docs: clarify heartbeat empty file behavior (#1535) (thanks @JustYannicc)

Fixed issue where trigger words would disappear when typing or when adding new trigger words. The problem was that `swabbleTriggerWords` changes were triggering `VoiceWakeRuntime.refresh()` which sanitized the array by removing empty strings in real-time.

Solution: Introduced local `@State` buffer `triggerEntries` with stable UUID identifiers for each trigger word entry. User edits now only affect the local state buffer and are synced back to `AppState` on explicit actions (submit, remove, disappear). This prevents premature sanitization during editing.

The local state is loaded on view appear and when the view becomes active, ensuring it stays in sync with `AppState`.

AGENTS.md

@@ -128,6 +128,10 @@
 - **Multi-agent safety:** do **not** switch branches / check out a different branch unless explicitly requested.
 - **Multi-agent safety:** running multiple agents is OK as long as each agent has its own session.
 - **Multi-agent safety:** when you see unrecognized files, keep going; focus on your changes and commit only those.
+- Lint/format churn:
+  - If staged+unstaged diffs are formatting-only, auto-resolve without asking.
+  - If commit/push already requested, auto-stage and include formatting-only follow-ups in the same commit (or a tiny follow-up commit if needed), no extra confirmation.
+  - Only ask when changes are semantic (logic/data/behavior).
 - Lobster seam: use the shared CLI palette in `src/terminal/palette.ts` (no hardcoded colors); apply palette to onboarding/config prompts and other TTY UI output as needed.
 - **Multi-agent safety:** focus reports on your edits; avoid guard-rail disclaimers unless truly blocked; when multiple agents touch the same file, continue if safe; end with a brief “other files present” note only if relevant.
 - Bug investigations: read source code of relevant npm dependencies and all related local code before concluding; aim for high-confidence root cause.

CHANGELOG.md

@@ -2,15 +2,49 @@
 
 Docs: https://docs.clawd.bot
 
-## 2026.1.23
+## 2026.1.23 (Unreleased)
 
 ### Changes
+- Plugins: add optional llm-task JSON-only tool for workflows. (#1498) Thanks @vignesh07.
 - CLI: restart the gateway by default after `clawdbot update`; add `--no-restart` to skip it.
+- CLI: add live auth probes to `clawdbot models status` for per-profile verification.
+- Agents: add Bedrock auto-discovery defaults + config overrides. (#1553) Thanks @fal3.
+- Docs: add cron vs heartbeat decision guide (with Lobster workflow notes). (#1533) Thanks @JustYannicc.
+- Docs: clarify HEARTBEAT.md empty file skips heartbeats, missing file still runs. (#1535) Thanks @JustYannicc.
 - Markdown: add per-channel table conversion (bullets for Signal/WhatsApp, code blocks elsewhere). (#1495) Thanks @odysseus0.
+- Tlon: add Urbit channel plugin (DMs, group mentions, thread replies). (#1544) Thanks @wca4a.
 
 ### Fixes
+- Docker: update gateway command in docker-compose and Hetzner guide. (#1514)
+- Voice wake: auto-save wake words on blur/submit across iOS/Android and align limits with macOS.
+- UI: keep the Control UI sidebar visible while scrolling long pages. (#1515) Thanks @pookNast.
+- UI: cache Control UI markdown rendering + memoize chat text extraction to reduce Safari typing jank.
+- Tailscale: retry serve/funnel with sudo only for permission errors and keep original failure details. (#1551) Thanks @sweepies.
+- Agents: add CLI log hint to "agent failed before reply" messages. (#1550) Thanks @sweepies.
+- Discord: limit autoThread mention bypass to bot-owned threads; keep ack reactions mention-gated. (#1511) Thanks @pvoo.
+- Gateway: accept null optional fields in exec approval requests. (#1511) Thanks @pvoo.
+- TUI: forward unknown slash commands (for example, `/context`) to the Gateway.
+- TUI: include Gateway slash commands in autocomplete and `/help`.
+- CLI: skip usage lines in `clawdbot models status` when provider usage is unavailable.
+- CLI: suppress diagnostic session/run noise during auth probes.
+- CLI: hide auth probe timeout warnings from embedded runs.
+- CLI: render auth probe results as a table in `clawdbot models status`.
+- CLI: suppress probe-only embedded logs unless `--verbose` is set.
+- CLI: move auth probe errors below the table to reduce wrapping.
+- CLI: prevent ANSI color bleed when table cells wrap.
+- CLI: explain when auth profiles are excluded by auth.order in probe details.
+- CLI: drop the em dash when the banner tagline wraps to a second line.
+- CLI: inline auth probe errors in status rows to reduce wrapping.
+- Telegram: render markdown in media captions. (#1478)
+- Agents: honor enqueue overrides for embedded runs to avoid queue deadlocks in tests.
+- Daemon: use platform PATH delimiters when building minimal service paths.
+- Tests: skip embedded runner ordering assertion on Windows to avoid CI timeouts.
+- Linux: include env-configured user bin roots in systemd PATH and align PATH audits. (#1512) Thanks @robbyczgw-cla.
+- TUI: render Gateway slash-command replies as system output (for example, `/context`).
 - Media: preserve PNG alpha when possible; fall back to JPEG when still over size cap. (#1491) Thanks @robbyczgw-cla.
 - Agents: treat plugin-only tool allowlists as opt-ins; keep core tools enabled. (#1467)
+- Exec approvals: persist allowlist entry ids to keep macOS allowlist rows stable. (#1521) Thanks @ngutman.
+- MS Teams (plugin): remove `.default` suffix from Graph scopes to avoid double-appending. (#1507) Thanks @Evizero.
 
 ## 2026.1.22
 

apps/macos/Sources/Clawdbot/ExecApprovals.swift

@@ -84,11 +84,52 @@ enum ExecApprovalDecision: String, Codable, Sendable {
     case deny
 }
 
-struct ExecAllowlistEntry: Codable, Hashable {
+struct ExecAllowlistEntry: Codable, Hashable, Identifiable {
+    var id: UUID
     var pattern: String
     var lastUsedAt: Double?
     var lastUsedCommand: String?
     var lastResolvedPath: String?
+
+    init(
+        id: UUID = UUID(),
+        pattern: String,
+        lastUsedAt: Double? = nil,
+        lastUsedCommand: String? = nil,
+        lastResolvedPath: String? = nil)
+    {
+        self.id = id
+        self.pattern = pattern
+        self.lastUsedAt = lastUsedAt
+        self.lastUsedCommand = lastUsedCommand
+        self.lastResolvedPath = lastResolvedPath
+    }
+
+    private enum CodingKeys: String, CodingKey {
+        case id
+        case pattern
+        case lastUsedAt
+        case lastUsedCommand
+        case lastResolvedPath
+    }
+
+    init(from decoder: Decoder) throws {
+        let container = try decoder.container(keyedBy: CodingKeys.self)
+        self.id = try container.decodeIfPresent(UUID.self, forKey: .id) ?? UUID()
+        self.pattern = try container.decode(String.self, forKey: .pattern)
+        self.lastUsedAt = try container.decodeIfPresent(Double.self, forKey: .lastUsedAt)
+        self.lastUsedCommand = try container.decodeIfPresent(String.self, forKey: .lastUsedCommand)
+        self.lastResolvedPath = try container.decodeIfPresent(String.self, forKey: .lastResolvedPath)
+    }
+
+    func encode(to encoder: Encoder) throws {
+        var container = encoder.container(keyedBy: CodingKeys.self)
+        try container.encode(self.id, forKey: .id)
+        try container.encode(self.pattern, forKey: .pattern)
+        try container.encodeIfPresent(self.lastUsedAt, forKey: .lastUsedAt)
+        try container.encodeIfPresent(self.lastUsedCommand, forKey: .lastUsedCommand)
+        try container.encodeIfPresent(self.lastResolvedPath, forKey: .lastResolvedPath)
+    }
 }
 
 struct ExecApprovalsDefaults: Codable {
@@ -295,6 +336,7 @@ enum ExecApprovalsStore {
         let allowlist = ((wildcardEntry.allowlist ?? []) + (agentEntry.allowlist ?? []))
             .map { entry in
                 ExecAllowlistEntry(
+                    id: entry.id,
                     pattern: entry.pattern.trimmingCharacters(in: .whitespacesAndNewlines),
                     lastUsedAt: entry.lastUsedAt,
                     lastUsedCommand: entry.lastUsedCommand,
@@ -379,6 +421,7 @@ enum ExecApprovalsStore {
             let allowlist = (entry.allowlist ?? []).map { item -> ExecAllowlistEntry in
                 guard item.pattern == pattern else { return item }
                 return ExecAllowlistEntry(
+                    id: item.id,
                     pattern: item.pattern,
                     lastUsedAt: Date().timeIntervalSince1970 * 1000,
                     lastUsedCommand: command,
@@ -398,6 +441,7 @@ enum ExecApprovalsStore {
             let cleaned = allowlist
                 .map { item in
                     ExecAllowlistEntry(
+                        id: item.id,
                         pattern: item.pattern.trimmingCharacters(in: .whitespacesAndNewlines),
                         lastUsedAt: item.lastUsedAt,
                         lastUsedCommand: item.lastUsedCommand,

apps/macos/Sources/Clawdbot/SystemRunSettingsView.swift

@@ -123,12 +123,12 @@ struct SystemRunSettingsView: View {
                         .foregroundStyle(.secondary)
                 } else {
                     VStack(alignment: .leading, spacing: 8) {
-                        ForEach(Array(self.model.entries.enumerated()), id: \.offset) { index, _ in
+                        ForEach(self.model.entries, id: \.id) { entry in
                             ExecAllowlistRow(
                                 entry: Binding(
-                                    get: { self.model.entries[index] },
-                                    set: { self.model.updateEntry($0, at: index) }),
-                                onRemove: { self.model.removeEntry(at: index) })
+                                    get: { self.model.entry(for: entry.id) ?? entry },
+                                    set: { self.model.updateEntry($0, id: entry.id) }),
+                                onRemove: { self.model.removeEntry(id: entry.id) })
                         }
                     }
                 }
@@ -373,20 +373,24 @@ final class ExecApprovalsSettingsModel {
         ExecApprovalsStore.updateAllowlist(agentId: self.selectedAgentId, allowlist: self.entries)
     }
 
-    func updateEntry(_ entry: ExecAllowlistEntry, at index: Int) {
+    func updateEntry(_ entry: ExecAllowlistEntry, id: UUID) {
         guard !self.isDefaultsScope else { return }
-        guard self.entries.indices.contains(index) else { return }
+        guard let index = self.entries.firstIndex(where: { $0.id == id }) else { return }
         self.entries[index] = entry
         ExecApprovalsStore.updateAllowlist(agentId: self.selectedAgentId, allowlist: self.entries)
     }
 
-    func removeEntry(at index: Int) {
+    func removeEntry(id: UUID) {
         guard !self.isDefaultsScope else { return }
-        guard self.entries.indices.contains(index) else { return }
+        guard let index = self.entries.firstIndex(where: { $0.id == id }) else { return }
         self.entries.remove(at: index)
         ExecApprovalsStore.updateAllowlist(agentId: self.selectedAgentId, allowlist: self.entries)
     }
 
+    func entry(for id: UUID) -> ExecAllowlistEntry? {
+        self.entries.first(where: { $0.id == id })
+    }
+
     func refreshSkillBins(force: Bool = false) async {
         guard self.autoAllowSkills else {
             self.skillBins = []

apps/macos/Sources/Clawdbot/VoiceWakeSettings.swift

@@ -21,6 +21,7 @@ struct VoiceWakeSettings: View {
     @State private var micObserver = AudioInputDeviceObserver()
     @State private var micRefreshTask: Task<Void, Never>?
     @State private var availableLocales: [Locale] = []
+    @State private var triggerEntries: [TriggerEntry] = []
     private let fieldLabelWidth: CGFloat = 140
     private let controlWidth: CGFloat = 240
     private let isPreview = ProcessInfo.processInfo.isPreview
@@ -31,9 +32,9 @@ struct VoiceWakeSettings: View {
         var id: String { self.uid }
     }
 
-    private struct IndexedWord: Identifiable {
-        let id: Int
-        let value: String
+    private struct TriggerEntry: Identifiable {
+        let id: UUID
+        var value: String
     }
 
     private var voiceWakeBinding: Binding<Bool> {
@@ -105,6 +106,7 @@ struct VoiceWakeSettings: View {
         .onAppear {
             guard !self.isPreview else { return }
             self.startMicObserver()
+            self.loadTriggerEntries()
         }
         .onChange(of: self.state.voiceWakeMicID) { _, _ in
             guard !self.isPreview else { return }
@@ -122,8 +124,10 @@ struct VoiceWakeSettings: View {
                 self.micRefreshTask = nil
                 Task { await self.meter.stop() }
                 self.micObserver.stop()
+                self.syncTriggerEntriesToState()
             } else {
                 self.startMicObserver()
+                self.loadTriggerEntries()
             }
         }
         .onDisappear {
@@ -136,11 +140,16 @@ struct VoiceWakeSettings: View {
             self.micRefreshTask = nil
             self.micObserver.stop()
             Task { await self.meter.stop() }
+            self.syncTriggerEntriesToState()
         }
     }
 
-    private var indexedWords: [IndexedWord] {
-        self.state.swabbleTriggerWords.enumerated().map { IndexedWord(id: $0.offset, value: $0.element) }
+    private func loadTriggerEntries() {
+        self.triggerEntries = self.state.swabbleTriggerWords.map { TriggerEntry(id: UUID(), value: $0) }
+    }
+
+    private func syncTriggerEntriesToState() {
+        self.state.swabbleTriggerWords = self.triggerEntries.map(\.value)
     }
 
     private var triggerTable: some View {
@@ -154,29 +163,42 @@ struct VoiceWakeSettings: View {
                 } label: {
                     Label("Add word", systemImage: "plus")
                 }
-                .disabled(self.state.swabbleTriggerWords
-                    .contains(where: { $0.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty }))
+                .disabled(self.triggerEntries
+                    .contains(where: { $0.value.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty }))
 
-                Button("Reset defaults") { self.state.swabbleTriggerWords = defaultVoiceWakeTriggers }
+                Button("Reset defaults") {
+                    self.triggerEntries = defaultVoiceWakeTriggers.map { TriggerEntry(id: UUID(), value: $0) }
+                    self.syncTriggerEntriesToState()
+                }
             }
 
-            Table(self.indexedWords) {
-                TableColumn("Word") { row in
-                    TextField("Wake word", text: self.binding(for: row.id))
-                        .textFieldStyle(.roundedBorder)
-                }
-                TableColumn("") { row in
-                    Button {
-                        self.removeWord(at: row.id)
-                    } label: {
-                        Image(systemName: "trash")
+            VStack(spacing: 0) {
+                ForEach(self.$triggerEntries) { $entry in
+                    HStack(spacing: 8) {
+                        TextField("Wake word", text: $entry.value)
+                            .textFieldStyle(.roundedBorder)
+                            .onSubmit {
+                                self.syncTriggerEntriesToState()
+                            }
+
+                        Button {
+                            self.removeWord(id: entry.id)
+                        } label: {
+                            Image(systemName: "trash")
+                        }
+                        .buttonStyle(.borderless)
+                        .help("Remove trigger word")
+                        .frame(width: 24)
+                    }
+                    .padding(8)
+
+                    if entry.id != self.triggerEntries.last?.id {
+                        Divider()
                     }
-                    .buttonStyle(.borderless)
-                    .help("Remove trigger word")
                 }
-                .width(36)
             }
-            .frame(minHeight: 180)
+            .frame(maxWidth: .infinity, minHeight: 180, alignment: .topLeading)
+            .background(Color(nsColor: .textBackgroundColor))
             .clipShape(RoundedRectangle(cornerRadius: 6))
             .overlay(
                 RoundedRectangle(cornerRadius: 6)
@@ -211,24 +233,12 @@ struct VoiceWakeSettings: View {
     }
 
     private func addWord() {
-        self.state.swabbleTriggerWords.append("")
+        self.triggerEntries.append(TriggerEntry(id: UUID(), value: ""))
     }
 
-    private func removeWord(at index: Int) {
-        guard self.state.swabbleTriggerWords.indices.contains(index) else { return }
-        self.state.swabbleTriggerWords.remove(at: index)
-    }
-
-    private func binding(for index: Int) -> Binding<String> {
-        Binding(
-            get: {
-                guard self.state.swabbleTriggerWords.indices.contains(index) else { return "" }
-                return self.state.swabbleTriggerWords[index]
-            },
-            set: { newValue in
-                guard self.state.swabbleTriggerWords.indices.contains(index) else { return }
-                self.state.swabbleTriggerWords[index] = newValue
-            })
+    private func removeWord(id: UUID) {
+        self.triggerEntries.removeAll { $0.id == id }
+        self.syncTriggerEntriesToState()
     }
 
     private func toggleTest() {
@@ -638,13 +648,14 @@ extension VoiceWakeSettings {
         state.voicePushToTalkEnabled = true
         state.swabbleTriggerWords = ["Claude", "Hey"]
 
-        let view = VoiceWakeSettings(state: state, isActive: true)
+        var view = VoiceWakeSettings(state: state, isActive: true)
         view.availableMics = [AudioInputDevice(uid: "mic-1", name: "Built-in")]
         view.availableLocales = [Locale(identifier: "en_US")]
         view.meterLevel = 0.42
         view.meterError = "No input"
         view.testState = .detected("ok")
         view.isTesting = true
+        view.triggerEntries = [TriggerEntry(id: UUID(), value: "Claude")]
 
         _ = view.body
         _ = view.localePicker
@@ -654,8 +665,9 @@ extension VoiceWakeSettings {
         _ = view.chimeSection
 
         view.addWord()
-        _ = view.binding(for: 0).wrappedValue
-        view.removeWord(at: 0)
+        if let entryId = view.triggerEntries.first?.id {
+            view.removeWord(id: entryId)
+        }
     }
 }
 #endif

docs/cli/index.md

@@ -700,8 +700,15 @@ Options:
 - `--json`
 - `--plain`
 - `--check` (exit 1=expired/missing, 2=expiring)
+- `--probe` (live probe of configured auth profiles)
+- `--probe-provider <name>`
+- `--probe-profile <id>` (repeat or comma-separated)
+- `--probe-timeout <ms>`
+- `--probe-concurrency <n>`
+- `--probe-max-tokens <n>`
 
 Always includes the auth overview and OAuth expiry status for profiles in the auth store.
+`--probe` runs live requests (may consume tokens and trigger rate limits).
 
 ### `models set <model>`
 Set `agents.defaults.model.primary`.

docs/cli/models.md

@@ -25,12 +25,26 @@ clawdbot models scan
 `clawdbot models status` shows the resolved default/fallbacks plus an auth overview.
 When provider usage snapshots are available, the OAuth/token status section includes
 provider usage headers.
+Add `--probe` to run live auth probes against each configured provider profile.
+Probes are real requests (may consume tokens and trigger rate limits).
 
 Notes:
 - `models set <model-or-alias>` accepts `provider/model` or an alias.
 - Model refs are parsed by splitting on the **first** `/`. If the model ID includes `/` (OpenRouter-style), include the provider prefix (example: `openrouter/moonshotai/kimi-k2`).
 - If you omit the provider, Clawdbot treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
 
+### `models status`
+Options:
+- `--json`
+- `--plain`
+- `--check` (exit 1=expired/missing, 2=expiring)
+- `--probe` (live probe of configured auth profiles)
+- `--probe-provider <name>` (probe one provider)
+- `--probe-profile <id>` (repeat or comma-separated profile ids)
+- `--probe-timeout <ms>`
+- `--probe-concurrency <n>`
+- `--probe-max-tokens <n>`
+
 ## Aliases + fallbacks
 
 ```bash

docs/gateway/heartbeat.md

@@ -159,6 +159,10 @@ If a `HEARTBEAT.md` file exists in the workspace, the default prompt tells the
 agent to read it. Think of it as your “heartbeat checklist”: small, stable, and
 safe to include every 30 minutes.
 
+If `HEARTBEAT.md` exists but is effectively empty (only blank lines and markdown
+headers like `# Heading`), Clawdbot skips the heartbeat run to save API calls.
+If the file is missing, the heartbeat still runs and the model decides what to do.
+
 Keep it tiny (short checklist or reminders) to avoid prompt bloat.
 
 Example `HEARTBEAT.md`:

docs/reference/templates/HEARTBEAT.md

@@ -5,4 +5,5 @@ read_when:
 ---
 # HEARTBEAT.md
 
-Keep this file empty unless you want a tiny checklist. Keep it small.
+# Keep this file empty (or with only comments) to skip heartbeat API calls.
+# Add tasks below when you want the agent to check something periodically.

docs/start/clawd.md

@@ -182,6 +182,8 @@ By default, Clawdbot runs a heartbeat every 30 minutes with the prompt:
 `Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK.`
 Set `agents.defaults.heartbeat.every: "0m"` to disable.
 
+- If `HEARTBEAT.md` exists but is effectively empty (only blank lines and markdown headers like `# Heading`), Clawdbot skips the heartbeat run to save API calls.
+- If the file is missing, the heartbeat still runs and the model decides what to do.
 - If the agent replies with `HEARTBEAT_OK` (optionally with short padding; see `agents.defaults.heartbeat.ackMaxChars`), Clawdbot suppresses outbound delivery for that heartbeat.
 - Heartbeats run full agent turns — shorter intervals burn more tokens.
 

docs/start/faq.md

@@ -324,6 +324,7 @@ brew install <formula>
 ```
 
 If you run Clawdbot via systemd, ensure the service PATH includes `/home/linuxbrew/.linuxbrew/bin` (or your brew prefix) so `brew`-installed tools resolve in non‑login shells.
+Recent builds also prepend common user bin dirs on Linux systemd services (for example `~/.local/bin`, `~/.npm-global/bin`, `~/.local/share/pnpm`, `~/.bun/bin`) and honor `PNPM_HOME`, `NPM_CONFIG_PREFIX`, `BUN_INSTALL`, `VOLTA_HOME`, `ASDF_DATA_DIR`, `NVM_DIR`, and `FNM_DIR` when set.
 
 ### Can I switch between npm and git installs later?
 
@@ -970,6 +971,10 @@ Heartbeats run every **30m** by default. Tune or disable them:
 }
 ```
 
+If `HEARTBEAT.md` exists but is effectively empty (only blank lines and markdown
+headers like `# Heading`), Clawdbot skips the heartbeat run to save API calls.
+If the file is missing, the heartbeat still runs and the model decides what to do.
+
 Per-agent overrides use `agents.list[].heartbeat`. Docs: [Heartbeat](/gateway/heartbeat).
 
 ### Do I need to add a “bot account” to a WhatsApp group?

docs/tools/exec-approvals.md

@@ -54,6 +54,7 @@ Example schema:
       "autoAllowSkills": true,
       "allowlist": [
         {
+          "id": "B0C8C0B3-2C2D-4F8A-9A3C-5A4B3C2D1E0F",
           "pattern": "~/Projects/**/bin/rg",
           "lastUsedAt": 1737150000000,
           "lastUsedCommand": "rg -n TODO",
@@ -96,6 +97,7 @@ Examples:
 - `/opt/homebrew/bin/rg`
 
 Each allowlist entry tracks:
+- **id** stable UUID used for UI identity (optional)
 - **last used** timestamp
 - **last used command**
 - **last resolved path**

docs/tui.md

@@ -88,6 +88,8 @@ Session lifecycle:
 - `/settings`
 - `/exit`
 
+Other Gateway slash commands (for example, `/context`) are forwarded to the Gateway and shown as system output. See [Slash commands](/tools/slash-commands).
+
 ## Local shell commands
 - Prefix a line with `!` to run a local shell command on the TUI host.
 - The TUI prompts once per session to allow local execution; declining keeps `!` disabled for the session.

extensions/bluebubbles/src/monitor.test.ts

@@ -222,6 +222,12 @@ function createMockResponse(): ServerResponse & { body: string; statusCode: numb
   return res;
 }
 
+const flushAsync = async () => {
+  for (let i = 0; i < 2; i += 1) {
+    await new Promise<void>((resolve) => setImmediate(resolve));
+  }
+};
+
 describe("BlueBubbles webhook monitor", () => {
   let unregister: () => void;
 
@@ -508,7 +514,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(resolveChatGuidForTarget).toHaveBeenCalledWith(
         expect.objectContaining({
@@ -556,7 +562,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(resolveChatGuidForTarget).not.toHaveBeenCalled();
       expect(sendMessageBlueBubbles).toHaveBeenCalledWith(
@@ -603,7 +609,7 @@ describe("BlueBubbles webhook monitor", () => {
       await handleBlueBubblesWebhookRequest(req, res);
 
       // Wait for async processing
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(res.statusCode).toBe(200);
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
@@ -642,7 +648,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(res.statusCode).toBe(200);
       expect(mockDispatchReplyWithBufferedBlockDispatcher).not.toHaveBeenCalled();
@@ -683,7 +689,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockUpsertPairingRequest).toHaveBeenCalled();
       expect(mockDispatchReplyWithBufferedBlockDispatcher).not.toHaveBeenCalled();
@@ -726,7 +732,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockUpsertPairingRequest).toHaveBeenCalled();
       // Should not send pairing reply since created=false
@@ -767,7 +773,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
     });
@@ -804,7 +810,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).not.toHaveBeenCalled();
     });
@@ -844,7 +850,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
     });
@@ -882,7 +888,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).not.toHaveBeenCalled();
     });
@@ -921,7 +927,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).not.toHaveBeenCalled();
     });
@@ -960,7 +966,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
     });
@@ -1001,7 +1007,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
       const callArgs = mockDispatchReplyWithBufferedBlockDispatcher.mock.calls[0][0];
@@ -1042,7 +1048,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).not.toHaveBeenCalled();
     });
@@ -1080,7 +1086,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
     });
@@ -1123,7 +1129,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
       const callArgs = mockDispatchReplyWithBufferedBlockDispatcher.mock.calls[0][0];
@@ -1169,7 +1175,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
       const callArgs = mockDispatchReplyWithBufferedBlockDispatcher.mock.calls[0][0];
@@ -1215,7 +1221,7 @@ describe("BlueBubbles webhook monitor", () => {
       const originalRes = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(originalReq, originalRes);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       // Only assert the reply message behavior below.
       mockDispatchReplyWithBufferedBlockDispatcher.mockClear();
@@ -1239,7 +1245,7 @@ describe("BlueBubbles webhook monitor", () => {
       const replyRes = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(replyReq, replyRes);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
       const callArgs = mockDispatchReplyWithBufferedBlockDispatcher.mock.calls[0][0];
@@ -1285,7 +1291,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
       const callArgs = mockDispatchReplyWithBufferedBlockDispatcher.mock.calls[0][0];
@@ -1333,7 +1339,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(sendBlueBubblesReaction).toHaveBeenCalledWith(
         expect.objectContaining({
@@ -1386,7 +1392,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       // Should process even without mention because it's an authorized control command
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
@@ -1429,7 +1435,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).not.toHaveBeenCalled();
     });
@@ -1472,7 +1478,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(markBlueBubblesChatRead).toHaveBeenCalled();
     });
@@ -1513,7 +1519,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(markBlueBubblesChatRead).not.toHaveBeenCalled();
     });
@@ -1556,7 +1562,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       // Should call typing start when reply flow triggers it.
       expect(sendBlueBubblesTyping).toHaveBeenCalledWith(
@@ -1606,7 +1612,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(sendBlueBubblesTyping).toHaveBeenCalledWith(
         expect.any(String),
@@ -1651,7 +1657,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(sendBlueBubblesTyping).toHaveBeenCalledWith(
         expect.any(String),
@@ -1699,7 +1705,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       // Outbound message ID uses short ID "2" (inbound msg-1 is "1", outbound msg-123 is "2")
       expect(mockEnqueueSystemEvent).toHaveBeenCalledWith(
@@ -1744,7 +1750,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockEnqueueSystemEvent).toHaveBeenCalledWith(
         expect.stringContaining("reaction added"),
@@ -1784,7 +1790,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockEnqueueSystemEvent).toHaveBeenCalledWith(
         expect.stringContaining("reaction removed"),
@@ -1824,7 +1830,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockEnqueueSystemEvent).not.toHaveBeenCalled();
     });
@@ -1862,7 +1868,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockEnqueueSystemEvent).toHaveBeenCalledWith(
         expect.stringContaining("👍"),
@@ -1903,7 +1909,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).toHaveBeenCalled();
       const callArgs = mockDispatchReplyWithBufferedBlockDispatcher.mock.calls[0][0];
@@ -1943,7 +1949,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       // The short ID "1" should resolve back to the full UUID
       expect(resolveBlueBubblesMessageId("1")).toBe("msg-uuid-12345");
@@ -1995,7 +2001,7 @@ describe("BlueBubbles webhook monitor", () => {
       const res = createMockResponse();
 
       await handleBlueBubblesWebhookRequest(req, res);
-      await new Promise((resolve) => setTimeout(resolve, 50));
+      await flushAsync();
 
       expect(mockDispatchReplyWithBufferedBlockDispatcher).not.toHaveBeenCalled();
     });

pnpm-lock.yaml

@@ -376,6 +376,8 @@ importers:
         specifier: ^4.3.5
         version: 4.3.5
 
+  extensions/open-prose: {}
+
   extensions/signal: {}
 
   extensions/slack: {}

src/agents/clawdbot-gateway-tool.test.ts

@@ -3,6 +3,7 @@ import os from "node:os";
 import path from "node:path";
 import { describe, expect, it, vi } from "vitest";
 
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 
 vi.mock("./tools/gateway.js", () => ({

src/agents/clawdbot-tools.agents.test.ts

@@ -16,6 +16,7 @@ vi.mock("../config/config.js", async (importOriginal) => {
   };
 });
 
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 
 describe("agents_list", () => {

src/agents/clawdbot-tools.camera.test.ts

@@ -10,6 +10,7 @@ vi.mock("../media/image-ops.js", () => ({
   resizeToJpeg: vi.fn(async () => Buffer.from("jpeg")),
 }));
 
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 
 describe("nodes camera_snap", () => {

src/agents/clawdbot-tools.session-status.test.ts

@@ -75,6 +75,7 @@ vi.mock("../infra/provider-usage.js", () => ({
   formatUsageSummaryLine: () => null,
 }));
 
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 
 describe("session_status tool", () => {

src/agents/clawdbot-tools.sessions.test.ts

@@ -4,9 +4,6 @@ const callGatewayMock = vi.fn();
 vi.mock("../gateway/call.js", () => ({
   callGateway: (opts: unknown) => callGatewayMock(opts),
 }));
-vi.mock("../plugins/tools.js", () => ({
-  resolvePluginTools: () => [],
-}));
 
 vi.mock("../config/config.js", async (importOriginal) => {
   const actual = await importOriginal<typeof import("../config/config.js")>();
@@ -23,6 +20,7 @@ vi.mock("../config/config.js", async (importOriginal) => {
   };
 });
 
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 
 const waitForCalls = async (getCount: () => number, count: number, timeoutMs = 2000) => {

src/agents/clawdbot-tools.subagents.sessions-spawn-allows-cross-agent-spawning-configured.test.ts

@@ -21,6 +21,7 @@ vi.mock("../config/config.js", async (importOriginal) => {
   };
 });
 
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 import { resetSubagentRegistryForTests } from "./subagent-registry.js";
 

src/agents/clawdbot-tools.subagents.sessions-spawn-announces-agent-wait-lifecycle-events.test.ts

@@ -21,6 +21,7 @@ vi.mock("../config/config.js", async (importOriginal) => {
   };
 });
 
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 import { resetSubagentRegistryForTests } from "./subagent-registry.js";
 

src/agents/clawdbot-tools.subagents.sessions-spawn-applies-model-child-session.test.ts

@@ -21,6 +21,7 @@ vi.mock("../config/config.js", async (importOriginal) => {
   };
 });
 
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 import { resetSubagentRegistryForTests } from "./subagent-registry.js";
 

src/agents/clawdbot-tools.subagents.sessions-spawn-normalizes-allowlisted-agent-ids.test.ts

@@ -22,6 +22,7 @@ vi.mock("../config/config.js", async (importOriginal) => {
 });
 
 import { emitAgentEvent } from "../infra/agent-events.js";
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 import { resetSubagentRegistryForTests } from "./subagent-registry.js";
 

src/agents/clawdbot-tools.subagents.sessions-spawn-prefers-per-agent-subagent-model.test.ts

@@ -21,6 +21,7 @@ vi.mock("../config/config.js", async (importOriginal) => {
   };
 });
 
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 import { resetSubagentRegistryForTests } from "./subagent-registry.js";
 

src/agents/clawdbot-tools.subagents.sessions-spawn-resolves-main-announce-target-from.test.ts

@@ -22,6 +22,7 @@ vi.mock("../config/config.js", async (importOriginal) => {
 });
 
 import { emitAgentEvent } from "../infra/agent-events.js";
+import "./test-helpers/fast-core-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 import { resetSubagentRegistryForTests } from "./subagent-registry.js";
 

src/agents/pi-embedded-runner/runs.ts

@@ -109,14 +109,18 @@ export function setActiveEmbeddedRun(sessionId: string, handle: EmbeddedPiQueueH
     state: "processing",
     reason: wasActive ? "run_replaced" : "run_started",
   });
-  diag.info(`run registered: sessionId=${sessionId} totalActive=${ACTIVE_EMBEDDED_RUNS.size}`);
+  if (!sessionId.startsWith("probe-")) {
+    diag.info(`run registered: sessionId=${sessionId} totalActive=${ACTIVE_EMBEDDED_RUNS.size}`);
+  }
 }
 
 export function clearActiveEmbeddedRun(sessionId: string, handle: EmbeddedPiQueueHandle) {
   if (ACTIVE_EMBEDDED_RUNS.get(sessionId) === handle) {
     ACTIVE_EMBEDDED_RUNS.delete(sessionId);
     logSessionStateChange({ sessionId, state: "idle", reason: "run_completed" });
-    diag.info(`run cleared: sessionId=${sessionId} totalActive=${ACTIVE_EMBEDDED_RUNS.size}`);
+    if (!sessionId.startsWith("probe-")) {
+      diag.info(`run cleared: sessionId=${sessionId} totalActive=${ACTIVE_EMBEDDED_RUNS.size}`);
+    }
     notifyEmbeddedRunEnded(sessionId);
   } else {
     diag.debug(`run clear skipped: sessionId=${sessionId} reason=handle_mismatch`);

src/agents/pi-tools.create-clawdbot-coding-tools.adds-claude-style-aliases-schemas-without-dropping-b.test.ts

@@ -1,5 +1,6 @@
 import { describe, expect, it } from "vitest";
 import type { ClawdbotConfig } from "../config/config.js";
+import "./test-helpers/fast-coding-tools.js";
 import { createClawdbotCodingTools } from "./pi-tools.js";
 
 const defaultTools = createClawdbotCodingTools();

src/agents/pi-tools.create-clawdbot-coding-tools.adds-claude-style-aliases-schemas-without-dropping-d.test.ts

@@ -3,6 +3,7 @@ import os from "node:os";
 import path from "node:path";
 import sharp from "sharp";
 import { describe, expect, it } from "vitest";
+import "./test-helpers/fast-coding-tools.js";
 import { createClawdbotCodingTools } from "./pi-tools.js";
 
 const defaultTools = createClawdbotCodingTools();

src/agents/pi-tools.create-clawdbot-coding-tools.adds-claude-style-aliases-schemas-without-dropping-f.test.ts

@@ -2,6 +2,7 @@ import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
 import { describe, expect, it } from "vitest";
+import "./test-helpers/fast-coding-tools.js";
 import { createClawdbotCodingTools } from "./pi-tools.js";
 
 describe("createClawdbotCodingTools", () => {

src/agents/pi-tools.create-clawdbot-coding-tools.adds-claude-style-aliases-schemas-without-dropping.test.ts

@@ -3,6 +3,7 @@ import os from "node:os";
 import path from "node:path";
 import type { AgentTool } from "@mariozechner/pi-agent-core";
 import { describe, expect, it, vi } from "vitest";
+import "./test-helpers/fast-coding-tools.js";
 import { createClawdbotTools } from "./clawdbot-tools.js";
 import { __testing, createClawdbotCodingTools } from "./pi-tools.js";
 import { createSandboxedReadTool } from "./pi-tools.read.js";

src/agents/session-write-lock.test.ts

@@ -0,0 +1,34 @@
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import { describe, expect, it } from "vitest";
+
+import { acquireSessionWriteLock } from "./session-write-lock.js";
+
+describe("acquireSessionWriteLock", () => {
+  it("reuses locks across symlinked session paths", async () => {
+    if (process.platform === "win32") {
+      expect(true).toBe(true);
+      return;
+    }
+
+    const root = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-lock-"));
+    try {
+      const realDir = path.join(root, "real");
+      const linkDir = path.join(root, "link");
+      await fs.mkdir(realDir, { recursive: true });
+      await fs.symlink(realDir, linkDir);
+
+      const sessionReal = path.join(realDir, "sessions.json");
+      const sessionLink = path.join(linkDir, "sessions.json");
+
+      const lockA = await acquireSessionWriteLock({ sessionFile: sessionReal, timeoutMs: 500 });
+      const lockB = await acquireSessionWriteLock({ sessionFile: sessionLink, timeoutMs: 500 });
+
+      await lockB.release();
+      await lockA.release();
+    } finally {
+      await fs.rm(root, { recursive: true, force: true });
+    }
+  });
+});

src/agents/session-write-lock.ts

@@ -45,20 +45,28 @@ export async function acquireSessionWriteLock(params: {
 }> {
   const timeoutMs = params.timeoutMs ?? 10_000;
   const staleMs = params.staleMs ?? 30 * 60 * 1000;
-  const sessionFile = params.sessionFile;
-  const lockPath = `${sessionFile}.lock`;
-  await fs.mkdir(path.dirname(lockPath), { recursive: true });
+  const sessionFile = path.resolve(params.sessionFile);
+  const sessionDir = path.dirname(sessionFile);
+  await fs.mkdir(sessionDir, { recursive: true });
+  let normalizedDir = sessionDir;
+  try {
+    normalizedDir = await fs.realpath(sessionDir);
+  } catch {
+    // Fall back to the resolved path if realpath fails (permissions, transient FS).
+  }
+  const normalizedSessionFile = path.join(normalizedDir, path.basename(sessionFile));
+  const lockPath = `${normalizedSessionFile}.lock`;
 
-  const held = HELD_LOCKS.get(sessionFile);
+  const held = HELD_LOCKS.get(normalizedSessionFile);
   if (held) {
     held.count += 1;
     return {
       release: async () => {
-        const current = HELD_LOCKS.get(sessionFile);
+        const current = HELD_LOCKS.get(normalizedSessionFile);
         if (!current) return;
         current.count -= 1;
         if (current.count > 0) return;
-        HELD_LOCKS.delete(sessionFile);
+        HELD_LOCKS.delete(normalizedSessionFile);
         await current.handle.close();
         await fs.rm(current.lockPath, { force: true });
       },
@@ -75,14 +83,14 @@ export async function acquireSessionWriteLock(params: {
         JSON.stringify({ pid: process.pid, createdAt: new Date().toISOString() }, null, 2),
         "utf8",
       );
-      HELD_LOCKS.set(sessionFile, { count: 1, handle, lockPath });
+      HELD_LOCKS.set(normalizedSessionFile, { count: 1, handle, lockPath });
       return {
         release: async () => {
-          const current = HELD_LOCKS.get(sessionFile);
+          const current = HELD_LOCKS.get(normalizedSessionFile);
           if (!current) return;
           current.count -= 1;
           if (current.count > 0) return;
-          HELD_LOCKS.delete(sessionFile);
+          HELD_LOCKS.delete(normalizedSessionFile);
           await current.handle.close();
           await fs.rm(current.lockPath, { force: true });
         },

src/agents/test-helpers/fast-coding-tools.ts

@@ -0,0 +1,22 @@
+import { vi } from "vitest";
+
+const stubTool = (name: string) => ({
+  name,
+  description: `${name} stub`,
+  parameters: { type: "object", properties: {} },
+  execute: vi.fn(),
+});
+
+vi.mock("../tools/image-tool.js", () => ({
+  createImageTool: () => stubTool("image"),
+}));
+
+vi.mock("../tools/web-tools.js", () => ({
+  createWebSearchTool: () => null,
+  createWebFetchTool: () => null,
+}));
+
+vi.mock("../../plugins/tools.js", () => ({
+  resolvePluginTools: () => [],
+  getPluginToolMeta: () => undefined,
+}));

src/agents/test-helpers/fast-core-tools.ts

@@ -0,0 +1,30 @@
+import { vi } from "vitest";
+
+const stubTool = (name: string) => ({
+  name,
+  description: `${name} stub`,
+  parameters: { type: "object", properties: {} },
+  execute: vi.fn(),
+});
+
+vi.mock("../tools/browser-tool.js", () => ({
+  createBrowserTool: () => stubTool("browser"),
+}));
+
+vi.mock("../tools/canvas-tool.js", () => ({
+  createCanvasTool: () => stubTool("canvas"),
+}));
+
+vi.mock("../tools/image-tool.js", () => ({
+  createImageTool: () => stubTool("image"),
+}));
+
+vi.mock("../tools/web-tools.js", () => ({
+  createWebSearchTool: () => null,
+  createWebFetchTool: () => null,
+}));
+
+vi.mock("../../plugins/tools.js", () => ({
+  resolvePluginTools: () => [],
+  getPluginToolMeta: () => undefined,
+}));

src/auto-reply/command-auth.test.ts

@@ -1,122 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import type { ClawdbotConfig } from "../config/config.js";
-import { resolveCommandAuthorization } from "./command-auth.js";
-import type { MsgContext } from "./templating.js";
-
-describe("resolveCommandAuthorization", () => {
-  it("falls back from empty SenderId to SenderE164", () => {
-    const cfg = {
-      channels: { whatsapp: { allowFrom: ["+123"] } },
-    } as ClawdbotConfig;
-
-    const ctx = {
-      Provider: "whatsapp",
-      Surface: "whatsapp",
-      From: "whatsapp:+999",
-      SenderId: "",
-      SenderE164: "+123",
-    } as MsgContext;
-
-    const auth = resolveCommandAuthorization({
-      ctx,
-      cfg,
-      commandAuthorized: true,
-    });
-
-    expect(auth.senderId).toBe("+123");
-    expect(auth.isAuthorizedSender).toBe(true);
-  });
-
-  it("falls back from whitespace SenderId to SenderE164", () => {
-    const cfg = {
-      channels: { whatsapp: { allowFrom: ["+123"] } },
-    } as ClawdbotConfig;
-
-    const ctx = {
-      Provider: "whatsapp",
-      Surface: "whatsapp",
-      From: "whatsapp:+999",
-      SenderId: "   ",
-      SenderE164: "+123",
-    } as MsgContext;
-
-    const auth = resolveCommandAuthorization({
-      ctx,
-      cfg,
-      commandAuthorized: true,
-    });
-
-    expect(auth.senderId).toBe("+123");
-    expect(auth.isAuthorizedSender).toBe(true);
-  });
-
-  it("falls back to From when SenderId and SenderE164 are whitespace", () => {
-    const cfg = {
-      channels: { whatsapp: { allowFrom: ["+999"] } },
-    } as ClawdbotConfig;
-
-    const ctx = {
-      Provider: "whatsapp",
-      Surface: "whatsapp",
-      From: "whatsapp:+999",
-      SenderId: "   ",
-      SenderE164: "   ",
-    } as MsgContext;
-
-    const auth = resolveCommandAuthorization({
-      ctx,
-      cfg,
-      commandAuthorized: true,
-    });
-
-    expect(auth.senderId).toBe("+999");
-    expect(auth.isAuthorizedSender).toBe(true);
-  });
-
-  it("falls back from un-normalizable SenderId to SenderE164", () => {
-    const cfg = {
-      channels: { whatsapp: { allowFrom: ["+123"] } },
-    } as ClawdbotConfig;
-
-    const ctx = {
-      Provider: "whatsapp",
-      Surface: "whatsapp",
-      From: "whatsapp:+999",
-      SenderId: "wat",
-      SenderE164: "+123",
-    } as MsgContext;
-
-    const auth = resolveCommandAuthorization({
-      ctx,
-      cfg,
-      commandAuthorized: true,
-    });
-
-    expect(auth.senderId).toBe("+123");
-    expect(auth.isAuthorizedSender).toBe(true);
-  });
-
-  it("prefers SenderE164 when SenderId does not match allowFrom", () => {
-    const cfg = {
-      channels: { whatsapp: { allowFrom: ["+41796666864"] } },
-    } as ClawdbotConfig;
-
-    const ctx = {
-      Provider: "whatsapp",
-      Surface: "whatsapp",
-      From: "whatsapp:120363401234567890@g.us",
-      SenderId: "123@lid",
-      SenderE164: "+41796666864",
-    } as MsgContext;
-
-    const auth = resolveCommandAuthorization({
-      ctx,
-      cfg,
-      commandAuthorized: true,
-    });
-
-    expect(auth.senderId).toBe("+41796666864");
-    expect(auth.isAuthorizedSender).toBe(true);
-  });
-});

src/auto-reply/command-control.test.ts

@@ -1,10 +1,14 @@
 import { afterEach, beforeEach, describe, expect, it } from "vitest";
+
+import type { ClawdbotConfig } from "../config/config.js";
+import { setActivePluginRegistry } from "../plugins/runtime.js";
+import { createTestRegistry } from "../test-utils/channel-plugins.js";
+import { resolveCommandAuthorization } from "./command-auth.js";
 import { hasControlCommand, hasInlineCommandTokens } from "./command-detection.js";
 import { listChatCommands } from "./commands-registry.js";
 import { parseActivationCommand } from "./group-activation.js";
 import { parseSendPolicyCommand } from "./send-policy.js";
-import { setActivePluginRegistry } from "../plugins/runtime.js";
-import { createTestRegistry } from "../test-utils/channel-plugins.js";
+import type { MsgContext } from "./templating.js";
 
 beforeEach(() => {
   setActivePluginRegistry(createTestRegistry([]));
@@ -14,6 +18,123 @@ afterEach(() => {
   setActivePluginRegistry(createTestRegistry([]));
 });
 
+describe("resolveCommandAuthorization", () => {
+  it("falls back from empty SenderId to SenderE164", () => {
+    const cfg = {
+      channels: { whatsapp: { allowFrom: ["+123"] } },
+    } as ClawdbotConfig;
+
+    const ctx = {
+      Provider: "whatsapp",
+      Surface: "whatsapp",
+      From: "whatsapp:+999",
+      SenderId: "",
+      SenderE164: "+123",
+    } as MsgContext;
+
+    const auth = resolveCommandAuthorization({
+      ctx,
+      cfg,
+      commandAuthorized: true,
+    });
+
+    expect(auth.senderId).toBe("+123");
+    expect(auth.isAuthorizedSender).toBe(true);
+  });
+
+  it("falls back from whitespace SenderId to SenderE164", () => {
+    const cfg = {
+      channels: { whatsapp: { allowFrom: ["+123"] } },
+    } as ClawdbotConfig;
+
+    const ctx = {
+      Provider: "whatsapp",
+      Surface: "whatsapp",
+      From: "whatsapp:+999",
+      SenderId: "   ",
+      SenderE164: "+123",
+    } as MsgContext;
+
+    const auth = resolveCommandAuthorization({
+      ctx,
+      cfg,
+      commandAuthorized: true,
+    });
+
+    expect(auth.senderId).toBe("+123");
+    expect(auth.isAuthorizedSender).toBe(true);
+  });
+
+  it("falls back to From when SenderId and SenderE164 are whitespace", () => {
+    const cfg = {
+      channels: { whatsapp: { allowFrom: ["+999"] } },
+    } as ClawdbotConfig;
+
+    const ctx = {
+      Provider: "whatsapp",
+      Surface: "whatsapp",
+      From: "whatsapp:+999",
+      SenderId: "   ",
+      SenderE164: "   ",
+    } as MsgContext;
+
+    const auth = resolveCommandAuthorization({
+      ctx,
+      cfg,
+      commandAuthorized: true,
+    });
+
+    expect(auth.senderId).toBe("+999");
+    expect(auth.isAuthorizedSender).toBe(true);
+  });
+
+  it("falls back from un-normalizable SenderId to SenderE164", () => {
+    const cfg = {
+      channels: { whatsapp: { allowFrom: ["+123"] } },
+    } as ClawdbotConfig;
+
+    const ctx = {
+      Provider: "whatsapp",
+      Surface: "whatsapp",
+      From: "whatsapp:+999",
+      SenderId: "wat",
+      SenderE164: "+123",
+    } as MsgContext;
+
+    const auth = resolveCommandAuthorization({
+      ctx,
+      cfg,
+      commandAuthorized: true,
+    });
+
+    expect(auth.senderId).toBe("+123");
+    expect(auth.isAuthorizedSender).toBe(true);
+  });
+
+  it("prefers SenderE164 when SenderId does not match allowFrom", () => {
+    const cfg = {
+      channels: { whatsapp: { allowFrom: ["+41796666864"] } },
+    } as ClawdbotConfig;
+
+    const ctx = {
+      Provider: "whatsapp",
+      Surface: "whatsapp",
+      From: "whatsapp:120363401234567890@g.us",
+      SenderId: "123@lid",
+      SenderE164: "+41796666864",
+    } as MsgContext;
+
+    const auth = resolveCommandAuthorization({
+      ctx,
+      cfg,
+      commandAuthorized: true,
+    });
+
+    expect(auth.senderId).toBe("+41796666864");
+    expect(auth.isAuthorizedSender).toBe(true);
+  });
+});
+
 describe("control command parsing", () => {
   it("requires slash for send policy", () => {
     expect(parseSendPolicyCommand("/send on")).toEqual({

src/auto-reply/commands-registry.args.test.ts

@@ -1,156 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import {
-  buildCommandTextFromArgs,
-  parseCommandArgs,
-  resolveCommandArgMenu,
-  serializeCommandArgs,
-} from "./commands-registry.js";
-import type { ChatCommandDefinition } from "./commands-registry.types.js";
-
-describe("commands registry args", () => {
-  it("parses positional args and captureRemaining", () => {
-    const command: ChatCommandDefinition = {
-      key: "debug",
-      description: "debug",
-      textAliases: [],
-      scope: "both",
-      argsParsing: "positional",
-      args: [
-        { name: "action", description: "action", type: "string" },
-        { name: "path", description: "path", type: "string" },
-        { name: "value", description: "value", type: "string", captureRemaining: true },
-      ],
-    };
-
-    const args = parseCommandArgs(command, "set foo bar baz");
-    expect(args?.values).toEqual({ action: "set", path: "foo", value: "bar baz" });
-  });
-
-  it("serializes args via raw first, then values", () => {
-    const command: ChatCommandDefinition = {
-      key: "model",
-      description: "model",
-      textAliases: [],
-      scope: "both",
-      argsParsing: "positional",
-      args: [{ name: "model", description: "model", type: "string", captureRemaining: true }],
-    };
-
-    expect(serializeCommandArgs(command, { raw: "gpt-5.2-codex" })).toBe("gpt-5.2-codex");
-    expect(serializeCommandArgs(command, { values: { model: "gpt-5.2-codex" } })).toBe(
-      "gpt-5.2-codex",
-    );
-    expect(buildCommandTextFromArgs(command, { values: { model: "gpt-5.2-codex" } })).toBe(
-      "/model gpt-5.2-codex",
-    );
-  });
-
-  it("resolves auto arg menus when missing a choice arg", () => {
-    const command: ChatCommandDefinition = {
-      key: "usage",
-      description: "usage",
-      textAliases: [],
-      scope: "both",
-      argsMenu: "auto",
-      argsParsing: "positional",
-      args: [
-        {
-          name: "mode",
-          description: "mode",
-          type: "string",
-          choices: ["off", "tokens", "full", "cost"],
-        },
-      ],
-    };
-
-    const menu = resolveCommandArgMenu({ command, args: undefined, cfg: {} as never });
-    expect(menu?.arg.name).toBe("mode");
-    expect(menu?.choices).toEqual(["off", "tokens", "full", "cost"]);
-  });
-
-  it("does not show menus when arg already provided", () => {
-    const command: ChatCommandDefinition = {
-      key: "usage",
-      description: "usage",
-      textAliases: [],
-      scope: "both",
-      argsMenu: "auto",
-      argsParsing: "positional",
-      args: [
-        {
-          name: "mode",
-          description: "mode",
-          type: "string",
-          choices: ["off", "tokens", "full", "cost"],
-        },
-      ],
-    };
-
-    const menu = resolveCommandArgMenu({
-      command,
-      args: { values: { mode: "tokens" } },
-      cfg: {} as never,
-    });
-    expect(menu).toBeNull();
-  });
-
-  it("resolves function-based choices with a default provider/model context", () => {
-    let seen: { provider: string; model: string; commandKey: string; argName: string } | null =
-      null;
-
-    const command: ChatCommandDefinition = {
-      key: "think",
-      description: "think",
-      textAliases: [],
-      scope: "both",
-      argsMenu: "auto",
-      argsParsing: "positional",
-      args: [
-        {
-          name: "level",
-          description: "level",
-          type: "string",
-          choices: ({ provider, model, command, arg }) => {
-            seen = { provider, model, commandKey: command.key, argName: arg.name };
-            return ["low", "high"];
-          },
-        },
-      ],
-    };
-
-    const menu = resolveCommandArgMenu({ command, args: undefined, cfg: {} as never });
-    expect(menu?.arg.name).toBe("level");
-    expect(menu?.choices).toEqual(["low", "high"]);
-    expect(seen?.commandKey).toBe("think");
-    expect(seen?.argName).toBe("level");
-    expect(seen?.provider).toBeTruthy();
-    expect(seen?.model).toBeTruthy();
-  });
-
-  it("does not show menus when args were provided as raw text only", () => {
-    const command: ChatCommandDefinition = {
-      key: "usage",
-      description: "usage",
-      textAliases: [],
-      scope: "both",
-      argsMenu: "auto",
-      argsParsing: "none",
-      args: [
-        {
-          name: "mode",
-          description: "on or off",
-          type: "string",
-          choices: ["off", "tokens", "full", "cost"],
-        },
-      ],
-    };
-
-    const menu = resolveCommandArgMenu({
-      command,
-      args: { raw: "on" },
-      cfg: {} as never,
-    });
-    expect(menu).toBeNull();
-  });
-});

src/auto-reply/commands-registry.test.ts

@@ -2,14 +2,19 @@ import { afterEach, beforeEach, describe, expect, it } from "vitest";
 
 import {
   buildCommandText,
+  buildCommandTextFromArgs,
   getCommandDetection,
   listChatCommands,
   listChatCommandsForConfig,
   listNativeCommandSpecs,
   listNativeCommandSpecsForConfig,
   normalizeCommandBody,
+  parseCommandArgs,
+  resolveCommandArgMenu,
+  serializeCommandArgs,
   shouldHandleTextCommands,
 } from "./commands-registry.js";
+import type { ChatCommandDefinition } from "./commands-registry.types.js";
 import { setActivePluginRegistry } from "../plugins/runtime.js";
 import { createTestRegistry } from "../test-utils/channel-plugins.js";
 
@@ -154,3 +159,150 @@ describe("commands registry", () => {
     expect(normalizeCommandBody("/dock_telegram")).toBe("/dock-telegram");
   });
 });
+
+describe("commands registry args", () => {
+  it("parses positional args and captureRemaining", () => {
+    const command: ChatCommandDefinition = {
+      key: "debug",
+      description: "debug",
+      textAliases: [],
+      scope: "both",
+      argsParsing: "positional",
+      args: [
+        { name: "action", description: "action", type: "string" },
+        { name: "path", description: "path", type: "string" },
+        { name: "value", description: "value", type: "string", captureRemaining: true },
+      ],
+    };
+
+    const args = parseCommandArgs(command, "set foo bar baz");
+    expect(args?.values).toEqual({ action: "set", path: "foo", value: "bar baz" });
+  });
+
+  it("serializes args via raw first, then values", () => {
+    const command: ChatCommandDefinition = {
+      key: "model",
+      description: "model",
+      textAliases: [],
+      scope: "both",
+      argsParsing: "positional",
+      args: [{ name: "model", description: "model", type: "string", captureRemaining: true }],
+    };
+
+    expect(serializeCommandArgs(command, { raw: "gpt-5.2-codex" })).toBe("gpt-5.2-codex");
+    expect(serializeCommandArgs(command, { values: { model: "gpt-5.2-codex" } })).toBe(
+      "gpt-5.2-codex",
+    );
+    expect(buildCommandTextFromArgs(command, { values: { model: "gpt-5.2-codex" } })).toBe(
+      "/model gpt-5.2-codex",
+    );
+  });
+
+  it("resolves auto arg menus when missing a choice arg", () => {
+    const command: ChatCommandDefinition = {
+      key: "usage",
+      description: "usage",
+      textAliases: [],
+      scope: "both",
+      argsMenu: "auto",
+      argsParsing: "positional",
+      args: [
+        {
+          name: "mode",
+          description: "mode",
+          type: "string",
+          choices: ["off", "tokens", "full", "cost"],
+        },
+      ],
+    };
+
+    const menu = resolveCommandArgMenu({ command, args: undefined, cfg: {} as never });
+    expect(menu?.arg.name).toBe("mode");
+    expect(menu?.choices).toEqual(["off", "tokens", "full", "cost"]);
+  });
+
+  it("does not show menus when arg already provided", () => {
+    const command: ChatCommandDefinition = {
+      key: "usage",
+      description: "usage",
+      textAliases: [],
+      scope: "both",
+      argsMenu: "auto",
+      argsParsing: "positional",
+      args: [
+        {
+          name: "mode",
+          description: "mode",
+          type: "string",
+          choices: ["off", "tokens", "full", "cost"],
+        },
+      ],
+    };
+
+    const menu = resolveCommandArgMenu({
+      command,
+      args: { values: { mode: "tokens" } },
+      cfg: {} as never,
+    });
+    expect(menu).toBeNull();
+  });
+
+  it("resolves function-based choices with a default provider/model context", () => {
+    let seen: { provider: string; model: string; commandKey: string; argName: string } | null =
+      null;
+
+    const command: ChatCommandDefinition = {
+      key: "think",
+      description: "think",
+      textAliases: [],
+      scope: "both",
+      argsMenu: "auto",
+      argsParsing: "positional",
+      args: [
+        {
+          name: "level",
+          description: "level",
+          type: "string",
+          choices: ({ provider, model, command, arg }) => {
+            seen = { provider, model, commandKey: command.key, argName: arg.name };
+            return ["low", "high"];
+          },
+        },
+      ],
+    };
+
+    const menu = resolveCommandArgMenu({ command, args: undefined, cfg: {} as never });
+    expect(menu?.arg.name).toBe("level");
+    expect(menu?.choices).toEqual(["low", "high"]);
+    expect(seen?.commandKey).toBe("think");
+    expect(seen?.argName).toBe("level");
+    expect(seen?.provider).toBeTruthy();
+    expect(seen?.model).toBeTruthy();
+  });
+
+  it("does not show menus when args were provided as raw text only", () => {
+    const command: ChatCommandDefinition = {
+      key: "usage",
+      description: "usage",
+      textAliases: [],
+      scope: "both",
+      argsMenu: "auto",
+      argsParsing: "none",
+      args: [
+        {
+          name: "mode",
+          description: "on or off",
+          type: "string",
+          choices: ["off", "tokens", "full", "cost"],
+        },
+      ],
+    };
+
+    const menu = resolveCommandArgMenu({
+      command,
+      args: { raw: "on" },
+      cfg: {} as never,
+    });
+    expect(menu).toBeNull();
+  });
+});

src/auto-reply/heartbeat.test.ts

@@ -1,6 +1,10 @@
 import { describe, expect, it } from "vitest";
 
-import { DEFAULT_HEARTBEAT_ACK_MAX_CHARS, stripHeartbeatToken } from "./heartbeat.js";
+import {
+  DEFAULT_HEARTBEAT_ACK_MAX_CHARS,
+  isHeartbeatContentEffectivelyEmpty,
+  stripHeartbeatToken,
+} from "./heartbeat.js";
 import { HEARTBEAT_TOKEN } from "./tokens.js";
 
 describe("stripHeartbeatToken", () => {
@@ -105,3 +109,76 @@ describe("stripHeartbeatToken", () => {
     });
   });
 });
+
+describe("isHeartbeatContentEffectivelyEmpty", () => {
+  it("returns false for undefined/null (missing file should not skip)", () => {
+    expect(isHeartbeatContentEffectivelyEmpty(undefined)).toBe(false);
+    expect(isHeartbeatContentEffectivelyEmpty(null)).toBe(false);
+  });
+
+  it("returns true for empty string", () => {
+    expect(isHeartbeatContentEffectivelyEmpty("")).toBe(true);
+  });
+
+  it("returns true for whitespace only", () => {
+    expect(isHeartbeatContentEffectivelyEmpty("   ")).toBe(true);
+    expect(isHeartbeatContentEffectivelyEmpty("\n\n\n")).toBe(true);
+    expect(isHeartbeatContentEffectivelyEmpty("  \n  \n  ")).toBe(true);
+    expect(isHeartbeatContentEffectivelyEmpty("\t\t")).toBe(true);
+  });
+
+  it("returns true for header-only content", () => {
+    expect(isHeartbeatContentEffectivelyEmpty("# HEARTBEAT.md")).toBe(true);
+    expect(isHeartbeatContentEffectivelyEmpty("# HEARTBEAT.md\n")).toBe(true);
+    expect(isHeartbeatContentEffectivelyEmpty("# HEARTBEAT.md\n\n")).toBe(true);
+  });
+
+  it("returns true for comments only", () => {
+    expect(isHeartbeatContentEffectivelyEmpty("# Header\n# Another comment")).toBe(true);
+    expect(isHeartbeatContentEffectivelyEmpty("## Subheader\n### Another")).toBe(true);
+  });
+
+  it("returns true for default template content (header + comment)", () => {
+    const defaultTemplate = `# HEARTBEAT.md
+
+Keep this file empty unless you want a tiny checklist. Keep it small.
+`;
+    // Note: The template has actual text content, so it's NOT effectively empty
+    expect(isHeartbeatContentEffectivelyEmpty(defaultTemplate)).toBe(false);
+  });
+
+  it("returns true for header with only empty lines", () => {
+    expect(isHeartbeatContentEffectivelyEmpty("# HEARTBEAT.md\n\n\n")).toBe(true);
+  });
+
+  it("returns false when actionable content exists", () => {
+    expect(isHeartbeatContentEffectivelyEmpty("- Check email")).toBe(false);
+    expect(isHeartbeatContentEffectivelyEmpty("# HEARTBEAT.md\n- Task 1")).toBe(false);
+    expect(isHeartbeatContentEffectivelyEmpty("Remind me to call mom")).toBe(false);
+  });
+
+  it("returns false for content with tasks after header", () => {
+    const content = `# HEARTBEAT.md
+
+- Task 1
+- Task 2
+`;
+    expect(isHeartbeatContentEffectivelyEmpty(content)).toBe(false);
+  });
+
+  it("returns false for mixed content with non-comment text", () => {
+    const content = `# HEARTBEAT.md
+## Tasks
+Check the server logs
+`;
+    expect(isHeartbeatContentEffectivelyEmpty(content)).toBe(false);
+  });
+
+  it("treats markdown headers as comments (effectively empty)", () => {
+    const content = `# HEARTBEAT.md
+## Section 1
+### Subsection
+`;
+    expect(isHeartbeatContentEffectivelyEmpty(content)).toBe(true);
+  });
+});

src/auto-reply/heartbeat.ts

@@ -7,6 +7,38 @@ export const HEARTBEAT_PROMPT =
 export const DEFAULT_HEARTBEAT_EVERY = "30m";
 export const DEFAULT_HEARTBEAT_ACK_MAX_CHARS = 300;
 
+/**
+ * Check if HEARTBEAT.md content is "effectively empty" - meaning it has no actionable tasks.
+ * This allows skipping heartbeat API calls when no tasks are configured.
+ *
+ * A file is considered effectively empty if it contains only:
+ * - Whitespace
+ * - Comment lines (lines starting with #)
+ * - Empty lines
+ *
+ * Note: A missing file returns false (not effectively empty) so the LLM can still
+ * decide what to do. This function is only for when the file exists but has no content.
+ */
+export function isHeartbeatContentEffectivelyEmpty(content: string | undefined | null): boolean {
+  if (content === undefined || content === null) return false;
+  if (typeof content !== "string") return false;
+
+  const lines = content.split("\n");
+  for (const line of lines) {
+    const trimmed = line.trim();
+    // Skip empty lines
+    if (!trimmed) continue;
+    // Skip markdown header lines (# followed by space or EOL, ## etc)
+    // This intentionally does NOT skip lines like "#TODO" or "#hashtag" which might be content
+    // (Those aren't valid markdown headers - ATX headers require space after #)
+    if (/^#+(\s|$)/.test(trimmed)) continue;
+    // Found a non-empty, non-comment line - there's actionable content
+    return false;
+  }
+  // All lines were either empty or comments
+  return true;
+}
+
 export function resolveHeartbeatPrompt(raw?: string): string {
   const trimmed = typeof raw === "string" ? raw.trim() : "";
   return trimmed || HEARTBEAT_PROMPT;

src/auto-reply/inbound-debounce.test.ts

@@ -1,48 +0,0 @@
-import { describe, expect, it, vi } from "vitest";
-
-import { createInboundDebouncer } from "./inbound-debounce.js";
-
-describe("createInboundDebouncer", () => {
-  it("debounces and combines items", async () => {
-    vi.useFakeTimers();
-    const calls: Array<string[]> = [];
-
-    const debouncer = createInboundDebouncer<{ key: string; id: string }>({
-      debounceMs: 10,
-      buildKey: (item) => item.key,
-      onFlush: async (items) => {
-        calls.push(items.map((entry) => entry.id));
-      },
-    });
-
-    await debouncer.enqueue({ key: "a", id: "1" });
-    await debouncer.enqueue({ key: "a", id: "2" });
-
-    expect(calls).toEqual([]);
-    await vi.advanceTimersByTimeAsync(10);
-    expect(calls).toEqual([["1", "2"]]);
-
-    vi.useRealTimers();
-  });
-
-  it("flushes buffered items before non-debounced item", async () => {
-    vi.useFakeTimers();
-    const calls: Array<string[]> = [];
-
-    const debouncer = createInboundDebouncer<{ key: string; id: string; debounce: boolean }>({
-      debounceMs: 50,
-      buildKey: (item) => item.key,
-      shouldDebounce: (item) => item.debounce,
-      onFlush: async (items) => {
-        calls.push(items.map((entry) => entry.id));
-      },
-    });
-
-    await debouncer.enqueue({ key: "a", id: "1", debounce: true });
-    await debouncer.enqueue({ key: "a", id: "2", debounce: false });
-
-    expect(calls).toEqual([["1"], ["2"]]);
-
-    vi.useRealTimers();
-  });
-});

src/auto-reply/inbound.test.ts

@@ -0,0 +1,402 @@
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+
+import { describe, expect, it, vi } from "vitest";
+
+import type { ClawdbotConfig } from "../config/config.js";
+import type { GroupKeyResolution } from "../config/sessions.js";
+import { createInboundDebouncer } from "./inbound-debounce.js";
+import { applyTemplate, type MsgContext, type TemplateContext } from "./templating.js";
+import { finalizeInboundContext } from "./reply/inbound-context.js";
+import {
+  buildInboundDedupeKey,
+  resetInboundDedupe,
+  shouldSkipDuplicateInbound,
+} from "./reply/inbound-dedupe.js";
+import { formatInboundBodyWithSenderMeta } from "./reply/inbound-sender-meta.js";
+import { normalizeInboundTextNewlines } from "./reply/inbound-text.js";
+import { resolveGroupRequireMention } from "./reply/groups.js";
+import {
+  buildMentionRegexes,
+  matchesMentionPatterns,
+  normalizeMentionText,
+} from "./reply/mentions.js";
+import { initSessionState } from "./reply/session.js";
+
+describe("applyTemplate", () => {
+  it("renders primitive values", () => {
+    const ctx = { MessageSid: "sid", IsNewSession: "no" } as TemplateContext;
+    const overrides = ctx as Record<string, unknown>;
+    overrides.MessageSid = 42;
+    overrides.IsNewSession = true;
+
+    expect(applyTemplate("sid={{MessageSid}} new={{IsNewSession}}", ctx)).toBe("sid=42 new=true");
+  });
+
+  it("renders arrays of primitives", () => {
+    const ctx = { MediaPaths: ["a"] } as TemplateContext;
+    (ctx as Record<string, unknown>).MediaPaths = ["a", 2, true, null, { ok: false }];
+
+    expect(applyTemplate("paths={{MediaPaths}}", ctx)).toBe("paths=a,2,true");
+  });
+
+  it("drops object values", () => {
+    const ctx: TemplateContext = { CommandArgs: { raw: "go" } };
+
+    expect(applyTemplate("args={{CommandArgs}}", ctx)).toBe("args=");
+  });
+
+  it("renders missing placeholders as empty", () => {
+    const ctx: TemplateContext = {};
+
+    expect(applyTemplate("missing={{Missing}}", ctx)).toBe("missing=");
+  });
+});
+
+describe("normalizeInboundTextNewlines", () => {
+  it("keeps real newlines", () => {
+    expect(normalizeInboundTextNewlines("a\nb")).toBe("a\nb");
+  });
+
+  it("normalizes CRLF/CR to LF", () => {
+    expect(normalizeInboundTextNewlines("a\r\nb")).toBe("a\nb");
+    expect(normalizeInboundTextNewlines("a\rb")).toBe("a\nb");
+  });
+
+  it("decodes literal \\n to newlines when no real newlines exist", () => {
+    expect(normalizeInboundTextNewlines("a\\nb")).toBe("a\nb");
+  });
+});
+
+describe("finalizeInboundContext", () => {
+  it("fills BodyForAgent/BodyForCommands and normalizes newlines", () => {
+    const ctx: MsgContext = {
+      Body: "a\\nb\r\nc",
+      RawBody: "raw\\nline",
+      ChatType: "channel",
+      From: "whatsapp:group:123@g.us",
+      GroupSubject: "Test",
+    };
+
+    const out = finalizeInboundContext(ctx);
+    expect(out.Body).toBe("a\nb\nc");
+    expect(out.RawBody).toBe("raw\nline");
+    expect(out.BodyForAgent).toBe("a\nb\nc");
+    expect(out.BodyForCommands).toBe("raw\nline");
+    expect(out.CommandAuthorized).toBe(false);
+    expect(out.ChatType).toBe("channel");
+    expect(out.ConversationLabel).toContain("Test");
+  });
+
+  it("can force BodyForCommands to follow updated CommandBody", () => {
+    const ctx: MsgContext = {
+      Body: "base",
+      BodyForCommands: "<media:audio>",
+      CommandBody: "say hi",
+      From: "signal:+15550001111",
+      ChatType: "direct",
+    };
+
+    finalizeInboundContext(ctx, { forceBodyForCommands: true });
+    expect(ctx.BodyForCommands).toBe("say hi");
+  });
+});
+
+describe("formatInboundBodyWithSenderMeta", () => {
+  it("does nothing for direct messages", () => {
+    const ctx: MsgContext = { ChatType: "direct", SenderName: "Alice", SenderId: "A1" };
+    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] hi" })).toBe("[X] hi");
+  });
+
+  it("appends a sender meta line for non-direct messages", () => {
+    const ctx: MsgContext = { ChatType: "group", SenderName: "Alice", SenderId: "A1" };
+    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] hi" })).toBe(
+      "[X] hi\n[from: Alice (A1)]",
+    );
+  });
+
+  it("prefers SenderE164 in the label when present", () => {
+    const ctx: MsgContext = {
+      ChatType: "group",
+      SenderName: "Bob",
+      SenderId: "bob@s.whatsapp.net",
+      SenderE164: "+222",
+    };
+    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] hi" })).toBe(
+      "[X] hi\n[from: Bob (+222)]",
+    );
+  });
+
+  it("appends with a real newline even if the body contains literal \\n", () => {
+    const ctx: MsgContext = { ChatType: "group", SenderName: "Bob", SenderId: "+222" };
+    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] one\\n[X] two" })).toBe(
+      "[X] one\\n[X] two\n[from: Bob (+222)]",
+    );
+  });
+
+  it("does not duplicate a sender meta line when one is already present", () => {
+    const ctx: MsgContext = { ChatType: "group", SenderName: "Alice", SenderId: "A1" };
+    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] hi\n[from: Alice (A1)]" })).toBe(
+      "[X] hi\n[from: Alice (A1)]",
+    );
+  });
+
+  it("does not append when the body already includes a sender prefix", () => {
+    const ctx: MsgContext = { ChatType: "group", SenderName: "Alice", SenderId: "A1" };
+    expect(formatInboundBodyWithSenderMeta({ ctx, body: "Alice (A1): hi" })).toBe("Alice (A1): hi");
+  });
+
+  it("does not append when the sender prefix follows an envelope header", () => {
+    const ctx: MsgContext = { ChatType: "group", SenderName: "Alice", SenderId: "A1" };
+    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[Signal Group] Alice (A1): hi" })).toBe(
+      "[Signal Group] Alice (A1): hi",
+    );
+  });
+});
+
+describe("inbound dedupe", () => {
+  it("builds a stable key when MessageSid is present", () => {
+    const ctx: MsgContext = {
+      Provider: "telegram",
+      OriginatingChannel: "telegram",
+      OriginatingTo: "telegram:123",
+      MessageSid: "42",
+    };
+    expect(buildInboundDedupeKey(ctx)).toBe("telegram|telegram:123|42");
+  });
+
+  it("skips duplicates with the same key", () => {
+    resetInboundDedupe();
+    const ctx: MsgContext = {
+      Provider: "whatsapp",
+      OriginatingChannel: "whatsapp",
+      OriginatingTo: "whatsapp:+1555",
+      MessageSid: "msg-1",
+    };
+    expect(shouldSkipDuplicateInbound(ctx, { now: 100 })).toBe(false);
+    expect(shouldSkipDuplicateInbound(ctx, { now: 200 })).toBe(true);
+  });
+
+  it("does not dedupe when the peer changes", () => {
+    resetInboundDedupe();
+    const base: MsgContext = {
+      Provider: "whatsapp",
+      OriginatingChannel: "whatsapp",
+      MessageSid: "msg-1",
+    };
+    expect(
+      shouldSkipDuplicateInbound({ ...base, OriginatingTo: "whatsapp:+1000" }, { now: 100 }),
+    ).toBe(false);
+    expect(
+      shouldSkipDuplicateInbound({ ...base, OriginatingTo: "whatsapp:+2000" }, { now: 200 }),
+    ).toBe(false);
+  });
+
+  it("does not dedupe across session keys", () => {
+    resetInboundDedupe();
+    const base: MsgContext = {
+      Provider: "whatsapp",
+      OriginatingChannel: "whatsapp",
+      OriginatingTo: "whatsapp:+1555",
+      MessageSid: "msg-1",
+    };
+    expect(
+      shouldSkipDuplicateInbound({ ...base, SessionKey: "agent:alpha:main" }, { now: 100 }),
+    ).toBe(false);
+    expect(
+      shouldSkipDuplicateInbound({ ...base, SessionKey: "agent:bravo:main" }, { now: 200 }),
+    ).toBe(false);
+    expect(
+      shouldSkipDuplicateInbound({ ...base, SessionKey: "agent:alpha:main" }, { now: 300 }),
+    ).toBe(true);
+  });
+});
+
+describe("createInboundDebouncer", () => {
+  it("debounces and combines items", async () => {
+    vi.useFakeTimers();
+    const calls: Array<string[]> = [];
+
+    const debouncer = createInboundDebouncer<{ key: string; id: string }>({
+      debounceMs: 10,
+      buildKey: (item) => item.key,
+      onFlush: async (items) => {
+        calls.push(items.map((entry) => entry.id));
+      },
+    });
+
+    await debouncer.enqueue({ key: "a", id: "1" });
+    await debouncer.enqueue({ key: "a", id: "2" });
+
+    expect(calls).toEqual([]);
+    await vi.advanceTimersByTimeAsync(10);
+    expect(calls).toEqual([["1", "2"]]);
+
+    vi.useRealTimers();
+  });
+
+  it("flushes buffered items before non-debounced item", async () => {
+    vi.useFakeTimers();
+    const calls: Array<string[]> = [];
+
+    const debouncer = createInboundDebouncer<{ key: string; id: string; debounce: boolean }>({
+      debounceMs: 50,
+      buildKey: (item) => item.key,
+      shouldDebounce: (item) => item.debounce,
+      onFlush: async (items) => {
+        calls.push(items.map((entry) => entry.id));
+      },
+    });
+
+    await debouncer.enqueue({ key: "a", id: "1", debounce: true });
+    await debouncer.enqueue({ key: "a", id: "2", debounce: false });
+
+    expect(calls).toEqual([["1"], ["2"]]);
+
+    vi.useRealTimers();
+  });
+});
+
+describe("initSessionState sender meta", () => {
+  it("injects sender meta into BodyStripped for group chats", async () => {
+    const root = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-sender-meta-"));
+    const storePath = path.join(root, "sessions.json");
+    const cfg = { session: { store: storePath } } as ClawdbotConfig;
+
+    const result = await initSessionState({
+      ctx: {
+        Body: "[WhatsApp 123@g.us] ping",
+        ChatType: "group",
+        SenderName: "Bob",
+        SenderE164: "+222",
+        SenderId: "222@s.whatsapp.net",
+        SessionKey: "agent:main:whatsapp:group:123@g.us",
+      },
+      cfg,
+      commandAuthorized: true,
+    });
+
+    expect(result.sessionCtx.BodyStripped).toBe("[WhatsApp 123@g.us] ping\n[from: Bob (+222)]");
+  });
+
+  it("does not inject sender meta for direct chats", async () => {
+    const root = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-sender-meta-direct-"));
+    const storePath = path.join(root, "sessions.json");
+    const cfg = { session: { store: storePath } } as ClawdbotConfig;
+
+    const result = await initSessionState({
+      ctx: {
+        Body: "[WhatsApp +1] ping",
+        ChatType: "direct",
+        SenderName: "Bob",
+        SenderE164: "+222",
+        SessionKey: "agent:main:whatsapp:dm:+222",
+      },
+      cfg,
+      commandAuthorized: true,
+    });
+
+    expect(result.sessionCtx.BodyStripped).toBe("[WhatsApp +1] ping");
+  });
+});
+
+describe("mention helpers", () => {
+  it("builds regexes and skips invalid patterns", () => {
+    const regexes = buildMentionRegexes({
+      messages: {
+        groupChat: { mentionPatterns: ["\\bclawd\\b", "(invalid"] },
+      },
+    });
+    expect(regexes).toHaveLength(1);
+    expect(regexes[0]?.test("clawd")).toBe(true);
+  });
+
+  it("normalizes zero-width characters", () => {
+    expect(normalizeMentionText("cl\u200bawd")).toBe("clawd");
+  });
+
+  it("matches patterns case-insensitively", () => {
+    const regexes = buildMentionRegexes({
+      messages: { groupChat: { mentionPatterns: ["\\bclawd\\b"] } },
+    });
+    expect(matchesMentionPatterns("CLAWD: hi", regexes)).toBe(true);
+  });
+
+  it("uses per-agent mention patterns when configured", () => {
+    const regexes = buildMentionRegexes(
+      {
+        messages: {
+          groupChat: { mentionPatterns: ["\\bglobal\\b"] },
+        },
+        agents: {
+          list: [
+            {
+              id: "work",
+              groupChat: { mentionPatterns: ["\\bworkbot\\b"] },
+            },
+          ],
+        },
+      },
+      "work",
+    );
+    expect(matchesMentionPatterns("workbot: hi", regexes)).toBe(true);
+    expect(matchesMentionPatterns("global: hi", regexes)).toBe(false);
+  });
+});
+
+describe("resolveGroupRequireMention", () => {
+  it("respects Discord guild/channel requireMention settings", () => {
+    const cfg: ClawdbotConfig = {
+      channels: {
+        discord: {
+          guilds: {
+            "145": {
+              requireMention: false,
+              channels: {
+                general: { allow: true },
+              },
+            },
+          },
+        },
+      },
+    };
+    const ctx: TemplateContext = {
+      Provider: "discord",
+      From: "discord:group:123",
+      GroupChannel: "#general",
+      GroupSpace: "145",
+    };
+    const groupResolution: GroupKeyResolution = {
+      channel: "discord",
+      id: "123",
+      chatType: "group",
+    };
+
+    expect(resolveGroupRequireMention({ cfg, ctx, groupResolution })).toBe(false);
+  });
+
+  it("respects Slack channel requireMention settings", () => {
+    const cfg: ClawdbotConfig = {
+      channels: {
+        slack: {
+          channels: {
+            C123: { requireMention: false },
+          },
+        },
+      },
+    };
+    const ctx: TemplateContext = {
+      Provider: "slack",
+      From: "slack:channel:C123",
+      GroupSubject: "#general",
+    };
+    const groupResolution: GroupKeyResolution = {
+      channel: "slack",
+      id: "C123",
+      chatType: "group",
+    };
+
+    expect(resolveGroupRequireMention({ cfg, ctx, groupResolution })).toBe(false);
+  });
+});

src/auto-reply/reply.triggers.trigger-handling.stages-inbound-media-into-sandbox-workspace.test.ts

@@ -2,174 +2,79 @@ import fs from "node:fs/promises";
 import { basename, join } from "node:path";
 import { afterEach, describe, expect, it, vi } from "vitest";
 import { withTempHome as withTempHomeBase } from "../../test/helpers/temp-home.js";
+import type { MsgContext, TemplateContext } from "./templating.js";
 
-vi.mock("../agents/pi-embedded.js", () => ({
-  abortEmbeddedPiRun: vi.fn().mockReturnValue(false),
-  compactEmbeddedPiSession: vi.fn(),
-  runEmbeddedPiAgent: vi.fn(),
-  queueEmbeddedPiMessage: vi.fn().mockReturnValue(false),
-  resolveEmbeddedSessionLane: (key: string) => `session:${key.trim() || "main"}`,
-  isEmbeddedPiRunActive: vi.fn().mockReturnValue(false),
-  isEmbeddedPiRunStreaming: vi.fn().mockReturnValue(false),
+const sandboxMocks = vi.hoisted(() => ({
+  ensureSandboxWorkspaceForSession: vi.fn(),
 }));
 
-const usageMocks = vi.hoisted(() => ({
-  loadProviderUsageSummary: vi.fn().mockResolvedValue({
-    updatedAt: 0,
-    providers: [],
-  }),
-  formatUsageSummaryLine: vi.fn().mockReturnValue("📊 Usage: Claude 80% left"),
-  resolveUsageProviderId: vi.fn((provider: string) => provider.split("/")[0]),
-}));
+vi.mock("../agents/sandbox.js", () => sandboxMocks);
 
-vi.mock("../infra/provider-usage.js", () => usageMocks);
-
-const modelCatalogMocks = vi.hoisted(() => ({
-  loadModelCatalog: vi.fn().mockResolvedValue([
-    {
-      provider: "anthropic",
-      id: "claude-opus-4-5",
-      name: "Claude Opus 4.5",
-      contextWindow: 200000,
-    },
-    {
-      provider: "openrouter",
-      id: "anthropic/claude-opus-4-5",
-      name: "Claude Opus 4.5 (OpenRouter)",
-      contextWindow: 200000,
-    },
-    { provider: "openai", id: "gpt-4.1-mini", name: "GPT-4.1 mini" },
-    { provider: "openai", id: "gpt-5.2", name: "GPT-5.2" },
-    { provider: "openai-codex", id: "gpt-5.2", name: "GPT-5.2 (Codex)" },
-    { provider: "minimax", id: "MiniMax-M2.1", name: "MiniMax M2.1" },
-  ]),
-  resetModelCatalogCacheForTest: vi.fn(),
-}));
-
-vi.mock("../agents/model-catalog.js", () => modelCatalogMocks);
-
-import { resolveAgentWorkspaceDir } from "../agents/agent-scope.js";
-import { abortEmbeddedPiRun, runEmbeddedPiAgent } from "../agents/pi-embedded.js";
 import { ensureSandboxWorkspaceForSession } from "../agents/sandbox.js";
-import { resolveAgentIdFromSessionKey, resolveSessionKey } from "../config/sessions.js";
-import { getReplyFromConfig } from "./reply.js";
-
-const _MAIN_SESSION_KEY = "agent:main:main";
-
-const webMocks = vi.hoisted(() => ({
-  webAuthExists: vi.fn().mockResolvedValue(true),
-  getWebAuthAgeMs: vi.fn().mockReturnValue(120_000),
-  readWebSelfId: vi.fn().mockReturnValue({ e164: "+1999" }),
-}));
-
-vi.mock("../web/session.js", () => webMocks);
+import { stageSandboxMedia } from "./reply/stage-sandbox-media.js";
 
 async function withTempHome<T>(fn: (home: string) => Promise<T>): Promise<T> {
-  return withTempHomeBase(
-    async (home) => {
-      vi.mocked(runEmbeddedPiAgent).mockClear();
-      vi.mocked(abortEmbeddedPiRun).mockClear();
-      return await fn(home);
-    },
-    { prefix: "clawdbot-triggers-" },
-  );
-}
-
-function _makeCfg(home: string) {
-  return {
-    agents: {
-      defaults: {
-        model: "anthropic/claude-opus-4-5",
-        workspace: join(home, "clawd"),
-      },
-    },
-    channels: {
-      whatsapp: {
-        allowFrom: ["*"],
-      },
-    },
-    session: { store: join(home, "sessions.json") },
-  };
+  return withTempHomeBase(async (home) => await fn(home), { prefix: "clawdbot-triggers-" });
 }
 
 afterEach(() => {
   vi.restoreAllMocks();
 });
 
-describe("trigger handling", () => {
-  it("stages inbound media into the sandbox workspace", { timeout: 60_000 }, async () => {
+describe("stageSandboxMedia", () => {
+  it("stages inbound media into the sandbox workspace", async () => {
     await withTempHome(async (home) => {
       const inboundDir = join(home, ".clawdbot", "media", "inbound");
       await fs.mkdir(inboundDir, { recursive: true });
       const mediaPath = join(inboundDir, "photo.jpg");
       await fs.writeFile(mediaPath, "test");
 
-      vi.mocked(runEmbeddedPiAgent).mockResolvedValue({
-        payloads: [{ text: "ok" }],
-        meta: {
-          durationMs: 1,
-          agentMeta: { sessionId: "s", provider: "p", model: "m" },
-        },
+      const sandboxDir = join(home, "sandboxes", "session");
+      vi.mocked(ensureSandboxWorkspaceForSession).mockResolvedValue({
+        workspaceDir: sandboxDir,
+        containerWorkdir: "/work",
       });
 
-      const cfg = {
-        agents: {
-          defaults: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: join(home, "clawd"),
-            sandbox: {
-              mode: "non-main" as const,
-              workspaceRoot: join(home, "sandboxes"),
-            },
-          },
-        },
-        channels: {
-          whatsapp: {
-            allowFrom: ["*"],
-          },
-        },
-        session: {
-          store: join(home, "sessions.json"),
-        },
-      };
-
-      const ctx = {
+      const ctx: MsgContext = {
         Body: "hi",
         From: "whatsapp:group:demo",
         To: "+2000",
-        ChatType: "group" as const,
-        Provider: "whatsapp" as const,
+        ChatType: "group",
+        Provider: "whatsapp",
         MediaPath: mediaPath,
         MediaType: "image/jpeg",
         MediaUrl: mediaPath,
       };
+      const sessionCtx: TemplateContext = { ...ctx };
 
-      const res = await getReplyFromConfig(ctx, {}, cfg);
-      const text = Array.isArray(res) ? res[0]?.text : res?.text;
-      expect(text).toBe("ok");
-      expect(runEmbeddedPiAgent).toHaveBeenCalledOnce();
-
-      const prompt = vi.mocked(runEmbeddedPiAgent).mock.calls[0]?.[0]?.prompt ?? "";
-      const stagedPath = `media/inbound/${basename(mediaPath)}`;
-      expect(prompt).toContain(stagedPath);
-      expect(prompt).not.toContain(mediaPath);
-
-      const sessionKey = resolveSessionKey(
-        cfg.session?.scope ?? "per-sender",
+      await stageSandboxMedia({
         ctx,
-        cfg.session?.mainKey,
-      );
-      const agentId = resolveAgentIdFromSessionKey(sessionKey);
-      const sandbox = await ensureSandboxWorkspaceForSession({
-        config: cfg,
-        sessionKey,
-        workspaceDir: resolveAgentWorkspaceDir(cfg, agentId),
+        sessionCtx,
+        cfg: {
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: join(home, "clawd"),
+              sandbox: {
+                mode: "non-main",
+                workspaceRoot: join(home, "sandboxes"),
+              },
+            },
+          },
+          channels: { whatsapp: { allowFrom: ["*"] } },
+          session: { store: join(home, "sessions.json") },
+        },
+        sessionKey: "agent:main:main",
+        workspaceDir: join(home, "clawd"),
       });
-      expect(sandbox).not.toBeNull();
-      if (!sandbox) {
-        throw new Error("Expected sandbox to be set");
-      }
-      const stagedFullPath = join(sandbox.workspaceDir, "media", "inbound", basename(mediaPath));
+
+      const stagedPath = `media/inbound/${basename(mediaPath)}`;
+      expect(ctx.MediaPath).toBe(stagedPath);
+      expect(sessionCtx.MediaPath).toBe(stagedPath);
+      expect(ctx.MediaUrl).toBe(stagedPath);
+      expect(sessionCtx.MediaUrl).toBe(stagedPath);
+
+      const stagedFullPath = join(sandboxDir, "media", "inbound", basename(mediaPath));
       await expect(fs.stat(stagedFullPath)).resolves.toBeTruthy();
     });
   });

src/auto-reply/reply/audio-tags.test.ts

@@ -1,25 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import { parseAudioTag } from "./audio-tags.js";
-
-describe("parseAudioTag", () => {
-  it("detects audio_as_voice and strips the tag", () => {
-    const result = parseAudioTag("Hello [[audio_as_voice]] world");
-    expect(result.audioAsVoice).toBe(true);
-    expect(result.hadTag).toBe(true);
-    expect(result.text).toBe("Hello world");
-  });
-
-  it("returns empty output for missing text", () => {
-    const result = parseAudioTag(undefined);
-    expect(result.audioAsVoice).toBe(false);
-    expect(result.hadTag).toBe(false);
-    expect(result.text).toBe("");
-  });
-
-  it("removes tag-only messages", () => {
-    const result = parseAudioTag("[[audio_as_voice]]");
-    expect(result.audioAsVoice).toBe(true);
-    expect(result.text).toBe("");
-  });
-});

src/auto-reply/reply/block-reply-coalescer.test.ts

@@ -1,71 +0,0 @@
-import { afterEach, describe, expect, it, vi } from "vitest";
-import { createBlockReplyCoalescer } from "./block-reply-coalescer.js";
-
-describe("block reply coalescer", () => {
-  afterEach(() => {
-    vi.useRealTimers();
-  });
-
-  it("coalesces chunks within the idle window", async () => {
-    vi.useFakeTimers();
-    const flushes: string[] = [];
-    const coalescer = createBlockReplyCoalescer({
-      config: { minChars: 1, maxChars: 200, idleMs: 100, joiner: " " },
-      shouldAbort: () => false,
-      onFlush: (payload) => {
-        flushes.push(payload.text ?? "");
-      },
-    });
-
-    coalescer.enqueue({ text: "Hello" });
-    coalescer.enqueue({ text: "world" });
-
-    await vi.advanceTimersByTimeAsync(100);
-    expect(flushes).toEqual(["Hello world"]);
-    coalescer.stop();
-  });
-
-  it("waits until minChars before idle flush", async () => {
-    vi.useFakeTimers();
-    const flushes: string[] = [];
-    const coalescer = createBlockReplyCoalescer({
-      config: { minChars: 10, maxChars: 200, idleMs: 50, joiner: " " },
-      shouldAbort: () => false,
-      onFlush: (payload) => {
-        flushes.push(payload.text ?? "");
-      },
-    });
-
-    coalescer.enqueue({ text: "short" });
-    await vi.advanceTimersByTimeAsync(50);
-    expect(flushes).toEqual([]);
-
-    coalescer.enqueue({ text: "message" });
-    await vi.advanceTimersByTimeAsync(50);
-    expect(flushes).toEqual(["short message"]);
-    coalescer.stop();
-  });
-
-  it("flushes buffered text before media payloads", () => {
-    const flushes: Array<{ text?: string; mediaUrls?: string[] }> = [];
-    const coalescer = createBlockReplyCoalescer({
-      config: { minChars: 1, maxChars: 200, idleMs: 0, joiner: " " },
-      shouldAbort: () => false,
-      onFlush: (payload) => {
-        flushes.push({
-          text: payload.text,
-          mediaUrls: payload.mediaUrls,
-        });
-      },
-    });
-
-    coalescer.enqueue({ text: "Hello" });
-    coalescer.enqueue({ text: "world" });
-    coalescer.enqueue({ mediaUrls: ["https://example.com/a.png"] });
-    void coalescer.flush({ force: true });
-
-    expect(flushes[0].text).toBe("Hello world");
-    expect(flushes[1].mediaUrls).toEqual(["https://example.com/a.png"]);
-    coalescer.stop();
-  });
-});

src/auto-reply/reply/commands-allowlist.test.ts

@@ -1,139 +0,0 @@
-import { describe, expect, it, vi } from "vitest";
-
-import type { ClawdbotConfig } from "../../config/config.js";
-import type { MsgContext } from "../templating.js";
-import { buildCommandContext, handleCommands } from "./commands.js";
-import { parseInlineDirectives } from "./directive-handling.js";
-
-const readConfigFileSnapshotMock = vi.hoisted(() => vi.fn());
-const validateConfigObjectWithPluginsMock = vi.hoisted(() => vi.fn());
-const writeConfigFileMock = vi.hoisted(() => vi.fn());
-
-vi.mock("../../config/config.js", async () => {
-  const actual =
-    await vi.importActual<typeof import("../../config/config.js")>("../../config/config.js");
-  return {
-    ...actual,
-    readConfigFileSnapshot: readConfigFileSnapshotMock,
-    validateConfigObjectWithPlugins: validateConfigObjectWithPluginsMock,
-    writeConfigFile: writeConfigFileMock,
-  };
-});
-
-const readChannelAllowFromStoreMock = vi.hoisted(() => vi.fn());
-const addChannelAllowFromStoreEntryMock = vi.hoisted(() => vi.fn());
-const removeChannelAllowFromStoreEntryMock = vi.hoisted(() => vi.fn());
-
-vi.mock("../../pairing/pairing-store.js", async () => {
-  const actual = await vi.importActual<typeof import("../../pairing/pairing-store.js")>(
-    "../../pairing/pairing-store.js",
-  );
-  return {
-    ...actual,
-    readChannelAllowFromStore: readChannelAllowFromStoreMock,
-    addChannelAllowFromStoreEntry: addChannelAllowFromStoreEntryMock,
-    removeChannelAllowFromStoreEntry: removeChannelAllowFromStoreEntryMock,
-  };
-});
-
-vi.mock("../../channels/plugins/pairing.js", async () => {
-  const actual = await vi.importActual<typeof import("../../channels/plugins/pairing.js")>(
-    "../../channels/plugins/pairing.js",
-  );
-  return {
-    ...actual,
-    listPairingChannels: () => ["telegram"],
-  };
-});
-
-function buildParams(commandBody: string, cfg: ClawdbotConfig, ctxOverrides?: Partial<MsgContext>) {
-  const ctx = {
-    Body: commandBody,
-    CommandBody: commandBody,
-    CommandSource: "text",
-    CommandAuthorized: true,
-    Provider: "telegram",
-    Surface: "telegram",
-    ...ctxOverrides,
-  } as MsgContext;
-
-  const command = buildCommandContext({
-    ctx,
-    cfg,
-    isGroup: false,
-    triggerBodyNormalized: commandBody.trim().toLowerCase(),
-    commandAuthorized: true,
-  });
-
-  return {
-    ctx,
-    cfg,
-    command,
-    directives: parseInlineDirectives(commandBody),
-    elevated: { enabled: true, allowed: true, failures: [] },
-    sessionKey: "agent:main:main",
-    workspaceDir: "/tmp",
-    defaultGroupActivation: () => "mention",
-    resolvedVerboseLevel: "off" as const,
-    resolvedReasoningLevel: "off" as const,
-    resolveDefaultThinkingLevel: async () => undefined,
-    provider: "telegram",
-    model: "test-model",
-    contextTokens: 0,
-    isGroup: false,
-  };
-}
-
-describe("handleCommands /allowlist", () => {
-  it("lists config + store allowFrom entries", async () => {
-    readChannelAllowFromStoreMock.mockResolvedValueOnce(["456"]);
-
-    const cfg = {
-      commands: { text: true },
-      channels: { telegram: { allowFrom: ["123", "@Alice"] } },
-    } as ClawdbotConfig;
-    const params = buildParams("/allowlist list dm", cfg);
-    const result = await handleCommands(params);
-
-    expect(result.shouldContinue).toBe(false);
-    expect(result.reply?.text).toContain("Channel: telegram");
-    expect(result.reply?.text).toContain("DM allowFrom (config): 123, @alice");
-    expect(result.reply?.text).toContain("Paired allowFrom (store): 456");
-  });
-
-  it("adds entries to config and pairing store", async () => {
-    readConfigFileSnapshotMock.mockResolvedValueOnce({
-      valid: true,
-      parsed: {
-        channels: { telegram: { allowFrom: ["123"] } },
-      },
-    });
-    validateConfigObjectWithPluginsMock.mockImplementation((config: unknown) => ({
-      ok: true,
-      config,
-    }));
-    addChannelAllowFromStoreEntryMock.mockResolvedValueOnce({
-      changed: true,
-      allowFrom: ["123", "789"],
-    });
-
-    const cfg = {
-      commands: { text: true, config: true },
-      channels: { telegram: { allowFrom: ["123"] } },
-    } as ClawdbotConfig;
-    const params = buildParams("/allowlist add dm 789", cfg);
-    const result = await handleCommands(params);
-
-    expect(result.shouldContinue).toBe(false);
-    expect(writeConfigFileMock).toHaveBeenCalledWith(
-      expect.objectContaining({
-        channels: { telegram: { allowFrom: ["123", "789"] } },
-      }),
-    );
-    expect(addChannelAllowFromStoreEntryMock).toHaveBeenCalledWith({
-      channel: "telegram",
-      entry: "789",
-    });
-    expect(result.reply?.text).toContain("DM allowlist added");
-  });
-});

src/auto-reply/reply/commands-config-writes.test.ts

@@ -1,57 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import type { ClawdbotConfig } from "../../config/config.js";
-import type { MsgContext } from "../templating.js";
-import { buildCommandContext, handleCommands } from "./commands.js";
-import { parseInlineDirectives } from "./directive-handling.js";
-
-function buildParams(commandBody: string, cfg: ClawdbotConfig, ctxOverrides?: Partial<MsgContext>) {
-  const ctx = {
-    Body: commandBody,
-    CommandBody: commandBody,
-    CommandSource: "text",
-    CommandAuthorized: true,
-    Provider: "whatsapp",
-    Surface: "whatsapp",
-    ...ctxOverrides,
-  } as MsgContext;
-
-  const command = buildCommandContext({
-    ctx,
-    cfg,
-    isGroup: false,
-    triggerBodyNormalized: commandBody.trim().toLowerCase(),
-    commandAuthorized: true,
-  });
-
-  return {
-    ctx,
-    cfg,
-    command,
-    directives: parseInlineDirectives(commandBody),
-    elevated: { enabled: true, allowed: true, failures: [] },
-    sessionKey: "agent:main:main",
-    workspaceDir: "/tmp",
-    defaultGroupActivation: () => "mention",
-    resolvedVerboseLevel: "off" as const,
-    resolvedReasoningLevel: "off" as const,
-    resolveDefaultThinkingLevel: async () => undefined,
-    provider: "whatsapp",
-    model: "test-model",
-    contextTokens: 0,
-    isGroup: false,
-  };
-}
-
-describe("handleCommands /config configWrites gating", () => {
-  it("blocks /config set when channel config writes are disabled", async () => {
-    const cfg = {
-      commands: { config: true, text: true },
-      channels: { whatsapp: { allowFrom: ["*"], configWrites: false } },
-    } as ClawdbotConfig;
-    const params = buildParams('/config set messages.ackReaction=":)"', cfg);
-    const result = await handleCommands(params);
-    expect(result.shouldContinue).toBe(false);
-    expect(result.reply?.text).toContain("Config writes are disabled");
-  });
-});

src/auto-reply/reply/commands-parsing.test.ts

@@ -0,0 +1,125 @@
+import { describe, expect, it } from "vitest";
+
+import type { ClawdbotConfig } from "../../config/config.js";
+import type { MsgContext } from "../templating.js";
+import { buildCommandContext, handleCommands } from "./commands.js";
+import { extractMessageText } from "./commands-subagents.js";
+import { parseConfigCommand } from "./config-commands.js";
+import { parseDebugCommand } from "./debug-commands.js";
+import { parseInlineDirectives } from "./directive-handling.js";
+
+function buildParams(commandBody: string, cfg: ClawdbotConfig, ctxOverrides?: Partial<MsgContext>) {
+  const ctx = {
+    Body: commandBody,
+    CommandBody: commandBody,
+    CommandSource: "text",
+    CommandAuthorized: true,
+    Provider: "whatsapp",
+    Surface: "whatsapp",
+    ...ctxOverrides,
+  } as MsgContext;
+
+  const command = buildCommandContext({
+    ctx,
+    cfg,
+    isGroup: false,
+    triggerBodyNormalized: commandBody.trim().toLowerCase(),
+    commandAuthorized: true,
+  });
+
+  return {
+    ctx,
+    cfg,
+    command,
+    directives: parseInlineDirectives(commandBody),
+    elevated: { enabled: true, allowed: true, failures: [] },
+    sessionKey: "agent:main:main",
+    workspaceDir: "/tmp",
+    defaultGroupActivation: () => "mention",
+    resolvedVerboseLevel: "off" as const,
+    resolvedReasoningLevel: "off" as const,
+    resolveDefaultThinkingLevel: async () => undefined,
+    provider: "whatsapp",
+    model: "test-model",
+    contextTokens: 0,
+    isGroup: false,
+  };
+}
+
+describe("parseConfigCommand", () => {
+  it("parses show/unset", () => {
+    expect(parseConfigCommand("/config")).toEqual({ action: "show" });
+    expect(parseConfigCommand("/config show")).toEqual({
+      action: "show",
+      path: undefined,
+    });
+    expect(parseConfigCommand("/config show foo.bar")).toEqual({
+      action: "show",
+      path: "foo.bar",
+    });
+    expect(parseConfigCommand("/config get foo.bar")).toEqual({
+      action: "show",
+      path: "foo.bar",
+    });
+    expect(parseConfigCommand("/config unset foo.bar")).toEqual({
+      action: "unset",
+      path: "foo.bar",
+    });
+  });
+
+  it("parses set with JSON", () => {
+    const cmd = parseConfigCommand('/config set foo={"a":1}');
+    expect(cmd).toEqual({ action: "set", path: "foo", value: { a: 1 } });
+  });
+});
+
+describe("parseDebugCommand", () => {
+  it("parses show/reset", () => {
+    expect(parseDebugCommand("/debug")).toEqual({ action: "show" });
+    expect(parseDebugCommand("/debug show")).toEqual({ action: "show" });
+    expect(parseDebugCommand("/debug reset")).toEqual({ action: "reset" });
+  });
+
+  it("parses set with JSON", () => {
+    const cmd = parseDebugCommand('/debug set foo={"a":1}');
+    expect(cmd).toEqual({ action: "set", path: "foo", value: { a: 1 } });
+  });
+
+  it("parses unset", () => {
+    const cmd = parseDebugCommand("/debug unset foo.bar");
+    expect(cmd).toEqual({ action: "unset", path: "foo.bar" });
+  });
+});
+
+describe("extractMessageText", () => {
+  it("preserves user text that looks like tool call markers", () => {
+    const message = {
+      role: "user",
+      content: "Here [Tool Call: foo (ID: 1)] ok",
+    };
+    const result = extractMessageText(message);
+    expect(result?.text).toContain("[Tool Call: foo (ID: 1)]");
+  });
+
+  it("sanitizes assistant tool call markers", () => {
+    const message = {
+      role: "assistant",
+      content: "Here [Tool Call: foo (ID: 1)] ok",
+    };
+    const result = extractMessageText(message);
+    expect(result?.text).toBe("Here ok");
+  });
+});
+
+describe("handleCommands /config configWrites gating", () => {
+  it("blocks /config set when channel config writes are disabled", async () => {
+    const cfg = {
+      commands: { config: true, text: true },
+      channels: { whatsapp: { allowFrom: ["*"], configWrites: false } },
+    } as ClawdbotConfig;
+    const params = buildParams('/config set messages.ackReaction=":)"', cfg);
+    const result = await handleCommands(params);
+    expect(result.shouldContinue).toBe(false);
+    expect(result.reply?.text).toContain("Config writes are disabled");
+  });
+});

src/auto-reply/reply/commands-policy.test.ts

@@ -5,6 +5,47 @@ import type { MsgContext } from "../templating.js";
 import { buildCommandContext, handleCommands } from "./commands.js";
 import { parseInlineDirectives } from "./directive-handling.js";
 
+const readConfigFileSnapshotMock = vi.hoisted(() => vi.fn());
+const validateConfigObjectWithPluginsMock = vi.hoisted(() => vi.fn());
+const writeConfigFileMock = vi.hoisted(() => vi.fn());
+
+vi.mock("../../config/config.js", async () => {
+  const actual =
+    await vi.importActual<typeof import("../../config/config.js")>("../../config/config.js");
+  return {
+    ...actual,
+    readConfigFileSnapshot: readConfigFileSnapshotMock,
+    validateConfigObjectWithPlugins: validateConfigObjectWithPluginsMock,
+    writeConfigFile: writeConfigFileMock,
+  };
+});
+
+const readChannelAllowFromStoreMock = vi.hoisted(() => vi.fn());
+const addChannelAllowFromStoreEntryMock = vi.hoisted(() => vi.fn());
+const removeChannelAllowFromStoreEntryMock = vi.hoisted(() => vi.fn());
+
+vi.mock("../../pairing/pairing-store.js", async () => {
+  const actual = await vi.importActual<typeof import("../../pairing/pairing-store.js")>(
+    "../../pairing/pairing-store.js",
+  );
+  return {
+    ...actual,
+    readChannelAllowFromStore: readChannelAllowFromStoreMock,
+    addChannelAllowFromStoreEntry: addChannelAllowFromStoreEntryMock,
+    removeChannelAllowFromStoreEntry: removeChannelAllowFromStoreEntryMock,
+  };
+});
+
+vi.mock("../../channels/plugins/pairing.js", async () => {
+  const actual = await vi.importActual<typeof import("../../channels/plugins/pairing.js")>(
+    "../../channels/plugins/pairing.js",
+  );
+  return {
+    ...actual,
+    listPairingChannels: () => ["telegram"],
+  };
+});
+
 vi.mock("../../agents/model-catalog.js", () => ({
   loadModelCatalog: vi.fn(async () => [
     { provider: "anthropic", id: "claude-opus-4-5", name: "Claude Opus" },
@@ -46,17 +87,70 @@ function buildParams(commandBody: string, cfg: ClawdbotConfig, ctxOverrides?: Pa
     resolvedVerboseLevel: "off" as const,
     resolvedReasoningLevel: "off" as const,
     resolveDefaultThinkingLevel: async () => undefined,
-    provider: "anthropic",
-    model: "claude-opus-4-5",
-    contextTokens: 16000,
+    provider: "telegram",
+    model: "test-model",
+    contextTokens: 0,
     isGroup: false,
   };
 }
 
+describe("handleCommands /allowlist", () => {
+  it("lists config + store allowFrom entries", async () => {
+    readChannelAllowFromStoreMock.mockResolvedValueOnce(["456"]);
+
+    const cfg = {
+      commands: { text: true },
+      channels: { telegram: { allowFrom: ["123", "@Alice"] } },
+    } as ClawdbotConfig;
+    const params = buildParams("/allowlist list dm", cfg);
+    const result = await handleCommands(params);
+
+    expect(result.shouldContinue).toBe(false);
+    expect(result.reply?.text).toContain("Channel: telegram");
+    expect(result.reply?.text).toContain("DM allowFrom (config): 123, @alice");
+    expect(result.reply?.text).toContain("Paired allowFrom (store): 456");
+  });
+
+  it("adds entries to config and pairing store", async () => {
+    readConfigFileSnapshotMock.mockResolvedValueOnce({
+      valid: true,
+      parsed: {
+        channels: { telegram: { allowFrom: ["123"] } },
+      },
+    });
+    validateConfigObjectWithPluginsMock.mockImplementation((config: unknown) => ({
+      ok: true,
+      config,
+    }));
+    addChannelAllowFromStoreEntryMock.mockResolvedValueOnce({
+      changed: true,
+      allowFrom: ["123", "789"],
+    });
+
+    const cfg = {
+      commands: { text: true, config: true },
+      channels: { telegram: { allowFrom: ["123"] } },
+    } as ClawdbotConfig;
+    const params = buildParams("/allowlist add dm 789", cfg);
+    const result = await handleCommands(params);
+
+    expect(result.shouldContinue).toBe(false);
+    expect(writeConfigFileMock).toHaveBeenCalledWith(
+      expect.objectContaining({
+        channels: { telegram: { allowFrom: ["123", "789"] } },
+      }),
+    );
+    expect(addChannelAllowFromStoreEntryMock).toHaveBeenCalledWith({
+      channel: "telegram",
+      entry: "789",
+    });
+    expect(result.reply?.text).toContain("DM allowlist added");
+  });
+});
+
 describe("/models command", () => {
   const cfg = {
     commands: { text: true },
-    // allowlist is empty => allowAny, but still okay for listing
     agents: { defaults: { model: { primary: "anthropic/claude-opus-4-5" } } },
   } as unknown as ClawdbotConfig;
 

src/auto-reply/reply/commands-subagents.test.ts

@@ -1,23 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import { extractMessageText } from "./commands-subagents.js";
-
-describe("extractMessageText", () => {
-  it("preserves user text that looks like tool call markers", () => {
-    const message = {
-      role: "user",
-      content: "Here [Tool Call: foo (ID: 1)] ok",
-    };
-    const result = extractMessageText(message);
-    expect(result?.text).toContain("[Tool Call: foo (ID: 1)]");
-  });
-
-  it("sanitizes assistant tool call markers", () => {
-    const message = {
-      role: "assistant",
-      content: "Here [Tool Call: foo (ID: 1)] ok",
-    };
-    const result = extractMessageText(message);
-    expect(result?.text).toBe("Here ok");
-  });
-});

src/auto-reply/reply/config-commands.test.ts

@@ -1,30 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import { parseConfigCommand } from "./config-commands.js";
-
-describe("parseConfigCommand", () => {
-  it("parses show/unset", () => {
-    expect(parseConfigCommand("/config")).toEqual({ action: "show" });
-    expect(parseConfigCommand("/config show")).toEqual({
-      action: "show",
-      path: undefined,
-    });
-    expect(parseConfigCommand("/config show foo.bar")).toEqual({
-      action: "show",
-      path: "foo.bar",
-    });
-    expect(parseConfigCommand("/config get foo.bar")).toEqual({
-      action: "show",
-      path: "foo.bar",
-    });
-    expect(parseConfigCommand("/config unset foo.bar")).toEqual({
-      action: "unset",
-      path: "foo.bar",
-    });
-  });
-
-  it("parses set with JSON", () => {
-    const cmd = parseConfigCommand('/config set foo={"a":1}');
-    expect(cmd).toEqual({ action: "set", path: "foo", value: { a: 1 } });
-  });
-});

src/auto-reply/reply/debug-commands.test.ts

@@ -1,21 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import { parseDebugCommand } from "./debug-commands.js";
-
-describe("parseDebugCommand", () => {
-  it("parses show/reset", () => {
-    expect(parseDebugCommand("/debug")).toEqual({ action: "show" });
-    expect(parseDebugCommand("/debug show")).toEqual({ action: "show" });
-    expect(parseDebugCommand("/debug reset")).toEqual({ action: "reset" });
-  });
-
-  it("parses set with JSON", () => {
-    const cmd = parseDebugCommand('/debug set foo={"a":1}');
-    expect(cmd).toEqual({ action: "set", path: "foo", value: { a: 1 } });
-  });
-
-  it("parses unset", () => {
-    const cmd = parseDebugCommand("/debug unset foo.bar");
-    expect(cmd).toEqual({ action: "unset", path: "foo.bar" });
-  });
-});

src/auto-reply/reply/directive-handling.model.chat-ux.test.ts

@@ -1,62 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import type { ModelAliasIndex } from "../../agents/model-selection.js";
-import type { ClawdbotConfig } from "../../config/config.js";
-import { parseInlineDirectives } from "./directive-handling.js";
-import {
-  maybeHandleModelDirectiveInfo,
-  resolveModelSelectionFromDirective,
-} from "./directive-handling.model.js";
-
-function baseAliasIndex(): ModelAliasIndex {
-  return { byAlias: new Map(), byKey: new Map() };
-}
-
-describe("/model chat UX", () => {
-  it("shows summary for /model with no args", async () => {
-    const directives = parseInlineDirectives("/model");
-    const cfg = { commands: { text: true } } as unknown as ClawdbotConfig;
-
-    const reply = await maybeHandleModelDirectiveInfo({
-      directives,
-      cfg,
-      agentDir: "/tmp/agent",
-      activeAgentId: "main",
-      provider: "anthropic",
-      model: "claude-opus-4-5",
-      defaultProvider: "anthropic",
-      defaultModel: "claude-opus-4-5",
-      aliasIndex: baseAliasIndex(),
-      allowedModelCatalog: [],
-      resetModelOverride: false,
-    });
-
-    expect(reply?.text).toContain("Current:");
-    expect(reply?.text).toContain("Browse: /models");
-    expect(reply?.text).toContain("Switch: /model <provider/model>");
-  });
-
-  it("auto-applies closest match for typos", () => {
-    const directives = parseInlineDirectives("/model anthropic/claud-opus-4-5");
-    const cfg = { commands: { text: true } } as unknown as ClawdbotConfig;
-
-    const resolved = resolveModelSelectionFromDirective({
-      directives,
-      cfg,
-      agentDir: "/tmp/agent",
-      defaultProvider: "anthropic",
-      defaultModel: "claude-opus-4-5",
-      aliasIndex: baseAliasIndex(),
-      allowedModelKeys: new Set(["anthropic/claude-opus-4-5"]),
-      allowedModelCatalog: [{ provider: "anthropic", id: "claude-opus-4-5" }],
-      provider: "anthropic",
-    });
-
-    expect(resolved.modelSelection).toEqual({
-      provider: "anthropic",
-      model: "claude-opus-4-5",
-      isDefault: true,
-    });
-    expect(resolved.errorText).toBeUndefined();
-  });
-});

src/auto-reply/reply/directive-handling.model.test.ts

@@ -5,8 +5,12 @@ import type { ClawdbotConfig } from "../../config/config.js";
 import type { SessionEntry } from "../../config/sessions.js";
 import { parseInlineDirectives } from "./directive-handling.js";
 import { handleDirectiveOnly } from "./directive-handling.impl.js";
+import {
+  maybeHandleModelDirectiveInfo,
+  resolveModelSelectionFromDirective,
+} from "./directive-handling.model.js";
 
-// Mock dependencies
+// Mock dependencies for directive handling persistence.
 vi.mock("../../agents/agent-scope.js", () => ({
   resolveAgentConfig: vi.fn(() => ({})),
   resolveAgentDir: vi.fn(() => "/tmp/agent"),
@@ -36,6 +40,55 @@ function baseConfig(): ClawdbotConfig {
   } as unknown as ClawdbotConfig;
 }
 
+describe("/model chat UX", () => {
+  it("shows summary for /model with no args", async () => {
+    const directives = parseInlineDirectives("/model");
+    const cfg = { commands: { text: true } } as unknown as ClawdbotConfig;
+
+    const reply = await maybeHandleModelDirectiveInfo({
+      directives,
+      cfg,
+      agentDir: "/tmp/agent",
+      activeAgentId: "main",
+      provider: "anthropic",
+      model: "claude-opus-4-5",
+      defaultProvider: "anthropic",
+      defaultModel: "claude-opus-4-5",
+      aliasIndex: baseAliasIndex(),
+      allowedModelCatalog: [],
+      resetModelOverride: false,
+    });
+
+    expect(reply?.text).toContain("Current:");
+    expect(reply?.text).toContain("Browse: /models");
+    expect(reply?.text).toContain("Switch: /model <provider/model>");
+  });
+
+  it("auto-applies closest match for typos", () => {
+    const directives = parseInlineDirectives("/model anthropic/claud-opus-4-5");
+    const cfg = { commands: { text: true } } as unknown as ClawdbotConfig;
+
+    const resolved = resolveModelSelectionFromDirective({
+      directives,
+      cfg,
+      agentDir: "/tmp/agent",
+      defaultProvider: "anthropic",
+      defaultModel: "claude-opus-4-5",
+      aliasIndex: baseAliasIndex(),
+      allowedModelKeys: new Set(["anthropic/claude-opus-4-5"]),
+      allowedModelCatalog: [{ provider: "anthropic", id: "claude-opus-4-5" }],
+      provider: "anthropic",
+    });
+
+    expect(resolved.modelSelection).toEqual({
+      provider: "anthropic",
+      model: "claude-opus-4-5",
+      isDefault: true,
+    });
+    expect(resolved.errorText).toBeUndefined();
+  });
+});
+
 describe("handleDirectiveOnly model persist behavior (fixes #1435)", () => {
   const allowedModelKeys = new Set(["anthropic/claude-opus-4-5", "openai/gpt-4o"]);
   const allowedModelCatalog = [
@@ -106,7 +159,6 @@ describe("handleDirectiveOnly model persist behavior (fixes #1435)", () => {
       formatModelSwitchEvent: (label) => `Switched to ${label}`,
     });
 
-    // No model directive = no model message
     expect(result?.text ?? "").not.toContain("Model set to");
     expect(result?.text ?? "").not.toContain("failed");
   });

src/auto-reply/reply/followup-runner.compaction.test.ts

@@ -1,105 +0,0 @@
-import fs from "node:fs/promises";
-import { tmpdir } from "node:os";
-import path from "node:path";
-import { describe, expect, it, vi } from "vitest";
-
-import type { SessionEntry } from "../../config/sessions.js";
-import type { FollowupRun } from "./queue.js";
-import { createMockTypingController } from "./test-helpers.js";
-
-const runEmbeddedPiAgentMock = vi.fn();
-
-vi.mock("../../agents/model-fallback.js", () => ({
-  runWithModelFallback: async ({
-    provider,
-    model,
-    run,
-  }: {
-    provider: string;
-    model: string;
-    run: (provider: string, model: string) => Promise<unknown>;
-  }) => ({
-    result: await run(provider, model),
-    provider,
-    model,
-  }),
-}));
-
-vi.mock("../../agents/pi-embedded.js", () => ({
-  runEmbeddedPiAgent: (params: unknown) => runEmbeddedPiAgentMock(params),
-}));
-
-import { createFollowupRunner } from "./followup-runner.js";
-
-describe("createFollowupRunner compaction", () => {
-  it("adds verbose auto-compaction notice and tracks count", async () => {
-    const storePath = path.join(
-      await fs.mkdtemp(path.join(tmpdir(), "clawdbot-compaction-")),
-      "sessions.json",
-    );
-    const sessionEntry: SessionEntry = {
-      sessionId: "session",
-      updatedAt: Date.now(),
-    };
-    const sessionStore: Record<string, SessionEntry> = {
-      main: sessionEntry,
-    };
-    const onBlockReply = vi.fn(async () => {});
-
-    runEmbeddedPiAgentMock.mockImplementationOnce(
-      async (params: {
-        onAgentEvent?: (evt: { stream: string; data: Record<string, unknown> }) => void;
-      }) => {
-        params.onAgentEvent?.({
-          stream: "compaction",
-          data: { phase: "end", willRetry: false },
-        });
-        return { payloads: [{ text: "final" }], meta: {} };
-      },
-    );
-
-    const runner = createFollowupRunner({
-      opts: { onBlockReply },
-      typing: createMockTypingController(),
-      typingMode: "instant",
-      sessionEntry,
-      sessionStore,
-      sessionKey: "main",
-      storePath,
-      defaultModel: "anthropic/claude-opus-4-5",
-    });
-
-    const queued = {
-      prompt: "hello",
-      summaryLine: "hello",
-      enqueuedAt: Date.now(),
-      run: {
-        sessionId: "session",
-        sessionKey: "main",
-        messageProvider: "whatsapp",
-        sessionFile: "/tmp/session.jsonl",
-        workspaceDir: "/tmp",
-        config: {},
-        skillsSnapshot: {},
-        provider: "anthropic",
-        model: "claude",
-        thinkLevel: "low",
-        verboseLevel: "on",
-        elevatedLevel: "off",
-        bashElevated: {
-          enabled: false,
-          allowed: false,
-          defaultLevel: "off",
-        },
-        timeoutMs: 1_000,
-        blockReplyBreak: "message_end",
-      },
-    } as FollowupRun;
-
-    await runner(queued);
-
-    expect(onBlockReply).toHaveBeenCalled();
-    expect(onBlockReply.mock.calls[0][0].text).toContain("Auto-compaction complete");
-    expect(sessionStore.main.compactionCount).toBe(1);
-  });
-});

src/auto-reply/reply/followup-runner.test.ts

@@ -1,5 +1,9 @@
+import fs from "node:fs/promises";
+import { tmpdir } from "node:os";
+import path from "node:path";
 import { describe, expect, it, vi } from "vitest";
 
+import type { SessionEntry } from "../../config/sessions.js";
 import type { FollowupRun } from "./queue.js";
 import { createMockTypingController } from "./test-helpers.js";
 
@@ -57,6 +61,79 @@ const baseQueuedRun = (messageProvider = "whatsapp"): FollowupRun =>
     },
   }) as FollowupRun;
 
+describe("createFollowupRunner compaction", () => {
+  it("adds verbose auto-compaction notice and tracks count", async () => {
+    const storePath = path.join(
+      await fs.mkdtemp(path.join(tmpdir(), "clawdbot-compaction-")),
+      "sessions.json",
+    );
+    const sessionEntry: SessionEntry = {
+      sessionId: "session",
+      updatedAt: Date.now(),
+    };
+    const sessionStore: Record<string, SessionEntry> = {
+      main: sessionEntry,
+    };
+    const onBlockReply = vi.fn(async () => {});
+
+    runEmbeddedPiAgentMock.mockImplementationOnce(
+      async (params: {
+        onAgentEvent?: (evt: { stream: string; data: Record<string, unknown> }) => void;
+      }) => {
+        params.onAgentEvent?.({
+          stream: "compaction",
+          data: { phase: "end", willRetry: false },
+        });
+        return { payloads: [{ text: "final" }], meta: {} };
+      },
+    );
+
+    const runner = createFollowupRunner({
+      opts: { onBlockReply },
+      typing: createMockTypingController(),
+      typingMode: "instant",
+      sessionEntry,
+      sessionStore,
+      sessionKey: "main",
+      storePath,
+      defaultModel: "anthropic/claude-opus-4-5",
+    });
+
+    const queued = {
+      prompt: "hello",
+      summaryLine: "hello",
+      enqueuedAt: Date.now(),
+      run: {
+        sessionId: "session",
+        sessionKey: "main",
+        messageProvider: "whatsapp",
+        sessionFile: "/tmp/session.jsonl",
+        workspaceDir: "/tmp",
+        config: {},
+        skillsSnapshot: {},
+        provider: "anthropic",
+        model: "claude",
+        thinkLevel: "low",
+        verboseLevel: "on",
+        elevatedLevel: "off",
+        bashElevated: {
+          enabled: false,
+          allowed: false,
+          defaultLevel: "off",
+        },
+        timeoutMs: 1_000,
+        blockReplyBreak: "message_end",
+      },
+    } as FollowupRun;
+
+    await runner(queued);
+
+    expect(onBlockReply).toHaveBeenCalled();
+    expect(onBlockReply.mock.calls[0][0].text).toContain("Auto-compaction complete");
+    expect(sessionStore.main.compactionCount).toBe(1);
+  });
+});
+
 describe("createFollowupRunner messaging tool dedupe", () => {
   it("drops payloads already sent via messaging tool", async () => {
     const onBlockReply = vi.fn(async () => {});

src/auto-reply/reply/formatting.test.ts

@@ -0,0 +1,185 @@
+import { afterEach, describe, expect, it, vi } from "vitest";
+
+import { parseAudioTag } from "./audio-tags.js";
+import { createBlockReplyCoalescer } from "./block-reply-coalescer.js";
+import { createReplyReferencePlanner } from "./reply-reference.js";
+import { createStreamingDirectiveAccumulator } from "./streaming-directives.js";
+
+describe("parseAudioTag", () => {
+  it("detects audio_as_voice and strips the tag", () => {
+    const result = parseAudioTag("Hello [[audio_as_voice]] world");
+    expect(result.audioAsVoice).toBe(true);
+    expect(result.hadTag).toBe(true);
+    expect(result.text).toBe("Hello world");
+  });
+
+  it("returns empty output for missing text", () => {
+    const result = parseAudioTag(undefined);
+    expect(result.audioAsVoice).toBe(false);
+    expect(result.hadTag).toBe(false);
+    expect(result.text).toBe("");
+  });
+
+  it("removes tag-only messages", () => {
+    const result = parseAudioTag("[[audio_as_voice]]");
+    expect(result.audioAsVoice).toBe(true);
+    expect(result.text).toBe("");
+  });
+});
+
+describe("block reply coalescer", () => {
+  afterEach(() => {
+    vi.useRealTimers();
+  });
+
+  it("coalesces chunks within the idle window", async () => {
+    vi.useFakeTimers();
+    const flushes: string[] = [];
+    const coalescer = createBlockReplyCoalescer({
+      config: { minChars: 1, maxChars: 200, idleMs: 100, joiner: " " },
+      shouldAbort: () => false,
+      onFlush: (payload) => {
+        flushes.push(payload.text ?? "");
+      },
+    });
+
+    coalescer.enqueue({ text: "Hello" });
+    coalescer.enqueue({ text: "world" });
+
+    await vi.advanceTimersByTimeAsync(100);
+    expect(flushes).toEqual(["Hello world"]);
+    coalescer.stop();
+  });
+
+  it("waits until minChars before idle flush", async () => {
+    vi.useFakeTimers();
+    const flushes: string[] = [];
+    const coalescer = createBlockReplyCoalescer({
+      config: { minChars: 10, maxChars: 200, idleMs: 50, joiner: " " },
+      shouldAbort: () => false,
+      onFlush: (payload) => {
+        flushes.push(payload.text ?? "");
+      },
+    });
+
+    coalescer.enqueue({ text: "short" });
+    await vi.advanceTimersByTimeAsync(50);
+    expect(flushes).toEqual([]);
+
+    coalescer.enqueue({ text: "message" });
+    await vi.advanceTimersByTimeAsync(50);
+    expect(flushes).toEqual(["short message"]);
+    coalescer.stop();
+  });
+
+  it("flushes buffered text before media payloads", () => {
+    const flushes: Array<{ text?: string; mediaUrls?: string[] }> = [];
+    const coalescer = createBlockReplyCoalescer({
+      config: { minChars: 1, maxChars: 200, idleMs: 0, joiner: " " },
+      shouldAbort: () => false,
+      onFlush: (payload) => {
+        flushes.push({
+          text: payload.text,
+          mediaUrls: payload.mediaUrls,
+        });
+      },
+    });
+
+    coalescer.enqueue({ text: "Hello" });
+    coalescer.enqueue({ text: "world" });
+    coalescer.enqueue({ mediaUrls: ["https://example.com/a.png"] });
+    void coalescer.flush({ force: true });
+
+    expect(flushes[0].text).toBe("Hello world");
+    expect(flushes[1].mediaUrls).toEqual(["https://example.com/a.png"]);
+    coalescer.stop();
+  });
+});
+
+describe("createReplyReferencePlanner", () => {
+  it("disables references when mode is off", () => {
+    const planner = createReplyReferencePlanner({
+      replyToMode: "off",
+      startId: "parent",
+    });
+    expect(planner.use()).toBeUndefined();
+    expect(planner.hasReplied()).toBe(false);
+  });
+
+  it("uses startId once when mode is first", () => {
+    const planner = createReplyReferencePlanner({
+      replyToMode: "first",
+      startId: "parent",
+    });
+    expect(planner.use()).toBe("parent");
+    expect(planner.hasReplied()).toBe(true);
+    planner.markSent();
+    expect(planner.use()).toBeUndefined();
+  });
+
+  it("returns startId for every call when mode is all", () => {
+    const planner = createReplyReferencePlanner({
+      replyToMode: "all",
+      startId: "parent",
+    });
+    expect(planner.use()).toBe("parent");
+    expect(planner.use()).toBe("parent");
+  });
+
+  it("prefers existing thread id regardless of mode", () => {
+    const planner = createReplyReferencePlanner({
+      replyToMode: "off",
+      existingId: "thread-1",
+      startId: "parent",
+    });
+    expect(planner.use()).toBe("thread-1");
+    expect(planner.hasReplied()).toBe(true);
+  });
+
+  it("honors allowReference=false", () => {
+    const planner = createReplyReferencePlanner({
+      replyToMode: "all",
+      startId: "parent",
+      allowReference: false,
+    });
+    expect(planner.use()).toBeUndefined();
+    expect(planner.hasReplied()).toBe(false);
+    planner.markSent();
+    expect(planner.hasReplied()).toBe(true);
+  });
+});
+
+describe("createStreamingDirectiveAccumulator", () => {
+  it("stashes reply_to_current until a renderable chunk arrives", () => {
+    const accumulator = createStreamingDirectiveAccumulator();
+
+    expect(accumulator.consume("[[reply_to_current]]")).toBeNull();
+
+    const result = accumulator.consume("Hello");
+    expect(result?.text).toBe("Hello");
+    expect(result?.replyToCurrent).toBe(true);
+    expect(result?.replyToTag).toBe(true);
+  });
+
+  it("handles reply tags split across chunks", () => {
+    const accumulator = createStreamingDirectiveAccumulator();
+
+    expect(accumulator.consume("[[reply_to_")).toBeNull();
+
+    const result = accumulator.consume("current]] Yo");
+    expect(result?.text).toBe("Yo");
+    expect(result?.replyToCurrent).toBe(true);
+    expect(result?.replyToTag).toBe(true);
+  });
+
+  it("propagates explicit reply ids across chunks", () => {
+    const accumulator = createStreamingDirectiveAccumulator();
+
+    expect(accumulator.consume("[[reply_to: abc-123]]")).toBeNull();
+
+    const result = accumulator.consume("Hi");
+    expect(result?.text).toBe("Hi");
+    expect(result?.replyToId).toBe("abc-123");
+    expect(result?.replyToTag).toBe(true);
+  });
+});

src/auto-reply/reply/get-reply.ts

@@ -28,6 +28,7 @@ export async function getReplyFromConfig(
   opts?: GetReplyOptions,
   configOverride?: ClawdbotConfig,
 ): Promise<ReplyPayload | ReplyPayload[] | undefined> {
+  const isFastTestEnv = process.env.CLAWDBOT_TEST_FAST === "1";
   const cfg = configOverride ?? loadConfig();
   const targetSessionKey =
     ctx.CommandSource === "native" ? ctx.CommandTargetSessionKey?.trim() : undefined;
@@ -62,7 +63,7 @@ export async function getReplyFromConfig(
   const workspaceDirRaw = resolveAgentWorkspaceDir(cfg, agentId) ?? DEFAULT_AGENT_WORKSPACE_DIR;
   const workspace = await ensureAgentWorkspace({
     dir: workspaceDirRaw,
-    ensureBootstrapFiles: !agentCfg?.skipBootstrap,
+    ensureBootstrapFiles: !agentCfg?.skipBootstrap && !isFastTestEnv,
   });
   const workspaceDir = workspace.dir;
   const agentDir = resolveAgentDir(cfg, agentId);
@@ -81,12 +82,14 @@ export async function getReplyFromConfig(
 
   const finalized = finalizeInboundContext(ctx);
 
-  await applyMediaUnderstanding({
-    ctx: finalized,
-    cfg,
-    agentDir,
-    activeModel: { provider, model },
-  });
+  if (!isFastTestEnv) {
+    await applyMediaUnderstanding({
+      ctx: finalized,
+      cfg,
+      agentDir,
+      activeModel: { provider, model },
+    });
+  }
 
   const commandAuthorized = finalized.CommandAuthorized;
   resolveCommandAuthorization({

src/auto-reply/reply/groups.test.ts

@@ -1,61 +0,0 @@
-import { describe, expect, it } from "vitest";
-import type { ClawdbotConfig } from "../../config/config.js";
-import type { GroupKeyResolution } from "../../config/sessions.js";
-import type { TemplateContext } from "../templating.js";
-import { resolveGroupRequireMention } from "./groups.js";
-
-describe("resolveGroupRequireMention", () => {
-  it("respects Discord guild/channel requireMention settings", () => {
-    const cfg: ClawdbotConfig = {
-      channels: {
-        discord: {
-          guilds: {
-            "145": {
-              requireMention: false,
-              channels: {
-                general: { allow: true },
-              },
-            },
-          },
-        },
-      },
-    };
-    const ctx: TemplateContext = {
-      Provider: "discord",
-      From: "discord:group:123",
-      GroupChannel: "#general",
-      GroupSpace: "145",
-    };
-    const groupResolution: GroupKeyResolution = {
-      channel: "discord",
-      id: "123",
-      chatType: "group",
-    };
-
-    expect(resolveGroupRequireMention({ cfg, ctx, groupResolution })).toBe(false);
-  });
-
-  it("respects Slack channel requireMention settings", () => {
-    const cfg: ClawdbotConfig = {
-      channels: {
-        slack: {
-          channels: {
-            C123: { requireMention: false },
-          },
-        },
-      },
-    };
-    const ctx: TemplateContext = {
-      Provider: "slack",
-      From: "slack:channel:C123",
-      GroupSubject: "#general",
-    };
-    const groupResolution: GroupKeyResolution = {
-      channel: "slack",
-      id: "C123",
-      chatType: "group",
-    };
-
-    expect(resolveGroupRequireMention({ cfg, ctx, groupResolution })).toBe(false);
-  });
-});

src/auto-reply/reply/inbound-context.test.ts

@@ -1,38 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import type { MsgContext } from "../templating.js";
-import { finalizeInboundContext } from "./inbound-context.js";
-
-describe("finalizeInboundContext", () => {
-  it("fills BodyForAgent/BodyForCommands and normalizes newlines", () => {
-    const ctx: MsgContext = {
-      Body: "a\\nb\r\nc",
-      RawBody: "raw\\nline",
-      ChatType: "channel",
-      From: "whatsapp:group:123@g.us",
-      GroupSubject: "Test",
-    };
-
-    const out = finalizeInboundContext(ctx);
-    expect(out.Body).toBe("a\nb\nc");
-    expect(out.RawBody).toBe("raw\nline");
-    expect(out.BodyForAgent).toBe("a\nb\nc");
-    expect(out.BodyForCommands).toBe("raw\nline");
-    expect(out.CommandAuthorized).toBe(false);
-    expect(out.ChatType).toBe("channel");
-    expect(out.ConversationLabel).toContain("Test");
-  });
-
-  it("can force BodyForCommands to follow updated CommandBody", () => {
-    const ctx: MsgContext = {
-      Body: "base",
-      BodyForCommands: "<media:audio>",
-      CommandBody: "say hi",
-      From: "signal:+15550001111",
-      ChatType: "direct",
-    };
-
-    finalizeInboundContext(ctx, { forceBodyForCommands: true });
-    expect(ctx.BodyForCommands).toBe("say hi");
-  });
-});

src/auto-reply/reply/inbound-dedupe.test.ts

@@ -1,66 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import type { MsgContext } from "../templating.js";
-import {
-  buildInboundDedupeKey,
-  resetInboundDedupe,
-  shouldSkipDuplicateInbound,
-} from "./inbound-dedupe.js";
-
-describe("inbound dedupe", () => {
-  it("builds a stable key when MessageSid is present", () => {
-    const ctx: MsgContext = {
-      Provider: "telegram",
-      OriginatingChannel: "telegram",
-      OriginatingTo: "telegram:123",
-      MessageSid: "42",
-    };
-    expect(buildInboundDedupeKey(ctx)).toBe("telegram|telegram:123|42");
-  });
-
-  it("skips duplicates with the same key", () => {
-    resetInboundDedupe();
-    const ctx: MsgContext = {
-      Provider: "whatsapp",
-      OriginatingChannel: "whatsapp",
-      OriginatingTo: "whatsapp:+1555",
-      MessageSid: "msg-1",
-    };
-    expect(shouldSkipDuplicateInbound(ctx, { now: 100 })).toBe(false);
-    expect(shouldSkipDuplicateInbound(ctx, { now: 200 })).toBe(true);
-  });
-
-  it("does not dedupe when the peer changes", () => {
-    resetInboundDedupe();
-    const base: MsgContext = {
-      Provider: "whatsapp",
-      OriginatingChannel: "whatsapp",
-      MessageSid: "msg-1",
-    };
-    expect(
-      shouldSkipDuplicateInbound({ ...base, OriginatingTo: "whatsapp:+1000" }, { now: 100 }),
-    ).toBe(false);
-    expect(
-      shouldSkipDuplicateInbound({ ...base, OriginatingTo: "whatsapp:+2000" }, { now: 200 }),
-    ).toBe(false);
-  });
-
-  it("does not dedupe across session keys", () => {
-    resetInboundDedupe();
-    const base: MsgContext = {
-      Provider: "whatsapp",
-      OriginatingChannel: "whatsapp",
-      OriginatingTo: "whatsapp:+1555",
-      MessageSid: "msg-1",
-    };
-    expect(
-      shouldSkipDuplicateInbound({ ...base, SessionKey: "agent:alpha:main" }, { now: 100 }),
-    ).toBe(false);
-    expect(
-      shouldSkipDuplicateInbound({ ...base, SessionKey: "agent:bravo:main" }, { now: 200 }),
-    ).toBe(false);
-    expect(
-      shouldSkipDuplicateInbound({ ...base, SessionKey: "agent:alpha:main" }, { now: 300 }),
-    ).toBe(true);
-  });
-});

src/auto-reply/reply/inbound-sender-meta.test.ts

@@ -1,56 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import type { MsgContext } from "../templating.js";
-import { formatInboundBodyWithSenderMeta } from "./inbound-sender-meta.js";
-
-describe("formatInboundBodyWithSenderMeta", () => {
-  it("does nothing for direct messages", () => {
-    const ctx: MsgContext = { ChatType: "direct", SenderName: "Alice", SenderId: "A1" };
-    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] hi" })).toBe("[X] hi");
-  });
-
-  it("appends a sender meta line for non-direct messages", () => {
-    const ctx: MsgContext = { ChatType: "group", SenderName: "Alice", SenderId: "A1" };
-    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] hi" })).toBe(
-      "[X] hi\n[from: Alice (A1)]",
-    );
-  });
-
-  it("prefers SenderE164 in the label when present", () => {
-    const ctx: MsgContext = {
-      ChatType: "group",
-      SenderName: "Bob",
-      SenderId: "bob@s.whatsapp.net",
-      SenderE164: "+222",
-    };
-    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] hi" })).toBe(
-      "[X] hi\n[from: Bob (+222)]",
-    );
-  });
-
-  it("appends with a real newline even if the body contains literal \\\\n", () => {
-    const ctx: MsgContext = { ChatType: "group", SenderName: "Bob", SenderId: "+222" };
-    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] one\\n[X] two" })).toBe(
-      "[X] one\\n[X] two\n[from: Bob (+222)]",
-    );
-  });
-
-  it("does not duplicate a sender meta line when one is already present", () => {
-    const ctx: MsgContext = { ChatType: "group", SenderName: "Alice", SenderId: "A1" };
-    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[X] hi\n[from: Alice (A1)]" })).toBe(
-      "[X] hi\n[from: Alice (A1)]",
-    );
-  });
-
-  it("does not append when the body already includes a sender prefix", () => {
-    const ctx: MsgContext = { ChatType: "group", SenderName: "Alice", SenderId: "A1" };
-    expect(formatInboundBodyWithSenderMeta({ ctx, body: "Alice (A1): hi" })).toBe("Alice (A1): hi");
-  });
-
-  it("does not append when the sender prefix follows an envelope header", () => {
-    const ctx: MsgContext = { ChatType: "group", SenderName: "Alice", SenderId: "A1" };
-    expect(formatInboundBodyWithSenderMeta({ ctx, body: "[Signal Group] Alice (A1): hi" })).toBe(
-      "[Signal Group] Alice (A1): hi",
-    );
-  });
-});

src/auto-reply/reply/inbound-text.test.ts

@@ -1,18 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import { normalizeInboundTextNewlines } from "./inbound-text.js";
-
-describe("normalizeInboundTextNewlines", () => {
-  it("keeps real newlines", () => {
-    expect(normalizeInboundTextNewlines("a\nb")).toBe("a\nb");
-  });
-
-  it("normalizes CRLF/CR to LF", () => {
-    expect(normalizeInboundTextNewlines("a\r\nb")).toBe("a\nb");
-    expect(normalizeInboundTextNewlines("a\rb")).toBe("a\nb");
-  });
-
-  it("decodes literal \\\\n to newlines when no real newlines exist", () => {
-    expect(normalizeInboundTextNewlines("a\\nb")).toBe("a\nb");
-  });
-});

src/auto-reply/reply/mentions.test.ts

@@ -1,47 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import { buildMentionRegexes, matchesMentionPatterns, normalizeMentionText } from "./mentions.js";
-
-describe("mention helpers", () => {
-  it("builds regexes and skips invalid patterns", () => {
-    const regexes = buildMentionRegexes({
-      messages: {
-        groupChat: { mentionPatterns: ["\\bclawd\\b", "(invalid"] },
-      },
-    });
-    expect(regexes).toHaveLength(1);
-    expect(regexes[0]?.test("clawd")).toBe(true);
-  });
-
-  it("normalizes zero-width characters", () => {
-    expect(normalizeMentionText("cl\u200bawd")).toBe("clawd");
-  });
-
-  it("matches patterns case-insensitively", () => {
-    const regexes = buildMentionRegexes({
-      messages: { groupChat: { mentionPatterns: ["\\bclawd\\b"] } },
-    });
-    expect(matchesMentionPatterns("CLAWD: hi", regexes)).toBe(true);
-  });
-
-  it("uses per-agent mention patterns when configured", () => {
-    const regexes = buildMentionRegexes(
-      {
-        messages: {
-          groupChat: { mentionPatterns: ["\\bglobal\\b"] },
-        },
-        agents: {
-          list: [
-            {
-              id: "work",
-              groupChat: { mentionPatterns: ["\\bworkbot\\b"] },
-            },
-          ],
-        },
-      },
-      "work",
-    );
-    expect(matchesMentionPatterns("workbot: hi", regexes)).toBe(true);
-    expect(matchesMentionPatterns("global: hi", regexes)).toBe(false);
-  });
-});

src/auto-reply/reply/reply-reference.test.ts

@@ -1,56 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import { createReplyReferencePlanner } from "./reply-reference.js";
-
-describe("createReplyReferencePlanner", () => {
-  it("disables references when mode is off", () => {
-    const planner = createReplyReferencePlanner({
-      replyToMode: "off",
-      startId: "parent",
-    });
-    expect(planner.use()).toBeUndefined();
-    expect(planner.hasReplied()).toBe(false);
-  });
-
-  it("uses startId once when mode is first", () => {
-    const planner = createReplyReferencePlanner({
-      replyToMode: "first",
-      startId: "parent",
-    });
-    expect(planner.use()).toBe("parent");
-    expect(planner.hasReplied()).toBe(true);
-    planner.markSent();
-    expect(planner.use()).toBeUndefined();
-  });
-
-  it("returns startId for every call when mode is all", () => {
-    const planner = createReplyReferencePlanner({
-      replyToMode: "all",
-      startId: "parent",
-    });
-    expect(planner.use()).toBe("parent");
-    expect(planner.use()).toBe("parent");
-  });
-
-  it("prefers existing thread id regardless of mode", () => {
-    const planner = createReplyReferencePlanner({
-      replyToMode: "off",
-      existingId: "thread-1",
-      startId: "parent",
-    });
-    expect(planner.use()).toBe("thread-1");
-    expect(planner.hasReplied()).toBe(true);
-  });
-
-  it("honors allowReference=false", () => {
-    const planner = createReplyReferencePlanner({
-      replyToMode: "all",
-      startId: "parent",
-      allowReference: false,
-    });
-    expect(planner.use()).toBeUndefined();
-    expect(planner.hasReplied()).toBe(false);
-    planner.markSent();
-    expect(planner.hasReplied()).toBe(true);
-  });
-});

src/auto-reply/reply/reply-routing.test.ts

@@ -1,6 +1,11 @@
 import { describe, expect, it, vi } from "vitest";
+
+import type { ClawdbotConfig } from "../../config/config.js";
 import { HEARTBEAT_TOKEN, SILENT_REPLY_TOKEN } from "../tokens.js";
 import { createReplyDispatcher } from "./reply-dispatcher.js";
+import { createReplyToModeFilter, resolveReplyToMode } from "./reply-threading.js";
+
+const emptyCfg = {} as ClawdbotConfig;
 
 describe("createReplyDispatcher", () => {
   it("drops empty payloads and silent tokens without media", async () => {
@@ -150,3 +155,94 @@ describe("createReplyDispatcher", () => {
     vi.useRealTimers();
   });
 });
+
+describe("resolveReplyToMode", () => {
+  it("defaults to first for Telegram", () => {
+    expect(resolveReplyToMode(emptyCfg, "telegram")).toBe("first");
+  });
+
+  it("defaults to off for Discord and Slack", () => {
+    expect(resolveReplyToMode(emptyCfg, "discord")).toBe("off");
+    expect(resolveReplyToMode(emptyCfg, "slack")).toBe("off");
+  });
+
+  it("defaults to all when channel is unknown", () => {
+    expect(resolveReplyToMode(emptyCfg, undefined)).toBe("all");
+  });
+
+  it("uses configured value when present", () => {
+    const cfg = {
+      channels: {
+        telegram: { replyToMode: "all" },
+        discord: { replyToMode: "first" },
+        slack: { replyToMode: "all" },
+      },
+    } as ClawdbotConfig;
+    expect(resolveReplyToMode(cfg, "telegram")).toBe("all");
+    expect(resolveReplyToMode(cfg, "discord")).toBe("first");
+    expect(resolveReplyToMode(cfg, "slack")).toBe("all");
+  });
+
+  it("uses chat-type replyToMode overrides for Slack when configured", () => {
+    const cfg = {
+      channels: {
+        slack: {
+          replyToMode: "off",
+          replyToModeByChatType: { direct: "all", group: "first" },
+        },
+      },
+    } as ClawdbotConfig;
+    expect(resolveReplyToMode(cfg, "slack", null, "direct")).toBe("all");
+    expect(resolveReplyToMode(cfg, "slack", null, "group")).toBe("first");
+    expect(resolveReplyToMode(cfg, "slack", null, "channel")).toBe("off");
+    expect(resolveReplyToMode(cfg, "slack", null, undefined)).toBe("off");
+  });
+
+  it("falls back to top-level replyToMode when no chat-type override is set", () => {
+    const cfg = {
+      channels: {
+        slack: {
+          replyToMode: "first",
+        },
+      },
+    } as ClawdbotConfig;
+    expect(resolveReplyToMode(cfg, "slack", null, "direct")).toBe("first");
+    expect(resolveReplyToMode(cfg, "slack", null, "channel")).toBe("first");
+  });
+
+  it("uses legacy dm.replyToMode for direct messages when no chat-type override exists", () => {
+    const cfg = {
+      channels: {
+        slack: {
+          replyToMode: "off",
+          dm: { replyToMode: "all" },
+        },
+      },
+    } as ClawdbotConfig;
+    expect(resolveReplyToMode(cfg, "slack", null, "direct")).toBe("all");
+    expect(resolveReplyToMode(cfg, "slack", null, "channel")).toBe("off");
+  });
+});
+
+describe("createReplyToModeFilter", () => {
+  it("drops replyToId when mode is off", () => {
+    const filter = createReplyToModeFilter("off");
+    expect(filter({ text: "hi", replyToId: "1" }).replyToId).toBeUndefined();
+  });
+
+  it("keeps replyToId when mode is off and reply tags are allowed", () => {
+    const filter = createReplyToModeFilter("off", { allowTagsWhenOff: true });
+    expect(filter({ text: "hi", replyToId: "1", replyToTag: true }).replyToId).toBe("1");
+  });
+
+  it("keeps replyToId when mode is all", () => {
+    const filter = createReplyToModeFilter("all");
+    expect(filter({ text: "hi", replyToId: "1" }).replyToId).toBe("1");
+  });
+
+  it("keeps only the first replyToId when mode is first", () => {
+    const filter = createReplyToModeFilter("first");
+    expect(filter({ text: "hi", replyToId: "1" }).replyToId).toBe("1");
+    expect(filter({ text: "next", replyToId: "1" }).replyToId).toBeUndefined();
+  });
+});

src/auto-reply/reply/reply-threading.test.ts

@@ -1,97 +0,0 @@
-import { describe, expect, it } from "vitest";
-
-import type { ClawdbotConfig } from "../../config/config.js";
-import { createReplyToModeFilter, resolveReplyToMode } from "./reply-threading.js";
-
-const emptyCfg = {} as ClawdbotConfig;
-
-describe("resolveReplyToMode", () => {
-  it("defaults to first for Telegram", () => {
-    expect(resolveReplyToMode(emptyCfg, "telegram")).toBe("first");
-  });
-
-  it("defaults to off for Discord and Slack", () => {
-    expect(resolveReplyToMode(emptyCfg, "discord")).toBe("off");
-    expect(resolveReplyToMode(emptyCfg, "slack")).toBe("off");
-  });
-
-  it("defaults to all when channel is unknown", () => {
-    expect(resolveReplyToMode(emptyCfg, undefined)).toBe("all");
-  });
-
-  it("uses configured value when present", () => {
-    const cfg = {
-      channels: {
-        telegram: { replyToMode: "all" },
-        discord: { replyToMode: "first" },
-        slack: { replyToMode: "all" },
-      },
-    } as ClawdbotConfig;
-    expect(resolveReplyToMode(cfg, "telegram")).toBe("all");
-    expect(resolveReplyToMode(cfg, "discord")).toBe("first");
-    expect(resolveReplyToMode(cfg, "slack")).toBe("all");
-  });
-
-  it("uses chat-type replyToMode overrides for Slack when configured", () => {
-    const cfg = {
-      channels: {
-        slack: {
-          replyToMode: "off",
-          replyToModeByChatType: { direct: "all", group: "first" },
-        },
-      },
-    } as ClawdbotConfig;
-    expect(resolveReplyToMode(cfg, "slack", null, "direct")).toBe("all");
-    expect(resolveReplyToMode(cfg, "slack", null, "group")).toBe("first");
-    expect(resolveReplyToMode(cfg, "slack", null, "channel")).toBe("off");
-    expect(resolveReplyToMode(cfg, "slack", null, undefined)).toBe("off");
-  });
-
-  it("falls back to top-level replyToMode when no chat-type override is set", () => {
-    const cfg = {
-      channels: {
-        slack: {
-          replyToMode: "first",
-        },
-      },
-    } as ClawdbotConfig;
-    expect(resolveReplyToMode(cfg, "slack", null, "direct")).toBe("first");
-    expect(resolveReplyToMode(cfg, "slack", null, "channel")).toBe("first");
-  });
-
-  it("uses legacy dm.replyToMode for direct messages when no chat-type override exists", () => {
-    const cfg = {
-      channels: {
-        slack: {
-          replyToMode: "off",
-          dm: { replyToMode: "all" },
-        },
-      },
-    } as ClawdbotConfig;
-    expect(resolveReplyToMode(cfg, "slack", null, "direct")).toBe("all");
-    expect(resolveReplyToMode(cfg, "slack", null, "channel")).toBe("off");
-  });
-});
-
-describe("createReplyToModeFilter", () => {
-  it("drops replyToId when mode is off", () => {
-    const filter = createReplyToModeFilter("off");
-    expect(filter({ text: "hi", replyToId: "1" }).replyToId).toBeUndefined();
-  });
-
-  it("keeps replyToId when mode is off and reply tags are allowed", () => {
-    const filter = createReplyToModeFilter("off", { allowTagsWhenOff: true });
-    expect(filter({ text: "hi", replyToId: "1", replyToTag: true }).replyToId).toBe("1");
-  });
-
-  it("keeps replyToId when mode is all", () => {
-    const filter = createReplyToModeFilter("all");
-    expect(filter({ text: "hi", replyToId: "1" }).replyToId).toBe("1");
-  });
-
-  it("keeps only the first replyToId when mode is first", () => {
-    const filter = createReplyToModeFilter("first");
-    expect(filter({ text: "hi", replyToId: "1" }).replyToId).toBe("1");
-    expect(filter({ text: "next", replyToId: "1" }).replyToId).toBeUndefined();
-  });
-});

src/auto-reply/reply/session-reset-model.test.ts

@@ -1,107 +0,0 @@
-import { describe, expect, it, vi } from "vitest";
-
-import type { ClawdbotConfig } from "../../config/config.js";
-import { buildModelAliasIndex } from "../../agents/model-selection.js";
-import { applyResetModelOverride } from "./session-reset-model.js";
-
-vi.mock("../../agents/model-catalog.js", () => ({
-  loadModelCatalog: vi.fn(async () => [
-    { provider: "minimax", id: "m2.1", name: "M2.1" },
-    { provider: "openai", id: "gpt-4o-mini", name: "GPT-4o mini" },
-  ]),
-}));
-
-describe("applyResetModelOverride", () => {
-  it("selects a model hint and strips it from the body", async () => {
-    const cfg = {} as ClawdbotConfig;
-    const aliasIndex = buildModelAliasIndex({ cfg, defaultProvider: "openai" });
-    const sessionEntry = {
-      sessionId: "s1",
-      updatedAt: Date.now(),
-    };
-    const sessionStore = { "agent:main:dm:1": sessionEntry };
-    const sessionCtx = { BodyStripped: "minimax summarize" };
-    const ctx = { ChatType: "direct" };
-
-    await applyResetModelOverride({
-      cfg,
-      resetTriggered: true,
-      bodyStripped: "minimax summarize",
-      sessionCtx,
-      ctx,
-      sessionEntry,
-      sessionStore,
-      sessionKey: "agent:main:dm:1",
-      defaultProvider: "openai",
-      defaultModel: "gpt-4o-mini",
-      aliasIndex,
-    });
-
-    expect(sessionEntry.providerOverride).toBe("minimax");
-    expect(sessionEntry.modelOverride).toBe("m2.1");
-    expect(sessionCtx.BodyStripped).toBe("summarize");
-  });
-
-  it("clears auth profile overrides when reset applies a model", async () => {
-    const cfg = {} as ClawdbotConfig;
-    const aliasIndex = buildModelAliasIndex({ cfg, defaultProvider: "openai" });
-    const sessionEntry = {
-      sessionId: "s1",
-      updatedAt: Date.now(),
-      authProfileOverride: "anthropic:default",
-      authProfileOverrideSource: "user",
-      authProfileOverrideCompactionCount: 2,
-    };
-    const sessionStore = { "agent:main:dm:1": sessionEntry };
-    const sessionCtx = { BodyStripped: "minimax summarize" };
-    const ctx = { ChatType: "direct" };
-
-    await applyResetModelOverride({
-      cfg,
-      resetTriggered: true,
-      bodyStripped: "minimax summarize",
-      sessionCtx,
-      ctx,
-      sessionEntry,
-      sessionStore,
-      sessionKey: "agent:main:dm:1",
-      defaultProvider: "openai",
-      defaultModel: "gpt-4o-mini",
-      aliasIndex,
-    });
-
-    expect(sessionEntry.authProfileOverride).toBeUndefined();
-    expect(sessionEntry.authProfileOverrideSource).toBeUndefined();
-    expect(sessionEntry.authProfileOverrideCompactionCount).toBeUndefined();
-  });
-
-  it("skips when resetTriggered is false", async () => {
-    const cfg = {} as ClawdbotConfig;
-    const aliasIndex = buildModelAliasIndex({ cfg, defaultProvider: "openai" });
-    const sessionEntry = {
-      sessionId: "s1",
-      updatedAt: Date.now(),
-    };
-    const sessionStore = { "agent:main:dm:1": sessionEntry };
-    const sessionCtx = { BodyStripped: "minimax summarize" };
-    const ctx = { ChatType: "direct" };
-
-    await applyResetModelOverride({
-      cfg,
-      resetTriggered: false,
-      bodyStripped: "minimax summarize",
-      sessionCtx,
-      ctx,
-      sessionEntry,
-      sessionStore,
-      sessionKey: "agent:main:dm:1",
-      defaultProvider: "openai",
-      defaultModel: "gpt-4o-mini",
-      aliasIndex,
-    });
-
-    expect(sessionEntry.providerOverride).toBeUndefined();
-    expect(sessionEntry.modelOverride).toBeUndefined();
-    expect(sessionCtx.BodyStripped).toBe("minimax summarize");
-  });
-});

src/auto-reply/reply/session-resets.test.ts

@@ -2,10 +2,21 @@ import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
 
-import { describe, expect, it } from "vitest";
+import { describe, expect, it, vi } from "vitest";
 
+import { buildModelAliasIndex } from "../../agents/model-selection.js";
 import type { ClawdbotConfig } from "../../config/config.js";
+import { enqueueSystemEvent, resetSystemEventsForTest } from "../../infra/system-events.js";
 import { initSessionState } from "./session.js";
+import { applyResetModelOverride } from "./session-reset-model.js";
+import { prependSystemEvents } from "./session-updates.js";
+
+vi.mock("../../agents/model-catalog.js", () => ({
+  loadModelCatalog: vi.fn(async () => [
+    { provider: "minimax", id: "m2.1", name: "M2.1" },
+    { provider: "openai", id: "gpt-4o-mini", name: "GPT-4o mini" },
+  ]),
+}));
 
 describe("initSessionState reset triggers in WhatsApp groups", () => {
   async function createStorePath(prefix: string): Promise<string> {
@@ -54,7 +65,6 @@ describe("initSessionState reset triggers in WhatsApp groups", () => {
       allowFrom: ["+41796666864"],
     });
 
-    // Group message context matching what WhatsApp handler creates
     const groupMessageCtx = {
       Body: `[Chat messages since your last reply - for context]\\n[WhatsApp 120363406150318674@g.us 2026-01-13T07:45Z] Someone: hello\\n\\n[Current message - respond to this]\\n[WhatsApp 120363406150318674@g.us 2026-01-13T07:45Z] Peschiño: /new\\n[from: Peschiño (+41796666864)]`,
       RawBody: "/new",
@@ -76,7 +86,6 @@ describe("initSessionState reset triggers in WhatsApp groups", () => {
       commandAuthorized: true,
     });
 
-    // The reset should be detected
     expect(result.triggerBodyNormalized).toBe("/new");
     expect(result.isNewSession).toBe(true);
     expect(result.sessionId).not.toBe(existingSessionId);
@@ -99,7 +108,6 @@ describe("initSessionState reset triggers in WhatsApp groups", () => {
       allowFrom: ["+41796666864"],
     });
 
-    // Group message from different sender (not in allowFrom)
     const groupMessageCtx = {
       Body: `[Context]\\n[WhatsApp ...] OtherPerson: /new\\n[from: OtherPerson (+1555123456)]`,
       RawBody: "/new",
@@ -111,7 +119,7 @@ describe("initSessionState reset triggers in WhatsApp groups", () => {
       Provider: "whatsapp",
       Surface: "whatsapp",
       SenderName: "OtherPerson",
-      SenderE164: "+1555123456", // Different sender (not authorized)
+      SenderE164: "+1555123456",
       SenderId: "1555123456:0@s.whatsapp.net",
     };
 
@@ -121,9 +129,8 @@ describe("initSessionState reset triggers in WhatsApp groups", () => {
       commandAuthorized: true,
     });
 
-    // Reset should NOT be triggered for unauthorized sender - session ID should stay the same
     expect(result.triggerBodyNormalized).toBe("/new");
-    expect(result.sessionId).toBe(existingSessionId); // Session should NOT change
+    expect(result.sessionId).toBe(existingSessionId);
     expect(result.isNewSession).toBe(false);
   });
 
@@ -143,9 +150,7 @@ describe("initSessionState reset triggers in WhatsApp groups", () => {
     });
 
     const groupMessageCtx = {
-      // Body is wrapped with context prefixes
       Body: `[WhatsApp 120363406150318674@g.us 2026-01-13T07:45Z] Jake: /new\n[from: Jake (+1222)]`,
-      // RawBody is clean
       RawBody: "/new",
       CommandBody: "/new",
       From: "120363406150318674@g.us",
@@ -251,3 +256,124 @@ describe("initSessionState reset triggers in WhatsApp groups", () => {
     expect(result.isNewSession).toBe(false);
   });
 });
+
+describe("applyResetModelOverride", () => {
+  it("selects a model hint and strips it from the body", async () => {
+    const cfg = {} as ClawdbotConfig;
+    const aliasIndex = buildModelAliasIndex({ cfg, defaultProvider: "openai" });
+    const sessionEntry = {
+      sessionId: "s1",
+      updatedAt: Date.now(),
+    };
+    const sessionStore = { "agent:main:dm:1": sessionEntry };
+    const sessionCtx = { BodyStripped: "minimax summarize" };
+    const ctx = { ChatType: "direct" };
+
+    await applyResetModelOverride({
+      cfg,
+      resetTriggered: true,
+      bodyStripped: "minimax summarize",
+      sessionCtx,
+      ctx,
+      sessionEntry,
+      sessionStore,
+      sessionKey: "agent:main:dm:1",
+      defaultProvider: "openai",
+      defaultModel: "gpt-4o-mini",
+      aliasIndex,
+    });
+
+    expect(sessionEntry.providerOverride).toBe("minimax");
+    expect(sessionEntry.modelOverride).toBe("m2.1");
+    expect(sessionCtx.BodyStripped).toBe("summarize");
+  });
+
+  it("clears auth profile overrides when reset applies a model", async () => {
+    const cfg = {} as ClawdbotConfig;
+    const aliasIndex = buildModelAliasIndex({ cfg, defaultProvider: "openai" });
+    const sessionEntry = {
+      sessionId: "s1",
+      updatedAt: Date.now(),
+      authProfileOverride: "anthropic:default",
+      authProfileOverrideSource: "user",
+      authProfileOverrideCompactionCount: 2,
+    };
+    const sessionStore = { "agent:main:dm:1": sessionEntry };
+    const sessionCtx = { BodyStripped: "minimax summarize" };
+    const ctx = { ChatType: "direct" };
+
+    await applyResetModelOverride({
+      cfg,
+      resetTriggered: true,
+      bodyStripped: "minimax summarize",
+      sessionCtx,
+      ctx,
+      sessionEntry,
+      sessionStore,
+      sessionKey: "agent:main:dm:1",
+      defaultProvider: "openai",
+      defaultModel: "gpt-4o-mini",
+      aliasIndex,
+    });
+
+    expect(sessionEntry.authProfileOverride).toBeUndefined();
+    expect(sessionEntry.authProfileOverrideSource).toBeUndefined();
+    expect(sessionEntry.authProfileOverrideCompactionCount).toBeUndefined();
+  });
+
+  it("skips when resetTriggered is false", async () => {
+    const cfg = {} as ClawdbotConfig;
+    const aliasIndex = buildModelAliasIndex({ cfg, defaultProvider: "openai" });
+    const sessionEntry = {
+      sessionId: "s1",
+      updatedAt: Date.now(),
+    };
+    const sessionStore = { "agent:main:dm:1": sessionEntry };
+    const sessionCtx = { BodyStripped: "minimax summarize" };
+    const ctx = { ChatType: "direct" };
+
+    await applyResetModelOverride({
+      cfg,
+      resetTriggered: false,
+      bodyStripped: "minimax summarize",
+      sessionCtx,
+      ctx,
+      sessionEntry,
+      sessionStore,
+      sessionKey: "agent:main:dm:1",
+      defaultProvider: "openai",
+      defaultModel: "gpt-4o-mini",
+      aliasIndex,
+    });
+
+    expect(sessionEntry.providerOverride).toBeUndefined();
+    expect(sessionEntry.modelOverride).toBeUndefined();
+    expect(sessionCtx.BodyStripped).toBe("minimax summarize");
+  });
+});
+
+describe("prependSystemEvents", () => {
+  it("adds a local timestamp to queued system events by default", async () => {
+    vi.useFakeTimers();
+    const originalTz = process.env.TZ;
+    process.env.TZ = "America/Los_Angeles";
+    const timestamp = new Date("2026-01-12T20:19:17Z");
+    vi.setSystemTime(timestamp);
+
+    enqueueSystemEvent("Model switched.", { sessionKey: "agent:main:main" });
+
+    const result = await prependSystemEvents({
+      cfg: {} as ClawdbotConfig,
+      sessionKey: "agent:main:main",
+      isMainSession: false,
+      isNewSession: false,
+      prefixedBodyBase: "User: hi",
+    });
+
+    expect(result).toMatch(/System: \[2026-01-12 12:19:17 [^\]]+\] Model switched\./);
+
+    resetSystemEventsForTest();
+    process.env.TZ = originalTz;
+    vi.useRealTimers();
+  });
+});

src/auto-reply/reply/session-updates.test.ts

@@ -1,31 +0,0 @@
-import { describe, expect, it, vi } from "vitest";
-
-import type { ClawdbotConfig } from "../../config/config.js";
-import { enqueueSystemEvent, resetSystemEventsForTest } from "../../infra/system-events.js";
-import { prependSystemEvents } from "./session-updates.js";
-
-describe("prependSystemEvents", () => {
-  it("adds a local timestamp to queued system events by default", async () => {
-    vi.useFakeTimers();
-    const originalTz = process.env.TZ;
-    process.env.TZ = "America/Los_Angeles";
-    const timestamp = new Date("2026-01-12T20:19:17Z");
-    vi.setSystemTime(timestamp);
-
-    enqueueSystemEvent("Model switched.", { sessionKey: "agent:main:main" });
-
-    const result = await prependSystemEvents({
-      cfg: {} as ClawdbotConfig,
-      sessionKey: "agent:main:main",
-      isMainSession: false,
-      isNewSession: false,
-      prefixedBodyBase: "User: hi",
-    });
-
-    expect(result).toMatch(/System: \[2026-01-12 12:19:17 [^\]]+\] Model switched\./);
-
-    resetSystemEventsForTest();
-    process.env.TZ = originalTz;
-    vi.useRealTimers();
-  });
-});

src/auto-reply/reply/session.sender-meta.test.ts

@@ -1,51 +0,0 @@
-import fs from "node:fs/promises";
-import os from "node:os";
-import path from "node:path";
-
-import { describe, expect, it } from "vitest";
-
-import type { ClawdbotConfig } from "../../config/config.js";
-import { initSessionState } from "./session.js";
-
-describe("initSessionState sender meta", () => {
-  it("injects sender meta into BodyStripped for group chats", async () => {
-    const root = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-sender-meta-"));
-    const storePath = path.join(root, "sessions.json");
-    const cfg = { session: { store: storePath } } as ClawdbotConfig;
-
-    const result = await initSessionState({
-      ctx: {
-        Body: "[WhatsApp 123@g.us] ping",
-        ChatType: "group",
-        SenderName: "Bob",
-        SenderE164: "+222",
-        SenderId: "222@s.whatsapp.net",
-        SessionKey: "agent:main:whatsapp:group:123@g.us",
-      },
-      cfg,
-      commandAuthorized: true,
-    });
-
-    expect(result.sessionCtx.BodyStripped).toBe("[WhatsApp 123@g.us] ping\n[from: Bob (+222)]");
-  });
-
-  it("does not inject sender meta for direct chats", async () => {
-    const root = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-sender-meta-direct-"));
-    const storePath = path.join(root, "sessions.json");
-    const cfg = { session: { store: storePath } } as ClawdbotConfig;
-
-    const result = await initSessionState({
-      ctx: {
-        Body: "[WhatsApp +1] ping",
-        ChatType: "direct",
-        SenderName: "Bob",
-        SenderE164: "+222",
-        SessionKey: "agent:main:whatsapp:dm:+222",
-      },
-      cfg,
-      commandAuthorized: true,
-    });
-
-    expect(result.sessionCtx.BodyStripped).toBe("[WhatsApp +1] ping");
-  });
-});

src/auto-reply/reply/streaming-directives.test.ts

@@ -1,37 +0,0 @@
-import { describe, expect, it } from "vitest";
-import { createStreamingDirectiveAccumulator } from "./streaming-directives.js";
-
-describe("createStreamingDirectiveAccumulator", () => {
-  it("stashes reply_to_current until a renderable chunk arrives", () => {
-    const accumulator = createStreamingDirectiveAccumulator();
-
-    expect(accumulator.consume("[[reply_to_current]]")).toBeNull();
-
-    const result = accumulator.consume("Hello");
-    expect(result?.text).toBe("Hello");
-    expect(result?.replyToCurrent).toBe(true);
-    expect(result?.replyToTag).toBe(true);
-  });
-
-  it("handles reply tags split across chunks", () => {
-    const accumulator = createStreamingDirectiveAccumulator();
-
-    expect(accumulator.consume("[[reply_to_")).toBeNull();
-
-    const result = accumulator.consume("current]] Yo");
-    expect(result?.text).toBe("Yo");
-    expect(result?.replyToCurrent).toBe(true);
-    expect(result?.replyToTag).toBe(true);
-  });
-
-  it("propagates explicit reply ids across chunks", () => {
-    const accumulator = createStreamingDirectiveAccumulator();
-
-    expect(accumulator.consume("[[reply_to: abc-123]]")).toBeNull();
-
-    const result = accumulator.consume("Hi");
-    expect(result?.text).toBe("Hi");
-    expect(result?.replyToId).toBe("abc-123");
-    expect(result?.replyToTag).toBe(true);
-  });
-});