prizmkit 1.1.128 → 1.1.130

package/bundled/dev-pipeline/tests/test_generate_bootstrap_prompt.py

@@ -1,6 +1,7 @@
 """Tests for generate-bootstrap-prompt.py core functions."""
 
 import json
+import importlib.util
 import os
 import re
 import time
@@ -25,6 +26,7 @@ from generate_bootstrap_prompt import (
     generate_checkpoint_definition,
     merge_checkpoint_state,
     load_active_agent_prompts,
+    validate_rendered,
     main as generate_bootstrap_main,
 )
 from continuation import append_continuation_handoff, checkpoint_cursor
@@ -44,6 +46,69 @@ FORBIDDEN_TEST_CMD_PLACEHOLDER = "(" + "$TEST_CMD" + ")"
 FORBIDDEN_THREE_STRIKE = "3-" + "strike"
 FORBIDDEN_TWENTY_STEP = "20-" + "step window"
 
+REVIEW_PROMPT_REQUIRED = (
+    "The current Main Agent is the only Code Review executor",
+    "Do not invoke another review skill or review workflow",
+    "finder, verifier, audit, compatibility review, verification, or gap sweep",
+    "`review-report.md` is the only persisted review artifact",
+)
+
+REVIEW_PROMPT_FORBIDDEN = (
+    "Orchestrator + Reviewer",
+    "Reviewer reviews",
+    "Reviewer subagents",
+    "Reviewer appends Review Notes",
+    "Implementation Log/Review Notes",
+    "internal Reviewer Agent",
+    "spawning Reviewer",
+    "delayed teammate/reviewer findings",
+    "Gate checks enforce Implementation Log and Review Notes",
+)
+
+
+def assert_unambiguous_main_agent_review(prompt):
+    for required in REVIEW_PROMPT_REQUIRED:
+        assert required in prompt
+    for forbidden in REVIEW_PROMPT_FORBIDDEN:
+        assert forbidden not in prompt
+
+
+PROMPT_RENDERING_FORBIDDEN = (
+    "If implementation is delegated to a Dev subagent",
+    "Document in Implementation Log or review notes",
+    "{{INIT_SCRIPT_PATH}}",
+)
+
+
+def assert_complete_prompt_rendering(prompt):
+    assert_unambiguous_main_agent_review(prompt)
+    for forbidden in PROMPT_RENDERING_FORBIDDEN:
+        assert forbidden not in prompt
+    assert re.findall(r"\{\{[A-Z][A-Z_0-9]+\}\}", prompt) == []
+
+
+def _load_recovery_prompt_module():
+    path = Path("dev-pipeline/scripts/generate-recovery-prompt.py")
+    spec = importlib.util.spec_from_file_location("generate_recovery_prompt", path)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+def test_rendered_prompt_validation_rejects_unresolved_control_placeholders():
+    content = (
+        "## Your Mission\n"
+        "## Execution\n"
+        "Run {{INIT_SCRIPT_PATH}}\n"
+        "## Failure Capture\n"
+    )
+
+    is_valid, warnings, errors = validate_rendered(content)
+
+    assert is_valid is False
+    assert warnings == []
+    assert errors == ["Unreplaced placeholders: {{INIT_SCRIPT_PATH}}"]
+
 
 def scoped_report_text(verdict="PASS", boundary_missing=0,
                        happy_path_only=0, completion_gate="yes",
@@ -884,10 +949,38 @@ class TestDirectOrchestratorImplementationPrompts:
             assert FORBIDDEN_TWENTY_STEP not in rendered
             assert "Main-Agent review loop" in rendered
             assert "up to ten completed rounds" in rendered
-            assert "code-review-specific subagent" in rendered
+            assert "The current Main Agent is the only Code Review executor" in rendered
+            assert "Do not invoke another review skill or review workflow" in rendered
             assert "low=0" not in rendered
             assert "Reviewer 3" not in rendered
 
+    def test_all_rendered_pipeline_prompts_have_one_main_agent_review_model(self, tmp_path):
+        recovery = _load_recovery_prompt_module()
+        prompts = [
+            _render_feature_prompt(tmp_path / "feature-lite", mode="lite"),
+            _render_feature_prompt(tmp_path / "feature-standard", mode="standard"),
+            _render_feature_prompt(tmp_path / "feature-full", mode="full"),
+            _render_feature_prompt(
+                tmp_path / "feature-tier3",
+                mode="full",
+                template="bootstrap-tier3.md",
+            ),
+            _render_bugfix_prompt(tmp_path / "bugfix"),
+            _render_refactor_prompt(tmp_path / "refactor"),
+            recovery.build_bugfix_prompt(
+                {
+                    "workflow_type": "bug-fix-workflow",
+                    "phase": 5,
+                    "phase_name": "Review",
+                    "workflow_data": {"bug_id": "B-001"},
+                },
+                str(tmp_path),
+            ),
+        ]
+
+        for prompt in prompts:
+            assert_complete_prompt_rendering(prompt)
+
     def test_retained_tier3_fallback_template_uses_direct_orchestrator_implementation(self):
         rendered = Path("dev-pipeline/templates/bootstrap-tier3.md").read_text(encoding="utf-8")
 
@@ -1217,7 +1310,7 @@ class TestFeaturePromptUnifiedFullGuidance:
             assert "### Scoped Feature Test Gate — PrizmKit Test" in prompt
             assert "## Test Failure Recovery Protocol" in prompt
             assert "Boundary Matrix" in prompt
-            assert "### Browser Verification — MANDATORY" in prompt
+            assert "### Browser Verification — MANDATORY" not in prompt
             assert "### TERMINAL STOP — Commit Completed" in prompt
             assert "# Dev-Pipeline Session Bootstrap — Tier 1" not in prompt
             assert "# Dev-Pipeline Session Bootstrap — Tier 2" not in prompt
@@ -1327,7 +1420,99 @@ class TestBrowserBlockingPromptPolicy:
             assert "Failures do NOT block the commit" not in prompt
 
 
-class TestManualHybridBugfixPromptPolicy:
+class TestBrowserOptInPromptPolicy:
+    @staticmethod
+    def _rendered_outputs(tmp_path, browser_interaction=None, env_value=None):
+        previous_env = os.environ.get("BROWSER_VERIFY")
+        if env_value is None:
+            os.environ.pop("BROWSER_VERIFY", None)
+        else:
+            os.environ["BROWSER_VERIFY"] = env_value
+        try:
+            feature_prompt = _render_feature_prompt(
+                tmp_path / "feature", browser_interaction=browser_interaction,
+            )
+            bugfix_prompt = _render_bugfix_prompt(
+                tmp_path / "bugfix",
+                bug_overrides=(
+                    {"browser_interaction": browser_interaction}
+                    if browser_interaction is not None else None
+                ),
+            )
+            refactor_prompt = _render_refactor_prompt(
+                tmp_path / "refactor",
+                refactor_overrides=(
+                    {"browser_interaction": browser_interaction}
+                    if browser_interaction is not None else None
+                ),
+            )
+            return feature_prompt, bugfix_prompt, refactor_prompt
+        finally:
+            if previous_env is None:
+                os.environ.pop("BROWSER_VERIFY", None)
+            else:
+                os.environ["BROWSER_VERIFY"] = previous_env
+
+    @staticmethod
+    def _checkpoint_skills(project_root, family):
+        if family == "feature":
+            pattern = "**/workflow-checkpoint.json"
+        elif family == "bugfix":
+            pattern = "**/bugfix/B-001/workflow-checkpoint.json"
+        else:
+            pattern = "**/refactor/R-001/workflow-checkpoint.json"
+        path = next(project_root.glob(pattern))
+        return [step["skill"] for step in json.loads(path.read_text(encoding="utf-8"))["steps"]]
+
+    def test_omitted_browser_interaction_disables_browser_for_all_families(self, tmp_path):
+        prompts = self._rendered_outputs(tmp_path / "omitted")
+
+        for prompt in prompts:
+            assert "Browser Verification" not in prompt
+            assert "playwright-cli" not in prompt
+            assert "opencli" not in prompt
+            assert "development-server" not in prompt
+            assert "browser-dev-server.pid" not in prompt
+
+        assert "browser-verification" not in self._checkpoint_skills(tmp_path / "omitted" / "feature", "feature")
+        assert "browser-verification" not in self._checkpoint_skills(tmp_path / "omitted" / "bugfix", "bugfix")
+        assert "browser-verification" not in self._checkpoint_skills(tmp_path / "omitted" / "refactor", "refactor")
+
+    def test_explicit_browser_interaction_preserves_configuration_for_all_families(self, tmp_path):
+        browser_interaction = {
+            "tool": "playwright-cli",
+            "verify_steps": ["Open the page", "Submit the form"],
+        }
+        prompts = self._rendered_outputs(tmp_path / "explicit", browser_interaction)
+
+        for prompt in prompts:
+            assert "Browser Verification" in prompt
+            assert "Browser Verification (playwright-cli)" in prompt
+            assert "playwright-cli" in prompt
+            assert "opencli" not in prompt
+            assert "Goal 1: Open the page" in prompt
+            assert "Goal 2: Submit the form" in prompt
+
+        assert "browser-verification" in self._checkpoint_skills(tmp_path / "explicit" / "feature", "feature")
+        assert "browser-verification" in self._checkpoint_skills(tmp_path / "explicit" / "bugfix", "bugfix")
+        assert "browser-verification" in self._checkpoint_skills(tmp_path / "explicit" / "refactor", "refactor")
+
+    def test_global_disable_suppresses_explicit_browser_for_all_families(self, tmp_path):
+        prompts = self._rendered_outputs(
+            tmp_path / "global-disable",
+            {"tool": "opencli", "verify_steps": ["Open the page"]},
+            env_value="false",
+        )
+
+        for prompt in prompts:
+            assert "Browser Verification" not in prompt
+            assert "opencli" not in prompt
+            assert "browser-dev-server.pid" not in prompt
+
+        assert "browser-verification" not in self._checkpoint_skills(tmp_path / "global-disable" / "feature", "feature")
+        assert "browser-verification" not in self._checkpoint_skills(tmp_path / "global-disable" / "bugfix", "bugfix")
+        assert "browser-verification" not in self._checkpoint_skills(tmp_path / "global-disable" / "refactor", "refactor")
+
     def test_fresh_manual_bugfix_prompt_stops_before_commit_phase(self, tmp_path):
         prompt = _render_bugfix_prompt(
             tmp_path / "fresh-manual-bugfix",
@@ -1446,7 +1631,8 @@ class TestHeadlessPromptCleanupF033:
 
         assert "{{" + "REVIEWER_" + "SUBAGENT_PATH" + "}}" not in replacements
         assert "Main-Agent review loop" in refactor_prompt
-        assert "code-review-specific subagent" in refactor_prompt
+        assert "The current Main Agent is the only Code Review executor" in refactor_prompt
+        assert "Do not invoke another review skill or review workflow" in refactor_prompt
         assert "Reviewer 3" not in refactor_prompt
 
     def test_bugfix_refactor_explicit_codex_override(self, tmp_path, monkeypatch):
@@ -1469,7 +1655,8 @@ class TestHeadlessPromptCleanupF033:
 
         assert "{{" + "REVIEWER_" + "SUBAGENT_PATH" + "}}" not in replacements
         assert "Main-Agent review loop" in refactor_prompt
-        assert "code-review-specific subagent" in refactor_prompt
+        assert "The current Main Agent is the only Code Review executor" in refactor_prompt
+        assert "Do not invoke another review skill or review workflow" in refactor_prompt
         assert "Reviewer 3" not in refactor_prompt
 
 

package/bundled/dev-pipeline/tests/test_python_runner_parity.py

@@ -1408,7 +1408,8 @@ def test_default_no_worktree_preserves_main_worktree_branch_launch(monkeypatch,
             lifecycle_order.append("branch_create")
             branch_events.append(("create", plan.commands[1].args[2]))
         if plan.name == "branch_merge":
-            branch_events.append(("merge", plan.commands[5].args[2]))
+            merge_command = next(command for command in plan.commands if command.args[:2] == ("merge", "--ff-only"))
+            branch_events.append(("merge", merge_command.args[2]))
         return SimpleNamespace(ok=True, plan=plan, results=())
 
     def fake_start_item(*args, **kwargs):
@@ -1603,6 +1604,79 @@ def test_worktree_recovers_completed_pending_branch_from_base_session_history(mo
     assert merge_calls and cleanup_calls[-1][1] is True
 
 
+def test_success_final_commit_failure_preserves_checkout_without_merge(monkeypatch, tmp_path):
+    from prizmkit_runtime import runners
+    from prizmkit_runtime.runner_models import family_for, parse_invocation
+    from prizmkit_runtime.task_checkout import load_task_checkout
+
+    monkeypatch.setenv("DEV_BRANCH", "dev/F-001-finalize-fail")
+    paths = _make_paths(tmp_path)
+    family = family_for("feature", paths)
+    invocation = parse_invocation(family, "run", ())
+    invocation = invocation.__class__(**{**invocation.__dict__, "list_path": paths.feature_plan})
+    _install_runner_session_fakes(monkeypatch, runners)
+    merge_calls = []
+
+    monkeypatch.setattr(
+        runners,
+        "commit_final_bookkeeping",
+        lambda *args, **kwargs: SimpleNamespace(ok=False, attempted=True, committed=False),
+    )
+    monkeypatch.setattr(
+        runners,
+        "commit_task_branch_changes",
+        lambda *args, **kwargs: SimpleNamespace(ok=True, attempted=False, committed=False),
+    )
+    monkeypatch.setattr(
+        runners,
+        "run_git_plan",
+        lambda root, plan: merge_calls.append(plan.name) or SimpleNamespace(ok=True, plan=plan, results=()),
+    )
+
+    status = runners._process_item(family, invocation, "F-001", paths, initial_metadata={})
+
+    assert status == "completed"
+    assert "branch_merge" not in merge_calls
+    checkout = load_task_checkout(family.state_dir, family.task_type, "F-001")
+    assert checkout is not None and checkout.is_active
+    session_status = paths.feature_state_dir / "F-001" / "sessions" / "F-001-session-1" / "session-status.json"
+    assert json.loads(session_status.read_text(encoding="utf-8"))["status"] == "merge_conflict"
+
+
+def test_wip_commit_failure_skips_base_return(monkeypatch, tmp_path):
+    from prizmkit_runtime import runners
+    from prizmkit_runtime.runner_models import family_for, parse_invocation
+
+    monkeypatch.setenv("DEV_BRANCH", "dev/F-001-wip-fail")
+    paths = _make_paths(tmp_path)
+    family = family_for("feature", paths)
+    invocation = parse_invocation(family, "run", ())
+    invocation = invocation.__class__(**{**invocation.__dict__, "list_path": paths.feature_plan})
+    _install_runner_session_fakes(monkeypatch, runners, statuses=("crashed",), update_status="failed")
+    returns = []
+
+    monkeypatch.setattr(
+        runners,
+        "commit_wip_changes",
+        lambda *args, **kwargs: SimpleNamespace(ok=False, attempted=True, committed=False),
+    )
+    monkeypatch.setattr(
+        runners,
+        "branch_ensure_return",
+        lambda *args, **kwargs: returns.append(args) or SimpleNamespace(ok=True),
+    )
+    monkeypatch.setattr(
+        runners,
+        "run_git_plan",
+        lambda root, plan: SimpleNamespace(ok=True, plan=plan, results=()),
+    )
+
+    status = runners._process_item(family, invocation, "F-001", paths, initial_metadata={})
+
+    assert status == "failed"
+    assert returns == []
+
+
 def test_default_branch_names_keep_timestamp_for_each_runner_family(monkeypatch, tmp_path):
     from prizmkit_runtime import runners
     from prizmkit_runtime.runner_models import family_for
@@ -1752,7 +1826,7 @@ def test_foreground_runner_emits_structured_feature_progress(monkeypatch, tmp_pa
     assert "Feature: F-001 — Readable output" in captured.err
     assert "Code retry: 1 / 3" in captured.err
     assert "Preflight: no user-visible changes to preserve before feature task F-001" in captured.err
-    assert "Pipeline mode: full (Tier 3 — Orchestrator + Reviewer)" in captured.err
+    assert "Pipeline mode: full (Tier 3 — Main-Agent Full Guardrails)" in captured.err
     assert "Agents: 3" in captured.err
     assert "Spawning AI CLI session: F-001-session-1" in captured.err
     assert "Session result: success" in captured.err
@@ -2098,24 +2172,27 @@ def test_preflight_ready_commit_includes_tracked_state_but_excludes_untracked_st
     assert untracked_state.relative_to(tmp_path).as_posix() not in _head_files(tmp_path)
 
 
-def test_preflight_ready_commit_includes_tracked_framework_support_but_excludes_untracked_support_and_state(tmp_path):
+def test_preflight_ready_commit_excludes_tracked_framework_manifest_but_preserves_other_tracked_support(tmp_path):
     from prizmkit_runtime.runner_bookkeeping import commit_preflight_ready_changes
 
     _init_bookkeeping_repo(tmp_path)
+    manifest_path = tmp_path / ".prizmkit" / "manifest.json"
     tracked_support_paths = [
-        tmp_path / ".prizmkit" / "manifest.json",
         tmp_path / ".prizmkit" / "dev-pipeline" / "prizmkit_runtime" / "runners.py",
         tmp_path / ".claude" / "commands" / "prizmkit.md",
     ]
+    manifest_path.parent.mkdir(parents=True, exist_ok=True)
+    manifest_path.write_text('{"version":"1.1.127"}\n', encoding="utf-8")
     for path in tracked_support_paths:
         path.parent.mkdir(parents=True, exist_ok=True)
         path.write_text("installed\n", encoding="utf-8")
     subprocess.run(
-        ["git", "add", *(path.relative_to(tmp_path).as_posix() for path in tracked_support_paths)],
+        ["git", "add", manifest_path.relative_to(tmp_path).as_posix(), *(path.relative_to(tmp_path).as_posix() for path in tracked_support_paths)],
         cwd=tmp_path,
         check=True,
     )
     subprocess.run(["git", "commit", "-m", "track support"], cwd=tmp_path, check=True, stdout=subprocess.DEVNULL)
+    manifest_path.write_text('{"version":"1.1.128"}\n', encoding="utf-8")
     for path in tracked_support_paths:
         path.write_text("upgraded\n", encoding="utf-8")
 
@@ -2129,19 +2206,23 @@ def test_preflight_ready_commit_includes_tracked_framework_support_but_excludes_
         path.write_text("transient\n", encoding="utf-8")
 
     result = commit_preflight_ready_changes(tmp_path, "B-001")
-    committed_files = _head_files(tmp_path)
 
-    assert result.committed is True
-    assert {path.relative_to(tmp_path).as_posix() for path in tracked_support_paths}.issubset(committed_files)
-    assert not {path.relative_to(tmp_path).as_posix() for path in untracked_support_paths}.intersection(committed_files)
-    assert _head_message(tmp_path) == "chore: ready for B-001"
+    assert result.attempted is True
+    assert result.committed is False
+    assert result.result is not None
+    assert "installer-owned .prizmkit/manifest.json" in result.result.stderr
+    assert _head_message(tmp_path) == "track support"
     assert subprocess.run(
         ["git", "status", "--short", "--untracked-files=no"],
         cwd=tmp_path,
         check=True,
         stdout=subprocess.PIPE,
         text=True,
-    ).stdout == ""
+    ).stdout.splitlines() == [
+        " M .claude/commands/prizmkit.md",
+        " M .prizmkit/dev-pipeline/prizmkit_runtime/runners.py",
+        " M .prizmkit/manifest.json",
+    ]
 
 
 def test_preflight_ready_commit_excludes_untracked_support_assets_and_state(tmp_path):
@@ -2176,6 +2257,53 @@ def test_preflight_ready_commit_excludes_untracked_support_assets_and_state(tmp_
     assert ".claude" in hidden_status or ".prizmkit/state" in hidden_status
 
 
+def test_preflight_ready_commit_rejects_unmerged_index(tmp_path):
+    from prizmkit_runtime.runner_bookkeeping import commit_preflight_ready_changes
+
+    _init_bookkeeping_repo(tmp_path)
+    subprocess.run(["git", "checkout", "-b", "other"], cwd=tmp_path, check=True, stdout=subprocess.DEVNULL)
+    (tmp_path / "staged.txt").write_text("other\n", encoding="utf-8")
+    subprocess.run(["git", "commit", "-am", "other"], cwd=tmp_path, check=True, stdout=subprocess.DEVNULL)
+    subprocess.run(["git", "checkout", "main"], cwd=tmp_path, check=True, stdout=subprocess.DEVNULL)
+    (tmp_path / "staged.txt").write_text("main\n", encoding="utf-8")
+    subprocess.run(["git", "commit", "-am", "main"], cwd=tmp_path, check=True, stdout=subprocess.DEVNULL)
+    subprocess.run(["git", "merge", "other"], cwd=tmp_path, check=False, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+    before_count = _head_commit_count(tmp_path)
+
+    result = commit_preflight_ready_changes(tmp_path, "F-126")
+
+    assert result.attempted is True
+    assert result.committed is False
+    assert result.result is not None
+    assert "unmerged Git paths" in result.result.stderr
+    assert _head_commit_count(tmp_path) == before_count
+
+
+def test_preflight_ready_commit_rejects_conflict_markers_and_malformed_manifest(tmp_path):
+    from prizmkit_runtime.runner_bookkeeping import commit_preflight_ready_changes
+
+    _init_bookkeeping_repo(tmp_path)
+    (tmp_path / "unstaged.txt").write_text("<<<<<<< Updated upstream\ncurrent\n=======\nstashed\n>>>>>>> Stashed changes\n", encoding="utf-8")
+
+    marker_result = commit_preflight_ready_changes(tmp_path, "F-127")
+
+    assert marker_result.committed is False
+    assert marker_result.result is not None
+    assert "unresolved conflict markers" in marker_result.result.stderr
+
+    (tmp_path / "unstaged.txt").write_text("safe\n", encoding="utf-8")
+    manifest = tmp_path / ".prizmkit" / "manifest.json"
+    manifest.parent.mkdir(parents=True, exist_ok=True)
+    manifest.write_text("<<<<<<< Updated upstream\n{}\n", encoding="utf-8")
+
+    manifest_result = commit_preflight_ready_changes(tmp_path, "F-128")
+
+    assert manifest_result.committed is False
+    assert manifest_result.result is not None
+    assert ".prizmkit/manifest.json" in manifest_result.result.stderr
+    assert "valid JSON" in manifest_result.result.stderr
+
+
 def test_preflight_ready_commit_noops_when_workspace_has_no_visible_dirty_content(tmp_path):
     from prizmkit_runtime.runner_bookkeeping import commit_preflight_ready_changes