hermes-agent/tests/agent/lsp/_mock_lsp_server.py
ethernet a632e68a01 fix(lsp): never report stale diagnostics — wait for fresh post-edit data
Slow language servers (tsserver on large projects especially) publish
diagnostics long after an edit. The client's wait/report path had three
holes that together surfaced the PREVIOUS edit's errors as if they were
current ("ghost diagnostics"), sending the agent chasing errors it had
already fixed:

1. open_file only cleared the diagnostic stores on first open — on the
   didChange path (every subsequent edit) stale push/pull entries
   survived.
2. wait_for_diagnostics' predicates were satisfiable by that leftover
   state (`path in _published`, `path in _pull_diagnostics`), so the
   "wait" often returned instantly with old data.
3. diagnostics_for merged the stale push store unconditionally, so even
   a fresh clean pull got the old error merged back in.

Fix: anchor freshness on a per-file didChange timestamp.

- Pull results record their request send-time and are dropped when a
  didChange raced past them; the pull store is invalidated on every
  change, not just first open.
- wait_for_diagnostics now returns bool (fresh data vs timeout), only
  counts pushes published at/after the change (and version >= ours when
  the server echoes versions), and accepts an explicit timeout — the
  user's lsp.wait_timeout config now actually controls the inner wait
  budget instead of only the outer thread-join.
- diagnostics_for(fresh_only=True) excludes stores that predate the
  latest change; all manager report paths use it.
- On timeout the manager returns [] ("no data") instead of stale
  state, logs a WARNING via eventlog, and does NOT mark the server
  broken — slow is not dead.
- seed-on-first-push no longer marks the file published, so the TS
  seed push can't satisfy a waiter.

Tests: new "stale" and "slow_push" mock-server scripts model the slow
tsserver, plus client- and service-level regression tests
(tests/agent/lsp/test_stale_diagnostics.py).
2026-07-20 13:43:36 -04:00

205 lines
7.2 KiB
Python

#!/usr/bin/env python3
"""A minimal in-process LSP server used by tests.
Speaks just enough LSP to drive :class:`agent.lsp.client.LSPClient`
through a full lifecycle: ``initialize``, ``initialized``,
``textDocument/didOpen``, ``textDocument/didChange``, then a
``textDocument/publishDiagnostics`` notification followed by
``shutdown`` + ``exit``.
Behaviour (all behaviours selectable via env var ``MOCK_LSP_SCRIPT``):
- ``"clean"`` — initialize, accept didOpen/didChange, push empty
diagnostics on every open/change, exit cleanly on shutdown.
- ``"errors"`` — same as ``clean`` but the published diagnostics
carry one severity-1 entry pointing at line 0:0.
- ``"crash"`` — exit immediately after responding to ``initialize``
(simulates a crashing server).
- ``"slow"`` — same as ``clean`` but sleeps 1s before responding to
``initialize`` (lets us test timeout behaviour).
- ``"stale"`` — pushes one error on ``didOpen``, then goes SILENT on
``didChange`` (no push) and rejects the pull endpoint with
method-not-found. Models a slow tsserver that hasn't re-checked
the edited content yet — the ghost-diagnostics scenario.
- ``"slow_push"`` — like ``stale`` on didOpen (one error) but on
``didChange`` sleeps ``MOCK_LSP_PUSH_DELAY`` seconds (default 1.0)
and then pushes EMPTY diagnostics. Models a server that fixes
the ghost if you actually wait for it. Pull endpoint rejects.
The script writes JSON-RPC framed messages to stdout and reads from
stdin. No third-party dependencies — uses only stdlib so it runs
under whatever Python the test process picks up.
"""
from __future__ import annotations
import json
import os
import sys
import time
def read_message():
"""Read one Content-Length framed JSON-RPC message from stdin."""
headers = {}
while True:
line = sys.stdin.buffer.readline()
if not line:
return None
line = line.rstrip(b"\r\n")
if not line:
break
k, _, v = line.decode("ascii").partition(":")
headers[k.strip().lower()] = v.strip()
n = int(headers["content-length"])
body = sys.stdin.buffer.read(n)
return json.loads(body.decode("utf-8"))
def write_message(obj):
body = json.dumps(obj, separators=(",", ":")).encode("utf-8")
sys.stdout.buffer.write(f"Content-Length: {len(body)}\r\n\r\n".encode("ascii"))
sys.stdout.buffer.write(body)
sys.stdout.buffer.flush()
def main():
script = os.environ.get("MOCK_LSP_SCRIPT", "clean")
while True:
msg = read_message()
if msg is None:
return 0
if "id" in msg and msg.get("method") == "initialize":
if script == "slow":
time.sleep(1.0)
write_message(
{
"jsonrpc": "2.0",
"id": msg["id"],
"result": {
"capabilities": {
"textDocumentSync": 1, # Full
"diagnosticProvider": {"interFileDependencies": False, "workspaceDiagnostics": False},
},
"serverInfo": {"name": "mock-lsp", "version": "0.1"},
},
}
)
if script == "crash":
return 0
continue
if msg.get("method") == "initialized":
continue
if msg.get("method") == "workspace/didChangeConfiguration":
continue
if msg.get("method") == "workspace/didChangeWatchedFiles":
continue
if msg.get("method") in {"textDocument/didOpen", "textDocument/didChange"}:
params = msg.get("params") or {}
td = params.get("textDocument") or {}
uri = td.get("uri", "")
version = td.get("version", 0)
is_change = msg.get("method") == "textDocument/didChange"
error_diag = [
{
"range": {
"start": {"line": 0, "character": 0},
"end": {"line": 0, "character": 5},
},
"severity": 1,
"code": "MOCK001",
"source": "mock-lsp",
"message": "synthetic error from mock-lsp",
}
]
if script == "stale":
# Ghost scenario: publish an error for the ORIGINAL
# content, then never publish again after edits.
if not is_change:
write_message(
{
"jsonrpc": "2.0",
"method": "textDocument/publishDiagnostics",
"params": {"uri": uri, "version": version, "diagnostics": error_diag},
}
)
continue
if script == "slow_push":
diagnostics = error_diag
if is_change:
time.sleep(float(os.environ.get("MOCK_LSP_PUSH_DELAY", "1.0")))
diagnostics = []
write_message(
{
"jsonrpc": "2.0",
"method": "textDocument/publishDiagnostics",
"params": {"uri": uri, "version": version, "diagnostics": diagnostics},
}
)
continue
diagnostics = []
if script == "errors":
diagnostics = error_diag
write_message(
{
"jsonrpc": "2.0",
"method": "textDocument/publishDiagnostics",
"params": {
"uri": uri,
"version": version,
"diagnostics": diagnostics,
},
}
)
continue
if msg.get("method") == "textDocument/diagnostic":
if script in {"stale", "slow_push"}:
# These scripts model push-only servers so the ghost
# can't be papered over by the pull channel.
write_message(
{
"jsonrpc": "2.0",
"id": msg["id"],
"error": {"code": -32601, "message": "method not found"},
}
)
continue
# Pull endpoint — return empty.
write_message(
{
"jsonrpc": "2.0",
"id": msg["id"],
"result": {"kind": "full", "items": []},
}
)
continue
if msg.get("method") == "textDocument/didSave":
continue
if msg.get("method") == "shutdown":
write_message({"jsonrpc": "2.0", "id": msg["id"], "result": None})
continue
if msg.get("method") == "exit":
return 0
# Unknown request: respond with method-not-found.
if "id" in msg:
write_message(
{
"jsonrpc": "2.0",
"id": msg["id"],
"error": {"code": -32601, "message": f"method not found: {msg.get('method')}"},
}
)
if __name__ == "__main__":
sys.exit(main())