@hunter-harness/workflow-harness 0.2.15 → 0.2.17

package/harness/bundles/java/cursor/scripts/harness_ledger.py

@@ -100,6 +100,37 @@ def emit_json(payload: dict[str, Any], *, as_json: bool) -> None:
             sys.stdout.write(("ok" if ok else "error") + "\n")
 
 
+def _compact_record_payload(payload: dict[str, Any]) -> dict[str, Any]:
+    """C5: record compact — ok/action/verification/status only."""
+    return {
+        "ok": payload.get("ok", True),
+        "action": payload.get("action"),
+        "verification": payload.get("verification"),
+        "status": payload.get("status"),
+    }
+
+
+def _compact_can_reuse_payload(payload: dict[str, Any]) -> dict[str, Any]:
+    """C5: can-reuse compact — ok/reuse/code only."""
+    return {
+        "ok": payload.get("ok", True),
+        "reuse": payload.get("reuse"),
+        "code": payload.get("code"),
+    }
+
+
+def emit_compact_or_verbose(
+    payload: dict[str, Any],
+    *,
+    as_json: bool,
+    verbose: bool,
+    compact_fn,
+) -> None:
+    """Emit compact payload by default; full payload when --verbose."""
+    out = payload if verbose else compact_fn(payload)
+    emit_json(out, as_json=as_json)
+
+
 def emit_error(message: str, *, as_json: bool, code: int = 1) -> int:
     payload = {"ok": False, "error": message}
     if as_json:
@@ -1227,6 +1258,7 @@ def cmd_hash(args: argparse.Namespace) -> int:
 
 def cmd_can_reuse(args: argparse.Namespace) -> int:
     as_json = bool(args.json)
+    verbose = bool(getattr(args, "verbose", False))
     verification = args.verification
     if verification not in VERIFICATIONS:
         return emit_error(
@@ -1253,7 +1285,10 @@ def cmd_can_reuse(args: argparse.Namespace) -> int:
                 "verification": verification,
                 "detail": err,
             }
-            emit_json(payload, as_json=as_json)
+            emit_compact_or_verbose(
+                payload, as_json=as_json, verbose=verbose,
+                compact_fn=_compact_can_reuse_payload,
+            )
             return 0
         files = resolve_input_files(resolved_files, project_root)
     if not files:
@@ -1275,12 +1310,16 @@ def cmd_can_reuse(args: argparse.Namespace) -> int:
     except (OSError, ValueError, json.JSONDecodeError) as exc:
         return emit_error(f"can-reuse failed: {exc}", as_json=as_json)
 
-    emit_json(payload, as_json=as_json)
+    emit_compact_or_verbose(
+        payload, as_json=as_json, verbose=verbose,
+        compact_fn=_compact_can_reuse_payload,
+    )
     return 0
 
 
 def cmd_record(args: argparse.Namespace) -> int:
     as_json = bool(args.json)
+    verbose = bool(getattr(args, "verbose", False))
     change_dir = resolve_path(args.change_dir)
     verification = args.verification
     if verification not in VERIFICATIONS:
@@ -1421,6 +1460,16 @@ def cmd_record(args: argparse.Namespace) -> int:
             if _nonempty_str(getattr(args, "tests_reused_from", None)):
                 entry["testsReusedFrom"] = str(args.tests_reused_from).strip()
 
+        # C9: bind scenario IDs from --scenario-ids to this ledger entry.
+        scenario_ids_raw = getattr(args, "scenario_ids", None)
+        if _nonempty_str(scenario_ids_raw):
+            ids = [s.strip() for s in str(scenario_ids_raw).split(",") if s.strip()]
+            if ids:
+                entry["scenarioIds"] = ids
+        elif "scenarioIds" in entry:
+            # Fresh record without scenario-ids must not keep stale ids from prev.
+            entry.pop("scenarioIds", None)
+
         ledger["validations"][verification] = entry
         if "changeName" not in ledger:
             ledger["changeName"] = change_dir.name
@@ -1487,7 +1536,10 @@ def cmd_record(args: argparse.Namespace) -> int:
         "diffHash": ledger.get("diffHash"),
         "resolvedProjectRoot": str(project_root) if project_root else None,
     }
-    emit_json(payload, as_json=as_json)
+    emit_compact_or_verbose(
+        payload, as_json=as_json, verbose=verbose,
+        compact_fn=_compact_record_payload,
+    )
     return 0
 
 
@@ -1589,6 +1641,11 @@ def build_parser() -> argparse.ArgumentParser:
         default=None,
         help="optional environment hash to compare against ledger entry (UT-017)",
     )
+    p_reuse.add_argument(
+        "--verbose",
+        action="store_true",
+        help="emit full payload (default: compact ok/reuse/code)",
+    )
     p_reuse.set_defaults(func=cmd_can_reuse)
 
     p_record = sub.add_parser("record", parents=[shared_json], help="write validation result into ledger")
@@ -1669,6 +1726,16 @@ def build_parser() -> argparse.ArgumentParser:
         default=None,
         help="ledger v3: scope reason (required when --applicability NOT_APPLICABLE)",
     )
+    p_record.add_argument(
+        "--scenario-ids",
+        default=None,
+        help="comma-separated scenario IDs from scenario-manifest.json to bind to this entry",
+    )
+    p_record.add_argument(
+        "--verbose",
+        action="store_true",
+        help="emit full payload (default: compact ok/action/verification/status)",
+    )
     p_record.set_defaults(func=cmd_record)
 
     p_diff = sub.add_parser(

package/harness/bundles/java/cursor/scripts/harness_paths.py

@@ -83,6 +83,23 @@ def _git_common_dir(cwd: Path) -> Path | None:
     return common
 
 
+def common_root(project_root: Path) -> Path:
+    """Resolve the shared "common" root for a project.
+
+    For a linked worktree, ``git rev-parse --git-common-dir`` points at the
+    main repository's ``.git`` directory; its parent is the main project root.
+    For the main worktree, the common dir is ``<root>/.git`` so the parent is
+    the project root itself. Falls back to the resolved input when not in a
+    git repo (e.g. exploratory scratch dirs).
+    """
+    cwd = Path(project_root).resolve()
+    common = _git_common_dir(cwd)
+    if common is None:
+        return cwd
+    # common dir is <root>/.git — its parent is the main project root.
+    return common.parent.resolve()
+
+
 def _root_commit(cwd: Path) -> str | None:
     raw = _git_text(cwd, "rev-list", "--max-parents=0", "HEAD")
     if not raw:

package/harness/bundles/java/cursor/scripts/harness_plan_finalize.py

@@ -30,11 +30,117 @@ if hasattr(sys.stderr, "reconfigure"):
 SCHEMA_VERSION = 1
 _LINK = re.compile(r"\[[^\]]+\]\(([^)]+)\)")
 
+# C8: valid ownerPhase values (lifecycle phases that can own tasks).
+VALID_OWNER_PHASES = {"plan", "run", "test", "review", "submit"}
+
+# C9: map scenario priority to required evidence kind.
+PRIORITY_EVIDENCE_KIND = {
+    "P0": "ledger",
+    "P1": "ledger",
+    "P2": "advisory",
+}
+
 
 def _result_error(code: str, message: str) -> dict[str, Any]:
     return {"ok": False, "code": code, "error": message}
 
 
+def parse_test_scenarios(scenarios_path: Path) -> list[dict[str, str]]:
+    """C9: parse test-scenarios.md tables, extracting scenario rows.
+
+    Returns a list of dicts with keys: id / priority / scenario / verification /
+    ownerPhase / requiredEvidenceKind (last one derived from priority).
+    """
+    text = Path(scenarios_path).read_text(encoding="utf-8-sig")
+    lines = text.splitlines()
+    scenarios: list[dict[str, str]] = []
+    # Find all tables whose header includes "ID" and "优先级" (or "priority").
+    i = 0
+    while i < len(lines):
+        line = lines[i].strip()
+        if line.startswith("|") and "ID" in line and ("优先级" in line or "priority" in line):
+            header_line = line
+            headers = [h.strip() for h in header_line.strip("|").split("|")]
+            col_map: dict[str, int] = {}
+            for idx, name in enumerate(headers):
+                key = name.lower()
+                col_map[key] = idx
+            # Skip separator row
+            i += 2
+            while i < len(lines):
+                row = lines[i].strip()
+                if not row.startswith("|"):
+                    break
+                cells = [c.strip() for c in row.strip("|").split("|")]
+                if len(cells) < len(headers):
+                    i += 1
+                    continue
+                scenario: dict[str, str] = {}
+                for cn, en in (
+                    ("ID", "id"),
+                    ("优先级", "priority"),
+                    ("场景", "scenario"),
+                    ("验证方式", "verification"),
+                    ("owner phase", "ownerPhase"),
+                ):
+                    if cn.lower() in col_map:
+                        scenario[en] = cells[col_map[cn.lower()]]
+                # Derive requiredEvidenceKind from priority
+                priority = scenario.get("priority", "")
+                scenario["requiredEvidenceKind"] = PRIORITY_EVIDENCE_KIND.get(priority, "advisory")
+                scenarios.append(scenario)
+                i += 1
+            continue
+        i += 1
+    return scenarios
+
+
+def parse_plan_tasks(plan_path: Path) -> list[dict[str, str]]:
+    """C8: parse plan.md task table rows, extracting optional ownerPhase/implementationDoneWhen/verificationPhase columns.
+
+    Returns a list of dicts with keys: # / 簇 / 任务 / ownerPhase / implementationDoneWhen /
+    verificationPhase / requiresExplicitAuthority (last four optional, only present when
+    the column header includes them).
+    """
+    text = Path(plan_path).read_text(encoding="utf-8-sig")
+    lines = text.splitlines()
+    # Find the task table: a header row starting with "| #" followed by a separator row.
+    header_idx = -1
+    for i, line in enumerate(lines):
+        stripped = line.strip()
+        if stripped.startswith("|") and "#" in stripped and "任务" in stripped:
+            header_idx = i
+            break
+    if header_idx < 0:
+        return []
+    header_line = lines[header_idx]
+    headers = [h.strip() for h in header_line.strip().strip("|").split("|")]
+    # Map header names to column indices (case-insensitive, English keys).
+    col_map: dict[str, int] = {}
+    for idx, name in enumerate(headers):
+        key = name.lower()
+        col_map[key] = idx
+    tasks: list[dict[str, str]] = []
+    for line in lines[header_idx + 2 :]:  # skip header + separator
+        stripped = line.strip()
+        if not stripped.startswith("|"):
+            break  # end of table
+        cells = [c.strip() for c in stripped.strip("|").split("|")]
+        if len(cells) < len(headers):
+            continue
+        task: dict[str, str] = {}
+        # Chinese headers
+        for cn, en in (("#", "num"), ("簇", "cluster"), ("任务", "task")):
+            if cn in col_map:
+                task[en] = cells[col_map[cn]]
+        # English optional columns
+        for en in ("ownerPhase", "implementationDoneWhen", "verificationPhase", "requiresExplicitAuthority"):
+            if en.lower() in col_map:
+                task[en] = cells[col_map[en.lower()]]
+        tasks.append(task)
+    return tasks
+
+
 def _atomic_write_json(path: Path, payload: dict[str, Any]) -> None:
     path.parent.mkdir(parents=True, exist_ok=True)
     fd, raw_tmp = tempfile.mkstemp(
@@ -146,6 +252,21 @@ def validate_staging(staging: Path, change_name: str) -> dict[str, Any]:
                         f"{rel.as_posix()}: missing reference {raw_link}",
                     )
 
+    # C8: validate ownerPhase values in plan.md task table.
+    plan_path = staging / "plans" / f"{change_name}-plan.md"
+    tasks = parse_plan_tasks(plan_path)
+    for task in tasks:
+        owner = task.get("ownerPhase")
+        if owner is not None and owner != "" and owner not in VALID_OWNER_PHASES:
+            return _result_error(
+                "PLAN_OWNER_PHASE_INVALID",
+                f"task {task.get('num', '?')}: ownerPhase '{owner}' not in {sorted(VALID_OWNER_PHASES)}",
+            )
+
+    # C9: parse test-scenarios.md for scenario manifest.
+    scenarios_path = staging / "plans" / f"{change_name}-test-scenarios.md"
+    scenarios = parse_test_scenarios(scenarios_path)
+
     digest = hashlib.sha256()
     artifact_names: list[str] = []
     for path in files:
@@ -159,6 +280,8 @@ def validate_staging(staging: Path, change_name: str) -> dict[str, Any]:
         "ok": True,
         "files": artifact_names,
         "artifactsHash": "sha256:" + digest.hexdigest(),
+        "tasks": tasks,
+        "scenarios": scenarios,
     }
 
 
@@ -177,6 +300,152 @@ def _terminal_exists(change_dir: Path, run_id: str, attempt: int) -> bool:
     )
 
 
+def verify_plan(change_dir: Path) -> dict[str, Any]:
+    """Read-only verification of a finalized plan (retro §5.8).
+
+    Validates the published artifacts, receipt and events stream without
+    requiring the original staging directory. Returns the artifact hash,
+    phase.end count/status, frontmatter, and consistency checks. Any parse
+    error or inconsistency results in ok=false with a non-zero exit code.
+    """
+    change_dir = change_dir.resolve()
+    receipt_path = change_dir / "meta" / "plan-finalization.json"
+    if not receipt_path.is_file():
+        return _result_error("RECEIPT_MISSING", f"receipt not found: {receipt_path}")
+
+    try:
+        receipt = json.loads(receipt_path.read_text(encoding="utf-8-sig"))
+    except (OSError, json.JSONDecodeError) as exc:
+        return _result_error("RECEIPT_INVALID", str(exc))
+    if not isinstance(receipt, dict):
+        return _result_error("RECEIPT_INVALID", "receipt top-level must be an object")
+
+    change_name = str(receipt.get("changeName") or "").strip()
+    if not change_name:
+        return _result_error("RECEIPT_INVALID", "receipt missing changeName")
+
+    expected_hash = str(receipt.get("artifactsHash") or "").strip()
+    if not expected_hash.startswith("sha256:"):
+        return _result_error("RECEIPT_INVALID", "receipt artifactsHash missing or malformed")
+
+    files_list = receipt.get("files")
+    if not isinstance(files_list, list) or not files_list:
+        return _result_error("RECEIPT_INVALID", "receipt files list missing or empty")
+
+    # Recompute artifacts hash from published files.
+    digest = hashlib.sha256()
+    artifact_names: list[str] = []
+    for rel_text in files_list:
+        rel = rel_text.as_posix() if hasattr(rel_text, "as_posix") else str(rel_text)
+        target = change_dir / rel
+        if not target.is_file():
+            return _result_error(
+                "ARTIFACT_MISSING", f"published artifact missing: {rel}"
+            )
+        artifact_names.append(rel)
+        digest.update(rel.encode("utf-8"))
+        digest.update(b"\0")
+        digest.update(target.read_bytes())
+        digest.update(b"\0")
+    actual_hash = "sha256:" + digest.hexdigest()
+    if actual_hash != expected_hash:
+        return _result_error(
+            "ARTIFACT_HASH_DRIFT",
+            f"published artifacts hash {actual_hash} != receipt {expected_hash}",
+        )
+
+    # Validate frontmatter on markdown artifacts.
+    frontmatter_results: dict[str, Any] = {}
+    for rel in artifact_names:
+        if not rel.endswith(".md"):
+            continue
+        target = change_dir / rel
+        try:
+            text = target.read_text(encoding="utf-8-sig")
+        except OSError as exc:
+            return _result_error("ARTIFACT_UNREADABLE", f"{rel}: {exc}")
+        fm = _frontmatter(text)
+        if fm is None:
+            return _result_error(
+                "ARTIFACT_FRONTMATTER_MISSING", f"{rel}: no frontmatter"
+            )
+        if fm.get("change-name") != change_name:
+            return _result_error(
+                "ARTIFACT_FRONTMATTER_INVALID",
+                f"{rel}: change-name '{fm.get('change-name')}' != '{change_name}'",
+            )
+        frontmatter_results[rel] = {
+            "change-name": fm.get("change-name"),
+            "status": fm.get("status"),
+        }
+
+    # Validate gate-policy.json is parseable JSON.
+    gate_policy_path = change_dir / "meta" / "gate-policy.json"
+    gate_policy_consistent = True
+    if gate_policy_path.is_file():
+        try:
+            json.loads(gate_policy_path.read_text(encoding="utf-8-sig"))
+        except (OSError, json.JSONDecodeError):
+            gate_policy_consistent = False
+    else:
+        gate_policy_consistent = False
+
+    # Validate events.ndjson: count phase.end, check for parse errors.
+    events_path = change_dir / "events.ndjson"
+    phase_end_count = 0
+    phase_end_status: str | None = None
+    events_parse_errors: list[str] = []
+    if events_path.is_file():
+        for line_no, line in enumerate(events_path.read_text(encoding="utf-8").splitlines(), 1):
+            if not line.strip():
+                continue
+            try:
+                event = json.loads(line)
+            except json.JSONDecodeError as exc:
+                events_parse_errors.append(f"line {line_no}: {exc}")
+                continue
+            if not isinstance(event, dict):
+                events_parse_errors.append(f"line {line_no}: not an object")
+                continue
+            if (
+                event.get("phase") == "plan"
+                and event.get("type") == "phase.end"
+            ):
+                phase_end_count += 1
+                phase_end_status = str(event.get("status") or "").upper()
+    else:
+        events_parse_errors.append("events.ndjson missing")
+
+    if events_parse_errors:
+        return _result_error(
+            "EVENTS_PARSE_ERROR", "; ".join(events_parse_errors[:5])
+        )
+
+    if phase_end_count == 0:
+        return _result_error("PHASE_END_MISSING", "no plan phase.end event found")
+    if phase_end_count > 1:
+        return _result_error(
+            "PHASE_END_DUPLICATE", f"found {phase_end_count} phase.end events"
+        )
+
+    # Receipt consistency: status should be finalized.
+    receipt_consistent = receipt.get("status") == "finalized"
+
+    return {
+        "ok": True,
+        "action": "verify",
+        "changeDir": str(change_dir),
+        "changeName": change_name,
+        "artifactsHash": actual_hash,
+        "phaseEndCount": phase_end_count,
+        "phaseEndStatus": phase_end_status,
+        "frontmatter": frontmatter_results,
+        "gatePolicyConsistent": gate_policy_consistent,
+        "receiptConsistent": receipt_consistent,
+        "files": artifact_names,
+    }
+
+
 def _read_design_capabilities(staging: Path, change_name: str) -> list[str]:
     """Read capabilities from design frontmatter (retro §5.4)."""
     design_path = staging / "spec" / f"{change_name}-design.md"
@@ -367,6 +636,30 @@ def finalize_plan(
             finally:
                 tmp.unlink(missing_ok=True)
 
+        # C8: write implementation-checkpoints.json with parsed task ownerPhase.
+        tasks = validation.get("tasks") or []
+        if tasks:
+            checkpoints_path = change_dir / "meta" / "implementation-checkpoints.json"
+            checkpoints_payload = {
+                "schemaVersion": 1,
+                "changeName": change_name,
+                "tasks": tasks,
+                "foundationGate": "approved",
+            }
+            _atomic_write_json(checkpoints_path, checkpoints_payload)
+            created.append(checkpoints_path)
+
+        # C9: write scenario-manifest.json with parsed scenarios.
+        scenarios = validation.get("scenarios") or []
+        manifest_path = change_dir / "meta" / "scenario-manifest.json"
+        manifest_payload = {
+            "schemaVersion": 1,
+            "changeName": change_name,
+            "scenarios": scenarios,
+        }
+        _atomic_write_json(manifest_path, manifest_payload)
+        created.append(manifest_path)
+
         pending_receipt = {
             "schemaVersion": SCHEMA_VERSION,
             "changeName": change_name,
@@ -422,18 +715,24 @@ def build_parser() -> argparse.ArgumentParser:
     finalize.add_argument("--run-id", required=True)
     finalize.add_argument("--attempt", required=True, type=int)
     finalize.add_argument("--json", action="store_true")
+    verify = sub.add_parser("verify")
+    verify.add_argument("--change-dir", required=True)
+    verify.add_argument("--json", action="store_true")
     return parser
 
 
 def main(argv: list[str] | None = None) -> int:
     args = build_parser().parse_args(argv)
-    result = finalize_plan(
-        Path(args.change_dir),
-        Path(args.staging_dir),
-        change_name=args.change,
-        run_id=args.run_id,
-        attempt=args.attempt,
-    )
+    if args.command == "verify":
+        result = verify_plan(Path(args.change_dir))
+    else:
+        result = finalize_plan(
+            Path(args.change_dir),
+            Path(args.staging_dir),
+            change_name=args.change,
+            run_id=args.run_id,
+            attempt=args.attempt,
+        )
     stream = sys.stdout if result["ok"] else sys.stderr
     if args.json:
         stream.write(json.dumps(result, ensure_ascii=False, indent=2) + "\n")

package/harness/bundles/java/cursor/scripts/harness_profile.py

@@ -27,6 +27,12 @@ import sys
 from pathlib import Path
 from typing import Any
 
+SCRIPTS_DIR = Path(__file__).resolve().parent
+if str(SCRIPTS_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPTS_DIR))
+
+import harness_paths  # noqa: E402
+
 
 if hasattr(sys.stdout, "reconfigure"):
     sys.stdout.reconfigure(encoding="utf-8")
@@ -358,14 +364,53 @@ def empty_profile_skeleton(excluded: tuple[str, ...] | list[str]) -> dict[str, A
 
 
 def load_profile(project: Path) -> dict[str, Any] | None:
-    path = project / PROFILE_REL
-    if not path.is_file():
-        return None
-    try:
-        data = read_json(path)
-    except (OSError, json.JSONDecodeError):
+    """C7: 分层读取 — 先读 common_root 的 build-profile.json，再叠加 execution root 的 override。
+
+    common_root 是 worktree 共享的主项目根（git common dir 的父目录）；
+    execution root 是当前工作目录（可能是 linked worktree）。
+    override 合并策略：execution 的 buildCommands 覆盖 common 的同名 key；
+    common 独有的 key 保留。
+    """
+    project = Path(project).resolve()
+    common = harness_paths.common_root(project)
+    common_path = common / PROFILE_REL
+    exec_path = project / PROFILE_REL
+
+    common_data: dict[str, Any] | None = None
+    if common_path.is_file():
+        try:
+            data = read_json(common_path)
+            if isinstance(data, dict):
+                common_data = data
+        except (OSError, json.JSONDecodeError):
+            pass
+
+    exec_data: dict[str, Any] | None = None
+    if exec_path.is_file():
+        try:
+            data = read_json(exec_path)
+            if isinstance(data, dict):
+                exec_data = data
+        except (OSError, json.JSONDecodeError):
+            pass
+
+    if common_data is None and exec_data is None:
         return None
-    return data if isinstance(data, dict) else None
+    if common_data is None:
+        return exec_data
+    if exec_data is None:
+        return common_data
+
+    # Merge: start from common, overlay execution's buildCommands.
+    merged = dict(common_data)
+    common_cmds = common_data.get("buildCommands") or {}
+    exec_cmds = exec_data.get("buildCommands") or {}
+    if common_cmds or exec_cmds:
+        merged_cmds = dict(common_cmds) if isinstance(common_cmds, dict) else {}
+        if isinstance(exec_cmds, dict):
+            merged_cmds.update(exec_cmds)
+        merged["buildCommands"] = merged_cmds
+    return merged
 
 
 def _merge_user_overrides(
@@ -616,6 +661,8 @@ def resolve_command(
     *,
     test_classes: list[str] | None = None,
     modules: list[str] | None = None,
+    common_root: Path | None = None,
+    execution_root: Path | None = None,
 ) -> dict[str, Any]:
     cmd = (profile.get("commands") or {}).get(key)
     if not isinstance(cmd, dict):
@@ -625,6 +672,10 @@ def resolve_command(
         replacements["{testClasses}"] = ",".join(test_classes)
     if modules is not None:
         replacements["{modules}"] = ",".join(modules)
+    if common_root is not None:
+        replacements["{commonRoot}"] = str(common_root)
+    if execution_root is not None:
+        replacements["{executionRoot}"] = str(execution_root)
 
     command = cmd.get("command", "")
     for placeholder, val in replacements.items():