mirror of
https://github.com/Twigpine/zero.git
synced 2026-11-12 08:41:32 -10:00
Kevin Codex
3c81fea228
* feat: agent quality, caching, retry, and tooling upgrades Ten self-contained improvements to the core agent engine and tools: - edit_file: fuzzy fallback matching (7-strategy cascade with uniqueness protection and a disproportion guard) when old_string does not match byte-for-byte; exact match remains the fast path - edit_file/write_file: inline error-severity LSP diagnostics in tool output so the model sees a break it introduced in the same turn - lsp: expand server registry from 4 to 28 languages; doctor grades only tier-1 servers and lists the long tail informationally - agent: consecutive read-only tool calls execute concurrently (bounded at 8), consumed in original order, never spanning a mutating call - anthropic: cache_control breakpoints on the last two conversation messages so the transcript prefix stays a prompt-cache hit - providerio: retry schedule raised to 6 attempts with exponential 2s-30s backoff when the server sends no Retry-After - tools: truncated exec/bash output spills to a redacted temp file referenced in the truncation notice; bash output (previously unbounded) now shares exec_command's token budget - web_fetch: dependency-free HTML-to-markdown conversion (format: auto|raw|markdown) and larger limits (256KiB default, 2MiB max, 30s) - modelregistry: live models.dev overlay refreshes context limits and base pricing from a TTL-cached fetch; opt-in at the CLI entrypoint - tools: opt-in format-on-write (ZERO_FORMAT_ON_WRITE=1) runs standard formatters across 27 extensions, ordered before the file-tracker re-baseline so conflict detection is preserved * fix: address PR review feedback on fuzzy edits, diagnostics, spill - edit_file: adapt the replacement to the fuzzy-resolved span — when the span is a uniformly deeper-indented copy of old_string (line-trimmed / indentation-flexible matches), the same indentation delta is applied to new_string, and a span ending in a bare CR keeps its CR so CRLF files never gain a mixed line ending; block-anchor matches with drifted interiors are deliberately left untouched - diagnostics: render workspace-relative paths in inline post-edit diagnostics (base name outside the workspace) so absolute paths never leak the local username or directory layout into the model prompt or session transcript - spill: harden the spill directory for shared temp dirs — per-uid name, reject symlinked or non-directory paths (MkdirAll follows symlinks), and on Unix require current-user ownership - bash: the branch's output cap and truncation-flag threading are superseded by main's capture-time bounding (boundedBuffer + budgetBashCapture), which already sets Result.Truncated; this rebase adopts that design and keeps spill-to-disk on exec_command, where the full output is still buffered and a spill is genuinely complete * fix: address review round 2 — permission-event race, fuzzy ambiguity, spill reachability - agent: serialize OnPermission behind the same mutex as OnPermissionRequest in the parallel read batch. buildPermissionEvent fires for batched reads with a non-trivial sandbox decision (e.g. a grant-matched extra root), and front-end handlers append to shared session-recording state without their own locking — two batched reads emitting concurrently was a data race the pre-batch serial loop never allowed. - edit_file: reject two or more DISTINCT candidate spans from one fuzzy strategy as ambiguous instead of silently editing the first. Duplicate blocks at different indentation each resolve to a unique literal, so the previous occurrence-uniqueness check passed and wrote the wrong span. A single candidate occurring at multiple positions still cascades to stricter strategies as before. - tools: make spill files actually reachable by the recovery path the truncation notice advertises — resolveScopedReadPath now recognizes files inside the per-uid spill dir (containment verified after symlink resolution, so a planted link cannot smuggle an out-of-scope file through the gate); read_file/grep can follow the notice instead of re-running the command. * fix: surface competing block-anchor spans; make write-barrier test observe cross-probe order - edit_file: blockAnchorReplacer now returns every span clearing the similarity threshold (best first) instead of silently picking the single most-similar block. Hiding competitors from the cascade's distinct-candidate check could edit the wrong block when two blocks share anchors and both interiors are plausible; one clear winner still resolves, two plausible blocks now report ambiguity (covered by a two-block test that asserts the file is untouched). - agent tests: the parallel write-barrier test now records both probes into one mutex-guarded shared log and asserts the cross-probe ordering it always claimed to (write starts after the first read batch ends; second read batch starts after the write ends). The previous version only compared indices within the read probe's own log, which a regression letting the write overlap a batch could still pass; the stray no-op mutex assignment is gone.
83 lines
2.4 KiB
Go
83 lines
2.4 KiB
Go
package tools
|
|
|
|
import (
|
|
"context"
|
|
"os"
|
|
"os/exec"
|
|
"path/filepath"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
// gofmt ships with the Go toolchain, so it is the one formatter guaranteed to
|
|
// exist wherever these tests run.
|
|
func requireGofmt(t *testing.T) {
|
|
t.Helper()
|
|
if _, err := exec.LookPath("gofmt"); err != nil {
|
|
t.Skip("gofmt not on PATH")
|
|
}
|
|
}
|
|
|
|
func TestFormatOnWriteDisabledByDefault(t *testing.T) {
|
|
requireGofmt(t)
|
|
t.Setenv("ZERO_FORMAT_ON_WRITE", "")
|
|
dir := t.TempDir()
|
|
ugly := "package a\n\nfunc A( ) { }\n"
|
|
|
|
result := NewWriteFileTool(dir).(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
|
|
"path": "a.go",
|
|
"content": ugly,
|
|
}, RunOptions{})
|
|
if result.Status != StatusOK {
|
|
t.Fatalf("write failed: %q", result.Output)
|
|
}
|
|
onDisk, err := os.ReadFile(filepath.Join(dir, "a.go"))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if string(onDisk) != ugly {
|
|
t.Fatalf("formatting must be off by default, got %q", onDisk)
|
|
}
|
|
}
|
|
|
|
func TestFormatOnWriteFormatsAndKeepsTrackerConsistent(t *testing.T) {
|
|
requireGofmt(t)
|
|
t.Setenv("ZERO_FORMAT_ON_WRITE", "1")
|
|
dir := t.TempDir()
|
|
tracker := NewFileTracker()
|
|
|
|
write := NewWriteFileTool(dir).(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
|
|
"path": "a.go",
|
|
"content": "package a\n\nfunc A( ) { }\n",
|
|
}, RunOptions{FileTracker: tracker})
|
|
if write.Status != StatusOK {
|
|
t.Fatalf("write failed: %q", write.Output)
|
|
}
|
|
onDisk, err := os.ReadFile(filepath.Join(dir, "a.go"))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if !strings.Contains(string(onDisk), "func A() {") {
|
|
t.Fatalf("expected gofmt-formatted content, got %q", onDisk)
|
|
}
|
|
|
|
// The tracker must have been re-baselined to the POST-format content: a
|
|
// follow-up edit must not trip the external-modification conflict guard.
|
|
edit := NewEditFileTool(dir).(optionsAwareTool).RunWithOptions(context.Background(), map[string]any{
|
|
"path": "a.go",
|
|
"old_string": "func A() {",
|
|
"new_string": "func B() {",
|
|
}, RunOptions{FileTracker: tracker})
|
|
if edit.Status != StatusOK {
|
|
t.Fatalf("follow-up edit must not conflict after formatting: %q", edit.Output)
|
|
}
|
|
}
|
|
|
|
func TestFormatOnWriteSkipsUnknownExtensions(t *testing.T) {
|
|
t.Setenv("ZERO_FORMAT_ON_WRITE", "1")
|
|
content := maybeFormatWrittenFile(context.Background(), filepath.Join(t.TempDir(), "notes.xyz"), "raw text")
|
|
if content != "raw text" {
|
|
t.Fatalf("unknown extension must pass through: %q", content)
|
|
}
|
|
}
|