truncateLine byte-sliced s[:maxLen-3], which can split a multibyte UTF-8 character and emit an invalid sequence (mojibake) on long non-ASCII match lines. Back off to the nearest rune boundary via utf8.RuneStart. Adds TestTruncateLineRuneSafe.
Only max_file_size and max_parse_size were clamped after reading .mcp-filepuff.json; max_edit_size and max_search_results were unbounded, letting a config file request excessive memory. Clamp max_edit_size to 100MB and max_search_results to 100k (and floor negatives to 0). Adds TestLoadClampsExcessiveLimits.
FormatDocComment emitted leftover tags by ranging a map, so multi-tag comments (@example/@see/@deprecated) rendered in random order run-to-run — nondeterministic output that defeats caching/diffing. Sort the remaining tag names before emitting.
extractGoSymbols/extractJSSymbols matched var/const/let at any tree depth, so every function-local var, const (Go) and let/const/var (JS/TS) was emitted as a top-level symbol — flooding include_ast/ast_query symbol lists with locals (inaccurate + token-wasteful). Skip declarations nested inside a function/block body (isNestedInBody); module-level and 'export const' declarations are still kept. Adds TestExtractSymbolsExcludesLocals.
Locks the documented guarantee that inserting LF content into a CRLF file normalizes to CRLF, with no bare-LF leaks. Closes a test gap on a stated design goal.
extractElixirStruct hardcoded Name="defstruct", so every Elixir struct surfaced as a symbol literally called "defstruct" — useless for navigation and colliding across modules. Walk ancestors to the enclosing defmodule and name the struct %ModuleName{}. Adds TestExtractElixirStructNamedByModule.
drainStderr discarded all server stderr, so an LSP init failure (e.g. 'command not found', missing module) surfaced as an opaque 'initialization failed'. Retain a bounded tail (StderrCaptureMax=4096B, oldest dropped) under a mutex and attach it to the init-failure error context. Adds TestClientStderrCapture.
The fallback skeleton (c/cpp/elixir/html/vue) is not valid source, so the '// ' comment framing and '(line N)' wording just cost tokens. Use a compact 'kind name :line' form. ~15-25% fewer tokens on fallback skeletons; output stays accurate.
Per the project's error-handling rule, an ignored error needs a comment. Marshalling the two-scalar payload struct cannot fail; document why the error is dropped. No behavior change.
skeletonPythonNode took lines[0] of a decorated_definition, which is the first @decorator line, dropping the def/class signature entirely. Now emit the decorator line(s) then recurse into the wrapped definition so its signature is preserved. Adds skeleton_test.go (decorated + plain function).
readLoop sent the response on the pending channel while holding c.mu. A misbehaving server sending a duplicate response for the same id would block on the buffered(1) channel under the lock, deadlocking all future dispatches. Use a non-blocking send (matching the notification path).
Counter.Add applied any delta, so a negative value would decrement a counter that must be monotonic, corrupting rate()-style downstream math. Ignore delta<0. Adds TestCounterRejectsNegativeAdd.
Two file_search gaps:
- max_results defaulted to 0 (unbounded), so a broad pattern returned every match — unbounded memory + token blowup. The configured MaxSearchResults (default 1000) existed but was dead; wire it as the builtIn default. Explicit max_results still wins, and the cursor footer pages the rest.
- search.Request.IncludeHidden was a dead field with no tool param. Add an include_hidden bool (default false) so dotfiles (.github/, etc.) are searchable.
ast_query defaulted to verbose output (full code + up to 500 chars/match + captures), which is very token-heavy on multi-match queries. Default to compact (one line per match: file:line (kind) firstline) — roughly 5-10x fewer tokens on typical queries — while verbose remains available per-call (format=verbose) or via the default_format session pref. Updates tool description, help resource, and TestASTQueryFormatCompactDefault.
hunkBounds approximated one-sided start lines by reusing the opposite side's number, and re-assigned it every iteration inside the count==0 guard. For pure insertion/deletion hunks (e.g. writing into an empty file, or deleting a whole file) this produced wrong headers like '@@ -2,0 +1,2 @@' instead of '@@ -0,0 +1,2 @@'. flattenDiffLines now records both running line numbers on every line, so hunkBounds takes the start from the first line directly and applies GNU's zero-count convention (line-before-change, clamped to 0). Adds TestGenerateDiffHunkHeaderBounds.
handleASTQuery rebuilt the formatter's '[remaining: N]' placeholder string and strings.ReplaceAll'd it with the cursor line, plus a fallback append — fragile coupling to the formatter's exact output. New FormatResultsWithCursor appends the prebuilt '[cursor: ..., remaining: N]' footer in place of the bare hint when results are truncated; the handler just passes it through. FormatResultsWithOptions is unchanged (delegates with empty cursor). Adds TestFormatResultsWithCursor.
Two ast_query/lsp_query ergonomics improvements that share the tool registration and help files:
- lsp_query accepts symbol_name (+symbol_kind) and resolves the position via AST (resolveLSPSymbolPosition), so callers need not know line:col; line/column are no longer required. SymbolCandidate gains NameLine/NameColumn for the precise identifier position. Ambiguous/unknown names error with candidates / a 'did you mean' hint. Adds TestResolveLSPSymbolPosition.
- ast_query help + tool description now document that matching is keyword/kind-based, not structural: pattern arg/return constraints are not enforced; use name_exact/name_matches/kind_in to filter. Fixes a misleading 'functions returning error' example.
The goroutine parks in the blocking stderr.Read, so closing c.done does not interrupt it; termination relies on the read erroring at pipe EOF when the process is killed. The c.done select is only a best-effort fast path.
renderSymbolsOnly (fallback for c/cpp/elixir/html/vue) appended each symbol's raw start line plus a literal ' { ... }'. For brace-less languages (Elixir 'def f do', HTML) that is syntactically wrong and wastes tokens. Emit only the accurate symbol list; drop the fabricated line and unused params.
A misspelled or stale symbol_name returned a bare 'not found' error, forcing blind retries. nearestSymbolSuggestion fuzzy-matches the requested name against the file's actual symbols (via existing pkg/fuzzy) and appends 'did you mean: a, b, c?'. The re-parse is served from the parser cache. Adds TestReadSymbolNotFoundSuggestsNearest.
When a pagination cursor footer is emitted it already reports the remaining count; the separate '(truncated, showing subset of N)' prose line duplicated that signal. Suppress the prose line when CursorLine is set; keep it for non-paginated truncation.
A replace with empty new_content failed with a bare 'new_content is required' message, leaving the model to guess. Append a hint to use operation=delete when the intent is removal. Adds TestValidateReplaceEmptySuggestsDelete.
extractGoVarConst used ChildByFieldName("name"), which returns only the first name field, so 'var a, b = 1, 2' and 'const ( C, D = 3, 4 )' surfaced only a/C. Iterate every "name"-field child so each declared identifier becomes its own symbol. Adds TestExtractGoVarConstMultiName.
Three strip=imports/license correctness fixes (all heuristic, keyword/structure-gated):
- stripTSImports now tracks multi-line named imports (import {\n ... \n} from 'x') instead of dropping only the first line and leaving dangling members; side-effect imports without semicolons no longer trigger runaway consumption.
- stripGoImports recognizes all single-import spec forms: import _ "x", import . "x", and aliased import m "x" (previously only import "x"/backtick).
- stripLicense peels a leading shebang (#!) or Go build-constraint (//go:build, // +build) block and preserves it above the license, and now strips // line-comment license headers (not just /* */ and #). Adds tests for each.
FindSymbolRange returned the first AST node matching a name, so file_read with symbol_name silently read the wrong symbol when a name collided (e.g. two String() methods on different receivers, or a func and type sharing a name). New FindSymbolCandidates returns all matches; the file_read handler now errors on ambiguity, listing each candidate's node type and line range so the caller can disambiguate via symbol_kind or line_start/line_end. FindSymbolRange is kept (first match) for callers that don't need ambiguity detection. Adds TestFindSymbolCandidates.
We advertise textDocument.definition.linkSupport=true, so gopls and rust-analyzer return the LocationLink shape (targetUri/targetRange). The old code only tried []Location then a single Location; unmarshaling LocationLink JSON into []Location silently succeeds with zero-value URIs/ranges, producing garbage locations (or a false 'No definition found'). parseDefinitionResult now decodes a unified shape capturing both field sets and normalizes to Location, and surfaces a real parse error instead of swallowing it. Adds TestParseDefinitionResult covering all shapes.
lspHover fell back to AST symbol info on any LSP error, but the '(AST fallback)' marker only showed when verbose=true. In the default mode the model received Node type/Text with no signal the answer was a degraded AST guess. Now always emit '[AST fallback — LSP unavailable]' so the model can decide whether to retry. Includes colocated QF1012 style fixups.
Two AST-summary/query path fixes plus colocated QF1012 style fixups:
- runASTQueryWalk now checks info.Size() > MaxFileSize before os.ReadFile, avoiding a full read of files it will discard.
- generateASTSummary used len(splitLines(...)) for the '(N lines)' header, over-counting newline-terminated files by one (phantom trailing element). New countLines() helper counts via bytes.Count. Adds TestCountLines.
extractErrors is a pure function of the parsed tree (it ignores content), so re-walking the whole tree on every cache hit wasted work on the hottest path (file_read+include_ast, ast_query, edit validation). Store []SyntaxError in CachedTree and return it directly on hits. Adds TestParseCachedErrorsMatch asserting cache-hit errors equal the cache-miss parse.
Mechanical fix applied by golangci-lint --fix. Pre-existing debt that fails the staticcheck QF1012 quickfix check; no behavior change. Clears the lint gate so subsequent commits in this package set pass.
- [x] Remove auto-indentation from text mode edits (caller controls whitespace)
- [x] Add line-ending detection and normalization for both AST and text modes
- [x] Share edit logic via new `spliceContent` function for both modes
- [x] Fix diff to emit "No newline at end of file" markers
- [x] Fix diff to strip raw CR from CRLF file output
- [x] Remove double-unescape of backslash sequences in new_content
- [x] Fix countDiffLines to be hunk-aware (correctly count lines starting with +/-)
- [x] Fix block-comment stripping to remove standalone lines cleanly
- [x] Fix Python license header stripping to preserve separator blank lines
* v2.0: token-optimization overhaul
Additive (backward-compatible flags):
- file_read: skeleton mode, strip (imports/license/block_comments),
compact_line_numbers, 8-char etag with prefix-match compat
- ast_query: format=verbose|compact|location, pagination cursor
- file_search: cluster mode, pagination cursor
- lsp_query (references): compact output
Breaking (v2):
- Preambles removed; opt-in verbose=true restores
- edit_apply: response=count|diff|none, default count
- ping tool removed
- symbol_at/find_definition/find_references merged into lsp_query
- Tool descriptions trimmed -83%, help moved to filepuff://help/<tool>
- Batch file_read dedups by etag
Protocol:
- ResourceLink returned for file_read >64 KiB (force_inline override)
- OnAfterInitialize hook reads capabilities.experimental.filepuff
for session defaults (default_format, default_max_results,
default_cluster, compact_refs, line_numbers,
resource_link_threshold)
* fix: drop --max-total-count from ripgrep args
The flag does not exist in stable ripgrep (confirmed up to 15.1.0 --
"unrecognized flag --max-total-count, similar flags that are
available: --max-count"). Every file_search call failed on hosts with
stock rg. --max-count is per-file, not a drop-in replacement, so rely
on the in-process truncation in parseOutput that was already the
documented safety net.
lukaszraczylo
