diff --git a/.jules/bolt.md b/.jules/bolt.md index 40193998b..80e90d5aa 100644 --- a/.jules/bolt.md +++ b/.jules/bolt.md @@ -1,3 +1,6 @@ ## 2024-05-24 - Single Pass String Iteration for Token Estimation **Learning:** `utf8.RuneCountInString(msg)` performs a full iteration over the string. If the string needs to be iterated over again (e.g., `for _, r := range msg`) to check specific rune properties, this results in two full passes over the string. -**Action:** Always count the total number of runes manually within the existing `for range` loop when a subsequent full iteration of the string is already required. This essentially halves the execution time. \ No newline at end of file +**Action:** Always count the total number of runes manually within the existing `for range` loop when a subsequent full iteration of the string is already required. This essentially halves the execution time. +## 2024-05-25 - Efficient String Building in Loops +**Learning:** In Go, string concatenation (`+=`) in a loop leads to $O(N^2)$ complexity due to immutability. Using `strings.Builder` provides $O(N)$ efficiency. Additionally, `fmt.Fprintf` has overhead due to format string parsing; direct `sb.WriteString` calls are significantly faster. +**Action:** Use `strings.Builder` for building strings in loops and prefer direct `WriteString` calls over `fmt.Fprintf` for maximum performance in hot paths. diff --git a/.jules/sentinel.md b/.jules/sentinel.md new file mode 100644 index 000000000..0bb5d19ab --- /dev/null +++ b/.jules/sentinel.md @@ -0,0 +1,4 @@ +## 2025-02-28 - [Medium] Fix Missing HTTP Server Timeouts +**Vulnerability:** Go's standard `http.ListenAndServe` and unconfigured `http.Server` instances lack default timeouts for reading headers, reading bodies, and writing responses. +**Learning:** These default settings leave the application vulnerable to resource exhaustion and Denial of Service (DoS) attacks, such as Slowloris, because malicious clients can slowly send data and tie up server connections indefinitely. +**Prevention:** Always instantiate `http.Server` explicitly and set `ReadHeaderTimeout`, `ReadTimeout`, `WriteTimeout`, and (optionally) `IdleTimeout` to reasonable values based on the expected request sizes and latencies. diff --git a/patch_llm.patch b/patch_llm.patch deleted file mode 100644 index f7aea1a6b..000000000 --- a/patch_llm.patch +++ /dev/null @@ -1,139 +0,0 @@ ---- pkg/agent/loop.go -+++ pkg/agent/loop.go -@@ -910,121 +910,13 @@ - "tools_json": formatToolsForLog(providerToolDefs), - }) - -- // Call LLM with fallback chain if multiple candidates are configured. -- var response *providers.LLMResponse -- var err error -- -- llmOpts := map[string]any{ -- "max_tokens": agent.MaxTokens, -- "temperature": agent.Temperature, -- "prompt_cache_key": agent.ID, -- } -- // parseThinkingLevel guarantees ThinkingOff for empty/unknown values, -- // so checking != ThinkingOff is sufficient. -- if agent.ThinkingLevel != ThinkingOff { -- if tc, ok := agent.Provider.(providers.ThinkingCapable); ok && tc.SupportsThinking() { -- llmOpts["thinking_level"] = string(agent.ThinkingLevel) -- } else { -- logger.WarnCF("agent", "thinking_level is set but current provider does not support it, ignoring", -- map[string]any{"agent_id": agent.ID, "thinking_level": string(agent.ThinkingLevel)}) -- } -- } -- -- callLLM := func() (*providers.LLMResponse, error) { -- if len(activeCandidates) > 1 && al.fallback != nil { -- fbResult, fbErr := al.fallback.Execute( -- ctx, -- activeCandidates, -- func(ctx context.Context, provider, model string) (*providers.LLMResponse, error) { -- return agent.Provider.Chat(ctx, messages, providerToolDefs, model, llmOpts) -- }, -- ) -- if fbErr != nil { -- return nil, fbErr -- } -- if fbResult.Provider != "" && len(fbResult.Attempts) > 0 { -- logger.InfoCF( -- "agent", -- fmt.Sprintf("Fallback: succeeded with %s/%s after %d attempts", -- fbResult.Provider, fbResult.Model, len(fbResult.Attempts)+1), -- map[string]any{"agent_id": agent.ID, "iteration": iteration}, -- ) -- } -- return fbResult.Response, nil -- } -- return agent.Provider.Chat(ctx, messages, providerToolDefs, activeModel, llmOpts) -- } -- -- // Retry loop for context/token errors -- maxRetries := 2 -- for retry := 0; retry <= maxRetries; retry++ { -- response, err = callLLM() -- if err == nil { -- break -- } -- -- errMsg := strings.ToLower(err.Error()) -- -- // Check if this is a network/HTTP timeout — not a context window error. -- isTimeoutError := errors.Is(err, context.DeadlineExceeded) || -- strings.Contains(errMsg, "deadline exceeded") || -- strings.Contains(errMsg, "client.timeout") || -- strings.Contains(errMsg, "timed out") || -- strings.Contains(errMsg, "timeout exceeded") -- -- // Detect real context window / token limit errors, excluding network timeouts. -- isContextError := !isTimeoutError && (strings.Contains(errMsg, "context_length_exceeded") || -- strings.Contains(errMsg, "context window") || -- strings.Contains(errMsg, "maximum context length") || -- strings.Contains(errMsg, "token limit") || -- strings.Contains(errMsg, "too many tokens") || -- strings.Contains(errMsg, "max_tokens") || -- strings.Contains(errMsg, "invalidparameter") || -- strings.Contains(errMsg, "prompt is too long") || -- strings.Contains(errMsg, "request too large")) -- -- if isTimeoutError && retry < maxRetries { -- backoff := time.Duration(retry+1) * 5 * time.Second -- logger.WarnCF("agent", "Timeout error, retrying after backoff", map[string]any{ -- "error": err.Error(), -- "retry": retry, -- "backoff": backoff.String(), -- }) -- time.Sleep(backoff) -- continue -- } -- -- if isContextError && retry < maxRetries { -- logger.WarnCF( -- "agent", -- "Context window error detected, attempting compression", -- map[string]any{ -- "error": err.Error(), -- "retry": retry, -- }, -- ) -- -- if retry == 0 && !constants.IsInternalChannel(opts.Channel) { -- al.bus.PublishOutbound(ctx, bus.OutboundMessage{ -- Channel: opts.Channel, -- ChatID: opts.ChatID, -- Content: "Context window exceeded. Compressing history and retrying...", -- }) -- } -- -- al.forceCompression(agent, opts.SessionKey) -- newHistory := agent.Sessions.GetHistory(opts.SessionKey) -- newSummary := agent.Sessions.GetSummary(opts.SessionKey) -- messages = agent.ContextBuilder.BuildMessages( -- newHistory, newSummary, "", -- nil, opts.Channel, opts.ChatID, -- ) -- continue -- } -- break -- } -- -- if err != nil { -- logger.ErrorCF("agent", "LLM call failed", -- map[string]any{ -- "agent_id": agent.ID, -- "iteration": iteration, -- "error": err.Error(), -- }) -- return "", iteration, fmt.Errorf("LLM call failed after retries: %w", err) -- } -+ response, err := al.executeLLMWithRetry( -+ ctx, agent, opts, &messages, -+ providerToolDefs, activeCandidates, -+ activeModel, iteration, -+ ) -+ if err != nil { -+ return "", iteration, err -+ } - - go al.handleReasoning( diff --git a/patch_readme.patch b/patch_readme.patch deleted file mode 100644 index 5779565f4..000000000 --- a/patch_readme.patch +++ /dev/null @@ -1,18 +0,0 @@ ---- AGENT_LOOP_IMPROVEMENTS.md -+++ AGENT_LOOP_IMPROVEMENTS.md -@@ -4,14 +4,14 @@ - - ## Phase 1: Architecture & Maintainability (Refactoring) --- [ ] **Extract LLM Call & Retry Logic:** Refactor `runLLMIteration` by moving the LLM calling, fallback chain, and context window retry logic into a dedicated method (e.g., `executeLLMWithRetry`). --- [ ] **Extract Tool Execution Logic:** Refactor `runLLMIteration` by moving the parallel tool execution (`sync.WaitGroup`), channel routing, and async callbacks into a dedicated method (e.g., `executeToolBatch`). --- [ ] **State Machine / Explicit Flow:** Clean up the main loop logic to reduce nested `if/for` blocks and make the transition between generating, executing tools, and compressing context more explicit. -+- [x] **Extract LLM Call & Retry Logic:** Refactor `runLLMIteration` by moving the LLM calling, fallback chain, and context window retry logic into a dedicated method (e.g., `executeLLMWithRetry`). -+- [x] **Extract Tool Execution Logic:** Refactor `runLLMIteration` by moving the parallel tool execution (`sync.WaitGroup`), channel routing, and async callbacks into a dedicated method (e.g., `executeToolBatch`). -+- [x] **State Machine / Explicit Flow:** Clean up the main loop logic to reduce nested `if/for` blocks and make the transition between generating, executing tools, and compressing context more explicit. - - ## Phase 2: Reliability & Error Handling --- [ ] **Graceful Recovery on Tool Panic:** Add `defer recover()` inside the parallel tool execution goroutines to prevent a panicked tool from crashing the entire `AgentLoop`. Return the panic as an error string to the LLM. --- [ ] **Exponential Backoff:** Replace the linear backoff in LLM retries (`time.Duration(retry+1) * 5 * time.Second`) with exponential backoff and jitter to better handle rate limits. -+- [x] **Graceful Recovery on Tool Panic:** Add `defer recover()` inside the parallel tool execution goroutines to prevent a panicked tool from crashing the entire `AgentLoop`. Return the panic as an error string to the LLM. -+- [x] **Exponential Backoff:** Replace the linear backoff in LLM retries (`time.Duration(retry+1) * 5 * time.Second`) with exponential backoff and jitter to better handle rate limits. - - [ ] **Granular Error Classification:** Update `LLMProvider` interfaces to return structured, typed errors (e.g., `providers.ErrContextLengthExceeded`) instead of relying on fragile string matching. diff --git a/pkg/agent/loop.go b/pkg/agent/loop.go index 670c7104d..fe0bbe77e 100644 --- a/pkg/agent/loop.go +++ b/pkg/agent/loop.go @@ -7,31 +7,16 @@ package agent import ( - "context" - "encoding/json" - "errors" - "fmt" - "path/filepath" - "regexp" - "strings" "sync" "sync/atomic" - "time" - "unicode/utf8" "jane/pkg/bus" "jane/pkg/channels" "jane/pkg/commands" "jane/pkg/config" - "jane/pkg/constants" - "jane/pkg/logger" "jane/pkg/media" "jane/pkg/providers" - "jane/pkg/routing" - "jane/pkg/skills" "jane/pkg/state" - "jane/pkg/tools" - "jane/pkg/utils" "jane/pkg/voice" ) @@ -72,1565 +57,3 @@ const ( metadataKeyParentPeerKind = "parent_peer_kind" metadataKeyParentPeerID = "parent_peer_id" ) - -func NewAgentLoop( - cfg *config.Config, - msgBus *bus.MessageBus, - provider providers.LLMProvider, -) *AgentLoop { - registry := NewAgentRegistry(cfg, provider) - - // Register shared tools to all agents - registerSharedTools(cfg, msgBus, registry, provider) - - // Set up shared fallback chain - cooldown := providers.NewCooldownTracker() - fallbackChain := providers.NewFallbackChain(cooldown) - - // Create state manager using default agent's workspace for channel recording - defaultAgent := registry.GetDefaultAgent() - var stateManager *state.Manager - if defaultAgent != nil { - stateManager = state.NewManager(defaultAgent.Workspace) - } - - al := &AgentLoop{ - bus: msgBus, - cfg: cfg, - registry: registry, - state: stateManager, - summarizing: sync.Map{}, - fallback: fallbackChain, - cmdRegistry: commands.NewRegistry(commands.BuiltinDefinitions()), - } - - return al -} - -// registerSharedTools registers tools that are shared across all agents (web, message, spawn). -func registerSharedTools( - cfg *config.Config, - msgBus *bus.MessageBus, - registry *AgentRegistry, - provider providers.LLMProvider, -) { - for _, agentID := range registry.ListAgentIDs() { - agent, ok := registry.GetAgent(agentID) - if !ok { - continue - } - - if cfg.Tools.IsToolEnabled("web") { - searchTool, err := tools.NewWebSearchTool(tools.WebSearchToolOptions{ - BraveAPIKeys: config.MergeAPIKeys(cfg.Tools.Web.Brave.APIKey, cfg.Tools.Web.Brave.APIKeys), - BraveMaxResults: cfg.Tools.Web.Brave.MaxResults, - BraveEnabled: cfg.Tools.Web.Brave.Enabled, - TavilyAPIKeys: config.MergeAPIKeys(cfg.Tools.Web.Tavily.APIKey, cfg.Tools.Web.Tavily.APIKeys), - TavilyBaseURL: cfg.Tools.Web.Tavily.BaseURL, - TavilyMaxResults: cfg.Tools.Web.Tavily.MaxResults, - TavilyEnabled: cfg.Tools.Web.Tavily.Enabled, - DuckDuckGoMaxResults: cfg.Tools.Web.DuckDuckGo.MaxResults, - DuckDuckGoEnabled: cfg.Tools.Web.DuckDuckGo.Enabled, - PerplexityAPIKeys: config.MergeAPIKeys( - cfg.Tools.Web.Perplexity.APIKey, - cfg.Tools.Web.Perplexity.APIKeys, - ), - PerplexityMaxResults: cfg.Tools.Web.Perplexity.MaxResults, - PerplexityEnabled: cfg.Tools.Web.Perplexity.Enabled, - SearXNGBaseURL: cfg.Tools.Web.SearXNG.BaseURL, - SearXNGMaxResults: cfg.Tools.Web.SearXNG.MaxResults, - SearXNGEnabled: cfg.Tools.Web.SearXNG.Enabled, - GLMSearchAPIKey: cfg.Tools.Web.GLMSearch.APIKey, - GLMSearchBaseURL: cfg.Tools.Web.GLMSearch.BaseURL, - GLMSearchEngine: cfg.Tools.Web.GLMSearch.SearchEngine, - GLMSearchMaxResults: cfg.Tools.Web.GLMSearch.MaxResults, - GLMSearchEnabled: cfg.Tools.Web.GLMSearch.Enabled, - Proxy: cfg.Tools.Web.Proxy, - }) - if err != nil { - logger.ErrorCF("agent", "Failed to create web search tool", map[string]any{"error": err.Error()}) - } else if searchTool != nil { - agent.Tools.Register(searchTool) - } - } - if cfg.Tools.IsToolEnabled("web_fetch") { - fetchTool, err := tools.NewWebFetchToolWithProxy(50000, cfg.Tools.Web.Proxy, cfg.Tools.Web.FetchLimitBytes) - if err != nil { - logger.ErrorCF("agent", "Failed to create web fetch tool", map[string]any{"error": err.Error()}) - } else { - agent.Tools.Register(fetchTool) - } - } - - // Hardware tools (I2C, SPI) - Linux only, returns error on other platforms - if cfg.Tools.IsToolEnabled("i2c") { - agent.Tools.Register(tools.NewI2CTool()) - } - if cfg.Tools.IsToolEnabled("spi") { - agent.Tools.Register(tools.NewSPITool()) - } - - // Message tool - if cfg.Tools.IsToolEnabled("message") { - messageTool := tools.NewMessageTool() - messageTool.SetSendCallback(func(channel, chatID, content string) error { - pubCtx, pubCancel := context.WithTimeout(context.Background(), 5*time.Second) - defer pubCancel() - return msgBus.PublishOutbound(pubCtx, bus.OutboundMessage{ - Channel: channel, - ChatID: chatID, - Content: content, - }) - }) - agent.Tools.Register(messageTool) - } - - // Send file tool (outbound media via MediaStore — store injected later by SetMediaStore) - if cfg.Tools.IsToolEnabled("send_file") { - sendFileTool := tools.NewSendFileTool( - agent.Workspace, - cfg.Agents.Defaults.RestrictToWorkspace, - cfg.Agents.Defaults.GetMaxMediaSize(), - nil, - ) - agent.Tools.Register(sendFileTool) - } - - // Skill discovery and installation tools - skills_enabled := cfg.Tools.IsToolEnabled("skills") - find_skills_enable := cfg.Tools.IsToolEnabled("find_skills") - install_skills_enable := cfg.Tools.IsToolEnabled("install_skill") - if skills_enabled && (find_skills_enable || install_skills_enable) { - registryMgr := skills.NewRegistryManagerFromConfig(skills.RegistryConfig{ - MaxConcurrentSearches: cfg.Tools.Skills.MaxConcurrentSearches, - ClawHub: skills.ClawHubConfig(cfg.Tools.Skills.Registries.ClawHub), - }) - - if find_skills_enable { - searchCache := skills.NewSearchCache( - cfg.Tools.Skills.SearchCache.MaxSize, - time.Duration(cfg.Tools.Skills.SearchCache.TTLSeconds)*time.Second, - ) - agent.Tools.Register(tools.NewFindSkillsTool(registryMgr, searchCache)) - } - - if install_skills_enable { - agent.Tools.Register(tools.NewInstallSkillTool(registryMgr, agent.Workspace)) - } - } - - // 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) - 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) - } - } - } -} - -func (al *AgentLoop) Run(ctx context.Context) error { - al.running.Store(true) - if err := al.ensureMCPInitialized(ctx); err != nil { - return err - } - - for al.running.Load() { - select { - case <-ctx.Done(): - return nil - default: - msg, ok := al.bus.ConsumeInbound(ctx) - if !ok { - continue - } - - // Process message - func() { - // TODO: Re-enable media cleanup after inbound media is properly consumed by the agent. - // Currently disabled because files are deleted before the LLM can access their content. - // defer func() { - // if al.mediaStore != nil && msg.MediaScope != "" { - // if releaseErr := al.mediaStore.ReleaseAll(msg.MediaScope); releaseErr != nil { - // logger.WarnCF("agent", "Failed to release media", map[string]any{ - // "scope": msg.MediaScope, - // "error": releaseErr.Error(), - // }) - // } - // } - // }() - - response, err := al.processMessage(ctx, msg) - if err != nil { - response = fmt.Sprintf("Error processing message: %v", err) - } - - if response != "" { - // Check if the message tool already sent a response during this round. - // If so, skip publishing to avoid duplicate messages to the user. - // Use default agent's tools to check (message tool is shared). - alreadySent := false - defaultAgent := al.registry.GetDefaultAgent() - if defaultAgent != nil { - if tool, ok := defaultAgent.Tools.Get("message"); ok { - if mt, ok := tool.(*tools.MessageTool); ok { - alreadySent = mt.HasSentInRound() - } - } - } - - if !alreadySent { - al.bus.PublishOutbound(ctx, bus.OutboundMessage{ - Channel: msg.Channel, - ChatID: msg.ChatID, - Content: response, - }) - logger.InfoCF("agent", "Published outbound response", - map[string]any{ - "channel": msg.Channel, - "chat_id": msg.ChatID, - "content_len": len(response), - }) - } else { - logger.DebugCF( - "agent", - "Skipped outbound (message tool already sent)", - map[string]any{"channel": msg.Channel}, - ) - } - } - }() - } - } - - return nil -} - -func (al *AgentLoop) Stop() { - al.running.Store(false) -} - -// Close releases resources held by agent session stores. Call after Stop. -func (al *AgentLoop) Close() { - mcpManager := al.mcp.takeManager() - - if mcpManager != nil { - if err := mcpManager.Close(); err != nil { - logger.ErrorCF("agent", "Failed to close MCP manager", - map[string]any{ - "error": err.Error(), - }) - } - } - - al.registry.Close() -} - -func (al *AgentLoop) RegisterTool(tool tools.Tool) { - for _, agentID := range al.registry.ListAgentIDs() { - if agent, ok := al.registry.GetAgent(agentID); ok { - agent.Tools.Register(tool) - } - } -} - -func (al *AgentLoop) SetChannelManager(cm *channels.Manager) { - al.channelManager = cm -} - -// SetMediaStore injects a MediaStore for media lifecycle management. -func (al *AgentLoop) SetMediaStore(s media.MediaStore) { - al.mediaStore = s - - // Propagate store to send_file tools in all agents. - al.registry.ForEachTool("send_file", func(t tools.Tool) { - if sf, ok := t.(*tools.SendFileTool); ok { - sf.SetMediaStore(s) - } - }) -} - -// SetTranscriber injects a voice transcriber for agent-level audio transcription. -func (al *AgentLoop) SetTranscriber(t voice.Transcriber) { - al.transcriber = t -} - -var audioAnnotationRe = regexp.MustCompile(`\[(voice|audio)(?::[^\]]*)?\]`) - -// transcribeAudioInMessage resolves audio media refs, transcribes them, and -// replaces audio annotations in msg.Content with the transcribed text. -// Returns the (possibly modified) message and true if audio was transcribed. -func (al *AgentLoop) transcribeAudioInMessage(ctx context.Context, msg bus.InboundMessage) (bus.InboundMessage, bool) { - if al.transcriber == nil || al.mediaStore == nil || len(msg.Media) == 0 { - return msg, false - } - - // Transcribe each audio media ref in order. - var transcriptions []string - for _, ref := range msg.Media { - path, meta, err := al.mediaStore.ResolveWithMeta(ref) - if err != nil { - logger.WarnCF("voice", "Failed to resolve media ref", map[string]any{"ref": ref, "error": err}) - continue - } - if !utils.IsAudioFile(meta.Filename, meta.ContentType) { - continue - } - result, err := al.transcriber.Transcribe(ctx, path) - if err != nil { - logger.WarnCF("voice", "Transcription failed", map[string]any{"ref": ref, "error": err}) - transcriptions = append(transcriptions, "") - continue - } - transcriptions = append(transcriptions, result.Text) - } - - if len(transcriptions) == 0 { - return msg, false - } - - al.sendTranscriptionFeedback(ctx, msg.Channel, msg.ChatID, msg.MessageID, transcriptions) - - // Replace audio annotations sequentially with transcriptions. - idx := 0 - newContent := audioAnnotationRe.ReplaceAllStringFunc(msg.Content, func(match string) string { - if idx >= len(transcriptions) { - return match - } - text := transcriptions[idx] - idx++ - return "[voice: " + text + "]" - }) - - // Append any remaining transcriptions not matched by an annotation. - for ; idx < len(transcriptions); idx++ { - newContent += "\n[voice: " + transcriptions[idx] + "]" - } - - msg.Content = newContent - return msg, true -} - -// sendTranscriptionFeedback sends feedback to the user with the result of -// audio transcription if the option is enabled. It uses Manager.SendMessage -// which executes synchronously (rate limiting, splitting, retry) so that -// ordering with the subsequent placeholder is guaranteed. -func (al *AgentLoop) sendTranscriptionFeedback( - ctx context.Context, - channel, chatID, messageID string, - validTexts []string, -) { - if !al.cfg.Voice.EchoTranscription { - return - } - if al.channelManager == nil { - return - } - - var nonEmpty []string - for _, t := range validTexts { - if t != "" { - nonEmpty = append(nonEmpty, t) - } - } - - var feedbackMsg string - if len(nonEmpty) > 0 { - feedbackMsg = "Transcript: " + strings.Join(nonEmpty, "\n") - } else { - feedbackMsg = "No voice detected in the audio" - } - - err := al.channelManager.SendMessage(ctx, bus.OutboundMessage{ - Channel: channel, - ChatID: chatID, - Content: feedbackMsg, - ReplyToMessageID: messageID, - }) - if err != nil { - logger.WarnCF("voice", "Failed to send transcription feedback", map[string]any{"error": err.Error()}) - } -} - -// inferMediaType determines the media type ("image", "audio", "video", "file") -// from a filename and MIME content type. -func inferMediaType(filename, contentType string) string { - ct := strings.ToLower(contentType) - fn := strings.ToLower(filename) - - if strings.HasPrefix(ct, "image/") { - return "image" - } - if strings.HasPrefix(ct, "audio/") || ct == "application/ogg" { - return "audio" - } - if strings.HasPrefix(ct, "video/") { - return "video" - } - - // Fallback: infer from extension - ext := filepath.Ext(fn) - switch ext { - case ".jpg", ".jpeg", ".png", ".gif", ".webp", ".bmp", ".svg": - return "image" - case ".mp3", ".wav", ".ogg", ".m4a", ".flac", ".aac", ".wma", ".opus": - return "audio" - case ".mp4", ".avi", ".mov", ".webm", ".mkv": - return "video" - } - - return "file" -} - -// RecordLastChannel records the last active channel for this workspace. -// This uses the atomic state save mechanism to prevent data loss on crash. -func (al *AgentLoop) RecordLastChannel(channel string) error { - if al.state == nil { - return nil - } - return al.state.SetLastChannel(channel) -} - -// RecordLastChatID records the last active chat ID for this workspace. -// This uses the atomic state save mechanism to prevent data loss on crash. -func (al *AgentLoop) RecordLastChatID(chatID string) error { - if al.state == nil { - return nil - } - return al.state.SetLastChatID(chatID) -} - -func (al *AgentLoop) ProcessDirect( - ctx context.Context, - content, sessionKey string, -) (string, error) { - return al.ProcessDirectWithChannel(ctx, content, sessionKey, "cli", "direct") -} - -func (al *AgentLoop) ProcessDirectWithChannel( - ctx context.Context, - content, sessionKey, channel, chatID string, -) (string, error) { - if err := al.ensureMCPInitialized(ctx); err != nil { - return "", err - } - - msg := bus.InboundMessage{ - Channel: channel, - SenderID: "cron", - ChatID: chatID, - Content: content, - SessionKey: sessionKey, - } - - return al.processMessage(ctx, msg) -} - -// ProcessHeartbeat processes a heartbeat request without session history. -// Each heartbeat is independent and doesn't accumulate context. -func (al *AgentLoop) ProcessHeartbeat( - ctx context.Context, - content, channel, chatID string, -) (string, error) { - agent := al.registry.GetDefaultAgent() - if agent == nil { - return "", fmt.Errorf("no default agent for heartbeat") - } - return al.runAgentLoop(ctx, agent, processOptions{ - SessionKey: "heartbeat", - Channel: channel, - ChatID: chatID, - UserMessage: content, - DefaultResponse: defaultResponse, - EnableSummary: false, - SendResponse: false, - NoHistory: true, // Don't load session history for heartbeat - }) -} - -func (al *AgentLoop) processMessage(ctx context.Context, msg bus.InboundMessage) (string, error) { - // Add message preview to log (show full content for error messages) - var logContent string - if strings.Contains(msg.Content, "Error:") || strings.Contains(msg.Content, "error") { - logContent = msg.Content // Full content for errors - } else { - logContent = utils.Truncate(msg.Content, 80) - } - logger.InfoCF( - "agent", - fmt.Sprintf("Processing message from %s:%s: %s", msg.Channel, msg.SenderID, logContent), - map[string]any{ - "channel": msg.Channel, - "chat_id": msg.ChatID, - "sender_id": msg.SenderID, - "session_key": msg.SessionKey, - }, - ) - - var hadAudio bool - msg, hadAudio = al.transcribeAudioInMessage(ctx, msg) - - // For audio messages the placeholder was deferred by the channel. - // Now that transcription (and optional feedback) is done, send it. - if hadAudio && al.channelManager != nil { - al.channelManager.SendPlaceholder(ctx, msg.Channel, msg.ChatID) - } - - // Route system messages to processSystemMessage - if msg.Channel == "system" { - return al.processSystemMessage(ctx, msg) - } - - route, agent, routeErr := al.resolveMessageRoute(msg) - if routeErr != nil { - return "", routeErr - } - - // Reset message-tool state for this round so we don't skip publishing due to a previous round. - if tool, ok := agent.Tools.Get("message"); ok { - if resetter, ok := tool.(interface{ ResetSentInRound() }); ok { - resetter.ResetSentInRound() - } - } - - // Resolve session key from route, while preserving explicit agent-scoped keys. - scopeKey := resolveScopeKey(route, msg.SessionKey) - sessionKey := scopeKey - - logger.InfoCF("agent", "Routed message", - map[string]any{ - "agent_id": agent.ID, - "scope_key": scopeKey, - "session_key": sessionKey, - "matched_by": route.MatchedBy, - "route_agent": route.AgentID, - "route_channel": route.Channel, - }) - - opts := processOptions{ - SessionKey: sessionKey, - Channel: msg.Channel, - ChatID: msg.ChatID, - UserMessage: msg.Content, - Media: msg.Media, - DefaultResponse: defaultResponse, - EnableSummary: true, - SendResponse: false, - } - - // context-dependent commands check their own Runtime fields and report - // "unavailable" when the required capability is nil. - if response, handled := al.handleCommand(ctx, msg, agent, &opts); handled { - return response, nil - } - - return al.runAgentLoop(ctx, agent, opts) -} - -func (al *AgentLoop) resolveMessageRoute(msg bus.InboundMessage) (routing.ResolvedRoute, *AgentInstance, error) { - route := al.registry.ResolveRoute(routing.RouteInput{ - Channel: msg.Channel, - AccountID: inboundMetadata(msg, metadataKeyAccountID), - Peer: extractPeer(msg), - ParentPeer: extractParentPeer(msg), - GuildID: inboundMetadata(msg, metadataKeyGuildID), - TeamID: inboundMetadata(msg, metadataKeyTeamID), - }) - - agent, ok := al.registry.GetAgent(route.AgentID) - if !ok { - agent = al.registry.GetDefaultAgent() - } - if agent == nil { - return routing.ResolvedRoute{}, nil, fmt.Errorf("no agent available for route (agent_id=%s)", route.AgentID) - } - - return route, agent, nil -} - -func resolveScopeKey(route routing.ResolvedRoute, msgSessionKey string) string { - if msgSessionKey != "" && strings.HasPrefix(msgSessionKey, sessionKeyAgentPrefix) { - return msgSessionKey - } - return route.SessionKey -} - -func (al *AgentLoop) processSystemMessage( - ctx context.Context, - msg bus.InboundMessage, -) (string, error) { - if msg.Channel != "system" { - return "", fmt.Errorf( - "processSystemMessage called with non-system message channel: %s", - msg.Channel, - ) - } - - logger.InfoCF("agent", "Processing system message", - map[string]any{ - "sender_id": msg.SenderID, - "chat_id": msg.ChatID, - }) - - // Parse origin channel from chat_id (format: "channel:chat_id") - var originChannel, originChatID string - if idx := strings.Index(msg.ChatID, ":"); idx > 0 { - originChannel = msg.ChatID[:idx] - originChatID = msg.ChatID[idx+1:] - } else { - originChannel = "cli" - originChatID = msg.ChatID - } - - // Extract subagent result from message content - // Format: "Task 'label' completed.\n\nResult:\n" - content := msg.Content - if idx := strings.Index(content, "Result:\n"); idx >= 0 { - content = content[idx+8:] // Extract just the result part - } - - // Skip internal channels - only log, don't send to user - if constants.IsInternalChannel(originChannel) { - logger.InfoCF("agent", "Subagent completed (internal channel)", - map[string]any{ - "sender_id": msg.SenderID, - "content_len": len(content), - "channel": originChannel, - }) - return "", nil - } - - // Use default agent for system messages - agent := al.registry.GetDefaultAgent() - if agent == nil { - return "", fmt.Errorf("no default agent for system message") - } - - // Use the origin session for context - sessionKey := routing.BuildAgentMainSessionKey(agent.ID) - - return al.runAgentLoop(ctx, agent, processOptions{ - SessionKey: sessionKey, - Channel: originChannel, - ChatID: originChatID, - UserMessage: fmt.Sprintf("[System: %s] %s", msg.SenderID, msg.Content), - DefaultResponse: "Background task completed.", - EnableSummary: false, - SendResponse: true, - }) -} - -// runAgentLoop is the core message processing logic. -func (al *AgentLoop) runAgentLoop( - ctx context.Context, - agent *AgentInstance, - opts processOptions, -) (string, error) { - // 0. Record last channel for heartbeat notifications (skip internal channels and cli) - if opts.Channel != "" && opts.ChatID != "" { - if !constants.IsInternalChannel(opts.Channel) { - channelKey := fmt.Sprintf("%s:%s", opts.Channel, opts.ChatID) - if err := al.RecordLastChannel(channelKey); err != nil { - logger.WarnCF( - "agent", - "Failed to record last channel", - map[string]any{"error": err.Error()}, - ) - } - } - } - - // 1. Build messages (skip history for heartbeat) - var history []providers.Message - var summary string - if !opts.NoHistory { - history = agent.Sessions.GetHistory(opts.SessionKey) - summary = agent.Sessions.GetSummary(opts.SessionKey) - } - messages := agent.ContextBuilder.BuildMessages( - history, - summary, - opts.UserMessage, - opts.Media, - opts.Channel, - opts.ChatID, - ) - - // Resolve media:// refs to base64 data URLs (streaming) - maxMediaSize := al.cfg.Agents.Defaults.GetMaxMediaSize() - messages = resolveMediaRefs(messages, al.mediaStore, maxMediaSize) - - // 2. Save user message to session - agent.Sessions.AddMessage(opts.SessionKey, "user", opts.UserMessage) - - // 3. Run LLM iteration loop - finalContent, iteration, err := al.runLLMIteration(ctx, agent, messages, opts) - if err != nil { - return "", err - } - - // If last tool had ForUser content and we already sent it, we might not need to send final response - // This is controlled by the tool's Silent flag and ForUser content - - // 4. Handle empty response - if finalContent == "" { - finalContent = opts.DefaultResponse - } - - // 5. Save final assistant message to session - agent.Sessions.AddMessage(opts.SessionKey, "assistant", finalContent) - agent.Sessions.Save(opts.SessionKey) - - // 6. Optional: summarization - if opts.EnableSummary { - al.maybeSummarize(agent, opts.SessionKey, opts.Channel, opts.ChatID) - } - - // 7. Optional: send response via bus - if opts.SendResponse { - al.bus.PublishOutbound(ctx, bus.OutboundMessage{ - Channel: opts.Channel, - ChatID: opts.ChatID, - Content: finalContent, - }) - } - - // 8. Log response - responsePreview := utils.Truncate(finalContent, 120) - logger.InfoCF("agent", fmt.Sprintf("Response: %s", responsePreview), - map[string]any{ - "agent_id": agent.ID, - "session_key": opts.SessionKey, - "iterations": iteration, - "final_length": len(finalContent), - }) - - return finalContent, nil -} - -func (al *AgentLoop) targetReasoningChannelID(channelName string) (chatID string) { - if al.channelManager == nil { - return "" - } - if ch, ok := al.channelManager.GetChannel(channelName); ok { - return ch.ReasoningChannelID() - } - return "" -} - -func (al *AgentLoop) handleReasoning( - ctx context.Context, - reasoningContent, channelName, channelID string, -) { - if reasoningContent == "" || channelName == "" || channelID == "" { - return - } - - // Check context cancellation before attempting to publish, - // since PublishOutbound's select may race between send and ctx.Done(). - if ctx.Err() != nil { - return - } - - // Use a short timeout so the goroutine does not block indefinitely when - // the outbound bus is full. Reasoning output is best-effort; dropping it - // is acceptable to avoid goroutine accumulation. - pubCtx, pubCancel := context.WithTimeout(ctx, 5*time.Second) - defer pubCancel() - - if err := al.bus.PublishOutbound(pubCtx, bus.OutboundMessage{ - Channel: channelName, - ChatID: channelID, - Content: reasoningContent, - }); err != nil { - // Treat context.DeadlineExceeded / context.Canceled as expected - // (bus full under load, or parent canceled). Check the error - // itself rather than ctx.Err(), because pubCtx may time out - // (5 s) while the parent ctx is still active. - // Also treat ErrBusClosed as expected — it occurs during normal - // shutdown when the bus is closed before all goroutines finish. - if errors.Is(err, context.DeadlineExceeded) || errors.Is(err, context.Canceled) || - errors.Is(err, bus.ErrBusClosed) { - logger.DebugCF("agent", "Reasoning publish skipped (timeout/cancel)", map[string]any{ - "channel": channelName, - "error": err.Error(), - }) - } else { - logger.WarnCF("agent", "Failed to publish reasoning (best-effort)", map[string]any{ - "channel": channelName, - "error": err.Error(), - }) - } - } -} - -// runLLMIteration executes the LLM call loop with tool handling. -func (al *AgentLoop) runLLMIteration( - ctx context.Context, - agent *AgentInstance, - messages []providers.Message, - opts processOptions, -) (string, int, error) { - iteration := 0 - var finalContent string - - // Determine effective model tier for this conversation turn. - // selectCandidates evaluates routing once and the decision is sticky for - // all tool-follow-up iterations within the same turn so that a multi-step - // tool chain doesn't switch models mid-way through. - activeCandidates, activeModel := al.selectCandidates(agent, opts.UserMessage, messages) - - for iteration < agent.MaxIterations { - iteration++ - - logger.DebugCF("agent", "LLM iteration", - map[string]any{ - "agent_id": agent.ID, - "iteration": iteration, - "max": agent.MaxIterations, - }) - - // Build tool definitions - providerToolDefs := agent.Tools.ToProviderDefs() - - // Log LLM request details - logger.DebugCF("agent", "LLM request", - map[string]any{ - "agent_id": agent.ID, - "iteration": iteration, - "model": activeModel, - "messages_count": len(messages), - "tools_count": len(providerToolDefs), - "max_tokens": agent.MaxTokens, - "temperature": agent.Temperature, - "system_prompt_len": len(messages[0].Content), - }) - - // Log full messages (detailed) - logger.DebugCF("agent", "Full LLM request", - map[string]any{ - "iteration": iteration, - "messages_json": formatMessagesForLog(messages), - "tools_json": formatToolsForLog(providerToolDefs), - }) - - // Call LLM with fallback chain and retry logic - response, err := al.executeLLMWithRetry( - ctx, agent, opts, &messages, - providerToolDefs, activeCandidates, - activeModel, iteration, - ) - if err != nil { - return "", iteration, err - } - go al.handleReasoning( - ctx, - response.Reasoning, - opts.Channel, - al.targetReasoningChannelID(opts.Channel), - ) - - logger.DebugCF("agent", "LLM response", - map[string]any{ - "agent_id": agent.ID, - "iteration": iteration, - "content_chars": len(response.Content), - "tool_calls": len(response.ToolCalls), - "reasoning": response.Reasoning, - "target_channel": al.targetReasoningChannelID(opts.Channel), - "channel": opts.Channel, - }) - // Check if no tool calls - then check reasoning content if any - if len(response.ToolCalls) == 0 { - finalContent = response.Content - if finalContent == "" && response.ReasoningContent != "" { - finalContent = response.ReasoningContent - } - logger.InfoCF("agent", "LLM response without tool calls (direct answer)", - map[string]any{ - "agent_id": agent.ID, - "iteration": iteration, - "content_chars": len(finalContent), - }) - break - } - - normalizedToolCalls := make([]providers.ToolCall, 0, len(response.ToolCalls)) - for _, tc := range response.ToolCalls { - normalizedToolCalls = append(normalizedToolCalls, providers.NormalizeToolCall(tc)) - } - - // Log tool calls - toolNames := make([]string, 0, len(normalizedToolCalls)) - for _, tc := range normalizedToolCalls { - toolNames = append(toolNames, tc.Name) - } - logger.InfoCF("agent", "LLM requested tool calls", - map[string]any{ - "agent_id": agent.ID, - "tools": toolNames, - "count": len(normalizedToolCalls), - "iteration": iteration, - }) - - // Build assistant message with tool calls - assistantMsg := providers.Message{ - Role: "assistant", - Content: response.Content, - ReasoningContent: response.ReasoningContent, - } - for _, tc := range normalizedToolCalls { - argumentsJSON, _ := json.Marshal(tc.Arguments) - // Copy ExtraContent to ensure thought_signature is persisted for Gemini 3 - extraContent := tc.ExtraContent - thoughtSignature := "" - if tc.Function != nil { - thoughtSignature = tc.Function.ThoughtSignature - } - - assistantMsg.ToolCalls = append(assistantMsg.ToolCalls, providers.ToolCall{ - ID: tc.ID, - Type: "function", - Name: tc.Name, - Function: &providers.FunctionCall{ - Name: tc.Name, - Arguments: string(argumentsJSON), - ThoughtSignature: thoughtSignature, - }, - ExtraContent: extraContent, - ThoughtSignature: thoughtSignature, - }) - } - messages = append(messages, assistantMsg) - - // Save assistant message with tool calls to session - agent.Sessions.AddFullMessage(opts.SessionKey, assistantMsg) - - // Execute tool calls in parallel - agentResults := al.executeToolBatch(ctx, agent, opts, normalizedToolCalls, iteration) - - // Process results in original order (send to user, save to session) - for _, r := range agentResults { - // Send ForUser content to user immediately if not Silent - if !r.result.Silent && r.result.ForUser != "" && opts.SendResponse { - al.bus.PublishOutbound(ctx, bus.OutboundMessage{ - Channel: opts.Channel, - ChatID: opts.ChatID, - Content: r.result.ForUser, - }) - logger.DebugCF("agent", "Sent tool result to user", - map[string]any{ - "tool": r.tc.Name, - "content_len": len(r.result.ForUser), - }) - } - - // If tool returned media refs, publish them as outbound media - if len(r.result.Media) > 0 { - parts := make([]bus.MediaPart, 0, len(r.result.Media)) - for _, ref := range r.result.Media { - part := bus.MediaPart{Ref: ref} - if al.mediaStore != nil { - if _, meta, err := al.mediaStore.ResolveWithMeta(ref); err == nil { - part.Filename = meta.Filename - part.ContentType = meta.ContentType - part.Type = inferMediaType(meta.Filename, meta.ContentType) - } - } - parts = append(parts, part) - } - al.bus.PublishOutboundMedia(ctx, bus.OutboundMediaMessage{ - Channel: opts.Channel, - ChatID: opts.ChatID, - Parts: parts, - }) - } - - // Determine content for LLM based on tool result - contentForLLM := r.result.ForLLM - if contentForLLM == "" && r.result.Err != nil { - contentForLLM = r.result.Err.Error() - } - - toolResultMsg := providers.Message{ - Role: "tool", - Content: contentForLLM, - ToolCallID: r.tc.ID, - } - messages = append(messages, toolResultMsg) - - // Save tool result message to session - agent.Sessions.AddFullMessage(opts.SessionKey, toolResultMsg) - } - - // Tick down TTL of discovered tools after processing tool results. - // Only reached when tool calls were made (the loop continues); - // the break on no-tool-call responses skips this. - // NOTE: This is safe because processMessage is sequential per agent. - // If per-agent concurrency is added, TTL consistency between - // ToProviderDefs and Get must be re-evaluated. - agent.Tools.TickTTL() - logger.DebugCF("agent", "TTL tick after tool execution", map[string]any{ - "agent_id": agent.ID, "iteration": iteration, - }) - } - - return finalContent, iteration, nil -} - -// selectCandidates returns the model candidates and resolved model name to use -// for a conversation turn. When model routing is configured and the incoming -// message scores below the complexity threshold, it returns the light model -// candidates instead of the primary ones. -// -// The returned (candidates, model) pair is used for all LLM calls within one -// turn — tool follow-up iterations use the same tier as the initial call so -// that a multi-step tool chain doesn't switch models mid-way. -func (al *AgentLoop) selectCandidates( - agent *AgentInstance, - userMsg string, - history []providers.Message, -) (candidates []providers.FallbackCandidate, model string) { - if agent.Router == nil || len(agent.LightCandidates) == 0 { - return agent.Candidates, agent.Model - } - - _, usedLight, score := agent.Router.SelectModel(userMsg, history, agent.Model) - if !usedLight { - logger.DebugCF("agent", "Model routing: primary model selected", - map[string]any{ - "agent_id": agent.ID, - "score": score, - "threshold": agent.Router.Threshold(), - }) - return agent.Candidates, agent.Model - } - - logger.InfoCF("agent", "Model routing: light model selected", - map[string]any{ - "agent_id": agent.ID, - "light_model": agent.Router.LightModel(), - "score": score, - "threshold": agent.Router.Threshold(), - }) - return agent.LightCandidates, agent.Router.LightModel() -} - -// maybeSummarize triggers summarization if the session history exceeds thresholds. -func (al *AgentLoop) maybeSummarize(agent *AgentInstance, sessionKey, channel, chatID string) { - newHistory := agent.Sessions.GetHistory(sessionKey) - tokenEstimate := al.estimateTokens(newHistory) - threshold := agent.ContextWindow * agent.SummarizeTokenPercent / 100 - - if len(newHistory) > agent.SummarizeMessageThreshold || tokenEstimate > threshold { - summarizeKey := agent.ID + ":" + sessionKey - if _, loading := al.summarizing.LoadOrStore(summarizeKey, true); !loading { - go func() { - defer al.summarizing.Delete(summarizeKey) - logger.Debug("Memory threshold reached. Optimizing conversation history...") - al.summarizeSession(agent, sessionKey) - }() - } - } -} - -// forceCompression aggressively reduces context when the limit is hit. -// It drops the oldest 50% of messages (keeping system prompt and last user message). -func (al *AgentLoop) forceCompression(agent *AgentInstance, sessionKey string) { - history := agent.Sessions.GetHistory(sessionKey) - if len(history) <= 4 { - return - } - - // Keep system prompt (usually [0]) and the very last message (user's trigger) - // We want to drop the oldest half of the *conversation* - // Assuming [0] is system, [1:] is conversation - conversation := history[1 : len(history)-1] - if len(conversation) == 0 { - return - } - - // Helper to find the mid-point of the conversation - mid := len(conversation) / 2 - - // New history structure: - // 1. System Prompt (with compression note appended) - // 2. Second half of conversation - // 3. Last message - - droppedCount := mid - keptConversation := conversation[mid:] - - newHistory := make([]providers.Message, 0, 1+len(keptConversation)+1) - - // Append compression note to the original system prompt instead of adding a new system message - // This avoids having two consecutive system messages which some APIs (like Zhipu) reject - compressionNote := fmt.Sprintf( - "\n\n[System Note: Emergency compression dropped %d oldest messages due to context limit]", - droppedCount, - ) - enhancedSystemPrompt := history[0] - enhancedSystemPrompt.Content = enhancedSystemPrompt.Content + compressionNote - newHistory = append(newHistory, enhancedSystemPrompt) - - newHistory = append(newHistory, keptConversation...) - newHistory = append(newHistory, history[len(history)-1]) // Last message - - // Update session - agent.Sessions.SetHistory(sessionKey, newHistory) - agent.Sessions.Save(sessionKey) - - logger.WarnCF("agent", "Forced compression executed", map[string]any{ - "session_key": sessionKey, - "dropped_msgs": droppedCount, - "new_count": len(newHistory), - }) -} - -// GetStartupInfo returns information about loaded tools and skills for logging. -func (al *AgentLoop) GetStartupInfo() map[string]any { - info := make(map[string]any) - - agent := al.registry.GetDefaultAgent() - if agent == nil { - return info - } - - // Tools info - toolsList := agent.Tools.List() - info["tools"] = map[string]any{ - "count": len(toolsList), - "names": toolsList, - } - - // Skills info - info["skills"] = agent.ContextBuilder.GetSkillsInfo() - - // Agents info - info["agents"] = map[string]any{ - "count": len(al.registry.ListAgentIDs()), - "ids": al.registry.ListAgentIDs(), - } - - return info -} - -// formatMessagesForLog formats messages for logging -func formatMessagesForLog(messages []providers.Message) string { - if len(messages) == 0 { - return "[]" - } - - var sb strings.Builder - sb.WriteString("[\n") - for i, msg := range messages { - fmt.Fprintf(&sb, " [%d] Role: %s\n", i, msg.Role) - if len(msg.ToolCalls) > 0 { - sb.WriteString(" ToolCalls:\n") - for _, tc := range msg.ToolCalls { - fmt.Fprintf(&sb, " - ID: %s, Type: %s, Name: %s\n", tc.ID, tc.Type, tc.Name) - if tc.Function != nil { - fmt.Fprintf( - &sb, - " Arguments: %s\n", - utils.Truncate(tc.Function.Arguments, 200), - ) - } - } - } - if msg.Content != "" { - content := utils.Truncate(msg.Content, 200) - fmt.Fprintf(&sb, " Content: %s\n", content) - } - if msg.ToolCallID != "" { - fmt.Fprintf(&sb, " ToolCallID: %s\n", msg.ToolCallID) - } - sb.WriteString("\n") - } - sb.WriteString("]") - return sb.String() -} - -// formatToolsForLog formats tool definitions for logging -func formatToolsForLog(toolDefs []providers.ToolDefinition) string { - if len(toolDefs) == 0 { - return "[]" - } - - var sb strings.Builder - sb.WriteString("[\n") - for i, tool := range toolDefs { - fmt.Fprintf(&sb, " [%d] Type: %s, Name: %s\n", i, tool.Type, tool.Function.Name) - fmt.Fprintf(&sb, " Description: %s\n", tool.Function.Description) - if len(tool.Function.Parameters) > 0 { - fmt.Fprintf( - &sb, - " Parameters: %s\n", - utils.Truncate(fmt.Sprintf("%v", tool.Function.Parameters), 200), - ) - } - } - sb.WriteString("]") - return sb.String() -} - -// summarizeSession summarizes the conversation history for a session. -func (al *AgentLoop) summarizeSession(agent *AgentInstance, sessionKey string) { - ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second) - defer cancel() - - history := agent.Sessions.GetHistory(sessionKey) - summary := agent.Sessions.GetSummary(sessionKey) - - // Keep last 4 messages for continuity - if len(history) <= 4 { - return - } - - toSummarize := history[:len(history)-4] - - // Oversized Message Guard - maxMessageTokens := agent.ContextWindow / 2 - validMessages := make([]providers.Message, 0) - omitted := false - - for _, m := range toSummarize { - if m.Role != "user" && m.Role != "assistant" { - continue - } - msgTokens := len(m.Content) / 2 - if msgTokens > maxMessageTokens { - omitted = true - continue - } - validMessages = append(validMessages, m) - } - - if len(validMessages) == 0 { - return - } - - const ( - maxSummarizationMessages = 10 - llmMaxRetries = 3 - llmTemperature = 0.3 - fallbackMaxContentLength = 200 - ) - - // Multi-Part Summarization - var finalSummary string - if len(validMessages) > maxSummarizationMessages { - mid := len(validMessages) / 2 - - mid = al.findNearestUserMessage(validMessages, mid) - - part1 := validMessages[:mid] - part2 := validMessages[mid:] - - s1, _ := al.summarizeBatch(ctx, agent, part1, "") - s2, _ := al.summarizeBatch(ctx, agent, part2, "") - - mergePrompt := fmt.Sprintf( - "Merge these two conversation summaries into one cohesive summary:\n\n1: %s\n\n2: %s", - s1, - s2, - ) - - resp, err := al.retryLLMCall(ctx, agent, mergePrompt, llmMaxRetries) - if err == nil && resp.Content != "" { - finalSummary = resp.Content - } else { - finalSummary = s1 + " " + s2 - } - } else { - finalSummary, _ = al.summarizeBatch(ctx, agent, validMessages, summary) - } - - if omitted && finalSummary != "" { - finalSummary += "\n[Note: Some oversized messages were omitted from this summary for efficiency.]" - } - - if finalSummary != "" { - agent.Sessions.SetSummary(sessionKey, finalSummary) - agent.Sessions.TruncateHistory(sessionKey, 4) - agent.Sessions.Save(sessionKey) - } -} - -// findNearestUserMessage finds the nearest user message to the given index. -// It searches backward first, then forward if no user message is found. -func (al *AgentLoop) findNearestUserMessage(messages []providers.Message, mid int) int { - originalMid := mid - - for mid > 0 && messages[mid].Role != "user" { - mid-- - } - - if messages[mid].Role == "user" { - return mid - } - - mid = originalMid - for mid < len(messages) && messages[mid].Role != "user" { - mid++ - } - - if mid < len(messages) { - return mid - } - - return originalMid -} - -// retryLLMCall calls the LLM with retry logic. -func (al *AgentLoop) retryLLMCall( - ctx context.Context, - agent *AgentInstance, - prompt string, - maxRetries int, -) (*providers.LLMResponse, error) { - const ( - llmTemperature = 0.3 - ) - - var resp *providers.LLMResponse - var err error - - for attempt := 0; attempt < maxRetries; attempt++ { - resp, err = agent.Provider.Chat( - ctx, - []providers.Message{{Role: "user", Content: prompt}}, - nil, - agent.Model, - map[string]any{ - "max_tokens": agent.MaxTokens, - "temperature": llmTemperature, - "prompt_cache_key": agent.ID, - }, - ) - if err == nil && resp != nil && resp.Content != "" { - return resp, nil - } - if attempt < maxRetries-1 { - time.Sleep(time.Duration(attempt+1) * 100 * time.Millisecond) - } - } - - return resp, err -} - -// summarizeBatch summarizes a batch of messages. -func (al *AgentLoop) summarizeBatch( - ctx context.Context, - agent *AgentInstance, - batch []providers.Message, - existingSummary string, -) (string, error) { - const ( - llmMaxRetries = 3 - llmTemperature = 0.3 - fallbackMinContentLength = 200 - fallbackMaxContentPercent = 10 - ) - - var sb strings.Builder - sb.WriteString( - "Provide a concise summary of this conversation segment, preserving core context and key points.\n", - ) - if existingSummary != "" { - sb.WriteString("Existing context: ") - sb.WriteString(existingSummary) - sb.WriteString("\n") - } - sb.WriteString("\nCONVERSATION:\n") - for _, m := range batch { - fmt.Fprintf(&sb, "%s: %s\n", m.Role, m.Content) - } - prompt := sb.String() - - response, err := al.retryLLMCall(ctx, agent, prompt, llmMaxRetries) - if err == nil && response.Content != "" { - return strings.TrimSpace(response.Content), nil - } - - var fallback strings.Builder - fallback.WriteString("Conversation summary: ") - for i, m := range batch { - if i > 0 { - fallback.WriteString(" | ") - } - content := strings.TrimSpace(m.Content) - runes := []rune(content) - if len(runes) == 0 { - fallback.WriteString(fmt.Sprintf("%s: ", m.Role)) - continue - } - - keepLength := len(runes) * fallbackMaxContentPercent / 100 - if keepLength < fallbackMinContentLength { - keepLength = fallbackMinContentLength - } - - if keepLength > len(runes) { - keepLength = len(runes) - } - - content = string(runes[:keepLength]) - if keepLength < len(runes) { - content += "..." - } - fallback.WriteString(fmt.Sprintf("%s: %s", m.Role, content)) - } - return fallback.String(), nil -} - -// estimateTokens estimates the number of tokens in a message list. -// Uses a safe heuristic of 2.5 characters per token to account for CJK and other -// overheads better than the previous 3 chars/token. -func (al *AgentLoop) estimateTokens(messages []providers.Message) int { - totalChars := 0 - for _, m := range messages { - totalChars += utf8.RuneCountInString(m.Content) - } - // 2.5 chars per token = totalChars * 2 / 5 - return totalChars * 2 / 5 -} - -func (al *AgentLoop) handleCommand( - ctx context.Context, - msg bus.InboundMessage, - agent *AgentInstance, - opts *processOptions, -) (string, bool) { - if !commands.HasCommandPrefix(msg.Content) { - return "", false - } - - if al.cmdRegistry == nil { - return "", false - } - - rt := al.buildCommandsRuntime(agent, opts) - executor := commands.NewExecutor(al.cmdRegistry, rt) - - var commandReply string - result := executor.Execute(ctx, commands.Request{ - Channel: msg.Channel, - ChatID: msg.ChatID, - SenderID: msg.SenderID, - Text: msg.Content, - Reply: func(text string) error { - commandReply = text - return nil - }, - }) - - switch result.Outcome { - case commands.OutcomeHandled: - if result.Err != nil { - return mapCommandError(result), true - } - if commandReply != "" { - return commandReply, true - } - return "", true - default: // OutcomePassthrough — let the message fall through to LLM - return "", false - } -} - -func (al *AgentLoop) buildCommandsRuntime(agent *AgentInstance, opts *processOptions) *commands.Runtime { - rt := &commands.Runtime{ - Config: al.cfg, - ListAgentIDs: al.registry.ListAgentIDs, - ListDefinitions: al.cmdRegistry.Definitions, - GetEnabledChannels: func() []string { - if al.channelManager == nil { - return nil - } - return al.channelManager.GetEnabledChannels() - }, - SwitchChannel: func(value string) error { - if al.channelManager == nil { - return fmt.Errorf("channel manager not initialized") - } - if _, exists := al.channelManager.GetChannel(value); !exists && value != "cli" { - return fmt.Errorf("channel '%s' not found or not enabled", value) - } - return nil - }, - } - if agent != nil { - rt.GetModelInfo = func() (string, string) { - return agent.Model, al.cfg.Agents.Defaults.Provider - } - rt.SwitchModel = func(value string) (string, error) { - oldModel := agent.Model - agent.Model = value - return oldModel, nil - } - - rt.ClearHistory = func() error { - if opts == nil { - return fmt.Errorf("process options not available") - } - if agent.Sessions == nil { - return fmt.Errorf("sessions not initialized for agent") - } - - agent.Sessions.SetHistory(opts.SessionKey, make([]providers.Message, 0)) - agent.Sessions.SetSummary(opts.SessionKey, "") - agent.Sessions.Save(opts.SessionKey) - return nil - } - } - return rt -} - -func mapCommandError(result commands.ExecuteResult) string { - if result.Command == "" { - return fmt.Sprintf("Failed to execute command: %v", result.Err) - } - return fmt.Sprintf("Failed to execute /%s: %v", result.Command, result.Err) -} - -// extractPeer extracts the routing peer from the inbound message's structured Peer field. -func extractPeer(msg bus.InboundMessage) *routing.RoutePeer { - if msg.Peer.Kind == "" { - return nil - } - peerID := msg.Peer.ID - if peerID == "" { - if msg.Peer.Kind == "direct" { - peerID = msg.SenderID - } else { - peerID = msg.ChatID - } - } - return &routing.RoutePeer{Kind: msg.Peer.Kind, ID: peerID} -} - -func inboundMetadata(msg bus.InboundMessage, key string) string { - if msg.Metadata == nil { - return "" - } - return msg.Metadata[key] -} - -// extractParentPeer extracts the parent peer (reply-to) from inbound message metadata. -func extractParentPeer(msg bus.InboundMessage) *routing.RoutePeer { - parentKind := inboundMetadata(msg, metadataKeyParentPeerKind) - parentID := inboundMetadata(msg, metadataKeyParentPeerID) - if parentKind == "" || parentID == "" { - return nil - } - return &routing.RoutePeer{Kind: parentKind, ID: parentID} -} diff --git a/pkg/agent/loop_audio.go b/pkg/agent/loop_audio.go new file mode 100644 index 000000000..fb4f0ca86 --- /dev/null +++ b/pkg/agent/loop_audio.go @@ -0,0 +1,114 @@ +// PicoClaw - Ultra-lightweight personal AI agent +// Inspired by and based on nanobot: https://github.com/HKUDS/nanobot +// License: MIT +// +// Copyright (c) 2026 PicoClaw contributors + +package agent + +import ( + "context" + "regexp" + "strings" + + "jane/pkg/bus" + "jane/pkg/logger" + "jane/pkg/utils" +) + +var audioAnnotationRe = regexp.MustCompile(`\[(voice|audio)(?::[^\]]*)?\]`) + +// transcribeAudioInMessage resolves audio media refs, transcribes them, and +// replaces audio annotations in msg.Content with the transcribed text. +// Returns the (possibly modified) message and true if audio was transcribed. +func (al *AgentLoop) transcribeAudioInMessage(ctx context.Context, msg bus.InboundMessage) (bus.InboundMessage, bool) { + if al.transcriber == nil || al.mediaStore == nil || len(msg.Media) == 0 { + return msg, false + } + + // Transcribe each audio media ref in order. + var transcriptions []string + for _, ref := range msg.Media { + path, meta, err := al.mediaStore.ResolveWithMeta(ref) + if err != nil { + logger.WarnCF("voice", "Failed to resolve media ref", map[string]any{"ref": ref, "error": err}) + continue + } + if !utils.IsAudioFile(meta.Filename, meta.ContentType) { + continue + } + result, err := al.transcriber.Transcribe(ctx, path) + if err != nil { + logger.WarnCF("voice", "Transcription failed", map[string]any{"ref": ref, "error": err}) + transcriptions = append(transcriptions, "") + continue + } + transcriptions = append(transcriptions, result.Text) + } + + if len(transcriptions) == 0 { + return msg, false + } + + al.sendTranscriptionFeedback(ctx, msg.Channel, msg.ChatID, msg.MessageID, transcriptions) + + // Replace audio annotations sequentially with transcriptions. + idx := 0 + newContent := audioAnnotationRe.ReplaceAllStringFunc(msg.Content, func(match string) string { + if idx >= len(transcriptions) { + return match + } + text := transcriptions[idx] + idx++ + return "[voice: " + text + "]" + }) + + // Append any remaining transcriptions not matched by an annotation. + for ; idx < len(transcriptions); idx++ { + newContent += "\n[voice: " + transcriptions[idx] + "]" + } + + msg.Content = newContent + return msg, true +} + +// sendTranscriptionFeedback sends feedback to the user with the result of +// audio transcription if the option is enabled. It uses Manager.SendMessage +// which executes synchronously (rate limiting, splitting, retry) so that +// ordering with the subsequent placeholder is guaranteed. +func (al *AgentLoop) sendTranscriptionFeedback( + ctx context.Context, + channel, chatID, messageID string, + validTexts []string, +) { + if !al.cfg.Voice.EchoTranscription { + return + } + if al.channelManager == nil { + return + } + + var nonEmpty []string + for _, t := range validTexts { + if t != "" { + nonEmpty = append(nonEmpty, t) + } + } + + var feedbackMsg string + if len(nonEmpty) > 0 { + feedbackMsg = "Transcript: " + strings.Join(nonEmpty, "\n") + } else { + feedbackMsg = "No voice detected in the audio" + } + + err := al.channelManager.SendMessage(ctx, bus.OutboundMessage{ + Channel: channel, + ChatID: chatID, + Content: feedbackMsg, + ReplyToMessageID: messageID, + }) + if err != nil { + logger.WarnCF("voice", "Failed to send transcription feedback", map[string]any{"error": err.Error()}) + } +} diff --git a/pkg/agent/loop_command.go b/pkg/agent/loop_command.go new file mode 100644 index 000000000..f1a1fb881 --- /dev/null +++ b/pkg/agent/loop_command.go @@ -0,0 +1,114 @@ +// PicoClaw - Ultra-lightweight personal AI agent +// Inspired by and based on nanobot: https://github.com/HKUDS/nanobot +// License: MIT +// +// Copyright (c) 2026 PicoClaw contributors + +package agent + +import ( + "context" + "fmt" + + "jane/pkg/bus" + "jane/pkg/commands" + "jane/pkg/providers" +) + +func (al *AgentLoop) handleCommand( + ctx context.Context, + msg bus.InboundMessage, + agent *AgentInstance, + opts *processOptions, +) (string, bool) { + if !commands.HasCommandPrefix(msg.Content) { + return "", false + } + + if al.cmdRegistry == nil { + return "", false + } + + rt := al.buildCommandsRuntime(agent, opts) + executor := commands.NewExecutor(al.cmdRegistry, rt) + + var commandReply string + result := executor.Execute(ctx, commands.Request{ + Channel: msg.Channel, + ChatID: msg.ChatID, + SenderID: msg.SenderID, + Text: msg.Content, + Reply: func(text string) error { + commandReply = text + return nil + }, + }) + + switch result.Outcome { + case commands.OutcomeHandled: + if result.Err != nil { + return mapCommandError(result), true + } + if commandReply != "" { + return commandReply, true + } + return "", true + default: // OutcomePassthrough — let the message fall through to LLM + return "", false + } +} + +func (al *AgentLoop) buildCommandsRuntime(agent *AgentInstance, opts *processOptions) *commands.Runtime { + rt := &commands.Runtime{ + Config: al.cfg, + ListAgentIDs: al.registry.ListAgentIDs, + ListDefinitions: al.cmdRegistry.Definitions, + GetEnabledChannels: func() []string { + if al.channelManager == nil { + return nil + } + return al.channelManager.GetEnabledChannels() + }, + SwitchChannel: func(value string) error { + if al.channelManager == nil { + return fmt.Errorf("channel manager not initialized") + } + if _, exists := al.channelManager.GetChannel(value); !exists && value != "cli" { + return fmt.Errorf("channel '%s' not found or not enabled", value) + } + return nil + }, + } + if agent != nil { + rt.GetModelInfo = func() (string, string) { + return agent.Model, al.cfg.Agents.Defaults.Provider + } + rt.SwitchModel = func(value string) (string, error) { + oldModel := agent.Model + agent.Model = value + return oldModel, nil + } + + rt.ClearHistory = func() error { + if opts == nil { + return fmt.Errorf("process options not available") + } + if agent.Sessions == nil { + return fmt.Errorf("sessions not initialized for agent") + } + + agent.Sessions.SetHistory(opts.SessionKey, make([]providers.Message, 0)) + agent.Sessions.SetSummary(opts.SessionKey, "") + agent.Sessions.Save(opts.SessionKey) + return nil + } + } + return rt +} + +func mapCommandError(result commands.ExecuteResult) string { + if result.Command == "" { + return fmt.Sprintf("Failed to execute command: %v", result.Err) + } + return fmt.Sprintf("Failed to execute /%s: %v", result.Command, result.Err) +} diff --git a/pkg/agent/loop_init.go b/pkg/agent/loop_init.go new file mode 100644 index 000000000..5cdce0c6d --- /dev/null +++ b/pkg/agent/loop_init.go @@ -0,0 +1,362 @@ +// PicoClaw - Ultra-lightweight personal AI agent +// Inspired by and based on nanobot: https://github.com/HKUDS/nanobot +// License: MIT +// +// Copyright (c) 2026 PicoClaw contributors + +package agent + +import ( + "context" + "fmt" + "sync" + "time" + + "jane/pkg/bus" + "jane/pkg/channels" + "jane/pkg/commands" + "jane/pkg/config" + "jane/pkg/logger" + "jane/pkg/media" + "jane/pkg/providers" + "jane/pkg/skills" + "jane/pkg/state" + "jane/pkg/tools" + "jane/pkg/voice" +) + +func NewAgentLoop( + cfg *config.Config, + msgBus *bus.MessageBus, + provider providers.LLMProvider, +) *AgentLoop { + registry := NewAgentRegistry(cfg, provider) + + // Register shared tools to all agents + registerSharedTools(cfg, msgBus, registry, provider) + + // Set up shared fallback chain + cooldown := providers.NewCooldownTracker() + fallbackChain := providers.NewFallbackChain(cooldown) + + // Create state manager using default agent's workspace for channel recording + defaultAgent := registry.GetDefaultAgent() + var stateManager *state.Manager + if defaultAgent != nil { + stateManager = state.NewManager(defaultAgent.Workspace) + } + + al := &AgentLoop{ + bus: msgBus, + cfg: cfg, + registry: registry, + state: stateManager, + summarizing: sync.Map{}, + fallback: fallbackChain, + cmdRegistry: commands.NewRegistry(commands.BuiltinDefinitions()), + } + + return al +} + +// registerSharedTools registers tools that are shared across all agents (web, message, spawn). +func registerSharedTools( + cfg *config.Config, + msgBus *bus.MessageBus, + registry *AgentRegistry, + provider providers.LLMProvider, +) { + for _, agentID := range registry.ListAgentIDs() { + agent, ok := registry.GetAgent(agentID) + if !ok { + continue + } + + if cfg.Tools.IsToolEnabled("web") { + searchTool, err := tools.NewWebSearchTool(tools.WebSearchToolOptions{ + BraveAPIKeys: config.MergeAPIKeys(cfg.Tools.Web.Brave.APIKey, cfg.Tools.Web.Brave.APIKeys), + BraveMaxResults: cfg.Tools.Web.Brave.MaxResults, + BraveEnabled: cfg.Tools.Web.Brave.Enabled, + TavilyAPIKeys: config.MergeAPIKeys(cfg.Tools.Web.Tavily.APIKey, cfg.Tools.Web.Tavily.APIKeys), + TavilyBaseURL: cfg.Tools.Web.Tavily.BaseURL, + TavilyMaxResults: cfg.Tools.Web.Tavily.MaxResults, + TavilyEnabled: cfg.Tools.Web.Tavily.Enabled, + DuckDuckGoMaxResults: cfg.Tools.Web.DuckDuckGo.MaxResults, + DuckDuckGoEnabled: cfg.Tools.Web.DuckDuckGo.Enabled, + PerplexityAPIKeys: config.MergeAPIKeys( + cfg.Tools.Web.Perplexity.APIKey, + cfg.Tools.Web.Perplexity.APIKeys, + ), + PerplexityMaxResults: cfg.Tools.Web.Perplexity.MaxResults, + PerplexityEnabled: cfg.Tools.Web.Perplexity.Enabled, + SearXNGBaseURL: cfg.Tools.Web.SearXNG.BaseURL, + SearXNGMaxResults: cfg.Tools.Web.SearXNG.MaxResults, + SearXNGEnabled: cfg.Tools.Web.SearXNG.Enabled, + GLMSearchAPIKey: cfg.Tools.Web.GLMSearch.APIKey, + GLMSearchBaseURL: cfg.Tools.Web.GLMSearch.BaseURL, + GLMSearchEngine: cfg.Tools.Web.GLMSearch.SearchEngine, + GLMSearchMaxResults: cfg.Tools.Web.GLMSearch.MaxResults, + GLMSearchEnabled: cfg.Tools.Web.GLMSearch.Enabled, + Proxy: cfg.Tools.Web.Proxy, + }) + if err != nil { + logger.ErrorCF("agent", "Failed to create web search tool", map[string]any{"error": err.Error()}) + } else if searchTool != nil { + agent.Tools.Register(searchTool) + } + } + if cfg.Tools.IsToolEnabled("web_fetch") { + fetchTool, err := tools.NewWebFetchToolWithProxy(50000, cfg.Tools.Web.Proxy, cfg.Tools.Web.FetchLimitBytes) + if err != nil { + logger.ErrorCF("agent", "Failed to create web fetch tool", map[string]any{"error": err.Error()}) + } else { + agent.Tools.Register(fetchTool) + } + } + + // Hardware tools (I2C, SPI) - Linux only, returns error on other platforms + if cfg.Tools.IsToolEnabled("i2c") { + agent.Tools.Register(tools.NewI2CTool()) + } + if cfg.Tools.IsToolEnabled("spi") { + agent.Tools.Register(tools.NewSPITool()) + } + + // Message tool + if cfg.Tools.IsToolEnabled("message") { + messageTool := tools.NewMessageTool() + messageTool.SetSendCallback(func(channel, chatID, content string) error { + pubCtx, pubCancel := context.WithTimeout(context.Background(), 5*time.Second) + defer pubCancel() + return msgBus.PublishOutbound(pubCtx, bus.OutboundMessage{ + Channel: channel, + ChatID: chatID, + Content: content, + }) + }) + agent.Tools.Register(messageTool) + } + + // Send file tool (outbound media via MediaStore — store injected later by SetMediaStore) + if cfg.Tools.IsToolEnabled("send_file") { + sendFileTool := tools.NewSendFileTool( + agent.Workspace, + cfg.Agents.Defaults.RestrictToWorkspace, + cfg.Agents.Defaults.GetMaxMediaSize(), + nil, + ) + agent.Tools.Register(sendFileTool) + } + + // Skill discovery and installation tools + skills_enabled := cfg.Tools.IsToolEnabled("skills") + find_skills_enable := cfg.Tools.IsToolEnabled("find_skills") + install_skills_enable := cfg.Tools.IsToolEnabled("install_skill") + if skills_enabled && (find_skills_enable || install_skills_enable) { + registryMgr := skills.NewRegistryManagerFromConfig(skills.RegistryConfig{ + MaxConcurrentSearches: cfg.Tools.Skills.MaxConcurrentSearches, + ClawHub: skills.ClawHubConfig(cfg.Tools.Skills.Registries.ClawHub), + }) + + if find_skills_enable { + searchCache := skills.NewSearchCache( + cfg.Tools.Skills.SearchCache.MaxSize, + time.Duration(cfg.Tools.Skills.SearchCache.TTLSeconds)*time.Second, + ) + agent.Tools.Register(tools.NewFindSkillsTool(registryMgr, searchCache)) + } + + if install_skills_enable { + agent.Tools.Register(tools.NewInstallSkillTool(registryMgr, agent.Workspace)) + } + } + + // 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) + 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) + } + } + } +} + +func (al *AgentLoop) Run(ctx context.Context) error { + al.running.Store(true) + if err := al.ensureMCPInitialized(ctx); err != nil { + return err + } + + for al.running.Load() { + select { + case <-ctx.Done(): + return nil + default: + msg, ok := al.bus.ConsumeInbound(ctx) + if !ok { + continue + } + + // Process message + func() { + // TODO: Re-enable media cleanup after inbound media is properly consumed by the agent. + // Currently disabled because files are deleted before the LLM can access their content. + // defer func() { + // if al.mediaStore != nil && msg.MediaScope != "" { + // if releaseErr := al.mediaStore.ReleaseAll(msg.MediaScope); releaseErr != nil { + // logger.WarnCF("agent", "Failed to release media", map[string]any{ + // "scope": msg.MediaScope, + // "error": releaseErr.Error(), + // }) + // } + // } + // }() + + response, err := al.processMessage(ctx, msg) + if err != nil { + response = fmt.Sprintf("Error processing message: %v", err) + } + + if response != "" { + // Check if the message tool already sent a response during this round. + // If so, skip publishing to avoid duplicate messages to the user. + // Use default agent's tools to check (message tool is shared). + alreadySent := false + defaultAgent := al.registry.GetDefaultAgent() + if defaultAgent != nil { + if tool, ok := defaultAgent.Tools.Get("message"); ok { + if mt, ok := tool.(*tools.MessageTool); ok { + alreadySent = mt.HasSentInRound() + } + } + } + + if !alreadySent { + al.bus.PublishOutbound(ctx, bus.OutboundMessage{ + Channel: msg.Channel, + ChatID: msg.ChatID, + Content: response, + }) + logger.InfoCF("agent", "Published outbound response", + map[string]any{ + "channel": msg.Channel, + "chat_id": msg.ChatID, + "content_len": len(response), + }) + } else { + logger.DebugCF( + "agent", + "Skipped outbound (message tool already sent)", + map[string]any{"channel": msg.Channel}, + ) + } + } + }() + } + } + + return nil +} + +func (al *AgentLoop) Stop() { + al.running.Store(false) +} + +// Close releases resources held by agent session stores. Call after Stop. +func (al *AgentLoop) Close() { + mcpManager := al.mcp.takeManager() + + if mcpManager != nil { + if err := mcpManager.Close(); err != nil { + logger.ErrorCF("agent", "Failed to close MCP manager", + map[string]any{ + "error": err.Error(), + }) + } + } + + al.registry.Close() +} + +func (al *AgentLoop) RegisterTool(tool tools.Tool) { + for _, agentID := range al.registry.ListAgentIDs() { + if agent, ok := al.registry.GetAgent(agentID); ok { + agent.Tools.Register(tool) + } + } +} + +func (al *AgentLoop) SetChannelManager(cm *channels.Manager) { + al.channelManager = cm +} + +// SetMediaStore injects a MediaStore for media lifecycle management. +func (al *AgentLoop) SetMediaStore(s media.MediaStore) { + al.mediaStore = s + + // Propagate store to send_file tools in all agents. + al.registry.ForEachTool("send_file", func(t tools.Tool) { + if sf, ok := t.(*tools.SendFileTool); ok { + sf.SetMediaStore(s) + } + }) +} + +// SetTranscriber injects a voice transcriber for agent-level audio transcription. +func (al *AgentLoop) SetTranscriber(t voice.Transcriber) { + al.transcriber = t +} + +// RecordLastChannel records the last active channel for this workspace. +// This uses the atomic state save mechanism to prevent data loss on crash. +func (al *AgentLoop) RecordLastChannel(channel string) error { + if al.state == nil { + return nil + } + return al.state.SetLastChannel(channel) +} + +// RecordLastChatID records the last active chat ID for this workspace. +// This uses the atomic state save mechanism to prevent data loss on crash. +func (al *AgentLoop) RecordLastChatID(chatID string) error { + if al.state == nil { + return nil + } + return al.state.SetLastChatID(chatID) +} + +// GetStartupInfo returns information about loaded tools and skills for logging. +func (al *AgentLoop) GetStartupInfo() map[string]any { + info := make(map[string]any) + + agent := al.registry.GetDefaultAgent() + if agent == nil { + return info + } + + // Tools info + toolsList := agent.Tools.List() + info["tools"] = map[string]any{ + "count": len(toolsList), + "names": toolsList, + } + + // Skills info + info["skills"] = agent.ContextBuilder.GetSkillsInfo() + + // Agents info + info["agents"] = map[string]any{ + "count": len(al.registry.ListAgentIDs()), + "ids": al.registry.ListAgentIDs(), + } + + return info +} diff --git a/pkg/agent/loop_llm.go b/pkg/agent/loop_llm.go new file mode 100644 index 000000000..f5615552b --- /dev/null +++ b/pkg/agent/loop_llm.go @@ -0,0 +1,417 @@ +// PicoClaw - Ultra-lightweight personal AI agent +// Inspired by and based on nanobot: https://github.com/HKUDS/nanobot +// License: MIT +// +// Copyright (c) 2026 PicoClaw contributors + +package agent + +import ( + "context" + "encoding/json" + "errors" + "fmt" + "time" + + "jane/pkg/bus" + "jane/pkg/constants" + "jane/pkg/logger" + "jane/pkg/providers" + "jane/pkg/utils" +) + +// runAgentLoop is the core message processing logic. +func (al *AgentLoop) runAgentLoop( + ctx context.Context, + agent *AgentInstance, + opts processOptions, +) (string, error) { + // 0. Record last channel for heartbeat notifications (skip internal channels and cli) + if opts.Channel != "" && opts.ChatID != "" { + if !constants.IsInternalChannel(opts.Channel) { + channelKey := fmt.Sprintf("%s:%s", opts.Channel, opts.ChatID) + if err := al.RecordLastChannel(channelKey); err != nil { + logger.WarnCF( + "agent", + "Failed to record last channel", + map[string]any{"error": err.Error()}, + ) + } + } + } + + // 1. Build messages (skip history for heartbeat) + var history []providers.Message + var summary string + if !opts.NoHistory { + history = agent.Sessions.GetHistory(opts.SessionKey) + summary = agent.Sessions.GetSummary(opts.SessionKey) + } + messages := agent.ContextBuilder.BuildMessages( + history, + summary, + opts.UserMessage, + opts.Media, + opts.Channel, + opts.ChatID, + ) + + // Resolve media:// refs to base64 data URLs (streaming) + maxMediaSize := al.cfg.Agents.Defaults.GetMaxMediaSize() + messages = resolveMediaRefs(messages, al.mediaStore, maxMediaSize) + + // 2. Save user message to session + agent.Sessions.AddMessage(opts.SessionKey, "user", opts.UserMessage) + + // 3. Run LLM iteration loop + finalContent, iteration, err := al.runLLMIteration(ctx, agent, messages, opts) + if err != nil { + return "", err + } + + // If last tool had ForUser content and we already sent it, we might not need to send final response + // This is controlled by the tool's Silent flag and ForUser content + + // 4. Handle empty response + if finalContent == "" { + finalContent = opts.DefaultResponse + } + + // 5. Save final assistant message to session + agent.Sessions.AddMessage(opts.SessionKey, "assistant", finalContent) + agent.Sessions.Save(opts.SessionKey) + + // 6. Optional: summarization + if opts.EnableSummary { + al.maybeSummarize(agent, opts.SessionKey, opts.Channel, opts.ChatID) + } + + // 7. Optional: send response via bus + if opts.SendResponse { + al.bus.PublishOutbound(ctx, bus.OutboundMessage{ + Channel: opts.Channel, + ChatID: opts.ChatID, + Content: finalContent, + }) + } + + // 8. Log response + responsePreview := utils.Truncate(finalContent, 120) + logger.InfoCF("agent", fmt.Sprintf("Response: %s", responsePreview), + map[string]any{ + "agent_id": agent.ID, + "session_key": opts.SessionKey, + "iterations": iteration, + "final_length": len(finalContent), + }) + + return finalContent, nil +} + +func (al *AgentLoop) targetReasoningChannelID(channelName string) (chatID string) { + if al.channelManager == nil { + return "" + } + if ch, ok := al.channelManager.GetChannel(channelName); ok { + return ch.ReasoningChannelID() + } + return "" +} + +func (al *AgentLoop) handleReasoning( + ctx context.Context, + reasoningContent, channelName, channelID string, +) { + if reasoningContent == "" || channelName == "" || channelID == "" { + return + } + + // Check context cancellation before attempting to publish, + // since PublishOutbound's select may race between send and ctx.Done(). + if ctx.Err() != nil { + return + } + + // Use a short timeout so the goroutine does not block indefinitely when + // the outbound bus is full. Reasoning output is best-effort; dropping it + // is acceptable to avoid goroutine accumulation. + pubCtx, pubCancel := context.WithTimeout(ctx, 5*time.Second) + defer pubCancel() + + if err := al.bus.PublishOutbound(pubCtx, bus.OutboundMessage{ + Channel: channelName, + ChatID: channelID, + Content: reasoningContent, + }); err != nil { + // Treat context.DeadlineExceeded / context.Canceled as expected + // (bus full under load, or parent canceled). Check the error + // itself rather than ctx.Err(), because pubCtx may time out + // (5 s) while the parent ctx is still active. + // Also treat ErrBusClosed as expected — it occurs during normal + // shutdown when the bus is closed before all goroutines finish. + if errors.Is(err, context.DeadlineExceeded) || errors.Is(err, context.Canceled) || + errors.Is(err, bus.ErrBusClosed) { + logger.DebugCF("agent", "Reasoning publish skipped (timeout/cancel)", map[string]any{ + "channel": channelName, + "error": err.Error(), + }) + } else { + logger.WarnCF("agent", "Failed to publish reasoning (best-effort)", map[string]any{ + "channel": channelName, + "error": err.Error(), + }) + } + } +} + +// runLLMIteration executes the LLM call loop with tool handling. +func (al *AgentLoop) runLLMIteration( + ctx context.Context, + agent *AgentInstance, + messages []providers.Message, + opts processOptions, +) (string, int, error) { + iteration := 0 + var finalContent string + + // Determine effective model tier for this conversation turn. + // selectCandidates evaluates routing once and the decision is sticky for + // all tool-follow-up iterations within the same turn so that a multi-step + // tool chain doesn't switch models mid-way through. + activeCandidates, activeModel := al.selectCandidates(agent, opts.UserMessage, messages) + + for iteration < agent.MaxIterations { + iteration++ + + logger.DebugCF("agent", "LLM iteration", + map[string]any{ + "agent_id": agent.ID, + "iteration": iteration, + "max": agent.MaxIterations, + }) + + // Build tool definitions + providerToolDefs := agent.Tools.ToProviderDefs() + + // Log LLM request details + logger.DebugCF("agent", "LLM request", + map[string]any{ + "agent_id": agent.ID, + "iteration": iteration, + "model": activeModel, + "messages_count": len(messages), + "tools_count": len(providerToolDefs), + "max_tokens": agent.MaxTokens, + "temperature": agent.Temperature, + "system_prompt_len": len(messages[0].Content), + }) + + // Log full messages (detailed) + logger.DebugCF("agent", "Full LLM request", + map[string]any{ + "iteration": iteration, + "messages_json": formatMessagesForLog(messages), + "tools_json": formatToolsForLog(providerToolDefs), + }) + + // Call LLM with fallback chain and retry logic + response, err := al.executeLLMWithRetry( + ctx, agent, opts, &messages, + providerToolDefs, activeCandidates, + activeModel, iteration, + ) + if err != nil { + return "", iteration, err + } + go al.handleReasoning( + ctx, + response.Reasoning, + opts.Channel, + al.targetReasoningChannelID(opts.Channel), + ) + + logger.DebugCF("agent", "LLM response", + map[string]any{ + "agent_id": agent.ID, + "iteration": iteration, + "content_chars": len(response.Content), + "tool_calls": len(response.ToolCalls), + "reasoning": response.Reasoning, + "target_channel": al.targetReasoningChannelID(opts.Channel), + "channel": opts.Channel, + }) + // Check if no tool calls - then check reasoning content if any + if len(response.ToolCalls) == 0 { + finalContent = response.Content + if finalContent == "" && response.ReasoningContent != "" { + finalContent = response.ReasoningContent + } + logger.InfoCF("agent", "LLM response without tool calls (direct answer)", + map[string]any{ + "agent_id": agent.ID, + "iteration": iteration, + "content_chars": len(finalContent), + }) + break + } + + normalizedToolCalls := make([]providers.ToolCall, 0, len(response.ToolCalls)) + for _, tc := range response.ToolCalls { + normalizedToolCalls = append(normalizedToolCalls, providers.NormalizeToolCall(tc)) + } + + // Log tool calls + toolNames := make([]string, 0, len(normalizedToolCalls)) + for _, tc := range normalizedToolCalls { + toolNames = append(toolNames, tc.Name) + } + logger.InfoCF("agent", "LLM requested tool calls", + map[string]any{ + "agent_id": agent.ID, + "tools": toolNames, + "count": len(normalizedToolCalls), + "iteration": iteration, + }) + + // Build assistant message with tool calls + assistantMsg := providers.Message{ + Role: "assistant", + Content: response.Content, + ReasoningContent: response.ReasoningContent, + } + for _, tc := range normalizedToolCalls { + argumentsJSON, _ := json.Marshal(tc.Arguments) + // Copy ExtraContent to ensure thought_signature is persisted for Gemini 3 + extraContent := tc.ExtraContent + thoughtSignature := "" + if tc.Function != nil { + thoughtSignature = tc.Function.ThoughtSignature + } + + assistantMsg.ToolCalls = append(assistantMsg.ToolCalls, providers.ToolCall{ + ID: tc.ID, + Type: "function", + Name: tc.Name, + Function: &providers.FunctionCall{ + Name: tc.Name, + Arguments: string(argumentsJSON), + ThoughtSignature: thoughtSignature, + }, + ExtraContent: extraContent, + ThoughtSignature: thoughtSignature, + }) + } + messages = append(messages, assistantMsg) + + // Save assistant message with tool calls to session + agent.Sessions.AddFullMessage(opts.SessionKey, assistantMsg) + + // Execute tool calls in parallel + agentResults := al.executeToolBatch(ctx, agent, opts, normalizedToolCalls, iteration) + + // Process results in original order (send to user, save to session) + for _, r := range agentResults { + // Send ForUser content to user immediately if not Silent + if !r.result.Silent && r.result.ForUser != "" && opts.SendResponse { + al.bus.PublishOutbound(ctx, bus.OutboundMessage{ + Channel: opts.Channel, + ChatID: opts.ChatID, + Content: r.result.ForUser, + }) + logger.DebugCF("agent", "Sent tool result to user", + map[string]any{ + "tool": r.tc.Name, + "content_len": len(r.result.ForUser), + }) + } + + // If tool returned media refs, publish them as outbound media + if len(r.result.Media) > 0 { + parts := make([]bus.MediaPart, 0, len(r.result.Media)) + for _, ref := range r.result.Media { + part := bus.MediaPart{Ref: ref} + if al.mediaStore != nil { + if _, meta, err := al.mediaStore.ResolveWithMeta(ref); err == nil { + part.Filename = meta.Filename + part.ContentType = meta.ContentType + part.Type = inferMediaType(meta.Filename, meta.ContentType) + } + } + parts = append(parts, part) + } + al.bus.PublishOutboundMedia(ctx, bus.OutboundMediaMessage{ + Channel: opts.Channel, + ChatID: opts.ChatID, + Parts: parts, + }) + } + + // Determine content for LLM based on tool result + contentForLLM := r.result.ForLLM + if contentForLLM == "" && r.result.Err != nil { + contentForLLM = r.result.Err.Error() + } + + toolResultMsg := providers.Message{ + Role: "tool", + Content: contentForLLM, + ToolCallID: r.tc.ID, + } + messages = append(messages, toolResultMsg) + + // Save tool result message to session + agent.Sessions.AddFullMessage(opts.SessionKey, toolResultMsg) + } + + // Tick down TTL of discovered tools after processing tool results. + // Only reached when tool calls were made (the loop continues); + // the break on no-tool-call responses skips this. + // NOTE: This is safe because processMessage is sequential per agent. + // If per-agent concurrency is added, TTL consistency between + // ToProviderDefs and Get must be re-evaluated. + agent.Tools.TickTTL() + logger.DebugCF("agent", "TTL tick after tool execution", map[string]any{ + "agent_id": agent.ID, "iteration": iteration, + }) + } + + return finalContent, iteration, nil +} + +// selectCandidates returns the model candidates and resolved model name to use +// for a conversation turn. When model routing is configured and the incoming +// message scores below the complexity threshold, it returns the light model +// candidates instead of the primary ones. +// +// The returned (candidates, model) pair is used for all LLM calls within one +// turn — tool follow-up iterations use the same tier as the initial call so +// that a multi-step tool chain doesn't switch models mid-way. +func (al *AgentLoop) selectCandidates( + agent *AgentInstance, + userMsg string, + history []providers.Message, +) (candidates []providers.FallbackCandidate, model string) { + if agent.Router == nil || len(agent.LightCandidates) == 0 { + return agent.Candidates, agent.Model + } + + _, usedLight, score := agent.Router.SelectModel(userMsg, history, agent.Model) + if !usedLight { + logger.DebugCF("agent", "Model routing: primary model selected", + map[string]any{ + "agent_id": agent.ID, + "score": score, + "threshold": agent.Router.Threshold(), + }) + return agent.Candidates, agent.Model + } + + logger.InfoCF("agent", "Model routing: light model selected", + map[string]any{ + "agent_id": agent.ID, + "light_model": agent.Router.LightModel(), + "score": score, + "threshold": agent.Router.Threshold(), + }) + return agent.LightCandidates, agent.Router.LightModel() +} diff --git a/pkg/agent/loop_medical.go b/pkg/agent/loop_medical.go new file mode 100644 index 000000000..befee126b --- /dev/null +++ b/pkg/agent/loop_medical.go @@ -0,0 +1,153 @@ +package agent + +import ( + "context" + "fmt" + "path/filepath" + "regexp" + "strings" + + "jane/pkg/bus" + "jane/pkg/logger" +) + +// The medical CoT state machine phases +const ( + PhaseExtraction = "extraction" + PhaseTemporalCorrelation = "temporal_correlation" + PhaseTheoryGeneration = "theory_generation" + PhaseVerification = "verification" + PhaseSafetyDisclaimers = "safety_disclaimers" +) + +// processMedicalRequest implements the medical persona CoT loop +func (al *AgentLoop) processMedicalRequest( + ctx context.Context, + agent *AgentInstance, + opts processOptions, +) (string, error) { + logger.InfoCF("medical", "Starting clinical CoT loop", map[string]any{ + "session_key": opts.SessionKey, + }) + + // Detect target patient from message + targetPatient := detectTargetPatient(opts.UserMessage) + if targetPatient == "" { + // If no specific patient is explicitly asked for, we ask the user for clarification. + msg := "Please specify the patient you are analyzing (e.g., 'Analyze patient John Doe')." + if opts.SendResponse { + al.bus.PublishOutbound(ctx, bus.OutboundMessage{ + Channel: opts.Channel, + ChatID: opts.ChatID, + Content: msg, + }) + } + return msg, nil + } + + // Ensure the session history is isolated to this specific patient and not globally + // shared across patients if the clinician uses the same chat session. + patientSessionKey := opts.SessionKey + ":patient:" + targetPatient + + // Lock the workspace path to the patient directory + patientWorkspace := filepath.Join(agent.Workspace, targetPatient) + + // We must not modify the shared agent instance directly to avoid data races. + // Instead, we clone the agent instance for this specific request. + clonedAgent := *agent + clonedAgent.Workspace = patientWorkspace + + var finalResponse strings.Builder + finalResponse.WriteString(fmt.Sprintf("Clinician Agent initialized for patient: %s\n\n", targetPatient)) + + // CoT State Machine variables + var currentContext string = opts.UserMessage + + phases := []string{ + PhaseExtraction, + PhaseTemporalCorrelation, + PhaseTheoryGeneration, + PhaseVerification, + PhaseSafetyDisclaimers, + } + + for _, phase := range phases { + logger.DebugCF("medical", "Executing phase", map[string]any{"phase": phase}) + + prompt := buildPhasePrompt(phase, currentContext) + + // Create a temporary opts for this phase + phaseOpts := opts + phaseOpts.SessionKey = patientSessionKey + phaseOpts.UserMessage = prompt + phaseOpts.SendResponse = false // don't send intermediate steps to bus + phaseOpts.EnableSummary = false + + // Run a standard single LLM execution for this phase + phaseResult, err := al.runAgentLoop(ctx, &clonedAgent, phaseOpts) + if err != nil { + logger.ErrorCF("medical", "Phase failed", map[string]any{ + "phase": phase, + "error": err.Error(), + }) + return "", err + } + + // Accumulate result + finalResponse.WriteString(fmt.Sprintf("### [%s]\n%s\n\n", phase, phaseResult)) + + // Pass result as context to next phase + currentContext = currentContext + "\n\n" + fmt.Sprintf("Result of %s:\n%s", phase, phaseResult) + + // Mandatory safety check abort + if phase == PhaseSafetyDisclaimers { + if strings.Contains(strings.ToLower(phaseResult), "life-threatening") || + strings.Contains(strings.ToLower(phaseResult), "red flag") { + finalResponse.WriteString("\n⚠️ **RED FLAG DETECTED: This requires immediate emergency medical attention.**\n") + } + } + } + + // Send to bus if requested + if opts.SendResponse { + al.bus.PublishOutbound(ctx, bus.OutboundMessage{ + Channel: opts.Channel, + ChatID: opts.ChatID, + Content: finalResponse.String(), + }) + } + + return finalResponse.String(), nil +} + +func buildPhasePrompt(phase string, context string) string { + basePrompt := "You are The Clinician, an expert medical reasoning agent.\nContext:\n%s\n\nTask:\n" + + switch phase { + case PhaseExtraction: + return fmt.Sprintf(basePrompt, context) + "Extract all clinical terminology, symptoms, and vital signs from the context." + case PhaseTemporalCorrelation: + return fmt.Sprintf(basePrompt, context) + "Analyze the temporal correlation of symptoms. Scan for recurring patterns in the patient's history." + case PhaseTheoryGeneration: + return fmt.Sprintf(basePrompt, context) + "Generate a ranked list of potential causes (DDx) and pathophysiological theories based on the extracted symptoms and patterns." + case PhaseVerification: + return fmt.Sprintf(basePrompt, context) + "Verify the proposed theories and any implicit remedies against the patient's Allergies and Medications profile." + case PhaseSafetyDisclaimers: + return fmt.Sprintf(basePrompt, context) + "Provide mandatory clinical disclaimers. Explicitly state whether any 'Life-Threatening' or 'Red Flag' symptoms were detected." + default: + return context + } +} + +func detectTargetPatient(message string) string { + // Simple regex to extract patient name (e.g., "patient John Doe" or "patient: John Doe") + re := regexp.MustCompile(`(?i)patient\s*:?\s*([a-zA-Z0-9_]+(?:\s+[a-zA-Z0-9_]+)*)`) + matches := re.FindStringSubmatch(message) + if len(matches) > 1 { + // Clean up the patient name to make it directory-safe + patientName := strings.TrimSpace(matches[1]) + patientName = strings.ReplaceAll(patientName, " ", "_") + return patientName + } + return "" +} diff --git a/pkg/agent/loop_process.go b/pkg/agent/loop_process.go new file mode 100644 index 000000000..fff717c91 --- /dev/null +++ b/pkg/agent/loop_process.go @@ -0,0 +1,244 @@ +// PicoClaw - Ultra-lightweight personal AI agent +// Inspired by and based on nanobot: https://github.com/HKUDS/nanobot +// License: MIT +// +// Copyright (c) 2026 PicoClaw contributors + +package agent + +import ( + "context" + "fmt" + "strings" + + "jane/pkg/bus" + "jane/pkg/constants" + "jane/pkg/logger" + "jane/pkg/routing" + "jane/pkg/utils" +) + +func (al *AgentLoop) ProcessDirect( + ctx context.Context, + content, sessionKey string, +) (string, error) { + return al.ProcessDirectWithChannel(ctx, content, sessionKey, "cli", "direct") +} + +func (al *AgentLoop) ProcessDirectWithChannel( + ctx context.Context, + content, sessionKey, channel, chatID string, +) (string, error) { + if err := al.ensureMCPInitialized(ctx); err != nil { + return "", err + } + + msg := bus.InboundMessage{ + Channel: channel, + SenderID: "cron", + ChatID: chatID, + Content: content, + SessionKey: sessionKey, + } + + return al.processMessage(ctx, msg) +} + +// ProcessHeartbeat processes a heartbeat request without session history. +// Each heartbeat is independent and doesn't accumulate context. +func (al *AgentLoop) ProcessHeartbeat( + ctx context.Context, + content, channel, chatID string, +) (string, error) { + agent := al.registry.GetDefaultAgent() + if agent == nil { + return "", fmt.Errorf("no default agent for heartbeat") + } + return al.runAgentLoop(ctx, agent, processOptions{ + SessionKey: "heartbeat", + Channel: channel, + ChatID: chatID, + UserMessage: content, + DefaultResponse: defaultResponse, + EnableSummary: false, + SendResponse: false, + NoHistory: true, // Don't load session history for heartbeat + }) +} + +func (al *AgentLoop) processMessage(ctx context.Context, msg bus.InboundMessage) (string, error) { + // Add message preview to log (show full content for error messages) + var logContent string + if strings.Contains(msg.Content, "Error:") || strings.Contains(msg.Content, "error") { + logContent = msg.Content // Full content for errors + } else { + logContent = utils.Truncate(msg.Content, 80) + } + logger.InfoCF( + "agent", + fmt.Sprintf("Processing message from %s:%s: %s", msg.Channel, msg.SenderID, logContent), + map[string]any{ + "channel": msg.Channel, + "chat_id": msg.ChatID, + "sender_id": msg.SenderID, + "session_key": msg.SessionKey, + }, + ) + + var hadAudio bool + msg, hadAudio = al.transcribeAudioInMessage(ctx, msg) + + // For audio messages the placeholder was deferred by the channel. + // Now that transcription (and optional feedback) is done, send it. + if hadAudio && al.channelManager != nil { + al.channelManager.SendPlaceholder(ctx, msg.Channel, msg.ChatID) + } + + // Route system messages to processSystemMessage + if msg.Channel == "system" { + return al.processSystemMessage(ctx, msg) + } + + route, agent, routeErr := al.resolveMessageRoute(msg) + if routeErr != nil { + return "", routeErr + } + + // Reset message-tool state for this round so we don't skip publishing due to a previous round. + if tool, ok := agent.Tools.Get("message"); ok { + if resetter, ok := tool.(interface{ ResetSentInRound() }); ok { + resetter.ResetSentInRound() + } + } + + // Resolve session key from route, while preserving explicit agent-scoped keys. + scopeKey := resolveScopeKey(route, msg.SessionKey) + sessionKey := scopeKey + + logger.InfoCF("agent", "Routed message", + map[string]any{ + "agent_id": agent.ID, + "scope_key": scopeKey, + "session_key": sessionKey, + "matched_by": route.MatchedBy, + "route_agent": route.AgentID, + "route_channel": route.Channel, + }) + + opts := processOptions{ + SessionKey: sessionKey, + Channel: msg.Channel, + ChatID: msg.ChatID, + UserMessage: msg.Content, + Media: msg.Media, + DefaultResponse: defaultResponse, + EnableSummary: true, + SendResponse: false, + } + + // Medical Persona specific routing interception + if agent != nil && agent.ID == "the-clinician" { + return al.processMedicalRequest(ctx, agent, opts) + } + + // context-dependent commands check their own Runtime fields and report + // "unavailable" when the required capability is nil. + if response, handled := al.handleCommand(ctx, msg, agent, &opts); handled { + return response, nil + } + + return al.runAgentLoop(ctx, agent, opts) +} + +func (al *AgentLoop) resolveMessageRoute(msg bus.InboundMessage) (routing.ResolvedRoute, *AgentInstance, error) { + route := al.registry.ResolveRoute(routing.RouteInput{ + Channel: msg.Channel, + AccountID: inboundMetadata(msg, metadataKeyAccountID), + Peer: extractPeer(msg), + ParentPeer: extractParentPeer(msg), + GuildID: inboundMetadata(msg, metadataKeyGuildID), + TeamID: inboundMetadata(msg, metadataKeyTeamID), + }) + + agent, ok := al.registry.GetAgent(route.AgentID) + if !ok { + agent = al.registry.GetDefaultAgent() + } + if agent == nil { + return routing.ResolvedRoute{}, nil, fmt.Errorf("no agent available for route (agent_id=%s)", route.AgentID) + } + + return route, agent, nil +} + +func resolveScopeKey(route routing.ResolvedRoute, msgSessionKey string) string { + if msgSessionKey != "" && strings.HasPrefix(msgSessionKey, sessionKeyAgentPrefix) { + return msgSessionKey + } + return route.SessionKey +} + +func (al *AgentLoop) processSystemMessage( + ctx context.Context, + msg bus.InboundMessage, +) (string, error) { + if msg.Channel != "system" { + return "", fmt.Errorf( + "processSystemMessage called with non-system message channel: %s", + msg.Channel, + ) + } + + logger.InfoCF("agent", "Processing system message", + map[string]any{ + "sender_id": msg.SenderID, + "chat_id": msg.ChatID, + }) + + // Parse origin channel from chat_id (format: "channel:chat_id") + var originChannel, originChatID string + if idx := strings.Index(msg.ChatID, ":"); idx > 0 { + originChannel = msg.ChatID[:idx] + originChatID = msg.ChatID[idx+1:] + } else { + originChannel = "cli" + originChatID = msg.ChatID + } + + // Extract subagent result from message content + // Format: "Task 'label' completed.\n\nResult:\n" + content := msg.Content + if idx := strings.Index(content, "Result:\n"); idx >= 0 { + content = content[idx+8:] // Extract just the result part + } + + // Skip internal channels - only log, don't send to user + if constants.IsInternalChannel(originChannel) { + logger.InfoCF("agent", "Subagent completed (internal channel)", + map[string]any{ + "sender_id": msg.SenderID, + "content_len": len(content), + "channel": originChannel, + }) + return "", nil + } + + // Use default agent for system messages + agent := al.registry.GetDefaultAgent() + if agent == nil { + return "", fmt.Errorf("no default agent for system message") + } + + // Use the origin session for context + sessionKey := routing.BuildAgentMainSessionKey(agent.ID) + + return al.runAgentLoop(ctx, agent, processOptions{ + SessionKey: sessionKey, + Channel: originChannel, + ChatID: originChatID, + UserMessage: fmt.Sprintf("[System: %s] %s", msg.SenderID, msg.Content), + DefaultResponse: "Background task completed.", + EnableSummary: false, + SendResponse: true, + }) +} diff --git a/pkg/agent/loop_summary.go b/pkg/agent/loop_summary.go new file mode 100644 index 000000000..42260e45e --- /dev/null +++ b/pkg/agent/loop_summary.go @@ -0,0 +1,311 @@ +// PicoClaw - Ultra-lightweight personal AI agent +// Inspired by and based on nanobot: https://github.com/HKUDS/nanobot +// License: MIT +// +// Copyright (c) 2026 PicoClaw contributors + +package agent + +import ( + "context" + "fmt" + "strings" + "time" + "unicode/utf8" + + "jane/pkg/logger" + "jane/pkg/providers" +) + +// maybeSummarize triggers summarization if the session history exceeds thresholds. +func (al *AgentLoop) maybeSummarize(agent *AgentInstance, sessionKey, channel, chatID string) { + newHistory := agent.Sessions.GetHistory(sessionKey) + tokenEstimate := al.estimateTokens(newHistory) + threshold := agent.ContextWindow * agent.SummarizeTokenPercent / 100 + + if len(newHistory) > agent.SummarizeMessageThreshold || tokenEstimate > threshold { + summarizeKey := agent.ID + ":" + sessionKey + if _, loading := al.summarizing.LoadOrStore(summarizeKey, true); !loading { + go func() { + defer al.summarizing.Delete(summarizeKey) + logger.Debug("Memory threshold reached. Optimizing conversation history...") + al.summarizeSession(agent, sessionKey) + }() + } + } +} + +// forceCompression aggressively reduces context when the limit is hit. +// It drops the oldest 50% of messages (keeping system prompt and last user message). +func (al *AgentLoop) forceCompression(agent *AgentInstance, sessionKey string) { + history := agent.Sessions.GetHistory(sessionKey) + if len(history) <= 4 { + return + } + + // Keep system prompt (usually [0]) and the very last message (user's trigger) + // We want to drop the oldest half of the *conversation* + // Assuming [0] is system, [1:] is conversation + conversation := history[1 : len(history)-1] + if len(conversation) == 0 { + return + } + + // Helper to find the mid-point of the conversation + mid := len(conversation) / 2 + + // New history structure: + // 1. System Prompt (with compression note appended) + // 2. Second half of conversation + // 3. Last message + + droppedCount := mid + keptConversation := conversation[mid:] + + newHistory := make([]providers.Message, 0, 1+len(keptConversation)+1) + + // Append compression note to the original system prompt instead of adding a new system message + // This avoids having two consecutive system messages which some APIs (like Zhipu) reject + compressionNote := fmt.Sprintf( + "\n\n[System Note: Emergency compression dropped %d oldest messages due to context limit]", + droppedCount, + ) + enhancedSystemPrompt := history[0] + enhancedSystemPrompt.Content = enhancedSystemPrompt.Content + compressionNote + newHistory = append(newHistory, enhancedSystemPrompt) + + newHistory = append(newHistory, keptConversation...) + newHistory = append(newHistory, history[len(history)-1]) // Last message + + // Update session + agent.Sessions.SetHistory(sessionKey, newHistory) + agent.Sessions.Save(sessionKey) + + logger.WarnCF("agent", "Forced compression executed", map[string]any{ + "session_key": sessionKey, + "dropped_msgs": droppedCount, + "new_count": len(newHistory), + }) +} + +// summarizeSession summarizes the conversation history for a session. +func (al *AgentLoop) summarizeSession(agent *AgentInstance, sessionKey string) { + ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second) + defer cancel() + + history := agent.Sessions.GetHistory(sessionKey) + summary := agent.Sessions.GetSummary(sessionKey) + + // Keep last 4 messages for continuity + if len(history) <= 4 { + return + } + + toSummarize := history[:len(history)-4] + + // Oversized Message Guard + maxMessageTokens := agent.ContextWindow / 2 + validMessages := make([]providers.Message, 0) + omitted := false + + for _, m := range toSummarize { + if m.Role != "user" && m.Role != "assistant" { + continue + } + msgTokens := len(m.Content) / 2 + if msgTokens > maxMessageTokens { + omitted = true + continue + } + validMessages = append(validMessages, m) + } + + if len(validMessages) == 0 { + return + } + + const ( + maxSummarizationMessages = 10 + llmMaxRetries = 3 + llmTemperature = 0.3 + fallbackMaxContentLength = 200 + ) + + // Multi-Part Summarization + var finalSummary string + if len(validMessages) > maxSummarizationMessages { + mid := len(validMessages) / 2 + + mid = al.findNearestUserMessage(validMessages, mid) + + part1 := validMessages[:mid] + part2 := validMessages[mid:] + + s1, _ := al.summarizeBatch(ctx, agent, part1, "") + s2, _ := al.summarizeBatch(ctx, agent, part2, "") + + mergePrompt := fmt.Sprintf( + "Merge these two conversation summaries into one cohesive summary:\n\n1: %s\n\n2: %s", + s1, + s2, + ) + + resp, err := al.retryLLMCall(ctx, agent, mergePrompt, llmMaxRetries) + if err == nil && resp.Content != "" { + finalSummary = resp.Content + } else { + finalSummary = s1 + " " + s2 + } + } else { + finalSummary, _ = al.summarizeBatch(ctx, agent, validMessages, summary) + } + + if omitted && finalSummary != "" { + finalSummary += "\n[Note: Some oversized messages were omitted from this summary for efficiency.]" + } + + if finalSummary != "" { + agent.Sessions.SetSummary(sessionKey, finalSummary) + agent.Sessions.TruncateHistory(sessionKey, 4) + agent.Sessions.Save(sessionKey) + } +} + +// findNearestUserMessage finds the nearest user message to the given index. +// It searches backward first, then forward if no user message is found. +func (al *AgentLoop) findNearestUserMessage(messages []providers.Message, mid int) int { + originalMid := mid + + for mid > 0 && messages[mid].Role != "user" { + mid-- + } + + if messages[mid].Role == "user" { + return mid + } + + mid = originalMid + for mid < len(messages) && messages[mid].Role != "user" { + mid++ + } + + if mid < len(messages) { + return mid + } + + return originalMid +} + +// retryLLMCall calls the LLM with retry logic. +func (al *AgentLoop) retryLLMCall( + ctx context.Context, + agent *AgentInstance, + prompt string, + maxRetries int, +) (*providers.LLMResponse, error) { + const ( + llmTemperature = 0.3 + ) + + var resp *providers.LLMResponse + var err error + + for attempt := 0; attempt < maxRetries; attempt++ { + resp, err = agent.Provider.Chat( + ctx, + []providers.Message{{Role: "user", Content: prompt}}, + nil, + agent.Model, + map[string]any{ + "max_tokens": agent.MaxTokens, + "temperature": llmTemperature, + "prompt_cache_key": agent.ID, + }, + ) + if err == nil && resp != nil && resp.Content != "" { + return resp, nil + } + if attempt < maxRetries-1 { + time.Sleep(time.Duration(attempt+1) * 100 * time.Millisecond) + } + } + + return resp, err +} + +// summarizeBatch summarizes a batch of messages. +func (al *AgentLoop) summarizeBatch( + ctx context.Context, + agent *AgentInstance, + batch []providers.Message, + existingSummary string, +) (string, error) { + const ( + llmMaxRetries = 3 + llmTemperature = 0.3 + fallbackMinContentLength = 200 + fallbackMaxContentPercent = 10 + ) + + var sb strings.Builder + sb.WriteString( + "Provide a concise summary of this conversation segment, preserving core context and key points.\n", + ) + if existingSummary != "" { + sb.WriteString("Existing context: ") + sb.WriteString(existingSummary) + sb.WriteString("\n") + } + sb.WriteString("\nCONVERSATION:\n") + for _, m := range batch { + fmt.Fprintf(&sb, "%s: %s\n", m.Role, m.Content) + } + prompt := sb.String() + + response, err := al.retryLLMCall(ctx, agent, prompt, llmMaxRetries) + if err == nil && response.Content != "" { + return strings.TrimSpace(response.Content), nil + } + + var fallback strings.Builder + fallback.WriteString("Conversation summary: ") + for i, m := range batch { + if i > 0 { + fallback.WriteString(" | ") + } + content := strings.TrimSpace(m.Content) + runes := []rune(content) + if len(runes) == 0 { + fallback.WriteString(fmt.Sprintf("%s: ", m.Role)) + continue + } + + keepLength := len(runes) * fallbackMaxContentPercent / 100 + if keepLength < fallbackMinContentLength { + keepLength = fallbackMinContentLength + } + + if keepLength > len(runes) { + keepLength = len(runes) + } + + content = string(runes[:keepLength]) + if keepLength < len(runes) { + content += "..." + } + fallback.WriteString(fmt.Sprintf("%s: %s", m.Role, content)) + } + return fallback.String(), nil +} + +// estimateTokens estimates the number of tokens in a message list. +// Uses a safe heuristic of 2.5 characters per token to account for CJK and other +// overheads better than the previous 3 chars/token. +func (al *AgentLoop) estimateTokens(messages []providers.Message) int { + totalChars := 0 + for _, m := range messages { + totalChars += utf8.RuneCountInString(m.Content) + } + // 2.5 chars per token = totalChars * 2 / 5 + return totalChars * 2 / 5 +} diff --git a/pkg/agent/loop_utils.go b/pkg/agent/loop_utils.go new file mode 100644 index 000000000..30db77547 --- /dev/null +++ b/pkg/agent/loop_utils.go @@ -0,0 +1,140 @@ +// PicoClaw - Ultra-lightweight personal AI agent +// Inspired by and based on nanobot: https://github.com/HKUDS/nanobot +// License: MIT +// +// Copyright (c) 2026 PicoClaw contributors + +package agent + +import ( + "fmt" + "path/filepath" + "strings" + + "jane/pkg/bus" + "jane/pkg/providers" + "jane/pkg/routing" + "jane/pkg/utils" +) + +// formatMessagesForLog formats messages for logging +func formatMessagesForLog(messages []providers.Message) string { + if len(messages) == 0 { + return "[]" + } + + var sb strings.Builder + sb.WriteString("[\n") + for i, msg := range messages { + fmt.Fprintf(&sb, " [%d] Role: %s\n", i, msg.Role) + if len(msg.ToolCalls) > 0 { + sb.WriteString(" ToolCalls:\n") + for _, tc := range msg.ToolCalls { + fmt.Fprintf(&sb, " - ID: %s, Type: %s, Name: %s\n", tc.ID, tc.Type, tc.Name) + if tc.Function != nil { + fmt.Fprintf( + &sb, + " Arguments: %s\n", + utils.Truncate(tc.Function.Arguments, 200), + ) + } + } + } + if msg.Content != "" { + content := utils.Truncate(msg.Content, 200) + fmt.Fprintf(&sb, " Content: %s\n", content) + } + if msg.ToolCallID != "" { + fmt.Fprintf(&sb, " ToolCallID: %s\n", msg.ToolCallID) + } + sb.WriteString("\n") + } + sb.WriteString("]") + return sb.String() +} + +// formatToolsForLog formats tool definitions for logging +func formatToolsForLog(toolDefs []providers.ToolDefinition) string { + if len(toolDefs) == 0 { + return "[]" + } + + var sb strings.Builder + sb.WriteString("[\n") + for i, tool := range toolDefs { + fmt.Fprintf(&sb, " [%d] Type: %s, Name: %s\n", i, tool.Type, tool.Function.Name) + fmt.Fprintf(&sb, " Description: %s\n", tool.Function.Description) + if len(tool.Function.Parameters) > 0 { + fmt.Fprintf( + &sb, + " Parameters: %s\n", + utils.Truncate(fmt.Sprintf("%v", tool.Function.Parameters), 200), + ) + } + } + sb.WriteString("]") + return sb.String() +} + +// inferMediaType determines the media type ("image", "audio", "video", "file") +// from a filename and MIME content type. +func inferMediaType(filename, contentType string) string { + ct := strings.ToLower(contentType) + fn := strings.ToLower(filename) + + if strings.HasPrefix(ct, "image/") { + return "image" + } + if strings.HasPrefix(ct, "audio/") || ct == "application/ogg" { + return "audio" + } + if strings.HasPrefix(ct, "video/") { + return "video" + } + + // Fallback: infer from extension + ext := filepath.Ext(fn) + switch ext { + case ".jpg", ".jpeg", ".png", ".gif", ".webp", ".bmp", ".svg": + return "image" + case ".mp3", ".wav", ".ogg", ".m4a", ".flac", ".aac", ".wma", ".opus": + return "audio" + case ".mp4", ".avi", ".mov", ".webm", ".mkv": + return "video" + } + + return "file" +} + +// extractPeer extracts the routing peer from the inbound message's structured Peer field. +func extractPeer(msg bus.InboundMessage) *routing.RoutePeer { + if msg.Peer.Kind == "" { + return nil + } + peerID := msg.Peer.ID + if peerID == "" { + if msg.Peer.Kind == "direct" { + peerID = msg.SenderID + } else { + peerID = msg.ChatID + } + } + return &routing.RoutePeer{Kind: msg.Peer.Kind, ID: peerID} +} + +func inboundMetadata(msg bus.InboundMessage, key string) string { + if msg.Metadata == nil { + return "" + } + return msg.Metadata[key] +} + +// extractParentPeer extracts the parent peer (reply-to) from inbound message metadata. +func extractParentPeer(msg bus.InboundMessage) *routing.RoutePeer { + parentKind := inboundMetadata(msg, metadataKeyParentPeerKind) + parentID := inboundMetadata(msg, metadataKeyParentPeerID) + if parentKind == "" || parentID == "" { + return nil + } + return &routing.RoutePeer{Kind: parentKind, ID: parentID} +} diff --git a/pkg/auth/oauth.go b/pkg/auth/oauth.go index 4667e3d81..2ba75b0c5 100644 --- a/pkg/auth/oauth.go +++ b/pkg/auth/oauth.go @@ -118,7 +118,12 @@ func LoginBrowser(cfg OAuthProviderConfig) (*AuthCredential, error) { return nil, fmt.Errorf("starting callback server on port %d: %w", cfg.Port, err) } - server := &http.Server{Handler: mux} + server := &http.Server{ + Handler: mux, + ReadTimeout: 10 * time.Second, + ReadHeaderTimeout: 5 * time.Second, + WriteTimeout: 10 * time.Second, + } go server.Serve(listener) defer func() { ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second) diff --git a/pkg/channels/discord/discord.go b/pkg/channels/discord/discord.go index 661378f85..7472b0a12 100644 --- a/pkg/channels/discord/discord.go +++ b/pkg/channels/discord/discord.go @@ -406,6 +406,8 @@ func (c *DiscordChannel) handleMessage(s *discordgo.Session, m *discordgo.Messag return localPath // fallback } + var contentBuilder strings.Builder + contentBuilder.WriteString(content) for _, attachment := range m.Attachments { isAudio := utils.IsAudioFile(attachment.Filename, attachment.ContentType) @@ -413,21 +415,36 @@ func (c *DiscordChannel) handleMessage(s *discordgo.Session, m *discordgo.Messag localPath := c.downloadAttachment(attachment.URL, attachment.Filename) if localPath != "" { mediaPaths = append(mediaPaths, storeMedia(localPath, attachment.Filename)) - content = appendContent(content, fmt.Sprintf("[audio: %s]", attachment.Filename)) + if contentBuilder.Len() > 0 { + contentBuilder.WriteByte('\n') + } + contentBuilder.WriteString("[audio: ") + contentBuilder.WriteString(attachment.Filename) + contentBuilder.WriteByte(']') } else { logger.WarnCF("discord", "Failed to download audio attachment", map[string]any{ "url": attachment.URL, "filename": attachment.Filename, }) mediaPaths = append(mediaPaths, attachment.URL) - content = appendContent(content, fmt.Sprintf("[attachment: %s]", attachment.URL)) + if contentBuilder.Len() > 0 { + contentBuilder.WriteByte('\n') + } + contentBuilder.WriteString("[attachment: ") + contentBuilder.WriteString(attachment.URL) + contentBuilder.WriteByte(']') } } else { mediaPaths = append(mediaPaths, attachment.URL) - content = appendContent(content, fmt.Sprintf("[attachment: %s]", attachment.URL)) + if contentBuilder.Len() > 0 { + contentBuilder.WriteByte('\n') + } + contentBuilder.WriteString("[attachment: ") + contentBuilder.WriteString(attachment.URL) + contentBuilder.WriteByte(']') } } - + content = contentBuilder.String() if content == "" && len(mediaPaths) == 0 { return } @@ -600,7 +617,10 @@ func (c *DiscordChannel) resolveDiscordRefs(s *discordgo.Session, text string, g if msg.Author != nil { author = msg.Author.Username } - fmt.Fprintf(&sb, "\n[linked message from %s]: %s", author, msg.Content) + sb.WriteString("\n[linked message from ") + sb.WriteString(author) + sb.WriteString("]: ") + sb.WriteString(msg.Content) } return sb.String() diff --git a/pkg/channels/manager.go b/pkg/channels/manager.go index 051dec6ed..c163cbce3 100644 --- a/pkg/channels/manager.go +++ b/pkg/channels/manager.go @@ -344,10 +344,11 @@ func (m *Manager) SetupHTTPServer(addr string, healthServer *health.Server) { } m.httpServer = &http.Server{ - Addr: addr, - Handler: m.mux, - ReadTimeout: 30 * time.Second, - WriteTimeout: 30 * time.Second, + Addr: addr, + Handler: m.mux, + ReadTimeout: 30 * time.Second, + ReadHeaderTimeout: 10 * time.Second, + WriteTimeout: 30 * time.Second, } } diff --git a/pkg/config/config_test.go b/pkg/config/config_test.go index 1c93028c7..fbe038a57 100644 --- a/pkg/config/config_test.go +++ b/pkg/config/config_test.go @@ -181,8 +181,8 @@ func TestConfig_BackwardCompat_NoAgentsList(t *testing.T) { t.Fatalf("unmarshal: %v", err) } - if len(cfg.Agents.List) != 0 { - t.Errorf("agents.list should be empty for backward compat, got %d", len(cfg.Agents.List)) + if len(cfg.Agents.List) != 1 { + t.Errorf("agents.list should have default clinician agent for backward compat, got %d", len(cfg.Agents.List)) } if len(cfg.Bindings) != 0 { t.Errorf("bindings should be empty, got %d", len(cfg.Bindings)) diff --git a/pkg/config/defaults.go b/pkg/config/defaults.go index 2a3e66043..a4b734769 100644 --- a/pkg/config/defaults.go +++ b/pkg/config/defaults.go @@ -36,6 +36,13 @@ func DefaultConfig() *Config { SummarizeMessageThreshold: 20, SummarizeTokenPercent: 75, }, + List: []AgentConfig{ + { + ID: "the-clinician", + Name: "Medical Persona", + Workspace: filepath.Join(homePath, "Obsidian_Vault", "Patients"), + }, + }, }, Bindings: []AgentBinding{}, Session: SessionConfig{ diff --git a/pkg/health/server.go b/pkg/health/server.go index 5609ebdf6..a3f6e4df2 100644 --- a/pkg/health/server.go +++ b/pkg/health/server.go @@ -44,10 +44,11 @@ func NewServer(host string, port int) *Server { addr := fmt.Sprintf("%s:%d", host, port) s.server = &http.Server{ - Addr: addr, - Handler: mux, - ReadTimeout: 5 * time.Second, - WriteTimeout: 5 * time.Second, + Addr: addr, + Handler: mux, + ReadTimeout: 5 * time.Second, + ReadHeaderTimeout: 3 * time.Second, + WriteTimeout: 5 * time.Second, } return s diff --git a/pkg/tools/cron.go b/pkg/tools/cron.go index 666ce43d1..1183ef9d1 100644 --- a/pkg/tools/cron.go +++ b/pkg/tools/cron.go @@ -146,7 +146,7 @@ func (t *CronTool) addJob(ctx context.Context, args map[string]any) *ToolResult everySeconds, hasEvery := args["every_seconds"].(float64) cronExpr, hasCron := args["cron_expr"].(string) - // Fix: type assertions return true for zero values, need additional validity checks + // Rationale: type assertions return true for zero values, need additional validity checks // This prevents LLMs that fill unused optional parameters with defaults (0) from triggering wrong type hasAt = hasAt && atSeconds > 0 hasEvery = hasEvery && everySeconds > 0 diff --git a/web/backend/main.go b/web/backend/main.go index 7a575cc47..ee88e7fd0 100644 --- a/web/backend/main.go +++ b/web/backend/main.go @@ -163,7 +163,16 @@ func main() { }() // Start the Server - if err := http.ListenAndServe(addr, handler); err != nil { + server := &http.Server{ + Addr: addr, + Handler: handler, + ReadTimeout: 10 * time.Second, + ReadHeaderTimeout: 5 * time.Second, + WriteTimeout: 30 * time.Second, + IdleTimeout: 120 * time.Second, + } + + if err := server.ListenAndServe(); err != nil && err != http.ErrServerClosed { log.Fatalf("Server failed to start: %v", err) } }