mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-24 05:41:40 +00:00
fix(lsp): shift baseline diagnostics into post-edit coordinates (#25978)
Pre-existing diagnostics below an edit point used to surface as 'LSP diagnostics introduced by this edit' whenever the edit deleted or inserted lines. The delta-filter key included the diagnostic's range, so the same logical error reported at a different line in the post-edit snapshot looked like a brand new diagnostic. Concrete case: deleting 14 lines in cli.py caused Pyright errors at lines 9873, 10590, 12413, 13004 (unrelated to the edit) to be reported as introduced by it. Fix: build a piecewise-linear line-shift map (via difflib's SequenceMatcher) from pre and post content, and remap baseline diagnostics into post-edit coordinates before the set-difference. Diagnostics in deleted regions drop out cleanly; diagnostics below the edit shift by the right amount; diagnostics above are untouched. The strict (range-aware) equality key stays — so a genuinely new instance of an identical error class at a different line still surfaces as new. Pieces: - agent/lsp/range_shift.py — build_line_shift, shift_diagnostic_range, shift_baseline. Pure functions, no LSP state. - agent/lsp/manager.py — LSPService.get_diagnostics_sync gains an optional line_shift kwarg; baseline is shift_baseline'd before computing the seen-set. _diag_key keeps the strict range key. - tools/file_operations.py — write_file captures pre_content for any LSP-handled extension (not just LINTERS_INPROC) and passes pre/post to _maybe_lsp_diagnostics, which builds the shift map. - New _lsp_handles_extension helper guards the pre_content read. Trade-offs preserved: - Genuinely new same-class errors at different lines still surface (content-only key would have swallowed them). - Pre-existing errors at unshifted positions still get filtered (covered by the strict-key path with no shift). - Best-effort: when pre_content can't be captured (file didn't exist, permissions), the unshifted comparison still catches most pre-existing errors; the edge case it misses is a new file with a non-empty baseline, which is structurally impossible.
This commit is contained in:
parent
ed84637d11
commit
19071529f6
5 changed files with 552 additions and 18 deletions
|
|
@ -40,7 +40,7 @@ import os
|
|||
import threading
|
||||
import time
|
||||
from concurrent.futures import Future as ConcurrentFuture
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
from typing import Any, Callable, Dict, List, Optional, Tuple
|
||||
|
||||
from agent.lsp import eventlog
|
||||
from agent.lsp.client import (
|
||||
|
|
@ -305,6 +305,7 @@ class LSPService:
|
|||
*,
|
||||
delta: bool = True,
|
||||
timeout: Optional[float] = None,
|
||||
line_shift: Optional[Callable[[int], Optional[int]]] = None,
|
||||
) -> List[Dict[str, Any]]:
|
||||
"""Synchronously open ``file_path`` in the right server, wait for
|
||||
diagnostics, return them.
|
||||
|
|
@ -314,6 +315,18 @@ class LSPService:
|
|||
Diagnostics present in the baseline are removed so the caller
|
||||
only sees errors introduced by the current edit.
|
||||
|
||||
When ``line_shift`` is provided, baseline diagnostics are
|
||||
remapped through it before the set-difference. This handles
|
||||
the case where the edit deleted or inserted lines, causing
|
||||
pre-existing diagnostics below the edit point to surface at
|
||||
different line numbers in the post-edit snapshot — without
|
||||
the shift, they'd all look "introduced by this edit". Pass
|
||||
a callable built by
|
||||
:func:`agent.lsp.range_shift.build_line_shift` (pre_text,
|
||||
post_text). Omit when pre/post content isn't available;
|
||||
the unshifted comparison still catches diagnostics that
|
||||
didn't move.
|
||||
|
||||
Returns an empty list when LSP is disabled, when no workspace
|
||||
can be detected, when no server matches, or when the server
|
||||
can't be spawned. Never raises.
|
||||
|
|
@ -344,6 +357,14 @@ class LSPService:
|
|||
if delta:
|
||||
baseline = self._delta_baseline.get(abs_path) or []
|
||||
if baseline:
|
||||
if line_shift is not None:
|
||||
# Remap baseline diagnostics into post-edit
|
||||
# coordinates so shifted-but-otherwise-identical
|
||||
# entries hash equal under _diag_key. Entries
|
||||
# that mapped into a deleted region drop out
|
||||
# silently — they no longer apply.
|
||||
from agent.lsp.range_shift import shift_baseline
|
||||
baseline = shift_baseline(baseline, line_shift)
|
||||
seen = {_diag_key(d) for d in baseline}
|
||||
diags = [d for d in diags if _diag_key(d) not in seen]
|
||||
# Roll baseline forward — next call returns deltas relative
|
||||
|
|
@ -585,8 +606,19 @@ class LSPService:
|
|||
|
||||
|
||||
def _diag_key(d: Dict[str, Any]) -> str:
|
||||
"""Content equality key used for delta filtering. Mirrors
|
||||
:func:`agent.lsp.client._diagnostic_key`."""
|
||||
"""Content equality key used for cross-edit delta filtering.
|
||||
|
||||
Includes the diagnostic's position range — when used together
|
||||
with :func:`agent.lsp.range_shift.shift_baseline`, the baseline
|
||||
is line-shifted into post-edit coordinates BEFORE this key is
|
||||
computed, so identical-but-shifted diagnostics hash equal. Two
|
||||
genuinely distinct diagnostics at different lines (e.g. the same
|
||||
error class introduced at a second site) hash differently and
|
||||
are surfaced as new.
|
||||
|
||||
Mirrors :func:`agent.lsp.client._diagnostic_key`; intentionally
|
||||
identical so the two layers agree on diagnostic identity.
|
||||
"""
|
||||
rng = d.get("range") or {}
|
||||
start = rng.get("start") or {}
|
||||
end = rng.get("end") or {}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue