picoclaw/pkg/agent/registry.go

141 lines
3.7 KiB
Go
Raw Normal View History

package agent
import (
"sync"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/logger"
"github.com/sipeed/picoclaw/pkg/providers"
"github.com/sipeed/picoclaw/pkg/routing"
feat(feishu,tools): add outbound media delivery via send_file tool (#1156) * feat(feishu): implement SendMedia and add send_file tool Add outbound media support for the Feishu channel so the agent can send images and files to users via the MediaStore pipeline. Feishu channel: - SendMedia dispatches media parts as image or file uploads - sendImage uploads via Image.Create then sends image message - sendFile uploads via File.Create then sends file message - feishuFileType maps extensions to Feishu file_type values send_file tool: - New tool lets the LLM send a local file to the current chat - Validates path, registers file in MediaStore, returns media ref - Agent loop wires tool registration, MediaStore propagation, and context updates Tested on Radxa Cubie A7A (arm64) with Feishu websocket channel. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(agent): publish outbound media regardless of SendResponse flag The SendResponse flag controls whether the agent loop publishes the final text response (callers that publish it themselves set this to false). However, the media publish path was also gated behind this flag, which meant tool-produced media was silently dropped for normal channel messages. Media should be published immediately when a tool returns media refs, independent of how the text response is delivered. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tools): use magic-bytes MIME detection and add file size limit to send_file - Replace hardcoded extension-to-MIME map with h2non/filetype (magic bytes) + mime.TypeByExtension fallback, consistent with the vision pipeline in resolveMediaRefs - Add configurable max file size check (defaults to config.DefaultMaxMediaSize, 20 MB) to prevent oversized uploads - Add tests for magic-bytes detection, extension fallback, size limit, and default max size Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor(agent): add ForEachTool to AgentRegistry for cross-agent tool lookup Extract the pattern of iterating agents to find a named tool into AgentRegistry.ForEachTool, simplifying SetMediaStore propagation. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(agent,tools): adapt send_file to ctx-based channel injection after upstream refactor Replace ContextualTool interface (removed upstream) with direct ctx reading in SendFileTool.Execute, using ToolChannel/ToolChatID helpers. Remove updateToolContexts which is no longer needed since ExecuteWithContext already injects channel/chatID into ctx for all tools. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(tools): support toggling send_file tool via config Add SendFileConfig with Enabled field to ToolsConfig, defaulting to true. Wrap send_file tool registration in loop.go with the config check, consistent with the pattern used by other tools. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 11:42:52 +00:00
"github.com/sipeed/picoclaw/pkg/tools"
)
// AgentRegistry manages multiple agent instances and routes messages to them.
type AgentRegistry struct {
agents map[string]*AgentInstance
resolver *routing.RouteResolver
mu sync.RWMutex
}
// NewAgentRegistry creates a registry from config, instantiating all agents.
func NewAgentRegistry(
cfg *config.Config,
provider providers.LLMProvider,
) *AgentRegistry {
registry := &AgentRegistry{
agents: make(map[string]*AgentInstance),
resolver: routing.NewRouteResolver(cfg),
}
agentConfigs := cfg.Agents.List
if len(agentConfigs) == 0 {
implicitAgent := &config.AgentConfig{
ID: "main",
Default: true,
}
instance := NewAgentInstance(implicitAgent, &cfg.Agents.Defaults, cfg, provider)
registry.agents["main"] = instance
logger.InfoCF("agent", "Created implicit main agent (no agents.list configured)", nil)
} else {
for i := range agentConfigs {
ac := &agentConfigs[i]
id := routing.NormalizeAgentID(ac.ID)
instance := NewAgentInstance(ac, &cfg.Agents.Defaults, cfg, provider)
registry.agents[id] = instance
logger.InfoCF("agent", "Registered agent",
2026-02-18 19:48:23 +00:00
map[string]any{
"agent_id": id,
"name": ac.Name,
"workspace": instance.Workspace,
"model": instance.Model,
})
}
}
return registry
}
// GetAgent returns the agent instance for a given ID.
func (r *AgentRegistry) GetAgent(agentID string) (*AgentInstance, bool) {
r.mu.RLock()
defer r.mu.RUnlock()
id := routing.NormalizeAgentID(agentID)
agent, ok := r.agents[id]
return agent, ok
}
// ResolveRoute determines which agent handles the message.
func (r *AgentRegistry) ResolveRoute(input routing.RouteInput) routing.ResolvedRoute {
return r.resolver.ResolveRoute(input)
}
// ListAgentIDs returns all registered agent IDs.
func (r *AgentRegistry) ListAgentIDs() []string {
r.mu.RLock()
defer r.mu.RUnlock()
ids := make([]string, 0, len(r.agents))
for id := range r.agents {
ids = append(ids, id)
}
return ids
}
// CanSpawnSubagent checks if parentAgentID is allowed to spawn targetAgentID.
func (r *AgentRegistry) CanSpawnSubagent(parentAgentID, targetAgentID string) bool {
parent, ok := r.GetAgent(parentAgentID)
if !ok {
return false
}
if parent.Subagents == nil || parent.Subagents.AllowAgents == nil {
return false
}
targetNorm := routing.NormalizeAgentID(targetAgentID)
for _, allowed := range parent.Subagents.AllowAgents {
if allowed == "*" {
return true
}
if routing.NormalizeAgentID(allowed) == targetNorm {
return true
}
}
return false
}
feat(feishu,tools): add outbound media delivery via send_file tool (#1156) * feat(feishu): implement SendMedia and add send_file tool Add outbound media support for the Feishu channel so the agent can send images and files to users via the MediaStore pipeline. Feishu channel: - SendMedia dispatches media parts as image or file uploads - sendImage uploads via Image.Create then sends image message - sendFile uploads via File.Create then sends file message - feishuFileType maps extensions to Feishu file_type values send_file tool: - New tool lets the LLM send a local file to the current chat - Validates path, registers file in MediaStore, returns media ref - Agent loop wires tool registration, MediaStore propagation, and context updates Tested on Radxa Cubie A7A (arm64) with Feishu websocket channel. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(agent): publish outbound media regardless of SendResponse flag The SendResponse flag controls whether the agent loop publishes the final text response (callers that publish it themselves set this to false). However, the media publish path was also gated behind this flag, which meant tool-produced media was silently dropped for normal channel messages. Media should be published immediately when a tool returns media refs, independent of how the text response is delivered. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tools): use magic-bytes MIME detection and add file size limit to send_file - Replace hardcoded extension-to-MIME map with h2non/filetype (magic bytes) + mime.TypeByExtension fallback, consistent with the vision pipeline in resolveMediaRefs - Add configurable max file size check (defaults to config.DefaultMaxMediaSize, 20 MB) to prevent oversized uploads - Add tests for magic-bytes detection, extension fallback, size limit, and default max size Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor(agent): add ForEachTool to AgentRegistry for cross-agent tool lookup Extract the pattern of iterating agents to find a named tool into AgentRegistry.ForEachTool, simplifying SetMediaStore propagation. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(agent,tools): adapt send_file to ctx-based channel injection after upstream refactor Replace ContextualTool interface (removed upstream) with direct ctx reading in SendFileTool.Execute, using ToolChannel/ToolChatID helpers. Remove updateToolContexts which is no longer needed since ExecuteWithContext already injects channel/chatID into ctx for all tools. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(tools): support toggling send_file tool via config Add SendFileConfig with Enabled field to ToolsConfig, defaulting to true. Wrap send_file tool registration in loop.go with the config check, consistent with the pattern used by other tools. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 11:42:52 +00:00
// ForEachTool calls fn for every tool registered under the given name
// across all agents. This is useful for propagating dependencies (e.g.
// MediaStore) to tools after registry construction.
func (r *AgentRegistry) ForEachTool(name string, fn func(tools.Tool)) {
r.mu.RLock()
defer r.mu.RUnlock()
for _, agent := range r.agents {
if t, ok := agent.Tools.Get(name); ok {
fn(t)
}
}
}
feat(session): integrate JSONL persistence into agent loop (#1170) * feat(session): add SessionStore interface and JSONL backend adapter Extract a SessionStore interface from the methods the agent loop uses (AddMessage, GetHistory, SetSummary, TruncateHistory, Save, etc.). Both SessionManager and the new JSONLBackend satisfy this interface, allowing the persistence layer to be swapped transparently. JSONLBackend wraps memory.Store and maps its error-returning API to the fire-and-forget contract that the agent loop expects — write errors are logged, reads return empty defaults on failure. Save() triggers compaction to reclaim space after logical truncation. Part of #1169 * test(session): add JSONLBackend integration tests 8 tests covering the full SessionStore contract through the JSONL backend: message roundtrip, tool calls, summary, truncation with compaction, history replacement, empty sessions, session isolation, and the complete summarization flow (SetSummary → TruncateHistory → Save). Includes compile-time interface satisfaction checks for both SessionManager and JSONLBackend. Part of #1169 * feat(agent): wire JSONL session store into agent loop Replace the concrete *SessionManager field with the SessionStore interface and initialize the JSONL backend by default. Legacy .json session files are auto-migrated on first startup. Falls back to SessionManager if the JSONL store cannot be initialized. The agent loop code (loop.go) requires zero changes — all method calls work identically through the interface. Closes #1169 * fix(session): propagate compact error from Save Save() was swallowing the error returned by Compact and always returning nil. Callers checking Save's return value would never see a compaction failure. Return the error directly so the agent loop can log or handle it as needed. * feat(session): add Close to SessionStore interface Add Close() error to SessionStore so callers can release resources through the interface. JSONLBackend already had Close; this adds a no-op implementation to SessionManager for compatibility. * fix(session): close session stores on shutdown and harden migration - Add Close() to AgentInstance, AgentRegistry, and AgentLoop so JSONL file handles are released during gateway shutdown and CLI exit. - Fall back to SessionManager when migration fails, preventing a split state where some sessions live in JSONL and others remain in JSON. - Add defer agentLoop.Close() in the CLI agent command path. - Document SessionStore interface methods (fire-and-forget contract).
2026-03-10 07:14:09 +00:00
// Close releases resources held by all registered agents.
func (r *AgentRegistry) Close() {
r.mu.RLock()
defer r.mu.RUnlock()
for _, agent := range r.agents {
if err := agent.Close(); err != nil {
logger.WarnCF("agent", "Failed to close agent",
map[string]any{"agent_id": agent.ID, "error": err.Error()})
}
}
}
// GetDefaultAgent returns the default agent instance.
func (r *AgentRegistry) GetDefaultAgent() *AgentInstance {
r.mu.RLock()
defer r.mu.RUnlock()
if agent, ok := r.agents["main"]; ok {
return agent
}
for _, agent := range r.agents {
return agent
}
return nil
}