fix: harden agent command layer (render sanitize, nil-safety, arrays)

Review follow-up on the agent command tree. A batch of low-risk hardening
fixes; no behavior change for the shipped example provider.

- Terminal-injection: pretty/TSV renderers now sanitize the agent-controlled
  State / UpdatedAt / CreatedAt fields (kvValue on pretty rows, stripANSI on
  TSV), matching the id/summary/title fields — a malicious provider can no
  longer inject CSI/OSC escapes via a forged state or timestamp.
- Nil-safety: `task get --watch` and artifact download return a typed
  invalid_response error when a provider hook yields (nil, nil) (a legitimate
  Call[*T] result on an empty "data") instead of panicking; an artifact with
  neither inline bytes nor a URL no longer writes a 0-byte file.
- Array convention: task/context/agent list normalize a nil slice to [] so an
  empty list serializes as [] not null, matching Card.Parameters.
- Error hint: unknown-agent errors keep LookupSpec's scheme-scoped
  `agent list <scheme>` hint instead of being flattened to the generic one.
- agent list <scheme> (online path) sets the resolved identity on its
  envelope, consistent with the other leaves.
- Comment/doc drift: drop references to the removed Deps probe / Discoverer /
  ProviderInfo / resolveProvider symbols; rename Supports(cap) -> capKey.
- Tests: cross-agent isolation in the example store, empty-list [] contract,
  State/timestamp sanitization regression, and a real stdout assertion for
  context list --jq.
This commit is contained in:
liuxinyang.lxy
2026-07-09 12:59:53 +08:00
parent 9144f0b5bd
commit f861daba45
11 changed files with 196 additions and 26 deletions

View File

@@ -174,6 +174,48 @@ func TestEchoMultiTurn(t *testing.T) {
}
}
// TestCrossAgentIsolation pins the load-bearing per-agent isolation guard: echo
// and reporter share one package-global store, so a task/context created under
// one agent MUST be invisible to the other agent's runtime (get/delete return a
// not-found error; list returns nothing). Without this guard
// `agent task get example:reporter <echo-task-id>` would leak echo's data.
func TestCrossAgentIsolation(t *testing.T) {
swapStore(t)
ctx := context.Background()
echo := fakeRuntime{"echo"}
reporter := fakeRuntime{"reporter"}
t1, err := echoSend(ctx, echo, agent.SendInput{Text: "secret"})
if err != nil {
t.Fatalf("echo send: %v", err)
}
// reporter must not read/delete echo's task or context.
if _, err := getTask(ctx, reporter, t1.TaskID); err == nil {
t.Error("reporter must not read echo's task (cross-agent leak)")
}
if _, err := getContext(ctx, reporter, t1.ContextID); err == nil {
t.Error("reporter must not read echo's context (cross-agent leak)")
}
if err := deleteContext(ctx, reporter, t1.ContextID); err == nil {
t.Error("reporter must not delete echo's context (cross-agent leak)")
}
if tasks, _ := listTasks(ctx, reporter, ""); len(tasks) != 0 {
t.Errorf("reporter should see no echo tasks, got %d", len(tasks))
}
if ctxs, _ := listContexts(ctx, reporter); len(ctxs) != 0 {
t.Errorf("reporter should see no echo contexts, got %d", len(ctxs))
}
// echo still sees its own data, and its context survived reporter's delete.
if _, err := getTask(ctx, echo, t1.TaskID); err != nil {
t.Errorf("echo must still read its own task: %v", err)
}
if _, err := getContext(ctx, echo, t1.ContextID); err != nil {
t.Errorf("echo's context must survive a cross-agent delete attempt: %v", err)
}
}
// TestStateSurvivesReload pins the cross-process semantics via the shared snapshot.
func TestStateSurvivesReload(t *testing.T) {
swapStore(t)

View File

@@ -26,10 +26,9 @@ import (
// naturally stateless; example is a pure mock and must manage state itself. Two
// disciplines the integrator needs to know:
//
// 1. Concurrency safety: provider instances may be constructed / called
// concurrently (e.g. list's probe alongside the real call), so package-level
// mutable state must be locked. A single coarse-grained Mutex covers all
// reads and writes here — the mock does not chase throughput; correctness comes first.
// 1. Concurrency safety: package-level mutable state must be locked. A single
// coarse-grained Mutex covers all reads and writes here — the mock does not
// chase throughput; correctness comes first.
// 2. CLI process boundary: every lark-cli command is a fresh process, so a pure
// in-memory map does not survive a single command — after `send`, a
// `task get` would find nothing. So a lazy JSON snapshot layer sits beneath
@@ -38,9 +37,10 @@ import (
// have this layer — it is a mock-only demo device.
//
// Note that the snapshot is loaded lazily (only on the first real read/write of
// state): Register's zero-value Deps probe constructs a provider once at
// registration time, and construction must have no side effects (the registry.go
// contract), so Factory / Card / ListAgents must not touch store.
// state): provider registration is a pure declarative Register(Provider) call
// (see agent/register.go) with no construction and no side effects, so nothing
// touches store at registration time — the snapshot is read on the first hook
// invocation, not at init.
// ============================================================================
// taskRecord is a task's storage form: a full AgentTask snapshot + owning agent

View File

@@ -83,6 +83,14 @@ func runtimeFor(f *cmdutil.Factory, id core.Identity, agentID string) (iagent.Ru
// shape; an unknown scheme points at `agent list` to discover the available
// providers. Both hints are copy-pasteable next steps, not just wording.
func wrapRefResolveError(err error) error {
// LookupSpec's unknown-catalog-id case is ALREADY a typed validation error
// carrying a scheme-scoped hint (`agent list <scheme>`); pass it through
// instead of flattening it via err.Error() and overwriting that hint with the
// generic provider-list one. Only the untyped ParseRef sentinel / unknown-
// scheme errors need wrapping.
if _, ok := errs.ProblemOf(err); ok {
return err
}
e := errs.NewValidationError(errs.SubtypeInvalidArgument, "%s", err.Error()).WithCause(err)
if errors.Is(err, iagent.ErrInvalidRef) {
return e.WithHint("agent_ref 形如 <scheme>:<agent_id>,如 example:echo")

View File

@@ -154,6 +154,9 @@ func agentContextListRun(opts *contextOptions) error {
// preserves the provider's relative order for equal timestamps, and contexts
// with no timestamp sort last.
sort.SliceStable(contexts, func(i, j int) bool { return contexts[i].UpdatedAt > contexts[j].UpdatedAt })
if contexts == nil {
contexts = []iagent.ContextSummary{} // always emit [] not null (matches the Card.Parameters array convention)
}
return scanAndEmitData(f, opts.Cmd, opts.Format,
map[string]interface{}{"contexts": contexts},
&output.Meta{Count: len(contexts)},
@@ -198,7 +201,7 @@ func agentContextGetRun(opts *contextOptions) error {
// agentContextDeleteRun runs `context delete`. The --yes confirmation guard runs
// first so a missing confirmation returns confirmation_required (exit 10) before
// any provider is built and holds even under a nil Factory. Only a
// confirmed delete reaches resolveProvider + DeleteContext.
// confirmed delete reaches resolveSpec + DeleteContext.
func agentContextDeleteRun(opts *contextOptions) error {
if !opts.Yes {
return cmdutil.RequireConfirmation("agent context delete")

View File

@@ -309,16 +309,53 @@ func TestContextGetInvalidRef(t *testing.T) {
}
}
// TestContextListWithJq exercises the --jq output branch for list.
// TestContextListWithJq pins the --jq output branch for list: the filtered
// value (not the full envelope) is what reaches stdout.
func TestContextListWithJq(t *testing.T) {
opts, _ := contextTestOpts(t, "list")
opts.Cmd.Flags().String("jq", ".data.contexts | length", "")
setScripted(t, scriptedHooks{listContexts: func() ([]iagent.ContextSummary, error) {
return []iagent.ContextSummary{{ContextID: "sess_1"}}, nil
}})
out := opts.Factory.IOStreams.Out.(interface{ Bytes() []byte })
if err := agentContextListRun(opts); err != nil {
t.Fatalf("context list --jq should not error: %v", err)
}
got := strings.TrimSpace(string(out.Bytes()))
if got != "1" {
t.Errorf("--jq .data.contexts | length should output 1, got %q", got)
}
if strings.Contains(got, `"ok"`) {
t.Errorf("--jq output should be the filtered value, not the full envelope, got %q", got)
}
}
// TestContextListEmptyEmitsArray pins the array convention: an empty context
// list serializes as [] (never null), matching Card.Parameters.
func TestContextListEmptyEmitsArray(t *testing.T) {
opts, _ := contextTestOpts(t, "list")
setScripted(t, scriptedHooks{listContexts: func() ([]iagent.ContextSummary, error) {
return nil, nil
}})
out := opts.Factory.IOStreams.Out.(interface{ Bytes() []byte })
if err := agentContextListRun(opts); err != nil {
t.Fatalf("context list should not error: %v", err)
}
var env output.Envelope
if err := json.Unmarshal(out.Bytes(), &env); err != nil {
t.Fatalf("output should be valid envelope JSON: %v (%s)", err, string(out.Bytes()))
}
data, _ := env.Data.(map[string]interface{})
v, present := data["contexts"]
if !present {
t.Fatal("data.contexts key should be present")
}
if _, ok := v.([]interface{}); !ok {
t.Errorf("empty context list should emit a JSON array (not null), got %T: %v", v, v)
}
if env.Meta == nil || env.Meta.Count != 0 {
t.Errorf("meta.count should be 0, got %+v", env.Meta)
}
}
// TestContextListPretty exercises the --format pretty human-view branch for

View File

@@ -93,7 +93,7 @@ func printTaskPretty(w io.Writer, task *iagent.AgentTask) {
fmt.Fprintln(w, "(no task)")
return
}
fmt.Fprintf(w, "state: %s\n", task.State)
fmt.Fprintf(w, "state: %s\n", kvValue(string(task.State)))
fmt.Fprintf(w, "task_id: %s\n", kvValue(task.TaskID))
if task.ContextID != "" {
fmt.Fprintf(w, "context_id: %s\n", kvValue(task.ContextID))
@@ -118,7 +118,7 @@ func printTaskSummariesTSV(w io.Writer, tasks []iagent.TaskSummary) {
fmt.Fprintf(w, "TASK_ID\tCONTEXT_ID\tSTATE\tIS_TERMINAL\tUPDATED_AT\tSUMMARY\n")
for _, t := range tasks {
fmt.Fprintf(w, "%s\t%s\t%s\t%t\t%s\t%s\n",
stripANSI(t.TaskID), stripANSI(t.ContextID), t.State, t.IsTerminal, t.UpdatedAt, kvValue(t.Summary))
stripANSI(t.TaskID), stripANSI(t.ContextID), stripANSI(string(t.State)), t.IsTerminal, stripANSI(t.UpdatedAt), kvValue(t.Summary))
}
}
@@ -129,7 +129,7 @@ func printContextsTSV(w io.Writer, contexts []iagent.ContextSummary) {
fmt.Fprintf(w, "CONTEXT_ID\tCREATED_AT\tUPDATED_AT\tTITLE\tTASK_COUNT\tAWAITING_INPUT\n")
for _, c := range contexts {
fmt.Fprintf(w, "%s\t%s\t%s\t%s\t%d\t%t\n",
stripANSI(c.ContextID), c.CreatedAt, c.UpdatedAt, stripANSI(c.Title), c.TaskCount, c.AwaitingInput)
stripANSI(c.ContextID), stripANSI(c.CreatedAt), stripANSI(c.UpdatedAt), stripANSI(c.Title), c.TaskCount, c.AwaitingInput)
}
}
@@ -147,10 +147,10 @@ func printContextDetailPretty(w io.Writer, detail *iagent.ContextDetail) {
}
fmt.Fprintf(w, "context_id: %s\n", kvValue(detail.ContextID))
if detail.CreatedAt != "" {
fmt.Fprintf(w, "created_at: %s\n", detail.CreatedAt)
fmt.Fprintf(w, "created_at: %s\n", kvValue(detail.CreatedAt))
}
if detail.UpdatedAt != "" {
fmt.Fprintf(w, "updated_at: %s\n", detail.UpdatedAt)
fmt.Fprintf(w, "updated_at: %s\n", kvValue(detail.UpdatedAt))
}
if detail.Title != "" {
fmt.Fprintf(w, "title: %s\n", kvValue(detail.Title))
@@ -158,7 +158,7 @@ func printContextDetailPretty(w io.Writer, detail *iagent.ContextDetail) {
fmt.Fprintf(w, "task_count: %d\n", detail.TaskCount)
fmt.Fprintf(w, "awaiting_input: %t\n", detail.AwaitingInput)
if at := detail.ActiveTask; at != nil {
fmt.Fprintf(w, "active_task: %s · %s · %s\n", at.State, at.UpdatedAt, kvValue(at.Summary))
fmt.Fprintf(w, "active_task: %s · %s · %s\n", kvValue(string(at.State)), kvValue(at.UpdatedAt), kvValue(at.Summary))
}
}

View File

@@ -15,7 +15,7 @@ import (
)
// providerInfo describes a registered provider adapter in `agent list` output.
// Every field is sourced from the registered iagent.ProviderInfo (the single
// Every field is sourced from the registered iagent.Provider (the single
// source of truth).
type providerInfo struct {
Scheme string `json:"scheme"`
@@ -36,9 +36,9 @@ type listOptions struct {
// NewCmdAgentList builds `agent list [scheme]`. Without an argument it
// enumerates the registered provider adapters with their metadata — a
// pure, API-free listing. With a scheme it performs second-level discovery:
// providers implementing Discoverer enumerate their agents;
// others return unsupported_capability with the agent_id_source
// guidance. Risk=read.
// catalog providers enumerate offline from their static set; instance providers
// enumerate via their optional ListAgents hook (absent ⇒ unsupported_capability
// with the agent_id_source guidance). Risk=read.
func NewCmdAgentList(f *cmdutil.Factory) *cobra.Command {
opts := &listOptions{Factory: f}
cmd := &cobra.Command{
@@ -120,6 +120,7 @@ func agentListSchemeRun(opts *listOptions) error {
}
var agents []iagent.AgentSummary
var identity string // set only on the online (instance) path, which resolves one
if prov.Kind() == iagent.KindCatalog {
agents = prov.ListCatalog() // offline
} else {
@@ -132,6 +133,7 @@ func agentListSchemeRun(opts *listOptions) error {
// The enumeration call carries the resolved identity; agentID is empty
// (enumeration is not scoped to a single agent).
id := f.ResolveAs(opts.Cmd.Context(), opts.Cmd, "")
identity = string(id)
rt, err := runtimeFor(f, id, "")
if err != nil {
return err
@@ -141,6 +143,9 @@ func agentListSchemeRun(opts *listOptions) error {
return err
}
}
if agents == nil {
agents = []iagent.AgentSummary{} // always emit [] not null
}
// pretty is a human view only; a --jq expression implies structured JSON.
if opts.Format == "pretty" && jqExpr(opts.Cmd) == "" {
@@ -154,10 +159,11 @@ func agentListSchemeRun(opts *listOptions) error {
}
env := output.Envelope{
OK: true,
Data: map[string]interface{}{"agents": agents},
Meta: &output.Meta{Count: len(agents)},
Notice: output.GetNotice(),
OK: true,
Identity: identity, // empty for the offline catalog path (omitempty)
Data: map[string]interface{}{"agents": agents},
Meta: &output.Meta{Count: len(agents)},
Notice: output.GetNotice(),
}
if jq := jqExpr(opts.Cmd); jq != "" {
return output.JqFilter(f.IOStreams.Out, env, jq)

View File

@@ -135,7 +135,7 @@ func scopeRemediationHint(id core.Identity, missing []string) string {
// seam, and runs the all-or-nothing preflight. Any gap in its own inputs (nil
// Factory, unparsable ref, unregistered scheme) yields nil — the preflight is
// an accelerator, never a new failure mode; the paths that validate ref/scheme
// for real have already run inside resolveProvider.
// for real have already run inside resolveSpec.
func preflightScopesForRef(f *cmdutil.Factory, id core.Identity, ref string) error {
if f == nil {
return nil

View File

@@ -245,6 +245,14 @@ func agentTaskGetRun(opts *taskOptions) error {
if err != nil {
return err
}
// A provider that decodes an empty "data" via Call[*AgentTask] legitimately
// returns (nil, nil) (see internal/agent decodeData). Surface that as a typed
// error rather than dereferencing task.State below (the --watch branch would
// otherwise panic; the sibling consumers all nil-guard).
if task == nil {
return errs.NewInternalError(errs.SubtypeInvalidResponse,
"provider 未返回任务数据(响应无 data")
}
if opts.Watch && !task.State.ShouldStopPolling() {
// A positive --timeout bounds the poll: pollToStop returns the most recent
@@ -315,6 +323,9 @@ func agentTaskListRun(opts *taskOptions) error {
// recently active task heads the list; a stable sort preserves the provider's
// relative order for equal timestamps, and tasks with no timestamp sort last.
sort.SliceStable(tasks, func(i, j int) bool { return tasks[i].UpdatedAt > tasks[j].UpdatedAt })
if tasks == nil {
tasks = []iagent.TaskSummary{} // always emit [] not null (matches the Card.Parameters array convention)
}
return scanAndEmitData(f, opts.Cmd, opts.Format,
map[string]interface{}{"tasks": tasks},
&output.Meta{Count: len(tasks)},
@@ -397,6 +408,19 @@ func downloadArtifact(opts *taskOptions) error {
if err != nil {
return err
}
// A provider decoding an empty "data" via Call[*ArtifactData] can return
// (nil, nil); and a non-nil descriptor with neither inline bytes nor a URL
// carries no downloadable content. Both are provider-response defects — fail
// with a typed error instead of dereferencing nil or writing a 0-byte file
// (which under --force would clobber an existing local file with emptiness).
if art == nil {
return errs.NewInternalError(errs.SubtypeInvalidResponse,
"provider 未返回产物数据(响应无 data")
}
if len(art.Bytes) == 0 && art.URL == "" {
return errs.NewInternalError(errs.SubtypeInvalidResponse,
"产物 '%s' 无可下载内容provider 既未提供内联字节也未提供下载 URL", opts.ArtifactID)
}
data := art.Bytes
if art.URL != "" {

View File

@@ -279,6 +279,34 @@ func TestTaskListEmitsCount(t *testing.T) {
}
}
// TestTaskListEmptyEmitsArray pins the array convention: an empty task list
// serializes as [] (never null), matching Card.Parameters.
func TestTaskListEmptyEmitsArray(t *testing.T) {
opts, _ := taskTestOpts(t, "list")
setScripted(t, scriptedHooks{listTasks: func(string) ([]iagent.TaskSummary, error) {
return nil, nil
}})
out := opts.Factory.IOStreams.Out.(interface{ Bytes() []byte })
if err := agentTaskListRun(opts); err != nil {
t.Fatalf("list should not error: %v", err)
}
var env output.Envelope
if err := json.Unmarshal(out.Bytes(), &env); err != nil {
t.Fatalf("output should be valid envelope JSON: %v (%s)", err, string(out.Bytes()))
}
data, _ := env.Data.(map[string]interface{})
v, present := data["tasks"]
if !present {
t.Fatal("data.tasks key should be present")
}
if _, ok := v.([]interface{}); !ok {
t.Errorf("empty task list should emit a JSON array (not null), got %T: %v", v, v)
}
if env.Meta == nil || env.Meta.Count != 0 {
t.Errorf("meta.count should be 0, got %+v", env.Meta)
}
}
// TestTaskListError surfaces a provider ListTasks failure.
func TestTaskListError(t *testing.T) {
opts, _ := taskTestOpts(t, "list")
@@ -505,6 +533,28 @@ func TestTaskListPrettyFormat(t *testing.T) {
}
}
// TestTaskListPrettySanitizesStateAndTimestamp pins that the agent-controlled
// State and UpdatedAt fields are ANSI-stripped on the pretty/TSV path, not just
// the ids/summary — a malicious provider must not inject terminal escapes via a
// forged state string or timestamp.
func TestTaskListPrettySanitizesStateAndTimestamp(t *testing.T) {
opts, _ := taskTestOpts(t, "list")
opts.Format = "pretty"
setScripted(t, scriptedHooks{listTasks: func(string) ([]iagent.TaskSummary, error) {
return []iagent.TaskSummary{
{TaskID: "chat_1", State: iagent.TaskState("completed\x1b[2J"), IsTerminal: true,
UpdatedAt: "2026-07-05T12:00:00Z\x1b]0;pwned\x07"},
}, nil
}})
out := opts.Factory.IOStreams.Out.(interface{ Bytes() []byte })
if err := agentTaskListRun(opts); err != nil {
t.Fatalf("task list --format pretty should not error: %v", err)
}
if text := string(out.Bytes()); strings.Contains(text, "\x1b") {
t.Errorf("ANSI/OSC sequences in State/UpdatedAt must be stripped, got %q", text)
}
}
// TestTaskListSortedByUpdatedAtDesc pins the ordering + enriched-field
// contract: the provider returns tasks out of order, and the command emits them
// newest-first by updated_at while carrying updated_at + summary on each.

View File

@@ -134,11 +134,11 @@ type CardSkill struct {
// Supports reports whether a capability is declared as supported (an unknown key
// or a nil card is treated as unsupported).
func (c *AgentCard) Supports(cap string) bool {
func (c *AgentCard) Supports(capKey string) bool {
if c == nil {
return false
}
switch cap {
switch capKey {
case CapArtifactDownload:
return c.Capabilities.ArtifactDownload
case CapFileInput: