hermes-agent/agent/lsp/eventlog.py

"""Structured logging with steady-state silence for the LSP layer.

LSP fires on every write_file/patch, so the level model keeps ``agent.log``
greppable (``rg 'lsp\\['``) without noise:

- ``DEBUG`` for steady-state events with no novel signal (clean, skipped,
  repeat "no project root", repeat "server unavailable").
- ``INFO`` for once-per-session transitions (``active for <root>`` the first
  time a client starts, first ``no project root`` per file) and for every
  diagnostic event (rare and exactly what users grep for).
- ``WARNING`` for action-required failures: first ``server unavailable`` per
  (server_id, binary), ``no server configured`` once per language, and every
  timeout / unexpected error.

Dedup uses module-level sets bounded by the distinct pairs touched in one
process.  A bounded LRU was rejected: evicting an entry would re-fire the
line we explicitly want suppressed.
"""
from __future__ import annotations

import logging
import os
import threading
from typing import List, Tuple

# Dedicated logger name so the documented grep recipe survives any
# ``logging.getLogger(__name__)`` rename of internal modules.
event_log = logging.getLogger("hermes.lint.lsp")

_announce_lock = threading.Lock()
_announced_active: set = set()        # keys: (server_id, workspace_root)
_announced_unavailable: set = set()   # keys: (server_id, binary_path_or_name)
_announced_no_root: set = set()       # keys: (server_id, file_path)
_ALL_BUCKETS = (_announced_active, _announced_unavailable, _announced_no_root)


def _short_path(file_path: str) -> str:
    """Render *file_path* relative to cwd when it's inside it, else absolute (no ``../..`` chains)."""
    if not file_path:
        return file_path
    try:
        rel = os.path.relpath(file_path)
    except ValueError:
        return file_path
    if rel.startswith(".." + os.sep) or rel == "..":
        return file_path
    return rel


def _emit(server_id: str, level: int, message: str) -> None:
    event_log.log(level, "lsp[%s] %s", server_id, message)


def _announce_once(bucket: set, key: Tuple) -> bool:
    """Atomically mark *key* announced; True only for the first caller."""
    with _announce_lock:
        if key in bucket:
            return False
        bucket.add(key)
        return True


def _emit_once(bucket: set, key: Tuple, server_id: str, level: int, first: str, repeat: str) -> None:
    """Log *first* at *level* the first time *key* is seen, *repeat* at DEBUG thereafter."""
    if _announce_once(bucket, key):
        _emit(server_id, level, first)
    else:
        _emit(server_id, logging.DEBUG, repeat)


# ---------------------------------------------------------------------------
# Public event helpers — call these from the LSP layer.
# ---------------------------------------------------------------------------


def log_clean(server_id: str, file_path: str) -> None:
    """No diagnostics emitted for *file_path*.  DEBUG."""
    _emit(server_id, logging.DEBUG, f"clean ({_short_path(file_path)})")


def log_disabled(server_id: str, file_path: str, reason: str) -> None:
    """LSP intentionally skipped for this file (feature off, ext unmapped, ...).  DEBUG."""
    _emit(server_id, logging.DEBUG, f"skipped: {reason} ({_short_path(file_path)})")


def log_active(server_id: str, workspace_root: str) -> None:
    """A client started for (server_id, workspace_root).  INFO once per pair, DEBUG thereafter."""
    _emit_once(
        _announced_active, (server_id, workspace_root), server_id, logging.INFO,
        f"active for {workspace_root}", f"reused client for {workspace_root}",
    )


def log_diagnostics(server_id: str, file_path: str, count: int) -> None:
    """Diagnostics arrived for a file.  INFO every time — rare per edit and what users grep for."""
    _emit(server_id, logging.INFO, f"{count} diags ({_short_path(file_path)})")


def log_no_project_root(server_id: str, file_path: str) -> None:
    """File had no recognised project marker.  INFO once per file, DEBUG thereafter."""
    msg = f"no project root for {_short_path(file_path)}"
    _emit_once(_announced_no_root, (server_id, file_path), server_id, logging.INFO, msg, msg)


def log_server_unavailable(server_id: str, binary_or_pkg: str) -> None:
    """Server binary unresolved.  WARNING once per (server_id, binary), DEBUG thereafter."""
    _emit_once(
        _announced_unavailable, (server_id, binary_or_pkg), server_id, logging.WARNING,
        f"server unavailable: {binary_or_pkg} not found "
        "(install via `hermes lsp install <id>` or set lsp.servers.<id>.command)",
        f"server still unavailable: {binary_or_pkg}",
    )


def log_timeout(server_id: str, file_path: str, kind: str = "diagnostics") -> None:
    """A request to the server timed out.  WARNING every time."""
    _emit(server_id, logging.WARNING, f"{kind} timed out for {_short_path(file_path)}")


def log_server_error(server_id: str, file_path: str, exc: BaseException) -> None:
    """An unexpected exception bubbled out of the LSP layer.  WARNING."""
    _emit(
        server_id,
        logging.WARNING,
        f"unexpected error for {_short_path(file_path)}: {type(exc).__name__}: {exc}",
    )


def log_spawn_failed(server_id: str, workspace_root: str, exc: BaseException) -> None:
    """The LSP server failed to spawn or initialize.  WARNING."""
    _emit(
        server_id,
        logging.WARNING,
        f"spawn/initialize failed for {workspace_root}: {type(exc).__name__}: {exc}",
    )


def log_reaped(keys: List[Tuple[str, str]], idle_timeout: float) -> None:
    """Idle clients were reaped.  INFO, one line per sweep.

    Also forgets the ``log_active`` announcement for those keys so a respawn
    re-announces at INFO instead of a misleading DEBUG "reused client".
    """
    with _announce_lock:
        for key in keys:
            _announced_active.discard(key)
    summary = ", ".join(f"{sid} ({root})" for sid, root in keys)
    _emit(
        "reaper",
        logging.INFO,
        f"reaped {len(keys)} idle client(s) after {idle_timeout:.0f}s: {summary}",
    )


def reset_announce_caches() -> None:
    """Test-only: clear the dedup caches.  Production code never calls this."""
    with _announce_lock:
        for bucket in _ALL_BUCKETS:
            bucket.clear()


__all__ = [
    "event_log",
    "log_clean",
    "log_disabled",
    "log_active",
    "log_diagnostics",
    "log_no_project_root",
    "log_server_unavailable",
    "log_timeout",
    "log_server_error",
    "log_spawn_failed",
    "log_reaped",
    "reset_announce_caches",
]