claude-dev-env 2.12.0 → 2.14.0

package/scripts/test_invoke_code_review.py

@@ -1,10 +1,4 @@
-"""Specifications for what a blocked mint tells the person it blocked.
-
-Enforcement refuses every push until a clean stamp covers the branch surface,
-and ``invoke_code_review.py --record-stamp`` is the only way to mint one. When
-that call cannot run, the reason it names is the person's only route back to a
-working push.
-"""
+"""Specifications for code-review error reporting and review-loop outcomes."""
 
 from __future__ import annotations
 
@@ -13,8 +7,7 @@ from pathlib import Path
 import pytest
 
 import invoke_code_review as invoker
-from claude_chain_runner import ChainConfigurationError, ChainInvocationOutcome
-from _code_review_test_support import FIXTURE_SESSION_OPUS
+from claude_chain_runner import ChainInvocationOutcome
 from dev_env_scripts_constants.claude_chain_constants import TERMINAL_STATUS_SERVED
 from dev_env_scripts_constants.code_review_constants import (
     ALL_FINDING_SEVERITIES,
@@ -52,8 +45,7 @@ from dev_env_scripts_constants.code_review_constants import (
 def test_review_arguments_carry_the_permission_mode_this_caller_resolves() -> None:
     """The review command asks for a permission mode the binary accepts here.
 
-    The binary refuses the bypass mode outright for a root caller, so asking
-    for it there means no review runs and no stamp is ever minted.
+    The binary refuses the bypass mode outright for a root caller.
     """
     all_arguments = invoker.build_code_review_arguments(DEFAULT_CODE_REVIEW_EFFORT)
 
@@ -104,8 +96,8 @@ def test_failed_review_reports_what_the_served_binary_wrote(
     """A review that a served binary refused names the refusal.
 
     The binary can decline for reasons the caller must act on, such as a
-    permission mode it will not accept. Dropping its words leaves a bare
-    exit code, and no stamp is minted either way.
+    permission mode it will not accept. Dropping its words leaves a bare exit
+    code without a usable recovery step.
     """
     monkeypatch.setattr(
         invoker, "_run_claude_with_empty_stdin", _serve_a_refusing_binary
@@ -122,54 +114,6 @@ def test_failed_review_reports_what_the_served_binary_wrote(
     assert REVIEW_BINARY_REFUSAL_TEXT in captured_streams.err
 
 
-def test_missing_chain_config_reports_its_remedy_on_stderr(
-    monkeypatch: pytest.MonkeyPatch,
-    tmp_path: Path,
-    capsys: pytest.CaptureFixture[str],
-) -> None:
-    def raise_chain_configuration_error(**_all_keyword_arguments: object) -> None:
-        raise ChainConfigurationError(CHAIN_CONFIG_REMEDY_TEXT)
-
-    monkeypatch.setattr(
-        invoker, "invoke_code_review_and_record_stamp", raise_chain_configuration_error
-    )
-
-    outcome = invoker._mint_or_config_outcome(
-        working_directory=tmp_path,
-        session_model=FIXTURE_SESSION_OPUS,
-        timeout_seconds=MINT_TIMEOUT_SECONDS,
-        effort=DEFAULT_CODE_REVIEW_EFFORT,
-    )
-
-    captured_streams = capsys.readouterr()
-    assert outcome.is_stamp_minted is False
-    assert CHAIN_CONFIG_REMEDY_TEXT in captured_streams.err
-
-
-def test_host_profile_failure_reports_its_reason_on_stderr(
-    monkeypatch: pytest.MonkeyPatch,
-    tmp_path: Path,
-    capsys: pytest.CaptureFixture[str],
-) -> None:
-    def raise_host_profile_error(**_all_keyword_arguments: object) -> None:
-        raise ValueError(HOST_PROFILE_FAILURE_TEXT)
-
-    monkeypatch.setattr(
-        invoker, "invoke_code_review_and_record_stamp", raise_host_profile_error
-    )
-
-    outcome = invoker._mint_or_config_outcome(
-        working_directory=tmp_path,
-        session_model=FIXTURE_SESSION_OPUS,
-        timeout_seconds=MINT_TIMEOUT_SECONDS,
-        effort=DEFAULT_CODE_REVIEW_EFFORT,
-    )
-
-    captured_streams = capsys.readouterr()
-    assert outcome.is_stamp_minted is False
-    assert HOST_PROFILE_FAILURE_TEXT in captured_streams.err
-
-
 HEAD_SHA_ONE: str = "aaa111"
 HEAD_SHA_TWO: str = "bbb222"
 HEAD_SHA_THREE: str = "ccc333"

package/scripts/test_invoke_code_review_cli.py

@@ -1,4 +1,4 @@
-"""CLI JSON output for in-session, error, effort, and record-stamp paths."""
+"""CLI JSON output for in-session, error, and effort paths."""
 
 from __future__ import annotations
 
@@ -9,8 +9,6 @@ import pytest
 
 import invoke_code_review as invoker
 from _code_review_test_support import (
-    DriftingReview,
-    EFFORT_LOW,
     FIXTURE_CHAIN_CONFIG_ERROR_MESSAGE,
     FIXTURE_HOST_PROFILE_ERROR_MESSAGE,
     FIXTURE_SESSION_OPUS,
@@ -19,8 +17,6 @@ from _code_review_test_support import (
     REJECTED_ULTRA_EFFORT,
     init_git_repository,
     install_seams,
-    prepared_surface_repo,
-    run_record_stamp_cli,
     run_review_cli,
 )
 from claude_chain_runner import ChainConfigurationError
@@ -32,17 +28,12 @@ from dev_env_scripts_constants.code_review_constants import (
     HOST_PROFILE_ERROR_RETURNCODE,
     IN_SESSION_RETURNCODE,
     INVALID_EFFORT_RETURNCODE,
-    MAXIMUM_STAMP_MINT_PASSES,
     MODE_CHAIN,
     MODE_IN_SESSION,
-    RESULT_KEY_BOUND_HASH,
     RESULT_KEY_DIRTY_TREE,
     RESULT_KEY_MODE,
-    RESULT_KEY_PASS_COUNT,
     RESULT_KEY_RETURNCODE,
     RESULT_KEY_SERVED_COMMAND,
-    RESULT_KEY_STAMP_MINTED,
-    STAMP_DID_NOT_CONVERGE_RETURNCODE,
 )
 from dev_env_scripts_constants.grok_worker_constants import CWD_FLAG
 
@@ -103,7 +94,6 @@ def test_cli_emits_json_on_chain_configuration_error(
         returncode=CHAIN_CONFIG_ERROR_EXIT_CODE,
         is_dirty_tree=False,
     )
-    assert invoker.is_code_review_clean_stamp_allowed(config_error_outcome) is False
 
 
 def test_cli_emits_json_on_host_profile_value_error(
@@ -156,37 +146,3 @@ def test_cli_rejects_ultra_effort_with_nonzero_exit(
     )
     assert exit_code == INVALID_EFFORT_RETURNCODE
     assert REJECTED_ULTRA_EFFORT in capsys.readouterr().err
-
-
-def test_cli_record_stamp_returns_non_convergence_code_on_cap(
-    monkeypatch: pytest.MonkeyPatch,
-    tmp_path: Path,
-    capsys: pytest.CaptureFixture[str],
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "invoke_code_review", DriftingReview())
-    exit_code = run_record_stamp_cli(working_directory, effort=EFFORT_LOW)
-    assert exit_code == STAMP_DID_NOT_CONVERGE_RETURNCODE
-    parsed_payload = json.loads(capsys.readouterr().out)
-    assert parsed_payload[RESULT_KEY_STAMP_MINTED] is False
-    assert parsed_payload[RESULT_KEY_PASS_COUNT] == MAXIMUM_STAMP_MINT_PASSES
-    assert parsed_payload[RESULT_KEY_BOUND_HASH] is None
-
-
-def test_cli_record_stamp_reports_missing_store_dependency(
-    monkeypatch: pytest.MonkeyPatch,
-    tmp_path: Path,
-    capsys: pytest.CaptureFixture[str],
-) -> None:
-    def raise_missing_store(*all_args: object, **all_keywords: object) -> object:
-        del all_args, all_keywords
-        raise ModuleNotFoundError("store missing", name="code_review_stamp_store")
-
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "load_code_review_stamp_store", raise_missing_store)
-    exit_code = run_record_stamp_cli(working_directory, effort=EFFORT_LOW)
-    assert exit_code == INVALID_EFFORT_RETURNCODE
-    captured = capsys.readouterr()
-    assert "stamp store" in captured.err
-    parsed_payload = json.loads(captured.out)
-    assert parsed_payload[RESULT_KEY_STAMP_MINTED] is False

package/scripts/test_invoke_code_review_contract.py

@@ -1,4 +1,4 @@
-"""Argument contract, encoding, clean-stamp rules, effort tokens, and stamps."""
+"""Argument contract, outcome encoding, and effort-token behavior."""
 
 from __future__ import annotations
 
@@ -8,40 +8,30 @@ import pytest
 
 import invoke_code_review as invoker
 from _code_review_test_support import (
-    DriftingReview,
     EFFORT_LOW,
     FIXTURE_CHAIN_RETURNCODE,
     FIXTURE_FAILED_RETURNCODE,
     FIXTURE_SERVED_COMMAND,
     FIXTURE_SESSION_OPUS,
     HOST_PROFILE_THIRD_PARTY,
-    MISSING_STORE_FILE_NAME,
     REJECTED_ULTRA_EFFORT,
-    SINGLE_PASS_CAP,
     claude_failed,
     init_git_repository,
     install_seams,
-    prepared_surface_repo,
     run_review,
-    stable_clean_review,
-    surface_changing_review,
 )
 from dev_env_scripts_constants.code_review_constants import (
     CODE_REVIEW_MODEL_ALIAS,
     DEFAULT_CODE_REVIEW_EFFORT,
     IN_SESSION_RETURNCODE,
-    MAXIMUM_STAMP_MINT_PASSES,
     MODE_CHAIN,
     MODE_IN_SESSION,
     REVIEW_PERMISSION_MODE as PERMISSION_MODE_BYPASS,
     PERMISSION_MODE_FLAG,
-    RESULT_KEY_BOUND_HASH,
     RESULT_KEY_DIRTY_TREE,
     RESULT_KEY_MODE,
-    RESULT_KEY_PASS_COUNT,
     RESULT_KEY_RETURNCODE,
     RESULT_KEY_SERVED_COMMAND,
-    RESULT_KEY_STAMP_MINTED,
 )
 from dev_env_scripts_constants.grok_worker_constants import (
     MODEL_FLAG,
@@ -109,16 +99,6 @@ def test_chain_failure_preserves_returncode(
     assert review_outcome.returncode == FIXTURE_FAILED_RETURNCODE
     assert review_outcome.is_dirty_tree is False
     assert invoker.is_successful_code_review(review_outcome) is False
-    assert invoker.is_code_review_clean_stamp_allowed(review_outcome) is False
-
-
-def test_clean_stamp_allowed_only_on_successful_clean_serve() -> None:
-    assert invoker.is_code_review_clean_stamp_allowed(CLEAN_SUCCESS_OUTCOME) is True
-    assert invoker.is_code_review_clean_stamp_allowed(DIRTY_SUCCESS_OUTCOME) is False
-    assert invoker.is_code_review_clean_stamp_allowed(FAILED_SERVE_OUTCOME) is False
-    assert invoker.is_code_review_clean_stamp_allowed(IN_SESSION_READY_OUTCOME) is True
-    assert invoker.is_successful_code_review(FAILED_SERVE_OUTCOME) is False
-    assert invoker.is_successful_code_review(CLEAN_SUCCESS_OUTCOME) is True
 
 
 def test_encode_code_review_outcome_shape() -> None:
@@ -157,100 +137,3 @@ def test_validate_effort_token_rejects_unknown_token() -> None:
 def test_build_code_review_prompt_reads_as_slash_command() -> None:
     assert invoker.build_code_review_prompt(EFFORT_LOW) == "/code-review low --fix"
     assert invoker.build_code_review_prompt("xhigh") == "/code-review xhigh --fix"
-
-
-def test_encode_stamp_mint_outcome_includes_mint_metadata() -> None:
-    review_outcome = invoker.CodeReviewOutcome(
-        mode=MODE_CHAIN,
-        served_command=FIXTURE_SERVED_COMMAND,
-        returncode=FIXTURE_CHAIN_RETURNCODE,
-        is_dirty_tree=False,
-    )
-    mint_outcome = invoker.StampMintOutcome(
-        review_outcome=review_outcome,
-        is_stamp_minted=True,
-        pass_count=SINGLE_PASS_CAP,
-        bound_hash="abc123",
-    )
-    encoded_payload = invoker.encode_stamp_mint_outcome(mint_outcome)
-    assert encoded_payload[RESULT_KEY_STAMP_MINTED] is True
-    assert encoded_payload[RESULT_KEY_PASS_COUNT] == SINGLE_PASS_CAP
-    assert encoded_payload[RESULT_KEY_BOUND_HASH] == "abc123"
-
-
-def test_record_stamp_mints_on_surface_stable_clean_pass(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "invoke_code_review", stable_clean_review)
-    mint_outcome = invoker.invoke_code_review_and_record_stamp(
-        working_directory=working_directory,
-        session_model=CODE_REVIEW_MODEL_ALIAS,
-        timeout_seconds=DEFAULT_CODE_REVIEW_TIMEOUT_SECONDS,
-        effort=EFFORT_LOW,
-    )
-    assert mint_outcome.is_stamp_minted is True
-    assert mint_outcome.bound_hash is not None
-    store_module = invoker.load_code_review_stamp_store()
-    assert store_module.stamp_covers_surface(
-        str(working_directory), mint_outcome.bound_hash, EFFORT_LOW
-    )
-
-
-def test_record_stamp_does_not_mint_when_review_changes_surface(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "invoke_code_review", surface_changing_review)
-    mint_outcome = invoker.invoke_code_review_and_record_stamp(
-        working_directory=working_directory,
-        session_model=CODE_REVIEW_MODEL_ALIAS,
-        timeout_seconds=DEFAULT_CODE_REVIEW_TIMEOUT_SECONDS,
-        effort=EFFORT_LOW,
-        maximum_passes=SINGLE_PASS_CAP,
-    )
-    assert mint_outcome.is_stamp_minted is False
-    assert mint_outcome.pass_count == SINGLE_PASS_CAP
-    assert mint_outcome.bound_hash is None
-
-
-def test_record_stamp_hits_cap_without_minting(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "invoke_code_review", DriftingReview())
-    mint_outcome = invoker.invoke_code_review_and_record_stamp(
-        working_directory=working_directory,
-        session_model=CODE_REVIEW_MODEL_ALIAS,
-        timeout_seconds=DEFAULT_CODE_REVIEW_TIMEOUT_SECONDS,
-        effort=EFFORT_LOW,
-        maximum_passes=MAXIMUM_STAMP_MINT_PASSES,
-    )
-    assert mint_outcome.is_stamp_minted is False
-    assert mint_outcome.pass_count == MAXIMUM_STAMP_MINT_PASSES
-
-
-def test_load_code_review_stamp_store_records_and_covers_surface(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    store_module = invoker.load_code_review_stamp_store()
-    surface_hash = store_module.live_surface_hash(str(working_directory))
-    assert surface_hash is not None
-    stamp_path = store_module.record_clean_stamp(
-        str(working_directory), surface_hash, EFFORT_LOW
-    )
-    assert stamp_path.exists()
-    assert store_module.stamp_covers_surface(
-        str(working_directory), surface_hash, EFFORT_LOW
-    )
-
-
-def test_load_code_review_stamp_store_raises_when_file_absent(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    monkeypatch.setattr(
-        invoker, "STAMP_STORE_MODULE_FILE_NAME", MISSING_STORE_FILE_NAME
-    )
-    with pytest.raises(ModuleNotFoundError):
-        invoker.load_code_review_stamp_store()

package/scripts/test_validate_instruction_pairs.py

@@ -0,0 +1,90 @@
+import subprocess
+from pathlib import Path
+
+from validate_instruction_pairs import validate_repository
+
+
+def initialize_repository(repository_root: Path) -> None:
+    subprocess.run(["git", "init", "--quiet"], cwd=repository_root, check=True)
+    subprocess.run(
+        ["git", "config", "user.email", "tests@example.com"],
+        cwd=repository_root,
+        check=True,
+    )
+    subprocess.run(
+        ["git", "config", "user.name", "Instruction tests"],
+        cwd=repository_root,
+        check=True,
+    )
+
+
+def stage_instruction_files(repository_root: Path) -> None:
+    subprocess.run(["git", "add", "AGENTS.md", "CLAUDE.md"], cwd=repository_root, check=True)
+
+
+def test_exact_import_passes(tmp_path: Path) -> None:
+    initialize_repository(tmp_path)
+    (tmp_path / "AGENTS.md").write_bytes(b"# Canonical guidance\n")
+    (tmp_path / "CLAUDE.md").write_bytes(b"@AGENTS.md\n")
+    stage_instruction_files(tmp_path)
+
+    assert validate_repository(tmp_path) == []
+
+
+def test_claude_context_fails_exact_import_check(tmp_path: Path) -> None:
+    initialize_repository(tmp_path)
+    (tmp_path / "AGENTS.md").write_bytes(b"# Canonical guidance\n")
+    (tmp_path / "CLAUDE.md").write_bytes(b"@AGENTS.md\n\nExtra context\n")
+    stage_instruction_files(tmp_path)
+
+    all_errors = validate_repository(tmp_path)
+
+    assert any("exactly import" in each_error for each_error in all_errors)
+
+
+def test_nearest_ancestor_import_passes(tmp_path: Path) -> None:
+    initialize_repository(tmp_path)
+    nested_directory = tmp_path / ".claude"
+    nested_directory.mkdir()
+    (tmp_path / "AGENTS.md").write_bytes(b"# Canonical guidance\n")
+    (nested_directory / "CLAUDE.md").write_bytes(b"@../AGENTS.md\n")
+    subprocess.run(["git", "add", "AGENTS.md", ".claude/CLAUDE.md"], cwd=tmp_path, check=True)
+
+    assert validate_repository(tmp_path) == []
+
+
+def test_crlf_import_fails_line_ending_check(tmp_path: Path) -> None:
+    initialize_repository(tmp_path)
+    (tmp_path / "AGENTS.md").write_bytes(b"# Canonical guidance\n")
+    (tmp_path / "CLAUDE.md").write_bytes(b"@AGENTS.md\r\n")
+    stage_instruction_files(tmp_path)
+
+    all_errors = validate_repository(tmp_path)
+
+    assert any("exactly import" in each_error for each_error in all_errors)
+
+
+def test_executable_import_fails_git_mode_check(tmp_path: Path) -> None:
+    initialize_repository(tmp_path)
+    (tmp_path / "AGENTS.md").write_bytes(b"# Canonical guidance\n")
+    (tmp_path / "CLAUDE.md").write_bytes(b"@AGENTS.md\n")
+    stage_instruction_files(tmp_path)
+    subprocess.run(
+        ["git", "update-index", "--chmod=+x", "CLAUDE.md"],
+        cwd=tmp_path,
+        check=True,
+    )
+
+    all_errors = validate_repository(tmp_path)
+
+    assert any("Git mode 100644" in each_error for each_error in all_errors)
+
+
+def test_untracked_import_fails_tracking_check(tmp_path: Path) -> None:
+    initialize_repository(tmp_path)
+    (tmp_path / "AGENTS.md").write_bytes(b"# Canonical guidance\n")
+    (tmp_path / "CLAUDE.md").write_bytes(b"@AGENTS.md\n")
+
+    all_errors = validate_repository(tmp_path)
+
+    assert any("Git mode 100644" in each_error for each_error in all_errors)

package/scripts/test_verify_installable_package.py

@@ -31,6 +31,7 @@ def test_load_manifest_lists_hooks_and_claude_md() -> None:
     all_root_files = mod.required_root_file_names(manifest)
     assert "hooks" in all_directories
     assert "output-styles" in all_directories
+    assert "AGENTS.md" in all_root_files
     assert "CLAUDE.md" in all_root_files
     assert MANIFEST_FILENAME in all_root_files
 
@@ -58,10 +59,12 @@ def test_surface_appears_in_tarball_members_for_directory_children() -> None:
     all_members = frozenset(
         {
             f"{TARBALL_PACKAGE_PREFIX}hooks/hooks.json",
+            f"{TARBALL_PACKAGE_PREFIX}AGENTS.md",
             f"{TARBALL_PACKAGE_PREFIX}CLAUDE.md",
         }
     )
     assert mod.surface_appears_in_tarball_members("hooks", all_members)
+    assert mod.surface_appears_in_tarball_members("AGENTS.md", all_members)
     assert mod.surface_appears_in_tarball_members("CLAUDE.md", all_members)
     assert not mod.surface_appears_in_tarball_members("missing-dir", all_members)
 
@@ -69,11 +72,12 @@ def test_surface_appears_in_tarball_members_for_directory_children() -> None:
 def test_missing_manifest_surfaces_in_tarball_reports_absent_root_file() -> None:
     manifest = {
         "directories": ["hooks"],
-        "root_files": ["CLAUDE.md", "codex-capability-map.json"],
+        "root_files": ["AGENTS.md", "CLAUDE.md", "codex-capability-map.json"],
     }
     all_members = frozenset(
         {
             f"{TARBALL_PACKAGE_PREFIX}hooks/hooks.json",
+            f"{TARBALL_PACKAGE_PREFIX}AGENTS.md",
             f"{TARBALL_PACKAGE_PREFIX}CLAUDE.md",
         }
     )

package/scripts/tests/AGENTS.md

@@ -0,0 +1,33 @@
+# scripts/tests
+
+pytest suite for the Python scripts and Pester suite for the PowerShell scripts in `scripts/`.
+
+## Test files
+
+| File | Covers |
+|---|---|
+| `test_setup_project_paths.py` | `setup_project_paths.py` — discovery, filtering, and `project-paths.json` writing |
+| `test_setup_project_paths_config.py` | Configuration constants used by `setup_project_paths.py` |
+| `test_sweep_empty_dirs.py` | `sweep_empty_dirs.py` — age check, one-shot mode, and continuous-watch behavior |
+| `test_sync_to_cursor.py` | `sync_to_cursor/` package — mapping, hashing, manifest, and path resolution |
+| `test_grok_worker_constants.py` | `grok_worker_constants.py` — the accepted batch worker-key set stays in step with the worker key constants, and the unknown-key message names both its placeholders |
+
+## PowerShell test files
+
+| File | Covers |
+|---|---|
+| `Get-SessionAccount.Tests.ps1` | `Get-SessionAccount.ps1` — noise filtering, profile-storage email recovery, CLI-vs-desktop account resolution, and output formatting |
+
+## Running
+
+Python scripts (pytest):
+
+```bash
+python -m pytest packages/claude-dev-env/scripts/tests/
+```
+
+PowerShell scripts (Pester 5+, `*.Tests.ps1`):
+
+```powershell
+Invoke-Pester -Path packages/claude-dev-env/scripts/tests/
+```

package/scripts/tests/CLAUDE.md

@@ -1,33 +1 @@
-# scripts/tests
-
-pytest suite for the Python scripts and Pester suite for the PowerShell scripts in `scripts/`.
-
-## Test files
-
-| File | Covers |
-|---|---|
-| `test_setup_project_paths.py` | `setup_project_paths.py` — discovery, filtering, and `project-paths.json` writing |
-| `test_setup_project_paths_config.py` | Configuration constants used by `setup_project_paths.py` |
-| `test_sweep_empty_dirs.py` | `sweep_empty_dirs.py` — age check, one-shot mode, and continuous-watch behavior |
-| `test_sync_to_cursor.py` | `sync_to_cursor/` package — mapping, hashing, manifest, and path resolution |
-| `test_grok_worker_constants.py` | `grok_worker_constants.py` — the accepted batch worker-key set stays in step with the worker key constants, and the unknown-key message names both its placeholders |
-
-## PowerShell test files
-
-| File | Covers |
-|---|---|
-| `Get-SessionAccount.Tests.ps1` | `Get-SessionAccount.ps1` — noise filtering, profile-storage email recovery, CLI-vs-desktop account resolution, and output formatting |
-
-## Running
-
-Python scripts (pytest):
-
-```bash
-python -m pytest packages/claude-dev-env/scripts/tests/
-```
-
-PowerShell scripts (Pester 5+, `*.Tests.ps1`):
-
-```powershell
-Invoke-Pester -Path packages/claude-dev-env/scripts/tests/
-```
+@AGENTS.md

package/scripts/tests/test_codex_compat_materializer.py

@@ -77,6 +77,42 @@ def test_discover_agents_returns_sorted_parsed_agents(tmp_path: Path) -> None:
     assert [agent.name for agent in agents] == ["Alpha", "Zulu"]
 
 
+def test_discover_agents_skips_instruction_aliases_and_keeps_real_agents(
+    tmp_path: Path,
+) -> None:
+    source = tmp_path / "source"
+    source.mkdir()
+    (source / "real-agent.md").write_text(
+        "---\nname: Real Agent\ndescription: real\n---\n",
+        encoding="utf-8",
+    )
+    (source / "CLAUDE.md").write_text("# Guidance\n", encoding="utf-8")
+    try:
+        (source / "AGENTS.md").symlink_to("CLAUDE.md")
+    except OSError as error:
+        pytest.skip(f"symlinks unavailable: {error}")
+
+    agents = materializer.discover_agents(MaterializerConfig(source, tmp_path / "target"))
+
+    assert [agent.name for agent in agents] == ["Real Agent"]
+
+
+def test_discover_agents_rejects_non_alias_reparse_points(tmp_path: Path) -> None:
+    source = tmp_path / "source"
+    source.mkdir()
+    (source / "real-agent.md").write_text(
+        "---\nname: Real Agent\ndescription: real\n---\n",
+        encoding="utf-8",
+    )
+    try:
+        (source / "linked-agent.md").symlink_to("real-agent.md")
+    except OSError as error:
+        pytest.skip(f"symlinks unavailable: {error}")
+
+    with pytest.raises(MaterializerError, match="source reparse point is not allowed"):
+        materializer.discover_agents(MaterializerConfig(source, tmp_path / "target"))
+
+
 def test_content_to_bytes_preserves_bytes_and_encodes_text() -> None:
     assert content_to_bytes(b"payload") == b"payload"
     assert content_to_bytes("payload") == b"payload"
@@ -662,4 +698,3 @@ def test_frontmatter_rejects_non_string_name() -> None:
             "---\nname: 1\ndescription: y\n---\n",
             "bad.md",
         )
-