@blulotus/trellis 0.7.0

package/dist/templates/trellis/scripts/common/task_context.py

@@ -0,0 +1,372 @@
+#!/usr/bin/env python3
+"""
+Task JSONL context management.
+
+Provides:
+    cmd_add_context   - Add entry to JSONL context file
+    cmd_validate      - Validate JSONL context files
+    cmd_list_context  - List JSONL context entries
+
+Note:
+    ``cmd_init_context`` was removed in v0.5.0-beta.12. JSONL context files
+    are now seeded at ``task.py create`` time with a self-describing
+    ``_example`` line; the AI agent curates real entries during planning when
+    the task needs sub-agent/spec context. See ``.trellis/workflow.md`` for the
+    current planning artifact contract.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+
+from .config import get_context_injection_limits
+from .git import branch_exists_locally
+from .io import read_json
+from .log import Colors, colored
+from .paths import DIR_ARCHIVE, DIR_TASKS, DIR_WORKFLOW, FILE_TASK_JSON, get_repo_root
+from .task_utils import resolve_task_dir
+
+# Extensions that look like code rather than spec/research docs. Entries with
+# one of these extensions outside .trellis/spec/, docs/docs-site, or the
+# task's own directory get a hygiene warning in `task.py validate` — the
+# reader is a sub-agent, not a human, so code paths belong in the diff the
+# agent reads itself, not in implement.jsonl / check.jsonl.
+_CODE_FILE_EXTENSIONS = {
+    ".ts",
+    ".tsx",
+    ".js",
+    ".jsx",
+    ".mjs",
+    ".cjs",
+    ".py",
+    ".go",
+    ".rs",
+    ".java",
+    ".rb",
+    ".c",
+    ".cc",
+    ".cpp",
+    ".h",
+}
+
+
+# =============================================================================
+# Command: add-context
+# =============================================================================
+
+def cmd_add_context(args: argparse.Namespace) -> int:
+    """Add entry to JSONL context file."""
+    repo_root = get_repo_root()
+    target_dir = resolve_task_dir(args.dir, repo_root)
+
+    jsonl_name = args.file
+    path = args.path
+    reason = args.reason or "Added manually"
+
+    if not target_dir or not target_dir.is_dir():
+        print(colored(f"Error: Directory not found: {target_dir}", Colors.RED))
+        return 1
+
+    # Support shorthand
+    if not jsonl_name.endswith(".jsonl"):
+        jsonl_name = f"{jsonl_name}.jsonl"
+
+    jsonl_file = target_dir / jsonl_name
+    full_path = repo_root / path
+
+    entry_type = "file"
+    if full_path.is_dir():
+        entry_type = "directory"
+        if not path.endswith("/"):
+            path = f"{path}/"
+    elif not full_path.is_file():
+        print(colored(f"Error: Path not found: {path}", Colors.RED))
+        return 1
+
+    # Check if already exists
+    if jsonl_file.is_file():
+        content = jsonl_file.read_text(encoding="utf-8")
+        if f'"{path}"' in content:
+            print(colored(f"Warning: Entry already exists for {path}", Colors.YELLOW))
+            return 0
+
+    # Add entry
+    entry: dict
+    if entry_type == "directory":
+        entry = {"file": path, "type": "directory", "reason": reason}
+    else:
+        entry = {"file": path, "reason": reason}
+
+    with jsonl_file.open("a", encoding="utf-8") as f:
+        f.write(json.dumps(entry, ensure_ascii=False) + "\n")
+
+    print(colored(f"Added {entry_type}: {path}", Colors.GREEN))
+    return 0
+
+
+# =============================================================================
+# Command: validate
+# =============================================================================
+
+def cmd_validate(args: argparse.Namespace) -> int:
+    """Validate JSONL context files."""
+    repo_root = get_repo_root()
+    target_dir = resolve_task_dir(args.dir, repo_root)
+
+    if not target_dir or not target_dir.is_dir():
+        print(colored("Error: task directory required", Colors.RED))
+        return 1
+
+    print(colored("=== Validating Context Files ===", Colors.BLUE))
+    print(f"Target dir: {target_dir}")
+    print()
+
+    # Warn (don't fail validation) when the recorded branch is stale — it
+    # was likely already merged and deleted (#399 item 2).
+    task_json_path = target_dir / FILE_TASK_JSON
+    if task_json_path.is_file():
+        task_data = read_json(task_json_path)
+        stored_branch = task_data.get("branch") if task_data else None
+        if stored_branch and not branch_exists_locally(stored_branch, repo_root):
+            print(
+                colored(
+                    f"Warning: recorded branch '{stored_branch}' no longer exists locally "
+                    "(likely merged and deleted).",
+                    Colors.YELLOW,
+                )
+            )
+            print()
+
+    total_errors = 0
+    for jsonl_name in ["implement.jsonl", "check.jsonl"]:
+        jsonl_file = target_dir / jsonl_name
+        errors = _validate_jsonl(jsonl_file, repo_root, target_dir)
+        total_errors += errors
+
+    print()
+    if total_errors == 0:
+        print(colored("✓ All validations passed", Colors.GREEN))
+        return 0
+    else:
+        print(colored(f"✗ Validation failed ({total_errors} errors)", Colors.RED))
+        return 1
+
+
+def _is_exempt_from_code_file_warning(file_path: str, task_rel: str) -> bool:
+    """Whether a jsonl entry path is exempt from the code-file hygiene warning.
+
+    Exempt: spec docs (``.trellis/spec/``), documentation (``docs``,
+    ``docs-site``), and the task's own directory (execution plans, generated
+    artifacts, etc. legitimately live there).
+    """
+    posix_path = file_path.replace("\\", "/").lstrip("/")
+    exempt_prefixes = (".trellis/spec/", "docs/", "docs-site/")
+    if posix_path.startswith(exempt_prefixes):
+        return True
+    if task_rel and (posix_path == task_rel or posix_path.startswith(f"{task_rel}/")):
+        return True
+    return False
+
+
+def _resolve_context_entry_path(
+    file_path: str, repo_root: Path, task_dir: Path | None
+) -> Path | None:
+    """Resolve a JSONL entry, binding archived self-references to the archive copy.
+
+    Exact historical self-references are remapped only for archived tasks.
+    ``None`` means the remapped path traversed or resolved outside that archive.
+    """
+    repo_path = repo_root / file_path
+    if task_dir is None:
+        return repo_path
+
+    try:
+        task_parts = task_dir.resolve().relative_to(repo_root.resolve()).parts
+    except ValueError:
+        return repo_path
+
+    archive_prefix = (DIR_WORKFLOW, DIR_TASKS, DIR_ARCHIVE)
+    if len(task_parts) != 5 or task_parts[:3] != archive_prefix:
+        return repo_path
+
+    year_month = task_parts[3]
+    if (
+        len(year_month) != 7
+        or year_month[4] != "-"
+        or not year_month[:4].isdigit()
+        or not year_month[5:].isdigit()
+    ):
+        return repo_path
+
+    historical_root = f"{DIR_WORKFLOW}/{DIR_TASKS}/{task_dir.name}"
+    posix_path = file_path.replace("\\", "/")
+    if posix_path == historical_root:
+        relative_parts: tuple[str, ...] = ()
+    elif posix_path.startswith(f"{historical_root}/"):
+        relative_path = posix_path[len(historical_root) + 1 :]
+        if relative_path.endswith("/"):
+            relative_path = relative_path[:-1]
+        relative_parts = tuple(relative_path.split("/")) if relative_path else ()
+        if any(part in ("", ".", "..") for part in relative_parts):
+            return None
+    else:
+        return repo_path
+
+    try:
+        archive_root = task_dir.resolve()
+        resolved_path = task_dir.joinpath(*relative_parts).resolve()
+        resolved_path.relative_to(archive_root)
+    except (OSError, RuntimeError, ValueError):
+        return None
+    return resolved_path
+
+
+def _validate_jsonl(jsonl_file: Path, repo_root: Path, task_dir: Path | None = None) -> int:
+    """Validate a single JSONL file.
+
+    Seed rows (no ``file`` field — typically ``{"_example": "..."}``) are
+    skipped silently; they are self-describing comments, not real entries.
+
+    Beyond hard errors (missing file/dir, invalid JSON), this also prints
+    non-blocking hygiene warnings (never counted in ``errors``, never change
+    the exit code): entries that look like code files rather than
+    spec/research docs, and entries whose file size exceeds the configured
+    sub-agent context injection cap (``context_injection.max_file_bytes``).
+    """
+    file_name = jsonl_file.name
+    errors = 0
+
+    if not jsonl_file.is_file():
+        print(f"  {colored(f'{file_name}: not found (skipped)', Colors.YELLOW)}")
+        return 0
+
+    task_rel = ""
+    if task_dir is not None:
+        try:
+            task_rel = task_dir.resolve().relative_to(repo_root.resolve()).as_posix()
+        except ValueError:
+            task_rel = ""
+
+    max_file_bytes = get_context_injection_limits(repo_root).get("max_file_bytes", 0)
+
+    line_num = 0
+    real_entries = 0
+    for line in jsonl_file.read_text(encoding="utf-8").splitlines():
+        line_num += 1
+        if not line.strip():
+            continue
+
+        try:
+            data = json.loads(line)
+        except json.JSONDecodeError:
+            print(f"  {colored(f'{file_name}:{line_num}: Invalid JSON', Colors.RED)}")
+            errors += 1
+            continue
+
+        file_path = data.get("file")
+        entry_type = data.get("type", "file")
+
+        if not file_path:
+            # Seed / comment row — skip silently
+            continue
+
+        real_entries += 1
+        full_path = _resolve_context_entry_path(file_path, repo_root, task_dir)
+        if entry_type == "directory":
+            if full_path is None or not full_path.is_dir():
+                print(f"  {colored(f'{file_name}:{line_num}: Directory not found: {file_path}', Colors.RED)}")
+                errors += 1
+            continue
+
+        if full_path is None or not full_path.is_file():
+            print(f"  {colored(f'{file_name}:{line_num}: File not found: {file_path}', Colors.RED)}")
+            errors += 1
+            continue
+
+        extension = Path(file_path).suffix.lower()
+        if extension in _CODE_FILE_EXTENSIONS and not _is_exempt_from_code_file_warning(
+            file_path, task_rel
+        ):
+            warning_message = (
+                f"{file_name}:{line_num}: Warning: {file_path} looks like a code file — "
+                "implement/check.jsonl should reference spec/research docs; "
+                "agents read code themselves"
+            )
+            print(f"  {colored(warning_message, Colors.YELLOW)}")
+
+        if max_file_bytes:
+            size = full_path.stat().st_size
+            if size > max_file_bytes:
+                warning_message = (
+                    f"{file_name}:{line_num}: Warning: {file_path} is {size} bytes, "
+                    f"exceeds context_injection.max_file_bytes ({max_file_bytes}); "
+                    "injection will truncate it"
+                )
+                print(f"  {colored(warning_message, Colors.YELLOW)}")
+
+    if errors == 0:
+        print(f"  {colored(f'{file_name}: ✓ ({real_entries} entries)', Colors.GREEN)}")
+    else:
+        print(f"  {colored(f'{file_name}: ✗ ({errors} errors)', Colors.RED)}")
+
+    return errors
+
+
+# =============================================================================
+# Command: list-context
+# =============================================================================
+
+def cmd_list_context(args: argparse.Namespace) -> int:
+    """List JSONL context entries."""
+    repo_root = get_repo_root()
+    target_dir = resolve_task_dir(args.dir, repo_root)
+
+    if not target_dir or not target_dir.is_dir():
+        print(colored("Error: task directory required", Colors.RED))
+        return 1
+
+    print(colored("=== Context Files ===", Colors.BLUE))
+    print()
+
+    for jsonl_name in ["implement.jsonl", "check.jsonl"]:
+        jsonl_file = target_dir / jsonl_name
+        if not jsonl_file.is_file():
+            continue
+
+        print(colored(f"[{jsonl_name}]", Colors.CYAN))
+
+        count = 0
+        seed_only = True
+        for line in jsonl_file.read_text(encoding="utf-8").splitlines():
+            if not line.strip():
+                continue
+
+            try:
+                data = json.loads(line)
+            except json.JSONDecodeError:
+                continue
+
+            file_path = data.get("file")
+            if not file_path:
+                # Seed / comment row — don't count as a real entry
+                continue
+            seed_only = False
+
+            count += 1
+            entry_type = data.get("type", "file")
+            reason = data.get("reason", "-")
+
+            if entry_type == "directory":
+                print(f"  {colored(f'{count}.', Colors.GREEN)} [DIR] {file_path}")
+            else:
+                print(f"  {colored(f'{count}.', Colors.GREEN)} {file_path}")
+            print(f"     {colored('→', Colors.YELLOW)} {reason}")
+
+        if seed_only:
+            print(f"  {colored('(no curated entries yet — only seed row)', Colors.YELLOW)}")
+
+        print()
+
+    return 0

package/dist/templates/trellis/scripts/common/task_queue.py

@@ -0,0 +1,188 @@
+#!/usr/bin/env python3
+"""
+Task queue utility functions.
+
+Provides:
+    list_tasks_by_status   - List tasks by status
+    list_pending_tasks     - List tasks with pending status
+    list_tasks_by_assignee - List tasks by assignee
+    list_my_tasks          - List tasks assigned to current developer
+    get_task_stats         - Get P0/P1/P2/P3 counts
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from .paths import (
+    get_repo_root,
+    get_developer,
+    get_tasks_dir,
+)
+from .tasks import iter_active_tasks
+
+
+# =============================================================================
+# Internal helper
+# =============================================================================
+
+def _task_to_dict(t) -> dict:
+    """Convert TaskInfo to the dict format callers expect."""
+    return {
+        "priority": t.priority,
+        "id": t.raw.get("id", ""),
+        "title": t.title,
+        "status": t.status,
+        "assignee": t.assignee or "-",
+        "dir": t.dir_name,
+        "children": list(t.children),
+        "parent": t.parent,
+    }
+
+
+# =============================================================================
+# Public Functions
+# =============================================================================
+
+def list_tasks_by_status(
+    filter_status: str | None = None,
+    repo_root: Path | None = None
+) -> list[dict]:
+    """List tasks by status.
+
+    Args:
+        filter_status: Optional status filter.
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        List of task info dicts with keys: priority, id, title, status, assignee.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    tasks_dir = get_tasks_dir(repo_root)
+    results = []
+
+    for t in iter_active_tasks(tasks_dir):
+        if filter_status and t.status != filter_status:
+            continue
+        results.append(_task_to_dict(t))
+
+    return results
+
+
+def list_pending_tasks(repo_root: Path | None = None) -> list[dict]:
+    """List pending tasks.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        List of task info dicts.
+    """
+    return list_tasks_by_status("planning", repo_root)
+
+
+def list_tasks_by_assignee(
+    assignee: str,
+    filter_status: str | None = None,
+    repo_root: Path | None = None
+) -> list[dict]:
+    """List tasks assigned to a specific developer.
+
+    Args:
+        assignee: Developer name.
+        filter_status: Optional status filter.
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        List of task info dicts.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    tasks_dir = get_tasks_dir(repo_root)
+    results = []
+
+    for t in iter_active_tasks(tasks_dir):
+        if (t.assignee or "-") != assignee:
+            continue
+        if filter_status and t.status != filter_status:
+            continue
+        results.append(_task_to_dict(t))
+
+    return results
+
+
+def list_my_tasks(
+    filter_status: str | None = None,
+    repo_root: Path | None = None
+) -> list[dict]:
+    """List tasks assigned to current developer.
+
+    Args:
+        filter_status: Optional status filter.
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        List of task info dicts.
+
+    Raises:
+        ValueError: If developer not set.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    developer = get_developer(repo_root)
+    if not developer:
+        raise ValueError("Developer not set")
+
+    return list_tasks_by_assignee(developer, filter_status, repo_root)
+
+
+def get_task_stats(repo_root: Path | None = None) -> dict[str, int]:
+    """Get task statistics.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        Dict with keys: P0, P1, P2, P3, Total.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    tasks_dir = get_tasks_dir(repo_root)
+    stats = {"P0": 0, "P1": 0, "P2": 0, "P3": 0, "Total": 0}
+
+    for t in iter_active_tasks(tasks_dir):
+        if t.priority in stats:
+            stats[t.priority] += 1
+        stats["Total"] += 1
+
+    return stats
+
+
+def format_task_stats(stats: dict[str, int]) -> str:
+    """Format task stats as string.
+
+    Args:
+        stats: Stats dict from get_task_stats.
+
+    Returns:
+        Formatted string like "P0:0 P1:1 P2:2 P3:0 Total:3".
+    """
+    return f"P0:{stats['P0']} P1:{stats['P1']} P2:{stats['P2']} P3:{stats['P3']} Total:{stats['Total']}"
+
+
+# =============================================================================
+# Main Entry (for testing)
+# =============================================================================
+
+if __name__ == "__main__":
+    stats = get_task_stats()
+    print(format_task_stats(stats))
+    print()
+    print("Pending tasks:")
+    for task in list_pending_tasks():
+        print(f"  {task['priority']}|{task['id']}|{task['title']}|{task['status']}|{task['assignee']}")