lzh/picoclaw
1
0
Fork 0
mirror of https://github.com/sipeed/picoclaw.git synced 2026-06-12 18:08:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into feat/markdown-output-format-web-fetch

Browse Source
This commit is contained in:
Mauro
2026-03-17 16:37:22 +01:00
committed by GitHub
parent de68688c75 c639e2c216
commit 3791f06faf
104 changed files with 6151 additions and 1202 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pkg/agent/context.go
+22 -3
View File
@@ -458,7 +458,23 @@ func (cb *ContextBuilder) LoadBootstrapFiles() string {
//
// See: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
// See: https://platform.openai.com/docs/guides/prompt-caching
func (cb *ContextBuilder) buildDynamicContext(channel, chatID string) string {
func formatCurrentSenderLine(senderID, senderDisplayName string) string {
senderID = strings.TrimSpace(senderID)
senderDisplayName = strings.TrimSpace(senderDisplayName)
switch {
case senderDisplayName != "" && senderID != "":
return fmt.Sprintf("Current sender: %s (ID: %s)", senderDisplayName, senderID)
case senderDisplayName != "":
return fmt.Sprintf("Current sender: %s", senderDisplayName)
case senderID != "":
return fmt.Sprintf("Current sender: %s", senderID)
default:
return ""
}
}
func (cb *ContextBuilder) buildDynamicContext(channel, chatID, senderID, senderDisplayName string) string {
now := time.Now().Format("2006-01-02 15:04 (Monday)")
rt := fmt.Sprintf("%s %s, Go %s", runtime.GOOS, runtime.GOARCH, runtime.Version())
@@ -468,6 +484,9 @@ func (cb *ContextBuilder) buildDynamicContext(channel, chatID string) string {
if channel != "" && chatID != "" {
fmt.Fprintf(&sb, "\n\n## Current Session\nChannel: %s\nChat ID: %s", channel, chatID)
}
if senderLine := formatCurrentSenderLine(senderID, senderDisplayName); senderLine != "" {
fmt.Fprintf(&sb, "\n\n## Current Sender\n%s", senderLine)
}
return sb.String()
}
@@ -477,7 +496,7 @@ func (cb *ContextBuilder) BuildMessages(
summary string,
currentMessage string,
media []string,
channel, chatID string,
channel, chatID, senderID, senderDisplayName string,
) []providers.Message {
messages := []providers.Message{}
@@ -493,7 +512,7 @@ func (cb *ContextBuilder) BuildMessages(
staticPrompt := cb.BuildSystemPromptWithCache()
// Build short dynamic context (time, runtime, session) — changes per request
dynamicCtx := cb.buildDynamicContext(channel, chatID)
dynamicCtx := cb.buildDynamicContext(channel, chatID, senderID, senderDisplayName)
// Compose a single system message: static (cached) + dynamic + optional summary.
// Keeping all system content in one message ensures every provider adapter can
pkg/agent/context_cache_test.go
+65 -3
View File
@@ -82,7 +82,7 @@ func TestSingleSystemMessage(t *testing.T) {
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
msgs := cb.BuildMessages(tt.history, tt.summary, tt.message, nil, "test", "chat1")
msgs := cb.BuildMessages(tt.history, tt.summary, tt.message, nil, "test", "chat1", "", "")
systemCount := 0
for _, m := range msgs {
@@ -126,6 +126,68 @@ func TestSingleSystemMessage(t *testing.T) {
}
}
func TestBuildMessages_CurrentSenderDynamicContext(t *testing.T) {
tmpDir := setupWorkspace(t, map[string]string{
"IDENTITY.md": "# Identity\nTest agent.",
})
defer os.RemoveAll(tmpDir)
cb := NewContextBuilder(tmpDir)
tests := []struct {
name string
senderID string
senderDisplayName string
wantLine string
wantSection bool
}{
{
name: "both id and display name",
senderID: "feishu:ou_xxx",
senderDisplayName: "Zhang San",
wantLine: "Current sender: Zhang San (ID: feishu:ou_xxx)",
wantSection: true,
},
{
name: "display name only",
senderDisplayName: "Alice",
wantLine: "Current sender: Alice",
wantSection: true,
},
{
name: "id only",
senderID: "discord:123",
wantLine: "Current sender: discord:123",
wantSection: true,
},
{
name: "no sender info",
wantSection: false,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
msgs := cb.BuildMessages(nil, "", "hello", nil, "discord", "chat1", tt.senderID, tt.senderDisplayName)
sys := msgs[0].Content
if tt.wantSection {
if !strings.Contains(sys, "## Current Sender") {
t.Fatalf("system prompt missing Current Sender section:\n%s", sys)
}
if !strings.Contains(sys, tt.wantLine) {
t.Fatalf("system prompt missing sender line %q:\n%s", tt.wantLine, sys)
}
return
}
if strings.Contains(sys, "## Current Sender") {
t.Fatalf("system prompt should omit Current Sender section:\n%s", sys)
}
})
}
}
// TestMtimeAutoInvalidation verifies that the cache detects source file changes
// via mtime without requiring explicit InvalidateCache().
// Fix: original implementation had no auto-invalidation — edits to bootstrap files,
@@ -576,7 +638,7 @@ func TestConcurrentBuildSystemPromptWithCache(t *testing.T) {
}
// Also exercise BuildMessages concurrently
msgs := cb.BuildMessages(nil, "", "hello", nil, "test", "chat")
msgs := cb.BuildMessages(nil, "", "hello", nil, "test", "chat", "", "")
if len(msgs) < 2 {
errs <- "BuildMessages returned fewer than 2 messages"
return
@@ -664,6 +726,6 @@ func BenchmarkBuildMessagesWithCache(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
_ = cb.BuildMessages(history, "summary", "new message", nil, "cli", "test")
_ = cb.BuildMessages(history, "summary", "new message", nil, "cli", "test", "", "")
}
}
pkg/agent/instance.go
+25 -2
View File
@@ -10,6 +10,7 @@ import (
"strings"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/media"
"github.com/sipeed/picoclaw/pkg/memory"
"github.com/sipeed/picoclaw/pkg/providers"
"github.com/sipeed/picoclaw/pkg/routing"
@@ -66,7 +67,7 @@ func NewAgentInstance(
readRestrict := restrict && !defaults.AllowReadOutsideWorkspace
// Compile path whitelist patterns from config.
allowReadPaths := compilePatterns(cfg.Tools.AllowReadPaths)
allowReadPaths := buildAllowReadPatterns(cfg)
allowWritePaths := compilePatterns(cfg.Tools.AllowWritePaths)
toolsRegistry := tools.NewToolRegistry()
@@ -82,7 +83,7 @@ func NewAgentInstance(
toolsRegistry.Register(tools.NewListDirTool(workspace, readRestrict, allowReadPaths))
}
if cfg.Tools.IsToolEnabled("exec") {
execTool, err := tools.NewExecToolWithConfig(workspace, restrict, cfg)
execTool, err := tools.NewExecToolWithConfig(workspace, restrict, cfg, allowReadPaths)
if err != nil {
log.Fatalf("Critical error: unable to initialize exec tool: %v", err)
}
@@ -282,6 +283,28 @@ func compilePatterns(patterns []string) []*regexp.Regexp {
return compiled
}
func buildAllowReadPatterns(cfg *config.Config) []*regexp.Regexp {
var configured []string
if cfg != nil {
configured = cfg.Tools.AllowReadPaths
}
compiled := compilePatterns(configured)
mediaDirPattern := regexp.MustCompile(mediaTempDirPattern())
for _, pattern := range compiled {
if pattern.String() == mediaDirPattern.String() {
return compiled
}
}
return append(compiled, mediaDirPattern)
}
func mediaTempDirPattern() string {
sep := regexp.QuoteMeta(string(os.PathSeparator))
return "^" + regexp.QuoteMeta(filepath.Clean(media.TempDir())) + "(?:" + sep + "|$)"
}
// Close releases resources held by the agent's session store.
func (a *AgentInstance) Close() error {
if a.Sessions != nil {
pkg/agent/instance_test.go
+86
View File
@@ -1,10 +1,14 @@
package agent
import (
"context"
"os"
"path/filepath"
"strings"
"testing"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/media"
)
func TestNewAgentInstance_UsesDefaultsTemperatureAndMaxTokens(t *testing.T) {
@@ -160,3 +164,85 @@ func TestNewAgentInstance_ResolveCandidatesFromModelListAlias(t *testing.T) {
})
}
}
func TestNewAgentInstance_AllowsMediaTempDirForReadListAndExec(t *testing.T) {
workspace := t.TempDir()
mediaDir := media.TempDir()
if err := os.MkdirAll(mediaDir, 0o700); err != nil {
t.Fatalf("MkdirAll(mediaDir) error = %v", err)
}
mediaFile, err := os.CreateTemp(mediaDir, "instance-tool-*.txt")
if err != nil {
t.Fatalf("CreateTemp(mediaDir) error = %v", err)
}
mediaPath := mediaFile.Name()
if _, err := mediaFile.WriteString("attachment content"); err != nil {
mediaFile.Close()
t.Fatalf("WriteString(mediaFile) error = %v", err)
}
if err := mediaFile.Close(); err != nil {
t.Fatalf("Close(mediaFile) error = %v", err)
}
t.Cleanup(func() { _ = os.Remove(mediaPath) })
cfg := &config.Config{
Agents: config.AgentsConfig{
Defaults: config.AgentDefaults{
Workspace: workspace,
ModelName: "test-model",
RestrictToWorkspace: true,
},
},
Tools: config.ToolsConfig{
ReadFile: config.ReadFileToolConfig{Enabled: true},
ListDir: config.ToolConfig{Enabled: true},
Exec: config.ExecConfig{
ToolConfig: config.ToolConfig{Enabled: true},
EnableDenyPatterns: true,
AllowRemote: true,
},
},
}
agent := NewAgentInstance(nil, &cfg.Agents.Defaults, cfg, &mockProvider{})
readTool, ok := agent.Tools.Get("read_file")
if !ok {
t.Fatal("read_file tool not registered")
}
readResult := readTool.Execute(context.Background(), map[string]any{"path": mediaPath})
if readResult.IsError {
t.Fatalf("read_file should allow media temp dir, got: %s", readResult.ForLLM)
}
if !strings.Contains(readResult.ForLLM, "attachment content") {
t.Fatalf("read_file output missing media content: %s", readResult.ForLLM)
}
listTool, ok := agent.Tools.Get("list_dir")
if !ok {
t.Fatal("list_dir tool not registered")
}
listResult := listTool.Execute(context.Background(), map[string]any{"path": mediaDir})
if listResult.IsError {
t.Fatalf("list_dir should allow media temp dir, got: %s", listResult.ForLLM)
}
if !strings.Contains(listResult.ForLLM, filepath.Base(mediaPath)) {
t.Fatalf("list_dir output missing media file: %s", listResult.ForLLM)
}
execTool, ok := agent.Tools.Get("exec")
if !ok {
t.Fatal("exec tool not registered")
}
execResult := execTool.Execute(context.Background(), map[string]any{
"command": "cat " + filepath.Base(mediaPath),
"working_dir": mediaDir,
})
if execResult.IsError {
t.Fatalf("exec should allow media temp dir, got: %s", execResult.ForLLM)
}
if !strings.Contains(execResult.ForLLM, "attachment content") {
t.Fatalf("exec output missing media content: %s", execResult.ForLLM)
}
}
pkg/agent/loop.go
+42 -26
View File
@@ -55,15 +55,17 @@ type AgentLoop struct {
// processOptions configures how a message is processed
type processOptions struct {
SessionKey string // Session identifier for history/context
Channel string // Target channel for tool execution
ChatID string // Target chat ID for tool execution
UserMessage string // User message content (may include prefix)
Media []string // media:// refs from inbound message
DefaultResponse string // Response when LLM returns empty
EnableSummary bool // Whether to trigger summarization
SendResponse bool // Whether to send response via bus
NoHistory bool // If true, don't load session history (for heartbeat)
SessionKey string // Session identifier for history/context
Channel string // Target channel for tool execution
ChatID string // Target chat ID for tool execution
SenderID string // Current sender ID for dynamic context
SenderDisplayName string // Current sender display name for dynamic context
UserMessage string // User message content (may include prefix)
Media []string // media:// refs from inbound message
DefaultResponse string // Response when LLM returns empty
EnableSummary bool // Whether to trigger summarization
SendResponse bool // Whether to send response via bus
NoHistory bool // If true, don't load session history (for heartbeat)
}
const (
@@ -117,6 +119,8 @@ func registerSharedTools(
registry *AgentRegistry,
provider providers.LLMProvider,
) {
allowReadPaths := buildAllowReadPatterns(cfg)
for _, agentID := range registry.ListAgentIDs() {
agent, ok := registry.GetAgent(agentID)
if !ok {
@@ -161,7 +165,8 @@ func registerSharedTools(
50000,
cfg.Tools.Web.Proxy,
cfg.Tools.Web.Format,
cfg.Tools.Web.FetchLimitBytes)
cfg.Tools.Web.FetchLimitBytes,
cfg.Tools.Web.PrivateHostWhitelist)
if err != nil {
logger.ErrorCF("agent", "Failed to create web fetch tool", map[string]any{"error": err.Error()})
} else {
@@ -199,6 +204,7 @@ func registerSharedTools(
cfg.Agents.Defaults.RestrictToWorkspace,
cfg.Agents.Defaults.GetMaxMediaSize(),
nil,
allowReadPaths,
)
agent.Tools.Register(sendFileTool)
}
@@ -226,20 +232,26 @@ func registerSharedTools(
}
}
// Spawn tool with allowlist checker
if cfg.Tools.IsToolEnabled("spawn") {
if cfg.Tools.IsToolEnabled("subagent") {
subagentManager := tools.NewSubagentManager(provider, agent.Model, agent.Workspace)
subagentManager.SetLLMOptions(agent.MaxTokens, agent.Temperature)
// Spawn and spawn_status tools share a SubagentManager.
// Construct it when either tool is enabled (both require subagent).
spawnEnabled := cfg.Tools.IsToolEnabled("spawn")
spawnStatusEnabled := cfg.Tools.IsToolEnabled("spawn_status")
if (spawnEnabled || spawnStatusEnabled) && cfg.Tools.IsToolEnabled("subagent") {
subagentManager := tools.NewSubagentManager(provider, agent.Model, agent.Workspace)
subagentManager.SetLLMOptions(agent.MaxTokens, agent.Temperature)
if spawnEnabled {
spawnTool := tools.NewSpawnTool(subagentManager)
currentAgentID := agentID
spawnTool.SetAllowlistChecker(func(targetAgentID string) bool {
return registry.CanSpawnSubagent(currentAgentID, targetAgentID)
})
agent.Tools.Register(spawnTool)
} else {
logger.WarnCF("agent", "spawn tool requires subagent to be enabled", nil)
}
if spawnStatusEnabled {
agent.Tools.Register(tools.NewSpawnStatusTool(subagentManager))
}
} else if (spawnEnabled || spawnStatusEnabled) && !cfg.Tools.IsToolEnabled("subagent") {
logger.WarnCF("agent", "spawn/spawn_status tools require subagent to be enabled", nil)
}
}
}
@@ -736,14 +748,16 @@ func (al *AgentLoop) processMessage(ctx context.Context, msg bus.InboundMessage)
})
opts := processOptions{
SessionKey: sessionKey,
Channel: msg.Channel,
ChatID: msg.ChatID,
UserMessage: msg.Content,
Media: msg.Media,
DefaultResponse: defaultResponse,
EnableSummary: true,
SendResponse: false,
SessionKey: sessionKey,
Channel: msg.Channel,
ChatID: msg.ChatID,
SenderID: msg.SenderID,
SenderDisplayName: msg.Sender.DisplayName,
UserMessage: msg.Content,
Media: msg.Media,
DefaultResponse: defaultResponse,
EnableSummary: true,
SendResponse: false,
}
// context-dependent commands check their own Runtime fields and report
@@ -883,6 +897,8 @@ func (al *AgentLoop) runAgentLoop(
opts.Media,
opts.Channel,
opts.ChatID,
opts.SenderID,
opts.SenderDisplayName,
)
// Resolve media:// refs: images→base64 data URLs, non-images→local paths in content
@@ -1154,7 +1170,7 @@ func (al *AgentLoop) runLLMIteration(
newSummary := agent.Sessions.GetSummary(opts.SessionKey)
messages = agent.ContextBuilder.BuildMessages(
newHistory, newSummary, "",
nil, opts.Channel, opts.ChatID,
nil, opts.Channel, opts.ChatID, opts.SenderID, opts.SenderDisplayName,
)
continue
}
pkg/agent/loop_test.go
+75
View File
@@ -30,6 +30,28 @@ func (f *fakeChannel) IsAllowed(string) bool {
func (f *fakeChannel) IsAllowedSender(sender bus.SenderInfo) bool { return true }
func (f *fakeChannel) ReasoningChannelID() string { return f.id }
type recordingProvider struct {
lastMessages []providers.Message
}
func (r *recordingProvider) Chat(
ctx context.Context,
messages []providers.Message,
tools []providers.ToolDefinition,
model string,
opts map[string]any,
) (*providers.LLMResponse, error) {
r.lastMessages = append([]providers.Message(nil), messages...)
return &providers.LLMResponse{
Content: "Mock response",
ToolCalls: []providers.ToolCall{},
}, nil
}
func (r *recordingProvider) GetDefaultModel() string {
return "mock-model"
}
func newTestAgentLoop(
t *testing.T,
) (al *AgentLoop, cfg *config.Config, msgBus *bus.MessageBus, provider *mockProvider, cleanup func()) {
@@ -54,6 +76,59 @@ func newTestAgentLoop(
return al, cfg, msgBus, provider, func() { os.RemoveAll(tmpDir) }
}
func TestProcessMessage_IncludesCurrentSenderInDynamicContext(t *testing.T) {
tmpDir, err := os.MkdirTemp("", "agent-test-*")
if err != nil {
t.Fatalf("Failed to create temp dir: %v", err)
}
defer os.RemoveAll(tmpDir)
cfg := &config.Config{
Agents: config.AgentsConfig{
Defaults: config.AgentDefaults{
Workspace: tmpDir,
Model: "test-model",
MaxTokens: 4096,
MaxToolIterations: 10,
},
},
}
msgBus := bus.NewMessageBus()
provider := &recordingProvider{}
al := NewAgentLoop(cfg, msgBus, provider)
response, err := al.processMessage(context.Background(), bus.InboundMessage{
Channel: "discord",
SenderID: "discord:123",
Sender: bus.SenderInfo{
DisplayName: "Alice",
},
ChatID: "group-1",
Content: "hello",
})
if err != nil {
t.Fatalf("processMessage() error = %v", err)
}
if response != "Mock response" {
t.Fatalf("processMessage() response = %q, want %q", response, "Mock response")
}
if len(provider.lastMessages) == 0 {
t.Fatal("provider did not receive any messages")
}
systemPrompt := provider.lastMessages[0].Content
wantSender := "## Current Sender\nCurrent sender: Alice (ID: discord:123)"
if !strings.Contains(systemPrompt, wantSender) {
t.Fatalf("system prompt missing sender context %q:\n%s", wantSender, systemPrompt)
}
lastMessage := provider.lastMessages[len(provider.lastMessages)-1]
if lastMessage.Role != "user" || lastMessage.Content != "hello" {
t.Fatalf("last provider message = %+v, want unchanged user message", lastMessage)
}
}
func TestRecordLastChannel(t *testing.T) {
al, cfg, msgBus, provider, cleanup := newTestAgentLoop(t)
defer cleanup()