test(agent): add tests for hook respond media error handling
Add comprehensive tests for the hook respond code path when media delivery fails. Tests cover error media channel scenarios and verify proper error state handling. Also document that AfterTool is not called when using respond action, as it provides the final answer directly (design decision).
This commit is contained in:
h4rm00n
parent
bbcda9a15c
commit
70f2072ee1
2 changed files with 354 additions and 5 deletions
|
|
@ -475,7 +475,7 @@ Common `Kind` values:
|
|||
|--------|-----------------|--------|
|
||||
| `continue` | All interceptor types | Pass through without modification |
|
||||
| `modify` | `before_llm`, `before_tool`, `after_llm`, `after_tool` | Modify request/response and pass through |
|
||||
| `respond` | `before_tool` | Return tool result directly, skip actual execution |
|
||||
| `respond` | `before_tool` | Return tool result directly, skip actual execution. **Note: AfterTool is NOT called (design decision - respond provides final answer).** |
|
||||
| `deny_tool` | `before_tool` | Deny tool execution |
|
||||
| `abort_turn` | All interceptor types | Abort current turn, return error |
|
||||
| `hard_abort` | All interceptor types | Force stop entire agent loop |
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@ package agent
|
|||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"os"
|
||||
"sync"
|
||||
"testing"
|
||||
|
|
@ -10,6 +11,7 @@ import (
|
|||
"github.com/sipeed/picoclaw/pkg/bus"
|
||||
"github.com/sipeed/picoclaw/pkg/config"
|
||||
"github.com/sipeed/picoclaw/pkg/providers"
|
||||
"github.com/sipeed/picoclaw/pkg/routing"
|
||||
"github.com/sipeed/picoclaw/pkg/tools"
|
||||
)
|
||||
|
||||
|
|
@ -483,7 +485,6 @@ func TestHookManager_BeforeTool_RespondAction(t *testing.T) {
|
|||
hm := NewHookManager(nil)
|
||||
defer hm.Close()
|
||||
|
||||
// Register a hook that returns respond action
|
||||
hook := &respondHook{
|
||||
respondTools: map[string]bool{"test_tool": true},
|
||||
}
|
||||
|
|
@ -491,19 +492,16 @@ func TestHookManager_BeforeTool_RespondAction(t *testing.T) {
|
|||
t.Fatalf("mount hook: %v", err)
|
||||
}
|
||||
|
||||
// Call BeforeTool
|
||||
req := &ToolCallHookRequest{
|
||||
Tool: "test_tool",
|
||||
Arguments: map[string]any{"arg": "value"},
|
||||
}
|
||||
result, decision := hm.BeforeTool(context.Background(), req)
|
||||
|
||||
// Verify decision is respond
|
||||
if decision.Action != HookActionRespond {
|
||||
t.Fatalf("expected action %q, got %q", HookActionRespond, decision.Action)
|
||||
}
|
||||
|
||||
// Verify HookResult is correctly set
|
||||
if result.HookResult == nil {
|
||||
t.Fatal("expected HookResult to be set")
|
||||
}
|
||||
|
|
@ -511,3 +509,354 @@ func TestHookManager_BeforeTool_RespondAction(t *testing.T) {
|
|||
t.Fatalf("unexpected HookResult.ForLLM: %q", result.HookResult.ForLLM)
|
||||
}
|
||||
}
|
||||
|
||||
type respondWithMediaHook struct {
|
||||
respondTools map[string]bool
|
||||
media []string
|
||||
responseHandled bool
|
||||
forLLM string
|
||||
sendMediaErr error
|
||||
}
|
||||
|
||||
func (h *respondWithMediaHook) BeforeTool(
|
||||
ctx context.Context,
|
||||
call *ToolCallHookRequest,
|
||||
) (*ToolCallHookRequest, HookDecision, error) {
|
||||
if h.respondTools[call.Tool] {
|
||||
next := call.Clone()
|
||||
next.HookResult = &tools.ToolResult{
|
||||
ForLLM: h.forLLM,
|
||||
ForUser: "media result",
|
||||
Media: h.media,
|
||||
ResponseHandled: h.responseHandled,
|
||||
Silent: false,
|
||||
IsError: false,
|
||||
}
|
||||
return next, HookDecision{Action: HookActionRespond}, nil
|
||||
}
|
||||
return call, HookDecision{Action: HookActionContinue}, nil
|
||||
}
|
||||
|
||||
func (h *respondWithMediaHook) AfterTool(
|
||||
ctx context.Context,
|
||||
result *ToolResultHookResponse,
|
||||
) (*ToolResultHookResponse, HookDecision, error) {
|
||||
return result, HookDecision{Action: HookActionContinue}, nil
|
||||
}
|
||||
|
||||
type errorMediaChannel struct {
|
||||
fakeChannel
|
||||
sendErr error
|
||||
}
|
||||
|
||||
func (f *errorMediaChannel) SendMedia(ctx context.Context, msg bus.OutboundMediaMessage) ([]string, error) {
|
||||
return nil, f.sendErr
|
||||
}
|
||||
|
||||
func TestAgentLoop_HookRespond_MediaError(t *testing.T) {
|
||||
provider := &multiToolProvider{
|
||||
toolCalls: []providers.ToolCall{
|
||||
{ID: "call-1", Name: "media_tool", Arguments: map[string]any{}},
|
||||
},
|
||||
finalContent: "done",
|
||||
}
|
||||
al, agent, cleanup := newHookTestLoop(t, provider)
|
||||
defer cleanup()
|
||||
|
||||
hook := &respondWithMediaHook{
|
||||
respondTools: map[string]bool{"media_tool": true},
|
||||
media: []string{"media://test/image.png"},
|
||||
responseHandled: true,
|
||||
forLLM: "media sent successfully",
|
||||
}
|
||||
if err := al.MountHook(NamedHook("media-hook", hook)); err != nil {
|
||||
t.Fatalf("MountHook failed: %v", err)
|
||||
}
|
||||
|
||||
al.channelManager = newStartedTestChannelManager(t, al.bus, al.mediaStore, "discord", &errorMediaChannel{
|
||||
sendErr: errors.New("channel unavailable"),
|
||||
})
|
||||
|
||||
sub := al.SubscribeEvents(16)
|
||||
defer al.UnsubscribeEvents(sub.ID)
|
||||
|
||||
_, err := al.runAgentLoop(context.Background(), agent, processOptions{
|
||||
SessionKey: "session-media-err",
|
||||
Channel: "discord",
|
||||
ChatID: "chat1",
|
||||
UserMessage: "send media",
|
||||
DefaultResponse: defaultResponse,
|
||||
EnableSummary: false,
|
||||
SendResponse: false,
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("runAgentLoop failed: %v", err)
|
||||
}
|
||||
|
||||
events := collectEventStream(sub.C)
|
||||
endEvt, ok := findEvent(events, EventKindToolExecEnd)
|
||||
if !ok {
|
||||
t.Fatal("expected ToolExecEnd event")
|
||||
}
|
||||
payload, ok := endEvt.Payload.(ToolExecEndPayload)
|
||||
if !ok {
|
||||
t.Fatalf("expected ToolExecEndPayload, got %T", endEvt.Payload)
|
||||
}
|
||||
|
||||
if !payload.IsError {
|
||||
t.Fatal("expected IsError=true when SendMedia fails")
|
||||
}
|
||||
|
||||
if payload.ForLLMLen < 30 {
|
||||
t.Fatalf("expected ForLLM to contain error message, got ForLLMLen=%d", payload.ForLLMLen)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAgentLoop_HookRespond_BusFallback(t *testing.T) {
|
||||
provider := &multiToolProvider{
|
||||
toolCalls: []providers.ToolCall{
|
||||
{ID: "call-1", Name: "media_tool", Arguments: map[string]any{}},
|
||||
},
|
||||
finalContent: "done",
|
||||
}
|
||||
al, agent, cleanup := newHookTestLoop(t, provider)
|
||||
defer cleanup()
|
||||
|
||||
hook := &respondWithMediaHook{
|
||||
respondTools: map[string]bool{"media_tool": true},
|
||||
media: []string{"media://test/image.png"},
|
||||
responseHandled: true,
|
||||
forLLM: "media queued",
|
||||
}
|
||||
if err := al.MountHook(NamedHook("media-hook", hook)); err != nil {
|
||||
t.Fatalf("MountHook failed: %v", err)
|
||||
}
|
||||
|
||||
sub := al.SubscribeEvents(16)
|
||||
defer al.UnsubscribeEvents(sub.ID)
|
||||
|
||||
resp, err := al.runAgentLoop(context.Background(), agent, processOptions{
|
||||
SessionKey: "session-bus-fallback",
|
||||
Channel: "cli",
|
||||
ChatID: "chat1",
|
||||
UserMessage: "send media",
|
||||
DefaultResponse: defaultResponse,
|
||||
EnableSummary: false,
|
||||
SendResponse: false,
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("runAgentLoop failed: %v", err)
|
||||
}
|
||||
|
||||
events := collectEventStream(sub.C)
|
||||
endEvt, ok := findEvent(events, EventKindToolExecEnd)
|
||||
if !ok {
|
||||
t.Fatal("expected ToolExecEnd event")
|
||||
}
|
||||
payload, ok := endEvt.Payload.(ToolExecEndPayload)
|
||||
if !ok {
|
||||
t.Fatalf("expected ToolExecEndPayload, got %T", endEvt.Payload)
|
||||
}
|
||||
|
||||
if payload.IsError {
|
||||
t.Fatal("expected IsError=false for bus fallback (media queued, not delivered)")
|
||||
}
|
||||
|
||||
if resp != "done" {
|
||||
t.Fatalf("expected response 'done', got %q", resp)
|
||||
}
|
||||
}
|
||||
|
||||
type multiToolProvider struct {
|
||||
mu sync.Mutex
|
||||
callCount int
|
||||
toolCalls []providers.ToolCall
|
||||
finalContent string
|
||||
}
|
||||
|
||||
func (p *multiToolProvider) Chat(
|
||||
ctx context.Context,
|
||||
messages []providers.Message,
|
||||
tools []providers.ToolDefinition,
|
||||
model string,
|
||||
opts map[string]any,
|
||||
) (*providers.LLMResponse, error) {
|
||||
p.mu.Lock()
|
||||
defer p.mu.Unlock()
|
||||
|
||||
p.callCount++
|
||||
if p.callCount == 1 && len(p.toolCalls) > 0 {
|
||||
return &providers.LLMResponse{
|
||||
ToolCalls: p.toolCalls,
|
||||
}, nil
|
||||
}
|
||||
|
||||
return &providers.LLMResponse{
|
||||
Content: p.finalContent,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (p *multiToolProvider) GetDefaultModel() string {
|
||||
return "multi-tool-provider"
|
||||
}
|
||||
|
||||
func TestAgentLoop_HookRespond_InterruptSkipsRemaining(t *testing.T) {
|
||||
provider := &multiToolProvider{
|
||||
toolCalls: []providers.ToolCall{
|
||||
{ID: "call-1", Name: "tool_one", Arguments: map[string]any{}},
|
||||
{ID: "call-2", Name: "tool_two", Arguments: map[string]any{}},
|
||||
{ID: "call-3", Name: "tool_three", Arguments: map[string]any{}},
|
||||
},
|
||||
finalContent: "done",
|
||||
}
|
||||
al, _, cleanup := newHookTestLoop(t, provider)
|
||||
defer cleanup()
|
||||
|
||||
tool1ExecCh := make(chan struct{}, 1)
|
||||
al.RegisterTool(&slowTool{name: "tool_two", duration: 100 * time.Millisecond, execCh: tool1ExecCh})
|
||||
al.RegisterTool(&slowTool{name: "tool_three", duration: 100 * time.Millisecond})
|
||||
|
||||
hook := &respondHook{
|
||||
respondTools: map[string]bool{"tool_one": true},
|
||||
}
|
||||
if err := al.MountHook(NamedHook("respond-hook", hook)); err != nil {
|
||||
t.Fatalf("MountHook failed: %v", err)
|
||||
}
|
||||
|
||||
sub := al.SubscribeEvents(32)
|
||||
defer al.UnsubscribeEvents(sub.ID)
|
||||
|
||||
sessionKey := routing.BuildAgentMainSessionKey(routing.DefaultAgentID)
|
||||
|
||||
type result struct {
|
||||
resp string
|
||||
err error
|
||||
}
|
||||
resultCh := make(chan result, 1)
|
||||
go func() {
|
||||
resp, err := al.ProcessDirectWithChannel(
|
||||
context.Background(),
|
||||
"run tools",
|
||||
sessionKey,
|
||||
"cli",
|
||||
"chat1",
|
||||
)
|
||||
resultCh <- result{resp: resp, err: err}
|
||||
}()
|
||||
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
|
||||
if err := al.InterruptGraceful("stop now"); err != nil {
|
||||
t.Fatalf("InterruptGraceful failed: %v", err)
|
||||
}
|
||||
|
||||
select {
|
||||
case r := <-resultCh:
|
||||
if r.err != nil {
|
||||
t.Fatalf("unexpected error: %v", r.err)
|
||||
}
|
||||
case <-time.After(3 * time.Second):
|
||||
t.Fatal("timeout waiting for result")
|
||||
}
|
||||
|
||||
events := collectEventStream(sub.C)
|
||||
|
||||
skippedEvts := filterEvents(events, EventKindToolExecSkipped)
|
||||
if len(skippedEvts) < 1 {
|
||||
t.Fatal("expected at least one ToolExecSkipped event after interrupt")
|
||||
}
|
||||
|
||||
for _, evt := range skippedEvts {
|
||||
payload, ok := evt.Payload.(ToolExecSkippedPayload)
|
||||
if !ok {
|
||||
t.Fatalf("expected ToolExecSkippedPayload, got %T", evt.Payload)
|
||||
}
|
||||
if payload.Reason != "graceful interrupt requested" {
|
||||
t.Fatalf("expected skip reason 'graceful interrupt requested', got %q", payload.Reason)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestAgentLoop_HookRespond_SteeringSkipsRemaining(t *testing.T) {
|
||||
provider := &multiToolProvider{
|
||||
toolCalls: []providers.ToolCall{
|
||||
{ID: "call-1", Name: "tool_one", Arguments: map[string]any{}},
|
||||
{ID: "call-2", Name: "tool_two", Arguments: map[string]any{}},
|
||||
{ID: "call-3", Name: "tool_three", Arguments: map[string]any{}},
|
||||
},
|
||||
finalContent: "done",
|
||||
}
|
||||
al, _, cleanup := newHookTestLoop(t, provider)
|
||||
defer cleanup()
|
||||
|
||||
al.RegisterTool(&slowTool{name: "tool_two", duration: 100 * time.Millisecond})
|
||||
al.RegisterTool(&slowTool{name: "tool_three", duration: 100 * time.Millisecond})
|
||||
|
||||
hook := &respondHook{
|
||||
respondTools: map[string]bool{"tool_one": true},
|
||||
}
|
||||
if err := al.MountHook(NamedHook("respond-hook", hook)); err != nil {
|
||||
t.Fatalf("MountHook failed: %v", err)
|
||||
}
|
||||
|
||||
sub := al.SubscribeEvents(32)
|
||||
defer al.UnsubscribeEvents(sub.ID)
|
||||
|
||||
sessionKey := routing.BuildAgentMainSessionKey(routing.DefaultAgentID)
|
||||
|
||||
type result struct {
|
||||
resp string
|
||||
err error
|
||||
}
|
||||
resultCh := make(chan result, 1)
|
||||
go func() {
|
||||
resp, err := al.ProcessDirectWithChannel(
|
||||
context.Background(),
|
||||
"run tools",
|
||||
sessionKey,
|
||||
"cli",
|
||||
"chat1",
|
||||
)
|
||||
resultCh <- result{resp: resp, err: err}
|
||||
}()
|
||||
|
||||
time.Sleep(50 * time.Millisecond)
|
||||
|
||||
al.Steer(providers.Message{Role: "user", Content: "change direction"})
|
||||
|
||||
select {
|
||||
case r := <-resultCh:
|
||||
if r.err != nil {
|
||||
t.Fatalf("unexpected error: %v", r.err)
|
||||
}
|
||||
case <-time.After(3 * time.Second):
|
||||
t.Fatal("timeout waiting for result")
|
||||
}
|
||||
|
||||
events := collectEventStream(sub.C)
|
||||
|
||||
skippedEvts := filterEvents(events, EventKindToolExecSkipped)
|
||||
if len(skippedEvts) < 1 {
|
||||
t.Fatal("expected at least one ToolExecSkipped event after steering")
|
||||
}
|
||||
|
||||
for _, evt := range skippedEvts {
|
||||
payload, ok := evt.Payload.(ToolExecSkippedPayload)
|
||||
if !ok {
|
||||
t.Fatalf("expected ToolExecSkippedPayload, got %T", evt.Payload)
|
||||
}
|
||||
if payload.Reason != "queued user steering message" {
|
||||
t.Fatalf("expected skip reason 'queued user steering message', got %q", payload.Reason)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func filterEvents(events []Event, kind EventKind) []Event {
|
||||
var result []Event
|
||||
for _, evt := range events {
|
||||
if evt.Kind == kind {
|
||||
result = append(result, evt)
|
||||
}
|
||||
}
|
||||
return result
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue