000,
     "deferred_resource_dirs": [
@@ -66,7 +66,7 @@
       ],
       "summary": "Large deferred resources are indexed and backed by evidence."
     },
-    "relevant_file_count": 650,
+    "relevant_file_count": 652,
     "unused_resource_dirs": [],
     "quality_signal_points": 130,
     "quality_density": 131.3

reports/python_compatibility.json

@@ -5,7 +5,7 @@
   "root": ".",
   "summary": {
     "target_python": "3.11",
-    "file_count": 205,
+    "file_count": 206,
     "issue_count": 0,
     "syntax_error_count": 0,
     "fstring_311_violation_count": 0,
@@ -1246,6 +1246,12 @@
       "issue_count": 0,
       "issues": []
     },
+    {
+      "path": "tests/yao_cli_helpers.py",
+      "ok": true,
+      "issue_count": 0,
+      "issues": []
+    },
     {
       "path": "tests/yao_cli_report_refresh.py",
       "ok": true,

reports/python_compatibility.md

@@ -6,7 +6,7 @@ Generated at: `2026-06-16`
 
 - decision: `pass`
 - target python: `3.11`
-- files scanned: `205`
+- files scanned: `206`
 - issues: `0`
 - syntax errors: `0`
 - f-string 3.11 violations: `0`

tests/verify_architecture_maintainability.py

@@ -48,7 +48,9 @@ def main() -> None:
     assert payload["summary"]["largest_file_lines"] < 900, payload["summary"]
     assert all(item["severity"] == "pass" for item in payload["largest_files"]), payload["largest_files"]
     assert all(item["severity"] == "pass" for item in payload["watchlist"]), payload["watchlist"]
-    assert any(item["path"] == "tests/verify_yao_cli.py" for item in payload["watchlist"]), payload["watchlist"]
+    watchlist_paths = {item["path"] for item in payload["watchlist"]}
+    assert "tests/verify_yao_cli.py" not in watchlist_paths, payload["watchlist"]
+    assert "tests/verify_review_studio.py" in watchlist_paths, payload["watchlist"]
     renderer_lines = len((ROOT / "scripts" / "render_review_studio.py").read_text(encoding="utf-8").splitlines())
     action_module = (ROOT / "scripts" / "review_studio_actions.py").read_text(encoding="utf-8")
     action_lines = len(action_module.splitlines())

tests/verify_yao_cli.py

@@ -1,64 +1,20 @@
 #!/usr/bin/env python3
 import json
-import os
 import subprocess
 import sys
 from pathlib import Path
 
-ROOT = Path(__file__).resolve().parent.parent
-CLI = ROOT / "scripts" / "yao.py"
-BENCHMARK_FIXTURE_DIR = ROOT / "tests" / "fixtures" / "github_benchmark_scan"
-sys.path.insert(0, str(ROOT / "scripts"))
-import yao as yao_cli_module  # noqa: E402
-import yao_cli_adaptation_commands  # noqa: E402
-import yao_cli_config  # noqa: E402
-import yao_cli_distribution_commands  # noqa: E402
-import yao_cli_output_commands  # noqa: E402
-import yao_cli_parser  # noqa: E402
-import yao_cli_parser_evidence  # noqa: E402
-import yao_cli_parser_operations  # noqa: E402
-import yao_cli_report_commands  # noqa: E402
-import yao_cli_runtime  # noqa: E402
-from yao_cli_report_refresh import refresh_root_report_consistency_inputs  # noqa: E402
-
-def run(*args: str, input_text: str | None = None) -> dict:
-    env = dict(os.environ)
-    env["YAO_CLI_TELEMETRY"] = "0"
-    env.pop("YAO_CLI_TELEMETRY_EVENTS", None)
-    proc = subprocess.run(
-        [sys.executable, str(CLI), *args],
-        cwd=ROOT,
-        capture_output=True,
-        text=True,
-        input=input_text,
-        env=env,
-    )
-    payload = json.loads(proc.stdout)
-    return {
-        "ok": proc.returncode == 0,
-        "returncode": proc.returncode,
-        "payload": payload,
-        "stderr": proc.stderr,
-    }
-
-
-def run_with_env(extra_env: dict[str, str], *args: str) -> dict:
-    env = dict(os.environ)
-    env.update(extra_env)
-    proc = subprocess.run(
-        [sys.executable, str(CLI), *args],
-        cwd=ROOT,
-        capture_output=True,
-        text=True,
-        env=env,
-    )
-    payload = json.loads(proc.stdout)
-    return {
-        "ok": proc.returncode == 0,
-        "returncode": proc.returncode,
-        "payload": payload,
-        "stderr": proc.stderr,
-    }
+from yao_cli_helpers import (
+    BENCHMARK_FIXTURE_DIR,
+    ROOT,
+    assert_cli_module_contracts,
+    assert_created_skill_reports,
+    assert_creation_report_view,
+    assert_help_surface,
+    refresh_root_report_consistency_inputs,
+    run,
+    run_with_env,
+)
 
 
 def main() -> None:
@@ -68,64 +24,17 @@ def main() -> None:
     tmp_root.mkdir(parents=True, exist_ok=True)
     remote_version = tmp_root / "remote-version.txt"
     remote_version.write_text("9.9.9\n", encoding="utf-8")
-    assert yao_cli_config.resolve_target("root")["title"] == "Root Description Optimization"
-    assert yao_cli_config.resolve_promotion_target("root") == "yao-meta-skill"
-    assert yao_cli_config.infer_archetype("Standardize team review workflow.", "")[0] == "production"
-    assert yao_cli_config.infer_archetype("Govern release policy.", "")[0] == "governed"
-    assert "--entry" in yao_cli_config.baseline_compare_args()
-    assert "scripts/provider_output_eval_runner.py" in yao_cli_config.provider_output_runner_command("openai")
-    assert "--allow-custom-base-url" in yao_cli_config.provider_output_runner_command("openai", allow_custom_base_url=True)
-    for module in (
-        yao_cli_parser,
-        yao_cli_parser_evidence,
-        yao_cli_parser_operations,
-        yao_cli_runtime,
-        yao_cli_adaptation_commands,
-        yao_cli_distribution_commands,
-        yao_cli_output_commands,
-        yao_cli_report_commands,
-    ):
-        assert module.SCRIPT_INTERFACE == "internal-module"
-    assert callable(yao_cli_module.command_review_studio)
-    parser_help = yao_cli_module.build_parser().format_help()
-    expected_help = (
-        "quickstart skill-interpretation review-studio python-compat architecture-audit skill-os2-audit skill-os2-coverage "
-        "world-class-evidence world-class-ledger world-class-intake world-class-preflight world-class-submission-kit world-class-submission-review world-class-runbook world-class-claim-guard "
-        "benchmark-reproducibility evidence-consistency output-review-kit output-review-import adapt-scan adapt-propose adapt-apply telemetry-import telemetry-emit telemetry-hooks weekly-curator --record-cli-telemetry"
-    ).split()
-    assert all(item in parser_help for item in expected_help), parser_help
+    assert_cli_module_contracts()
+    assert_help_surface()
 
     init_result = run("init", "cli-demo-skill", "--description", "CLI demo skill.", "--output-dir", str(tmp_root))
     assert init_result["ok"], init_result
     created = Path(init_result["payload"]["root"])
     assert (created / "SKILL.md").exists(), created
     assert (created / "README.md").exists(), created
-    expected_reports = [
-        "intent-dialogue.md", "intent-confidence.md", "skill-overview.html", "skill-interpretation.html",
-        "skill-interpretation.json", "review-studio.html", "review-studio.json", "review-viewer.html",
-        "reference-scan.md", "reference-synthesis.md", "output-risk-profile.md", "artifact-design-profile.md",
-        "prompt-quality-profile.md", "system-model.md", "skill-ir.json", "compiled_targets.md",
-        "compiled_targets.json", "iteration-directions.md", "adoption_drift_report.md",
-        "adoption_drift_report.json", "review_waivers.md", "review_waivers.json", "review_annotations.md",
-        "review_annotations.json",
-    ]
-    assert all((created / "reports" / path).exists() for path in expected_reports), created
+    assert_created_skill_reports(created)
     assert "Honest Boundaries" in (created / "SKILL.md").read_text(encoding="utf-8"), created
-    init_report_view = init_result["payload"]["report_view"]
-    assert init_report_view["html_report"].endswith("reports/skill-overview.html"), init_report_view
-    assert init_report_view["interpretation_report"].endswith("reports/skill-interpretation.html"), init_report_view
-    assert Path(init_report_view["html_report"]).exists(), init_report_view
-    assert Path(init_report_view["interpretation_report"]).exists(), init_report_view
-    assert init_report_view["review_studio"].endswith("reports/review-studio.html"), init_report_view
-    assert Path(init_report_view["review_studio"]).exists(), init_report_view
-    assert "Skill 已创建完成" in init_report_view["message"], init_report_view
-    assert "reports/skill-interpretation.html" in init_report_view["message"], init_report_view
-    assert "Review Studio 2.0" in init_report_view["message"], init_report_view
-    assert "目标编译" in init_report_view["message"], init_report_view
-    assert "reports/compiled_targets.md" in init_report_view["message"], init_report_view
-    assert "概述、指标、原理、触发边界、输入输出、目标编译、质量评估、风险治理、包体资产和升级路线" in init_report_view["message"], init_report_view
-    assert "默认使用中文简体" in init_report_view["message"], init_report_view
-    assert "切换英文版" in init_report_view["message"], init_report_view
+    assert_creation_report_view(init_result["payload"]["report_view"])
     init_skill_ir = init_result["payload"]["skill_ir"]
     assert init_skill_ir["name"] == "cli-demo-skill", init_skill_ir
     assert init_skill_ir["trigger_samples"] >= 1, init_skill_ir

tests/yao_cli_helpers.py

@@ -0,0 +1,125 @@
+import json
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parent.parent
+CLI = ROOT / "scripts" / "yao.py"
+BENCHMARK_FIXTURE_DIR = ROOT / "tests" / "fixtures" / "github_benchmark_scan"
+
+sys.path.insert(0, str(ROOT / "scripts"))
+import yao as yao_cli_module  # noqa: E402
+import yao_cli_adaptation_commands  # noqa: E402
+import yao_cli_config  # noqa: E402
+import yao_cli_distribution_commands  # noqa: E402
+import yao_cli_output_commands  # noqa: E402
+import yao_cli_parser  # noqa: E402
+import yao_cli_parser_evidence  # noqa: E402
+import yao_cli_parser_operations  # noqa: E402
+import yao_cli_report_commands  # noqa: E402
+import yao_cli_runtime  # noqa: E402
+from yao_cli_report_refresh import refresh_root_report_consistency_inputs  # noqa: E402
+
+
+def run(*args: str, input_text: str | None = None) -> dict:
+    env = dict(os.environ)
+    env["YAO_CLI_TELEMETRY"] = "0"
+    env.pop("YAO_CLI_TELEMETRY_EVENTS", None)
+    proc = subprocess.run(
+        [sys.executable, str(CLI), *args],
+        cwd=ROOT,
+        capture_output=True,
+        text=True,
+        input=input_text,
+        env=env,
+    )
+    payload = json.loads(proc.stdout)
+    return {
+        "ok": proc.returncode == 0,
+        "returncode": proc.returncode,
+        "payload": payload,
+        "stderr": proc.stderr,
+    }
+
+
+def run_with_env(extra_env: dict[str, str], *args: str) -> dict:
+    env = dict(os.environ)
+    env.update(extra_env)
+    proc = subprocess.run(
+        [sys.executable, str(CLI), *args],
+        cwd=ROOT,
+        capture_output=True,
+        text=True,
+        env=env,
+    )
+    payload = json.loads(proc.stdout)
+    return {
+        "ok": proc.returncode == 0,
+        "returncode": proc.returncode,
+        "payload": payload,
+        "stderr": proc.stderr,
+    }
+
+
+def assert_cli_module_contracts() -> None:
+    assert yao_cli_config.resolve_target("root")["title"] == "Root Description Optimization"
+    assert yao_cli_config.resolve_promotion_target("root") == "yao-meta-skill"
+    assert yao_cli_config.infer_archetype("Standardize team review workflow.", "")[0] == "production"
+    assert yao_cli_config.infer_archetype("Govern release policy.", "")[0] == "governed"
+    assert "--entry" in yao_cli_config.baseline_compare_args()
+    assert "scripts/provider_output_eval_runner.py" in yao_cli_config.provider_output_runner_command("openai")
+    assert "--allow-custom-base-url" in yao_cli_config.provider_output_runner_command("openai", allow_custom_base_url=True)
+    for module in (
+        yao_cli_parser,
+        yao_cli_parser_evidence,
+        yao_cli_parser_operations,
+        yao_cli_runtime,
+        yao_cli_adaptation_commands,
+        yao_cli_distribution_commands,
+        yao_cli_output_commands,
+        yao_cli_report_commands,
+    ):
+        assert module.SCRIPT_INTERFACE == "internal-module"
+    assert callable(yao_cli_module.command_review_studio)
+
+
+def assert_help_surface() -> None:
+    parser_help = yao_cli_module.build_parser().format_help()
+    expected_help = (
+        "quickstart skill-interpretation review-studio python-compat architecture-audit skill-os2-audit skill-os2-coverage "
+        "world-class-evidence world-class-ledger world-class-intake world-class-preflight world-class-submission-kit world-class-submission-review world-class-runbook world-class-claim-guard "
+        "benchmark-reproducibility evidence-consistency output-review-kit output-review-import adapt-scan adapt-propose adapt-apply telemetry-import telemetry-emit telemetry-hooks weekly-curator --record-cli-telemetry"
+    ).split()
+    assert all(item in parser_help for item in expected_help), parser_help
+
+
+def assert_created_skill_reports(created: Path) -> None:
+    expected_reports = [
+        "intent-dialogue.md", "intent-confidence.md", "skill-overview.html", "skill-interpretation.html",
+        "skill-interpretation.json", "review-studio.html", "review-studio.json", "review-viewer.html",
+        "reference-scan.md", "reference-synthesis.md", "output-risk-profile.md", "artifact-design-profile.md",
+        "prompt-quality-profile.md", "system-model.md", "skill-ir.json", "compiled_targets.md",
+        "compiled_targets.json", "iteration-directions.md", "adoption_drift_report.md",
+        "adoption_drift_report.json", "review_waivers.md", "review_waivers.json", "review_annotations.md",
+        "review_annotations.json",
+    ]
+    assert all((created / "reports" / path).exists() for path in expected_reports), created
+
+
+def assert_creation_report_view(report_view: dict) -> None:
+    assert report_view["html_report"].endswith("reports/skill-overview.html"), report_view
+    assert report_view["interpretation_report"].endswith("reports/skill-interpretation.html"), report_view
+    assert Path(report_view["html_report"]).exists(), report_view
+    assert Path(report_view["interpretation_report"]).exists(), report_view
+    assert report_view["review_studio"].endswith("reports/review-studio.html"), report_view
+    assert Path(report_view["review_studio"]).exists(), report_view
+    assert "Skill 已创建完成" in report_view["message"], report_view
+    assert "reports/skill-interpretation.html" in report_view["message"], report_view
+    assert "Review Studio 2.0" in report_view["message"], report_view
+    assert "目标编译" in report_view["message"], report_view
+    assert "reports/compiled_targets.md" in report_view["message"], report_view
+    assert "概述、指标、原理、触发边界、输入输出、目标编译、质量评估、风险治理、包体资产和升级路线" in report_view["message"], report_view
+    assert "默认使用中文简体" in report_view["message"], report_view
+    assert "切换英文版" in report_view["message"], report_view