Files
zero/internal/agent/parallel_tools_test.go
Kevin Codex 3c81fea228 feat: agent quality, caching, retry, and tooling upgrades (#506)
* 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.
2026-07-05 17:25:26 +08:00

205 lines
7.1 KiB
Go

package agent
import (
"context"
"fmt"
"sync"
"testing"
"time"
"github.com/Gitlawb/zero/internal/tools"
"github.com/Gitlawb/zero/internal/zeroruntime"
)
// probeTool records execution overlap and ordering so tests can assert what
// actually ran concurrently.
type probeTool struct {
name string
sideEffect tools.SideEffect
delay time.Duration
// shared, when set, receives this probe's start/end entries too, so a test
// can observe ordering ACROSS probes (e.g. reads vs a write barrier).
shared *probeLog
mu sync.Mutex
active int
maxActive int
log []string
}
// probeLog is a mutex-guarded event log shared between probes.
type probeLog struct {
mu sync.Mutex
entries []string
}
func (log *probeLog) append(entry string) {
log.mu.Lock()
defer log.mu.Unlock()
log.entries = append(log.entries, entry)
}
func (log *probeLog) snapshot() []string {
log.mu.Lock()
defer log.mu.Unlock()
return append([]string(nil), log.entries...)
}
func (tool *probeTool) Name() string { return tool.name }
func (tool *probeTool) Description() string { return "test probe tool" }
func (tool *probeTool) Parameters() tools.Schema {
return tools.Schema{
Type: "object",
Properties: map[string]tools.PropertySchema{"id": {Type: "string"}},
AdditionalProperties: false,
}
}
func (tool *probeTool) Safety() tools.Safety {
return tools.Safety{SideEffect: tool.sideEffect, Permission: tools.PermissionAllow, Reason: "test"}
}
func (tool *probeTool) Run(_ context.Context, args map[string]any) tools.Result {
id, _ := args["id"].(string)
tool.mu.Lock()
tool.active++
if tool.active > tool.maxActive {
tool.maxActive = tool.active
}
tool.log = append(tool.log, "start:"+id)
tool.mu.Unlock()
if tool.shared != nil {
tool.shared.append("start:" + id)
}
time.Sleep(tool.delay)
if tool.shared != nil {
tool.shared.append("end:" + id)
}
tool.mu.Lock()
tool.active--
tool.log = append(tool.log, "end:"+id)
tool.mu.Unlock()
return tools.Result{Status: tools.StatusOK, Output: "probe " + id}
}
func probeCallEvents(callID, toolName, id string) []zeroruntime.StreamEvent {
return []zeroruntime.StreamEvent{
{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: callID, ToolName: toolName},
{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: callID, ArgumentsFragment: fmt.Sprintf(`{"id":%q}`, id)},
{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: callID},
}
}
func TestParallelSafeToolCall(t *testing.T) {
registry := tools.NewRegistry()
registry.Register(&probeTool{name: "probe_read", sideEffect: tools.SideEffectRead})
registry.Register(&probeTool{name: "probe_write", sideEffect: tools.SideEffectWrite})
call := func(name, args string) ToolCall { return ToolCall{ID: "c", Name: name, Arguments: args} }
if !parallelSafeToolCall(registry, call("probe_read", `{"id":"a"}`), Options{}) {
t.Fatal("auto-allowed read tool must be parallel-safe")
}
if parallelSafeToolCall(registry, call("probe_write", `{"id":"a"}`), Options{}) {
t.Fatal("mutating tool must not be parallel-safe")
}
if parallelSafeToolCall(registry, call("unknown_tool", `{}`), Options{}) {
t.Fatal("unknown tool must not be parallel-safe")
}
if parallelSafeToolCall(registry, call("probe_read", `{"id":`), Options{}) {
t.Fatal("undecodable arguments must not be parallel-safe")
}
if parallelSafeToolCall(registry, call("ask_user", `{}`), Options{}) {
t.Fatal("loop-intercepted tools must stay sequential")
}
}
func TestRunExecutesConsecutiveReadsConcurrently(t *testing.T) {
probe := &probeTool{name: "probe_read", sideEffect: tools.SideEffectRead, delay: 60 * time.Millisecond}
registry := tools.NewRegistry()
registry.Register(probe)
turnOne := append(probeCallEvents("call-1", "probe_read", "a"), probeCallEvents("call-2", "probe_read", "b")...)
turnOne = append(turnOne, probeCallEvents("call-3", "probe_read", "c")...)
turnOne = append(turnOne, zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone})
provider := &mockProvider{
turns: [][]zeroruntime.StreamEvent{
turnOne,
{{Type: zeroruntime.StreamEventText, Content: "done"}, {Type: zeroruntime.StreamEventDone}},
},
}
var results []ToolResult
_, err := Run(context.Background(), "probe", provider, Options{
Registry: registry,
OnToolResult: func(result ToolResult) { results = append(results, result) },
})
if err != nil {
t.Fatal(err)
}
if probe.maxActive < 2 {
t.Fatalf("consecutive read-only calls must overlap, max concurrency was %d", probe.maxActive)
}
// Results must still be recorded in original call order.
if len(results) != 3 || results[0].ToolCallID != "call-1" || results[1].ToolCallID != "call-2" || results[2].ToolCallID != "call-3" {
t.Fatalf("tool results out of order: %#v", results)
}
messages := provider.requests[1].Messages
var toolOrder []string
for _, message := range messages {
if message.Role == zeroruntime.MessageRoleTool {
toolOrder = append(toolOrder, message.ToolCallID)
}
}
if len(toolOrder) != 3 || toolOrder[0] != "call-1" || toolOrder[1] != "call-2" || toolOrder[2] != "call-3" {
t.Fatalf("recorded tool messages out of order: %v", toolOrder)
}
}
func TestRunParallelReadsNeverSpanMutatingCall(t *testing.T) {
shared := &probeLog{}
read := &probeTool{name: "probe_read", sideEffect: tools.SideEffectRead, delay: 30 * time.Millisecond, shared: shared}
write := &probeTool{name: "probe_write", sideEffect: tools.SideEffectWrite, shared: shared}
registry := tools.NewRegistry()
registry.Register(read)
registry.Register(write)
turnOne := append(probeCallEvents("call-1", "probe_read", "r1"), probeCallEvents("call-2", "probe_read", "r2")...)
turnOne = append(turnOne, probeCallEvents("call-3", "probe_write", "w")...)
turnOne = append(turnOne, probeCallEvents("call-4", "probe_read", "r3")...)
turnOne = append(turnOne, probeCallEvents("call-5", "probe_read", "r4")...)
turnOne = append(turnOne, zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone})
provider := &mockProvider{
turns: [][]zeroruntime.StreamEvent{
turnOne,
{{Type: zeroruntime.StreamEventText, Content: "done"}, {Type: zeroruntime.StreamEventDone}},
},
}
_, err := Run(context.Background(), "probe", provider, Options{Registry: registry})
if err != nil {
t.Fatal(err)
}
// Cross-probe ordering on the SHARED log: the write must start only after
// both first-batch reads finished, and both second-batch reads must start
// only after the write finished — batches never cross a mutating call.
log := shared.snapshot()
index := func(entry string) int {
for i, e := range log {
if e == entry {
return i
}
}
t.Fatalf("entry %q missing from shared log: %v", entry, log)
return -1
}
writeStart, writeEnd := index("start:w"), index("end:w")
if firstBatchMaxEnd := max(index("end:r1"), index("end:r2")); writeStart < firstBatchMaxEnd {
t.Fatalf("write started before the first read batch finished: %v", log)
}
if secondBatchMinStart := min(index("start:r3"), index("start:r4")); secondBatchMinStart < writeEnd {
t.Fatalf("second read batch started before the write finished: %v", log)
}
if read.maxActive < 2 {
t.Fatalf("reads within a batch must overlap, max concurrency was %d", read.maxActive)
}
}