fix: merge subagent auth profiles

fix: avoid format keyword in tool schemas
Co-authored-by: marcmarg <marcmarg@users.noreply.github.com>
2026-01-16 20:19:19 +00:00 · 2026-01-16 20:19:15 +00:00 · 2026-01-16 19:56:04 +00:00 · 2026-01-16 19:48:52 +00:00 · 2026-01-16 19:40:45 +00:00 · 2026-01-16 19:29:48 +00:00
149 changed files with 21379 additions and 16057 deletions
@@ -55,3 +55,5 @@ apps/ios/*.mobileprovision
 # Local untracked files
 .local/
 .vscode/
+IDENTITY.md
+USER.md
@@ -107,6 +107,7 @@
 - Bug investigations: read source code of relevant npm dependencies and all related local code before concluding; aim for high-confidence root cause.
 - Code style: add brief comments for tricky logic; keep files under ~500 LOC when feasible (split/refactor as needed).
 - Tool schema guardrails (google-antigravity): avoid `Type.Union` in tool input schemas; no `anyOf`/`oneOf`/`allOf`. Use `stringEnum`/`optionalStringEnum` (Type.Unsafe enum) for string lists, and `Type.Optional(...)` instead of `... | null`. Keep top-level tool schema as `type: "object"` with `properties`.
+- Tool schema guardrails: avoid raw `format` property names in tool schemas; some validators treat `format` as a reserved keyword and reject the schema.
 - When asked to open a “session” file, open the Pi session logs under `~/.clawdbot/agents/main/sessions/*.jsonl` (newest unless a specific ID is given), not the default `sessions.json`. If logs are needed from another machine, SSH via Tailscale and read the same path there.
 - Menubar dimming + restart flow mirrors Trimmy: use `scripts/restart-mac.sh` (kills all Clawdbot variants, runs `swift build`, packages, relaunches). Icon dimming depends on MenuBarExtraAccess wiring in AppMain; keep `appearsDisabled` updates intact when touching the status item.
 - Do not rebuild the macOS app over SSH; rebuilds must be run directly on the Mac.
@@ -1,49 +1,82 @@
 # Changelog

-## 2026.1.15 (unreleased)
+## 2026.1.16 (unreleased)

+### Highlights
+- Plugins: add provider auth registry + `clawdbot models auth login` for plugin-driven OAuth/API key flows.
+- Browser: improve remote CDP/Browserless support (auth passthrough, `wss` upgrade, timeouts, clearer errors).
+- Heartbeat: per-agent configuration + 24h duplicate suppression. (#980) — thanks @voidserf.
+- Security: audit warns on weak model tiers; app nodes store auth tokens encrypted (Keychain/SecurePrefs).
+
+### Breaking
+- **BREAKING:** iOS minimum version is now 18.0 to support Textual markdown rendering in native chat. (#702)
 - **BREAKING:** Microsoft Teams is now a plugin; install `@clawdbot/msteams` via `clawdbot plugins install @clawdbot/msteams`.
+
+### Changes
 - CLI: set process titles to `clawdbot-<command>` for clearer process listings.
 - CLI/macOS: sync remote SSH target/identity to config and let `gateway status` auto-infer SSH targets (ssh-config aware).
 - Heartbeat: tighten prompt guidance + suppress duplicate alerts for 24h. (#980) — thanks @voidserf.
+- Repo: ignore local identity files to avoid accidental commits. (#1001) — thanks @gerardward2007.
 - Sessions/Security: add `session.dmScope` for multi-user DM isolation and audit warnings. (#948) — thanks @Alphonse-arianee.
 - Plugins: add provider auth registry + `clawdbot models auth login` for plugin-driven OAuth/API key flows.
+- Skills: add user-invocable skill commands with sanitized names and an opt-out for model invocation.
 - Onboarding: switch channels setup to a single-select loop with per-channel actions and disabled hints in the picker.
 - TUI: show provider/model labels for the active session and default model.
 - Heartbeat: add per-agent heartbeat configuration and multi-agent docs example.
- Fix: list model picker entries as provider/model pairs for explicit selection. (#970) — thanks @mcinteerj.
- Fix: persist `gateway.mode=local` after selecting Local run mode in `clawdbot configure`, even if no other sections are chosen.
- Daemon: fix profile-aware service label resolution (env-driven) and add coverage for launchd/systemd/schtasks. (#969) — thanks @bjesuiter.
+- UI: show gateway auth guidance + doc link on unauthorized Control UI connections.
+- Security: warn on weak model tiers (Haiku, below GPT-5, below Claude 4.5) in `clawdbot security audit`.
+- Apps: store node auth tokens encrypted (Keychain/SecurePrefs).
 - Daemon: share profile/state-dir resolution across service helpers and honor `CLAWDBOT_STATE_DIR` for Windows task scripts.
 - Docs: clarify multi-gateway rescue bot guidance. (#969) — thanks @bjesuiter.
 - Agents: add Current Date & Time system prompt section with configurable time format (auto/12/24).
- Agents: avoid false positives when logging unsupported Google tool schema keywords.
- Agents: skip Gemini history downgrades for google-antigravity to preserve tool calls. (#894) — thanks @mukhtharcm.
- Status: restore usage summary line for current provider when no OAuth profiles exist.
+- Agents: default to no narration for routine tool calls. (#1008) — thanks @cpojer.
 - Tools: normalize Slack/Discord message timestamps with `timestampMs`/`timestampUtc` while keeping raw provider fields.
 - macOS: add `system.which` for prompt-free remote skill discovery (with gateway fallback to `system.run`).
 - Docs: add Date & Time guide and update prompt/timezone configuration docs.
 - Messages: debounce rapid inbound messages across channels with per-connector overrides. (#971) — thanks @juanpablodlc.
 - Messages: allow media-only sends (CLI/tool) and show Telegram voice recording status for voice notes. (#957) — thanks @rdev.
 - Auth/Status: keep auth profiles sticky per session (rotate on compaction/new), surface provider usage headers in `/status` and `clawdbot models status`, and update docs.
- Fix: guard model fallback against undefined provider/model values. (#954) — thanks @roshanasingh4.
- Fix: refactor session store updates, add chat.inject, and harden subagent cleanup flow. (#944) — thanks @tyler6204.
- Fix: clean up suspended CLI processes across backends. (#978) — thanks @Nachx639.
- Fix: support MiniMax coding plan usage responses with `model_remains`/`current_interval_*` payloads.
 - CLI: add `--json` output for `clawdbot daemon` lifecycle/install commands.
 - Memory: make `node-llama-cpp` an optional dependency (avoid Node 25 install failures) and improve local-embeddings fallback/errors.
 - Browser: add `snapshot refs=aria` (Playwright aria-ref ids) for self-resolving refs across `snapshot` → `act`.
 - Browser: `profile="chrome"` now defaults to host control and returns clearer “attach a tab” errors.
- Browser: extension mode recovers when only one tab is attached (stale targetId fallback).
 - Browser: prefer stable Chrome for auto-detect, with Brave/Edge fallbacks and updated docs. (#983) — thanks @cpojer.
- Browser: fix `tab not found` for extension relay snapshots/actions when Playwright blocks `newCDPSession` (use the single available Page).
+- Browser: increase remote CDP reachability timeouts + add `remoteCdpTimeoutMs`/`remoteCdpHandshakeTimeoutMs`.
+- Browser: preserve auth/query tokens for remote CDP endpoints and pass Basic auth for CDP HTTP/WS. (#895) — thanks @mukhtharcm.
 - Telegram: add bidirectional reaction support with configurable notifications and agent guidance. (#964) — thanks @bohdanpodvirnyi.
- Telegram: skip `message_thread_id=1` for General topic sends while keeping typing indicators. (#848) — thanks @azade-c.
+- Telegram: allow custom commands in the bot menu (merged with native; conflicts ignored). (#860) — thanks @nachoiacovino.
 - Discord: allow allowlisted guilds without channel lists to receive messages when `groupPolicy="allowlist"`. — thanks @thewilloftheshadow.
 - Discord: allow emoji/sticker uploads + channel actions in config defaults. (#870) — thanks @JDIVE.
+
+### Fixes
+- WhatsApp: default response prefix only for self-chat, using identity name when set.
+ - Auth: merge main auth profiles into per-agent stores for sub-agents and document inheritance. (#1013) — thanks @marcmarg.
+ - Agents: avoid JSON Schema `format` collisions in tool params by renaming snapshot format fields. (#1013) — thanks @marcmarg.
+- Fix: make `clawdbot update` auto-update global installs when installed via a package manager.
+- Fix: list model picker entries as provider/model pairs for explicit selection. (#970) — thanks @mcinteerj.
+- Fix: align OpenAI image-gen defaults with DALL-E 3 standard quality and document output formats. (#880) — thanks @mkbehr.
+- Fix: persist `gateway.mode=local` after selecting Local run mode in `clawdbot configure`, even if no other sections are chosen.
+- Daemon: fix profile-aware service label resolution (env-driven) and add coverage for launchd/systemd/schtasks. (#969) — thanks @bjesuiter.
+- Agents: avoid false positives when logging unsupported Google tool schema keywords.
+- Agents: skip Gemini history downgrades for google-antigravity to preserve tool calls. (#894) — thanks @mukhtharcm.
+- Status: restore usage summary line for current provider when no OAuth profiles exist.
+- Fix: guard model fallback against undefined provider/model values. (#954) — thanks @roshanasingh4.
+- Fix: refactor session store updates, add chat.inject, and harden subagent cleanup flow. (#944) — thanks @tyler6204.
+- Fix: clean up suspended CLI processes across backends. (#978) — thanks @Nachx639.
+- Fix: support MiniMax coding plan usage responses with `model_remains`/`current_interval_*` payloads.
+- Fix: suppress WhatsApp pairing replies for historical catch-up DMs on initial link. (#904)
+- Browser: extension mode recovers when only one tab is attached (stale targetId fallback).
+- Browser: fix `tab not found` for extension relay snapshots/actions when Playwright blocks `newCDPSession` (use the single available Page).
+- Browser: upgrade `ws` → `wss` when remote CDP uses `https` (fixes Browserless handshake).
+- Telegram: skip `message_thread_id=1` for General topic sends while keeping typing indicators. (#848) — thanks @azade-c.
 - Fix: sanitize user-facing error text + strip `<final>` tags across reply pipelines. (#975) — thanks @ThomsenDrake.
 - Fix: normalize pairing CLI aliases, allow extension channels, and harden Zalo webhook payload parsing. (#991) — thanks @longmaba.
 - Fix: allow local Tailscale Serve hostnames without treating tailnet clients as direct. (#885) — thanks @oswalpalash.
+- Fix: reset sessions after role-ordering conflicts to recover from consecutive user turns. (#998)
+- Fix: keep background exec aborts from killing backgrounded sessions while honoring timeouts.
+- Fix: use local auth for gateway security probe unless remote mode has a URL. (#1011) — thanks @ivanrvpereira.
+- Discord: truncate skill command descriptions for slash command limits. (#1018) — thanks @evalexpr.
+- macOS: resolve gateway token/password using config mode/remote URL, and warn when `launchctl setenv` overrides config. (#1022, #1021) — thanks @kkarimi.

 ## 2026.1.14-1

@@ -25,6 +25,8 @@ RUN pnpm install --frozen-lockfile

 COPY . .
 RUN pnpm build
+# Force pnpm for UI build (Bun may fail on ARM/Synology architectures)
+ENV CLAWDBOT_PREFER_PNPM=1
 RUN pnpm ui:install
 RUN pnpm ui:build

@@ -2,6 +2,87 @@
 <rss xmlns:sparkle="http://www.andymatuschak.org/xml-namespaces/sparkle" version="2.0">
    <channel>
        <title>Clawdbot</title>
+        <item>
+            <title>2026.1.15</title>
+            <pubDate>Fri, 16 Jan 2026 10:31:53 +0000</pubDate>
+            <link>https://raw.githubusercontent.com/clawdbot/clawdbot/main/appcast.xml</link>
+            <sparkle:version>5998</sparkle:version>
+            <sparkle:shortVersionString>2026.1.15</sparkle:shortVersionString>
+            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
+            <description><![CDATA[<h2>Clawdbot 2026.1.15</h2>
+<h3>Highlights</h3>
+<ul>
+<li>Plugins: add provider auth registry + <code>clawdbot models auth login</code> for plugin-driven OAuth/API key flows.</li>
+<li>Browser: improve remote CDP/Browserless support (auth passthrough, <code>wss</code> upgrade, timeouts, clearer errors).</li>
+<li>Heartbeat: per-agent configuration + 24h duplicate suppression. (#980) — thanks @voidserf.</li>
+<li>Security: audit warns on weak model tiers; app nodes store auth tokens encrypted (Keychain/SecurePrefs).</li>
+</ul>
+<h3>Breaking</h3>
+<ul>
+<li><strong>BREAKING:</strong> iOS minimum version is now 18.0 to support Textual markdown rendering in native chat. (#702)</li>
+<li><strong>BREAKING:</strong> Microsoft Teams is now a plugin; install <code>@clawdbot/msteams</code> via <code>clawdbot plugins install @clawdbot/msteams</code>.</li>
+</ul>
+<h3>Changes</h3>
+<ul>
+<li>CLI: set process titles to <code>clawdbot-<command></code> for clearer process listings.</li>
+<li>CLI/macOS: sync remote SSH target/identity to config and let <code>gateway status</code> auto-infer SSH targets (ssh-config aware).</li>
+<li>Heartbeat: tighten prompt guidance + suppress duplicate alerts for 24h. (#980) — thanks @voidserf.</li>
+<li>Sessions/Security: add <code>session.dmScope</code> for multi-user DM isolation and audit warnings. (#948) — thanks @Alphonse-arianee.</li>
+<li>Plugins: add provider auth registry + <code>clawdbot models auth login</code> for plugin-driven OAuth/API key flows.</li>
+<li>Onboarding: switch channels setup to a single-select loop with per-channel actions and disabled hints in the picker.</li>
+<li>TUI: show provider/model labels for the active session and default model.</li>
+<li>Heartbeat: add per-agent heartbeat configuration and multi-agent docs example.</li>
+<li>UI: show gateway auth guidance + doc link on unauthorized Control UI connections.</li>
+<li>Security: warn on weak model tiers (Haiku, below GPT-5, below Claude 4.5) in <code>clawdbot security audit</code>.</li>
+<li>Apps: store node auth tokens encrypted (Keychain/SecurePrefs).</li>
+<li>Daemon: share profile/state-dir resolution across service helpers and honor <code>CLAWDBOT_STATE_DIR</code> for Windows task scripts.</li>
+<li>Docs: clarify multi-gateway rescue bot guidance. (#969) — thanks @bjesuiter.</li>
+<li>Agents: add Current Date & Time system prompt section with configurable time format (auto/12/24).</li>
+<li>Tools: normalize Slack/Discord message timestamps with <code>timestampMs</code>/<code>timestampUtc</code> while keeping raw provider fields.</li>
+<li>macOS: add <code>system.which</code> for prompt-free remote skill discovery (with gateway fallback to <code>system.run</code>).</li>
+<li>Docs: add Date & Time guide and update prompt/timezone configuration docs.</li>
+<li>Messages: debounce rapid inbound messages across channels with per-connector overrides. (#971) — thanks @juanpablodlc.</li>
+<li>Messages: allow media-only sends (CLI/tool) and show Telegram voice recording status for voice notes. (#957) — thanks @rdev.</li>
+<li>Auth/Status: keep auth profiles sticky per session (rotate on compaction/new), surface provider usage headers in <code>/status</code> and <code>clawdbot models status</code>, and update docs.</li>
+<li>CLI: add <code>--json</code> output for <code>clawdbot daemon</code> lifecycle/install commands.</li>
+<li>Memory: make <code>node-llama-cpp</code> an optional dependency (avoid Node 25 install failures) and improve local-embeddings fallback/errors.</li>
+<li>Browser: add <code>snapshot refs=aria</code> (Playwright aria-ref ids) for self-resolving refs across <code>snapshot</code> → <code>act</code>.</li>
+<li>Browser: <code>profile="chrome"</code> now defaults to host control and returns clearer “attach a tab” errors.</li>
+<li>Browser: prefer stable Chrome for auto-detect, with Brave/Edge fallbacks and updated docs. (#983) — thanks @cpojer.</li>
+<li>Browser: increase remote CDP reachability timeouts + add <code>remoteCdpTimeoutMs</code>/<code>remoteCdpHandshakeTimeoutMs</code>.</li>
+<li>Browser: preserve auth/query tokens for remote CDP endpoints and pass Basic auth for CDP HTTP/WS. (#895) — thanks @mukhtharcm.</li>
+<li>Telegram: add bidirectional reaction support with configurable notifications and agent guidance. (#964) — thanks @bohdanpodvirnyi.</li>
+<li>Telegram: allow custom commands in the bot menu (merged with native; conflicts ignored). (#860) — thanks @nachoiacovino.</li>
+<li>Discord: allow allowlisted guilds without channel lists to receive messages when <code>groupPolicy="allowlist"</code>. — thanks @thewilloftheshadow.</li>
+<li>Discord: allow emoji/sticker uploads + channel actions in config defaults. (#870) — thanks @JDIVE.</li>
+</ul>
+<h3>Fixes</h3>
+<ul>
+<li>Fix: list model picker entries as provider/model pairs for explicit selection. (#970) — thanks @mcinteerj.</li>
+<li>Fix: align OpenAI image-gen defaults with DALL-E 3 standard quality and document output formats. (#880) — thanks @mkbehr.</li>
+<li>Fix: persist <code>gateway.mode=local</code> after selecting Local run mode in <code>clawdbot configure</code>, even if no other sections are chosen.</li>
+<li>Daemon: fix profile-aware service label resolution (env-driven) and add coverage for launchd/systemd/schtasks. (#969) — thanks @bjesuiter.</li>
+<li>Agents: avoid false positives when logging unsupported Google tool schema keywords.</li>
+<li>Agents: skip Gemini history downgrades for google-antigravity to preserve tool calls. (#894) — thanks @mukhtharcm.</li>
+<li>Status: restore usage summary line for current provider when no OAuth profiles exist.</li>
+<li>Fix: guard model fallback against undefined provider/model values. (#954) — thanks @roshanasingh4.</li>
+<li>Fix: refactor session store updates, add chat.inject, and harden subagent cleanup flow. (#944) — thanks @tyler6204.</li>
+<li>Fix: clean up suspended CLI processes across backends. (#978) — thanks @Nachx639.</li>
+<li>Fix: support MiniMax coding plan usage responses with <code>model_remains</code>/<code>current_interval_*</code> payloads.</li>
+<li>Fix: suppress WhatsApp pairing replies for historical catch-up DMs on initial link. (#904)</li>
+<li>Browser: extension mode recovers when only one tab is attached (stale targetId fallback).</li>
+<li>Browser: fix <code>tab not found</code> for extension relay snapshots/actions when Playwright blocks <code>newCDPSession</code> (use the single available Page).</li>
+<li>Browser: upgrade <code>ws</code> → <code>wss</code> when remote CDP uses <code>https</code> (fixes Browserless handshake).</li>
+<li>Telegram: skip <code>message_thread_id=1</code> for General topic sends while keeping typing indicators. (#848) — thanks @azade-c.</li>
+<li>Fix: sanitize user-facing error text + strip <code><final></code> tags across reply pipelines. (#975) — thanks @ThomsenDrake.</li>
+<li>Fix: normalize pairing CLI aliases, allow extension channels, and harden Zalo webhook payload parsing. (#991) — thanks @longmaba.</li>
+<li>Fix: allow local Tailscale Serve hostnames without treating tailnet clients as direct. (#885) — thanks @oswalpalash.</li>
+<li>Fix: reset sessions after role-ordering conflicts to recover from consecutive user turns. (#998)</li>
+</ul>
+<p><a href="https://github.com/clawdbot/clawdbot/blob/main/CHANGELOG.md">View full changelog</a></p>
+]]></description>
+            <enclosure url="https://github.com/clawdbot/clawdbot/releases/download/v2026.1.15/Clawdbot-2026.1.15.zip" length="12127276" type="application/octet-stream" sparkle:edSignature="o79vwTbtW/d91NQFRVfUDhsv6D4zIw7IkhY0N1iLImMu94BURgLcecA6z7Smy3bMobPwOyzN8yfm6mA/Rt8FCA=="/>
+        </item>
        <item>
            <title>2026.1.14-1</title>
            <pubDate>Thu, 15 Jan 2026 11:14:40 +0000</pubDate>
@@ -190,22 +271,5 @@
 ]]></description>
            <enclosure url="https://github.com/clawdbot/clawdbot/releases/download/v2026.1.12-2/Clawdbot-2026.1.12-2.zip" length="19854203" type="application/octet-stream" sparkle:edSignature="CVpUofNS+pl6Smk/K0Q8q35saRuuFx90s4sePABORFvGcAF1biajC8zpiImKuXpqD0ENb+VTwDJ1ul1Oxh3wDA=="/>
        </item>
-        <item>
-            <title>2026.1.11-3</title>
-            <pubDate>Mon, 12 Jan 2026 10:40:23 +0000</pubDate>
-            <link>https://raw.githubusercontent.com/clawdbot/clawdbot/main/appcast.xml</link>
-            <sparkle:version>5212</sparkle:version>
-            <sparkle:shortVersionString>2026.1.11-3</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>Clawdbot 2026.1.11-3</h2>
-<h3>Fixes</h3>
-<ul>
-<li>CLI: avoid top-level await warnings in the entrypoint on fresh installs.</li>
-<li>CLI: show a commit hash in the banner for npm installs (package.json gitHead fallback).</li>
-</ul>
-<p><a href="https://github.com/clawdbot/clawdbot/blob/main/CHANGELOG.md">View full changelog</a></p>
-]]></description>
-            <enclosure url="https://github.com/clawdbot/clawdbot/releases/download/v2026.1.11-3/Clawdbot-2026.1.11-3.zip" length="19860758" type="application/octet-stream" sparkle:edSignature="LbvGUSjc3jGO7aVo2UVA0nEkaJbb3O4iwRBo1TBqoapdTtxnDlS3s6N+Z4vOSLRAoAm22EoZOwbpK9085c7HAQ=="/>
-        </item>
    </channel>
 </rss>
@@ -26,7 +26,8 @@ Sources/Voice/VoiceTab.swift
 Sources/Voice/VoiceWakeManager.swift
 Sources/Voice/VoiceWakePreferences.swift
 ../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatComposer.swift
-../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatMarkdownSplitter.swift
+../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatMarkdownRenderer.swift
+../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatMarkdownPreprocessor.swift
 ../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatMessageViews.swift
 ../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatModels.swift
 ../shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatPayloadDecoding.swift
@@ -2,7 +2,7 @@ name: Clawdbot
 options:
  bundleIdPrefix: com.clawdbot
  deploymentTarget:
-    iOS: "17.0"
+    iOS: "18.0"
  xcodeVersion: "16.0"

 settings:
@@ -1,5 +1,5 @@
 {
-  "originHash" : "9de32b5fc115432dadd84c3ab4d67d2fed22ffaf5675a77033d69ea194ac3862",
+  "originHash" : "7eec77e2b399c480e76fdfc7dc3162652f5c775530e9fc282953de38ef2de79b",
  "pins" : [
    {
      "identity" : "elevenlabskit",
@@ -73,6 +73,15 @@
        "revision" : "8e5e4a8f3617283b556064574651fc0869943c9a"
      }
    },
+    {
+      "identity" : "swift-concurrency-extras",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/pointfreeco/swift-concurrency-extras",
+      "state" : {
+        "revision" : "5a3825302b1a0d744183200915a47b508c828e6f",
+        "version" : "1.3.2"
+      }
+    },
    {
      "identity" : "swift-configuration",
      "kind" : "remoteSourceControl",
@@ -144,6 +153,24 @@
        "revision" : "395a77f0aa927f0ff73941d7ac35f2b46d47c9db",
        "version" : "1.6.3"
      }
+    },
+    {
+      "identity" : "swiftui-math",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/gonzalezreal/swiftui-math",
+      "state" : {
+        "revision" : "0b5c2cfaaec8d6193db206f675048eeb5ce95f71",
+        "version" : "0.1.0"
+      }
+    },
+    {
+      "identity" : "textual",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/gonzalezreal/textual",
+      "state" : {
+        "revision" : "a03c1e103d88de4ea0dd8320ea1611ec0d4b29b3",
+        "version" : "0.2.0"
+      }
    }
  ],
  "version" : 3
@@ -257,30 +257,8 @@ final class AppState {

        let configRoot = ClawdbotConfigFile.loadDict()
        let configGateway = configRoot["gateway"] as? [String: Any]
-        let configModeRaw = (configGateway?["mode"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines)
-        let configMode: ConnectionMode? = switch configModeRaw {
-        case "local":
-            .local
-        case "remote":
-            .remote
-        default:
-            nil
-        }
        let configRemoteUrl = (configGateway?["remote"] as? [String: Any])?["url"] as? String
-        let configHasRemoteUrl = !(configRemoteUrl?
-            .trimmingCharacters(in: .whitespacesAndNewlines)
-            .isEmpty ?? true)
-
-        let storedMode = UserDefaults.standard.string(forKey: connectionModeKey)
-        let resolvedConnectionMode: ConnectionMode = if let configMode {
-            configMode
-        } else if configHasRemoteUrl {
-            .remote
-        } else if let storedMode {
-            ConnectionMode(rawValue: storedMode) ?? .local
-        } else {
-            onboardingSeen ? .local : .unconfigured
-        }
+        let resolvedConnectionMode = ConnectionModeResolver.resolve(root: configRoot).mode
        self.connectionMode = resolvedConnectionMode

        let storedRemoteTarget = UserDefaults.standard.string(forKey: remoteTargetKey) ?? ""
@@ -385,14 +385,8 @@ enum CommandResolver {
    }

    static func connectionSettings(defaults: UserDefaults = .standard) -> RemoteSettings {
-        let modeRaw = defaults.string(forKey: connectionModeKey)
-        let mode: AppState.ConnectionMode
-        if let modeRaw {
-            mode = AppState.ConnectionMode(rawValue: modeRaw) ?? .local
-        } else {
-            let seen = defaults.bool(forKey: "clawdbot.onboardingSeen")
-            mode = seen ? .local : .unconfigured
-        }
+        let root = ClawdbotConfigFile.loadDict()
+        let mode = ConnectionModeResolver.resolve(root: root, defaults: defaults).mode
        let target = defaults.string(forKey: remoteTargetKey) ?? ""
        let identity = defaults.string(forKey: remoteIdentityKey) ?? ""
        let projectRoot = defaults.string(forKey: remoteProjectRootKey) ?? ""
@@ -0,0 +1,49 @@
+import Foundation
+
+enum EffectiveConnectionModeSource: Sendable, Equatable {
+    case configMode
+    case configRemoteURL
+    case userDefaults
+    case onboarding
+}
+
+struct EffectiveConnectionMode: Sendable, Equatable {
+    let mode: AppState.ConnectionMode
+    let source: EffectiveConnectionModeSource
+}
+
+enum ConnectionModeResolver {
+    static func resolve(
+        root: [String: Any],
+        defaults: UserDefaults = .standard) -> EffectiveConnectionMode
+    {
+        let gateway = root["gateway"] as? [String: Any]
+        let configModeRaw = (gateway?["mode"] as? String) ?? ""
+        let configMode = configModeRaw
+            .trimmingCharacters(in: .whitespacesAndNewlines)
+            .lowercased()
+
+        switch configMode {
+        case "local":
+            return EffectiveConnectionMode(mode: .local, source: .configMode)
+        case "remote":
+            return EffectiveConnectionMode(mode: .remote, source: .configMode)
+        default:
+            break
+        }
+
+        let remoteURLRaw = ((gateway?["remote"] as? [String: Any])?["url"] as? String) ?? ""
+        let remoteURL = remoteURLRaw.trimmingCharacters(in: .whitespacesAndNewlines)
+        if !remoteURL.isEmpty {
+            return EffectiveConnectionMode(mode: .remote, source: .configRemoteURL)
+        }
+
+        if let storedModeRaw = defaults.string(forKey: connectionModeKey) {
+            let storedMode = AppState.ConnectionMode(rawValue: storedModeRaw) ?? .local
+            return EffectiveConnectionMode(mode: storedMode, source: .userDefaults)
+        }
+
+        let seen = defaults.bool(forKey: "clawdbot.onboardingSeen")
+        return EffectiveConnectionMode(mode: seen ? .local : .unconfigured, source: .onboarding)
+    }
+}
@@ -191,8 +191,8 @@ extension CronJobEditor {
    func applyDeleteAfterRun(
        to root: inout [String: Any],
        scheduleKind: ScheduleKind? = nil,
-        deleteAfterRun: Bool? = nil
-    ) {
+        deleteAfterRun: Bool? = nil)
+    {
        let resolvedSchedule = scheduleKind ?? self.scheduleKind
        let resolvedDelete = deleteAfterRun ?? self.deleteAfterRun
        if resolvedSchedule == .at {
@@ -1,3 +1,4 @@
+import ConcurrencyExtras
 import Foundation
 import OSLog

@@ -16,6 +17,13 @@ actor GatewayEndpointStore {
    static let shared = GatewayEndpointStore()
    private static let supportedBindModes: Set<String> = ["loopback", "tailnet", "lan", "auto"]
    private static let remoteConnectingDetail = "Connecting to remote gateway…"
+    private static let staticLogger = Logger(subsystem: "com.clawdbot", category: "gateway-endpoint")
+    private enum EnvOverrideWarningKind: Sendable {
+        case token
+        case password
+    }
+
+    private static let envOverrideWarnings = LockIsolated((token: false, password: false))

    struct Deps: Sendable {
        let mode: @Sendable () async -> AppState.ConnectionMode
@@ -30,16 +38,18 @@ actor GatewayEndpointStore {
            mode: { await MainActor.run { AppStateStore.shared.connectionMode } },
            token: {
                let root = ClawdbotConfigFile.loadDict()
+                let isRemote = ConnectionModeResolver.resolve(root: root).mode == .remote
                return GatewayEndpointStore.resolveGatewayToken(
-                    isRemote: CommandResolver.connectionModeIsRemote(),
+                    isRemote: isRemote,
                    root: root,
                    env: ProcessInfo.processInfo.environment,
                    launchdSnapshot: GatewayLaunchAgentManager.launchdConfigSnapshot())
            },
            password: {
                let root = ClawdbotConfigFile.loadDict()
+                let isRemote = ConnectionModeResolver.resolve(root: root).mode == .remote
                return GatewayEndpointStore.resolveGatewayPassword(
-                    isRemote: CommandResolver.connectionModeIsRemote(),
+                    isRemote: isRemote,
                    root: root,
                    env: ProcessInfo.processInfo.environment,
                    launchdSnapshot: GatewayLaunchAgentManager.launchdConfigSnapshot())
@@ -68,6 +78,14 @@ actor GatewayEndpointStore {
        let raw = env["CLAWDBOT_GATEWAY_PASSWORD"] ?? ""
        let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
        if !trimmed.isEmpty {
+            if let configPassword = self.resolveConfigPassword(isRemote: isRemote, root: root),
+               !configPassword.isEmpty
+            {
+                self.warnEnvOverrideOnce(
+                    kind: .password,
+                    envVar: "CLAWDBOT_GATEWAY_PASSWORD",
+                    configKey: isRemote ? "gateway.remote.password" : "gateway.auth.password")
+            }
            return trimmed
        }
        if isRemote {
@@ -99,6 +117,26 @@ actor GatewayEndpointStore {
        return nil
    }

+    private static func resolveConfigPassword(isRemote: Bool, root: [String: Any]) -> String? {
+        if isRemote {
+            if let gateway = root["gateway"] as? [String: Any],
+               let remote = gateway["remote"] as? [String: Any],
+               let password = remote["password"] as? String
+            {
+                return password.trimmingCharacters(in: .whitespacesAndNewlines)
+            }
+            return nil
+        }
+
+        if let gateway = root["gateway"] as? [String: Any],
+           let auth = gateway["auth"] as? [String: Any],
+           let password = auth["password"] as? String
+        {
+            return password.trimmingCharacters(in: .whitespacesAndNewlines)
+        }
+        return nil
+    }
+
    private static func resolveGatewayToken(
        isRemote: Bool,
        root: [String: Any],
@@ -108,6 +146,14 @@ actor GatewayEndpointStore {
        let raw = env["CLAWDBOT_GATEWAY_TOKEN"] ?? ""
        let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
        if !trimmed.isEmpty {
+            if let configToken = self.resolveConfigToken(isRemote: isRemote, root: root),
+               !configToken.isEmpty
+            {
+                self.warnEnvOverrideOnce(
+                    kind: .token,
+                    envVar: "CLAWDBOT_GATEWAY_TOKEN",
+                    configKey: isRemote ? "gateway.remote.token" : "gateway.auth.token")
+            }
            return trimmed
        }
        if isRemote {
@@ -139,6 +185,49 @@ actor GatewayEndpointStore {
        return nil
    }

+    private static func resolveConfigToken(isRemote: Bool, root: [String: Any]) -> String? {
+        if isRemote {
+            if let gateway = root["gateway"] as? [String: Any],
+               let remote = gateway["remote"] as? [String: Any],
+               let token = remote["token"] as? String
+            {
+                return token.trimmingCharacters(in: .whitespacesAndNewlines)
+            }
+            return nil
+        }
+
+        if let gateway = root["gateway"] as? [String: Any],
+           let auth = gateway["auth"] as? [String: Any],
+           let token = auth["token"] as? String
+        {
+            return token.trimmingCharacters(in: .whitespacesAndNewlines)
+        }
+        return nil
+    }
+
+    private static func warnEnvOverrideOnce(
+        kind: EnvOverrideWarningKind,
+        envVar: String,
+        configKey: String)
+    {
+        let shouldWarn = Self.envOverrideWarnings.withValue { state in
+            switch kind {
+            case .token:
+                guard !state.token else { return false }
+                state.token = true
+                return true
+            case .password:
+                guard !state.password else { return false }
+                state.password = true
+                return true
+            }
+        }
+        guard shouldWarn else { return }
+        Self.staticLogger.warning(
+            "\(envVar, privacy: .public) is set and overrides \(configKey, privacy: .public). " +
+                "If this is unintentional, clear it with: launchctl unsetenv \(envVar, privacy: .public)")
+    }
+
    private let deps: Deps
    private let logger = Logger(subsystem: "com.clawdbot", category: "gateway-endpoint")

@@ -395,7 +395,7 @@ extension InstancesSettings {
            host: "phone",
            ip: "10.0.0.3",
            version: "2.0.0",
-            platform: "iOS 17.2",
+            platform: "iOS 18.0",
            deviceFamily: "iPhone",
            modelIdentifier: nil,
            lastInputSeconds: 35,
@@ -446,7 +446,7 @@ extension InstancesSettings {
        _ = view.platformIcon("watchOS 10")
        _ = view.platformIcon("unknown 1.0")
        _ = view.prettyPlatform("macOS 14.2")
-        _ = view.prettyPlatform("iOS 17")
+        _ = view.prettyPlatform("iOS 18")
        _ = view.prettyPlatform("ipados 17.1")
        _ = view.prettyPlatform("linux")
        _ = view.prettyPlatform("   ")
@@ -3,6 +3,13 @@ import Testing
@testable import Clawdbot

@Suite struct GatewayEndpointStoreTests {
+    private func makeDefaults() -> UserDefaults {
+        let suiteName = "GatewayEndpointStoreTests.\(UUID().uuidString)"
+        let defaults = UserDefaults(suiteName: suiteName)!
+        defaults.removePersistentDomain(forName: suiteName)
+        return defaults
+    }
+
    @Test func resolveGatewayTokenPrefersEnvAndFallsBackToLaunchd() {
        let snapshot = LaunchAgentPlistSnapshot(
            programArguments: [],
@@ -66,4 +73,70 @@ import Testing
            launchdSnapshot: snapshot)
        #expect(password == "launchd-pass")
    }
+
+    @Test func connectionModeResolverPrefersConfigModeOverDefaults() {
+        let defaults = self.makeDefaults()
+        defaults.set("remote", forKey: connectionModeKey)
+
+        let root: [String: Any] = [
+            "gateway": [
+                "mode": " local ",
+            ],
+        ]
+
+        let resolved = ConnectionModeResolver.resolve(root: root, defaults: defaults)
+        #expect(resolved.mode == .local)
+    }
+
+    @Test func connectionModeResolverTrimsConfigMode() {
+        let defaults = self.makeDefaults()
+        defaults.set("local", forKey: connectionModeKey)
+
+        let root: [String: Any] = [
+            "gateway": [
+                "mode": " remote ",
+            ],
+        ]
+
+        let resolved = ConnectionModeResolver.resolve(root: root, defaults: defaults)
+        #expect(resolved.mode == .remote)
+    }
+
+    @Test func connectionModeResolverFallsBackToDefaultsWhenMissingConfig() {
+        let defaults = self.makeDefaults()
+        defaults.set("remote", forKey: connectionModeKey)
+
+        let resolved = ConnectionModeResolver.resolve(root: [:], defaults: defaults)
+        #expect(resolved.mode == .remote)
+    }
+
+    @Test func connectionModeResolverFallsBackToDefaultsOnUnknownConfig() {
+        let defaults = self.makeDefaults()
+        defaults.set("local", forKey: connectionModeKey)
+
+        let root: [String: Any] = [
+            "gateway": [
+                "mode": "staging",
+            ],
+        ]
+
+        let resolved = ConnectionModeResolver.resolve(root: root, defaults: defaults)
+        #expect(resolved.mode == .local)
+    }
+
+    @Test func connectionModeResolverPrefersRemoteURLWhenModeMissing() {
+        let defaults = self.makeDefaults()
+        defaults.set("local", forKey: connectionModeKey)
+
+        let root: [String: Any] = [
+            "gateway": [
+                "remote": [
+                    "url": " ws://umbrel:18789 ",
+                ],
+            ],
+        ]
+
+        let resolved = ConnectionModeResolver.resolve(root: root, defaults: defaults)
+        #expect(resolved.mode == .remote)
+    }
 }
@@ -39,7 +39,7 @@ struct InstancesSettingsSmokeTests {
                host: "gateway",
                ip: "10.0.0.4",
                version: "3.0.0",
-                platform: "iOS 17",
+                platform: "iOS 18",
                deviceFamily: nil,
                modelIdentifier: nil,
                lastInputSeconds: nil,
@@ -8,7 +8,7 @@ import Testing
        let wav = makeWav16Mono(sampleRate: 8000, samples: 80)
        defer { _ = TalkAudioPlayer.shared.stop() }

-        _ = try await withTimeout(seconds: 2.0) {
+        _ = try await withTimeout(seconds: 4.0) {
            await TalkAudioPlayer.shared.play(data: wav)
        }

@@ -27,7 +27,7 @@ import Testing
        await Task.yield()
        _ = await TalkAudioPlayer.shared.play(data: wav)

-        _ = try await withTimeout(seconds: 2.0) {
+        _ = try await withTimeout(seconds: 4.0) {
            await first.value
        }
        #expect(true)
@@ -5,7 +5,7 @@ import PackageDescription
 let package = Package(
    name: "ClawdbotKit",
    platforms: [
-        .iOS(.v17),
+        .iOS(.v18),
        .macOS(.v15),
    ],
    products: [
@@ -14,6 +14,7 @@ let package = Package(
    ],
    dependencies: [
        .package(url: "https://github.com/steipete/ElevenLabsKit", exact: "0.1.0"),
+        .package(url: "https://github.com/gonzalezreal/textual", exact: "0.2.0"),
    ],
    targets: [
        .target(
@@ -29,7 +30,13 @@ let package = Package(
            ]),
        .target(
            name: "ClawdbotChatUI",
-            dependencies: ["ClawdbotKit"],
+            dependencies: [
+                "ClawdbotKit",
+                .product(
+                    name: "Textual",
+                    package: "textual",
+                    condition: .when(platforms: [.macOS, .iOS])),
+            ],
            swiftSettings: [
                .enableUpcomingFeature("StrictConcurrency"),
            ]),
@@ -0,0 +1,51 @@
+import Foundation
+
+enum ChatMarkdownPreprocessor {
+    struct InlineImage: Identifiable {
+        let id = UUID()
+        let label: String
+        let image: ClawdbotPlatformImage?
+    }
+
+    struct Result {
+        let cleaned: String
+        let images: [InlineImage]
+    }
+
+    static func preprocess(markdown raw: String) -> Result {
+        let pattern = #"!\[([^\]]*)\]\((data:image\/[^;]+;base64,[^)]+)\)"#
+        guard let re = try? NSRegularExpression(pattern: pattern) else {
+            return Result(cleaned: raw, images: [])
+        }
+
+        let ns = raw as NSString
+        let matches = re.matches(in: raw, range: NSRange(location: 0, length: ns.length))
+        if matches.isEmpty { return Result(cleaned: raw, images: []) }
+
+        var images: [InlineImage] = []
+        var cleaned = raw
+
+        for match in matches.reversed() {
+            guard match.numberOfRanges >= 3 else { continue }
+            let label = ns.substring(with: match.range(at: 1))
+            let dataURL = ns.substring(with: match.range(at: 2))
+
+            let image: ClawdbotPlatformImage? = {
+                guard let comma = dataURL.firstIndex(of: ",") else { return nil }
+                let b64 = String(dataURL[dataURL.index(after: comma)...])
+                guard let data = Data(base64Encoded: b64) else { return nil }
+                return ClawdbotPlatformImage(data: data)
+            }()
+            images.append(InlineImage(label: label, image: image))
+
+            let start = cleaned.index(cleaned.startIndex, offsetBy: match.range.location)
+            let end = cleaned.index(start, offsetBy: match.range.length)
+            cleaned.replaceSubrange(start..<end, with: "")
+        }
+
+        let normalized = cleaned
+            .replacingOccurrences(of: "\n\n\n", with: "\n\n")
+            .trimmingCharacters(in: .whitespacesAndNewlines)
+        return Result(cleaned: normalized, images: images.reversed())
+    }
+}
@@ -0,0 +1,90 @@
+import SwiftUI
+import Textual
+
+public enum ChatMarkdownVariant: String, CaseIterable, Sendable {
+    case standard
+    case compact
+}
+
+@MainActor
+struct ChatMarkdownRenderer: View {
+    enum Context {
+        case user
+        case assistant
+    }
+
+    let text: String
+    let context: Context
+    let variant: ChatMarkdownVariant
+    let font: Font
+    let textColor: Color
+
+    var body: some View {
+        let processed = ChatMarkdownPreprocessor.preprocess(markdown: self.text)
+        VStack(alignment: .leading, spacing: 10) {
+            StructuredText(markdown: processed.cleaned)
+                .modifier(ChatMarkdownStyle(
+                    variant: self.variant,
+                    context: self.context,
+                    font: self.font,
+                    textColor: self.textColor))
+
+            if !processed.images.isEmpty {
+                InlineImageList(images: processed.images)
+            }
+        }
+    }
+}
+
+private struct ChatMarkdownStyle: ViewModifier {
+    let variant: ChatMarkdownVariant
+    let context: ChatMarkdownRenderer.Context
+    let font: Font
+    let textColor: Color
+
+    func body(content: Content) -> some View {
+        Group {
+            if self.variant == .compact {
+                content.textual.structuredTextStyle(.default)
+            } else {
+                content.textual.structuredTextStyle(.gitHub)
+            }
+        }
+        .font(self.font)
+        .foregroundStyle(self.textColor)
+        .textual.inlineStyle(self.inlineStyle)
+        .textual.textSelection(.enabled)
+    }
+
+    private var inlineStyle: InlineStyle {
+        let linkColor: Color = self.context == .user ? self.textColor : .accentColor
+        let codeScale: CGFloat = self.variant == .compact ? 0.85 : 0.9
+        return InlineStyle()
+            .code(.monospaced, .fontScale(codeScale))
+            .link(.foregroundColor(linkColor))
+    }
+}
+
+@MainActor
+private struct InlineImageList: View {
+    let images: [ChatMarkdownPreprocessor.InlineImage]
+
+    var body: some View {
+        ForEach(images, id: \.id) { item in
+            if let img = item.image {
+                ClawdbotPlatformImageFactory.image(img)
+                    .resizable()
+                    .scaledToFit()
+                    .frame(maxHeight: 260)
+                    .clipShape(RoundedRectangle(cornerRadius: 12, style: .continuous))
+                    .overlay(
+                        RoundedRectangle(cornerRadius: 12, style: .continuous)
+                            .strokeBorder(Color.white.opacity(0.12), lineWidth: 1))
+            } else {
+                Text(item.label.isEmpty ? "Image" : item.label)
+                    .font(.footnote)
+                    .foregroundStyle(.secondary)
+            }
+        }
+    }
+}
@@ -1,114 +0,0 @@
-import Foundation
-
-enum ChatMarkdownSplitter {
-    struct InlineImage: Identifiable {
-        let id = UUID()
-        let label: String
-        let image: ClawdbotPlatformImage?
-    }
-
-    struct Block: Identifiable {
-        enum Kind: Equatable {
-            case text
-            case code(language: String?)
-        }
-
-        let id = UUID()
-        let kind: Kind
-        let text: String
-    }
-
-    struct SplitResult {
-        let blocks: [Block]
-        let images: [InlineImage]
-    }
-
-    static func split(markdown raw: String) -> SplitResult {
-        let extracted = self.extractInlineImages(from: raw)
-        let blocks = self.splitCodeBlocks(from: extracted.cleaned)
-        return SplitResult(blocks: blocks, images: extracted.images)
-    }
-
-    private static func splitCodeBlocks(from raw: String) -> [Block] {
-        var blocks: [Block] = []
-        var buffer: [String] = []
-        var inCode = false
-        var codeLang: String?
-        var codeLines: [String] = []
-
-        for line in raw.split(separator: "\n", omittingEmptySubsequences: false).map(String.init) {
-            if line.hasPrefix("```") {
-                if inCode {
-                    blocks.append(Block(kind: .code(language: codeLang), text: codeLines.joined(separator: "\n")))
-                    codeLines.removeAll(keepingCapacity: true)
-                    inCode = false
-                    codeLang = nil
-                } else {
-                    let text = buffer.joined(separator: "\n").trimmingCharacters(in: .whitespacesAndNewlines)
-                    if !text.isEmpty {
-                        blocks.append(Block(kind: .text, text: text))
-                    }
-                    buffer.removeAll(keepingCapacity: true)
-                    inCode = true
-                    codeLang = line.dropFirst(3).trimmingCharacters(in: .whitespacesAndNewlines)
-                    if codeLang?.isEmpty == true { codeLang = nil }
-                }
-                continue
-            }
-
-            if inCode {
-                codeLines.append(line)
-            } else {
-                buffer.append(line)
-            }
-        }
-
-        if inCode {
-            blocks.append(Block(kind: .code(language: codeLang), text: codeLines.joined(separator: "\n")))
-        } else {
-            let text = buffer.joined(separator: "\n").trimmingCharacters(in: .whitespacesAndNewlines)
-            if !text.isEmpty {
-                blocks.append(Block(kind: .text, text: text))
-            }
-        }
-
-        return blocks.isEmpty ? [Block(kind: .text, text: raw)] : blocks
-    }
-
-    private static func extractInlineImages(from raw: String) -> (cleaned: String, images: [InlineImage]) {
-        let pattern = #"!\[([^\]]*)\]\((data:image\/[^;]+;base64,[^)]+)\)"#
-        guard let re = try? NSRegularExpression(pattern: pattern) else {
-            return (raw, [])
-        }
-
-        let ns = raw as NSString
-        let matches = re.matches(in: raw, range: NSRange(location: 0, length: ns.length))
-        if matches.isEmpty { return (raw, []) }
-
-        var images: [InlineImage] = []
-        var cleaned = raw
-
-        for match in matches.reversed() {
-            guard match.numberOfRanges >= 3 else { continue }
-            let label = ns.substring(with: match.range(at: 1))
-            let dataURL = ns.substring(with: match.range(at: 2))
-
-            let image: ClawdbotPlatformImage? = {
-                guard let comma = dataURL.firstIndex(of: ",") else { return nil }
-                let b64 = String(dataURL[dataURL.index(after: comma)...])
-                guard let data = Data(base64Encoded: b64) else { return nil }
-                return ClawdbotPlatformImage(data: data)
-            }()
-            images.append(InlineImage(label: label, image: image))
-
-            let start = cleaned.index(cleaned.startIndex, offsetBy: match.range.location)
-            let end = cleaned.index(start, offsetBy: match.range.length)
-            cleaned.replaceSubrange(start..<end, with: "")
-        }
-
-        let normalized = cleaned
-            .replacingOccurrences(of: "\n\n\n", with: "\n\n")
-            .trimmingCharacters(in: .whitespacesAndNewlines)
-        return (normalized, images.reversed())
-    }
-}
@@ -137,10 +137,16 @@ private struct ChatBubbleShape: InsettableShape {
 struct ChatMessageBubble: View {
    let message: ClawdbotChatMessage
    let style: ClawdbotChatView.Style
+    let markdownVariant: ChatMarkdownVariant
    let userAccent: Color?

    var body: some View {
-        ChatMessageBody(message: self.message, isUser: self.isUser, style: self.style, userAccent: self.userAccent)
+        ChatMessageBody(
+            message: self.message,
+            isUser: self.isUser,
+            style: self.style,
+            markdownVariant: self.markdownVariant,
+            userAccent: self.userAccent)
            .frame(maxWidth: ChatUIConstants.bubbleMaxWidth, alignment: self.isUser ? .trailing : .leading)
            .frame(maxWidth: .infinity, alignment: self.isUser ? .trailing : .leading)
            .padding(.horizontal, 2)
@@ -154,6 +160,7 @@ private struct ChatMessageBody: View {
    let message: ClawdbotChatMessage
    let isUser: Bool
    let style: ClawdbotChatView.Style
+    let markdownVariant: ChatMarkdownVariant
    let userAccent: Color?

    var body: some View {
@@ -169,39 +176,14 @@ private struct ChatMessageBody: View {
                        isUser: self.isUser)
                }
            } else if self.isUser {
-                let split = ChatMarkdownSplitter.split(markdown: text)
-                ForEach(split.blocks) { block in
-                    switch block.kind {
-                    case .text:
-                        MarkdownTextView(text: block.text, textColor: textColor, font: .system(size: 14))
-                    case let .code(language):
-                        CodeBlockView(code: block.text, language: language, isUser: self.isUser)
-                    }
-                }
-
-                if !split.images.isEmpty {
-                    ForEach(
-                        split.images,
-                        id: \ChatMarkdownSplitter.InlineImage.id)
-                    { (item: ChatMarkdownSplitter.InlineImage) in
-                        if let img = item.image {
-                            ClawdbotPlatformImageFactory.image(img)
-                                .resizable()
-                                .scaledToFit()
-                                .frame(maxHeight: 260)
-                                .clipShape(RoundedRectangle(cornerRadius: 12, style: .continuous))
-                                .overlay(
-                                    RoundedRectangle(cornerRadius: 12, style: .continuous)
-                                        .strokeBorder(Color.white.opacity(0.12), lineWidth: 1))
-                        } else {
-                            Text(item.label.isEmpty ? "Image" : item.label)
-                                .font(.footnote)
-                                .foregroundStyle(.secondary)
-                        }
-                    }
-                }
+                ChatMarkdownRenderer(
+                    text: text,
+                    context: .user,
+                    variant: self.markdownVariant,
+                    font: .system(size: 14),
+                    textColor: textColor)
            } else {
-                ChatAssistantTextBody(text: text)
+                ChatAssistantTextBody(text: text, markdownVariant: self.markdownVariant)
            }

            if !self.inlineAttachments.isEmpty {
@@ -505,10 +487,11 @@ extension ChatTypingIndicatorBubble: @MainActor Equatable {
@MainActor
 struct ChatStreamingAssistantBubble: View {
    let text: String
+    let markdownVariant: ChatMarkdownVariant

    var body: some View {
        VStack(alignment: .leading, spacing: 10) {
-            ChatAssistantTextBody(text: self.text)
+            ChatAssistantTextBody(text: self.text, markdownVariant: self.markdownVariant)
        }
        .padding(12)
        .background(
@@ -612,114 +595,22 @@ private struct TypingDots: View {
    }
 }

-@MainActor
-private struct MarkdownTextView: View {
-    let text: String
-    let textColor: Color
-    let font: Font
-
-    var body: some View {
-        let normalized = self.text.replacingOccurrences(
-            of: "(?<!\\n)\\n(?!\\n)",
-            with: " ",
-            options: .regularExpression)
-        let options = AttributedString.MarkdownParsingOptions(
-            interpretedSyntax: .inlineOnlyPreservingWhitespace)
-        if let attributed = try? AttributedString(markdown: normalized, options: options) {
-            Text(attributed)
-                .font(self.font)
-                .foregroundStyle(self.textColor)
-        } else {
-            Text(normalized)
-                .font(self.font)
-                .foregroundStyle(self.textColor)
-        }
-    }
-}
-
-@MainActor
 private struct ChatAssistantTextBody: View {
    let text: String
+    let markdownVariant: ChatMarkdownVariant

    var body: some View {
        let segments = AssistantTextParser.segments(from: self.text)
        VStack(alignment: .leading, spacing: 10) {
            ForEach(segments) { segment in
                let font = segment.kind == .thinking ? Font.system(size: 14).italic() : Font.system(size: 14)
-                ChatMarkdownBody(text: segment.text, textColor: ClawdbotChatTheme.assistantText, font: font)
+                ChatMarkdownRenderer(
+                    text: segment.text,
+                    context: .assistant,
+                    variant: self.markdownVariant,
+                    font: font,
+                    textColor: ClawdbotChatTheme.assistantText)
            }
        }
    }
 }
-
-@MainActor
-private struct ChatMarkdownBody: View {
-    let text: String
-    let textColor: Color
-    let font: Font
-
-    var body: some View {
-        let split = ChatMarkdownSplitter.split(markdown: self.text)
-        VStack(alignment: .leading, spacing: 10) {
-            ForEach(split.blocks) { block in
-                switch block.kind {
-                case .text:
-                    MarkdownTextView(text: block.text, textColor: self.textColor, font: self.font)
-                case let .code(language):
-                    CodeBlockView(code: block.text, language: language, isUser: false)
-                }
-            }
-
-            if !split.images.isEmpty {
-                ForEach(
-                    split.images,
-                    id: \ChatMarkdownSplitter.InlineImage.id)
-                { (item: ChatMarkdownSplitter.InlineImage) in
-                    if let img = item.image {
-                        ClawdbotPlatformImageFactory.image(img)
-                            .resizable()
-                            .scaledToFit()
-                            .frame(maxHeight: 260)
-                            .clipShape(RoundedRectangle(cornerRadius: 12, style: .continuous))
-                            .overlay(
-                                RoundedRectangle(cornerRadius: 12, style: .continuous)
-                                    .strokeBorder(Color.white.opacity(0.12), lineWidth: 1))
-                    } else {
-                        Text(item.label.isEmpty ? "Image" : item.label)
-                            .font(.footnote)
-                            .foregroundStyle(.secondary)
-                    }
-                }
-            }
-        }
-        .textSelection(.enabled)
-    }
-}
-
-@MainActor
-private struct CodeBlockView: View {
-    let code: String
-    let language: String?
-    let isUser: Bool
-
-    var body: some View {
-        VStack(alignment: .leading, spacing: 8) {
-            if let language, !language.isEmpty {
-                Text(language)
-                    .font(.caption2.monospaced())
-                    .foregroundStyle(.secondary)
-            }
-            Text(self.code)
-                .font(.system(size: 13, weight: .regular, design: .monospaced))
-                .foregroundStyle(self.isUser ? .white : .primary)
-                .textSelection(.enabled)
-        }
-        .padding(12)
-        .frame(maxWidth: .infinity, alignment: .leading)
-        .background(self.isUser ? Color.white.opacity(0.16) : Color.black.opacity(0.06))
-        .overlay(
-            RoundedRectangle(cornerRadius: 12, style: .continuous)
-                .strokeBorder(Color.black.opacity(0.08), lineWidth: 1))
-        .clipShape(RoundedRectangle(cornerRadius: 12, style: .continuous))
-    }
-}
@@ -14,6 +14,7 @@ public struct ClawdbotChatView: View {
    @State private var hasPerformedInitialScroll = false
    private let showsSessionSwitcher: Bool
    private let style: Style
+    private let markdownVariant: ChatMarkdownVariant
    private let userAccent: Color?

    private enum Layout {
@@ -42,11 +43,13 @@ public struct ClawdbotChatView: View {
        viewModel: ClawdbotChatViewModel,
        showsSessionSwitcher: Bool = false,
        style: Style = .standard,
+        markdownVariant: ChatMarkdownVariant = .standard,
        userAccent: Color? = nil)
    {
        self._viewModel = State(initialValue: viewModel)
        self.showsSessionSwitcher = showsSessionSwitcher
        self.style = style
+        self.markdownVariant = markdownVariant
        self.userAccent = userAccent
    }

@@ -151,7 +154,11 @@ public struct ClawdbotChatView: View {
    @ViewBuilder
    private var messageListRows: some View {
        ForEach(self.visibleMessages) { msg in
-            ChatMessageBubble(message: msg, style: self.style, userAccent: self.userAccent)
+            ChatMessageBubble(
+                message: msg,
+                style: self.style,
+                markdownVariant: self.markdownVariant,
+                userAccent: self.userAccent)
                .frame(
                    maxWidth: .infinity,
                    alignment: msg.role.lowercased() == "user" ? .trailing : .leading)
@@ -172,7 +179,7 @@ public struct ClawdbotChatView: View {
        }

        if let text = self.viewModel.streamingAssistantText, AssistantTextParser.hasVisibleContent(in: text) {
-            ChatStreamingAssistantBubble(text: text)
+            ChatStreamingAssistantBubble(text: text, markdownVariant: self.markdownVariant)
                .frame(maxWidth: .infinity, alignment: .leading)
        }
    }
@@ -0,0 +1,20 @@
+import Testing
+@testable import ClawdbotChatUI
+
+@Suite("ChatMarkdownPreprocessor")
+struct ChatMarkdownPreprocessorTests {
+    @Test func extractsDataURLImages() {
+        let base64 = "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVQIHWP4////GQAJ+wP/2hN8NwAAAABJRU5ErkJggg=="
+        let markdown = """
+        Hello
+
+        ![Pixel](data:image/png;base64,\(base64))
+        """
+
+        let result = ChatMarkdownPreprocessor.preprocess(markdown: markdown)
+
+        #expect(result.cleaned == "Hello")
+        #expect(result.images.count == 1)
+        #expect(result.images.first?.image != nil)
+    }
+}
@@ -101,6 +101,29 @@ group messages, so use admin if you need full visibility.
 - Raw HTML from models is escaped to avoid Telegram parse errors.
 - If Telegram rejects the HTML payload, Clawdbot retries the same message as plain text.

+## Commands (native + custom)
+Clawdbot registers native commands (like `/status`, `/reset`, `/model`) with Telegram’s bot menu on startup.
+You can add custom commands to the menu via config:
+
+```json5
+{
+  channels: {
+    telegram: {
+      customCommands: [
+        { command: "backup", description: "Git backup" },
+        { command: "generate", description: "Create an image" }
+      ]
+    }
+  }
+}
+```
+
+Notes:
+- Custom commands are **menu entries only**; Clawdbot does not implement them unless you handle them elsewhere.
+- Command names are normalized (leading `/` stripped, lowercased) and must match `a-z`, `0-9`, `_` (1–32 chars).
+- Custom commands **cannot override native commands**. Conflicts are ignored and logged.
+- If `commands.native` is disabled, only custom commands are registered (or cleared if none).
+
 ## Limits
 - Outbound text is chunked to `channels.telegram.textChunkLimit` (default 4000).
 - Media downloads/uploads are capped by `channels.telegram.mediaMaxMb` (default 5).
@@ -82,15 +82,13 @@ When the wizard asks for your personal WhatsApp number, enter the phone you will
    "selfChatMode": true,
    "dmPolicy": "allowlist",
    "allowFrom": ["+15551234567"]
-  },
-  "messages": {
-    "responsePrefix": "[clawdbot]"
  }
 }
 ```

-Tip: set `messages.responsePrefix` explicitly if you want a consistent bot prefix
-on outbound replies.
+Self-chat replies default to `[{identity.name}]` when set (otherwise `[clawdbot]`)
+if `messages.responsePrefix` is unset. Set it explicitly to customize or disable
+the prefix (use `""` to remove it).

 ### Number sourcing tips
 - **Local eSIM** from your country's mobile carrier (most reliable)
@@ -21,3 +21,14 @@ clawdbot doctor --repair
 clawdbot doctor --deep
 ```

+## macOS: `launchctl` env overrides
+
+If you previously ran `launchctl setenv CLAWDBOT_GATEWAY_TOKEN ...` (or `...PASSWORD`), that value overrides your config file and can cause persistent “unauthorized” errors.
+
+```bash
+launchctl getenv CLAWDBOT_GATEWAY_TOKEN
+launchctl getenv CLAWDBOT_GATEWAY_PASSWORD
+
+launchctl unsetenv CLAWDBOT_GATEWAY_TOKEN
+launchctl unsetenv CLAWDBOT_GATEWAY_PASSWORD
+```
@@ -871,6 +871,7 @@ Notes:
 - `commands.text: false` disables parsing chat messages for commands.
 - `commands.native: "auto"` (default) turns on native commands for Discord/Telegram and leaves Slack off; unsupported channels stay text-only.
 - Set `commands.native: true|false` to force all, or override per channel with `channels.discord.commands.native`, `channels.telegram.commands.native`, `channels.slack.commands.native` (bool or `"auto"`). `false` clears previously registered commands on Discord/Telegram at startup; Slack commands are managed in the Slack app.
+- `channels.telegram.customCommands` adds extra Telegram bot menu entries. Names are normalized; conflicts with native commands are ignored.
 - `commands.bash: true` enables `! <cmd>` to run host shell commands (`/bash <cmd>` also works as an alias). Requires `tools.elevated.enabled` and allowlisting the sender in `tools.elevated.allowFrom.<channel>`.
 - `commands.bashForegroundMs` controls how long bash waits before backgrounding. While a bash job is running, new `! <cmd>` requests are rejected (one at a time).
 - `commands.config: true` enables `/config` (reads/writes `clawdbot.json`).
@@ -929,6 +930,10 @@ Set `channels.telegram.configWrites: false` to block Telegram-initiated config w
          }
        }
      },
+      customCommands: [
+        { command: "backup", description: "Git backup" },
+        { command: "generate", description: "Create an image" }
+      ],
      historyLimit: 50,                     // include last N group messages as context (0 disables)
      replyToMode: "first",                 // off | first | all
      streamMode: "partial",               // off | partial | block (draft streaming; separate from block streaming)
@@ -1266,7 +1271,9 @@ See [Messages](/concepts/messages) for queueing, sessions, and streaming context
 `responsePrefix` is applied to **all outbound replies** (tool summaries, block
 streaming, final replies) across channels unless already present.

-If `messages.responsePrefix` is unset, no prefix is applied by default.
+If `messages.responsePrefix` is unset, no prefix is applied by default. WhatsApp self-chat
+replies are the exception: they default to `[{identity.name}]` when set, otherwise
+`[clawdbot]`, so same-phone conversations stay legible.
 Set it to `"auto"` to derive `[{identity.name}]` for the routed agent (when set).

 #### Template variables
@@ -161,6 +161,15 @@ Even with strong system prompts, **prompt injection is not solved**. What helps
 - Run sensitive tool execution in a sandbox; keep secrets out of the agent’s reachable filesystem.
 - **Model choice matters:** older/legacy models can be less robust against prompt injection and tool misuse. Prefer modern, instruction-hardened models for any bot with tools. We recommend Anthropic Opus 4.5 because it’s quite good at recognizing prompt injections (see [“A step forward on safety”](https://www.anthropic.com/news/claude-opus-4-5)).

+### Model strength (security note)
+
+Prompt injection resistance is **not** uniform across model tiers. Smaller/cheaper models are generally more susceptible to tool misuse and instruction hijacking, especially under adversarial prompts.
+
+Recommendations:
+- **Use the latest generation, best-tier model** for any bot that can run tools or touch files/networks.
+- **Avoid weaker tiers** (for example, Sonnet or Haiku) for tool-enabled agents or untrusted inboxes.
+- If you must use a smaller model, **reduce blast radius** (read-only tools, strong sandboxing, minimal filesystem access, strict allowlists).
+
 ## Reasoning & verbose output in groups

 `/reasoning` and `/verbose` can expose internal reasoning or tool output that
@@ -1355,9 +1355,11 @@ Facts (from code):

 Fix:
 - Fastest: `clawdbot dashboard` (prints + copies tokenized link, tries to open; shows SSH hint if headless).
+- If you don’t have a token yet: `clawdbot doctor --generate-gateway-token`.
 - If remote, tunnel first: `ssh -N -L 18789:127.0.0.1:18789 user@host` then open `http://127.0.0.1:18789/?token=...`.
 - Set `gateway.auth.token` (or `CLAWDBOT_GATEWAY_TOKEN`) on the gateway host.
 - In the Control UI settings, paste the same token (or refresh with a one-time `?token=...` link).
+- Still stuck? Run `clawdbot status --all` and follow [Troubleshooting](/gateway/troubleshooting). See [Dashboard](/web/dashboard) for auth details.

 ### I set `gateway.bind: "tailnet"` but it can’t bind / nothing listens

@@ -146,6 +146,19 @@ Full setup walkthrough (28m) by VelvetShark.

  14+ agents under one gateway with Opus 4.5 orchestrator delegating to Codex workers. Comprehensive [technical write-up](https://github.com/adam91holt/orchestrated-ai-articles) covering the Dream Team roster, model selection, sandboxing, webhooks, heartbeats, and delegation flows. [Clawdspace](https://github.com/adam91holt/clawdspace) for agent sandboxing. [Blog post](https://adams-ai-journey.ghost.io/2026-the-year-of-the-orchestrator/).
 </Card>
+
+<Card title="Linear CLI" icon="terminal" href="https://github.com/Finesssee/linear-cli">
+  **@NessZerra** • `devtools` `linear` `cli` `issues`
+
+  CLI for Linear that integrates with agentic workflows (Claude Code, Clawdbot). Manage issues, projects, and workflows from the terminal. First external PR merged!
+</Card>
+
+<Card title="Beeper CLI" icon="message" href="https://github.com/blqke/beepcli">
+  **@jules** • `messaging` `beeper` `cli` `automation`
+
+  Read, send, and archive messages via Beeper Desktop. Uses Beeper local MCP API so agents can manage all your chats (iMessage, WhatsApp, etc.) in one place.
+</Card>
+
 </CardGroup>

 ## 🤖 Automation & Workflows
@@ -59,6 +59,8 @@ Browser settings live in `~/.clawdbot/clawdbot.json`.
    enabled: true,                    // default: true
    controlUrl: "http://127.0.0.1:18791",
    cdpUrl: "http://127.0.0.1:18792", // defaults to controlUrl + 1
+    remoteCdpTimeoutMs: 1500,         // remote CDP HTTP timeout (ms)
+    remoteCdpHandshakeTimeoutMs: 3000, // remote CDP WebSocket handshake timeout (ms)
    defaultProfile: "chrome",
    color: "#FF4500",
    headless: false,
@@ -79,6 +81,8 @@ Notes:
 - If you override the Gateway port (`gateway.port` or `CLAWDBOT_GATEWAY_PORT`),
  the default browser ports shift to stay in the same “family” (control = gateway + 2).
 - `cdpUrl` defaults to `controlUrl + 1` when unset.
+- `remoteCdpTimeoutMs` applies to remote (non-loopback) CDP reachability checks.
+- `remoteCdpHandshakeTimeoutMs` applies to remote CDP WebSocket reachability checks.
 - `attachOnly: true` means “never launch a local browser; only attach if it is already running.”
 - `color` + per-profile `color` tint the browser UI so you can see which profile is active.
 - Default profile is `chrome` (extension relay). Use `defaultProfile: "clawd"` for the managed browser.
@@ -154,6 +158,42 @@ Example:
 Use `profiles.<name>.cdpUrl` for **remote CDP** if you want the Gateway to talk
 directly to a Chromium-based browser instance without a remote control server.

+Remote CDP URLs can include auth:
+- Query tokens (e.g., `https://provider.example?token=<token>`)
+- HTTP Basic auth (e.g., `https://user:pass@provider.example`)
+
+Clawdbot preserves the auth when calling `/json/*` endpoints and when connecting
+to the CDP WebSocket. Prefer environment variables or secrets managers for
+tokens instead of committing them to config files.
+
+### Browserless (hosted remote CDP)
+
+[Browserless](https://browserless.io) is a hosted Chromium service that exposes
+CDP endpoints over HTTPS. You can point a Clawdbot browser profile at a
+Browserless region endpoint and authenticate with your API key.
+
+Example:
+```json5
+{
+  browser: {
+    enabled: true,
+    defaultProfile: "browserless",
+    remoteCdpTimeoutMs: 2000,
+    remoteCdpHandshakeTimeoutMs: 4000,
+    profiles: {
+      browserless: {
+        cdpUrl: "https://production-sfo.browserless.io?token=<BROWSERLESS_API_KEY>",
+        color: "#00AA00"
+      }
+    }
+  }
+}
+```
+
+Notes:
+- Replace `<BROWSERLESS_API_KEY>` with your real Browserless token.
+- Choose the region endpoint that matches your Browserless account (see their docs).
+
 ### Running the control server on the browser machine

 Run a standalone browser control server (recommended when your Gateway is remote):
@@ -80,6 +80,8 @@ Notes:
 - Use `{baseDir}` in instructions to reference the skill folder path.
 - Optional frontmatter keys:
  - `homepage` — URL surfaced as “Website” in the macOS Skills UI (also supported via `metadata.clawdbot.homepage`).
+  - `user-invocable` — `true|false` (default: `true`). When `true`, the skill is exposed as a user slash command.
+  - `disable-model-invocation` — `true|false` (default: `false`). When `true`, the skill is excluded from the model prompt (still available via user invocation).

 ## Gating (load-time filters)

@@ -96,6 +96,7 @@ Notes:
  - Example: `hey /status` triggers a status reply, and the remaining text continues through the normal flow.
  - Currently: `/help`, `/commands`, `/status` (`/usage`), `/whoami` (`/id`).
 - Unauthorized command-only messages are silently ignored, and inline `/...` tokens are treated as plain text.
+- **Skill commands:** `user-invocable` skills are exposed as slash commands. Names are sanitized to `a-z0-9_` (max 32 chars); collisions get numeric suffixes (e.g. `_2`).
 - **Native command arguments:** Discord uses autocomplete for dynamic options (and button menus when you omit required args). Telegram and Slack show a button menu when a command supports choices and you omit the arg.

 ## Usage vs cost (what shows where)
@@ -43,6 +43,15 @@ Auto-archive:
 - Auto-archive is best-effort; pending timers are lost if the gateway restarts.
 - `runTimeoutSeconds` does **not** auto-archive; it only stops the run. The session remains until auto-archive.

+## Authentication
+
+Sub-agent auth is resolved by **agent id**, not by session type:
+- The sub-agent session key is `agent:<agentId>:subagent:<uuid>`.
+- The auth store is loaded from that agent’s `agentDir`.
+- The main agent’s auth profiles are merged in as a **fallback**; agent profiles override main profiles on conflicts.
+
+Note: the merge is additive, so main profiles are always available as fallbacks. Fully isolated auth per agent is not supported yet.
+
 ## Announce

 Sub-agents report back via an announce step:
@@ -323,38 +323,41 @@ run_profile() {
  local workspace="$3"
  local agent_model_provider="$4" # "openai"|"anthropic"

-  echo "==> Onboard ($profile)"
-  if [[ "$agent_model_provider" == "openai" ]]; then
-    clawdbot --profile "$profile" onboard \
-      --non-interactive \
-      --flow quickstart \
-      --auth-choice openai-api-key \
-      --openai-api-key "$OPENAI_API_KEY" \
-      --gateway-port "$port" \
+	  echo "==> Onboard ($profile)"
+	  if [[ "$agent_model_provider" == "openai" ]]; then
+	    clawdbot --profile "$profile" onboard \
+	      --non-interactive \
+	      --accept-risk \
+	      --flow quickstart \
+	      --auth-choice openai-api-key \
+	      --openai-api-key "$OPENAI_API_KEY" \
+	      --gateway-port "$port" \
+	      --gateway-bind loopback \
+      --gateway-auth token \
+      --workspace "$workspace" \
+      --skip-health
+	  elif [[ -n "$ANTHROPIC_API_TOKEN" ]]; then
+	    clawdbot --profile "$profile" onboard \
+	      --non-interactive \
+	      --accept-risk \
+	      --flow quickstart \
+	      --auth-choice token \
+	      --token-provider anthropic \
+	      --token "$ANTHROPIC_API_TOKEN" \
+	      --gateway-port "$port" \
      --gateway-bind loopback \
      --gateway-auth token \
      --workspace "$workspace" \
      --skip-health
-  elif [[ -n "$ANTHROPIC_API_TOKEN" ]]; then
-    clawdbot --profile "$profile" onboard \
-      --non-interactive \
-      --flow quickstart \
-      --auth-choice token \
-      --token-provider anthropic \
-      --token "$ANTHROPIC_API_TOKEN" \
-      --gateway-port "$port" \
-      --gateway-bind loopback \
-      --gateway-auth token \
-      --workspace "$workspace" \
-      --skip-health
-  else
-    clawdbot --profile "$profile" onboard \
-      --non-interactive \
-      --flow quickstart \
-      --auth-choice apiKey \
-      --anthropic-api-key "$ANTHROPIC_API_KEY" \
-      --gateway-port "$port" \
-      --gateway-bind loopback \
+	  else
+	    clawdbot --profile "$profile" onboard \
+	      --non-interactive \
+	      --accept-risk \
+	      --flow quickstart \
+	      --auth-choice apiKey \
+	      --anthropic-api-key "$ANTHROPIC_API_KEY" \
+	      --gateway-port "$port" \
+	      --gateway-bind loopback \
      --gateway-auth token \
      --workspace "$workspace" \
      --skip-health
@@ -69,15 +69,20 @@ if [[ "$*" == *"enable-linger"* ]]; then
 fi
 exit 0
 LOGINCTL
-	  chmod +x /tmp/clawdbot-bin/loginctl
-	
-	  # Install the npm-global variant from the local /app source.
-	  pkg_tgz="$(npm pack --silent /app)"
-	  npm install -g --prefix /tmp/npm-prefix "/app/$pkg_tgz"
-	
-	  npm_bin="/tmp/npm-prefix/bin/clawdbot"
-	  npm_entry="/tmp/npm-prefix/lib/node_modules/clawdbot/dist/entry.js"
-	  git_entry="/app/dist/entry.js"
+  chmod +x /tmp/clawdbot-bin/loginctl
+
+  # Install the npm-global variant from the local /app source.
+  # `npm pack` can emit script output; keep only the tarball name.
+  pkg_tgz="$(npm pack --silent /app | tail -n 1 | tr -d '\r')"
+  if [ ! -f "/app/$pkg_tgz" ]; then
+    echo "npm pack failed (expected /app/$pkg_tgz)"
+    exit 1
+  fi
+  npm install -g --prefix /tmp/npm-prefix "/app/$pkg_tgz"
+
+  npm_bin="/tmp/npm-prefix/bin/clawdbot"
+  npm_entry="/tmp/npm-prefix/lib/node_modules/clawdbot/dist/entry.js"
+  git_entry="/app/dist/entry.js"

  assert_entrypoint() {
    local unit_path="$1"
@@ -126,17 +131,17 @@ LOGINCTL
    assert_entrypoint "$unit_path" "$doctor_expected"
  }

-	  run_flow \
-	    "npm-to-git" \
-	    "$npm_bin daemon install --force" \
-	    "$npm_entry" \
-	    "node $git_entry doctor --repair --force" \
-	    "$git_entry"
+  run_flow \
+    "npm-to-git" \
+    "$npm_bin daemon install --force" \
+    "$npm_entry" \
+    "node $git_entry doctor --repair --force" \
+    "$git_entry"

-	  run_flow \
-	    "git-to-npm" \
-	    "node $git_entry daemon install --force" \
-	    "$git_entry" \
-	    "$npm_bin doctor --repair --force" \
-	    "$npm_entry"
+  run_flow \
+    "git-to-npm" \
+    "node $git_entry daemon install --force" \
+    "$git_entry" \
+    "$npm_bin doctor --repair --force" \
+    "$npm_entry"
 '
@@ -42,6 +42,38 @@ TRASH
    printf "%b" "$payload" >&3 2>/dev/null || true
  }

+  wait_for_log() {
+    local needle="$1"
+    local timeout_s="${2:-45}"
+    local needle_compact
+    needle_compact="$(printf "%s" "$needle" | sed -E "s/[[:space:]]+//g")"
+    local start_s
+    start_s="$(date +%s)"
+    while true; do
+      if [ -n "${WIZARD_LOG_PATH:-}" ] && [ -f "$WIZARD_LOG_PATH" ]; then
+        if NEEDLE="$needle_compact" node --input-type=module -e "
+          import fs from \"node:fs\";
+          const file = process.env.WIZARD_LOG_PATH;
+          const needle = process.env.NEEDLE ?? \"\";
+          let text = \"\";
+          try { text = fs.readFileSync(file, \"utf8\"); } catch { process.exit(1); }
+          text = text.replace(/\\x1b\\[[0-9;]*[A-Za-z]/g, \"\").replace(/\\s+/g, \"\");
+          process.exit(text.includes(needle) ? 0 : 1);
+        "; then
+          return 0
+        fi
+      fi
+      if [ $(( $(date +%s) - start_s )) -ge "$timeout_s" ]; then
+        echo "Timeout waiting for log: $needle"
+        if [ -n "${WIZARD_LOG_PATH:-}" ] && [ -f "$WIZARD_LOG_PATH" ]; then
+          tail -n 140 "$WIZARD_LOG_PATH" || true
+        fi
+        return 1
+      fi
+      sleep 0.2
+    done
+  }
+
  start_gateway() {
    node dist/index.js gateway --port 18789 --bind loopback --allow-unconfigured > /tmp/gateway-e2e.log 2>&1 &
    GATEWAY_PID="$!"
@@ -81,6 +113,8 @@ TRASH
    input_fifo="$(mktemp -u "/tmp/clawdbot-onboard-${case_name}.XXXXXX")"
    mkfifo "$input_fifo"
    local log_path="/tmp/clawdbot-onboard-${case_name}.log"
+    WIZARD_LOG_PATH="$log_path"
+    export WIZARD_LOG_PATH
    # Run under script to keep an interactive TTY for clack prompts.
    script -q -c "$command" "$log_path" < "$input_fifo" &
    wizard_pid=$!
@@ -135,36 +169,44 @@ TRASH
  }

  send_local_basic() {
+    # Risk acknowledgement (default is "No").
+    send $'"'"'y\r'"'"' 0.6
    # Choose local gateway, accept defaults, skip channels/skills/daemon, skip UI.
    send $'"'"'\r'"'"' 0.5
  }

-  send_reset_config_only() {
-    # Reset config + reuse the local defaults flow.
-    send $'"'"'\e[B'"'"' 0.3
-    send $'"'"'\e[B'"'"' 0.3
-    send $'"'"'\r'"'"' 0.4
-    send $'"'"'\r'"'"' 0.4
-    send "" 1.2
-    send_local_basic
-  }
+	  send_reset_config_only() {
+	    # Risk acknowledgement (default is "No").
+	    send $'"'"'y\r'"'"' 0.8
+	    # Reset config + reuse the local defaults flow.
+	    send $'"'"'\e[B'"'"' 0.3
+	    send $'"'"'\e[B'"'"' 0.3
+	    send $'"'"'\r'"'"' 0.4
+	    send $'"'"'\r'"'"' 0.4
+	    send "" 1.2
+	    send_local_basic
+	  }

  send_channels_flow() {
    # Configure channels via configure wizard.
-    send $'"'"'\r'"'"' 1.0
-    send "" 1.5
-    # Mode (default Configure channels)
-    send $'"'"'\r'"'"' 0.8
-    send "" 1.0
-    # Configure chat channels now? -> No
-    send $'"'"'n\r'"'"' 0.6
+    # Prompts are interactive; notes are not. Use conservative delays to stay in sync.
+    # Where will the Gateway run? -> Local (default)
+    send $'"'"'\r'"'"' 1.2
+    # Channels mode -> Configure/link (default)
+    send $'"'"'\r'"'"' 1.5
+    # Select a channel -> Finished (last option; clack wraps on Up)
+    send $'"'"'\e[A\r'"'"' 2.0
+    # Keep stdin open until wizard exits.
+    send "" 2.5
  }

  send_skills_flow() {
    # Select skills section and skip optional installs.
-    send $'"'"'\r'"'"' 1.0
-    send "" 1.2
-    send $'"'"'n\r'"'"' 0.6
+    send $'"'"'\r'"'"' 1.2
+    send "" 1.0
+    # Configure skills now? -> No
+    send $'"'"'n\r'"'"' 1.2
+    send "" 2.0
  }

  run_case_local_basic() {
@@ -257,7 +299,7 @@ NODE
    export HOME="$home_dir"
    mkdir -p "$HOME"
    # Smoke test non-interactive remote config write.
-    node dist/index.js onboard --non-interactive \
+    node dist/index.js onboard --non-interactive --accept-risk \
      --mode remote \
      --remote-url ws://gateway.local:18789 \
      --remote-token remote-token \
@@ -45,10 +45,19 @@ function which(cmd) {
 }

 function resolveRunner() {
-  const bun = which("bun");
-  if (bun) return { cmd: bun, kind: "bun" };
+  // CLAWDBOT_PREFER_PNPM=1 forces pnpm (useful in Docker on architectures where Bun fails)
+  const preferPnpm = process.env.CLAWDBOT_PREFER_PNPM === "1";
+  if (!preferPnpm) {
+    const bun = which("bun");
+    if (bun) return { cmd: bun, kind: "bun" };
+  }
  const pnpm = which("pnpm");
  if (pnpm) return { cmd: pnpm, kind: "pnpm" };
+  if (preferPnpm) {
+    // Fallback to bun if pnpm not found even when preferring pnpm
+    const bun = which("bun");
+    if (bun) return { cmd: bun, kind: "bun" };
+  }
  return null;
 }

@@ -19,13 +19,53 @@ open ~/Projects/tmp/openai-image-gen-*/index.html  # if ~/Projects/tmp exists; e
 Useful flags:

 ```bash
+# GPT image models with various options
 python3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-1
 python3 {baseDir}/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 4
 python3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images
+python3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp
+
+# DALL-E 3 (note: count is automatically limited to 1)
+python3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid
+python3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt "serene mountain landscape"
+
+# DALL-E 2
+python3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 4
 ```

+## Model-Specific Parameters
+
+Different models support different parameter values. The script automatically selects appropriate defaults based on the model.
+
+### Size
+
+- **GPT image models** (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`): `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto`
+  - Default: `1024x1024`
+- **dall-e-3**: `1024x1024`, `1792x1024`, or `1024x1792`
+  - Default: `1024x1024`
+- **dall-e-2**: `256x256`, `512x512`, or `1024x1024`
+  - Default: `1024x1024`
+
+### Quality
+
+- **GPT image models**: `auto`, `high`, `medium`, or `low`
+  - Default: `high`
+- **dall-e-3**: `hd` or `standard`
+  - Default: `standard`
+- **dall-e-2**: `standard` only
+  - Default: `standard`
+
+### Other Notable Differences
+
+- **dall-e-3** only supports generating 1 image at a time (`n=1`). The script automatically limits count to 1 when using this model.
+- **GPT image models** support additional parameters:
+  - `--background`: `transparent`, `opaque`, or `auto` (default)
+  - `--output-format`: `png` (default), `jpeg`, or `webp`
+  - Note: `stream` and `moderation` are available via API but not yet implemented in this script
+- **dall-e-3** has a `--style` parameter: `vivid` (hyper-real, dramatic) or `natural` (more natural looking)
+
 ## Output

- `*.png` images
+- `*.png`, `*.jpeg`, or `*.webp` images (output format depends on model + `--output-format`)
 - `prompts.json` (prompt → file mapping)
 - `index.html` (thumbnail gallery)
@@ -62,24 +62,53 @@ def pick_prompts(count: int) -> list[str]:
    return prompts


+def get_model_defaults(model: str) -> tuple[str, str]:
+    """Return (default_size, default_quality) for the given model."""
+    if model == "dall-e-2":
+        # quality will be ignored
+        return ("1024x1024", "standard")
+    elif model == "dall-e-3":
+        return ("1024x1024", "standard")
+    else:
+        # GPT image or future models
+        return ("1024x1024", "high")
+
+
 def request_images(
    api_key: str,
    prompt: str,
    model: str,
    size: str,
    quality: str,
+    background: str = "",
+    output_format: str = "",
+    style: str = "",
 ) -> dict:
    url = "https://api.openai.com/v1/images/generations"
-    body = json.dumps(
-        {
-            "model": model,
-            "prompt": prompt,
-            "size": size,
-            "quality": quality,
-            "n": 1,
-            "response_format": "b64_json",
-        }
-    ).encode("utf-8")
+    args = {
+        "model": model,
+        "prompt": prompt,
+        "size": size,
+        "n": 1,
+    }
+
+    # Quality parameter - dall-e-2 doesn't accept this parameter
+    if model != "dall-e-2":
+        args["quality"] = quality
+
+    if model.startswith("dall-e"):
+        args["response_format"] = "b64_json"
+
+    if model.startswith("gpt-image"):
+        if background:
+            args["background"] = background
+        if output_format:
+            args["output_format"] = output_format
+
+    if model == "dall-e-3" and style:
+        args["style"] = style
+
+    body = json.dumps(args).encode("utf-8")
    req = urllib.request.Request(
        url,
        method="POST",
@@ -136,8 +165,11 @@ def main() -> int:
    ap.add_argument("--prompt", help="Single prompt. If omitted, random prompts are generated.")
    ap.add_argument("--count", type=int, default=8, help="How many images to generate.")
    ap.add_argument("--model", default="gpt-image-1", help="Image model id.")
-    ap.add_argument("--size", default="1024x1024", help="Image size (e.g. 1024x1024, 1536x1024).")
-    ap.add_argument("--quality", default="high", help="Image quality (varies by model).")
+    ap.add_argument("--size", default="", help="Image size (e.g. 1024x1024, 1536x1024). Defaults based on model if not specified.")
+    ap.add_argument("--quality", default="", help="Image quality (e.g. high, standard). Defaults based on model if not specified.")
+    ap.add_argument("--background", default="", help="Background transparency (GPT models only): transparent, opaque, or auto.")
+    ap.add_argument("--output-format", default="", help="Output format (GPT models only): png, jpeg, or webp.")
+    ap.add_argument("--style", default="", help="Image style (dall-e-3 only): vivid or natural.")
    ap.add_argument("--out-dir", default="", help="Output directory (default: ./tmp/openai-image-gen-<ts>).")
    args = ap.parse_args()

@@ -146,21 +178,46 @@ def main() -> int:
        print("Missing OPENAI_API_KEY", file=sys.stderr)
        return 2

+    # Apply model-specific defaults if not specified
+    default_size, default_quality = get_model_defaults(args.model)
+    size = args.size or default_size
+    quality = args.quality or default_quality
+
+    count = args.count
+    if args.model == "dall-e-3" and count > 1:
+        print(f"Warning: dall-e-3 only supports generating 1 image at a time. Reducing count from {count} to 1.", file=sys.stderr)
+        count = 1
+
    out_dir = Path(args.out_dir).expanduser() if args.out_dir else default_out_dir()
    out_dir.mkdir(parents=True, exist_ok=True)

-    prompts = [args.prompt] * args.count if args.prompt else pick_prompts(args.count)
+    prompts = [args.prompt] * count if args.prompt else pick_prompts(count)
+
+    # Determine file extension based on output format
+    if args.model.startswith("gpt-image") and args.output_format:
+        file_ext = args.output_format
+    else:
+        file_ext = "png"

    items: list[dict] = []
    for idx, prompt in enumerate(prompts, start=1):
        print(f"[{idx}/{len(prompts)}] {prompt}")
-        res = request_images(api_key, prompt, args.model, args.size, args.quality)
+        res = request_images(
+            api_key,
+            prompt,
+            args.model,
+            size,
+            quality,
+            args.background,
+            args.output_format,
+            args.style,
+        )
        b64 = res.get("data", [{}])[0].get("b64_json")
        if not b64:
            raise RuntimeError(f"Unexpected response: {json.dumps(res)[:400]}")
-        png = base64.b64decode(b64)
-        filename = f"{idx:03d}-{slugify(prompt)[:40]}.png"
-        (out_dir / filename).write_bytes(png)
+        image_bytes = base64.b64decode(b64)
+        filename = f"{idx:03d}-{slugify(prompt)[:40]}.{file_ext}"
+        (out_dir / filename).write_bytes(image_bytes)
        items.append({"prompt": prompt, "file": filename})

    (out_dir / "prompts.json").write_text(json.dumps(items, indent=2), encoding="utf-8")
@@ -3,6 +3,7 @@ import os from "node:os";
 import path from "node:path";
 import { describe, expect, it } from "vitest";
 import { ensureAuthProfileStore } from "./auth-profiles.js";
+import { AUTH_STORE_VERSION } from "./auth-profiles/constants.js";

 describe("ensureAuthProfileStore", () => {
  it("migrates legacy auth.json and deletes it (PR #368)", () => {
@@ -45,4 +46,80 @@ describe("ensureAuthProfileStore", () => {
      fs.rmSync(agentDir, { recursive: true, force: true });
    }
  });
+
+  it("merges main auth profiles into agent store and keeps agent overrides", () => {
+    const root = fs.mkdtempSync(path.join(os.tmpdir(), "clawdbot-auth-merge-"));
+    const previousAgentDir = process.env.CLAWDBOT_AGENT_DIR;
+    const previousPiAgentDir = process.env.PI_CODING_AGENT_DIR;
+    try {
+      const mainDir = path.join(root, "main-agent");
+      const agentDir = path.join(root, "agent-x");
+      fs.mkdirSync(mainDir, { recursive: true });
+      fs.mkdirSync(agentDir, { recursive: true });
+
+      process.env.CLAWDBOT_AGENT_DIR = mainDir;
+      process.env.PI_CODING_AGENT_DIR = mainDir;
+
+      const mainStore = {
+        version: AUTH_STORE_VERSION,
+        profiles: {
+          "openai:default": {
+            type: "api_key",
+            provider: "openai",
+            key: "main-key",
+          },
+          "anthropic:default": {
+            type: "api_key",
+            provider: "anthropic",
+            key: "main-anthropic-key",
+          },
+        },
+      };
+      fs.writeFileSync(
+        path.join(mainDir, "auth-profiles.json"),
+        `${JSON.stringify(mainStore, null, 2)}\n`,
+        "utf8",
+      );
+
+      const agentStore = {
+        version: AUTH_STORE_VERSION,
+        profiles: {
+          "openai:default": {
+            type: "api_key",
+            provider: "openai",
+            key: "agent-key",
+          },
+        },
+      };
+      fs.writeFileSync(
+        path.join(agentDir, "auth-profiles.json"),
+        `${JSON.stringify(agentStore, null, 2)}\n`,
+        "utf8",
+      );
+
+      const store = ensureAuthProfileStore(agentDir);
+      expect(store.profiles["anthropic:default"]).toMatchObject({
+        type: "api_key",
+        provider: "anthropic",
+        key: "main-anthropic-key",
+      });
+      expect(store.profiles["openai:default"]).toMatchObject({
+        type: "api_key",
+        provider: "openai",
+        key: "agent-key",
+      });
+    } finally {
+      if (previousAgentDir === undefined) {
+        delete process.env.CLAWDBOT_AGENT_DIR;
+      } else {
+        process.env.CLAWDBOT_AGENT_DIR = previousAgentDir;
+      }
+      if (previousPiAgentDir === undefined) {
+        delete process.env.PI_CODING_AGENT_DIR;
+      } else {
+        process.env.PI_CODING_AGENT_DIR = previousPiAgentDir;
+      }
+      fs.rmSync(root, { recursive: true, force: true });
+    }
+  });
 });
@@ -111,6 +111,34 @@ function coerceAuthStore(raw: unknown): AuthProfileStore | null {
  };
 }

+function mergeRecord<T>(
+  base?: Record<string, T>,
+  override?: Record<string, T>,
+): Record<string, T> | undefined {
+  if (!base && !override) return undefined;
+  if (!base) return { ...override };
+  if (!override) return { ...base };
+  return { ...base, ...override };
+}
+
+function mergeAuthProfileStores(base: AuthProfileStore, override: AuthProfileStore): AuthProfileStore {
+  if (
+    Object.keys(override.profiles).length === 0 &&
+    !override.order &&
+    !override.lastGood &&
+    !override.usageStats
+  ) {
+    return base;
+  }
+  return {
+    version: Math.max(base.version, override.version ?? base.version),
+    profiles: { ...base.profiles, ...override.profiles },
+    order: mergeRecord(base.order, override.order),
+    lastGood: mergeRecord(base.lastGood, override.lastGood),
+    usageStats: mergeRecord(base.usageStats, override.usageStats),
+  };
+}
+
 function mergeOAuthFileIntoStore(store: AuthProfileStore): boolean {
  const oauthPath = resolveOAuthPath();
  const oauthRaw = loadJsonFile(oauthPath);
@@ -191,7 +219,7 @@ export function loadAuthProfileStore(): AuthProfileStore {
  return store;
 }

-export function ensureAuthProfileStore(
+function loadAuthProfileStoreForAgent(
  agentDir?: string,
  options?: { allowKeychainPrompt?: boolean },
 ): AuthProfileStore {
@@ -207,6 +235,19 @@ export function ensureAuthProfileStore(
    return asStore;
  }

+  // Fallback: inherit auth-profiles from main agent if subagent has none
+  if (agentDir) {
+    const mainAuthPath = resolveAuthStorePath(); // without agentDir = main
+    const mainRaw = loadJsonFile(mainAuthPath);
+    const mainStore = coerceAuthStore(mainRaw);
+    if (mainStore && Object.keys(mainStore.profiles).length > 0) {
+      // Clone main store to subagent directory for auth inheritance
+      saveJsonFile(authPath, mainStore);
+      log.info("inherited auth-profiles from main agent", { agentDir });
+      return mainStore;
+    }
+  }
+
  const legacyRaw = loadJsonFile(resolveLegacyAuthStorePath(agentDir));
  const legacy = coerceLegacyStore(legacyRaw);
  const store: AuthProfileStore = {
@@ -274,6 +315,21 @@ export function ensureAuthProfileStore(
  return store;
 }

+export function ensureAuthProfileStore(
+  agentDir?: string,
+  options?: { allowKeychainPrompt?: boolean },
+): AuthProfileStore {
+  const store = loadAuthProfileStoreForAgent(agentDir, options);
+  const authPath = resolveAuthStorePath(agentDir);
+  const mainAuthPath = resolveAuthStorePath();
+  if (!agentDir || authPath === mainAuthPath) {
+    return store;
+  }
+
+  const mainStore = loadAuthProfileStoreForAgent(undefined, options);
+  return mergeAuthProfileStores(mainStore, store);
+}
+
 export function saveAuthProfileStore(store: AuthProfileStore, agentDir?: string): void {
  const authPath = resolveAuthStorePath(agentDir);
  const payload = {
@@ -0,0 +1,140 @@
+import { afterEach, expect, test } from "vitest";
+
+import { createExecTool } from "./bash-tools.exec";
+import {
+  getFinishedSession,
+  getSession,
+  resetProcessRegistryForTests,
+} from "./bash-process-registry";
+import { killProcessTree } from "./shell-utils";
+
+const sleep = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
+
+afterEach(() => {
+  resetProcessRegistryForTests();
+});
+
+test("background exec is not killed when tool signal aborts", async () => {
+  const tool = createExecTool({ allowBackground: true, backgroundMs: 0 });
+  const abortController = new AbortController();
+
+  const result = await tool.execute(
+    "toolcall",
+    { command: 'node -e "setTimeout(() => {}, 5000)"', background: true },
+    abortController.signal,
+  );
+
+  expect(result.details.status).toBe("running");
+  const sessionId = (result.details as { sessionId: string }).sessionId;
+
+  abortController.abort();
+
+  await sleep(150);
+
+  const running = getSession(sessionId);
+  const finished = getFinishedSession(sessionId);
+
+  try {
+    expect(finished).toBeUndefined();
+    expect(running?.exited).toBe(false);
+  } finally {
+    const pid = running?.pid;
+    if (pid) killProcessTree(pid);
+  }
+});
+
+test("background exec still times out after tool signal abort", async () => {
+  const tool = createExecTool({ allowBackground: true, backgroundMs: 0 });
+  const abortController = new AbortController();
+
+  const result = await tool.execute(
+    "toolcall",
+    {
+      command: 'node -e "setTimeout(() => {}, 5000)"',
+      background: true,
+      timeout: 0.2,
+    },
+    abortController.signal,
+  );
+
+  expect(result.details.status).toBe("running");
+  const sessionId = (result.details as { sessionId: string }).sessionId;
+
+  abortController.abort();
+
+  let finished = getFinishedSession(sessionId);
+  const deadline = Date.now() + (process.platform === "win32" ? 10_000 : 2_000);
+  while (!finished && Date.now() < deadline) {
+    await sleep(20);
+    finished = getFinishedSession(sessionId);
+  }
+
+  const running = getSession(sessionId);
+
+  try {
+    expect(finished).toBeTruthy();
+    expect(finished?.status).toBe("failed");
+  } finally {
+    const pid = running?.pid;
+    if (pid) killProcessTree(pid);
+  }
+});
+
+test("yielded background exec is not killed when tool signal aborts", async () => {
+  const tool = createExecTool({ allowBackground: true, backgroundMs: 10 });
+  const abortController = new AbortController();
+
+  const result = await tool.execute(
+    "toolcall",
+    { command: 'node -e "setTimeout(() => {}, 5000)"', yieldMs: 5 },
+    abortController.signal,
+  );
+
+  expect(result.details.status).toBe("running");
+  const sessionId = (result.details as { sessionId: string }).sessionId;
+
+  abortController.abort();
+
+  await sleep(150);
+
+  const running = getSession(sessionId);
+  const finished = getFinishedSession(sessionId);
+
+  try {
+    expect(finished).toBeUndefined();
+    expect(running?.exited).toBe(false);
+  } finally {
+    const pid = running?.pid;
+    if (pid) killProcessTree(pid);
+  }
+});
+
+test("yielded background exec still times out", async () => {
+  const tool = createExecTool({ allowBackground: true, backgroundMs: 10 });
+
+  const result = await tool.execute("toolcall", {
+    command: 'node -e "setTimeout(() => {}, 5000)"',
+    yieldMs: 5,
+    timeout: 0.2,
+  });
+
+  expect(result.details.status).toBe("running");
+  const sessionId = (result.details as { sessionId: string }).sessionId;
+
+  let finished = getFinishedSession(sessionId);
+  const deadline = Date.now() + (process.platform === "win32" ? 10_000 : 2_000);
+  while (!finished && Date.now() < deadline) {
+    await sleep(20);
+    finished = getFinishedSession(sessionId);
+  }
+
+  const running = getSession(sessionId);
+
+  try {
+    expect(finished).toBeTruthy();
+    expect(finished?.status).toBe("failed");
+  } finally {
+    const pid = running?.pid;
+    if (pid) killProcessTree(pid);
+  }
+});
@@ -262,21 +262,28 @@ export function createExecTool(
        fn();
      };

-      const onAbort = () => {
+      // Tool-call abort should not kill backgrounded sessions; timeouts still must.
+      const onAbortSignal = () => {
+        if (yielded || session.backgrounded) return;
        killSession(session);
      };

-      if (signal?.aborted) onAbort();
+      // Timeouts always terminate, even for backgrounded sessions.
+      const onTimeout = () => {
+        timedOut = true;
+        killSession(session);
+      };
+
+      if (signal?.aborted) onAbortSignal();
      else if (signal) {
-        signal.addEventListener("abort", onAbort, { once: true });
+        signal.addEventListener("abort", onAbortSignal, { once: true });
      }

      const effectiveTimeout =
        typeof params.timeout === "number" ? params.timeout : defaultTimeoutSec;
      if (effectiveTimeout > 0) {
        timeoutTimer = setTimeout(() => {
-          timedOut = true;
-          onAbort();
+          onTimeout();
        }, effectiveTimeout * 1000);
      }

@@ -99,6 +99,7 @@ describe("session_status tool", () => {
    expect(details.ok).toBe(true);
    expect(details.statusText).toContain("Clawdbot");
    expect(details.statusText).toContain("🧠 Model:");
+    expect(details.statusText).not.toContain("OAuth/token status");
  });

  it("errors for unknown session keys", async () => {
@@ -62,6 +62,11 @@ function isModelNotFoundErrorMessage(raw: string): boolean {
  return false;
 }

+function isChatGPTUsageLimitErrorMessage(raw: string): boolean {
+  const msg = raw.toLowerCase();
+  return msg.includes("hit your chatgpt usage limit") && msg.includes("try again in");
+}
+
 function toInt(value: string | undefined, fallback: number): number {
  const trimmed = value?.trim();
  if (!trimmed) return fallback;
@@ -371,6 +376,18 @@ describeLive("live models (profile keys)", () => {
              logProgress(`${progressLabel}: skip (empty response)`);
              break;
            }
+            if (
+              ok.text.length === 0 &&
+              allowNotFoundSkip &&
+              (model.provider === "google-antigravity" || model.provider === "openai-codex")
+            ) {
+              skipped.push({
+                model: id,
+                reason: "no text returned (provider returned empty content)",
+              });
+              logProgress(`${progressLabel}: skip (empty response)`);
+              break;
+            }
            expect(ok.text.length).toBeGreaterThan(0);
            logProgress(`${progressLabel}: done`);
            break;
@@ -416,6 +433,15 @@ describeLive("live models (profile keys)", () => {
              logProgress(`${progressLabel}: skip (rate limit)`);
              break;
            }
+            if (
+              allowNotFoundSkip &&
+              model.provider === "openai-codex" &&
+              isChatGPTUsageLimitErrorMessage(message)
+            ) {
+              skipped.push({ model: id, reason: message });
+              logProgress(`${progressLabel}: skip (chatgpt usage limit)`);
+              break;
+            }
            logProgress(`${progressLabel}: failed`);
            failures.push({ model: id, error: message });
            break;
@@ -58,9 +58,7 @@ export function stripThoughtSignatures<T>(
    if (!block || typeof block !== "object") return block;
    const rec = block as ContentBlockWithSignature;
    const stripSnake = shouldStripSignature(rec.thought_signature);
-    const stripCamel = includeCamelCase
-      ? shouldStripSignature(rec.thoughtSignature)
-      : false;
+    const stripCamel = includeCamelCase ? shouldStripSignature(rec.thoughtSignature) : false;
    if (!stripSnake && !stripCamel) {
      return block;
    }
@@ -162,7 +162,7 @@ describe("sanitizeSessionHistory (google thinking)", () => {
            id: "call_1",
            name: "read",
            arguments: { path: "/tmp/foo" },
-            thoughtSignature: "{\"id\":1}",
+            thoughtSignature: '{"id":1}',
          },
          {
            type: "toolCall",
@@ -192,7 +192,7 @@ describe("sanitizeSessionHistory (google thinking)", () => {
      { type: "text", text: "ok" },
      {
        type: "text",
-        text: "[Tool Call: read (ID: call_1)]\nArguments: {\n  \"path\": \"/tmp/foo\"\n}",
+        text: '[Tool Call: read (ID: call_1)]\nArguments: {\n  "path": "/tmp/foo"\n}',
      },
      {
        type: "toolCall",
@@ -261,4 +261,64 @@ describe("runEmbeddedPiAgent", () => {
    expect(secondUserIndex).toBeGreaterThan(firstAssistantIndex);
    expect(secondAssistantIndex).toBeGreaterThan(secondUserIndex);
  }, 20_000);
+  it("returns role ordering error when session ends with a user turn", async () => {
+    const { SessionManager } = await import("@mariozechner/pi-coding-agent");
+
+    const agentDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-agent-"));
+    const workspaceDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-workspace-"));
+    const sessionFile = path.join(workspaceDir, "session.jsonl");
+
+    const sessionManager = SessionManager.open(sessionFile);
+    sessionManager.appendMessage({
+      role: "user",
+      content: [{ type: "text", text: "seed user 1" }],
+    });
+    sessionManager.appendMessage({
+      role: "assistant",
+      content: [{ type: "text", text: "seed assistant" }],
+      stopReason: "stop",
+      api: "openai-responses",
+      provider: "openai",
+      model: "mock-1",
+      usage: {
+        input: 1,
+        output: 1,
+        cacheRead: 0,
+        cacheWrite: 0,
+        totalTokens: 2,
+        cost: {
+          input: 0,
+          output: 0,
+          cacheRead: 0,
+          cacheWrite: 0,
+          total: 0,
+        },
+      },
+      timestamp: Date.now(),
+    });
+    sessionManager.appendMessage({
+      role: "user",
+      content: [{ type: "text", text: "seed user 2" }],
+    });
+
+    const cfg = makeOpenAiConfig(["mock-1"]);
+    await ensureModels(cfg, agentDir);
+
+    const result = await runEmbeddedPiAgent({
+      sessionId: "session:test",
+      sessionKey: "agent:main:main",
+      sessionFile,
+      workspaceDir,
+      config: cfg,
+      prompt: "hello",
+      provider: "openai",
+      model: "mock-1",
+      timeoutMs: 5_000,
+      agentDir,
+    });
+
+    expect(result.meta.error?.kind).toBe("role_ordering");
+    expect(result.meta.error?.message).toMatch(/incorrect role information|roles must alternate/i);
+    expect(result.payloads?.[0]?.text).toContain("Message ordering conflict");
+  });
 });
@@ -11,9 +11,7 @@ vi.mock("./pi-embedded-helpers.js", async () => {
    ...actual,
    isGoogleModelApi: vi.fn(),
    downgradeGeminiHistory: vi.fn(),
-    sanitizeSessionMessagesImages: vi
-      .fn()
-      .mockImplementation(async (msgs) => msgs),
+    sanitizeSessionMessagesImages: vi.fn().mockImplementation(async (msgs) => msgs),
  };
 });

@@ -30,9 +28,7 @@ describe("sanitizeSessionHistory", () => {

  beforeEach(() => {
    vi.resetAllMocks();
-    vi.mocked(helpers.sanitizeSessionMessagesImages).mockImplementation(
-      async (msgs) => msgs,
-    );
+    vi.mocked(helpers.sanitizeSessionMessagesImages).mockImplementation(async (msgs) => msgs);
    // Default mock implementation
    vi.mocked(helpers.downgradeGeminiHistory).mockImplementation((msgs) => {
      if (!msgs) return [];
@@ -82,12 +82,13 @@ function findUnsupportedSchemaKeywords(schema: unknown, path: string): string[]
  return violations;
 }

-export function sanitizeToolsForGoogle<TSchemaType extends TSchema = TSchema, TResult = unknown>(
-  params: {
-    tools: AgentTool<TSchemaType, TResult>[];
-    provider: string;
-  },
-): AgentTool<TSchemaType, TResult>[] {
+export function sanitizeToolsForGoogle<
+  TSchemaType extends TSchema = TSchema,
+  TResult = unknown,
+>(params: {
+  tools: AgentTool<TSchemaType, TResult>[];
+  provider: string;
+}): AgentTool<TSchemaType, TResult>[] {
  if (params.provider !== "google-antigravity" && params.provider !== "google-gemini-cli") {
    return params.tools;
  }
@@ -95,7 +96,9 @@ export function sanitizeToolsForGoogle<TSchemaType extends TSchema = TSchema, TR
    if (!tool.parameters || typeof tool.parameters !== "object") return tool;
    return {
      ...tool,
-      parameters: cleanToolSchemaForGemini(tool.parameters as Record<string, unknown>) as TSchemaType,
+      parameters: cleanToolSchemaForGemini(
+        tool.parameters as Record<string, unknown>,
+      ) as TSchemaType,
    };
  });
 }
@@ -274,6 +274,8 @@ export async function runEmbeddedPiAgent(
                    provider,
                    model: model.id,
                  },
+                  systemPromptReport: attempt.systemPromptReport,
+                  error: { kind: "role_ordering", message: errorText },
                },
              };
            }
@@ -20,7 +20,7 @@ export type EmbeddedPiRunMeta = {
  aborted?: boolean;
  systemPromptReport?: SessionSystemPromptReport;
  error?: {
-    kind: "context_overflow" | "compaction_failure";
+    kind: "context_overflow" | "compaction_failure" | "role_ordering";
    message: string;
  };
 };
@@ -22,10 +22,7 @@ export type SubscribeEmbeddedPiSessionParams = {
  blockReplyChunking?: BlockReplyChunking;
  onPartialReply?: (payload: { text?: string; mediaUrls?: string[] }) => void | Promise<void>;
  onAssistantMessageStart?: () => void | Promise<void>;
-  onAgentEvent?: (evt: {
-    stream: string;
-    data: Record<string, unknown>;
-  }) => void | Promise<void>;
+  onAgentEvent?: (evt: { stream: string; data: Record<string, unknown> }) => void | Promise<void>;
  enforceFinalTag?: boolean;
 };

@@ -129,16 +129,16 @@ describe("createClawdbotCodingTools", () => {
    expect(Array.isArray(action?.enum)).toBe(true);
    expect(action?.enum).toContain("act");

-    const format = parameters.properties?.format as
+    const snapshotFormat = parameters.properties?.snapshotFormat as
      | {
          type?: unknown;
          enum?: unknown[];
          anyOf?: unknown[];
        }
      | undefined;
-    expect(format?.type).toBe("string");
-    expect(format?.anyOf).toBeUndefined();
-    expect(format?.enum).toEqual(["aria", "ai"]);
+    expect(snapshotFormat?.type).toBe("string");
+    expect(snapshotFormat?.anyOf).toBeUndefined();
+    expect(snapshotFormat?.enum).toEqual(["aria", "ai"]);
  });
  it("inlines local $ref before removing unsupported keywords", () => {
    const cleaned = __testing.cleanToolSchemaForGemini({
@@ -51,6 +51,8 @@ function buildSandboxBrowserResolvedConfig(params: {
    cdpProtocol: "http",
    cdpHost,
    cdpIsLoopback: true,
+    remoteCdpTimeoutMs: 1500,
+    remoteCdpHandshakeTimeoutMs: 3000,
    color: DEFAULT_CLAWD_BROWSER_COLOR,
    executablePath: undefined,
    headless: params.headless,
@@ -0,0 +1,92 @@
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import { describe, expect, it } from "vitest";
+import { buildWorkspaceSkillCommandSpecs } from "./skills.js";
+
+async function writeSkill(params: {
+  dir: string;
+  name: string;
+  description: string;
+  frontmatterExtra?: string;
+}) {
+  const { dir, name, description, frontmatterExtra } = params;
+  await fs.mkdir(dir, { recursive: true });
+  await fs.writeFile(
+    path.join(dir, "SKILL.md"),
+    `---
+name: ${name}
+description: ${description}
+${frontmatterExtra ?? ""}
+---
+
+# ${name}
+`,
+    "utf-8",
+  );
+}
+
+describe("buildWorkspaceSkillCommandSpecs", () => {
+  it("sanitizes and de-duplicates command names", async () => {
+    const workspaceDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-"));
+    await writeSkill({
+      dir: path.join(workspaceDir, "skills", "hello-world"),
+      name: "hello-world",
+      description: "Hello world skill",
+    });
+    await writeSkill({
+      dir: path.join(workspaceDir, "skills", "hello_world"),
+      name: "hello_world",
+      description: "Hello underscore skill",
+    });
+    await writeSkill({
+      dir: path.join(workspaceDir, "skills", "help"),
+      name: "help",
+      description: "Help skill",
+    });
+    await writeSkill({
+      dir: path.join(workspaceDir, "skills", "hidden"),
+      name: "hidden-skill",
+      description: "Hidden skill",
+      frontmatterExtra: "user-invocable: false",
+    });
+
+    const commands = buildWorkspaceSkillCommandSpecs(workspaceDir, {
+      managedSkillsDir: path.join(workspaceDir, ".managed"),
+      bundledSkillsDir: path.join(workspaceDir, ".bundled"),
+      reservedNames: new Set(["help"]),
+    });
+
+    const names = commands.map((entry) => entry.name).sort();
+    expect(names).toEqual(["hello_world", "hello_world_2", "help_2"]);
+    expect(commands.find((entry) => entry.skillName === "hidden-skill")).toBeUndefined();
+  });
+
+  it("truncates descriptions longer than 100 characters for Discord compatibility", async () => {
+    const workspaceDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-"));
+    const longDescription =
+      "This is a very long description that exceeds Discord's 100 character limit for slash command descriptions and should be truncated";
+    await writeSkill({
+      dir: path.join(workspaceDir, "skills", "long-desc"),
+      name: "long-desc",
+      description: longDescription,
+    });
+    await writeSkill({
+      dir: path.join(workspaceDir, "skills", "short-desc"),
+      name: "short-desc",
+      description: "Short description",
+    });
+
+    const commands = buildWorkspaceSkillCommandSpecs(workspaceDir, {
+      managedSkillsDir: path.join(workspaceDir, ".managed"),
+      bundledSkillsDir: path.join(workspaceDir, ".bundled"),
+    });
+
+    const longCmd = commands.find((entry) => entry.skillName === "long-desc");
+    const shortCmd = commands.find((entry) => entry.skillName === "short-desc");
+
+    expect(longCmd?.description.length).toBeLessThanOrEqual(100);
+    expect(longCmd?.description.endsWith("…")).toBe(true);
+    expect(shortCmd?.description).toBe("Short description");
+  });
+});
@@ -9,15 +9,17 @@ async function _writeSkill(params: {
  name: string;
  description: string;
  metadata?: string;
+  frontmatterExtra?: string;
  body?: string;
 }) {
-  const { dir, name, description, metadata, body } = params;
+  const { dir, name, description, metadata, frontmatterExtra, body } = params;
  await fs.mkdir(dir, { recursive: true });
  await fs.writeFile(
    path.join(dir, "SKILL.md"),
    `---
 name: ${name}
 description: ${description}${metadata ? `\nmetadata: ${metadata}` : ""}
+${frontmatterExtra ?? ""}
 ---

 ${body ?? `# ${name}\n`}
@@ -38,4 +40,31 @@ describe("buildWorkspaceSkillSnapshot", () => {
    expect(snapshot.prompt).toBe("");
    expect(snapshot.skills).toEqual([]);
  });
+
+  it("omits disable-model-invocation skills from the prompt", async () => {
+    const workspaceDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-"));
+    await _writeSkill({
+      dir: path.join(workspaceDir, "skills", "visible-skill"),
+      name: "visible-skill",
+      description: "Visible skill",
+    });
+    await _writeSkill({
+      dir: path.join(workspaceDir, "skills", "hidden-skill"),
+      name: "hidden-skill",
+      description: "Hidden skill",
+      frontmatterExtra: "disable-model-invocation: true",
+    });
+
+    const snapshot = buildWorkspaceSkillSnapshot(workspaceDir, {
+      managedSkillsDir: path.join(workspaceDir, ".managed"),
+      bundledSkillsDir: path.join(workspaceDir, ".bundled"),
+    });
+
+    expect(snapshot.prompt).toContain("visible-skill");
+    expect(snapshot.prompt).not.toContain("hidden-skill");
+    expect(snapshot.skills.map((skill) => skill.name).sort()).toEqual([
+      "hidden-skill",
+      "visible-skill",
+    ]);
+  });
 });
@@ -16,6 +16,7 @@ export {
 export type {
  ClawdbotSkillMetadata,
  SkillEligibilityContext,
+  SkillCommandSpec,
  SkillEntry,
  SkillInstallSpec,
  SkillSnapshot,
@@ -24,6 +25,7 @@ export type {
 export {
  buildWorkspaceSkillSnapshot,
  buildWorkspaceSkillsPrompt,
+  buildWorkspaceSkillCommandSpecs,
  filterWorkspaceSkillEntries,
  loadWorkspaceSkillEntries,
  resolveSkillsPromptForRun,
@@ -5,6 +5,7 @@ import type {
  ParsedSkillFrontmatter,
  SkillEntry,
  SkillInstallSpec,
+  SkillInvocationPolicy,
 } from "./types.js";

 function stripQuotes(value: string): string {
@@ -79,6 +80,19 @@ function getFrontmatterValue(frontmatter: ParsedSkillFrontmatter, key: string):
  return typeof raw === "string" ? raw : undefined;
 }

+function parseFrontmatterBool(value: string | undefined, fallback: boolean): boolean {
+  if (!value) return fallback;
+  const normalized = value.trim().toLowerCase();
+  if (!normalized) return fallback;
+  if (normalized === "true" || normalized === "1" || normalized === "yes" || normalized === "on") {
+    return true;
+  }
+  if (normalized === "false" || normalized === "0" || normalized === "no" || normalized === "off") {
+    return false;
+  }
+  return fallback;
+}
+
 export function resolveClawdbotMetadata(
  frontmatter: ParsedSkillFrontmatter,
 ): ClawdbotSkillMetadata | undefined {
@@ -121,6 +135,18 @@ export function resolveClawdbotMetadata(
  }
 }

+export function resolveSkillInvocationPolicy(
+  frontmatter: ParsedSkillFrontmatter,
+): SkillInvocationPolicy {
+  return {
+    userInvocable: parseFrontmatterBool(getFrontmatterValue(frontmatter, "user-invocable"), true),
+    disableModelInvocation: parseFrontmatterBool(
+      getFrontmatterValue(frontmatter, "disable-model-invocation"),
+      false,
+    ),
+  };
+}
+
 export function resolveSkillKey(skill: Skill, entry?: SkillEntry): string {
  return entry?.clawdbot?.skillKey ?? skill.name;
 }
@@ -26,6 +26,17 @@ export type ClawdbotSkillMetadata = {
  install?: SkillInstallSpec[];
 };

+export type SkillInvocationPolicy = {
+  userInvocable: boolean;
+  disableModelInvocation: boolean;
+};
+
+export type SkillCommandSpec = {
+  name: string;
+  skillName: string;
+  description: string;
+};
+
 export type SkillsInstallPreferences = {
  preferBrew: boolean;
  nodeManager: "npm" | "pnpm" | "yarn" | "bun";
@@ -37,6 +48,7 @@ export type SkillEntry = {
  skill: Skill;
  frontmatter: ParsedSkillFrontmatter;
  clawdbot?: ClawdbotSkillMetadata;
+  invocation?: SkillInvocationPolicy;
 };

 export type SkillEligibilityContext = {
@@ -11,11 +11,16 @@ import type { ClawdbotConfig } from "../../config/config.js";
 import { CONFIG_DIR, resolveUserPath } from "../../utils.js";
 import { resolveBundledSkillsDir } from "./bundled-dir.js";
 import { shouldIncludeSkill } from "./config.js";
-import { parseFrontmatter, resolveClawdbotMetadata } from "./frontmatter.js";
+import {
+  parseFrontmatter,
+  resolveClawdbotMetadata,
+  resolveSkillInvocationPolicy,
+} from "./frontmatter.js";
 import { serializeByKey } from "./serialize.js";
 import type {
  ParsedSkillFrontmatter,
  SkillEligibilityContext,
+  SkillCommandSpec,
  SkillEntry,
  SkillSnapshot,
 } from "./types.js";
@@ -43,6 +48,36 @@ function filterSkillEntries(
  return filtered;
 }

+const SKILL_COMMAND_MAX_LENGTH = 32;
+const SKILL_COMMAND_FALLBACK = "skill";
+// Discord command descriptions must be ≤100 characters
+const SKILL_COMMAND_DESCRIPTION_MAX_LENGTH = 100;
+
+function sanitizeSkillCommandName(raw: string): string {
+  const normalized = raw
+    .toLowerCase()
+    .replace(/[^a-z0-9_]+/g, "_")
+    .replace(/_+/g, "_")
+    .replace(/^_+|_+$/g, "");
+  const trimmed = normalized.slice(0, SKILL_COMMAND_MAX_LENGTH);
+  return trimmed || SKILL_COMMAND_FALLBACK;
+}
+
+function resolveUniqueSkillCommandName(base: string, used: Set<string>): string {
+  const normalizedBase = base.toLowerCase();
+  if (!used.has(normalizedBase)) return base;
+  for (let index = 2; index < 1000; index += 1) {
+    const suffix = `_${index}`;
+    const maxBaseLength = Math.max(1, SKILL_COMMAND_MAX_LENGTH - suffix.length);
+    const trimmedBase = base.slice(0, maxBaseLength);
+    const candidate = `${trimmedBase}${suffix}`;
+    const candidateKey = candidate.toLowerCase();
+    if (!used.has(candidateKey)) return candidate;
+  }
+  const fallback = `${base.slice(0, Math.max(1, SKILL_COMMAND_MAX_LENGTH - 2))}_x`;
+  return fallback;
+}
+
 function loadSkillEntries(
  workspaceDir: string,
  opts?: {
@@ -114,6 +149,7 @@ function loadSkillEntries(
      skill,
      frontmatter,
      clawdbot: resolveClawdbotMetadata(frontmatter),
+      invocation: resolveSkillInvocationPolicy(frontmatter),
    };
  });
  return skillEntries;
@@ -139,7 +175,10 @@ export function buildWorkspaceSkillSnapshot(
    opts?.skillFilter,
    opts?.eligibility,
  );
-  const resolvedSkills = eligible.map((entry) => entry.skill);
+  const promptEntries = eligible.filter(
+    (entry) => entry.invocation?.disableModelInvocation !== true,
+  );
+  const resolvedSkills = promptEntries.map((entry) => entry.skill);
  const remoteNote = opts?.eligibility?.remote?.note?.trim();
  const prompt = [remoteNote, formatSkillsForPrompt(resolvedSkills)].filter(Boolean).join("\n");
  return {
@@ -172,8 +211,11 @@ export function buildWorkspaceSkillsPrompt(
    opts?.skillFilter,
    opts?.eligibility,
  );
+  const promptEntries = eligible.filter(
+    (entry) => entry.invocation?.disableModelInvocation !== true,
+  );
  const remoteNote = opts?.eligibility?.remote?.note?.trim();
-  return [remoteNote, formatSkillsForPrompt(eligible.map((entry) => entry.skill))]
+  return [remoteNote, formatSkillsForPrompt(promptEntries.map((entry) => entry.skill))]
    .filter(Boolean)
    .join("\n");
 }
@@ -251,3 +293,47 @@ export function filterWorkspaceSkillEntries(
 ): SkillEntry[] {
  return filterSkillEntries(entries, config);
 }
+
+export function buildWorkspaceSkillCommandSpecs(
+  workspaceDir: string,
+  opts?: {
+    config?: ClawdbotConfig;
+    managedSkillsDir?: string;
+    bundledSkillsDir?: string;
+    entries?: SkillEntry[];
+    skillFilter?: string[];
+    eligibility?: SkillEligibilityContext;
+    reservedNames?: Set<string>;
+  },
+): SkillCommandSpec[] {
+  const skillEntries = opts?.entries ?? loadSkillEntries(workspaceDir, opts);
+  const eligible = filterSkillEntries(
+    skillEntries,
+    opts?.config,
+    opts?.skillFilter,
+    opts?.eligibility,
+  );
+  const userInvocable = eligible.filter((entry) => entry.invocation?.userInvocable !== false);
+  const used = new Set<string>();
+  for (const reserved of opts?.reservedNames ?? []) {
+    used.add(reserved.toLowerCase());
+  }
+
+  const specs: SkillCommandSpec[] = [];
+  for (const entry of userInvocable) {
+    const base = sanitizeSkillCommandName(entry.skill.name);
+    const unique = resolveUniqueSkillCommandName(base, used);
+    used.add(unique.toLowerCase());
+    const rawDescription = entry.skill.description?.trim() || entry.skill.name;
+    const description =
+      rawDescription.length > SKILL_COMMAND_DESCRIPTION_MAX_LENGTH
+        ? rawDescription.slice(0, SKILL_COMMAND_DESCRIPTION_MAX_LENGTH - 1) + "…"
+        : rawDescription;
+    specs.push({
+      name: unique,
+      skillName: entry.skill.name,
+      description,
+    });
+  }
+  return specs;
+}
@@ -327,6 +327,11 @@ export function buildAgentSystemPrompt(params: {
    "TOOLS.md does not control tool availability; it is user guidance for how to use external tools.",
    "If a task is more complex or takes longer, spawn a sub-agent. It will do the work for you and ping you when it's done. You can always check up on it.",
    "",
+    "## Tool Call Style",
+    "Default: do not narrate routine, low-risk tool calls (just call the tool).",
+    "Narrate only when it helps: multi-step work, complex/challenging problems, sensitive actions (e.g., deletions), or when the user explicitly asks.",
+    "Keep narration brief and value-dense; avoid repeating obvious steps.",
+    "",
    "## Clawdbot CLI Quick Reference",
    "Clawdbot is controlled via subcommands. Do not invent commands.",
    "To manage the Gateway daemon service (start/stop/restart):",
@@ -409,9 +414,7 @@ export function buildAgentSystemPrompt(params: {
            ? "You may also send /elevated on|off when needed."
            : "",
          params.sandboxInfo.elevated?.allowed
-            ? `Current elevated level: ${
-                params.sandboxInfo.elevated.defaultLevel
-              } (on runs exec on host; off runs in sandbox).`
+            ? `Current elevated level: ${params.sandboxInfo.elevated.defaultLevel} (on runs exec on host; off runs in sandbox).`
            : "",
        ]
          .filter(Boolean)
@@ -91,7 +91,7 @@ export const BrowserToolSchema = Type.Object({
  limit: Type.Optional(Type.Number()),
  maxChars: Type.Optional(Type.Number()),
  mode: optionalStringEnum(BROWSER_SNAPSHOT_MODES),
-  format: optionalStringEnum(BROWSER_SNAPSHOT_FORMATS),
+  snapshotFormat: optionalStringEnum(BROWSER_SNAPSHOT_FORMATS),
  refs: optionalStringEnum(BROWSER_SNAPSHOT_REFS),
  interactive: Type.Optional(Type.Boolean()),
  compact: Type.Optional(Type.Boolean()),
@@ -191,8 +191,8 @@ export function createBrowserTool(opts?: {
        }
        case "snapshot": {
          const format =
-            params.format === "ai" || params.format === "aria"
-              ? (params.format as "ai" | "aria")
+            params.snapshotFormat === "ai" || params.snapshotFormat === "aria"
+              ? (params.snapshotFormat as "ai" | "aria")
              : "ai";
          const mode = params.mode === "efficient" ? "efficient" : undefined;
          const labels = typeof params.labels === "boolean" ? params.labels : undefined;
@@ -40,7 +40,7 @@ const CanvasToolSchema = Type.Object({
  // eval
  javaScript: Type.Optional(Type.String()),
  // snapshot
-  format: optionalStringEnum(CANVAS_SNAPSHOT_FORMATS),
+  outputFormat: optionalStringEnum(CANVAS_SNAPSHOT_FORMATS),
  maxWidth: Type.Optional(Type.Number()),
  quality: Type.Optional(Type.Number()),
  delayMs: Type.Optional(Type.Number()),
@@ -127,7 +127,7 @@ export function createCanvasTool(): AnyAgentTool {
          return jsonResult({ ok: true });
        }
        case "snapshot": {
-          const formatRaw = typeof params.format === "string" ? params.format.toLowerCase() : "png";
+          const formatRaw = typeof params.outputFormat === "string" ? params.outputFormat.toLowerCase() : "png";
          const format = formatRaw === "jpg" || formatRaw === "jpeg" ? "jpeg" : "png";
          const maxWidth =
            typeof params.maxWidth === "number" && Number.isFinite(params.maxWidth)
@@ -1,6 +1,5 @@
 import { Type } from "@sinclair/typebox";
 import { resolveAgentDir } from "../../agents/agent-scope.js";
-import { buildAuthHealthSummary, formatRemainingShort } from "../../agents/auth-health.js";
 import {
  ensureAuthProfileStore,
  resolveAuthProfileDisplayLabel,
@@ -32,7 +31,6 @@ import {
  formatUsageWindowSummary,
  loadProviderUsageSummary,
  resolveUsageProviderId,
-  type UsageProviderId,
 } from "../../infra/provider-usage.js";
 import {
  buildAgentMainSessionKey,
@@ -283,48 +281,31 @@ export function createSessionStatusTool(opts?: {
        defaultModel: DEFAULT_MODEL,
      });
      const providerForCard = resolved.entry.providerOverride?.trim() || configured.provider;
-      const authStore = ensureAuthProfileStore(agentDir, { allowKeychainPrompt: false });
-      const authHealth = buildAuthHealthSummary({
-        store: authStore,
-        cfg,
-      });
-      const oauthProfiles = authHealth.profiles.filter(
-        (profile) => profile.type === "oauth" || profile.type === "token",
-      );
-
-      const usageProviders = Array.from(
-        new Set(
-          oauthProfiles
-            .map((profile) => resolveUsageProviderId(profile.provider))
-            .filter((provider): provider is UsageProviderId => Boolean(provider)),
-        ),
-      );
-      const usageByProvider = new Map<string, string>();
-      if (usageProviders.length > 0) {
+      const usageProvider = resolveUsageProviderId(providerForCard);
+      let usageLine: string | undefined;
+      if (usageProvider) {
        try {
          const usageSummary = await loadProviderUsageSummary({
            timeoutMs: 3500,
-            providers: usageProviders,
+            providers: [usageProvider],
            agentDir,
          });
-          for (const snapshot of usageSummary.providers) {
+          const snapshot = usageSummary.providers.find((entry) => entry.provider === usageProvider);
+          if (snapshot) {
            const formatted = formatUsageWindowSummary(snapshot, {
              now: Date.now(),
              maxWindows: 2,
+              includeResets: true,
            });
-            if (formatted) usageByProvider.set(snapshot.provider, formatted);
+            if (formatted && !formatted.startsWith("error:")) {
+              usageLine = `📊 Usage: ${formatted}`;
+            }
          }
        } catch {
          // ignore
        }
      }

-      const usageProvider = resolveUsageProviderId(providerForCard);
-      const usageLine =
-        oauthProfiles.length === 0 && usageProvider && usageByProvider.has(usageProvider)
-          ? `📊 Usage: ${usageByProvider.get(usageProvider)}`
-          : undefined;
-
      const isGroup =
        resolved.entry.chatType === "group" ||
        resolved.entry.chatType === "room" ||
@@ -370,53 +351,13 @@ export function createSessionStatusTool(opts?: {
        includeTranscriptUsage: false,
      });

-      const authStatusLines = (() => {
-        if (oauthProfiles.length === 0) return [];
-        const formatStatus = (status: string) => {
-          if (status === "ok") return "ok";
-          if (status === "static") return "static";
-          if (status === "expiring") return "expiring";
-          if (status === "missing") return "unknown";
-          return "expired";
-        };
-        const profilesByProvider = new Map<string, typeof oauthProfiles>();
-        for (const profile of oauthProfiles) {
-          const current = profilesByProvider.get(profile.provider);
-          if (current) current.push(profile);
-          else profilesByProvider.set(profile.provider, [profile]);
-        }
-        const lines: string[] = ["OAuth/token status"];
-        for (const [provider, profiles] of profilesByProvider) {
-          const usageKey = resolveUsageProviderId(provider);
-          const usage = usageKey ? usageByProvider.get(usageKey) : undefined;
-          const usageSuffix = usage ? ` — usage: ${usage}` : "";
-          lines.push(`- ${provider}${usageSuffix}`);
-          for (const profile of profiles) {
-            const labelText = profile.label || profile.profileId;
-            const status = formatStatus(profile.status);
-            const expiry =
-              profile.status === "static"
-                ? ""
-                : profile.expiresAt
-                  ? ` expires in ${formatRemainingShort(profile.remainingMs)}`
-                  : " expires unknown";
-            const source = profile.source !== "store" ? ` (${profile.source})` : "";
-            lines.push(`  - ${labelText} ${status}${expiry}${source}`);
-          }
-        }
-        return lines;
-      })();
-
-      const fullStatusText =
-        authStatusLines.length > 0 ? `${statusText}\n\n${authStatusLines.join("\n")}` : statusText;
-
      return {
-        content: [{ type: "text", text: fullStatusText }],
+        content: [{ type: "text", text: statusText }],
        details: {
          ok: true,
          sessionKey: resolved.key,
          changedModel,
-          statusText: fullStatusText,
+          statusText,
        },
      };
    },
@@ -45,6 +45,29 @@ describe("commands registry", () => {
    expect(nativeDisabled.find((spec) => spec.name === "debug")).toBeFalsy();
  });

+  it("appends skill commands when provided", () => {
+    const skillCommands = [
+      {
+        name: "demo_skill",
+        skillName: "demo-skill",
+        description: "Demo skill",
+      },
+    ];
+    const commands = listChatCommandsForConfig(
+      {
+        commands: { config: false, debug: false },
+      },
+      { skillCommands },
+    );
+    expect(commands.find((spec) => spec.nativeName === "demo_skill")).toBeTruthy();
+
+    const native = listNativeCommandSpecsForConfig(
+      { commands: { config: false, debug: false, native: true } },
+      { skillCommands },
+    );
+    expect(native.find((spec) => spec.name === "demo_skill")).toBeTruthy();
+  });
+
  it("detects known text commands", () => {
    const detection = getCommandDetection();
    expect(detection.exact.has("/commands")).toBe(true);
@@ -1,4 +1,5 @@
 import type { ClawdbotConfig } from "../config/types.js";
+import type { SkillCommandSpec } from "../agents/skills.js";
 import { CHAT_COMMANDS, getNativeCommandSurfaces } from "./commands-registry.data.js";
 import { DEFAULT_MODEL, DEFAULT_PROVIDER } from "../agents/defaults.js";
 import { resolveConfiguredModelRef } from "../agents/model-selection.js";
@@ -61,8 +62,24 @@ function escapeRegExp(value: string) {
  return value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
 }

-export function listChatCommands(): ChatCommandDefinition[] {
-  return [...CHAT_COMMANDS];
+function buildSkillCommandDefinitions(skillCommands?: SkillCommandSpec[]): ChatCommandDefinition[] {
+  if (!skillCommands || skillCommands.length === 0) return [];
+  return skillCommands.map((spec) => ({
+    key: `skill:${spec.skillName}`,
+    nativeName: spec.name,
+    description: spec.description,
+    textAliases: [`/${spec.name}`],
+    acceptsArgs: true,
+    argsParsing: "none",
+    scope: "both",
+  }));
+}
+
+export function listChatCommands(params?: {
+  skillCommands?: SkillCommandSpec[];
+}): ChatCommandDefinition[] {
+  if (!params?.skillCommands?.length) return [...CHAT_COMMANDS];
+  return [...CHAT_COMMANDS, ...buildSkillCommandDefinitions(params.skillCommands)];
 }

 export function isCommandEnabled(cfg: ClawdbotConfig, commandKey: string): boolean {
@@ -72,23 +89,33 @@ export function isCommandEnabled(cfg: ClawdbotConfig, commandKey: string): boole
  return true;
 }

-export function listChatCommandsForConfig(cfg: ClawdbotConfig): ChatCommandDefinition[] {
-  return CHAT_COMMANDS.filter((command) => isCommandEnabled(cfg, command.key));
+export function listChatCommandsForConfig(
+  cfg: ClawdbotConfig,
+  params?: { skillCommands?: SkillCommandSpec[] },
+): ChatCommandDefinition[] {
+  const base = CHAT_COMMANDS.filter((command) => isCommandEnabled(cfg, command.key));
+  if (!params?.skillCommands?.length) return base;
+  return [...base, ...buildSkillCommandDefinitions(params.skillCommands)];
 }

-export function listNativeCommandSpecs(): NativeCommandSpec[] {
-  return CHAT_COMMANDS.filter((command) => command.scope !== "text" && command.nativeName).map(
-    (command) => ({
+export function listNativeCommandSpecs(params?: {
+  skillCommands?: SkillCommandSpec[];
+}): NativeCommandSpec[] {
+  return listChatCommands({ skillCommands: params?.skillCommands })
+    .filter((command) => command.scope !== "text" && command.nativeName)
+    .map((command) => ({
      name: command.nativeName ?? command.key,
      description: command.description,
      acceptsArgs: Boolean(command.acceptsArgs),
      args: command.args,
-    }),
-  );
+    }));
 }

-export function listNativeCommandSpecsForConfig(cfg: ClawdbotConfig): NativeCommandSpec[] {
-  return listChatCommandsForConfig(cfg)
+export function listNativeCommandSpecsForConfig(
+  cfg: ClawdbotConfig,
+  params?: { skillCommands?: SkillCommandSpec[] },
+): NativeCommandSpec[] {
+  return listChatCommandsForConfig(cfg, params)
    .filter((command) => command.scope !== "text" && command.nativeName)
    .map((command) => ({
      name: command.nativeName ?? command.key,
@@ -63,6 +63,7 @@ export async function runAgentTurnWithFallback(params: {
  shouldEmitToolResult: () => boolean;
  pendingToolTasks: Set<Promise<void>>;
  resetSessionAfterCompactionFailure: (reason: string) => Promise<boolean>;
+  resetSessionAfterRoleOrderingConflict: (reason: string) => Promise<boolean>;
  isHeartbeat: boolean;
  sessionKey?: string;
  getActiveSessionEntry: () => SessionEntry | undefined;
@@ -376,6 +377,17 @@ export async function runAgentTurnWithFallback(params: {
        didResetAfterCompactionFailure = true;
        continue;
      }
+      if (embeddedError?.kind === "role_ordering") {
+        const didReset = await params.resetSessionAfterRoleOrderingConflict(embeddedError.message);
+        if (didReset) {
+          return {
+            kind: "final",
+            payload: {
+              text: "⚠️ Message ordering conflict. I've reset the conversation - please try again.",
+            },
+          };
+        }
+      }

      break;
    } catch (err) {
@@ -395,6 +407,17 @@ export async function runAgentTurnWithFallback(params: {
        didResetAfterCompactionFailure = true;
        continue;
      }
+      if (isRoleOrderingError) {
+        const didReset = await params.resetSessionAfterRoleOrderingConflict(message);
+        if (didReset) {
+          return {
+            kind: "final",
+            payload: {
+              text: "⚠️ Message ordering conflict. I've reset the conversation - please try again.",
+            },
+          };
+        }
+      }

      // Auto-recover from Gemini session corruption by resetting the session
      if (
@@ -3,6 +3,7 @@ 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 * as sessions from "../../config/sessions.js";
 import type { TypingMode } from "../../config/types.js";
 import type { TemplateContext } from "../templating.js";
 import type { GetReplyOptions } from "../types.js";
@@ -127,11 +128,14 @@ describe("runReplyAgent typing (heartbeat)", () => {
    try {
      const sessionId = "session";
      const storePath = path.join(stateDir, "sessions", "sessions.json");
-      const sessionEntry = { sessionId, updatedAt: Date.now() };
+      const transcriptPath = sessions.resolveSessionTranscriptPath(sessionId);
+      const sessionEntry = { sessionId, updatedAt: Date.now(), sessionFile: transcriptPath };
      const sessionStore = { main: sessionEntry };

      await fs.mkdir(path.dirname(storePath), { recursive: true });
      await fs.writeFile(storePath, JSON.stringify(sessionStore), "utf-8");
+      await fs.mkdir(path.dirname(transcriptPath), { recursive: true });
+      await fs.writeFile(transcriptPath, "ok", "utf-8");

      runEmbeddedPiAgentMock
        .mockImplementationOnce(async () => {
@@ -175,11 +179,14 @@ describe("runReplyAgent typing (heartbeat)", () => {
    try {
      const sessionId = "session";
      const storePath = path.join(stateDir, "sessions", "sessions.json");
-      const sessionEntry = { sessionId, updatedAt: Date.now() };
+      const transcriptPath = sessions.resolveSessionTranscriptPath(sessionId);
+      const sessionEntry = { sessionId, updatedAt: Date.now(), sessionFile: transcriptPath };
      const sessionStore = { main: sessionEntry };

      await fs.mkdir(path.dirname(storePath), { recursive: true });
      await fs.writeFile(storePath, JSON.stringify(sessionStore), "utf-8");
+      await fs.mkdir(path.dirname(transcriptPath), { recursive: true });
+      await fs.writeFile(transcriptPath, "ok", "utf-8");

      runEmbeddedPiAgentMock
        .mockImplementationOnce(async () => ({
@@ -212,6 +219,59 @@ describe("runReplyAgent typing (heartbeat)", () => {
      expect(payload).toMatchObject({ text: "ok" });
      expect(sessionStore.main.sessionId).not.toBe(sessionId);

+      const persisted = JSON.parse(await fs.readFile(storePath, "utf-8"));
+      expect(persisted.main.sessionId).toBe(sessionStore.main.sessionId);
+    } finally {
+      if (prevStateDir) {
+        process.env.CLAWDBOT_STATE_DIR = prevStateDir;
+      } else {
+        delete process.env.CLAWDBOT_STATE_DIR;
+      }
+    }
+  });
+  it("resets the session after role ordering payloads", async () => {
+    const prevStateDir = process.env.CLAWDBOT_STATE_DIR;
+    const stateDir = await fs.mkdtemp(path.join(tmpdir(), "clawdbot-session-role-ordering-"));
+    process.env.CLAWDBOT_STATE_DIR = stateDir;
+    try {
+      const sessionId = "session";
+      const storePath = path.join(stateDir, "sessions", "sessions.json");
+      const transcriptPath = sessions.resolveSessionTranscriptPath(sessionId);
+      const sessionEntry = { sessionId, updatedAt: Date.now(), sessionFile: transcriptPath };
+      const sessionStore = { main: sessionEntry };
+
+      await fs.mkdir(path.dirname(storePath), { recursive: true });
+      await fs.writeFile(storePath, JSON.stringify(sessionStore), "utf-8");
+      await fs.mkdir(path.dirname(transcriptPath), { recursive: true });
+      await fs.writeFile(transcriptPath, "ok", "utf-8");
+
+      runEmbeddedPiAgentMock.mockImplementationOnce(async () => ({
+        payloads: [{ text: "Message ordering conflict - please try again.", isError: true }],
+        meta: {
+          durationMs: 1,
+          error: {
+            kind: "role_ordering",
+            message: 'messages: roles must alternate between "user" and "assistant"',
+          },
+        },
+      }));
+
+      const { run } = createMinimalRun({
+        sessionEntry,
+        sessionStore,
+        sessionKey: "main",
+        storePath,
+      });
+      const res = await run();
+
+      const payload = Array.isArray(res) ? res[0] : res;
+      expect(payload).toMatchObject({
+        text: expect.stringContaining("Message ordering conflict"),
+      });
+      expect(payload.text?.toLowerCase()).toContain("reset");
+      expect(sessionStore.main.sessionId).not.toBe(sessionId);
+      await expect(fs.access(transcriptPath)).rejects.toBeDefined();
+
      const persisted = JSON.parse(await fs.readFile(storePath, "utf-8"));
      expect(persisted.main.sessionId).toBe(sessionStore.main.sessionId);
    } finally {
@@ -1,4 +1,5 @@
 import crypto from "node:crypto";
+import fs from "node:fs";
 import { setCliSessionId } from "../../agents/cli-session.js";
 import { lookupContextTokens } from "../../agents/context.js";
 import { DEFAULT_CONTEXT_TOKENS } from "../../agents/defaults.js";
@@ -8,6 +9,7 @@ import { queueEmbeddedPiMessage } from "../../agents/pi-embedded.js";
 import { hasNonzeroUsage } from "../../agents/usage.js";
 import {
  resolveAgentIdFromSessionKey,
+  resolveSessionFilePath,
  resolveSessionTranscriptPath,
  type SessionEntry,
  updateSessionStore,
@@ -209,11 +211,23 @@ export async function runReplyAgent(params: {
  });

  let responseUsageLine: string | undefined;
-  const resetSessionAfterCompactionFailure = async (reason: string): Promise<boolean> => {
+  type SessionResetOptions = {
+    failureLabel: string;
+    buildLogMessage: (nextSessionId: string) => string;
+    cleanupTranscripts?: boolean;
+  };
+  const resetSession = async ({
+    failureLabel,
+    buildLogMessage,
+    cleanupTranscripts,
+  }: SessionResetOptions): Promise<boolean> => {
    if (!sessionKey || !activeSessionStore || !storePath) return false;
+    const prevEntry = activeSessionStore[sessionKey] ?? activeSessionEntry;
+    if (!prevEntry) return false;
+    const prevSessionId = cleanupTranscripts ? prevEntry.sessionId : undefined;
    const nextSessionId = crypto.randomUUID();
    const nextEntry: SessionEntry = {
-      ...(activeSessionStore[sessionKey] ?? activeSessionEntry),
+      ...prevEntry,
      sessionId: nextSessionId,
      updatedAt: Date.now(),
      systemSent: false,
@@ -233,18 +247,42 @@ export async function runReplyAgent(params: {
      });
    } catch (err) {
      defaultRuntime.error(
-        `Failed to persist session reset after compaction failure (${sessionKey}): ${String(err)}`,
+        `Failed to persist session reset after ${failureLabel} (${sessionKey}): ${String(err)}`,
      );
    }
    followupRun.run.sessionId = nextSessionId;
    followupRun.run.sessionFile = nextSessionFile;
    activeSessionEntry = nextEntry;
    activeIsNewSession = true;
-    defaultRuntime.error(
-      `Auto-compaction failed (${reason}). Restarting session ${sessionKey} -> ${nextSessionId} and retrying.`,
-    );
+    defaultRuntime.error(buildLogMessage(nextSessionId));
+    if (cleanupTranscripts && prevSessionId) {
+      const transcriptCandidates = new Set<string>();
+      const resolved = resolveSessionFilePath(prevSessionId, prevEntry, { agentId });
+      if (resolved) transcriptCandidates.add(resolved);
+      transcriptCandidates.add(resolveSessionTranscriptPath(prevSessionId, agentId));
+      for (const candidate of transcriptCandidates) {
+        try {
+          fs.unlinkSync(candidate);
+        } catch {
+          // Best-effort cleanup.
+        }
+      }
+    }
    return true;
  };
+  const resetSessionAfterCompactionFailure = async (reason: string): Promise<boolean> =>
+    resetSession({
+      failureLabel: "compaction failure",
+      buildLogMessage: (nextSessionId) =>
+        `Auto-compaction failed (${reason}). Restarting session ${sessionKey} -> ${nextSessionId} and retrying.`,
+    });
+  const resetSessionAfterRoleOrderingConflict = async (reason: string): Promise<boolean> =>
+    resetSession({
+      failureLabel: "role ordering conflict",
+      buildLogMessage: (nextSessionId) =>
+        `Role ordering conflict (${reason}). Restarting session ${sessionKey} -> ${nextSessionId}.`,
+      cleanupTranscripts: true,
+    });
  try {
    const runOutcome = await runAgentTurnWithFallback({
      commandBody,
@@ -260,6 +298,7 @@ export async function runReplyAgent(params: {
      shouldEmitToolResult,
      pendingToolTasks,
      resetSessionAfterCompactionFailure,
+      resetSessionAfterRoleOrderingConflict,
      isHeartbeat,
      sessionKey,
      getActiveSessionEntry: () => activeSessionEntry,
@@ -1,4 +1,5 @@
 import { logVerbose } from "../../globals.js";
+import { listSkillCommandsForWorkspace } from "../skill-commands.js";
 import { buildCommandsMessage, buildHelpMessage } from "../status.js";
 import { buildStatusReply } from "./commands-status.js";
 import { buildContextReply } from "./commands-context-report.js";
@@ -28,9 +29,15 @@ export const handleCommandsListCommand: CommandHandler = async (params, allowTex
    );
    return { shouldContinue: false };
  }
+  const skillCommands =
+    params.skillCommands ??
+    listSkillCommandsForWorkspace({
+      workspaceDir: params.workspaceDir,
+      cfg: params.cfg,
+    });
  return {
    shouldContinue: false,
-    reply: { text: buildCommandsMessage(params.cfg) },
+    reply: { text: buildCommandsMessage(params.cfg, skillCommands) },
  };
 };

@@ -168,6 +168,7 @@ export async function buildStatusReply(params: {
        const formatted = formatUsageWindowSummary(snapshot, {
          now: Date.now(),
          maxWindows: 2,
+          includeResets: true,
        });
        if (formatted) usageByProvider.set(snapshot.provider, formatted);
      }
@@ -1,6 +1,7 @@
 import type { ChannelId } from "../../channels/plugins/types.js";
 import type { ClawdbotConfig } from "../../config/config.js";
 import type { SessionEntry, SessionScope } from "../../config/sessions.js";
+import type { SkillCommandSpec } from "../../agents/skills.js";
 import type { MsgContext } from "../templating.js";
 import type { ElevatedLevel, ReasoningLevel, ThinkLevel, VerboseLevel } from "../thinking.js";
 import type { ReplyPayload } from "../types.js";
@@ -47,6 +48,7 @@ export type HandleCommandsParams = {
  model: string;
  contextTokens: number;
  isGroup: boolean;
+  skillCommands?: SkillCommandSpec[];
 };

 export type CommandHandlerResult = {
@@ -11,6 +11,8 @@ import { isDirectiveOnly } from "./directive-handling.js";
 import type { createModelSelectionState } from "./model-selection.js";
 import { extractInlineSimpleCommand } from "./reply-inline.js";
 import type { TypingController } from "./typing.js";
+import { listSkillCommandsForWorkspace, resolveSkillCommandInvocation } from "../skill-commands.js";
+import { logVerbose } from "../../globals.js";

 export type InlineActionResult =
  | { kind: "reply"; reply: ReplyPayload | ReplyPayload[] | undefined }
@@ -55,6 +57,7 @@ export async function handleInlineActions(params: {
  contextTokens: number;
  directiveAck?: ReplyPayload;
  abortedLastRun: boolean;
+  skillFilter?: string[];
 }): Promise<InlineActionResult> {
  const {
    ctx,
@@ -89,11 +92,47 @@ export async function handleInlineActions(params: {
    contextTokens,
    directiveAck,
    abortedLastRun: initialAbortedLastRun,
+    skillFilter,
  } = params;

  let directives = initialDirectives;
  let cleanedBody = initialCleanedBody;

+  const shouldLoadSkillCommands = command.commandBodyNormalized.startsWith("/");
+  const skillCommands = shouldLoadSkillCommands
+    ? listSkillCommandsForWorkspace({
+        workspaceDir,
+        cfg,
+        skillFilter,
+      })
+    : [];
+
+  const skillInvocation =
+    allowTextCommands && skillCommands.length > 0
+      ? resolveSkillCommandInvocation({
+          commandBodyNormalized: command.commandBodyNormalized,
+          skillCommands,
+        })
+      : null;
+  if (skillInvocation) {
+    if (!command.isAuthorizedSender) {
+      logVerbose(
+        `Ignoring /${skillInvocation.command.name} from unauthorized sender: ${command.senderId || "<unknown>"}`,
+      );
+      typing.cleanup();
+      return { kind: "reply", reply: undefined };
+    }
+    const promptParts = [
+      `Use the "${skillInvocation.command.skillName}" skill for this request.`,
+      skillInvocation.args ? `User input:\n${skillInvocation.args}` : null,
+    ].filter((entry): entry is string => Boolean(entry));
+    const rewrittenBody = promptParts.join("\n\n");
+    ctx.Body = rewrittenBody;
+    sessionCtx.Body = rewrittenBody;
+    sessionCtx.BodyStripped = rewrittenBody;
+    cleanedBody = rewrittenBody;
+  }
+
  const sendInlineReply = async (reply?: ReplyPayload) => {
    if (!reply) return;
    if (!opts?.onBlockReply) return;
@@ -174,6 +213,7 @@ export async function handleInlineActions(params: {
      model,
      contextTokens,
      isGroup,
+      skillCommands,
    });
    if (inlineResult.reply) {
      if (!inlineCommand.cleaned) {
@@ -235,6 +275,7 @@ export async function handleInlineActions(params: {
    model,
    contextTokens,
    isGroup,
+    skillCommands,
  });
  if (!commandResult.shouldContinue) {
    typing.cleanup();
@@ -203,6 +203,7 @@ export async function getReplyFromConfig(
    contextTokens,
    directiveAck,
    abortedLastRun,
+    skillFilter: opts?.skillFilter,
  });
  if (inlineActionResult.kind === "reply") {
    return inlineActionResult.reply;
@@ -0,0 +1,21 @@
+import { describe, expect, it } from "vitest";
+import { resolveSkillCommandInvocation } from "./skill-commands.js";
+
+describe("resolveSkillCommandInvocation", () => {
+  it("matches skill commands and parses args", () => {
+    const invocation = resolveSkillCommandInvocation({
+      commandBodyNormalized: "/demo_skill do the thing",
+      skillCommands: [{ name: "demo_skill", skillName: "demo-skill", description: "Demo" }],
+    });
+    expect(invocation?.command.skillName).toBe("demo-skill");
+    expect(invocation?.args).toBe("do the thing");
+  });
+
+  it("returns null for unknown commands", () => {
+    const invocation = resolveSkillCommandInvocation({
+      commandBodyNormalized: "/unknown arg",
+      skillCommands: [{ name: "demo_skill", skillName: "demo-skill", description: "Demo" }],
+    });
+    expect(invocation).toBeNull();
+  });
+});
@@ -0,0 +1,46 @@
+import type { ClawdbotConfig } from "../config/config.js";
+import { getRemoteSkillEligibility } from "../infra/skills-remote.js";
+import { buildWorkspaceSkillCommandSpecs, type SkillCommandSpec } from "../agents/skills.js";
+import { listChatCommands } from "./commands-registry.js";
+
+function resolveReservedCommandNames(): Set<string> {
+  const reserved = new Set<string>();
+  for (const command of listChatCommands()) {
+    if (command.nativeName) reserved.add(command.nativeName.toLowerCase());
+    for (const alias of command.textAliases) {
+      const trimmed = alias.trim();
+      if (!trimmed.startsWith("/")) continue;
+      reserved.add(trimmed.slice(1).toLowerCase());
+    }
+  }
+  return reserved;
+}
+
+export function listSkillCommandsForWorkspace(params: {
+  workspaceDir: string;
+  cfg: ClawdbotConfig;
+  skillFilter?: string[];
+}): SkillCommandSpec[] {
+  return buildWorkspaceSkillCommandSpecs(params.workspaceDir, {
+    config: params.cfg,
+    skillFilter: params.skillFilter,
+    eligibility: { remote: getRemoteSkillEligibility() },
+    reservedNames: resolveReservedCommandNames(),
+  });
+}
+
+export function resolveSkillCommandInvocation(params: {
+  commandBodyNormalized: string;
+  skillCommands: SkillCommandSpec[];
+}): { command: SkillCommandSpec; args?: string } | null {
+  const trimmed = params.commandBodyNormalized.trim();
+  if (!trimmed.startsWith("/")) return null;
+  const match = trimmed.match(/^\/([^\s]+)(?:\s+([\s\S]+))?$/);
+  if (!match) return null;
+  const commandName = match[1]?.trim().toLowerCase();
+  if (!commandName) return null;
+  const command = params.skillCommands.find((entry) => entry.name.toLowerCase() === commandName);
+  if (!command) return null;
+  const args = match[2]?.trim();
+  return { command, args: args || undefined };
+}
@@ -318,6 +318,22 @@ describe("buildCommandsMessage", () => {
    expect(text).not.toContain("/config");
    expect(text).not.toContain("/debug");
  });
+
+  it("includes skill commands when provided", () => {
+    const text = buildCommandsMessage(
+      {
+        commands: { config: false, debug: false },
+      } as ClawdbotConfig,
+      [
+        {
+          name: "demo_skill",
+          skillName: "demo-skill",
+          description: "Demo skill",
+        },
+      ],
+    );
+    expect(text).toContain("/demo_skill - Demo skill");
+  });
 });

 describe("buildHelpMessage", () => {
@@ -22,6 +22,7 @@ import {
 } from "../utils/usage-format.js";
 import { VERSION } from "../version.js";
 import { listChatCommands, listChatCommandsForConfig } from "./commands-registry.js";
+import type { SkillCommandSpec } from "../agents/skills.js";
 import type { ElevatedLevel, ReasoningLevel, ThinkLevel, VerboseLevel } from "./thinking.js";

 type AgentConfig = Partial<NonNullable<NonNullable<ClawdbotConfig["agents"]>["defaults"]>>;
@@ -352,9 +353,14 @@ export function buildHelpMessage(cfg?: ClawdbotConfig): string {
  ].join("\n");
 }

-export function buildCommandsMessage(cfg?: ClawdbotConfig): string {
+export function buildCommandsMessage(
+  cfg?: ClawdbotConfig,
+  skillCommands?: SkillCommandSpec[],
+): string {
  const lines = ["ℹ️ Slash commands"];
-  const commands = cfg ? listChatCommandsForConfig(cfg) : listChatCommands();
+  const commands = cfg
+    ? listChatCommandsForConfig(cfg, { skillCommands })
+    : listChatCommands({ skillCommands });
  for (const command of commands) {
    const primary = command.nativeName
      ? `/${command.nativeName}`
@@ -0,0 +1,27 @@
+import { describe, expect, it } from "vitest";
+
+import { appendCdpPath, getHeadersWithAuth } from "./cdp.helpers.js";
+
+describe("cdp.helpers", () => {
+  it("preserves query params when appending CDP paths", () => {
+    const url = appendCdpPath("https://example.com?token=abc", "/json/version");
+    expect(url).toBe("https://example.com/json/version?token=abc");
+  });
+
+  it("appends paths under a base prefix", () => {
+    const url = appendCdpPath("https://example.com/chrome/?token=abc", "json/list");
+    expect(url).toBe("https://example.com/chrome/json/list?token=abc");
+  });
+
+  it("adds basic auth headers when credentials are present", () => {
+    const headers = getHeadersWithAuth("https://user:pass@example.com");
+    expect(headers.Authorization).toBe(`Basic ${Buffer.from("user:pass").toString("base64")}`);
+  });
+
+  it("keeps preexisting authorization headers", () => {
+    const headers = getHeadersWithAuth("https://user:pass@example.com", {
+      Authorization: "Bearer token",
+    });
+    expect(headers.Authorization).toBe("Bearer token");
+  });
+});
@@ -28,6 +28,29 @@ export function isLoopbackHost(host: string) {
  );
 }

+export function getHeadersWithAuth(url: string, headers: Record<string, string> = {}) {
+  try {
+    const parsed = new URL(url);
+    const hasAuthHeader = Object.keys(headers).some((key) => key.toLowerCase() === "authorization");
+    if (hasAuthHeader) return headers;
+    if (parsed.username || parsed.password) {
+      const auth = Buffer.from(`${parsed.username}:${parsed.password}`).toString("base64");
+      return { ...headers, Authorization: `Basic ${auth}` };
+    }
+  } catch {
+    // ignore
+  }
+  return headers;
+}
+
+export function appendCdpPath(cdpUrl: string, path: string): string {
+  const url = new URL(cdpUrl);
+  const basePath = url.pathname.replace(/\/$/, "");
+  const suffix = path.startsWith("/") ? path : `/${path}`;
+  url.pathname = `${basePath}${suffix}`;
+  return url.toString();
+}
+
 function createCdpSender(ws: WebSocket) {
  let nextId = 1;
  const pending = new Map<number, Pending>();
@@ -75,11 +98,12 @@ function createCdpSender(ws: WebSocket) {
  return { send, closeWithError };
 }

-export async function fetchJson<T>(url: string, timeoutMs = 1500): Promise<T> {
+export async function fetchJson<T>(url: string, timeoutMs = 1500, init?: RequestInit): Promise<T> {
  const ctrl = new AbortController();
  const t = setTimeout(() => ctrl.abort(), timeoutMs);
  try {
-    const res = await fetch(url, { signal: ctrl.signal });
+    const headers = getHeadersWithAuth(url, (init?.headers as Record<string, string>) || {});
+    const res = await fetch(url, { ...init, headers, signal: ctrl.signal });
    if (!res.ok) throw new Error(`HTTP ${res.status}`);
    return (await res.json()) as T;
  } finally {
@@ -87,11 +111,28 @@ export async function fetchJson<T>(url: string, timeoutMs = 1500): Promise<T> {
  }
 }

+export async function fetchOk(url: string, timeoutMs = 1500, init?: RequestInit): Promise<void> {
+  const ctrl = new AbortController();
+  const t = setTimeout(() => ctrl.abort(), timeoutMs);
+  try {
+    const headers = getHeadersWithAuth(url, (init?.headers as Record<string, string>) || {});
+    const res = await fetch(url, { ...init, headers, signal: ctrl.signal });
+    if (!res.ok) throw new Error(`HTTP ${res.status}`);
+  } finally {
+    clearTimeout(t);
+  }
+}
+
 export async function withCdpSocket<T>(
  wsUrl: string,
  fn: (send: CdpSendFn) => Promise<T>,
+  opts?: { headers?: Record<string, string> },
 ): Promise<T> {
-  const ws = new WebSocket(wsUrl, { handshakeTimeout: 5000 });
+  const headers = getHeadersWithAuth(wsUrl, opts?.headers ?? {});
+  const ws = new WebSocket(wsUrl, {
+    handshakeTimeout: 5000,
+    ...(Object.keys(headers).length ? { headers } : {}),
+  });
  const { send, closeWithError } = createCdpSender(ws);

  const openPromise = new Promise<void>((resolve, reject) => {
@@ -165,4 +165,20 @@ describe("cdp", () => {
    );
    expect(normalized).toBe("ws://example.com:9222/devtools/browser/ABC");
  });
+
+  it("propagates auth and query params onto normalized websocket URLs", () => {
+    const normalized = normalizeCdpWsUrl(
+      "ws://127.0.0.1:9222/devtools/browser/ABC",
+      "https://user:pass@example.com?token=abc",
+    );
+    expect(normalized).toBe("wss://user:pass@example.com/devtools/browser/ABC?token=abc");
+  });
+
+  it("upgrades ws to wss when CDP uses https", () => {
+    const normalized = normalizeCdpWsUrl(
+      "ws://production-sfo.browserless.io",
+      "https://production-sfo.browserless.io?token=abc",
+    );
+    expect(normalized).toBe("wss://production-sfo.browserless.io/?token=abc");
+  });
 });
@@ -1,4 +1,6 @@
-import { fetchJson, isLoopbackHost, withCdpSocket } from "./cdp.helpers.js";
+import { appendCdpPath, fetchJson, isLoopbackHost, withCdpSocket } from "./cdp.helpers.js";
+
+export { appendCdpPath, fetchJson, fetchOk, getHeadersWithAuth } from "./cdp.helpers.js";

 export function normalizeCdpWsUrl(wsUrl: string, cdpUrl: string): string {
  const ws = new URL(wsUrl);
@@ -9,6 +11,16 @@ export function normalizeCdpWsUrl(wsUrl: string, cdpUrl: string): string {
    if (cdpPort) ws.port = cdpPort;
    ws.protocol = cdp.protocol === "https:" ? "wss:" : "ws:";
  }
+  if (cdp.protocol === "https:" && ws.protocol === "ws:") {
+    ws.protocol = "wss:";
+  }
+  if (!ws.username && !ws.password && (cdp.username || cdp.password)) {
+    ws.username = cdp.username;
+    ws.password = cdp.password;
+  }
+  for (const [key, value] of cdp.searchParams.entries()) {
+    if (!ws.searchParams.has(key)) ws.searchParams.append(key, value);
+  }
  return ws.toString();
 }

@@ -68,8 +80,10 @@ export async function createTargetViaCdp(opts: {
  cdpUrl: string;
  url: string;
 }): Promise<{ targetId: string }> {
-  const base = opts.cdpUrl.replace(/\/$/, "");
-  const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(`${base}/json/version`, 1500);
+  const version = await fetchJson<{ webSocketDebuggerUrl?: string }>(
+    appendCdpPath(opts.cdpUrl, "/json/version"),
+    1500,
+  );
  const wsUrlRaw = String(version?.webSocketDebuggerUrl ?? "").trim();
  const wsUrl = wsUrlRaw ? normalizeCdpWsUrl(wsUrlRaw, opts.cdpUrl) : "";
  if (!wsUrl) throw new Error("CDP /json/version missing webSocketDebuggerUrl");
@@ -24,10 +24,12 @@ describe("browser default executable detection", () => {
  it("prefers default Chromium browser on macOS", async () => {
    vi.mocked(execFileSync).mockImplementation((cmd, args) => {
      const argsStr = Array.isArray(args) ? args.join(" ") : "";
-      if (cmd === "/usr/bin/osascript" && argsStr.includes("id of application")) {
-        return "com.google.Chrome";
+      if (cmd === "/usr/bin/plutil" && argsStr.includes("LSHandlers")) {
+        return JSON.stringify([
+          { LSHandlerURLScheme: "http", LSHandlerRoleAll: "com.google.Chrome" },
+        ]);
      }
-      if (cmd === "/usr/bin/osascript" && argsStr.includes("POSIX path")) {
+      if (cmd === "/usr/bin/osascript" && argsStr.includes("path to application id")) {
        return "/Applications/Google Chrome.app";
      }
      if (cmd === "/usr/bin/defaults") {
@@ -35,9 +37,11 @@ describe("browser default executable detection", () => {
      }
      return "";
    });
-    vi.mocked(fs.existsSync).mockImplementation((p) =>
-      String(p).includes("/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"),
-    );
+    vi.mocked(fs.existsSync).mockImplementation((p) => {
+      const value = String(p);
+      if (value.includes("com.apple.launchservices.secure.plist")) return true;
+      return value.includes("/Applications/Google Chrome.app/Contents/MacOS/Google Chrome");
+    });

    const { resolveBrowserExecutableForPlatform } = await import("./chrome.executables.js");
    const exe = resolveBrowserExecutableForPlatform(
@@ -52,14 +56,18 @@ describe("browser default executable detection", () => {
  it("falls back when default browser is non-Chromium on macOS", async () => {
    vi.mocked(execFileSync).mockImplementation((cmd, args) => {
      const argsStr = Array.isArray(args) ? args.join(" ") : "";
-      if (cmd === "/usr/bin/osascript" && argsStr.includes("id of application")) {
-        return "com.apple.Safari";
+      if (cmd === "/usr/bin/plutil" && argsStr.includes("LSHandlers")) {
+        return JSON.stringify([
+          { LSHandlerURLScheme: "http", LSHandlerRoleAll: "com.apple.Safari" },
+        ]);
      }
      return "";
    });
-    vi.mocked(fs.existsSync).mockImplementation((p) =>
-      String(p).includes("Google Chrome.app/Contents/MacOS/Google Chrome"),
-    );
+    vi.mocked(fs.existsSync).mockImplementation((p) => {
+      const value = String(p);
+      if (value.includes("com.apple.launchservices.secure.plist")) return true;
+      return value.includes("Google Chrome.app/Contents/MacOS/Google Chrome");
+    });

    const { resolveBrowserExecutableForPlatform } = await import("./chrome.executables.js");
    const exe = resolveBrowserExecutableForPlatform(
@@ -95,12 +95,17 @@ function exists(filePath: string) {
  }
 }

-function execText(command: string, args: string[], timeoutMs = 1200): string | null {
+function execText(
+  command: string,
+  args: string[],
+  timeoutMs = 1200,
+  maxBuffer = 1024 * 1024,
+): string | null {
  try {
    const output = execFileSync(command, args, {
      timeout: timeoutMs,
      encoding: "utf8",
-      maxBuffer: 1024 * 1024,
+      maxBuffer,
    });
    return String(output ?? "").trim() || null;
  } catch {
@@ -114,7 +119,12 @@ function inferKindFromIdentifier(identifier: string): BrowserExecutable["kind"]
  if (id.includes("edge")) return "edge";
  if (id.includes("chromium")) return "chromium";
  if (id.includes("canary")) return "canary";
-  if (id.includes("opera") || id.includes("vivaldi") || id.includes("yandex") || id.includes("thebrowser")) {
+  if (
+    id.includes("opera") ||
+    id.includes("vivaldi") ||
+    id.includes("yandex") ||
+    id.includes("thebrowser")
+  ) {
    return "chromium";
  }
  return "chrome";
@@ -126,13 +136,12 @@ function inferKindFromExecutableName(name: string): BrowserExecutable["kind"] {
  if (lower.includes("edge") || lower.includes("msedge")) return "edge";
  if (lower.includes("chromium")) return "chromium";
  if (lower.includes("canary") || lower.includes("sxs")) return "canary";
-  if (lower.includes("opera") || lower.includes("vivaldi") || lower.includes("yandex")) return "chromium";
+  if (lower.includes("opera") || lower.includes("vivaldi") || lower.includes("yandex"))
+    return "chromium";
  return "chrome";
 }

-function detectDefaultChromiumExecutable(
-  platform: NodeJS.Platform,
-): BrowserExecutable | null {
+function detectDefaultChromiumExecutable(platform: NodeJS.Platform): BrowserExecutable | null {
  if (platform === "darwin") return detectDefaultChromiumExecutableMac();
  if (platform === "linux") return detectDefaultChromiumExecutableLinux();
  if (platform === "win32") return detectDefaultChromiumExecutableWindows();
@@ -140,14 +149,12 @@ function detectDefaultChromiumExecutable(
 }

 function detectDefaultChromiumExecutableMac(): BrowserExecutable | null {
-  const bundleId = execText("/usr/bin/osascript", [
-    "-e",
-    'id of application (path to default application for URL "http://example.com")',
-  ]);
-  if (!bundleId || !CHROMIUM_BUNDLE_IDS.has(bundleId.trim())) return null;
+  const bundleId = detectDefaultBrowserBundleIdMac();
+  if (!bundleId || !CHROMIUM_BUNDLE_IDS.has(bundleId)) return null;
+
  const appPathRaw = execText("/usr/bin/osascript", [
    "-e",
-    'POSIX path of (path to default application for URL "http://example.com")',
+    `POSIX path of (path to application id "${bundleId}")`,
  ]);
  if (!appPathRaw) return null;
  const appPath = appPathRaw.trim().replace(/\/$/, "");
@@ -162,6 +169,45 @@ function detectDefaultChromiumExecutableMac(): BrowserExecutable | null {
  return { kind: inferKindFromIdentifier(bundleId), path: exePath };
 }

+function detectDefaultBrowserBundleIdMac(): string | null {
+  const plistPath = path.join(
+    os.homedir(),
+    "Library/Preferences/com.apple.LaunchServices/com.apple.launchservices.secure.plist",
+  );
+  if (!exists(plistPath)) return null;
+  const handlersRaw = execText(
+    "/usr/bin/plutil",
+    ["-extract", "LSHandlers", "json", "-o", "-", "--", plistPath],
+    2000,
+    5 * 1024 * 1024,
+  );
+  if (!handlersRaw) return null;
+  let handlers: unknown;
+  try {
+    handlers = JSON.parse(handlersRaw);
+  } catch {
+    return null;
+  }
+  if (!Array.isArray(handlers)) return null;
+
+  const resolveScheme = (scheme: string) => {
+    let candidate: string | null = null;
+    for (const entry of handlers) {
+      if (!entry || typeof entry !== "object") continue;
+      const record = entry as Record<string, unknown>;
+      if (record.LSHandlerURLScheme !== scheme) continue;
+      const role =
+        (typeof record.LSHandlerRoleAll === "string" && record.LSHandlerRoleAll) ||
+        (typeof record.LSHandlerRoleViewer === "string" && record.LSHandlerRoleViewer) ||
+        null;
+      if (role) candidate = role;
+    }
+    return candidate;
+  };
+
+  return resolveScheme("http") ?? resolveScheme("https");
+}
+
 function detectDefaultChromiumExecutableLinux(): BrowserExecutable | null {
  const desktopId =
    execText("xdg-settings", ["get", "default-web-browser"]) ||
@@ -185,8 +231,7 @@ function detectDefaultChromiumExecutableLinux(): BrowserExecutable | null {
 function detectDefaultChromiumExecutableWindows(): BrowserExecutable | null {
  const progId = readWindowsProgId();
  const command =
-    (progId ? readWindowsCommandForProgId(progId) : null) ||
-    readWindowsCommandForProgId("http");
+    (progId ? readWindowsCommandForProgId(progId) : null) || readWindowsCommandForProgId("http");
  if (!command) return null;
  const expanded = expandWindowsEnvVars(command);
  const exePath = extractWindowsExecutablePath(expanded);
@@ -243,7 +288,7 @@ function splitExecLine(line: string): string[] {
  let quoteChar = "";
  for (let i = 0; i < line.length; i += 1) {
    const ch = line[i];
-    if ((ch === "\"" || ch === "'") && (!inQuotes || ch === quoteChar)) {
+    if ((ch === '"' || ch === "'") && (!inQuotes || ch === quoteChar)) {
      if (inQuotes) {
        inQuotes = false;
        quoteChar = "";
@@ -300,7 +345,7 @@ function readWindowsCommandForProgId(progId: string): string | null {
 function expandWindowsEnvVars(value: string): string {
  return value.replace(/%([^%]+)%/g, (_match, name) => {
    const key = String(name ?? "").trim();
-    return key ? process.env[key] ?? `%${key}%` : _match;
+    return key ? (process.env[key] ?? `%${key}%`) : _match;
  });
 }

@@ -7,7 +7,8 @@ import WebSocket from "ws";
 import { ensurePortAvailable } from "../infra/ports.js";
 import { createSubsystemLogger } from "../logging.js";
 import { CONFIG_DIR } from "../utils.js";
-import { normalizeCdpWsUrl } from "./cdp.js";
+import { getHeadersWithAuth, normalizeCdpWsUrl } from "./cdp.js";
+import { appendCdpPath } from "./cdp.helpers.js";
 import {
  type BrowserExecutable,
  resolveBrowserExecutableForPlatform,
@@ -71,9 +72,10 @@ async function fetchChromeVersion(cdpUrl: string, timeoutMs = 500): Promise<Chro
  const ctrl = new AbortController();
  const t = setTimeout(() => ctrl.abort(), timeoutMs);
  try {
-    const base = cdpUrl.replace(/\/$/, "");
-    const res = await fetch(`${base}/json/version`, {
+    const versionUrl = appendCdpPath(cdpUrl, "/json/version");
+    const res = await fetch(versionUrl, {
      signal: ctrl.signal,
+      headers: getHeadersWithAuth(versionUrl),
    });
    if (!res.ok) return null;
    const data = (await res.json()) as ChromeVersion;
@@ -98,7 +100,11 @@ export async function getChromeWebSocketUrl(

 async function canOpenWebSocket(wsUrl: string, timeoutMs = 800): Promise<boolean> {
  return await new Promise<boolean>((resolve) => {
-    const ws = new WebSocket(wsUrl, { handshakeTimeout: timeoutMs });
+    const headers = getHeadersWithAuth(wsUrl);
+    const ws = new WebSocket(wsUrl, {
+      handshakeTimeout: timeoutMs,
+      ...(Object.keys(headers).length ? { headers } : {}),
+    });
    const timer = setTimeout(
      () => {
        try {
@@ -19,6 +19,8 @@ describe("browser config", () => {
    expect(clawd?.driver).toBe("clawd");
    expect(clawd?.cdpPort).toBe(18800);
    expect(clawd?.cdpUrl).toBe("http://127.0.0.1:18800");
+    expect(resolved.remoteCdpTimeoutMs).toBe(1500);
+    expect(resolved.remoteCdpHandshakeTimeoutMs).toBe(3000);
  });

  it("derives default ports from CLAWDBOT_GATEWAY_PORT when unset", () => {
@@ -52,6 +54,16 @@ describe("browser config", () => {
    expect(resolved.color).toBe("#FF4500");
  });

+  it("supports custom remote CDP timeouts", () => {
+    const resolved = resolveBrowserConfig({
+      controlUrl: "http://127.0.0.1:18791",
+      remoteCdpTimeoutMs: 2200,
+      remoteCdpHandshakeTimeoutMs: 5000,
+    });
+    expect(resolved.remoteCdpTimeoutMs).toBe(2200);
+    expect(resolved.remoteCdpHandshakeTimeoutMs).toBe(5000);
+  });
+
  it("falls back to default color for invalid hex", () => {
    const resolved = resolveBrowserConfig({
      controlUrl: "http://localhost:18791",
@@ -21,6 +21,8 @@ export type ResolvedBrowserConfig = {
  cdpProtocol: "http" | "https";
  cdpHost: string;
  cdpIsLoopback: boolean;
+  remoteCdpTimeoutMs: number;
+  remoteCdpHandshakeTimeoutMs: number;
  color: string;
  executablePath?: string;
  headless: boolean;
@@ -61,6 +63,11 @@ function normalizeHexColor(raw: string | undefined) {
  return normalized.toUpperCase();
 }

+function normalizeTimeoutMs(raw: number | undefined, fallback: number) {
+  const value = typeof raw === "number" && Number.isFinite(raw) ? Math.floor(raw) : fallback;
+  return value < 0 ? fallback : value;
+}
+
 export function parseHttpUrl(raw: string, label: string) {
  const trimmed = raw.trim();
  const parsed = new URL(trimmed);
@@ -149,6 +156,11 @@ export function resolveBrowserConfig(cfg: BrowserConfig | undefined): ResolvedBr
  );
  const controlPort = controlInfo.port;
  const defaultColor = normalizeHexColor(cfg?.color);
+  const remoteCdpTimeoutMs = normalizeTimeoutMs(cfg?.remoteCdpTimeoutMs, 1500);
+  const remoteCdpHandshakeTimeoutMs = normalizeTimeoutMs(
+    cfg?.remoteCdpHandshakeTimeoutMs,
+    Math.max(2000, remoteCdpTimeoutMs * 2),
+  );

  const derivedCdpRange = deriveDefaultBrowserCdpPortRange(controlPort);

@@ -206,6 +218,8 @@ export function resolveBrowserConfig(cfg: BrowserConfig | undefined): ResolvedBr
    cdpProtocol,
    cdpHost: cdpInfo.parsed.hostname,
    cdpIsLoopback: isLoopbackHost(cdpInfo.parsed.hostname),
+    remoteCdpTimeoutMs,
+    remoteCdpHandshakeTimeoutMs,
    color: defaultColor,
    executablePath,
    headless,
@@ -8,6 +8,7 @@ import type {
 } from "playwright-core";
 import { chromium } from "playwright-core";
 import { formatErrorMessage } from "../infra/errors.js";
+import { getHeadersWithAuth } from "./cdp.helpers.js";
 import { getChromeWebSocketUrl } from "./chrome.js";

 export type BrowserConsoleMessage = {
@@ -268,7 +269,8 @@ async function connectBrowser(cdpUrl: string): Promise<ConnectedBrowser> {
        const timeout = 5000 + attempt * 2000;
        const wsUrl = await getChromeWebSocketUrl(normalized, timeout).catch(() => null);
        const endpoint = wsUrl ?? normalized;
-        const browser = await chromium.connectOverCDP(endpoint, { timeout });
+        const headers = getHeadersWithAuth(endpoint);
+        const browser = await chromium.connectOverCDP(endpoint, { timeout, headers });
        const connected: ConnectedBrowser = { browser, cdpUrl: normalized };
        cached = connected;
        observeBrowser(browser);
@@ -1,6 +1,6 @@
 import fs from "node:fs";

-import { createTargetViaCdp, normalizeCdpWsUrl } from "./cdp.js";
+import { appendCdpPath, createTargetViaCdp, getHeadersWithAuth, normalizeCdpWsUrl } from "./cdp.js";
 import {
  isChromeCdpReady,
  isChromeReachable,
@@ -50,7 +50,8 @@ async function fetchJson<T>(url: string, timeoutMs = 1500, init?: RequestInit):
  const ctrl = new AbortController();
  const t = setTimeout(() => ctrl.abort(), timeoutMs);
  try {
-    const res = await fetch(url, { ...init, signal: ctrl.signal });
+    const headers = getHeadersWithAuth(url, (init?.headers as Record<string, string>) || {});
+    const res = await fetch(url, { ...init, headers, signal: ctrl.signal });
    if (!res.ok) throw new Error(`HTTP ${res.status}`);
    return (await res.json()) as T;
  } finally {
@@ -62,7 +63,8 @@ async function fetchOk(url: string, timeoutMs = 1500, init?: RequestInit): Promi
  const ctrl = new AbortController();
  const t = setTimeout(() => ctrl.abort(), timeoutMs);
  try {
-    const res = await fetch(url, { ...init, signal: ctrl.signal });
+    const headers = getHeadersWithAuth(url, (init?.headers as Record<string, string>) || {});
+    const res = await fetch(url, { ...init, headers, signal: ctrl.signal });
    if (!res.ok) throw new Error(`HTTP ${res.status}`);
  } finally {
    clearTimeout(t);
@@ -106,7 +108,7 @@ function createProfileContext(
        webSocketDebuggerUrl?: string;
        type?: string;
      }>
-    >(`${profile.cdpUrl.replace(/\/$/, "")}/json/list`);
+    >(appendCdpPath(profile.cdpUrl, "/json/list"));
    return raw
      .map((t) => ({
        targetId: t.id ?? "",
@@ -146,8 +148,13 @@ function createProfileContext(
      type?: string;
    };

-    const base = profile.cdpUrl.replace(/\/$/, "");
-    const endpoint = `${base}/json/new?${encoded}`;
+    const endpointUrl = new URL(appendCdpPath(profile.cdpUrl, "/json/new"));
+    const endpoint = endpointUrl.search
+      ? (() => {
+          endpointUrl.searchParams.set("url", url);
+          return endpointUrl.toString();
+        })()
+      : `${endpointUrl.toString()}?${encoded}`;
    const created = await fetchJson<CdpTarget>(endpoint, 1500, {
      method: "PUT",
    }).catch(async (err) => {
@@ -164,18 +171,41 @@ function createProfileContext(
      targetId: created.id,
      title: created.title ?? "",
      url: created.url ?? url,
-      wsUrl: normalizeWsUrl(created.webSocketDebuggerUrl, base),
+      wsUrl: normalizeWsUrl(created.webSocketDebuggerUrl, profile.cdpUrl),
      type: created.type,
    };
  };

-  const isReachable = async (timeoutMs = 300) => {
-    const wsTimeout = Math.max(200, Math.min(2000, timeoutMs * 2));
-    return await isChromeCdpReady(profile.cdpUrl, timeoutMs, wsTimeout);
+  const resolveRemoteHttpTimeout = (timeoutMs: number | undefined) => {
+    if (profile.cdpIsLoopback) return timeoutMs ?? 300;
+    const resolved = state().resolved;
+    if (typeof timeoutMs === "number" && Number.isFinite(timeoutMs)) {
+      return Math.max(Math.floor(timeoutMs), resolved.remoteCdpTimeoutMs);
+    }
+    return resolved.remoteCdpTimeoutMs;
  };

-  const isHttpReachable = async (timeoutMs = 300) => {
-    return await isChromeReachable(profile.cdpUrl, timeoutMs);
+  const resolveRemoteWsTimeout = (timeoutMs: number | undefined) => {
+    if (profile.cdpIsLoopback) {
+      const base = timeoutMs ?? 300;
+      return Math.max(200, Math.min(2000, base * 2));
+    }
+    const resolved = state().resolved;
+    if (typeof timeoutMs === "number" && Number.isFinite(timeoutMs)) {
+      return Math.max(Math.floor(timeoutMs) * 2, resolved.remoteCdpHandshakeTimeoutMs);
+    }
+    return resolved.remoteCdpHandshakeTimeoutMs;
+  };
+
+  const isReachable = async (timeoutMs?: number) => {
+    const httpTimeout = resolveRemoteHttpTimeout(timeoutMs);
+    const wsTimeout = resolveRemoteWsTimeout(timeoutMs);
+    return await isChromeCdpReady(profile.cdpUrl, httpTimeout, wsTimeout);
+  };
+
+  const isHttpReachable = async (timeoutMs?: number) => {
+    const httpTimeout = resolveRemoteHttpTimeout(timeoutMs);
+    return await isChromeReachable(profile.cdpUrl, httpTimeout);
  };

  const attachRunning = (running: NonNullable<ProfileRuntimeState["running"]>) => {
@@ -327,7 +357,6 @@ function createProfileContext(
  };

  const focusTab = async (targetId: string): Promise<void> => {
-    const base = profile.cdpUrl.replace(/\/$/, "");
    const tabs = await listTabs();
    const resolved = resolveTargetIdFromTabs(targetId, tabs);
    if (!resolved.ok) {
@@ -336,13 +365,12 @@ function createProfileContext(
      }
      throw new Error("tab not found");
    }
-    await fetchOk(`${base}/json/activate/${resolved.targetId}`);
+    await fetchOk(appendCdpPath(profile.cdpUrl, `/json/activate/${resolved.targetId}`));
    const profileState = getProfileState();
    profileState.lastTargetId = resolved.targetId;
  };

  const closeTab = async (targetId: string): Promise<void> => {
-    const base = profile.cdpUrl.replace(/\/$/, "");
    const tabs = await listTabs();
    const resolved = resolveTargetIdFromTabs(targetId, tabs);
    if (!resolved.ok) {
@@ -351,7 +379,7 @@ function createProfileContext(
      }
      throw new Error("tab not found");
    }
-    await fetchOk(`${base}/json/close/${resolved.targetId}`);
+    await fetchOk(appendCdpPath(profile.cdpUrl, `/json/close/${resolved.targetId}`));
  };

  const stopRunningBrowser = async (): Promise<{ stopped: boolean }> => {
@@ -128,6 +128,12 @@ vi.mock("./cdp.js", () => ({
  createTargetViaCdp: cdpMocks.createTargetViaCdp,
  normalizeCdpWsUrl: vi.fn((wsUrl: string) => wsUrl),
  snapshotAria: cdpMocks.snapshotAria,
+  getHeadersWithAuth: vi.fn(() => ({})),
+  appendCdpPath: vi.fn((cdpUrl: string, path: string) => {
+    const base = cdpUrl.replace(/\/$/, "");
+    const suffix = path.startsWith("/") ? path : `/${path}`;
+    return `${base}${suffix}`;
+  }),
 }));

 vi.mock("./pw-ai.js", () => pwMocks);
@@ -129,6 +129,12 @@ vi.mock("./cdp.js", () => ({
  createTargetViaCdp: cdpMocks.createTargetViaCdp,
  normalizeCdpWsUrl: vi.fn((wsUrl: string) => wsUrl),
  snapshotAria: cdpMocks.snapshotAria,
+  getHeadersWithAuth: vi.fn(() => ({})),
+  appendCdpPath: vi.fn((cdpUrl: string, path: string) => {
+    const base = cdpUrl.replace(/\/$/, "");
+    const suffix = path.startsWith("/") ? path : `/${path}`;
+    return `${base}${suffix}`;
+  }),
 }));

 vi.mock("./pw-ai.js", () => pwMocks);
@@ -128,6 +128,12 @@ vi.mock("./cdp.js", () => ({
  createTargetViaCdp: cdpMocks.createTargetViaCdp,
  normalizeCdpWsUrl: vi.fn((wsUrl: string) => wsUrl),
  snapshotAria: cdpMocks.snapshotAria,
+  getHeadersWithAuth: vi.fn(() => ({})),
+  appendCdpPath: vi.fn((cdpUrl: string, path: string) => {
+    const base = cdpUrl.replace(/\/$/, "");
+    const suffix = path.startsWith("/") ? path : `/${path}`;
+    return `${base}${suffix}`;
+  }),
 }));

 vi.mock("./pw-ai.js", () => pwMocks);
@@ -128,6 +128,12 @@ vi.mock("./cdp.js", () => ({
  createTargetViaCdp: cdpMocks.createTargetViaCdp,
  normalizeCdpWsUrl: vi.fn((wsUrl: string) => wsUrl),
  snapshotAria: cdpMocks.snapshotAria,
+  getHeadersWithAuth: vi.fn(() => ({})),
+  appendCdpPath: vi.fn((cdpUrl: string, path: string) => {
+    const base = cdpUrl.replace(/\/$/, "");
+    const suffix = path.startsWith("/") ? path : `/${path}`;
+    return `${base}${suffix}`;
+  }),
 }));

 vi.mock("./pw-ai.js", () => pwMocks);
@@ -128,6 +128,12 @@ vi.mock("./cdp.js", () => ({
  createTargetViaCdp: cdpMocks.createTargetViaCdp,
  normalizeCdpWsUrl: vi.fn((wsUrl: string) => wsUrl),
  snapshotAria: cdpMocks.snapshotAria,
+  getHeadersWithAuth: vi.fn(() => ({})),
+  appendCdpPath: vi.fn((cdpUrl: string, path: string) => {
+    const base = cdpUrl.replace(/\/$/, "");
+    const suffix = path.startsWith("/") ? path : `/${path}`;
+    return `${base}${suffix}`;
+  }),
 }));

 vi.mock("./pw-ai.js", () => pwMocks);
@@ -128,6 +128,12 @@ vi.mock("./cdp.js", () => ({
  createTargetViaCdp: cdpMocks.createTargetViaCdp,
  normalizeCdpWsUrl: vi.fn((wsUrl: string) => wsUrl),
  snapshotAria: cdpMocks.snapshotAria,
+  getHeadersWithAuth: vi.fn(() => ({})),
+  appendCdpPath: vi.fn((cdpUrl: string, path: string) => {
+    const base = cdpUrl.replace(/\/$/, "");
+    const suffix = path.startsWith("/") ? path : `/${path}`;
+    return `${base}${suffix}`;
+  }),
 }));

 vi.mock("./pw-ai.js", () => pwMocks);
Author	SHA1	Message	Date
Marc	38841c71e0	fix: merge subagent auth profiles	2026-01-16 20:19:19 +00:00
Marcandmarcmarg	ec1b430a2c	fix: avoid format keyword in tool schemas Co-authored-by: marcmarg <marcmarg@users.noreply.github.com>	2026-01-16 20:19:15 +00:00
Peter SteinbergerandChristoph Nakazawa	3431d3d115	chore: tweak tool call narration guidance (#1008 ) Co-authored-by: Christoph Nakazawa <christoph.pojer@gmail.com>	2026-01-16 19:56:04 +00:00
Peter Steinberger	fe9e027d58	test: deflake background exec timeout	2026-01-16 19:48:52 +00:00
Peter Steinberger	33d17957e5	test: cover doctor launchctl env overrides (#1037 ) * test: cover doctor launchctl env overrides * style(macos): fix swiftformat lint	2026-01-16 19:40:45 +00:00
Nima KarimiandPeter Steinberger	25ae5f897e	fix(macos): check config file mode for gateway token/password resolution (#1022 ) * fix: honor config gateway mode for credentials * chore: oxfmt doctor platform notes --------- Co-authored-by: Peter Steinberger <steipete@gmail.com>	2026-01-16 19:29:48 +00:00
Peter Steinberger	624ff09314	test: expand gateway auth probe coverage	2026-01-16 19:16:03 +00:00
Peter Steinberger	c8003ae472	docs: update changelog for gateway probe fix (#1011 ) (thanks @ivanrvpereira)	2026-01-16 19:07:44 +00:00
Peter Steinberger	6bf627bce8	Merge pull request #1011 from ivanrvpereira/fix/security-audit-gateway-auth fix(security): resolve local auth for gateway probe	2026-01-16 19:05:07 +00:00
henrymascot	08525435e0	showcase: add Linear CLI and Beeper CLI - @NessZerra Linear CLI - manage Linear issues from terminal, works with Claude Code/Clawdbot - @jules Beeper CLI - read/send/archive messages via Beeper Desktop MCP API	2026-01-16 19:05:02 +00:00
Shadow	026cf1130e	Changelog: note Discord skill truncation	2026-01-16 10:03:53 -06:00
Wilkins	bb14b19922	fix: truncate skill command descriptions to 100 chars for Discord (#1018 ) * fix: truncate skill command descriptions to 100 chars for Discord Discord slash commands have a 100 character limit for descriptions. Skill descriptions were not being truncated, causing command registration to fail with an empty error from the Discord API. * style: format * style: format	2026-01-16 10:01:59 -06:00
Ivan Pereira	544ca062a3	test(security): add coverage for gateway probe auth selection	2026-01-16 13:31:01 +00:00
Ivan Pereira	be9aa5494a	fix(security): resolve local auth for gateway probe	2026-01-16 13:19:55 +00:00
Peter Steinberger	0d6af15d1c	feat: add user-invocable skill commands	2026-01-16 12:10:29 +00:00
Peter Steinberger	eda9410bce	fix: stabilize docker test suite	2026-01-16 11:47:14 +00:00
Peter Steinberger	a51ed8a5dd	fix(cli): auto-update global installs	2026-01-16 11:45:37 +00:00
Peter Steinberger	19bcbf85df	fix: scope whatsapp self-chat response prefix	2026-01-16 10:54:11 +00:00
Peter Steinberger	f49d0e5476	fix: expand exec abort/timeout coverage	2026-01-16 10:43:22 +00:00
Peter Steinberger	9c4c9c5edd	chore: release 2026.1.15	2026-01-16 10:37:30 +00:00
gerardward2007 Claude Opus 4.5 Peter Steinberger	0f34255359	chore: ignore local identity files (#1001 ) (thanks @gerardward2007) * chore: ignore local identity files (IDENTITY.md, USER.md) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: ignore local identity files (#1001) (thanks @gerardward2007) * chore: format session status tool * chore: format bash exec background abort test --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Peter Steinberger <steipete@gmail.com>	2026-01-16 10:30:04 +00:00
tosh-hamburg	de5fb65cb8	fix: docker-setup fails on Synology because of problem with bun (#1002 )	2026-01-16 10:03:56 +00:00
Roshan Singh	e773f84e39	fix: keep background exec aborts from killing sessions (#1000 ) (thanks @roshanasingh4) When exec returns early in background mode, the tool-call AbortSignal can fire and previously caused killProcessTree(SIGKILL). Ignore abort after yielding/backgrounding so background sessions keep running.	2026-01-16 10:01:39 +00:00
Peter Steinberger	b969c216fc	docs: refresh unreleased highlights	2026-01-16 09:51:27 +00:00
Peter Steinberger	f51a4d2aca	docs: sort unreleased changelog	2026-01-16 09:46:12 +00:00
Peter Steinberger	30b3a9de30	fix: drop oauth status from session status	2026-01-16 09:39:12 +00:00
Peter Steinberger	0391f6553b	fix: correct minimax usage + show reset	2026-01-16 09:36:45 +00:00
Peter Steinberger	d0c986c4f0	feat: warn on weak model tiers	2026-01-16 09:34:37 +00:00
Peter Steinberger	384028e12e	refactor: unify session reset helper	2026-01-16 09:33:39 +00:00
Peter Steinberger	4c14d6c8db	chore: format web monitor inbox tests	2026-01-16 09:26:18 +00:00
Peter Steinberger	6fa437613b	fix: delete transcripts on role ordering reset	2026-01-16 09:20:16 +00:00
Peter Steinberger	949fa1051f	fix: wire markdown variant renderer	2026-01-16 09:19:25 +00:00
Peter Steinberger	4965727f39	chore: run format and fix sandbox browser timeouts	2026-01-16 09:18:58 +00:00
Peter Steinberger	7c34883267	refactor: consolidate chat markdown rendering	2026-01-16 09:16:43 +00:00
Peter Steinberger	072c3dc55c	fix: suppress WhatsApp pairing replies for historical DMs	2026-01-16 09:10:44 +00:00
Peter Steinberger	83b3875131	docs: add control UI unauthorized FAQ hint	2026-01-16 09:07:20 +00:00
Peter Steinberger	a35083808c	chore: update macOS package lock	2026-01-16 09:06:23 +00:00
Peter Steinberger	3d3ec9d972	docs: add browserless remote CDP example	2026-01-16 09:05:30 +00:00
Peter Steinberger	9838a2850f	fix: reset sessions after role ordering conflicts	2026-01-16 09:04:04 +00:00
Peter Steinberger	6c6bc6ff1c	fix: add control UI auth guidance	2026-01-16 09:03:02 +00:00
Peter Steinberger	1791c1a765	feat: render native chat markdown via Textual	2026-01-16 09:02:27 +00:00
Peter Steinberger	6e53c061ff	fix: tune remote CDP timeouts	2026-01-16 09:01:25 +00:00
Peter Steinberger	1773f8aea2	fix: upgrade ws to wss for https CDP	2026-01-16 08:44:08 +00:00
Peter Steinberger	52bdf57743	Merge pull request #880 from mkbehr/openai-image-gen-fix fix: Make openai-image-gen skill use appropriate defaults per model.	2026-01-16 08:42:13 +00:00
Peter Steinberger	b3ab24eb8e	fix: align image-gen defaults (#880 ) (thanks @mkbehr)	2026-01-16 08:41:23 +00:00
Michael BehrandClaude Opus 4.5	6ac1c1d6ea	fix(openai-image-gen): use correct file extension for output format When --output-format is specified for GPT models, save files with the correct extension (.webp, .jpeg, or .png) instead of always using .png. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-01-16 08:37:57 +00:00
Michael BehrandClaude Opus 4.5	7655a501d0	feat(openai-image-gen): add model-specific parameter support - Auto-detect model and apply appropriate defaults for size/quality - Add --background, --output-format, and --style parameters - Enforce dall-e-3 count=1 limitation with automatic adjustment - Omit quality parameter for dall-e-2 (not supported) - Document model-specific parameters and supported values 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-01-16 08:37:57 +00:00
Peter Steinberger	3b1b14b0b1	Merge pull request #895 from mukhtharcm/feat/chrome-browser-improvements feat(browser): add support for authenticated remote browser profiles	2026-01-16 08:32:02 +00:00
Peter Steinberger	bf15c87d2b	fix: support authenticated remote CDP URLs (#895 ) (thanks @mukhtharcm)	2026-01-16 08:31:51 +00:00
Peter Steinberger	2dae4d382f	Merge pull request #860 from nachoiacovino/feat/telegram-custom-commands feat(telegram): support custom commands in config	2026-01-16 08:26:26 +00:00
Peter Steinberger	e9a47a02d1	fix: stabilize macOS audio test and default browser detection	2026-01-16 08:25:39 +00:00
Peter SteinbergerandNacho Iacovino	929666a8c8	fix: add telegram custom commands (#860 ) (thanks @nachoiacovino) Co-authored-by: Nacho Iacovino <50103937+nachoiacovino@users.noreply.github.com>	2026-01-16 08:22:09 +00:00
Muhammed Mukhthar CMandPeter Steinberger	cd409e5667	fix: exclude google-antigravity from history downgrade hack (#894 ) * Agent: exclude google-antigravity from history downgrade hack * Lint: fix formatting in test * Lint: formatting and unused vars in test * fix: preserve google-antigravity tool calls (#894) (thanks @mukhtharcm) --------- Co-authored-by: Peter Steinberger <steipete@gmail.com>	2026-01-16 08:14:56 +00:00
Muhammed Mukhthar CM	8e80823b03	test(browser): fix missing getHeadersWithAuth mock in server tests	2026-01-16 08:11:00 +00:00
Muhammed Mukhthar CM	319afd192d	feat(browser): add support for remote playwright websocket auth	2026-01-16 08:11:00 +00:00
Muhammed Mukhthar CM	6e0daf0936	feat(browser): add support for authenticated remote CDP profiles	2026-01-16 08:10:32 +00:00