fix(tools): hide exec compatibility aliases from schema

Add a WebUI-only $<skill> completion shortcut without changing slash command behavior.

Keep slash autocomplete command-only and allow dollar skill shortcuts anywhere in the composer.

Co-authored-by: Alan Chen <zc2610@nyu.edu>

SECURITY.md

@@ -107,6 +107,7 @@ File operations have path traversal protection, but:
 **API Calls:**
 - All external API calls use HTTPS by default
 - Timeouts are configured to prevent hanging requests
+- The OpenAI-compatible API server must set `api.api_key` when binding to `0.0.0.0` or `::`; otherwise startup fails to prevent unauthenticated network access
 - Consider using a firewall to restrict outbound connections if needed
 
 **WhatsApp:**

docs/channel-plugin-guide.md

@@ -103,7 +103,8 @@ class WebhookChannel(BaseChannel):
         msg.content  — markdown text (convert to platform format as needed)
         msg.media    — list of local file paths to attach
         msg.chat_id  — the recipient (same chat_id you passed to _handle_message)
-        msg.metadata — may contain "_progress": True for streaming chunks
+        msg.metadata — channel routing context such as message/thread ids
+        msg.event    — typed runtime event for progress/status messages
         """
         logger.info("[webhook] -> {}: {}", msg.chat_id, msg.content[:80])
         # In a real plugin: POST to a callback URL, send via SDK, etc.
@@ -238,15 +239,15 @@ nanobot channels login <channel_name> --force  # re-authenticate
 | `supports_streaming` (property) | `True` when config has `"streaming": true` **and** subclass overrides `send_delta()`. |
 | `is_running` | Returns `self._running`. |
 | `login(force=False)` | Perform interactive login (e.g. QR code scan). Returns `True` if already authenticated or login succeeds. Override in subclasses that support interactive login. |
-| `send_reasoning_delta(chat_id, delta, metadata?)` | Optional hook for streamed model reasoning/thinking content. Default is no-op. |
+| `send_reasoning_delta(chat_id, delta, metadata?, *, stream_id?)` | Optional hook for streamed model reasoning/thinking content. Default is no-op. |
-| `send_reasoning_end(chat_id, metadata?)` | Optional hook marking the end of a reasoning block. Default is no-op. |
+| `send_reasoning_end(chat_id, metadata?, *, stream_id?)` | Optional hook marking the end of a reasoning block. Default is no-op. |
 | `send_reasoning(msg)` | Optional one-shot reasoning fallback. Default translates to `send_reasoning_delta()` + `send_reasoning_end()`. |
 
 ### Optional (streaming)
 
 | Method | Description |
 |--------|-------------|
-| `async send_delta(chat_id, delta, metadata?)` | Override to receive streaming chunks. See [Streaming Support](#streaming-support) for details. |
+| `async send_delta(chat_id, delta, metadata?, *, stream_id?, stream_end=False, resuming=False)` | Override to receive streaming chunks. See [Streaming Support](#streaming-support) for details. |
 
 ### Message Types
 
@@ -257,10 +258,12 @@ class OutboundMessage:
     chat_id: str        # recipient (same value you passed to _handle_message)
     content: str        # markdown text — convert to platform format as needed
     media: list[str]    # local file paths to attach (images, audio, docs)
-    metadata: dict      # may contain: "_progress" (bool) for streaming chunks,
+    metadata: dict      # channel routing context, e.g. "message_id" for threading
-                        #              "message_id" for reply threading
+    event: object | None # typed runtime/UI event; usually inspect with isinstance()
 ```
 
+Runtime/UI semantics live on `msg.event`. Plugin-authored outbound messages should use typed events instead of legacy metadata flags such as `_progress`, `_stream_delta`, `_stream_end`, `_reasoning_delta`, `_turn_end`, or `_goal_status`. nanobot still accepts those old flags as a compatibility bridge for existing in-process extensions, but new plugin code should not add fresh dependencies on them.
+
 ## Streaming Support
 
 Channels can opt into real-time streaming — the agent sends content token-by-token instead of one final message. This is entirely optional; channels work fine without it.
@@ -279,10 +282,18 @@ If either is missing, the agent falls back to the normal one-shot `send()` path.
 Override `send_delta` to handle two types of calls:
 
 ```python
-async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> None:
+async def send_delta(
-    meta = metadata or {}
+    self,
-
+    chat_id: str,
-    if meta.get("_stream_end"):
+    delta: str,
+    metadata: dict[str, Any] | None = None,
+    *,
+    stream_id: str | None = None,
+    stream_end: bool = False,
+    resuming: bool = False,
+) -> None:
+    buffer_key = stream_id or chat_id
+    if stream_end:
         # Streaming finished — do final formatting, cleanup, etc.
         return
 
@@ -290,12 +301,7 @@ async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] |
     # delta contains a small chunk of text (a few tokens)
 ```
 
-**Metadata flags:**
+Streaming state is passed through keyword-only arguments, not `_stream_delta` or `_stream_end` metadata flags. Use `stream_id` to key any per-stream buffers; fall back to `chat_id` when it is missing.
-
-| Flag | Meaning |
-|------|---------|
-| `_stream_delta: True` | A content chunk (delta contains the new text) |
-| `_stream_end: True` | Streaming finished (delta is empty) |
 
 ### Example: Webhook with Streaming
 
@@ -310,18 +316,27 @@ class WebhookChannel(BaseChannel):
         super().__init__(config, bus)
         self._buffers: dict[str, str] = {}
 
-    async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> None:
+    async def send_delta(
-        meta = metadata or {}
+        self,
-        if meta.get("_stream_end"):
+        chat_id: str,
-            text = self._buffers.pop(chat_id, "")
+        delta: str,
+        metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
+        stream_end: bool = False,
+        resuming: bool = False,
+    ) -> None:
+        buffer_key = stream_id or chat_id
+        if stream_end:
+            text = self._buffers.pop(buffer_key, "")
             # Final delivery — format and send the complete message
             await self._deliver(chat_id, text, final=True)
             return
 
-        self._buffers.setdefault(chat_id, "")
+        self._buffers.setdefault(buffer_key, "")
-        self._buffers[chat_id] += delta
+        self._buffers[buffer_key] += delta
         # Incremental update — push partial text to the client
-        await self._deliver(chat_id, self._buffers[chat_id], final=False)
+        await self._deliver(chat_id, self._buffers[buffer_key], final=False)
 
     async def send(self, msg: OutboundMessage) -> None:
         # Non-streaming path — unchanged
@@ -350,7 +365,7 @@ When `streaming` is `false` (default) or omitted, only `send()` is called — no
 
 | Method / Property | Description |
 |-------------------|-------------|
-| `async send_delta(chat_id, delta, metadata?)` | Override to handle streaming chunks. No-op by default. |
+| `async send_delta(chat_id, delta, metadata?, *, stream_id?, stream_end=False, resuming=False)` | Override to handle streaming chunks. No-op by default. |
 | `supports_streaming` (property) | Returns `True` when config has `streaming: true` **and** subclass overrides `send_delta`. |
 
 ## Progress, Tool Hints, and Reasoning
@@ -359,18 +374,20 @@ Besides normal assistant text, nanobot can emit low-emphasis trace blocks. These
 
 ### Progress and Tool Hints
 
-Progress and tool hints arrive through the normal `send(msg)` path. Check `msg.metadata` before rendering:
+Progress and tool hints arrive through the normal `send(msg)` path. Check `msg.event` before rendering:
 
 ```python
-async def send(self, msg: OutboundMessage) -> None:
+from nanobot.bus.outbound_events import ProgressEvent
-    meta = msg.metadata or {}
 
-    if meta.get("_tool_hint"):
+async def send(self, msg: OutboundMessage) -> None:
+    event = msg.event
+
+    if isinstance(event, ProgressEvent) and event.tool_hint:
         # A short tool breadcrumb, e.g. read_file("config.json")
         await self._send_trace(msg.chat_id, msg.content, kind="tool")
         return
 
-    if meta.get("_progress"):
+    if isinstance(event, ProgressEvent):
         # Generic non-final status, e.g. "Thinking..." or "Running command..."
         await self._send_trace(msg.chat_id, msg.content, kind="progress")
         return
@@ -412,32 +429,33 @@ class WebhookChannel(BaseChannel):
         chat_id: str,
         delta: str,
         metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
     ) -> None:
-        meta = metadata or {}
+        buffer_key = stream_id or chat_id
-        stream_id = str(meta.get("_stream_id") or chat_id)
+        self._reasoning_buffers[buffer_key] = self._reasoning_buffers.get(buffer_key, "") + delta
-        self._reasoning_buffers[stream_id] = self._reasoning_buffers.get(stream_id, "") + delta
+        await self._update_reasoning_block(chat_id, self._reasoning_buffers[buffer_key], final=False)
-        await self._update_reasoning_block(chat_id, self._reasoning_buffers[stream_id], final=False)
 
     async def send_reasoning_end(
         self,
         chat_id: str,
         metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
     ) -> None:
-        meta = metadata or {}
+        buffer_key = stream_id or chat_id
-        stream_id = str(meta.get("_stream_id") or chat_id)
+        text = self._reasoning_buffers.pop(buffer_key, "")
-        text = self._reasoning_buffers.pop(stream_id, "")
         if text:
             await self._update_reasoning_block(chat_id, text, final=True)
 ```
 
-**Reasoning metadata flags:**
+**Reasoning arguments:**
 
-| Flag | Meaning |
+| Argument | Meaning |
 |------|---------|
-| `_reasoning_delta: True` | A reasoning/thinking chunk; `delta` contains the new text. |
+| `delta` | A reasoning/thinking chunk for `send_reasoning_delta()`. |
-| `_reasoning_end: True` | The current reasoning block is complete; `delta` is empty. |
+| `stream_id` | Stable id for this assistant turn/segment. Use it to key buffers instead of only `chat_id`. |
-| `_reasoning: True` | Legacy one-shot reasoning. `BaseChannel.send_reasoning()` converts it to delta + end. |
+| `send_reasoning_end()` | The current reasoning block is complete. |
-| `_stream_id` | Stable id for this assistant turn/segment. Use it to key buffers instead of only `chat_id`. |
 
 Reasoning visibility is controlled by `showReasoning` globally or per channel:
 

docs/configuration.md

@@ -240,6 +240,7 @@ Tracing covers the providers that go through nanobot's OpenAI-compatible client
 > - **Xiaomi MiMo thinking mode**: MiMo models (e.g. `mimo-v2.5-pro`) default to enabled thinking. Use `agents.defaults.reasoningEffort: "none"` to disable it, or `"low"` / `"medium"` / `"high"` to keep it on. Omitting the field preserves the provider's per-model default.
 > - **Xiaomi MiMo Token Plan**: If you're on MiMo's token plan, set `"apiBase": "https://token-plan-sgp.xiaomimimo.com/v1"` in your xiaomi_mimo provider config.
 > - **Custom OpenAI-compatible providers**: Besides the built-in `custom` provider, any extra key under `providers` can define its own OpenAI-compatible endpoint. For example, `providers.companyProxy.apiBase` plus `modelPresets.primary.provider: "companyProxy"` creates a separate custom provider. Set `apiBase`; set `apiKey` only when the endpoint requires it. This named-custom path uses the OpenAI-compatible request format only. For Anthropic-compatible proxies, use `providers.anthropic.apiBase` with `provider: "anthropic"`.
+> - **Provider-scoped proxy**: `providers.<name>.proxy` routes only that provider through an HTTP proxy. It is supported for OpenAI-compatible providers and `openai_codex`. Native provider backends such as `anthropic`, `bedrock`, `azure_openai`, and `github_copilot` reject `proxy`.
 
 | Provider | Purpose | Get API Key |
 |----------|---------|-------------|
@@ -632,20 +633,37 @@ nanobot agent -m "Reply with one short sentence."
 <details>
 <summary><b>OpenAI Codex (OAuth)</b></summary>
 
-Codex uses OAuth instead of API keys. Requires a ChatGPT Plus or Pro account. No `providers.openaiCodex` block is needed in `config.json`; `nanobot provider login` stores the OAuth session outside config.
+Codex uses OAuth instead of API keys. Requires a ChatGPT Plus or Pro account. `nanobot provider login` stores the OAuth session outside config. A `providers.openai_codex` block is optional and is only needed for provider-specific settings such as a proxy.
 
 **1. Login:**
 ```bash
 nanobot provider login openai-codex
 ```
 
-**2. Set model** (merge into `~/.nanobot/config.json`):
+If the machine running nanobot cannot open a graphical browser, copy the printed URL into a real browser. For remote SSH login, open the URL locally, then paste the final `http://localhost:1455/auth/callback?...` redirect URL back into the terminal when prompted.
+
+**2. Optional proxy** (merge into `~/.nanobot/config.json` if Codex OAuth or Codex API traffic must use a proxy):
+
+```json
+{
+  "providers": {
+    "openai_codex": {
+      "proxy": "http://127.0.0.1:7890"
+    }
+  }
+}
+```
+
+The proxy applies to Codex OAuth token refresh, interactive token exchange, and Codex Responses API requests. It does not affect other providers; configure `proxy` separately on each supported provider that needs it.
+
+**3. Set model** (merge into `~/.nanobot/config.json`):
 ```json
 {
   "modelPresets": {
     "codex": {
       "provider": "openai_codex",
-      "model": "openai-codex/gpt-5.1-codex"
+      "model": "gpt-5.1-codex",
+      "reasoningEffort": "high"
     }
   },
   "agents": {
@@ -656,7 +674,9 @@ nanobot provider login openai-codex
 }
 ```
 
-**3. Chat:**
+Use `reasoningEffort` in the preset to send a Codex reasoning effort such as `"low"`, `"medium"`, `"high"`, or another value supported by the selected model. When `provider` is explicitly `openai_codex`, the model name does not need the `openai-codex/` prefix.
+
+**4. Chat:**
 ```bash
 nanobot agent -m "Hello!"
 
@@ -675,7 +695,17 @@ nanobot agent -c ~/.nanobot-telegram/config.json -w /tmp/nanobot-telegram-test -
 <details>
 <summary><b>GitHub Copilot (OAuth)</b></summary>
 
-GitHub Copilot uses OAuth instead of API keys. Requires a [GitHub account with a plan](https://github.com/features/copilot/plans) configured. No `providers.githubCopilot` block is needed in `config.json`; `nanobot provider login` stores the OAuth session outside config.
+GitHub Copilot uses OAuth instead of API keys. Requires a [GitHub account with a plan](https://github.com/features/copilot/plans) configured. No `providers.github_copilot` block is needed in `config.json`; `nanobot provider login` stores the OAuth session outside config.
+
+For GitHub Enterprise / Copilot for Business, set the endpoint overrides you need before login:
+```bash
+export NANOBOT_GITHUB_COPILOT_CLIENT_ID="your-enterprise-client-id"
+export NANOBOT_GITHUB_DEVICE_CODE_URL="https://ghe.example/login/device/code"
+export NANOBOT_GITHUB_ACCESS_TOKEN_URL="https://ghe.example/login/oauth/access_token"
+export NANOBOT_GITHUB_USER_URL="https://api.ghe.example/user"
+export NANOBOT_COPILOT_TOKEN_URL="https://api.ghe.example/copilot_internal/v2/token"
+export NANOBOT_COPILOT_BASE_URL="https://copilot-api.ghe.example"
+```
 
 **1. Login:**
 ```bash
@@ -1974,6 +2004,7 @@ The heartbeat job is backed by the same cron service as user-created reminders.
 | `gateway.heartbeat.enabled` | `true` | Register the built-in heartbeat cron job on gateway startup. |
 | `gateway.heartbeat.intervalS` | `1800` | Seconds between heartbeat checks. |
 | `gateway.heartbeat.keepRecentMessages` | `8` | Number of recent heartbeat-session messages to retain after each run. |
+| `gateway.restartMode` | `auto` | Restart strategy for `/restart`: `auto` uses `spawn` on Windows foreground runs and `exec` elsewhere. Use `exit` with Windows service wrappers such as WinSW or nssm so the service manager owns the restart. |
 
 
 ## Subagent Concurrency

docs/openai-api.md

@@ -12,6 +12,32 @@ Run the CLI check first. If `nanobot agent -m "Hello!"` fails, fix provider or c
 
 For setup help, see [`quick-start.md`](./quick-start.md), [`providers.md`](./providers.md), and [`troubleshooting.md`](./troubleshooting.md).
 
+## Authentication
+
+Local-only `127.0.0.1` usage does not require an API key. If you bind the API
+server to all interfaces with `api.host: "0.0.0.0"` or `"::"`, nanobot requires
+`api.apiKey`; otherwise startup fails to avoid exposing an unauthenticated agent
+endpoint on the network.
+
+```json
+{
+  "api": {
+    "host": "0.0.0.0",
+    "port": 8900,
+    "apiKey": "${NANOBOT_API_KEY}"
+  }
+}
+```
+
+When `api.apiKey` is set, send it as a Bearer token on API routes. The health
+endpoint remains unauthenticated so local probes and load balancers can still
+check process health.
+
+```bash
+curl http://127.0.0.1:8900/v1/models \
+  -H "Authorization: Bearer $NANOBOT_API_KEY"
+```
+
 ## Behavior
 
 - Session isolation: pass `"session_id"` in the request body to isolate conversations; omit for a shared default session (`api:default`)

docs/providers.md

@@ -61,9 +61,12 @@ These fields answer different questions:
 | `model` | `modelPresets.<name>.model` | The model ID expected by that provider or gateway. |
 | `apiKey` | `providers.<provider>.apiKey` | Credential for that provider. Use `${ENV_VAR}` for secrets. |
 | `apiBase` | `providers.<provider>.apiBase` | HTTP base URL of the provider endpoint. |
+| `proxy` | `providers.<provider>.proxy` | Optional HTTP proxy for this provider only. Supported for OpenAI-compatible providers and OpenAI Codex. |
 
 You usually omit `apiBase` for hosted built-in providers such as OpenRouter, Anthropic direct, OpenAI direct, Groq, or Bedrock because nanobot knows their default endpoints. Set `apiBase` for `custom`, local OpenAI-compatible servers, provider proxies, regional endpoints, or subscription endpoints. Include the API version path when the endpoint requires it, for example `https://api.example.com/v1` or `http://localhost:11434/v1`.
 
+Use `proxy` when one provider must send HTTP traffic through a proxy without changing process-wide `HTTP_PROXY` / `HTTPS_PROXY`. This is supported for providers that use nanobot's OpenAI-compatible client, including `openai`, `custom`, named custom providers, OpenRouter-style gateways, local OpenAI-compatible servers, and similar registry entries. It is also supported for `openai_codex`, including Codex OAuth token exchange/refresh and Codex Responses API requests. Native provider backends such as `anthropic`, `bedrock`, `azure_openai`, and `github_copilot` reject `proxy`; use their endpoint-specific configuration instead.
+
 ## Common Provider Patterns
 
 ### OpenRouter Gateway
@@ -422,6 +425,32 @@ nanobot provider login github-copilot
 
 Then explicitly select the provider and model in a preset. OAuth providers are not valid automatic fallbacks.
 
+For OpenAI Codex, add `providers.openai_codex.proxy` only when Codex OAuth/token refresh or Codex API requests must use a proxy:
+
+```json
+{
+  "providers": {
+    "openai_codex": {
+      "proxy": "http://127.0.0.1:7890"
+    }
+  },
+  "modelPresets": {
+    "codex": {
+      "provider": "openai_codex",
+      "model": "gpt-5.1-codex",
+      "reasoningEffort": "high"
+    }
+  },
+  "agents": {
+    "defaults": {
+      "modelPreset": "codex"
+    }
+  }
+}
+```
+
+If you run the login command on a remote/headless machine and open the authorization URL in a local browser, paste the final `http://localhost:1455/auth/callback?...` redirect URL back into the terminal when prompted. See [`configuration.md#providers`](./configuration.md#providers) for the full OAuth provider notes.
+
 ## Provider Resolution
 
 The recommended path is a named preset selected by `agents.defaults.modelPreset`. The effective model parameters come from:

nanobot/agent/autocompact.py

@@ -34,6 +34,26 @@ class AutoCompact:
             ts = datetime.fromisoformat(ts)
         return ((now or datetime.now()) - ts).total_seconds() >= self._ttl * 60
 
+    def _has_compactable_idle_tail(self, key: str) -> bool:
+        session = self.sessions.get_or_create(key)
+        tail = list(session.messages[session.last_consolidated:])
+        if not tail:
+            return False
+        probe = Session(
+            key=session.key,
+            messages=tail,
+            created_at=session.created_at,
+            updated_at=session.updated_at,
+            metadata={},
+            last_consolidated=0,
+        )
+        result = probe.retain_recent_legal_suffix(
+            self._RECENT_SUFFIX_MESSAGES,
+            extend_to_user=True,
+        )
+        messages_to_remove = result.dropped[result.already_consolidated_count:]
+        return bool(messages_to_remove)
+
     @staticmethod
     def _format_summary(text: str, last_active: datetime) -> str:
         return f"Previous conversation summary (last active {last_active.isoformat()}):\n{text}"
@@ -52,7 +72,8 @@ class AutoCompact:
                 continue
             if key in active_session_keys:
                 continue
-            if self._is_expired(info.get("updated_at"), now):
+            updated_at = info.get("updated_at")
+            if self._is_expired(updated_at, now) and self._has_compactable_idle_tail(key):
                 self._archiving.add(key)
                 schedule_background(self._archive(key))
 

nanobot/agent/context_governance.py

@@ -36,6 +36,23 @@ COMPACTABLE_TOOLS = frozenset({
 # read_file is the recovery path for persisted results; exempting it prevents persist->read->persist loops.
 TOOL_RESULT_OFFLOAD_EXEMPT_TOOLS = frozenset({"read_file"})
 BACKFILL_CONTENT = "[Tool result unavailable — call was interrupted or lost]"
+PLACEHOLDER_TEXTS = frozenset({
+    "[Previous assistant message omitted.]",
+})
+
+
+def _tool_call_name_is_valid(tool_call: Any) -> bool:
+    """Whether a persisted OpenAI-style tool_call carries a usable name.
+
+    Mirrors ``ToolCallRequest.has_valid_name`` for the dict shape stored in
+    message history: a degenerate call with ``name=None`` / ``""`` cannot be
+    executed and is rejected by upstream APIs if replayed.
+    """
+    if not isinstance(tool_call, dict):
+        return False
+    fn = tool_call.get("function")
+    name = fn.get("name") if isinstance(fn, dict) else tool_call.get("name")
+    return isinstance(name, str) and bool(name)
 
 
 @dataclass(slots=True)
@@ -61,7 +78,9 @@ class ContextGovernor:
         messages: list[dict[str, Any]],
         compacted_tool_call_ids: set[str],
     ) -> list[dict[str, Any]]:
-        updated = self.drop_orphan_tool_results(messages)
+        updated = self.strip_placeholder_assistant_messages(messages)
+        updated = self.strip_malformed_tool_calls(updated)
+        updated = self.drop_orphan_tool_results(updated)
         updated = self.backfill_missing_tool_results(updated)
         updated = self.apply_tool_result_budget(config, updated)
         updated = self.compact_inflight_overflow(config, updated, compacted_tool_call_ids)
@@ -116,6 +135,99 @@ class ContextGovernor:
             return truncate_text(content, config.max_tool_result_chars)
         return content
 
+    @staticmethod
+    def strip_placeholder_assistant_messages(
+        messages: list[dict[str, Any]],
+    ) -> list[dict[str, Any]]:
+        """Remove assistant messages that are compaction placeholders.
+
+        Messages like ``[Previous assistant message omitted.]`` carry no useful
+        context for the model and can cause it to repeatedly attempt tool calls
+        that previously failed, producing malformed responses in a loop.
+        Consecutive same-role messages that result from removal are handled
+        downstream by the provider's merge-consecutive logic. Only the
+        model-facing copy is repaired; the persisted transcript is untouched
+        (a copy is returned, or the same list object when nothing changes).
+        """
+        updated: list[dict[str, Any]] | None = None
+        for idx, msg in enumerate(messages):
+            if msg.get("role") != "assistant":
+                if updated is not None:
+                    updated.append(msg)
+                continue
+            content = msg.get("content", "")
+            text = content if isinstance(content, str) else ""
+            is_placeholder = text.strip() in PLACEHOLDER_TEXTS
+            has_tool_calls = bool(msg.get("tool_calls"))
+            if is_placeholder and not has_tool_calls:
+                if updated is None:
+                    updated = list(messages[:idx])
+                logger.debug(
+                    "Stripping placeholder assistant message from history: {!r}",
+                    text[:60],
+                )
+                continue
+            if updated is not None:
+                updated.append(msg)
+        if updated is None:
+            return messages
+        return updated
+
+    @staticmethod
+    def strip_malformed_tool_calls(
+        messages: list[dict[str, Any]],
+    ) -> list[dict[str, Any]]:
+        """Drop persisted assistant tool_calls whose name is missing/non-string.
+
+        A degenerate tool call (``name=None`` or ``""``) that slipped into the
+        saved history before this guard existed gets replayed on every turn and
+        makes upstream APIs reject the whole request
+        (``messages.content.N.tool_use.name: Input should be a valid string``),
+        permanently wedging the session. Removing the bad call here lets the
+        existing orphan-result cleanup drop its now-dangling tool result, so a
+        polluted session self-heals on its next turn. The persisted transcript
+        is left untouched; only the model-facing copy is repaired (a copy is
+        returned, or the same list object when nothing changes).
+        """
+        updated: list[dict[str, Any]] | None = None
+        for idx, msg in enumerate(messages):
+            if msg.get("role") != "assistant":
+                if updated is not None:
+                    updated.append(msg)
+                continue
+            calls = msg.get("tool_calls")
+            if not calls:
+                if updated is not None:
+                    updated.append(msg)
+                continue
+            kept = [tc for tc in calls if _tool_call_name_is_valid(tc)]
+            if len(kept) == len(calls):
+                if updated is not None:
+                    updated.append(msg)
+                continue
+            if updated is None:
+                updated = [dict(m) for m in messages[:idx]]
+            logger.warning(
+                "Stripping {} malformed tool_call(s) with missing/non-string "
+                "name from assistant history before request",
+                len(calls) - len(kept),
+            )
+            repaired = dict(msg)
+            if kept:
+                repaired["tool_calls"] = kept
+            else:
+                repaired.pop("tool_calls", None)
+            # An assistant turn with neither content nor any valid tool call is
+            # itself invalid upstream; drop it entirely in that case.
+            has_content = bool(repaired.get("content"))
+            if not kept and not has_content:
+                continue
+            updated.append(repaired)
+
+        if updated is None:
+            return messages
+        return updated
+
     @staticmethod
     def drop_orphan_tool_results(
         messages: list[dict[str, Any]],

nanobot/agent/loop.py

@@ -31,6 +31,13 @@ from nanobot.agent.tools.message import MessageTool
 from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.agent.tools.self import MyTool
 from nanobot.bus.events import InboundMessage, OutboundMessage
+from nanobot.bus.outbound_events import (
+    RetryWaitEvent,
+    StreamDeltaEvent,
+    StreamedResponseEvent,
+    StreamEndEvent,
+    outbound_message_for_event,
+)
 from nanobot.bus.progress import build_bus_progress_callback
 from nanobot.bus.queue import MessageBus
 from nanobot.bus.runtime_events import (
@@ -57,7 +64,11 @@ from nanobot.session.goal_state import (
     sustained_goal_active,
 )
 from nanobot.session.keys import UNIFIED_SESSION_KEY, session_key_for_channel
-from nanobot.session.manager import Session, SessionManager
+from nanobot.session.manager import (
+    Session,
+    SessionManager,
+    replay_max_messages_for_context,
+)
 from nanobot.utils.document import extract_documents, reference_non_image_attachments
 from nanobot.utils.helpers import image_placeholder_text
 from nanobot.utils.helpers import truncate_text as truncate_text_fn
@@ -201,7 +212,6 @@ class AgentLoop:
         timezone: str | None = None,
         session_ttl_minutes: int = 0,
         consolidation_ratio: float = 0.5,
-        max_messages: int = 120,
         hooks: list[AgentHook] | None = None,
         unified_session: bool = False,
         disabled_skills: list[str] | None = None,
@@ -215,6 +225,7 @@ class AgentLoop:
         preset_snapshot_loader: preset_helpers.PresetSnapshotLoader | None = None,
         runtime_events: RuntimeEventBus | None = None,
         runtime_model_publisher: Callable[[str, str | None], None] | None = None,
+        restart_mode: str = "auto",
     ):
         from nanobot.config.schema import ToolsConfig
 
@@ -224,6 +235,7 @@ class AgentLoop:
         self.runtime_events = runtime_events or RuntimeEventBus()
         self.runtime_event_publisher = RuntimeEventPublisher(self.runtime_events)
         self.channels_config = channels_config
+        self.restart_mode = restart_mode
         self.provider = provider
         self._provider_snapshot_loader = provider_snapshot_loader
         self._preset_snapshot_loader = preset_snapshot_loader
@@ -292,7 +304,7 @@ class AgentLoop:
             llm_wall_timeout_for_session=lambda sk: runner_wall_llm_timeout_s(self.sessions, sk),
         )
         self._unified_session = unified_session
-        self._max_messages = max_messages if max_messages > 0 else 120
+        self._max_messages = replay_max_messages_for_context(self.context_window_tokens)
         self._running = False
         self._mcp_servers = mcp_servers or {}
         self._mcp_stacks: dict[str, AsyncExitStack] = {}
@@ -390,10 +402,10 @@ class AgentLoop:
             disabled_skills=defaults.disabled_skills,
             session_ttl_minutes=defaults.session_ttl_minutes,
             consolidation_ratio=defaults.consolidation_ratio,
-            max_messages=defaults.max_messages,
             tools_config=config.tools,
             model_presets=preset_helpers.configured_model_presets(config),
             model_preset=defaults.model_preset,
+            restart_mode=config.gateway.restart_mode,
             provider_snapshot_loader=provider_snapshot_loader,
             preset_snapshot_loader=preset_snapshot_loader,
             **extra,
@@ -421,6 +433,7 @@ class AgentLoop:
         self.runner.provider = provider
         self.subagents.set_provider(provider, model)
         self.consolidator.set_provider(provider, model, context_window_tokens)
+        self._sync_replay_max_messages()
         self._provider_signature = snapshot.signature
         if publish_update and self._runtime_model_publisher is not None:
             self._runtime_model_publisher(
@@ -434,6 +447,9 @@ class AgentLoop:
             )
         logger.info("Runtime model switched for next turn: {} -> {}", old_model, model)
 
+    def _sync_replay_max_messages(self) -> None:
+        self._max_messages = replay_max_messages_for_context(self.context_window_tokens)
+
     def _refresh_provider_snapshot(self) -> None:
         if self._provider_snapshot_loader is None:
             return
@@ -558,14 +574,12 @@ class AgentLoop:
         """Build a retry-wait callback that publishes to the message bus."""
 
         async def _on_retry_wait(content: str) -> None:
-            meta = dict(msg.metadata or {})
-            meta["_retry_wait"] = True
             await self.bus.publish_outbound(
-                OutboundMessage(
+                outbound_message_for_event(
                     channel=msg.channel,
                     chat_id=msg.chat_id,
-                    content=content,
+                    event=RetryWaitEvent(content=content),
-                    metadata=meta,
+                    metadata=msg.metadata,
                 )
             )
 
@@ -990,26 +1004,31 @@ class AgentLoop:
                             return f"{stream_base_id}:{stream_segment}"
 
                         async def on_stream(delta: str) -> None:
-                            meta = dict(msg.metadata or {})
+                            await self.bus.publish_outbound(
-                            meta["_stream_delta"] = True
+                                outbound_message_for_event(
-                            meta["_stream_id"] = _current_stream_id()
+                                    channel=msg.channel,
-                            await self.bus.publish_outbound(OutboundMessage(
+                                    chat_id=msg.chat_id,
-                                channel=msg.channel, chat_id=msg.chat_id,
+                                    event=StreamDeltaEvent(
                                         content=delta,
-                                metadata=meta,
+                                        stream_id=_current_stream_id(),
-                            ))
+                                    ),
+                                    metadata=msg.metadata,
+                                )
+                            )
 
                         async def on_stream_end(*, resuming: bool = False) -> None:
                             nonlocal stream_segment
-                            meta = dict(msg.metadata or {})
+                            await self.bus.publish_outbound(
-                            meta["_stream_end"] = True
+                                outbound_message_for_event(
-                            meta["_resuming"] = resuming
+                                    channel=msg.channel,
-                            meta["_stream_id"] = _current_stream_id()
+                                    chat_id=msg.chat_id,
-                            await self.bus.publish_outbound(OutboundMessage(
+                                    event=StreamEndEvent(
-                                channel=msg.channel, chat_id=msg.chat_id,
+                                        stream_id=_current_stream_id(),
-                                content="",
+                                        resuming=resuming,
-                                metadata=meta,
+                                    ),
-                            ))
+                                    metadata=msg.metadata,
+                                )
+                            )
                             stream_segment += 1
 
                     response = await self._process_message(
@@ -1362,9 +1381,10 @@ class AgentLoop:
         preview = final_content[:120] + "..." if len(final_content) > 120 else final_content
         logger.info("Response to {}:{}: {}", msg.channel, msg.sender_id, preview)
 
+        event = None
         meta = dict(msg.metadata or {})
         if on_stream is not None and stop_reason not in {"error", "tool_error"}:
-            meta["_streamed"] = True
+            event = StreamedResponseEvent()
         if turn_latency_ms is not None:
             meta["latency_ms"] = int(turn_latency_ms)
 
@@ -1372,6 +1392,7 @@ class AgentLoop:
             channel=msg.channel,
             chat_id=msg.chat_id,
             content=final_content,
+            event=event,
             metadata=meta,
         )
 

nanobot/agent/memory.py

@@ -33,7 +33,6 @@ if TYPE_CHECKING:
     from nanobot.providers.base import LLMProvider
     from nanobot.session.manager import SessionManager
 
-
 # ---------------------------------------------------------------------------
 # MemoryStore — pure file I/O layer
 # ---------------------------------------------------------------------------
@@ -1006,7 +1005,6 @@ class Consolidator:
 
             messages_to_summarize = list(session.messages[session.last_consolidated:])
             if not messages_to_summarize:
-                session.updated_at = datetime.now()
                 self.sessions.save(session)
                 return ""
 
@@ -1018,12 +1016,11 @@ class Consolidator:
                 metadata={},
                 last_consolidated=0,
             )
-            dropped, already_consolidated = probe.retain_recent_legal_suffix(max_suffix, extend_to_user=True)
+            result = probe.retain_recent_legal_suffix(max_suffix, extend_to_user=True)
             messages_to_keep = probe.messages
-            messages_to_remove = dropped[already_consolidated:]
+            messages_to_remove = result.dropped[result.already_consolidated_count:]
 
             if not messages_to_remove and not messages_to_keep:
-                session.updated_at = datetime.now()
                 self.sessions.save(session)
                 return ""
 
@@ -1046,7 +1043,6 @@ class Consolidator:
 
             session.messages = messages_to_keep
             session.last_consolidated = 0
-            session.updated_at = datetime.now()
             self.sessions.save(session)
 
             if messages_to_remove:

nanobot/agent/runner.py

@@ -18,7 +18,7 @@ from nanobot.agent.context_governance import (
     ContextGovernor,
 )
 from nanobot.agent.hook import AgentHook, AgentHookContext, AgentRunHookContext
-from nanobot.agent.tools.registry import ToolRegistry
+from nanobot.agent.tools.registry import ToolRegistry, is_tool_error_result
 from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
 from nanobot.utils.file_edit_events import (
     StreamingFileEditTracker,
@@ -389,7 +389,15 @@ class AgentRunner:
                     spec.session_key or "default",
                 )
                 try:
-                    messages_for_model = ContextGovernor.drop_orphan_tool_results(messages)
+                    messages_for_model = ContextGovernor.strip_placeholder_assistant_messages(
+                        messages
+                    )
+                    messages_for_model = ContextGovernor.strip_malformed_tool_calls(
+                        messages_for_model
+                    )
+                    messages_for_model = ContextGovernor.drop_orphan_tool_results(
+                        messages_for_model
+                    )
                     messages_for_model = ContextGovernor.backfill_missing_tool_results(
                         messages_for_model
                     )
@@ -725,6 +733,8 @@ class AgentRunner:
         messages: list[dict[str, Any]],
         hook: AgentHook,
         context: AgentHookContext,
+        *,
+        malformed_retry: bool = False,
     ):
         timeout_s: float | None = spec.llm_timeout_s
         if timeout_s is None:
@@ -867,8 +877,94 @@ class AgentRunner:
             )
         if progress_state and progress_state.get("reasoning_open"):
             await hook.emit_reasoning_end()
+        dropped, all_dropped, original_finish_reason = (
+            self._drop_malformed_tool_calls(response)
+        )
+        if (
+            all_dropped
+            and original_finish_reason in ("tool_calls", "function_call")
+            and not malformed_retry
+        ):
+            logger.warning(
+                "Retrying LLM request after all {} malformed tool call(s) were dropped",
+                dropped,
+            )
+            retry_messages = self._malformed_tool_call_retry_messages(
+                messages, response.content,
+            )
+            return await self._request_model(
+                spec, retry_messages, hook, context,
+                malformed_retry=True,
+            )
+        if (
+            all_dropped
+            and original_finish_reason in ("tool_calls", "function_call")
+            and malformed_retry
+        ):
+            logger.warning(
+                "Malformed tool calls persisted after retry; falling back to no-tools request",
+            )
+            fallback_messages = self._malformed_tool_call_retry_messages(
+                messages, response.content,
+            )
+            return await self._request_no_tools(spec, fallback_messages)
         return response
 
+    @staticmethod
+    def _drop_malformed_tool_calls(
+        response: LLMResponse,
+    ) -> tuple[int, bool, str | None]:
+        """Strip tool calls whose name is missing/non-string from the response.
+
+        Returns (dropped_count, all_dropped, original_finish_reason).
+
+        A degenerate call (name=None or "") cannot be executed, and if it were
+        persisted into the assistant message it would be replayed on every
+        subsequent turn, causing upstream validation errors
+        (``tool_use.name: Input should be a valid string``) that permanently
+        wedge the session. Dropping it here keeps it out of execution, the
+        assistant message, and the saved history in one place.
+        """
+        calls = getattr(response, "tool_calls", None)
+        if not calls:
+            return (0, False, getattr(response, "finish_reason", None))
+        valid = [tc for tc in calls if tc.has_valid_name()]
+        if len(valid) == len(calls):
+            return (0, False, getattr(response, "finish_reason", None))
+        dropped = len(calls) - len(valid)
+        original_finish_reason = getattr(response, "finish_reason", None)
+        logger.warning(
+            "Dropped {} malformed tool call(s) with missing/non-string name "
+            "from LLM response (finish_reason={!r})",
+            dropped,
+            original_finish_reason,
+        )
+        response.tool_calls = valid
+        if not valid:
+            response.finish_reason = "stop"
+        return (dropped, not valid, original_finish_reason)
+
+    @staticmethod
+    def _malformed_tool_call_retry_messages(
+        messages: list[dict[str, Any]],
+        assistant_text: str | None,
+    ) -> list[dict[str, Any]]:
+        retry_messages = list(messages)
+        note = (
+            "The previous model response attempted to call tools, but every tool call "
+            "was malformed: the tool_use blocks had missing or non-string tool names. "
+            "Do not answer with a promise to use tools. Either call the required tools again "
+            "using valid tool names from the provided tool list and JSON object inputs, or give "
+            "a final answer only if no tool is required."
+        )
+        if assistant_text:
+            note += (
+                f"\n\nPrevious assistant text before the malformed calls:\n"
+                f"{assistant_text}"
+            )
+        retry_messages.append({"role": "user", "content": note})
+        return retry_messages
+
     async def _request_finalization_retry(
         self,
         spec: AgentRunSpec,
@@ -1170,7 +1266,7 @@ class AgentRunner:
                 return payload, event, exc
             return payload, event, None
 
-        if isinstance(result, str) and result.startswith("Error"):
+        if is_tool_error_result(tool_call.name, result):
             if file_edit_trackers and progress_callback is not None:
                 await invoke_file_edit_progress(
                     progress_callback,

nanobot/agent/tools/__init__.py

@@ -1,6 +1,6 @@
 """Agent tools module."""
 
-from nanobot.agent.tools.base import Schema, Tool, tool_parameters
+from nanobot.agent.tools.base import Schema, Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.context import ToolContext
 from nanobot.agent.tools.loader import ToolLoader
 from nanobot.agent.tools.registry import ToolRegistry
@@ -25,6 +25,7 @@ __all__ = [
     "Tool",
     "ToolContext",
     "ToolLoader",
+    "ToolResult",
     "ToolRegistry",
     "tool_parameters",
     "tool_parameters_schema",

nanobot/agent/tools/apply_patch.py

@@ -7,7 +7,7 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Any
 
-from nanobot.agent.tools.base import tool_parameters
+from nanobot.agent.tools.base import ToolResult, tool_parameters
 from nanobot.agent.tools.filesystem import _FsTool
 from nanobot.agent.tools.schema import (
     ArraySchema,
@@ -289,8 +289,8 @@ class ApplyPatchTool(_FsTool):
                 _format_summary(summary) for summary in summaries
             )
         except PermissionError as exc:
-            return f"Error: {exc}"
+            return ToolResult.error(f"Error: {exc}")
         except _PatchError as exc:
-            return f"Error applying patch: {exc}"
+            return ToolResult.error(f"Error applying patch: {exc}")
         except Exception as exc:
-            return f"Error applying patch: {exc}"
+            return ToolResult.error(f"Error applying patch: {exc}")

nanobot/agent/tools/base.py

@@ -128,6 +128,21 @@ class Schema(ABC):
         return Schema.validate_json_schema_value(value, self.to_json_schema(), path)
 
 
+class ToolResult(str):
+    """String-compatible tool output with structured status."""
+
+    is_error: bool
+
+    def __new__(cls, content: str, *, is_error: bool = False) -> ToolResult:
+        obj = str.__new__(cls, content)
+        obj.is_error = is_error
+        return obj
+
+    @classmethod
+    def error(cls, content: str) -> ToolResult:
+        return cls(content, is_error=True)
+
+
 class Tool(ABC):
     """Agent capability: read files, run commands, etc."""
 
@@ -193,9 +208,13 @@ class Tool(ABC):
 
     @abstractmethod
     async def execute(self, **kwargs: Any) -> Any:
-        """Run the tool; returns a string or list of content blocks."""
+        """Run the tool; return content, or ``ToolResult.error(...)`` for failures."""
         ...
 
+    @staticmethod
+    def error(content: str) -> ToolResult:
+        return ToolResult.error(content)
+
     def _cast_object(self, obj: Any, schema: dict[str, Any]) -> dict[str, Any]:
         if not isinstance(obj, dict):
             return obj

nanobot/agent/tools/cli_apps.py

@@ -7,7 +7,7 @@ from typing import Any
 
 from pydantic import Field
 
-from nanobot.agent.tools.base import Tool, tool_parameters
+from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.schema import (
     ArraySchema,
     BooleanSchema,
@@ -136,4 +136,4 @@ class CliAppsTool(Tool):
                 restrict_to_workspace=access.restrict_to_workspace,
             )
         except CliAppError as exc:
-            return f"Error: {exc.message}"
+            return ToolResult.error(f"Error: {exc.message}")

nanobot/agent/tools/cron.py

@@ -6,7 +6,7 @@ from contextvars import ContextVar
 from datetime import datetime
 from typing import Any
 
-from nanobot.agent.tools.base import Tool, tool_parameters
+from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.context import ContextAware, RequestContext
 from nanobot.agent.tools.schema import (
     IntegerSchema,
@@ -99,7 +99,7 @@ class CronTool(Tool, ContextAware):
         try:
             ZoneInfo(tz)
         except (KeyError, Exception):
-            return f"Error: unknown timezone '{tz}'"
+            return ToolResult.error(f"Error: unknown timezone '{tz}'")
         return None
 
     def _display_timezone(self, schedule: CronSchedule) -> str:
@@ -148,7 +148,7 @@ class CronTool(Tool, ContextAware):
     ) -> str:
         if action == "add":
             if self._in_cron_context.get():
-                return "Error: cannot schedule new jobs from within a cron job execution"
+                return ToolResult.error("Error: cannot schedule new jobs from within a cron job execution")
             return self._add_job(name, message, every_seconds, cron_expr, tz, at)
         elif action == "list":
             return self._list_jobs()
@@ -166,20 +166,20 @@ class CronTool(Tool, ContextAware):
         at: str | None,
     ) -> str:
         if not message:
-            return (
+            return ToolResult.error(
                 "Error: cron action='add' requires a non-empty 'message' parameter "
                 "describing what to do when the job triggers "
                 "(e.g. the reminder text). Retry including message=\"...\"."
             )
         session_key = self._session_key.get()
         if not session_key:
-            return "Error: scheduled cron jobs must be created from a chat session"
+            return ToolResult.error("Error: scheduled cron jobs must be created from a chat session")
         origin_channel = self._origin_channel.get()
         origin_chat_id = self._origin_chat_id.get()
         if not origin_channel or not origin_chat_id:
-            return "Error: scheduled cron jobs must be created from a chat session"
+            return ToolResult.error("Error: scheduled cron jobs must be created from a chat session")
         if tz and not cron_expr:
-            return "Error: tz can only be used with cron_expr"
+            return ToolResult.error("Error: tz can only be used with cron_expr")
         if tz:
             if err := self._validate_timezone(tz):
                 return err
@@ -199,7 +199,7 @@ class CronTool(Tool, ContextAware):
             try:
                 dt = datetime.fromisoformat(at)
             except ValueError:
-                return f"Error: invalid ISO datetime format '{at}'. Expected format: YYYY-MM-DDTHH:MM:SS"
+                return ToolResult.error(f"Error: invalid ISO datetime format '{at}'. Expected format: YYYY-MM-DDTHH:MM:SS")
             if dt.tzinfo is None:
                 if err := self._validate_timezone(self._default_timezone):
                     return err
@@ -208,7 +208,7 @@ class CronTool(Tool, ContextAware):
             schedule = CronSchedule(kind="at", at_ms=at_ms)
             delete_after = True
         else:
-            return "Error: either every_seconds, cron_expr, or at is required"
+            return ToolResult.error("Error: either every_seconds, cron_expr, or at is required")
 
         job = self._cron.add_job(
             name=name or message[:30],
@@ -279,7 +279,7 @@ class CronTool(Tool, ContextAware):
 
     def _remove_job(self, job_id: str | None) -> str:
         if not job_id:
-            return "Error: job_id is required for remove"
+            return ToolResult.error("Error: job_id is required for remove")
         result = self._cron.remove_job(job_id)
         if result == "removed":
             return f"Removed job {job_id}"

nanobot/agent/tools/exec_session.py

@@ -9,7 +9,7 @@ from contextlib import suppress
 from dataclasses import dataclass
 from typing import Any
 
-from nanobot.agent.tools.base import Tool, tool_parameters
+from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.context import current_request_session_key
 from nanobot.agent.tools.schema import (
     BooleanSchema,
@@ -492,11 +492,12 @@ class WriteStdinTool(Tool):
                 max_output_chars=output_limit,
                 owner_session_key=current_request_session_key(),
             )
-            return format_session_poll(session_id, poll)
+            result = format_session_poll(session_id, poll)
+            return ToolResult.error(result) if poll.timed_out else result
         except KeyError:
-            return f"Error: exec session not found: {session_id}"
+            return ToolResult.error(f"Error: exec session not found: {session_id!r}")
         except Exception as exc:
-            return f"Error writing to exec session: {exc}"
+            return ToolResult.error(f"Error writing to exec session: {exc}")
 
     async def _wait_for_output(
         self,
@@ -532,13 +533,14 @@ class WriteStdinTool(Tool):
                 joined = "".join(aggregate)
                 if wait_for in joined:
                     poll.output = joined
-                    return format_session_poll(session_id, poll)
+                    result = format_session_poll(session_id, poll)
+                    return ToolResult.error(result) if poll.timed_out else result
             if poll.done or remaining_ms <= 0:
                 poll.output = "".join(aggregate)
                 result = format_session_poll(session_id, poll)
                 if wait_for not in poll.output:
                     result += f"\nWait target not observed: {wait_for!r}"
-                return result
+                return ToolResult.error(result) if poll.timed_out else result
 
 
 @tool_parameters(tool_parameters_schema())
@@ -606,4 +608,4 @@ class ListExecSessionsTool(Tool):
                 )
             return "\n".join(lines)
         except Exception as exc:
-            return f"Error listing exec sessions: {exc}"
+            return ToolResult.error(f"Error listing exec sessions: {exc}")

nanobot/agent/tools/filesystem.py

@@ -7,7 +7,7 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Any
 
-from nanobot.agent.tools.base import Tool, tool_parameters
+from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.file_state import FileStates, _hash_file, current_file_states
 from nanobot.agent.tools.path_utils import resolve_workspace_path
 from nanobot.agent.tools.schema import (
@@ -268,19 +268,19 @@ class ReadFileTool(_FsTool):
     ) -> Any:
         try:
             if not path:
-                return "Error reading file: Unknown path"
+                return ToolResult.error("Error reading file: Unknown path")
 
             # Device path blacklist
             if _is_blocked_device(path):
-                return f"Error: Reading {path} is blocked (device path that could hang or produce infinite output)."
+                return ToolResult.error(f"Error: Reading {path} is blocked (device path that could hang or produce infinite output).")
 
             fp = self._resolve_read(path)
             if _is_blocked_device(fp):
-                return f"Error: Reading {fp} is blocked (device path that could hang or produce infinite output)."
+                return ToolResult.error(f"Error: Reading {fp} is blocked (device path that could hang or produce infinite output).")
             if not fp.exists():
-                return f"Error: File not found: {path}"
+                return ToolResult.error(f"Error: File not found: {path}")
             if not fp.is_file():
-                return f"Error: Not a file: {path}"
+                return ToolResult.error(f"Error: Not a file: {path}")
 
             # PDF support
             if fp.suffix.lower() == ".pdf":
@@ -343,7 +343,7 @@ class ReadFileTool(_FsTool):
                 mime = detect_image_mime(raw) or mimetypes.guess_type(path)[0]
                 if mime and mime.startswith("image/"):
                     return build_image_content_blocks(raw, mime, str(fp), f"(Image file: {path})")
-                return f"Error: Cannot read binary file {path} (MIME: {mime or 'unknown'}). Only UTF-8 text and images are supported."
+                return ToolResult.error(f"Error: Cannot read binary file {path} (MIME: {mime or 'unknown'}). Only UTF-8 text and images are supported.")
 
             # Normalize CRLF -> LF before line-splitting. Primarily a Windows
             # concern (git checkouts with autocrlf, editors saving CRLF) but
@@ -357,7 +357,7 @@ class ReadFileTool(_FsTool):
             if offset < 1:
                 offset = 1
             if offset > total:
-                return f"Error: offset {offset} is beyond end of file ({total} lines)"
+                return ToolResult.error(f"Error: offset {offset} is beyond end of file ({total} lines)")
 
             start = offset - 1
             end = min(start + (limit or self._DEFAULT_LIMIT), total)
@@ -381,20 +381,20 @@ class ReadFileTool(_FsTool):
             self._file_states.record_read(fp, offset=offset, limit=limit)
             return result
         except PermissionError as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
         except Exception as e:
-            return f"Error reading file: {e}"
+            return ToolResult.error(f"Error reading file: {e}")
 
     def _read_pdf(self, fp: Path, pages: str | None) -> str:
         try:
             import fitz  # pymupdf
         except ImportError:
-            return "Error: PDF reading requires pymupdf. Install with: pip install pymupdf"
+            return ToolResult.error("Error: PDF reading requires pymupdf. Install with: pip install pymupdf")
 
         try:
             doc = fitz.open(str(fp))
         except Exception as e:
-            return f"Error reading PDF: {e}"
+            return ToolResult.error(f"Error reading PDF: {e}")
 
         total_pages = len(doc)
         if pages:
@@ -402,10 +402,10 @@ class ReadFileTool(_FsTool):
                 start, end = _parse_page_range(pages, total_pages)
             except (ValueError, IndexError):
                 doc.close()
-                return f"Error: Invalid page range '{pages}'. Use format like '1-5'."
+                return ToolResult.error(f"Error: Invalid page range '{pages}'. Use format like '1-5'.")
             if start > end or start >= total_pages:
                 doc.close()
-                return f"Error: Page range '{pages}' is out of bounds (document has {total_pages} pages)."
+                return ToolResult.error(f"Error: Page range '{pages}' is out of bounds (document has {total_pages} pages).")
         else:
             start = 0
             end = min(total_pages - 1, self._MAX_PDF_PAGES - 1)
@@ -437,10 +437,10 @@ class ReadFileTool(_FsTool):
         result = extract_text(fp)
 
         if result is None:
-            return f"Error: Unsupported file format: {fp.suffix}"
+            return ToolResult.error(f"Error: Unsupported file format: {fp.suffix}")
 
         if result.startswith("[error:"):
-            return f"Error reading {fp.suffix.upper()} file: {result}"
+            return ToolResult.error(f"Error reading {fp.suffix.upper()} file: {result}")
 
         if not result:
             return f"({fp.suffix.upper().lstrip('.')} has no extractable text: {fp})"
@@ -492,9 +492,9 @@ class WriteFileTool(_FsTool):
             self._file_states.record_write(fp)
             return f"Successfully wrote {len(content)} characters to {fp}"
         except PermissionError as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
         except Exception as e:
-            return f"Error writing file: {e}"
+            return ToolResult.error(f"Error writing file: {e}")
 
 
 # ---------------------------------------------------------------------------
@@ -830,11 +830,11 @@ class EditFileTool(_FsTool):
             if new_text is None:
                 raise ValueError("Unknown new_text")
             if occurrence is not None and occurrence < 1:
-                return "Error: occurrence must be >= 1."
+                return ToolResult.error("Error: occurrence must be >= 1.")
             if line_hint is not None and line_hint < 1:
-                return "Error: line_hint must be >= 1."
+                return ToolResult.error("Error: line_hint must be >= 1.")
             if expected_replacements is not None and expected_replacements < 1:
-                return "Error: expected_replacements must be >= 1."
+                return ToolResult.error("Error: expected_replacements must be >= 1.")
 
             fp = self._resolve_write(path)
 
@@ -853,14 +853,14 @@ class EditFileTool(_FsTool):
             except OSError:
                 fsize = 0
             if fsize > self._MAX_EDIT_FILE_SIZE:
-                return f"Error: File too large to edit ({fsize / (1024**3):.1f} GiB). Maximum is 1 GiB."
+                return ToolResult.error(f"Error: File too large to edit ({fsize / (1024**3):.1f} GiB). Maximum is 1 GiB.")
 
             # Create-file: old_text='' but file exists and not empty → reject
             if old_text == "":
                 raw = fp.read_bytes()
                 content = raw.decode("utf-8")
                 if content.strip():
-                    return f"Error: Cannot create file — {path} already exists and is not empty."
+                    return ToolResult.error(f"Error: Cannot create file — {path} already exists and is not empty.")
                 fp.write_text(new_text, encoding="utf-8")
                 self._file_states.record_write(fp)
                 return f"Successfully edited {fp}"
@@ -878,15 +878,15 @@ class EditFileTool(_FsTool):
                 return self._not_found_msg(old_text, content, path)
             count = len(matches)
             if replace_all and occurrence is not None:
-                return "Error: occurrence cannot be used with replace_all=true."
+                return ToolResult.error("Error: occurrence cannot be used with replace_all=true.")
             if replace_all and line_hint is not None:
-                return "Error: line_hint cannot be used with replace_all=true."
+                return ToolResult.error("Error: line_hint cannot be used with replace_all=true.")
             if occurrence is not None and line_hint is not None:
-                return "Error: line_hint cannot be used with occurrence."
+                return ToolResult.error("Error: line_hint cannot be used with occurrence.")
             if count > 1 and not replace_all:
                 if occurrence is not None:
                     if occurrence > count:
-                        return (
+                        return ToolResult.error(
                             f"Error: occurrence {occurrence} is out of range; "
                             f"old_text appears {count} times."
                         )
@@ -894,7 +894,7 @@ class EditFileTool(_FsTool):
                     nearest = min(matches, key=lambda match: abs(match.line - line_hint))
                     distance = abs(nearest.line - line_hint)
                     if sum(1 for match in matches if abs(match.line - line_hint) == distance) > 1:
-                        return (
+                        return ToolResult.error(
                             f"Error: line_hint {line_hint} is ambiguous; "
                             f"old_text appears {count} times."
                         )
@@ -910,7 +910,7 @@ class EditFileTool(_FsTool):
                         "or set replace_all=true."
                     )
             elif occurrence is not None and occurrence > count:
-                return (
+                return ToolResult.error(
                     f"Error: occurrence {occurrence} is out of range; "
                     f"old_text appears {count} time."
                 )
@@ -928,7 +928,7 @@ class EditFileTool(_FsTool):
             else:
                 selected = [matches[occurrence - 1 if occurrence else 0]]
             if expected_replacements is not None and len(selected) != expected_replacements:
-                return (
+                return ToolResult.error(
                     f"Error: expected {expected_replacements} replacements but "
                     f"would make {len(selected)}."
                 )
@@ -954,9 +954,9 @@ class EditFileTool(_FsTool):
                 msg = f"{warning}\n{msg}"
             return msg
         except PermissionError as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
         except Exception as e:
-            return f"Error editing file: {e}"
+            return ToolResult.error(f"Error editing file: {e}")
 
     def _file_not_found_msg(self, path: str, fp: Path) -> str:
         """Build an error message with 'Did you mean ...?' suggestions."""
@@ -969,7 +969,7 @@ class EditFileTool(_FsTool):
         parts = [f"Error: File not found: {path}"]
         if suggestions:
             parts.append("Did you mean: " + ", ".join(suggestions) + "?")
-        return "\n".join(parts)
+        return ToolResult.error("\n".join(parts))
 
     @staticmethod
     def _not_found_msg(old_text: str, content: str, path: str) -> str:
@@ -985,18 +985,18 @@ class EditFileTool(_FsTool):
             hint_text = ""
             if hints:
                 hint_text = "\nPossible cause: " + ", ".join(hints) + "."
-            return (
+            return ToolResult.error(
                 f"Error: old_text not found in {path}."
                 f"{hint_text}\nBest match ({best_ratio:.0%} similar) at line {best_start + 1}:\n{diff}"
             )
 
         if hints:
-            return (
+            return ToolResult.error(
                 f"Error: old_text not found in {path}. "
                 f"Possible cause: {', '.join(hints)}. "
                 "Copy the exact text from read_file and try again."
             )
-        return f"Error: old_text not found in {path}. No similar text found. Verify the file content."
+        return ToolResult.error(f"Error: old_text not found in {path}. No similar text found. Verify the file content.")
 
 
 # ---------------------------------------------------------------------------
@@ -1051,9 +1051,9 @@ class ListDirTool(_FsTool):
                 raise ValueError("Unknown path")
             dp = self._resolve(path)
             if not dp.exists():
-                return f"Error: Directory not found: {path}"
+                return ToolResult.error(f"Error: Directory not found: {path}")
             if not dp.is_dir():
-                return f"Error: Not a directory: {path}"
+                return ToolResult.error(f"Error: Not a directory: {path}")
 
             cap = max_entries or self._DEFAULT_MAX
             items: list[str] = []
@@ -1084,6 +1084,6 @@ class ListDirTool(_FsTool):
                 result += f"\n\n(truncated, showing first {cap} of {total} entries)"
             return result
         except PermissionError as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
         except Exception as e:
-            return f"Error listing directory: {e}"
+            return ToolResult.error(f"Error listing directory: {e}")

nanobot/agent/tools/image_generation.py

@@ -7,7 +7,7 @@ from typing import TYPE_CHECKING, Any
 
 from pydantic import Field
 
-from nanobot.agent.tools.base import Tool, tool_parameters
+from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.schema import (
     ArraySchema,
     IntegerSchema,
@@ -172,11 +172,11 @@ class ImageGenerationTool(Tool):
     ) -> str:
         client = self._provider_client()
         if client is None:
-            return f"Error: unsupported image generation provider '{self.config.provider}'"
+            return ToolResult.error(f"Error: unsupported image generation provider '{self.config.provider}'")
 
         requested = count or 1
         if requested > self.config.max_images_per_turn:
-            return (
+            return ToolResult.error(
                 "Error: count exceeds tools.imageGeneration.maxImagesPerTurn "
                 f"({self.config.max_images_per_turn})"
             )
@@ -206,4 +206,4 @@ class ImageGenerationTool(Tool):
                         break
             return generated_image_tool_result(artifacts)
         except (ArtifactError, ImageGenerationError, OSError) as exc:
-            return f"Error: {exc}"
+            return ToolResult.error(f"Error: {exc}")

nanobot/agent/tools/loader.py

@@ -8,7 +8,7 @@ from typing import Any
 
 from loguru import logger
 
-from nanobot.agent.tools.base import Tool
+from nanobot.agent.tools.base import Tool, ToolResult
 from nanobot.agent.tools.registry import ToolRegistry
 
 _SKIP_MODULES = frozenset({
@@ -96,6 +96,8 @@ class ToolLoader:
                     if not tool_cls.enabled(ctx):
                         continue
                     tool = tool_cls.create(ctx)
+                    if is_plugin_source:
+                        tool = _LegacyErrorPrefixTool(tool)
                     if registry.has(tool.name):
                         if is_plugin_source and tool.name in builtin_names:
                             logger.warning(
@@ -114,3 +116,67 @@ class ToolLoader:
                 except Exception:
                     logger.exception("Failed to register tool: %s", cls_label)
         return registered
+
+
+class _LegacyErrorPrefixTool(Tool):
+    """Compatibility wrapper for external tools using the old error-string contract."""
+
+    _plugin_discoverable = False
+
+    def __init__(self, wrapped: Tool) -> None:
+        self._wrapped = wrapped
+
+    @property
+    def name(self) -> str:
+        return self._wrapped.name
+
+    @property
+    def description(self) -> str:
+        return self._wrapped.description
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return self._wrapped.parameters
+
+    @property
+    def read_only(self) -> bool:
+        return self._wrapped.read_only
+
+    @property
+    def exclusive(self) -> bool:
+        return self._wrapped.exclusive
+
+    @property
+    def concurrency_safe(self) -> bool:
+        return self._wrapped.concurrency_safe
+
+    @property
+    def config_key(self) -> str:
+        return getattr(self._wrapped, "config_key", "")
+
+    def set_context(self, ctx: Any) -> None:
+        set_context = getattr(self._wrapped, "set_context", None)
+        if callable(set_context):
+            set_context(ctx)
+
+    def cast_params(self, params: dict[str, Any]) -> dict[str, Any]:
+        return self._wrapped.cast_params(params)
+
+    def validate_params(self, params: dict[str, Any]) -> list[str]:
+        return self._wrapped.validate_params(params)
+
+    def to_schema(self) -> dict[str, Any]:
+        return self._wrapped.to_schema()
+
+    async def execute(self, **kwargs: Any) -> Any:
+        result = await self._wrapped.execute(**kwargs)
+        if (
+            isinstance(result, str)
+            and not isinstance(result, ToolResult)
+            and result.startswith("Error:")
+        ):
+            return ToolResult.error(result)
+        return result
+
+    def __getattr__(self, name: str) -> Any:
+        return getattr(self._wrapped, name)

nanobot/agent/tools/long_task.py

@@ -20,7 +20,7 @@ from contextvars import ContextVar
 from datetime import datetime
 from typing import TYPE_CHECKING, Any
 
-from nanobot.agent.tools.base import Tool, tool_parameters
+from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.context import ContextAware, RequestContext
 from nanobot.agent.tools.schema import StringSchema, tool_parameters_schema
 from nanobot.bus.runtime_events import GoalStateChanged, RuntimeEventBus, RuntimeEventContext
@@ -150,12 +150,12 @@ class LongTaskTool(Tool, _GoalToolsMixin):
     async def execute(self, goal: str, ui_summary: str | None = None, **kwargs: Any) -> str:
         sess = self._session()
         if sess is None:
-            return (
+            return ToolResult.error(
                 "Error: long_task requires an active chat session (missing routing context)."
             )
         prior = parse_goal_state(goal_state_raw(sess.metadata))
         if isinstance(prior, dict) and prior.get("status") == "active":
-            return (
+            return ToolResult.error(
                 "Error: a sustained goal is already active. "
                 "Use complete_goal when finished, or ask the user before replacing it."
             )
@@ -230,7 +230,7 @@ class CompleteGoalTool(Tool, _GoalToolsMixin):
     async def execute(self, recap: str | None = None, **kwargs: Any) -> str:
         sess = self._session()
         if sess is None:
-            return "Error: complete_goal requires an active chat session."
+            return ToolResult.error("Error: complete_goal requires an active chat session.")
         prior = parse_goal_state(goal_state_raw(sess.metadata))
         if not isinstance(prior, dict) or prior.get("status") != "active":
             return "No active goal to complete."

nanobot/agent/tools/mcp.py

@@ -1,6 +1,7 @@
 """MCP client: connects to MCP servers and wraps their tools as native nanobot tools."""
 
 import asyncio
+import json
 import os
 import re
 import shutil
@@ -13,7 +14,7 @@ from weakref import WeakKeyDictionary
 import httpx
 from loguru import logger
 
-from nanobot.agent.tools.base import Tool
+from nanobot.agent.tools.base import Tool, ToolResult
 from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.bus.events import (
     INBOUND_META_RUNTIME_CONTROL,
@@ -165,12 +166,31 @@ async def _probe_http_url(url: str, timeout: float = 3.0) -> bool:
         return False
 
 
+def _redact_url(url: str) -> str:
+    """Strip credentials and query/fragment before logging an MCP URL.
+
+    Server URLs may embed secrets (``https://user:token@host/sse`` or a
+    ``?token=`` query). Some deployments also put opaque tokens in the path, so
+    log only the origin and a path placeholder.
+    """
+    try:
+        parts = urllib.parse.urlsplit(url)
+        hostname = parts.hostname or ""
+        netloc = f"[{hostname}]" if ":" in hostname else hostname
+        if parts.port:
+            netloc = f"{netloc}:{parts.port}"
+        path = "/..." if parts.path and parts.path != "/" else parts.path
+        return urllib.parse.urlunsplit((parts.scheme, netloc, path, "", ""))
+    except Exception:
+        return "<redacted-url>"
+
+
 async def _validate_mcp_request_url(request: httpx.Request) -> None:
     """Validate each outgoing MCP HTTP request, including redirect targets."""
     ok, error = validate_url_target(str(request.url))
     if not ok:
         raise httpx.RequestError(
-            f"Blocked unsafe MCP URL {request.url} ({error})",
+            f"Blocked unsafe MCP URL {_redact_url(str(request.url))} ({error})",
             request=request,
         )
 
@@ -313,6 +333,52 @@ class _MCPWrapperBase(Tool):
         return True
 
 
+def _image_block_data_url(block: Any, types: Any) -> str | None:
+    """Return a base64 ``data:`` URL for an MCP image-bearing content block.
+
+    Handles ``ImageContent`` directly and ``EmbeddedResource`` wrapping a binary
+    blob with an ``image/*`` MIME type. Returns ``None`` for anything else.
+    ``getattr`` guards keep this safe when the installed/faked ``mcp`` SDK does
+    not expose a given type.
+    """
+    image_cls = getattr(types, "ImageContent", None)
+    if image_cls is not None and isinstance(block, image_cls):
+        mime = getattr(block, "mimeType", None) or "image/png"
+        return f"data:{mime};base64,{block.data}"
+
+    embedded_cls = getattr(types, "EmbeddedResource", None)
+    blob_cls = getattr(types, "BlobResourceContents", None)
+    if embedded_cls is not None and isinstance(block, embedded_cls):
+        resource = getattr(block, "resource", None)
+        if blob_cls is not None and isinstance(resource, blob_cls):
+            mime = getattr(resource, "mimeType", None) or ""
+            if isinstance(mime, str) and mime.startswith("image/"):
+                return f"data:{mime};base64,{resource.blob}"
+    return None
+
+
+def _mcp_image_tool_result(text_parts: list[str], artifacts: list[dict[str, Any]]) -> str:
+    """Build the compact tool result for an MCP call that returned image(s).
+
+    The base64 stays out of the model context entirely — only artifact paths and
+    metadata are returned, so the result is small and the channel can deliver the
+    saved file via the message tool.
+    """
+    payload: dict[str, Any] = {
+        "artifacts": artifacts,
+        "next_step": (
+            "These images were returned by an MCP tool and saved as local artifacts. "
+            "Call the message tool with the artifact 'path' values in the media "
+            "parameter to deliver the images to the user. Do not paste base64 or raw "
+            "paths into your reply unless the user asks for debug details."
+        ),
+    }
+    text = "\n".join(part for part in text_parts if part)
+    if text:
+        payload["text"] = text
+    return json.dumps(payload, ensure_ascii=False)
+
+
 class MCPToolWrapper(_MCPWrapperBase):
     """Wraps a single MCP server tool as a nanobot Tool."""
 
@@ -340,8 +406,6 @@ class MCPToolWrapper(_MCPWrapperBase):
         return self._parameters
 
     async def execute(self, **kwargs: Any) -> str:
-        from mcp import types
-
         retried_transient = False
         refreshed_session = False
         while True:
@@ -396,17 +460,66 @@ class MCPToolWrapper(_MCPWrapperBase):
                 )
                 return f"(MCP tool call failed: {type(exc).__name__})"
             else:
-                # Success — extract result
+                # Success — extract text and persist any image content as artifacts.
-                parts = []
+                rendered = self._render_call_result(result.content, kwargs)
-                for block in result.content:
+                if getattr(result, "isError", False):
-                    if isinstance(block, types.TextContent):
+                    return ToolResult.error(rendered)
-                        parts.append(block.text)
+                return rendered
-                    else:
-                        parts.append(str(block))
-                return "\n".join(parts) or "(no output)"
 
         return "(MCP tool call failed)"  # Unreachable, but satisfies type checkers
 
+    def _render_call_result(self, content: Any, arguments: Mapping[str, Any]) -> str:
+        """Turn MCP content blocks into a tool result string.
+
+        Text is concatenated as before. Image blocks are decoded and saved as
+        local artifacts (mirroring the built-in image generation tool) so the
+        model can deliver them via the message tool instead of trying to forward
+        base64 — which would be truncated and bloat the context window.
+        """
+        from mcp import types
+
+        text_parts: list[str] = []
+        artifacts: list[dict[str, Any]] = []
+        for block in content:
+            if isinstance(block, types.TextContent):
+                text_parts.append(block.text)
+                continue
+            data_url = _image_block_data_url(block, types)
+            if data_url is not None:
+                stored = self._store_image_block(data_url, arguments)
+                if stored is not None:
+                    artifacts.append(stored)
+                else:
+                    text_parts.append("(MCP tool returned an image that could not be stored)")
+                continue
+            text_parts.append(str(block))
+
+        if artifacts:
+            return _mcp_image_tool_result(text_parts, artifacts)
+        return "\n".join(text_parts) or "(no output)"
+
+    def _store_image_block(
+        self, data_url: str, arguments: Mapping[str, Any]
+    ) -> dict[str, Any] | None:
+        """Persist one image data URL as an artifact; return its metadata or None."""
+        from nanobot.utils.artifacts import ArtifactError, store_generated_image_artifact
+
+        try:
+            return store_generated_image_artifact(
+                data_url,
+                prompt=str(arguments.get("prompt") or ""),
+                model=str(arguments.get("model") or ""),
+                save_dir="generated",
+                provider=f"mcp:{self._server_name}",
+            )
+        except (ArtifactError, OSError) as exc:
+            logger.warning(
+                "MCP tool '{}' returned an image that could not be stored: {}",
+                self._name,
+                exc,
+            )
+            return None
+
 
 class MCPResourceWrapper(_MCPWrapperBase):
     """Wraps an MCP resource URI as a read-only nanobot Tool."""
@@ -683,7 +796,7 @@ async def connect_mcp_servers(
                     logger.warning(
                         "MCP server '{}': blocked unsafe URL {} ({})",
                         name,
-                        cfg.url,
+                        _redact_url(cfg.url),
                         error,
                     )
                     await server_stack.aclose()
@@ -704,7 +817,7 @@ async def connect_mcp_servers(
                 read, write = await server_stack.enter_async_context(stdio_client(params))
             elif transport_type == "sse":
                 if not await _probe_http_url(cfg.url):
-                    logger.warning("MCP server '{}': {} unreachable, skipping", name, cfg.url)
+                    logger.warning("MCP server '{}': {} unreachable, skipping", name, _redact_url(cfg.url))
                     await server_stack.aclose()
                     return name, None
 
@@ -731,7 +844,7 @@ async def connect_mcp_servers(
                 )
             elif transport_type == "streamableHttp":
                 if not await _probe_http_url(cfg.url):
-                    logger.warning("MCP server '{}': {} unreachable, skipping", name, cfg.url)
+                    logger.warning("MCP server '{}': {} unreachable, skipping", name, _redact_url(cfg.url))
                     await server_stack.aclose()
                     return name, None
 

nanobot/agent/tools/message.py

@@ -6,7 +6,7 @@ from typing import Any, Awaitable, Callable
 
 from loguru import logger
 
-from nanobot.agent.tools.base import Tool, tool_parameters
+from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.context import ContextAware, RequestContext
 from nanobot.agent.tools.path_utils import resolve_workspace_path
 from nanobot.agent.tools.schema import ArraySchema, StringSchema, tool_parameters_schema
@@ -198,7 +198,7 @@ class MessageTool(Tool, ContextAware):
                 not isinstance(row, list) or any(not isinstance(label, str) for label in row)
                 for row in buttons
             ):
-                return "Error: buttons must be a list of list of strings"
+                return ToolResult.error("Error: buttons must be a list of list of strings")
         default_channel = self._default_channel.get()
         default_chat_id = self._default_chat_id.get()
         channel = channel or default_channel
@@ -210,7 +210,7 @@ class MessageTool(Tool, ContextAware):
             and str(explicit_chat_id).strip() != ""
             and str(explicit_chat_id).strip() != str(default_chat_id).strip()
         ):
-            return (
+            return ToolResult.error(
                 "Error: chat_id does not match the active WebSocket conversation. "
                 "Omit chat_id (and usually channel) so delivery uses the current "
                 "conversation id from context — WebSocket client_id strings "
@@ -229,16 +229,16 @@ class MessageTool(Tool, ContextAware):
             message_id = None
 
         if not channel or not chat_id:
-            return "Error: No target channel/chat specified"
+            return ToolResult.error("Error: No target channel/chat specified")
 
         if not self._send_callback:
-            return "Error: Message sending not configured"
+            return ToolResult.error("Error: Message sending not configured")
 
         if media:
             try:
                 media = self._resolve_media(media)
             except (OSError, PermissionError, ValueError) as e:
-                return f"Error: media path is not allowed: {str(e)}"
+                return ToolResult.error(f"Error: media path is not allowed: {str(e)}")
 
         metadata = dict(self._default_metadata.get()) if same_target else {}
         if message_id:
@@ -270,4 +270,4 @@ class MessageTool(Tool, ContextAware):
             button_info = f" with {sum(len(row) for row in buttons)} button(s)" if buttons else ""
             return f"Message sent to {channel}:{chat_id}{media_info}{button_info}"
         except Exception as e:
-            return f"Error sending message: {str(e)}"
+            return ToolResult.error(f"Error sending message: {str(e)}")

nanobot/agent/tools/registry.py

@@ -3,7 +3,11 @@
 import json
 from typing import Any
 
-from nanobot.agent.tools.base import Tool
+from nanobot.agent.tools.base import Tool, ToolResult
+
+
+def is_tool_error_result(name: str, result: Any) -> bool:
+    return isinstance(result, ToolResult) and result.is_error
 
 
 class ToolRegistry:
@@ -100,22 +104,26 @@ class ToolRegistry:
             suggestion = self._suggest_name(str(name))
             hint = f" Did you mean '{suggestion}'? Tool names must match exactly." if suggestion else ""
             return None, params, (
+                ToolResult.error(
                     f"Error: Tool '{name}' not found.{hint} Available: {', '.join(self.tool_names)}"
                 )
+            )
 
         params = self._coerce_params(tool, params)
         if not isinstance(params, dict):
             return tool, params, (
+                ToolResult.error(
                     f"Error: Tool '{name}' parameters must be a JSON object, got "
                     f"{type(params).__name__}. Use named parameters like "
                     'tool_name(param1="value1", param2="value2") matching the tool schema.'
                 )
+            )
 
         cast_params = tool.cast_params(params)
         errors = tool.validate_params(cast_params)
         if errors:
             return tool, cast_params, (
-                f"Error: Invalid parameters for tool '{name}': " + "; ".join(errors)
+                ToolResult.error(f"Error: Invalid parameters for tool '{name}': " + "; ".join(errors))
             )
         return tool, cast_params, None
 
@@ -159,16 +167,16 @@ class ToolRegistry:
         hint = "\n\n[Analyze the error above and try a different approach.]"
         tool, params, error = self.prepare_call(name, params)
         if error:
-            return error + hint
+            return ToolResult.error(str(error) + hint)
 
         try:
             assert tool is not None  # guarded by prepare_call()
             result = await tool.execute(**params)
-            if isinstance(result, str) and result.startswith("Error"):
+            if is_tool_error_result(name, result):
-                return result + hint
+                return ToolResult.error(str(result) + hint)
             return result
         except Exception as e:
-            return f"Error executing {name}: {str(e)}" + hint
+            return ToolResult.error(f"Error executing {name}: {str(e)}" + hint)
 
     @property
     def tool_names(self) -> list[str]:

nanobot/agent/tools/search.py

@@ -9,6 +9,7 @@ from contextlib import suppress
 from pathlib import Path, PurePosixPath
 from typing import Any, Iterable, TypeVar
 
+from nanobot.agent.tools.base import ToolResult
 from nanobot.agent.tools.filesystem import ListDirTool, _FsTool
 
 _DEFAULT_HEAD_LIMIT = 250
@@ -218,12 +219,12 @@ class FindFilesTool(_SearchTool):
         try:
             target = self._resolve(path or ".")
             if not target.exists():
-                return f"Error: Path not found: {path}"
+                return ToolResult.error(f"Error: Path not found: {path}")
             if not (target.is_dir() or target.is_file()):
-                return f"Error: Unsupported path: {path}"
+                return ToolResult.error(f"Error: Unsupported path: {path}")
 
             if sort not in {"path", "modified"}:
-                return "Error: sort must be 'path' or 'modified'"
+                return ToolResult.error("Error: sort must be 'path' or 'modified'")
 
             limit = (
                 _DEFAULT_FILE_HEAD_LIMIT
@@ -271,9 +272,9 @@ class FindFilesTool(_SearchTool):
                 result += "\n\n" + note
             return result
         except PermissionError as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
         except Exception as e:
-            return f"Error finding files: {e}"
+            return ToolResult.error(f"Error finding files: {e}")
 
 
 class GrepTool(_SearchTool):
@@ -425,16 +426,16 @@ class GrepTool(_SearchTool):
         try:
             target = self._resolve(path or ".")
             if not target.exists():
-                return f"Error: Path not found: {path}"
+                return ToolResult.error(f"Error: Path not found: {path}")
             if not (target.is_dir() or target.is_file()):
-                return f"Error: Unsupported path: {path}"
+                return ToolResult.error(f"Error: Unsupported path: {path}")
 
             flags = re.IGNORECASE if case_insensitive else 0
             try:
                 needle = re.escape(pattern) if fixed_strings else pattern
                 regex = re.compile(needle, flags)
             except re.error as e:
-                return f"Error: invalid regex pattern: {e}"
+                return ToolResult.error(f"Error: invalid regex pattern: {e}")
 
             if head_limit is not None:
                 limit = None if head_limit == 0 else head_limit
@@ -579,6 +580,6 @@ class GrepTool(_SearchTool):
                 result += "\n\n" + "\n".join(notes)
             return result
         except PermissionError as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
         except Exception as e:
-            return f"Error searching files: {e}"
+            return ToolResult.error(f"Error searching files: {e}")

nanobot/agent/tools/self.py

@@ -7,7 +7,7 @@ from typing import TYPE_CHECKING, Any
 
 from loguru import logger
 
-from nanobot.agent.tools.base import Tool
+from nanobot.agent.tools.base import Tool, ToolResult
 from nanobot.agent.tools.context import ContextAware, RequestContext
 from nanobot.agent.tools.runtime_state import RuntimeState
 from nanobot.config_base import Base
@@ -216,7 +216,7 @@ class MyTool(Tool, ContextAware):
     @staticmethod
     def _validate_key(key: str | None, label: str = "key") -> str | None:
         if not key or not key.strip():
-            return f"Error: '{label}' cannot be empty or whitespace"
+            return ToolResult.error(f"Error: '{label}' cannot be empty or whitespace")
         return None
 
     # ------------------------------------------------------------------
@@ -321,7 +321,7 @@ class MyTool(Tool, ContextAware):
         if action in ("inspect", "check"):
             return self._inspect(key)
         if not self._modify_allowed:
-            return "Error: set is disabled (tools.my.allow_set is false)"
+            return ToolResult.error("Error: set is disabled (tools.my.allow_set is false)")
         if action in ("modify", "set"):
             return self._modify(key, value)
         return f"Unknown action: {action}"
@@ -333,7 +333,7 @@ class MyTool(Tool, ContextAware):
             return self._inspect_all()
         top = key.split(".")[0]
         if top in self._DENIED_ATTRS or top.startswith("__"):
-            return f"Error: '{top}' is not accessible"
+            return ToolResult.error(f"Error: '{top}' is not accessible")
         obj, err = self._resolve_path(key)
         if err:
             # "scratchpad" alias for _runtime_vars
@@ -343,12 +343,12 @@ class MyTool(Tool, ContextAware):
             # Fallback: check _runtime_vars for simple keys stored by modify
             if "." not in key and key in self._runtime_state._runtime_vars:
                 return self._format_value(self._runtime_state._runtime_vars[key], key)
-            return f"Error: {err}"
+            return ToolResult.error(f"Error: {err}")
         # Guard against mock auto-generated attributes
         if "." not in key and not _has_real_attr(self._runtime_state, key):
             if key in self._runtime_state._runtime_vars:
                 return self._format_value(self._runtime_state._runtime_vars[key], key)
-            return f"Error: '{key}' not found"
+            return ToolResult.error(f"Error: '{key}' not found")
         return self._format_value(obj, key)
 
     def _inspect_all(self) -> str:
@@ -379,21 +379,21 @@ class MyTool(Tool, ContextAware):
         top = key.split(".")[0]
         if top in self.BLOCKED or top in self._DENIED_ATTRS or top.startswith("__") or top.lower() in self._SENSITIVE_NAMES:
             self._audit("modify", f"BLOCKED {key}")
-            return f"Error: '{key}' is protected and cannot be modified"
+            return ToolResult.error(f"Error: '{key}' is protected and cannot be modified")
         if top in self.READ_ONLY:
             self._audit("modify", f"READ_ONLY {key}")
-            return f"Error: '{key}' is read-only and cannot be modified"
+            return ToolResult.error(f"Error: '{key}' is read-only and cannot be modified")
         if "." in key:
             parent_path, leaf = key.rsplit(".", 1)
             if leaf in self._DENIED_ATTRS or leaf.startswith("__"):
                 self._audit("modify", f"BLOCKED leaf '{leaf}'")
-                return f"Error: '{leaf}' is not accessible"
+                return ToolResult.error(f"Error: '{leaf}' is not accessible")
             if leaf.lower() in self._SENSITIVE_NAMES:
                 self._audit("modify", f"BLOCKED sensitive leaf '{leaf}'")
-                return f"Error: '{leaf}' is not accessible"
+                return ToolResult.error(f"Error: '{leaf}' is not accessible")
             parent, err = self._resolve_path(parent_path)
             if err:
-                return f"Error: {err}"
+                return ToolResult.error(f"Error: {err}")
             if isinstance(parent, dict):
                 parent[leaf] = value
             else:
@@ -408,11 +408,11 @@ class MyTool(Tool, ContextAware):
 
     def _modify_model_preset(self, value: Any) -> str:
         if not isinstance(value, str) or not value.strip():
-            return "Error: 'model_preset' must be a non-empty string"
+            return ToolResult.error("Error: 'model_preset' must be a non-empty string")
         name = value.strip()
         result = self._modify_free("model_preset", name)
-        if result.startswith("Error:"):
+        if isinstance(result, ToolResult) and result.is_error:
-            return result if result.endswith((".", "!", "?")) else f"{result}."
+            return result if result.endswith((".", "!", "?")) else ToolResult.error(f"{result}.")
         return (
             f"{result}; model is now {self._runtime_state.model!r}; "
             f"context_window_tokens is now {self._runtime_state.context_window_tokens!r}"
@@ -422,22 +422,25 @@ class MyTool(Tool, ContextAware):
         spec = self.RESTRICTED[key]
         expected = spec["type"]
         if expected is int and isinstance(value, bool):
-            return f"Error: '{key}' must be {expected.__name__}, got bool"
+            return ToolResult.error(f"Error: '{key}' must be {expected.__name__}, got bool")
         if not isinstance(value, expected):
             try:
                 value = expected(value)
             except (ValueError, TypeError):
-                return f"Error: '{key}' must be {expected.__name__}, got {type(value).__name__}"
+                return ToolResult.error(f"Error: '{key}' must be {expected.__name__}, got {type(value).__name__}")
         old = getattr(self._runtime_state, key)
         if "min" in spec and value < spec["min"]:
-            return f"Error: '{key}' must be >= {spec['min']}"
+            return ToolResult.error(f"Error: '{key}' must be >= {spec['min']}")
         if "max" in spec and value > spec["max"]:
-            return f"Error: '{key}' must be <= {spec['max']}"
+            return ToolResult.error(f"Error: '{key}' must be <= {spec['max']}")
         if "min_len" in spec and len(str(value)) < spec["min_len"]:
-            return f"Error: '{key}' must be at least {spec['min_len']} characters"
+            return ToolResult.error(f"Error: '{key}' must be at least {spec['min_len']} characters")
         setattr(self._runtime_state, key, value)
         if key == "model":
             self._runtime_state._active_preset = None
+        sync_replay = getattr(self._runtime_state, "_sync_replay_max_messages", None)
+        if key == "context_window_tokens" and callable(sync_replay):
+            sync_replay()
         if key == "max_iterations" and hasattr(self._runtime_state, "_sync_subagent_runtime_limits"):
             self._runtime_state._sync_subagent_runtime_limits()
         self._audit("modify", f"{key}: {old!r} -> {value!r}")
@@ -455,25 +458,25 @@ class MyTool(Tool, ContextAware):
                         "modify",
                         f"REJECTED type mismatch {key}: expects {old_t.__name__}, got {new_t.__name__}",
                     )
-                    return f"Error: '{key}' expects {old_t.__name__}, got {new_t.__name__}"
+                    return ToolResult.error(f"Error: '{key}' expects {old_t.__name__}, got {new_t.__name__}")
             try:
                 setattr(self._runtime_state, key, value)
             except (ValueError, KeyError) as e:
                 message = str(e.args[0] if isinstance(e, KeyError) and e.args else e).strip('"')
                 self._audit("modify", f"REJECTED {key}: {message}")
-                return f"Error: {message}"
+                return ToolResult.error(f"Error: {message}")
             self._audit("modify", f"{key}: {old!r} -> {value!r}")
             return f"Set {key} = {value!r} (was {old!r})"
         if callable(value):
             self._audit("modify", f"REJECTED callable {key}")
-            return "Error: cannot store callable values"
+            return ToolResult.error("Error: cannot store callable values")
         err = self._validate_json_safe(value)
         if err:
             self._audit("modify", f"REJECTED {key}: {err}")
-            return f"Error: {err}"
+            return ToolResult.error(f"Error: {err}")
         if key not in self._runtime_state._runtime_vars and len(self._runtime_state._runtime_vars) >= self._MAX_RUNTIME_KEYS:
             self._audit("modify", f"REJECTED {key}: max keys ({self._MAX_RUNTIME_KEYS}) reached")
-            return f"Error: scratchpad is full (max {self._MAX_RUNTIME_KEYS} keys). Remove unused keys first."
+            return ToolResult.error(f"Error: scratchpad is full (max {self._MAX_RUNTIME_KEYS} keys). Remove unused keys first.")
         old = self._runtime_state._runtime_vars.get(key)
         self._runtime_state._runtime_vars[key] = value
         self._audit("modify", f"scratchpad.{key}: {old!r} -> {value!r}")

nanobot/agent/tools/shell.py

@@ -8,6 +8,7 @@ import re
 import shutil
 import sys
 from contextlib import suppress
+from copy import deepcopy
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Any
@@ -15,7 +16,7 @@ from typing import Any
 from loguru import logger
 from pydantic import Field
 
-from nanobot.agent.tools.base import Tool, tool_parameters
+from nanobot.agent.tools.base import Schema, Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.context import current_request_session_key
 from nanobot.agent.tools.exec_session import (
     DEFAULT_EXEC_SESSION_MANAGER,
@@ -73,12 +74,9 @@ class _PreparedCommand:
     login: bool
 
 
-@tool_parameters(
+_EXEC_TOOL_PARAMETERS = tool_parameters_schema(
-    tool_parameters_schema(
     command=StringSchema("The shell command to execute"),
-        cmd=StringSchema("Compatibility alias for command"),
     working_dir=StringSchema("Optional working directory for the command"),
-        workdir=StringSchema("Compatibility alias for working_dir"),
     timeout=IntegerSchema(
         60,
         description=(
@@ -117,7 +115,14 @@ class _PreparedCommand:
         maximum=MAX_OUTPUT_CHARS,
         nullable=True,
     ),
-        max_output_tokens=IntegerSchema(
+)
+
+_EXEC_TOOL_COMPAT_PARAMETERS = deepcopy(_EXEC_TOOL_PARAMETERS)
+_EXEC_TOOL_COMPAT_PARAMETERS["properties"].update(
+    {
+        "cmd": StringSchema("Compatibility alias for command").to_json_schema(),
+        "workdir": StringSchema("Compatibility alias for working_dir").to_json_schema(),
+        "max_output_tokens": IntegerSchema(
             description=(
                 "Compatibility alias for max_output_chars. The current runtime "
                 "uses a character budget."
@@ -125,9 +130,12 @@ class _PreparedCommand:
             minimum=1000,
             maximum=MAX_OUTPUT_CHARS,
             nullable=True,
-        ),
+        ).to_json_schema(),
-    )
+    }
 )
+
+
+@tool_parameters(_EXEC_TOOL_PARAMETERS)
 class ExecTool(Tool):
     """Tool to execute shell commands."""
     _scopes = {"core", "subagent"}
@@ -244,6 +252,18 @@ class ExecTool(Tool):
     def exclusive(self) -> bool:
         return True
 
+    def cast_params(self, params: dict[str, Any]) -> dict[str, Any]:
+        return self._cast_object(params, _EXEC_TOOL_COMPAT_PARAMETERS)
+
+    def validate_params(self, params: dict[str, Any]) -> list[str]:
+        if not isinstance(params, dict):
+            return [f"parameters must be an object, got {type(params).__name__}"]
+        return Schema.validate_json_schema_value(
+            params,
+            {**_EXEC_TOOL_COMPAT_PARAMETERS, "type": "object"},
+            "",
+        )
+
     async def execute(
         self, command: str | None = None, cmd: str | None = None,
         working_dir: str | None = None, workdir: str | None = None,
@@ -256,7 +276,7 @@ class ExecTool(Tool):
         command = command or cmd
         working_dir = working_dir or workdir
         if not command:
-            return "Error: Missing command. Provide command or cmd."
+            return ToolResult.error("Error: Missing command. Provide command or cmd.")
         if max_output_chars is None:
             max_output_chars = max_output_tokens
 
@@ -283,7 +303,7 @@ class ExecTool(Tool):
                 )
             except asyncio.TimeoutError:
                 await self._kill_process(process)
-                return f"Error: Command timed out after {prepared.timeout} seconds"
+                return ToolResult.error(f"Error: Command timed out after {prepared.timeout} seconds")
             except asyncio.CancelledError:
                 await self._kill_process(process)
                 raise
@@ -314,7 +334,7 @@ class ExecTool(Tool):
             return result
 
         except Exception as e:
-            return f"Error executing command: {str(e)}"
+            return ToolResult.error(f"Error executing command: {str(e)}")
 
     async def _execute_session(
         self,
@@ -339,9 +359,10 @@ class ExecTool(Tool):
                     MAX_OUTPUT_CHARS,
                 ),
             )
-            return format_session_poll(session_id, poll)
+            result = format_session_poll(session_id, poll)
+            return ToolResult.error(result) if poll.timed_out else result
         except Exception as exc:
-            return f"Error executing command: {exc}"
+            return ToolResult.error(f"Error executing command: {exc}")
 
     def _resolve_timeout(self, timeout: int | None) -> int | None:
         """Resolve the effective hard timeout in seconds (None = no limit).
@@ -383,12 +404,12 @@ class ExecTool(Tool):
                 requested = Path(cwd).expanduser().resolve()
                 resolved_root = Path(workspace_root).expanduser().resolve()
             except Exception:
-                return (
+                return ToolResult.error(
                     "Error: working_dir could not be resolved"
                     + _WORKSPACE_BOUNDARY_NOTE
                 )
             if not is_path_within(requested, resolved_root):
-                return (
+                return ToolResult.error(
                     "Error: working_dir is outside the configured workspace"
                     + _WORKSPACE_BOUNDARY_NOTE
                 )
@@ -504,24 +525,24 @@ class ExecTool(Tool):
         if not shell:
             return None, None
         if _IS_WINDOWS:
-            return None, "Error: shell parameter is not supported on Windows"
+            return None, ToolResult.error("Error: shell parameter is not supported on Windows")
         if "\0" in shell or "\n" in shell or "\r" in shell:
-            return None, "Error: shell contains invalid characters"
+            return None, ToolResult.error("Error: shell contains invalid characters")
         allowed = {"sh", "bash", "zsh"}
         path = Path(shell).expanduser()
         if path.is_absolute():
             if path.name not in allowed:
-                return None, f"Error: unsupported shell {shell!r}. Allowed: bash, sh, zsh"
+                return None, ToolResult.error(f"Error: unsupported shell {shell!r}. Allowed: bash, sh, zsh")
             if not path.is_file() or not os.access(path, os.X_OK):
-                return None, f"Error: shell is not executable: {shell}"
+                return None, ToolResult.error(f"Error: shell is not executable: {shell}")
             return str(path), None
         if "/" in shell or "\\" in shell:
-            return None, "Error: shell must be a shell name or absolute path"
+            return None, ToolResult.error("Error: shell must be a shell name or absolute path")
         if shell not in allowed:
-            return None, f"Error: unsupported shell {shell!r}. Allowed: bash, sh, zsh"
+            return None, ToolResult.error(f"Error: unsupported shell {shell!r}. Allowed: bash, sh, zsh")
         resolved = shutil.which(shell)
         if not resolved:
-            return None, f"Error: shell not found: {shell}"
+            return None, ToolResult.error(f"Error: shell not found: {shell}")
         return resolved, None
 
     @staticmethod
@@ -608,10 +629,10 @@ class ExecTool(Tool):
         if not explicitly_allowed:
             for pattern in self.deny_patterns:
                 if re.search(pattern, lower):
-                    return "Error: Command blocked by deny pattern filter"
+                    return ToolResult.error("Error: Command blocked by deny pattern filter")
 
             if self.allow_patterns:
-                return "Error: Command blocked by allowlist filter (not in allowlist)"
+                return ToolResult.error("Error: Command blocked by allowlist filter (not in allowlist)")
 
         from nanobot.security.network import contains_internal_url
         if contains_internal_url(
@@ -621,12 +642,12 @@ class ExecTool(Tool):
             ),
         ):
             # The runner turns this marker into a non-retryable security hint.
-            return "Error: Command blocked by safety guard (internal/private URL detected)"
+            return ToolResult.error("Error: Command blocked by safety guard (internal/private URL detected)")
 
         should_restrict = self.restrict_to_workspace if restrict_to_workspace is None else restrict_to_workspace
         if should_restrict:
             if "..\\" in cmd or "../" in cmd:
-                return (
+                return ToolResult.error(
                     "Error: Command blocked by safety guard (path traversal detected)"
                     + _WORKSPACE_BOUNDARY_NOTE
                 )
@@ -661,7 +682,7 @@ class ExecTool(Tool):
                 if not allowed and resolved_workspace is not None:
                     allowed = is_path_within(p, resolved_workspace)
                 if p.is_absolute() and not allowed:
-                    return (
+                    return ToolResult.error(
                         "Error: Command blocked by safety guard (path outside working dir)"
                         + _WORKSPACE_BOUNDARY_NOTE
                     )

nanobot/agent/tools/web.py

@@ -14,7 +14,7 @@ import httpx
 from loguru import logger
 from pydantic import Field
 
-from nanobot.agent.tools.base import Tool, tool_parameters
+from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
 from nanobot.agent.tools.schema import (
     BooleanSchema,
     IntegerSchema,
@@ -395,13 +395,13 @@ class WebSearchTool(Tool):
         elif provider == "keenable":
             return await self._search_keenable(query, n)
         else:
-            return f"Error: unknown search provider '{provider}'"
+            return ToolResult.error(f"Error: unknown search provider '{provider}'")
 
     async def _search_olostep(self, query: str, n: int) -> str:
         try:
             from olostep import AsyncOlostep, Olostep_BaseError
         except ImportError:
-            return "Error: olostep package not installed. Run: pip install olostep"
+            return ToolResult.error("Error: olostep package not installed. Run: pip install olostep")
         api_key = self.config.api_key or os.environ.get("OLOSTEP_API_KEY", "")
         if not api_key:
             logger.warning("OLOSTEP_API_KEY not set, falling back to DuckDuckGo")
@@ -445,9 +445,9 @@ class WebSearchTool(Tool):
             items = [{"title": answer_text or "Olostep answer", "url": "", "content": "\n".join(source_lines)}]
             return _format_results(query, items, n)
         except Olostep_BaseError as e:
-            return f"Olostep search error: {type(e).__name__}: {e}"
+            return ToolResult.error(f"Error: Olostep search error: {type(e).__name__}: {e}")
         except Exception as e:
-            return f"Olostep search error: {type(e).__name__}: {e}"
+            return ToolResult.error(f"Error: Olostep search error: {type(e).__name__}: {e}")
 
     async def _search_brave(self, query: str, n: int) -> str:
         api_key = self.config.api_key or os.environ.get("BRAVE_API_KEY", "")
@@ -481,13 +481,13 @@ class WebSearchTool(Tool):
             return _format_results(query, items, n)
         except httpx.HTTPStatusError as e:
             if e.response.status_code == 429:
-                return (
+                return ToolResult.error(
                     "Error: Brave search rate limited after retry. "
                     "Retry later or reduce consecutive web_search calls."
                 )
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
         except Exception as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
 
     async def _search_tavily(self, query: str, n: int) -> str:
         api_key = self.config.api_key or os.environ.get("TAVILY_API_KEY", "")
@@ -505,7 +505,7 @@ class WebSearchTool(Tool):
                 r.raise_for_status()
             return _format_results(query, r.json().get("results", []), n)
         except Exception as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
 
     async def _search_keenable(self, query: str, n: int) -> str:
         api_key = self.config.api_key or os.environ.get("KEENABLE_API_KEY", "")
@@ -540,10 +540,10 @@ class WebSearchTool(Tool):
             return _format_results(query, items, n)
         except httpx.HTTPStatusError as e:
             if e.response.status_code == 429:
-                return "Error: Keenable search rate limited. Try again later or reduce search frequency."
+                return ToolResult.error("Error: Keenable search rate limited. Try again later or reduce search frequency.")
-            return f"Error: Keenable search failed ({e.response.status_code}): {e}"
+            return ToolResult.error(f"Error: Keenable search failed ({e.response.status_code}): {e}")
         except Exception as e:
-            return f"Error: Keenable search failed: {e}"
+            return ToolResult.error(f"Error: Keenable search failed: {e}")
 
     async def _search_searxng(self, query: str, n: int) -> str:
         base_url = (self.config.base_url or os.environ.get("SEARXNG_BASE_URL", "")).strip()
@@ -553,7 +553,7 @@ class WebSearchTool(Tool):
         endpoint = f"{base_url.rstrip('/')}/search"
         is_valid, error_msg = _validate_url(endpoint)
         if not is_valid:
-            return f"Error: invalid SearXNG URL: {error_msg}"
+            return ToolResult.error(f"Error: invalid SearXNG URL: {error_msg}")
         try:
             async with httpx.AsyncClient(proxy=self.proxy) as client:
                 r = await client.get(
@@ -565,7 +565,7 @@ class WebSearchTool(Tool):
                 r.raise_for_status()
             return _format_results(query, r.json().get("results", []), n)
         except Exception as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
 
     async def _search_jina(self, query: str, n: int) -> str:
         api_key = self.config.api_key or os.environ.get("JINA_API_KEY", "")
@@ -616,7 +616,7 @@ class WebSearchTool(Tool):
             ]
             return _format_results(query, items, n)
         except Exception as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
 
     async def _search_exa(self, query: str, n: int) -> str:
         api_key = self.config.api_key or os.environ.get("EXA_API_KEY", "")
@@ -663,10 +663,10 @@ class WebSearchTool(Tool):
             return _format_results(query, items, n)
         except httpx.HTTPStatusError as e:
             if e.response.status_code == 429:
-                return "Error: Exa search rate limited. Try again later or reduce search frequency."
+                return ToolResult.error("Error: Exa search rate limited. Try again later or reduce search frequency.")
-            return f"Error: Exa search failed ({e.response.status_code}): {e}"
+            return ToolResult.error(f"Error: Exa search failed ({e.response.status_code}): {e}")
         except Exception as e:
-            return f"Error: Exa search failed: {e}"
+            return ToolResult.error(f"Error: Exa search failed: {e}")
 
     async def _search_volcengine(
         self,
@@ -690,7 +690,7 @@ class WebSearchTool(Tool):
             normalized_time_range = _normalize_volcengine_time_range(time_range) if time_range else None
             normalized_auth_level = _normalize_volcengine_auth_level(auth_level) if auth_level is not None else None
         except ValueError as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
 
         body: dict[str, Any] = {
             "Query": query,
@@ -723,18 +723,18 @@ class WebSearchTool(Tool):
             data = r.json()
         except httpx.HTTPStatusError as e:
             if e.response.status_code == 429:
-                return "Error: Volcengine search rate limited. Try again later or reduce search frequency."
+                return ToolResult.error("Error: Volcengine search rate limited. Try again later or reduce search frequency.")
-            return f"Error: Volcengine search failed ({e.response.status_code}): {e}"
+            return ToolResult.error(f"Error: Volcengine search failed ({e.response.status_code}): {e}")
         except Exception as e:
-            return f"Error: Volcengine search failed: {e}"
+            return ToolResult.error(f"Error: Volcengine search failed: {e}")
 
         error = (data.get("ResponseMetadata") or {}).get("Error") or data.get("Error") or data.get("error")
         if error:
             if isinstance(error, dict):
                 code = error.get("Code") or error.get("code") or "unknown"
                 message = error.get("Message") or error.get("message") or error
-                return f"Error: Volcengine search error {code}: {message}"
+                return ToolResult.error(f"Error: Volcengine search error {code}: {message}")
-            return f"Error: Volcengine search error: {error}"
+            return ToolResult.error(f"Error: Volcengine search error: {error}")
 
         result = data.get("Result") or data
         web_results = result.get("WebResults") or result.get("webResults") or result.get("results") or []
@@ -791,7 +791,7 @@ class WebSearchTool(Tool):
             return _format_results(query, items, n)
         except Exception as e:
             logger.warning("DuckDuckGo search failed: {}", e)
-            return f"Error: DuckDuckGo search failed ({e})"
+            return ToolResult.error(f"Error: DuckDuckGo search failed ({e})")
 
     async def _search_bocha(self, query: str, n: int, freshness: str = "noLimit") -> str:
         api_key = self.config.api_key or os.environ.get("BOCHA_API_KEY", "")
@@ -819,7 +819,7 @@ class WebSearchTool(Tool):
                     timeout=self.config.timeout,
                 )
                 if r.status_code == 429:
-                    return "Error: Bocha search rate-limited (HTTP 429). Wait and retry."
+                    return ToolResult.error("Error: Bocha search rate-limited (HTTP 429). Wait and retry.")
                 r.raise_for_status()
             data = r.json()
             wrapped_data = data.get("data") if isinstance(data, dict) else None
@@ -839,9 +839,9 @@ class WebSearchTool(Tool):
             ]
             return _format_results(query, items, n)
         except httpx.HTTPStatusError as e:
-            return f"Error: Bocha search HTTP {e.response.status_code}: {e.response.text[:200]}"
+            return ToolResult.error(f"Error: Bocha search HTTP {e.response.status_code}: {e.response.text[:200]}")
         except Exception as e:
-            return f"Error: {e}"
+            return ToolResult.error(f"Error: {e}")
 
 
 @tool_parameters(

nanobot/api/server.py

@@ -8,6 +8,7 @@ from __future__ import annotations
 
 import asyncio
 import contextlib
+import hmac
 import json as _json
 import time
 import uuid
@@ -392,7 +393,10 @@ async def handle_health(request: web.Request) -> web.Response:
 
 
 def create_app(
-    agent_loop, model_name: str = "nanobot", request_timeout: float = 120.0
+    agent_loop,
+    model_name: str = "nanobot",
+    request_timeout: float = 120.0,
+    api_key: str = "",
 ) -> web.Application:
     """Create the aiohttp application.
 
@@ -400,6 +404,7 @@ def create_app(
         agent_loop: An initialized AgentLoop instance.
         model_name: Model name reported in responses.
         request_timeout: Per-request timeout in seconds.
+        api_key: Optional API key for Bearer-token authentication.
     """
     app = web.Application(client_max_size=20 * 1024 * 1024)  # 20MB for base64 images
     app["agent_loop"] = agent_loop
@@ -407,6 +412,22 @@ def create_app(
     app["request_timeout"] = request_timeout
     app["session_locks"] = {}  # per-user locks, keyed by session_key
 
+    @web.middleware
+    async def auth_middleware(request: web.Request, handler) -> web.StreamResponse:
+        if not api_key:
+            return await handler(request)
+        # Allow unauthenticated health checks.
+        if request.path == "/health":
+            return await handler(request)
+        auth = request.headers.get("Authorization", "")
+        if not auth.startswith("Bearer "):
+            return _error_json(401, "Missing Authorization header. Use: Bearer <api_key>")
+        if not hmac.compare_digest(auth[len("Bearer "):], api_key):
+            return _error_json(401, "Invalid API key")
+        return await handler(request)
+
+    app.middlewares.append(auth_middleware)
+
     app.router.add_post("/v1/chat/completions", handle_chat_completions)
     app.router.add_get("/v1/models", handle_models)
     app.router.add_get("/health", handle_health)

nanobot/bus/events.py

@@ -2,7 +2,10 @@
 
 from dataclasses import dataclass, field
 from datetime import datetime
-from typing import Any
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from nanobot.bus.outbound_events import OutboundEvent
 
 # Optional ``OutboundMessage.metadata`` key for structured, channel-agnostic UI
 # payloads. Value is JSON-serializable with at least ``kind``; rich clients may
@@ -39,9 +42,9 @@ class InboundMessage:
 class OutboundMessage:
     """Message to send to a chat channel.
 
-    ``metadata`` can carry routing (``message_id``, …), trace flags (``_progress``),
+    ``event`` carries internal runtime/UI semantics. ``metadata`` is reserved
-    and optional ``OUTBOUND_META_AGENT_UI`` blobs for rich clients; non-WebUI
+    for channel routing context (``message_id``, thread ids, etc.) and optional
-    channels may ignore unknown keys.
+    ``OUTBOUND_META_AGENT_UI`` blobs for rich clients.
     """
 
     channel: str
@@ -51,3 +54,4 @@ class OutboundMessage:
     media: list[str] = field(default_factory=list)
     metadata: dict[str, Any] = field(default_factory=dict)
     buttons: list[list[str]] = field(default_factory=list)
+    event: "OutboundEvent | None" = None

nanobot/bus/outbound_events.py

@@ -0,0 +1,226 @@
+"""Typed outbound events carried by :class:`OutboundMessage`.
+
+The message bus still transports :class:`nanobot.bus.events.OutboundMessage`
+because channels need chat routing fields. Runtime/UI semantics live on the
+message's explicit ``event`` field rather than in reserved metadata flags.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from dataclasses import dataclass, replace
+from typing import Any
+
+from nanobot.bus.events import OutboundMessage
+
+
+class OutboundEvent:
+    """Marker base for internal outbound runtime events."""
+
+
+@dataclass(frozen=True)
+class ProgressEvent(OutboundEvent):
+    content: str = ""
+    tool_hint: bool = False
+    reasoning: bool = False
+    reasoning_delta: bool = False
+    reasoning_end: bool = False
+    stream_id: str | None = None
+    tool_events: list[dict[str, Any]] | None = None
+    file_edit_events: list[dict[str, Any]] | None = None
+
+
+@dataclass(frozen=True)
+class RetryWaitEvent(OutboundEvent):
+    content: str = ""
+
+
+@dataclass(frozen=True)
+class StreamDeltaEvent(OutboundEvent):
+    content: str = ""
+    stream_id: str | None = None
+
+
+@dataclass(frozen=True)
+class StreamEndEvent(OutboundEvent):
+    content: str = ""
+    stream_id: str | None = None
+    resuming: bool = False
+
+
+@dataclass(frozen=True)
+class StreamedResponseEvent(OutboundEvent):
+    pass
+
+
+@dataclass(frozen=True)
+class TurnEndEvent(OutboundEvent):
+    latency_ms: int | None = None
+    goal_state: dict[str, Any] | None = None
+
+
+@dataclass(frozen=True)
+class GoalStatusEvent(OutboundEvent):
+    status: str
+    started_at: float | None = None
+
+
+@dataclass(frozen=True)
+class GoalStateSyncEvent(OutboundEvent):
+    goal_state: dict[str, Any]
+
+
+@dataclass(frozen=True)
+class SessionUpdatedEvent(OutboundEvent):
+    scope: str | None = None
+
+
+@dataclass(frozen=True)
+class RuntimeModelUpdatedEvent(OutboundEvent):
+    model: str | None
+    model_preset: str | None = None
+
+
+def outbound_message_for_event(
+    *,
+    channel: str,
+    chat_id: str,
+    event: OutboundEvent,
+    content: str | None = None,
+    metadata: Mapping[str, Any] | None = None,
+) -> OutboundMessage:
+    """Build an :class:`OutboundMessage` for a typed event."""
+
+    return OutboundMessage(
+        channel=channel,
+        chat_id=chat_id,
+        content=_event_content(event) if content is None else content,
+        event=event,
+        metadata=dict(metadata or {}),
+    )
+
+
+def outbound_event_from_message(msg: OutboundMessage) -> OutboundEvent | None:
+    """Return the typed outbound event carried by *msg*, if any."""
+
+    if msg.event is not None:
+        return msg.event
+    return _legacy_event_from_metadata(msg)
+
+
+def replace_outbound_event(
+    msg: OutboundMessage,
+    event: OutboundEvent,
+    *,
+    content: str | None = None,
+) -> OutboundMessage:
+    """Return *msg* with a new event and optional content."""
+
+    return replace(
+        msg,
+        content=_event_content(event) if content is None else content,
+        event=event,
+    )
+
+
+def _event_content(event: OutboundEvent) -> str:
+    if isinstance(event, ProgressEvent | RetryWaitEvent | StreamDeltaEvent | StreamEndEvent):
+        return event.content
+    return ""
+
+
+def _legacy_event_from_metadata(msg: OutboundMessage) -> OutboundEvent | None:
+    """Bridge pre-typed outbound metadata flags into typed events.
+
+    New code should set ``OutboundMessage.event`` directly. The fallback keeps
+    older in-process extensions and channel plugins from losing runtime events
+    while they migrate off reserved metadata flags.
+    """
+
+    meta = msg.metadata or {}
+    if meta.get("_runtime_model_updated"):
+        return RuntimeModelUpdatedEvent(
+            model=_metadata_str(meta, "model"),
+            model_preset=_metadata_str(meta, "model_preset"),
+        )
+    if meta.get("_goal_state_sync"):
+        goal_state = meta.get("goal_state")
+        return GoalStateSyncEvent(goal_state if isinstance(goal_state, dict) else {"active": False})
+    if meta.get("_goal_status"):
+        status = meta.get("goal_status")
+        if not isinstance(status, str) or not status:
+            return None
+        return GoalStatusEvent(
+            status=status,
+            started_at=_metadata_float(meta, "started_at", "goal_started_at"),
+        )
+    if meta.get("_turn_end"):
+        goal_state = meta.get("goal_state")
+        return TurnEndEvent(
+            latency_ms=_metadata_int(meta, "latency_ms"),
+            goal_state=goal_state if isinstance(goal_state, dict) else None,
+        )
+    if meta.get("_session_updated"):
+        return SessionUpdatedEvent(scope=_metadata_str(meta, "_session_update_scope"))
+    if meta.get("_retry_wait"):
+        return RetryWaitEvent(content=msg.content)
+    if meta.get("_stream_end"):
+        return StreamEndEvent(
+            content=msg.content,
+            stream_id=_metadata_str(meta, "_stream_id"),
+            resuming=bool(meta.get("_resuming")),
+        )
+    if meta.get("_stream_delta"):
+        return StreamDeltaEvent(
+            content=msg.content,
+            stream_id=_metadata_str(meta, "_stream_id"),
+        )
+    if meta.get("_streamed"):
+        return StreamedResponseEvent()
+    if (
+        meta.get("_progress")
+        or meta.get("_reasoning_delta")
+        or meta.get("_reasoning_end")
+        or meta.get("_reasoning")
+        or meta.get("_file_edit_events")
+        or meta.get("_tool_events")
+    ):
+        tool_events = meta.get("_tool_events")
+        file_edit_events = meta.get("_file_edit_events")
+        return ProgressEvent(
+            content=msg.content,
+            tool_hint=bool(meta.get("_tool_hint")),
+            reasoning=bool(meta.get("_reasoning")),
+            reasoning_delta=bool(meta.get("_reasoning_delta")),
+            reasoning_end=bool(meta.get("_reasoning_end")),
+            stream_id=_metadata_str(meta, "_stream_id"),
+            tool_events=tool_events if isinstance(tool_events, list) else None,
+            file_edit_events=file_edit_events if isinstance(file_edit_events, list) else None,
+        )
+    return None
+
+
+def _metadata_str(meta: Mapping[str, Any], key: str) -> str | None:
+    value = meta.get(key)
+    return value if isinstance(value, str) and value else None
+
+
+def _metadata_int(meta: Mapping[str, Any], key: str) -> int | None:
+    value = meta.get(key)
+    if isinstance(value, bool):
+        return None
+    if isinstance(value, int):
+        return value
+    if isinstance(value, float) and value.is_integer():
+        return int(value)
+    return None
+
+
+def _metadata_float(meta: Mapping[str, Any], *keys: str) -> float | None:
+    for key in keys:
+        value = meta.get(key)
+        if isinstance(value, bool):
+            continue
+        if isinstance(value, int | float):
+            return float(value)
+    return None

nanobot/bus/progress.py

@@ -10,7 +10,8 @@ from __future__ import annotations
 from collections.abc import Awaitable, Callable
 from typing import Any
 
-from nanobot.bus.events import InboundMessage, OutboundMessage
+from nanobot.bus.events import InboundMessage
+from nanobot.bus.outbound_events import ProgressEvent, outbound_message_for_event
 from nanobot.bus.queue import MessageBus
 
 
@@ -29,23 +30,19 @@ def build_bus_progress_callback(
         reasoning: bool = False,
         reasoning_end: bool = False,
     ) -> None:
-        meta = dict(msg.metadata or {})
-        meta["_progress"] = True
-        meta["_tool_hint"] = tool_hint
-        if reasoning:
-            meta["_reasoning_delta"] = True
-        if reasoning_end:
-            meta["_reasoning_end"] = True
-        if tool_events:
-            meta["_tool_events"] = tool_events
-        if file_edit_events:
-            meta["_file_edit_events"] = file_edit_events
         await bus.publish_outbound(
-            OutboundMessage(
+            outbound_message_for_event(
                 channel=msg.channel,
                 chat_id=msg.chat_id,
+                event=ProgressEvent(
                     content=content,
-                metadata=meta,
+                    tool_hint=tool_hint,
+                    reasoning_delta=reasoning,
+                    reasoning_end=reasoning_end,
+                    tool_events=tool_events,
+                    file_edit_events=file_edit_events,
+                ),
+                metadata=msg.metadata,
             )
         )
 

nanobot/channels/base.py

@@ -101,20 +101,33 @@ class BaseChannel(ABC):
         """
         pass
 
-    async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> None:
+    async def send_delta(
+        self,
+        chat_id: str,
+        delta: str,
+        metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
+        stream_end: bool = False,
+        resuming: bool = False,
+    ) -> None:
         """Deliver a streaming text chunk.
 
         Override in subclasses to enable streaming. Implementations should
         raise on delivery failure so the channel manager can retry.
 
-        Streaming contract: ``_stream_delta`` is a chunk, ``_stream_end`` ends
+        Stateful implementations should key buffers by ``stream_id`` rather
-        the current segment, and stateful implementations must key buffers by
+        than only by ``chat_id`` when it is provided.
-        ``_stream_id`` rather than only by ``chat_id``.
         """
         pass
 
     async def send_reasoning_delta(
-        self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None
+        self,
+        chat_id: str,
+        delta: str,
+        metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
     ) -> None:
         """Stream a chunk of model reasoning/thinking content.
 
@@ -123,15 +136,17 @@ class BaseChannel(ABC):
         subtext, WebUI italic bubble, ...) override to render reasoning
         as a subordinate trace that updates in place as the model thinks.
 
-        Streaming contract mirrors :meth:`send_delta`: ``_reasoning_delta``
+        Streaming contract mirrors :meth:`send_delta`: stateful implementations
-        is a chunk, ``_reasoning_end`` ends the current reasoning segment,
+        should key buffers by ``stream_id`` rather than only by ``chat_id``.
-        and stateful implementations should key buffers by ``_stream_id``
-        rather than only by ``chat_id``.
         """
         return
 
     async def send_reasoning_end(
-        self, chat_id: str, metadata: dict[str, Any] | None = None
+        self,
+        chat_id: str,
+        metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
     ) -> None:
         """Mark the end of a reasoning stream segment.
 
@@ -165,13 +180,18 @@ class BaseChannel(ABC):
         """
         if not msg.content:
             return
-        meta = dict(msg.metadata or {})
+        stream_id = getattr(msg.event, "stream_id", None)
-        meta.setdefault("_reasoning_delta", True)
+        await self.send_reasoning_delta(
-        await self.send_reasoning_delta(msg.chat_id, msg.content, meta)
+            msg.chat_id,
-        end_meta = dict(meta)
+            msg.content,
-        end_meta.pop("_reasoning_delta", None)
+            msg.metadata,
-        end_meta["_reasoning_end"] = True
+            stream_id=stream_id,
-        await self.send_reasoning_end(msg.chat_id, end_meta)
+        )
+        await self.send_reasoning_end(
+            msg.chat_id,
+            msg.metadata,
+            stream_id=stream_id,
+        )
 
     @property
     def supports_streaming(self) -> bool:

nanobot/channels/discord.py

@@ -13,6 +13,7 @@ from typing import TYPE_CHECKING, Any, Literal
 from pydantic import Field
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.command.builtin import build_help_text
@@ -458,7 +459,7 @@ class DiscordChannel(BaseChannel):
             self.logger.warning("client not ready; dropping outbound message")
             return
 
-        is_progress = bool((msg.metadata or {}).get("_progress"))
+        is_progress = isinstance(msg.event, ProgressEvent)
 
         try:
             await client.send_outbound(msg)
@@ -471,7 +472,14 @@ class DiscordChannel(BaseChannel):
                 await self._clear_reactions(msg.chat_id)
 
     async def send_delta(
-        self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None
+        self,
+        chat_id: str,
+        delta: str,
+        metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
+        stream_end: bool = False,
+        resuming: bool = False,
     ) -> None:
         """Progressive Discord delivery: send once, then edit until the stream ends."""
         client = self._client
@@ -479,10 +487,7 @@ class DiscordChannel(BaseChannel):
             self.logger.warning("client not ready; dropping stream delta")
             return
 
-        meta = metadata or {}
+        if stream_end:
-        stream_id = meta.get("_stream_id")
-
-        if meta.get("_stream_end"):
             buf = self._stream_bufs.get(chat_id)
             if not buf or buf.message is None or not buf.text:
                 return

nanobot/channels/email.py

@@ -23,6 +23,7 @@ from loguru import logger
 from pydantic import Field
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.paths import get_media_dir
@@ -218,7 +219,7 @@ class EmailChannel(BaseChannel):
             return
 
         # Skip progress messages to prevent sending an empty email after each tool call
-        if (msg.metadata or {}).get("_progress"):
+        if isinstance(msg.event, ProgressEvent):
             self.logger.debug("Skip progress message to {}", msg.chat_id)
             return
 

nanobot/channels/feishu.py

@@ -22,6 +22,7 @@ from rich.panel import Panel
 from rich.text import Text
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.paths import get_media_dir
@@ -1797,14 +1798,19 @@ class FeishuChannel(BaseChannel):
         return self._stream_update_text_sync(card_id, content, sequence), sequence
 
     async def send_delta(
-        self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None
+        self,
+        chat_id: str,
+        delta: str,
+        metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
+        stream_end: bool = False,
+        resuming: bool = False,
     ) -> None:
         """Progressive streaming via CardKit: create card on first delta, stream-update on subsequent.
 
         Supported metadata keys:
-            _stream_end: Finalize the streaming card.
+            message_id:  Original message id (used with stream end for reaction cleanup).
-            _tool_hint:  Delta is a formatted tool hint (for display only).
-            message_id:  Original message id (used with _stream_end for reaction cleanup).
             chat_type:   "group" or "p2p" — controls reply-in-thread for streaming cards.
         """
         if not self._client:
@@ -1815,14 +1821,14 @@ class FeishuChannel(BaseChannel):
         rid_type = "chat_id" if chat_id.startswith("oc_") else "open_id"
 
         # --- stream end: final update or fallback ---
-        if meta.get("_stream_end"):
+        if stream_end:
             message_id = meta.get("message_id")
             # Only finalize the OnIt -> DONE reaction transition on the truly
-            # final stream end. _resuming=True means the agent will keep
+            # final stream end. resuming=True means the agent will keep
             # working (more tool-call rounds), so leave the reaction state
             # in place — otherwise the OnIt indicator disappears prematurely
             # and the DONE reaction fires after every tool call.
-            if message_id and not meta.get("_resuming"):
+            if message_id and not resuming:
                 reaction_id = self._reaction_ids.pop(message_id, None)
                 if reaction_id:
                     await self._remove_reaction(message_id, reaction_id)
@@ -1965,7 +1971,9 @@ class FeishuChannel(BaseChannel):
             # Handle tool hint messages.  When a streaming card is active for
             # this chat, inline the hint into the card instead of sending a
             # separate message so the user experience stays cohesive.
-            if msg.metadata.get("_tool_hint"):
+            progress_event = msg.event if isinstance(msg.event, ProgressEvent) else None
+
+            if progress_event and progress_event.tool_hint:
                 hint = (msg.content or "").strip()
                 if not hint:
                     return
@@ -1976,6 +1984,7 @@ class FeishuChannel(BaseChannel):
                     await self.send_delta(
                         msg.chat_id,
                         "\n\n" + self._format_tool_hint_delta(hint) + "\n\n",
+                        metadata=msg.metadata,
                     )
                     return
                 # No active streaming card — send as a regular interactive card
@@ -2009,7 +2018,7 @@ class FeishuChannel(BaseChannel):
             reply_message_id: str | None = None
             _msg_id = msg.metadata.get("message_id")
             has_thread_id = msg.metadata.get("thread_id")
-            if self.config.reply_to_message and not msg.metadata.get("_progress", False):
+            if self.config.reply_to_message and progress_event is None:
                 reply_message_id = _msg_id
             # For topic group messages, always reply to keep context in thread
             elif has_thread_id:

nanobot/channels/manager.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import asyncio
 import hashlib
+import inspect
 from collections.abc import Callable
 from contextlib import suppress
 from pathlib import Path
@@ -12,6 +13,16 @@ from typing import TYPE_CHECKING, Any
 from loguru import logger
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import (
+    ProgressEvent,
+    RetryWaitEvent,
+    RuntimeModelUpdatedEvent,
+    StreamDeltaEvent,
+    StreamedResponseEvent,
+    StreamEndEvent,
+    outbound_event_from_message,
+    replace_outbound_event,
+)
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.schema import Config
@@ -266,7 +277,7 @@ class ChannelManager:
 
     def _should_suppress_outbound(self, msg: OutboundMessage) -> bool:
         metadata = msg.metadata or {}
-        if metadata.get("_progress"):
+        if isinstance(outbound_event_from_message(msg), ProgressEvent):
             return False
         fingerprint = self._fingerprint_content(msg.content)
         if not fingerprint:
@@ -305,57 +316,59 @@ class ChannelManager:
                         timeout=1.0
                     )
 
-                if (
+                event = outbound_event_from_message(msg)
-                    msg.metadata.get("_reasoning_delta")
+                progress_event = event if isinstance(event, ProgressEvent) else None
-                    or msg.metadata.get("_reasoning_end")
+                if progress_event and (
-                    or msg.metadata.get("_reasoning")
+                    progress_event.reasoning_delta
+                    or progress_event.reasoning_end
+                    or progress_event.reasoning
                 ):
                     # Reasoning rides its own plugin channel: only delivered
                     # when the destination channel opts in via ``show_reasoning``
                     # and overrides the streaming primitives. Channels without
                     # a low-emphasis UI affordance keep the base no-op and the
-                    # content silently drops here. ``_reasoning`` (one-shot)
+                    # content silently drops here.
-                    # is accepted for backward compatibility with hooks that
-                    # haven't migrated to delta/end yet.
                     channel = self.channels.get(msg.channel)
                     if channel is not None and channel.show_reasoning:
                         await self._send_with_retry(channel, msg)
                     continue
 
-                if msg.metadata.get("_progress"):
+                if progress_event:
-                    if msg.metadata.get("_tool_hint") and not self._should_send_progress(
+                    if progress_event.tool_hint and not self._should_send_progress(
                         msg.channel, tool_hint=True,
                     ):
                         continue
-                    if not msg.metadata.get("_tool_hint") and not self._should_send_progress(
+                    if not progress_event.tool_hint and not self._should_send_progress(
                         msg.channel, tool_hint=False,
                     ):
                         continue
 
-                if msg.metadata.get("_retry_wait"):
+                if isinstance(event, RetryWaitEvent):
                     continue
 
                 if (
-                    msg.metadata.get("_runtime_model_updated")
+                    isinstance(event, RuntimeModelUpdatedEvent)
                     and msg.channel == "websocket"
                     and "websocket" not in self.channels
                 ):
                     continue
 
-                # Coalesce consecutive _stream_delta messages for the same (channel, chat_id)
+                # Coalesce consecutive stream delta messages for the same (channel, chat_id)
                 # to reduce API calls and improve streaming latency
-                if msg.metadata.get("_stream_delta") and not msg.metadata.get("_stream_end"):
+                if isinstance(event, StreamDeltaEvent):
                     msg, extra_pending = self._coalesce_stream_deltas(msg)
                     pending.extend(extra_pending)
+                    event = outbound_event_from_message(msg)
 
                 channel = self.channels.get(msg.channel)
                 if channel:
                     # Duplicate suppression is scoped to a known source message
                     # so repeated content from separate turns is still delivered.
                     if (
-                        not msg.metadata.get("_stream_delta")
+                        not isinstance(
-                        and not msg.metadata.get("_stream_end")
+                            event,
-                        and not msg.metadata.get("_streamed")
+                            StreamDeltaEvent | StreamEndEvent | StreamedResponseEvent,
+                        )
                     ):
                         if self._should_suppress_outbound(msg):
                             logger.info("Suppressing duplicate outbound message to {}:{}", msg.channel, msg.chat_id)
@@ -369,34 +382,116 @@ class ChannelManager:
             except asyncio.CancelledError:
                 break
 
+    @staticmethod
+    def _accepts_keyword(callable_obj: Callable[..., Any], name: str) -> bool:
+        try:
+            signature = inspect.signature(callable_obj)
+        except (TypeError, ValueError):
+            return True
+        return any(
+            parameter.kind is inspect.Parameter.VAR_KEYWORD or parameter.name == name
+            for parameter in signature.parameters.values()
+        )
+
+    @classmethod
+    async def _send_reasoning_delta(cls, channel: BaseChannel, msg: OutboundMessage, event: ProgressEvent) -> None:
+        metadata = msg.metadata
+        kwargs: dict[str, Any] = {}
+        if cls._accepts_keyword(channel.send_reasoning_delta, "stream_id"):
+            kwargs["stream_id"] = event.stream_id
+        else:
+            metadata = dict(metadata or {})
+            metadata["_reasoning_delta"] = True
+            if event.stream_id is not None:
+                metadata["_stream_id"] = event.stream_id
+        await channel.send_reasoning_delta(
+            msg.chat_id,
+            msg.content,
+            metadata,
+            **kwargs,
+        )
+
+    @classmethod
+    async def _send_reasoning_end(cls, channel: BaseChannel, msg: OutboundMessage, event: ProgressEvent) -> None:
+        metadata = msg.metadata
+        kwargs: dict[str, Any] = {}
+        if cls._accepts_keyword(channel.send_reasoning_end, "stream_id"):
+            kwargs["stream_id"] = event.stream_id
+        else:
+            metadata = dict(metadata or {})
+            metadata["_reasoning_end"] = True
+            if event.stream_id is not None:
+                metadata["_stream_id"] = event.stream_id
+        await channel.send_reasoning_end(
+            msg.chat_id,
+            metadata,
+            **kwargs,
+        )
+
+    @classmethod
+    async def _send_stream_event(
+        cls,
+        channel: BaseChannel,
+        msg: OutboundMessage,
+        event: StreamDeltaEvent | StreamEndEvent,
+    ) -> None:
+        metadata = msg.metadata
+        kwargs: dict[str, Any] = {}
+        if cls._accepts_keyword(channel.send_delta, "stream_id"):
+            kwargs["stream_id"] = event.stream_id
+        else:
+            metadata = dict(metadata or {})
+            if event.stream_id is not None:
+                metadata["_stream_id"] = event.stream_id
+
+        if isinstance(event, StreamEndEvent):
+            if cls._accepts_keyword(channel.send_delta, "stream_end"):
+                kwargs["stream_end"] = True
+            else:
+                metadata = dict(metadata or {})
+                metadata["_stream_end"] = True
+            if cls._accepts_keyword(channel.send_delta, "resuming"):
+                kwargs["resuming"] = event.resuming
+        elif not kwargs:
+            metadata = dict(metadata or {})
+            metadata["_stream_delta"] = True
+
+        await channel.send_delta(
+            msg.chat_id,
+            msg.content,
+            metadata,
+            **kwargs,
+        )
+
     @staticmethod
     async def _send_once(channel: BaseChannel, msg: OutboundMessage) -> None:
         """Send one outbound message without retry policy."""
-        if msg.metadata.get("_reasoning_end"):
+        event = outbound_event_from_message(msg)
-            await channel.send_reasoning_end(msg.chat_id, msg.metadata)
+        if isinstance(event, ProgressEvent) and event.reasoning_end:
-        elif msg.metadata.get("_reasoning_delta"):
+            await ChannelManager._send_reasoning_end(channel, msg, event)
-            await channel.send_reasoning_delta(msg.chat_id, msg.content, msg.metadata)
+        elif isinstance(event, ProgressEvent) and event.reasoning_delta:
-        elif msg.metadata.get("_reasoning"):
+            await ChannelManager._send_reasoning_delta(channel, msg, event)
-            # Back-compat: one-shot reasoning. BaseChannel translates this
+        elif isinstance(event, ProgressEvent) and event.reasoning:
-            # to a single delta + end pair so plugins only implement the
+            # BaseChannel translates one-shot reasoning to a single delta +
-            # streaming primitives.
+            # end pair so plugins only implement the streaming primitives.
             await channel.send_reasoning(msg)
-        elif msg.metadata.get("_file_edit_events"):
+        elif isinstance(event, ProgressEvent) and event.file_edit_events:
-            edits = msg.metadata.get("_file_edit_events")
             await channel.send_file_edit_events(
                 msg.chat_id,
-                edits if isinstance(edits, list) else [],
+                event.file_edit_events,
                 msg.metadata,
             )
-        elif msg.metadata.get("_stream_delta") or msg.metadata.get("_stream_end"):
+        elif isinstance(event, StreamDeltaEvent):
-            await channel.send_delta(msg.chat_id, msg.content, msg.metadata)
+            await ChannelManager._send_stream_event(channel, msg, event)
-        elif not msg.metadata.get("_streamed"):
+        elif isinstance(event, StreamEndEvent):
+            await ChannelManager._send_stream_event(channel, msg, event)
+        elif not isinstance(event, StreamedResponseEvent):
             await channel.send(msg)
 
     def _coalesce_stream_deltas(
         self, first_msg: OutboundMessage
     ) -> tuple[OutboundMessage, list[OutboundMessage]]:
-        """Merge consecutive _stream_delta messages for the same (channel, chat_id).
+        """Merge consecutive stream deltas for the same (channel, chat_id, stream_id).
 
         This reduces the number of API calls when the queue has accumulated multiple
         deltas, which happens when LLM generates faster than the channel can process.
@@ -404,9 +499,15 @@ class ChannelManager:
         Returns:
             tuple of (merged_message, list_of_non_matching_messages)
         """
-        target_key = (first_msg.channel, first_msg.chat_id)
+        first_event = outbound_event_from_message(first_msg)
+        first_stream_id = first_event.stream_id if isinstance(first_event, StreamDeltaEvent) else None
+        target_key = (first_msg.channel, first_msg.chat_id, first_stream_id)
         combined_content = first_msg.content
-        final_metadata = dict(first_msg.metadata or {})
+        final_event: StreamDeltaEvent | StreamEndEvent = (
+            first_event
+            if isinstance(first_event, StreamDeltaEvent)
+            else StreamDeltaEvent(stream_id=first_stream_id)
+        )
         non_matching: list[OutboundMessage] = []
 
         # Only merge consecutive deltas. As soon as we hit any other message,
@@ -418,16 +519,29 @@ class ChannelManager:
                 break
 
             # Check if this message belongs to the same stream
-            same_target = (next_msg.channel, next_msg.chat_id) == target_key
+            next_event = outbound_event_from_message(next_msg)
-            is_delta = next_msg.metadata and next_msg.metadata.get("_stream_delta")
+            next_stream_id = (
-            is_end = next_msg.metadata and next_msg.metadata.get("_stream_end")
+                next_event.stream_id
+                if isinstance(next_event, StreamDeltaEvent | StreamEndEvent)
+                else None
+            )
+            same_target = (
+                next_msg.channel,
+                next_msg.chat_id,
+                next_stream_id,
+            ) == target_key
+            is_delta = isinstance(next_event, StreamDeltaEvent)
+            is_end = isinstance(next_event, StreamEndEvent)
 
-            if same_target and is_delta and not final_metadata.get("_stream_end"):
+            if same_target and (is_delta or (is_end and next_msg.content)):
                 # Accumulate content
                 combined_content += next_msg.content
-                # If we see _stream_end, remember it and stop coalescing this stream
+                # If we see stream_end, remember it and stop coalescing this stream
-                if is_end:
+                if isinstance(next_event, StreamEndEvent):
-                    final_metadata["_stream_end"] = True
+                    final_event = StreamEndEvent(
+                        stream_id=next_stream_id,
+                        resuming=next_event.resuming,
+                    )
                     # Stream ended - stop coalescing this stream
                     break
             else:
@@ -435,12 +549,7 @@ class ChannelManager:
                 non_matching.append(next_msg)
                 break
 
-        merged = OutboundMessage(
+        merged = replace_outbound_event(first_msg, final_event, content=combined_content)
-            channel=first_msg.channel,
-            chat_id=first_msg.chat_id,
-            content=combined_content,
-            metadata=final_metadata,
-        )
         return merged, non_matching
 
     async def _send_with_retry(self, channel: BaseChannel, msg: OutboundMessage) -> None:

nanobot/channels/matrix.py

@@ -49,6 +49,7 @@ except ImportError as e:
     ) from e
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.paths import get_data_dir, get_media_dir
@@ -504,7 +505,7 @@ class MatrixChannel(BaseChannel):
         text = msg.content or ""
         candidates = self._collect_outbound_media_candidates(msg.media)
         relates_to = self._build_thread_relates_to(msg.metadata)
-        is_progress = bool((msg.metadata or {}).get("_progress"))
+        is_progress = isinstance(msg.event, ProgressEvent)
         try:
             failures: list[str] = []
             if candidates:
@@ -528,11 +529,19 @@ class MatrixChannel(BaseChannel):
             if not is_progress:
                 await self._stop_typing_keepalive(msg.chat_id, clear_typing=True)
 
-    async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> None:
+    async def send_delta(
-        meta = metadata or {}
+        self,
+        chat_id: str,
+        delta: str,
+        metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
+        stream_end: bool = False,
+        resuming: bool = False,
+    ) -> None:
         relates_to = self._build_thread_relates_to(metadata)
 
-        if meta.get("_stream_end"):
+        if stream_end:
             buf = self._stream_bufs.pop(chat_id, None)
             if not buf or not buf.event_id or not buf.text:
                 return

nanobot/channels/signal.py

@@ -18,6 +18,7 @@ import httpx
 from pydantic import Field, computed_field, field_validator
 
 from nanobot.bus.events import InboundMessage, OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.paths import get_media_dir
@@ -539,7 +540,7 @@ class SignalChannel(BaseChannel):
 
     async def send(self, msg: OutboundMessage) -> None:
         """Send a message through Signal."""
-        is_progress_message = bool(msg.metadata.get("_progress"))
+        is_progress_message = isinstance(msg.event, ProgressEvent)
         try:
             plain_text, text_styles = _markdown_to_signal(msg.content)
             if not plain_text and not msg.media:

nanobot/channels/slack.py

@@ -14,6 +14,7 @@ from slack_sdk.web.async_client import AsyncWebClient
 from slackify_markdown import slackify_markdown
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.paths import get_media_dir
@@ -164,7 +165,7 @@ class SlackChannel(BaseChannel):
             # only makes sense within the originating conversation.
             thread_ts_param = thread_ts if thread_ts and target_chat_id == origin_chat_id else None
 
-            is_progress = (msg.metadata or {}).get("_progress", False)
+            is_progress = isinstance(msg.event, ProgressEvent)
             if is_progress and not msg.content:
                 pass  # skip empty progress messages (e.g. tool-event-only updates)
             elif msg.content or not (msg.media or []):
@@ -190,7 +191,7 @@ class SlackChannel(BaseChannel):
                     self.logger.exception("Failed to upload file {}", media_path)
 
             # Update reaction emoji when the final (non-progress) response is sent
-            if not (msg.metadata or {}).get("_progress"):
+            if not is_progress:
                 event = slack_meta.get("event", {})
                 await self._update_react_emoji(origin_chat_id, event.get("ts"))
 

nanobot/channels/telegram.py

@@ -26,6 +26,7 @@ from telegram.ext import Application, CallbackQueryHandler, ContextTypes, Messag
 from telegram.request import HTTPXRequest
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.command.builtin import build_help_text
@@ -36,7 +37,7 @@ from nanobot.utils.helpers import split_message
 
 TELEGRAM_MAX_MESSAGE_LEN = 4000  # Telegram message character limit
 # Telegram's actual API limit is 4096; we split raw markdown at 4000 as a
-# safety margin for mid-stream edits (plain text).  For _stream_end, we split
+# safety margin for mid-stream edits (plain text).  On stream end, we split
 # raw markdown into chunks whose rendered HTML fits Telegram's true 4096-char
 # boundary so the final rendered message never overflows.
 TELEGRAM_HTML_MAX_LEN = 4096
@@ -706,8 +707,10 @@ class TelegramChannel(BaseChannel):
             self.logger.warning("bot not running")
             return
 
+        progress_event = msg.event if isinstance(msg.event, ProgressEvent) else None
+
         # Only stop typing indicator and remove reaction for final responses
-        if not msg.metadata.get("_progress", False):
+        if progress_event is None:
             self._stop_typing(msg.chat_id)
             if reply_to_message_id := msg.metadata.get("message_id"):
                 with suppress(ValueError):
@@ -792,7 +795,7 @@ class TelegramChannel(BaseChannel):
 
         # Send text content
         if msg.content and msg.content != "[empty message]":
-            render_as_blockquote = bool(msg.metadata.get("_tool_hint"))
+            render_as_blockquote = bool(progress_event and progress_event.tool_hint)
             buttons = getattr(msg, "buttons", None) or []
             reply_markup = self._build_keyboard(buttons) if buttons else None
             text = msg.content
@@ -887,15 +890,23 @@ class TelegramChannel(BaseChannel):
     def _is_not_modified_error(exc: Exception) -> bool:
         return isinstance(exc, BadRequest) and "message is not modified" in str(exc).lower()
 
-    async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> None:
+    async def send_delta(
+        self,
+        chat_id: str,
+        delta: str,
+        metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
+        stream_end: bool = False,
+        resuming: bool = False,
+    ) -> None:
         """Progressive message editing: send on first delta, edit on subsequent ones."""
         if not self._app:
             return
         meta = metadata or {}
         int_chat_id = int(chat_id)
-        stream_id = meta.get("_stream_id")
 
-        if meta.get("_stream_end"):
+        if stream_end:
             buf = self._stream_bufs.get(chat_id)
             if not buf or not buf.message_id or not buf.text:
                 return

nanobot/channels/websocket.py

@@ -19,6 +19,16 @@ from websockets.exceptions import ConnectionClosed
 from websockets.http11 import Request as WsRequest
 
 from nanobot.bus.events import OUTBOUND_META_AGENT_UI, OutboundMessage
+from nanobot.bus.outbound_events import (
+    GoalStateSyncEvent,
+    GoalStatusEvent,
+    ProgressEvent,
+    RuntimeModelUpdatedEvent,
+    SessionUpdatedEvent,
+    TurnEndEvent,
+    outbound_event_from_message,
+    outbound_message_for_event,
+)
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.paths import get_media_dir
@@ -148,16 +158,13 @@ def publish_runtime_model_update(
     model_preset: str | None,
 ) -> None:
     """Enqueue a runtime model snapshot for websocket subscribers (fan-out in-channel)."""
-    bus.outbound.put_nowait(OutboundMessage(
+    bus.outbound.put_nowait(
+        outbound_message_for_event(
             channel="websocket",
             chat_id="*",
-        content="",
+            event=RuntimeModelUpdatedEvent(model=model, model_preset=model_preset),
-        metadata={
+        )
-            "_runtime_model_updated": True,
+    )
-            "model": model,
-            "model_preset": model_preset,
-        },
-    ))
 
 
 def _parse_inbound_payload(raw: str) -> str | None:
@@ -851,70 +858,63 @@ class WebSocketChannel(BaseChannel):
             raise
 
     async def send(self, msg: OutboundMessage) -> None:
-        if msg.metadata.get("_runtime_model_updated"):
+        event = outbound_event_from_message(msg)
+        progress_event = event if isinstance(event, ProgressEvent) else None
+        if isinstance(event, RuntimeModelUpdatedEvent):
             await self.send_runtime_model_updated(
-                model_name=msg.metadata.get("model"),
+                model_name=event.model,
-                model_preset=msg.metadata.get("model_preset"),
+                model_preset=event.model_preset,
             )
             return
 
         # Snapshot the subscriber set so ConnectionClosed cleanups mid-iteration are safe.
         conns = list(self._subs.get(msg.chat_id, ()))
         if not conns:
-            if (
+            if isinstance(
-                msg.metadata.get("_progress")
+                event,
-                or msg.metadata.get("_file_edit_events")
+                ProgressEvent
-                or msg.metadata.get("_turn_end")
+                | TurnEndEvent
-                or msg.metadata.get("_session_updated")
+                | SessionUpdatedEvent
-                or msg.metadata.get("_goal_status")
+                | GoalStatusEvent
-                or msg.metadata.get("_goal_state_sync")
+                | GoalStateSyncEvent,
             ):
                 self.logger.debug("no active subscribers for chat_id={}", msg.chat_id)
             else:
                 self.logger.warning("no active subscribers for chat_id={}", msg.chat_id)
-        if msg.metadata.get("_goal_state_sync"):
+        if isinstance(event, GoalStateSyncEvent):
             if conns:
-                blob = msg.metadata.get("goal_state")
+                await self.send_goal_state(msg.chat_id, event.goal_state or {"active": False})
-                await self.send_goal_state(msg.chat_id, blob if isinstance(blob, dict) else {"active": False})
             return
-        if msg.metadata.get("_goal_status"):
+        if isinstance(event, GoalStatusEvent):
             if conns:
-                status = msg.metadata.get("goal_status")
+                if event.status in ("running", "idle"):
-                if status in ("running", "idle"):
-                    started_raw = msg.metadata.get("started_at", msg.metadata.get("goal_started_at"))
                     await self.send_goal_status(
                         msg.chat_id,
-                        status,
+                        event.status,
-                        started_at=float(started_raw) if isinstance(started_raw, int | float) else None,
+                        started_at=event.started_at,
                     )
             return
         # Signal that the agent has fully finished processing the current turn.
-        if msg.metadata.get("_turn_end"):
+        if isinstance(event, TurnEndEvent):
-            lat = msg.metadata.get("latency_ms")
-            lat_i = int(lat) if isinstance(lat, (int, float)) else None
-            gs = msg.metadata.get("goal_state")
-            gs_blob = gs if isinstance(gs, dict) else None
             await self.send_turn_end(
                 msg.chat_id,
-                latency_ms=lat_i,
+                latency_ms=event.latency_ms,
-                goal_state=gs_blob,
+                goal_state=event.goal_state,
                 metadata=msg.metadata,
             )
             await self.send_session_updated(msg.chat_id, scope="thread")
             return
-        if msg.metadata.get("_session_updated"):
+        if isinstance(event, SessionUpdatedEvent):
             if conns:
-                scope = msg.metadata.get("_session_update_scope")
                 await self.send_session_updated(
                     msg.chat_id,
-                    scope=scope if isinstance(scope, str) else None,
+                    scope=event.scope,
                 )
             return
-        if msg.metadata.get("_file_edit_events"):
+        if progress_event and progress_event.file_edit_events:
-            edits = msg.metadata.get("_file_edit_events")
             await self.send_file_edit_events(
                 msg.chat_id,
-                edits if isinstance(edits, list) else [],
+                progress_event.file_edit_events,
                 msg.metadata,
             )
             return
@@ -939,17 +939,17 @@ class WebSocketChannel(BaseChannel):
         lat = msg.metadata.get("latency_ms")
         if isinstance(lat, (int, float)):
             payload["latency_ms"] = int(lat)
-        if msg.metadata.get("_tool_events"):
+        if progress_event and progress_event.tool_events:
-            payload["tool_events"] = msg.metadata["_tool_events"]
+            payload["tool_events"] = progress_event.tool_events
         agent_ui = msg.metadata.get(OUTBOUND_META_AGENT_UI)
         if agent_ui is not None:
             payload["agent_ui"] = agent_ui
         # Mark intermediate agent breadcrumbs (tool-call hints, generic
         # progress strings) so WS clients can render them as subordinate
         # trace rows rather than conversational replies.
-        if msg.metadata.get("_tool_hint"):
+        if progress_event and progress_event.tool_hint:
             payload["kind"] = "tool_hint"
-        elif msg.metadata.get("_progress"):
+        elif progress_event:
             payload["kind"] = "progress"
         phase = "activity" if payload.get("kind") in ("tool_hint", "progress") else "answer"
         self._transcripts.prepare_and_append(
@@ -971,6 +971,8 @@ class WebSocketChannel(BaseChannel):
         chat_id: str,
         delta: str,
         metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
     ) -> None:
         """Push one chunk of model reasoning. Mirrors ``send_delta`` shape so
         clients receive a stream that opens, updates in place, and closes —
@@ -986,7 +988,6 @@ class WebSocketChannel(BaseChannel):
             "chat_id": chat_id,
             "text": delta,
         }
-        stream_id = meta.get("_stream_id")
         if stream_id is not None:
             body["stream_id"] = stream_id
         self._transcripts.prepare_and_append(
@@ -1005,6 +1006,8 @@ class WebSocketChannel(BaseChannel):
         self,
         chat_id: str,
         metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
     ) -> None:
         """Close the current reasoning stream segment for in-place renderers."""
         conns = list(self._subs.get(chat_id, ()))
@@ -1013,7 +1016,6 @@ class WebSocketChannel(BaseChannel):
             "event": "reasoning_end",
             "chat_id": chat_id,
         }
-        stream_id = meta.get("_stream_id")
         if stream_id is not None:
             body["stream_id"] = stream_id
         self._transcripts.prepare_and_append(
@@ -1057,11 +1059,15 @@ class WebSocketChannel(BaseChannel):
         chat_id: str,
         delta: str,
         metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
+        stream_end: bool = False,
+        resuming: bool = False,
     ) -> None:
         conns = list(self._subs.get(chat_id, ()))
         meta = metadata or {}
-        stream_key = (chat_id, str(meta.get("_stream_id") or ""))
+        stream_key = (chat_id, str(stream_id or ""))
-        if meta.get("_stream_end"):
+        if stream_end:
             body: dict[str, Any] = {"event": "stream_end", "chat_id": chat_id}
             buffered = self._stream_text_buffers.pop(stream_key, [])
             if delta:
@@ -1077,8 +1083,8 @@ class WebSocketChannel(BaseChannel):
                 "text": delta,
             }
             self._stream_text_buffers.setdefault(stream_key, []).append(delta)
-        if meta.get("_stream_id") is not None:
+        if stream_id is not None:
-            body["stream_id"] = meta["_stream_id"]
+            body["stream_id"] = stream_id
         self._transcripts.prepare_and_append(
             chat_id,
             body,

nanobot/channels/wecom.py

@@ -13,6 +13,7 @@ from typing import Any
 from pydantic import Field
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.paths import get_media_dir
@@ -497,7 +498,7 @@ class WecomChannel(BaseChannel):
 
         try:
             content = (msg.content or "").strip()
-            is_progress = bool(msg.metadata.get("_progress"))
+            is_progress = isinstance(msg.event, ProgressEvent)
 
             # Get the stored frame for this chat
             frame = self._chat_frames.get(msg.chat_id)

nanobot/channels/weixin.py

@@ -29,6 +29,7 @@ from loguru import logger
 from pydantic import Field
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.paths import get_media_dir, get_runtime_subdir
@@ -129,6 +130,13 @@ class WeixinConfig(Base):
     token: str = ""  # Manually set token, or obtained via QR login
     state_dir: str = ""  # Default: ~/.nanobot/weixin/
     poll_timeout: int = DEFAULT_LONG_POLL_TIMEOUT_S  # seconds for long-poll
+    # Default on: WeChat iLink has no native incremental delivery (send_delta is
+    # buffered and the final answer is still sent in one shot), so streaming has
+    # zero user-facing effect here — it only switches the LLM call to the
+    # streaming API. That avoids upstream Anthropic relays that drop tool_use
+    # id/name/input on the non-streaming Messages path (a common third-party
+    # relay bug). Set to false only if a relay's streaming/SSE path is broken.
+    streaming: bool = True
 
 
 class WeixinChannel(BaseChannel):
@@ -167,6 +175,10 @@ class WeixinChannel(BaseChannel):
         self._typing_tickets: dict[str, dict[str, Any]] = {}
         self._context_token_at: dict[str, float] = {}
         self._pending_tool_hints: dict[str, list[str]] = {}
+        # Buffers streamed content deltas per chat. WeChat iLink has no native
+        # incremental delivery, so when streaming is enabled we accumulate the
+        # deltas and flush the full reply in one shot at _stream_end.
+        self._stream_buffers: dict[str, list[str]] = {}
 
     # ------------------------------------------------------------------
     # State persistence
@@ -1090,11 +1102,13 @@ class WeixinChannel(BaseChannel):
             raise RuntimeError("WeChat client not initialized or not authenticated")
         self._assert_session_active()
 
-        is_progress = bool((msg.metadata or {}).get("_progress", False))
+        event = getattr(msg, "event", None)
+        progress_event = event if isinstance(event, ProgressEvent) else None
+        is_progress = progress_event is not None
 
         # Buffer tool hints to coalesce consecutive ones and avoid burning
         # WeChat iLink rate-limit quota (~7 msgs / 5 min).
-        if is_progress and (msg.metadata or {}).get("_tool_hint"):
+        if progress_event and progress_event.tool_hint:
             if not self.send_tool_hints:
                 return
             self._pending_tool_hints.setdefault(msg.chat_id, []).append(msg.content)
@@ -1107,7 +1121,7 @@ class WeixinChannel(BaseChannel):
 
         # Reasoning deltas are invisible in WeChat (there is no reasoning
         # UI).  Skip them entirely — do not send and do not flush buffer.
-        if is_progress and (msg.metadata or {}).get("_reasoning_delta"):
+        if progress_event and (progress_event.reasoning_delta or progress_event.reasoning):
             self.logger.debug(
                 "Dropped invisible reasoning delta for {}", msg.chat_id
             )
@@ -1221,16 +1235,46 @@ class WeixinChannel(BaseChannel):
                     await self._send_typing(msg.chat_id, typing_ticket, TYPING_STATUS_CANCEL)
 
     async def send_delta(
-        self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None
+        self,
+        chat_id: str,
+        delta: str,
+        metadata: dict[str, Any] | None = None,
+        *,
+        stream_id: str | None = None,
+        stream_end: bool = False,
+        resuming: bool = False,
     ) -> None:
-        """Weixin iLink does not support native streaming deltas.
+        """Deliver a streamed reply to WeChat.
 
-        We only hook ``_stream_end`` so buffered tool hints are flushed even
+        WeChat iLink has no native incremental delivery, and the manager
-        when the final answer carries the ``_streamed`` flag and bypasses
+        bypasses :meth:`send` for the ``_streamed`` final answer. So we
-        :meth:`send`.
+        accumulate content deltas and flush the full reply as a single message
+        at stream end. Reasoning deltas are invisible in WeChat and are dropped.
         """
-        if metadata and metadata.get("_stream_end"):
+        meta = metadata or {}
+        if meta.get("_reasoning_delta") or meta.get("_reasoning"):
+            return
+        is_end = stream_end or bool(meta.get("_stream_end"))
+        buffer_key = stream_id or chat_id
+        # Accumulate intermediate deltas. The stream_end message's own content
+        # (present when the manager coalesces deltas into the end message) is
+        # folded into `full` below instead of appended here, so a send retry
+        # recomputes the same `full` from an unchanged buffer rather than
+        # double-counting that delta.
+        if delta and not is_end:
+            self._stream_buffers.setdefault(buffer_key, []).append(delta)
+        if not is_end:
+            return
+        full = ("".join(self._stream_buffers.get(buffer_key, [])) + (delta or "")).strip()
         await self._flush_tool_hints(chat_id)
+        if full:
+            # Send before clearing the buffer: if the send raises, the buffer is
+            # left intact so ChannelManager._send_with_retry can re-deliver the
+            # same stream_end message instead of silently losing the reply.
+            await self.send(
+                OutboundMessage(channel=self.name, chat_id=chat_id, content=full)
+            )
+        self._stream_buffers.pop(buffer_key, None)
 
     async def _start_typing(self, chat_id: str, context_token: str = "") -> None:
         """Start typing indicator immediately when a message is received."""

nanobot/channels/whatsapp.py

@@ -499,6 +499,30 @@ class WhatsAppChannel(BaseChannel):
                 self._self_jids.add(jid)
                 self._self_jids.add(_bare_jid(jid))
 
+    async def _send_read_receipt(self, client: Any, source: Any, message_id: str) -> None:
+        """Send a read receipt (blue double-check) for an incoming message.
+
+        Best-effort: any failure is logged at debug level and swallowed so it
+        never blocks message processing.
+        """
+        if not message_id:
+            return
+        try:
+            from neonize.utils.enum import ReceiptType
+
+            chat = _safe_attr(source, "Chat")
+            sender = _safe_attr(source, "Sender")
+            if chat is None or sender is None:
+                return
+            await client.mark_read(
+                message_id,
+                chat=chat,
+                sender=sender,
+                receipt=ReceiptType.READ,
+            )
+        except Exception as exc:  # noqa: BLE001 - read receipt is best-effort
+            self.logger.debug("Failed to send WhatsApp read receipt: {}", exc)
+
     async def _handle_neonize_message(self, client: Any, event: Any) -> None:
         info = _safe_attr(event, "Info")
         message = _safe_attr(event, "Message")
@@ -532,6 +556,9 @@ class WhatsAppChannel(BaseChannel):
             while len(self._processed_message_ids) > 1000:
                 self._processed_message_ids.popitem(last=False)
 
+        # Mark the incoming message as read (blue double-check). Best-effort.
+        await self._send_read_receipt(client, source, message_id)
+
         participant_jid = _normalize_jid(_safe_attr(source, "Sender"))
         sender_alt_jid = _normalize_jid(_safe_attr(source, "SenderAlt"))
         sender_candidates = [sender_alt_jid, participant_jid]

nanobot/cli/commands.py

@@ -50,6 +50,14 @@ from rich.text import Text  # noqa: E402
 
 from nanobot import __logo__, __version__  # noqa: E402
 from nanobot.agent.loop import AgentLoop  # noqa: E402
+from nanobot.bus.outbound_events import (  # noqa: E402
+    ProgressEvent,
+    RetryWaitEvent,
+    StreamDeltaEvent,
+    StreamedResponseEvent,
+    StreamEndEvent,
+    outbound_event_from_message,
+)
 from nanobot.cli.gateway import create_gateway_app  # noqa: E402
 from nanobot.cli.stream import StreamRenderer, ThinkingSpinner  # noqa: E402
 from nanobot.config.paths import get_workspace_path, is_default_workspace  # noqa: E402
@@ -461,25 +469,25 @@ async def _maybe_print_interactive_progress(
     renderer: StreamRenderer | None = None,
     reasoning_buffer: _ReasoningBuffer | None = None,
 ) -> bool:
-    metadata = msg.metadata or {}
+    event = outbound_event_from_message(msg)
-    if metadata.get("_retry_wait"):
+    if isinstance(event, RetryWaitEvent):
         await _print_interactive_progress_line(msg.content, thinking, renderer)
         return True
 
-    if not metadata.get("_progress"):
+    if not isinstance(event, ProgressEvent):
         return False
 
     reasoning_buffer = reasoning_buffer or _ReasoningBuffer()
 
-    if metadata.get("_reasoning_end"):
+    if event.reasoning_end:
         if channels_config and not channels_config.show_reasoning:
             reasoning_buffer.clear()
         else:
             _flush_cli_reasoning(reasoning_buffer, thinking, renderer)
         return True
 
-    is_tool_hint = metadata.get("_tool_hint", False)
+    is_tool_hint = event.tool_hint
-    is_reasoning = metadata.get("_reasoning", False) or metadata.get("_reasoning_delta", False)
+    is_reasoning = event.reasoning or event.reasoning_delta
     if is_reasoning:
         if channels_config and not channels_config.show_reasoning:
             reasoning_buffer.clear()
@@ -798,14 +806,24 @@ def serve(
     console.print(f"  [cyan]Model[/cyan]    : {model_name}{preset_tag}")
     console.print("  [cyan]Session[/cyan]  : api:default")
     console.print(f"  [cyan]Timeout[/cyan]  : {timeout}s")
+    api_key = api_cfg.api_key.strip() if api_cfg.api_key else ""
     if host in {"0.0.0.0", "::"}:
+        if not api_key:
             console.print(
-            "[yellow]Warning:[/yellow] API is bound to all interfaces. "
+                "[red]Error: host is 0.0.0.0 (all interfaces) but api_key is not set. "
-            "Only do this behind a trusted network boundary, firewall, or reverse proxy."
+                "Set api.api_key in config to prevent unauthenticated access.[/red]"
+            )
+            raise typer.Exit(1)
+        console.print(
+            "[yellow]API is bound to all interfaces "
+            "(authentication required).[/yellow]"
         )
     console.print()
 
-    api_app = create_app(agent_loop, model_name=model_name, request_timeout=timeout)
+    api_app = create_app(
+        agent_loop, model_name=model_name, request_timeout=timeout,
+        api_key=api_key,
+    )
 
     async def on_startup(_app):
         await agent_loop._connect_mcp()
@@ -1446,7 +1464,7 @@ def agent(
             bus_task = asyncio.create_task(agent_loop.run())
             turn_done = asyncio.Event()
             turn_done.set()
-            turn_response: list[tuple[str, dict]] = []
+            turn_response: list[Any] = []
             renderer: StreamRenderer | None = None
             reasoning_buffer = _ReasoningBuffer()
 
@@ -1454,18 +1472,19 @@ def agent(
                 while True:
                     try:
                         msg = await asyncio.wait_for(bus.consume_outbound(), timeout=1.0)
+                        event = outbound_event_from_message(msg)
 
-                        if msg.metadata.get("_stream_delta"):
+                        if isinstance(event, StreamDeltaEvent):
                             if renderer:
                                 await renderer.on_delta(msg.content)
                             continue
-                        if msg.metadata.get("_stream_end"):
+                        if isinstance(event, StreamEndEvent):
                             if renderer:
                                 await renderer.on_end(
-                                    resuming=msg.metadata.get("_resuming", False),
+                                    resuming=event.resuming,
                                 )
                             continue
-                        if msg.metadata.get("_streamed"):
+                        if isinstance(event, StreamedResponseEvent):
                             turn_done.set()
                             continue
 
@@ -1480,7 +1499,7 @@ def agent(
 
                         if not turn_done.is_set():
                             if msg.content:
-                                turn_response.append((msg.content, dict(msg.metadata or {})))
+                                turn_response.append(msg)
                             turn_done.set()
                         elif msg.content:
                             await _print_interactive_response(
@@ -1533,8 +1552,10 @@ def agent(
                         await turn_done.wait()
 
                         if turn_response:
-                            content, meta = turn_response[0]
+                            response_msg = turn_response[0]
-                            if content and not meta.get("_streamed"):
+                            content = response_msg.content
+                            meta = response_msg.metadata
+                            if content and not isinstance(response_msg.event, StreamedResponseEvent):
                                 if renderer:
                                     await renderer.close()
                                 print_kwargs: dict[str, Any] = {}
@@ -1744,6 +1765,11 @@ _PROVIDER_DISPLAY: dict[str, str] = {
     "github_copilot": "GitHub Copilot",
 }
 
+_OAUTH_PROVIDER_DEFAULT_MODELS: dict[str, str] = {
+    "openai_codex": "openai-codex/gpt-5.4-mini",
+    "github_copilot": "github-copilot/gpt-5.4-mini",
+}
+
 
 def _register_login(name: str):
     """Register an OAuth login handler."""
@@ -1775,9 +1801,51 @@ def _resolve_oauth_provider(provider: str):
     return spec
 
 
+def _set_oauth_provider_as_main(
+    provider_name: str,
+    *,
+    model: str | None = None,
+    config_path: str | None = None,
+) -> None:
+    """Persist an OAuth provider as the active agent provider."""
+    from nanobot.config.loader import get_config_path, load_config, save_config, set_config_path
+
+    resolved_config_path = Path(config_path).expanduser().resolve() if config_path else None
+    if resolved_config_path is not None:
+        set_config_path(resolved_config_path)
+        console.print(f"[dim]Using config: {resolved_config_path}[/dim]")
+
+    config = load_config(resolved_config_path)
+    selected_model = (model or "").strip() or _OAUTH_PROVIDER_DEFAULT_MODELS[provider_name]
+    config.agents.defaults.model_preset = None
+    config.agents.defaults.provider = provider_name
+    config.agents.defaults.model = selected_model
+    save_config(config, resolved_config_path)
+
+    saved_path = resolved_config_path or get_config_path()
+    console.print(
+        f"[green]✓ Set {provider_name.replace('_', '-')} as the main provider[/green]  "
+        f"[dim]{selected_model}[/dim]"
+    )
+    console.print(f"[dim]Saved: {saved_path}[/dim]")
+
+
 @provider_app.command("login")
 def provider_login(
     provider: str = typer.Argument(..., help="OAuth provider (e.g. 'openai-codex', 'github-copilot')"),
+    set_main: bool = typer.Option(
+        False,
+        "--set-main",
+        "--main",
+        help="Set this OAuth provider as the active agent provider after login",
+    ),
+    model: str | None = typer.Option(
+        None,
+        "--model",
+        "-m",
+        help="Model to use when setting this provider as the active provider",
+    ),
+    config: str | None = typer.Option(None, "--config", "-c", help="Path to config file"),
 ):
     """Authenticate with an OAuth provider."""
     spec = _resolve_oauth_provider(provider)
@@ -1789,6 +1857,8 @@ def provider_login(
 
     console.print(f"{__logo__} OAuth Login - {spec.label}\n")
     handler()
+    if set_main or model:
+        _set_oauth_provider_as_main(spec.name, model=model, config_path=config)
 
 
 @provider_app.command("logout")
@@ -1812,14 +1882,23 @@ def _login_openai_codex() -> None:
     try:
         from oauth_cli_kit import get_token, login_oauth_interactive
 
+        from nanobot.config.loader import load_config, resolve_config_env_vars
+
+        proxy = None
+        try:
+            proxy = resolve_config_env_vars(load_config()).providers.openai_codex.proxy or None
+        except ValueError as e:
+            console.print(f"[red]{e}[/red]")
+            raise typer.Exit(1) from e
         token = None
         with suppress(Exception):
-            token = get_token()
+            token = get_token(proxy=proxy)
         if not (token and token.access):
             console.print("[cyan]Starting interactive OAuth login...[/cyan]\n")
             token = login_oauth_interactive(
                 print_fn=lambda s: console.print(s),
                 prompt_fn=lambda s: typer.prompt(s),
+                proxy=proxy,
             )
         if not (token and token.access):
             console.print("[red]✗ Authentication failed[/red]")

nanobot/command/builtin.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import asyncio
 import os
+import subprocess
 import sys
 import time
 from contextlib import suppress
@@ -50,7 +51,7 @@ BUILTIN_COMMAND_SPECS: tuple[BuiltinCommandSpec, ...] = (
     BuiltinCommandSpec(
         "/restart",
         "Restart nanobot",
-        "Restart the bot process in place.",
+        "Restart the bot process.",
         "rotate-cw",
     ),
     BuiltinCommandSpec(
@@ -130,6 +131,15 @@ async def cmd_stop(ctx: CommandContext) -> OutboundMessage:
     loop = ctx.loop
     msg = ctx.msg
     total = await loop._cancel_active_tasks(ctx.key)
+    # Also drain pending queue to prevent mid-turn injection deadlock
+    pending = loop._pending_queues.pop(ctx.key, None)
+    if pending is not None:
+        while not pending.empty():
+            try:
+                pending.get_nowait()
+                total += 1
+            except Exception:
+                break
     content = f"Stopped {total} task(s)." if total else "No active task to stop."
     return OutboundMessage(
         channel=msg.channel, chat_id=msg.chat_id, content=content,
@@ -138,7 +148,7 @@ async def cmd_stop(ctx: CommandContext) -> OutboundMessage:
 
 
 async def cmd_restart(ctx: CommandContext) -> OutboundMessage:
-    """Restart the process in-place via os.execv."""
+    """Restart the process."""
     msg = ctx.msg
     set_restart_notice_to_env(
         channel=msg.channel,
@@ -148,7 +158,19 @@ async def cmd_restart(ctx: CommandContext) -> OutboundMessage:
 
     async def _do_restart():
         await asyncio.sleep(1)
-        os.execv(sys.executable, [sys.executable, "-m", "nanobot"] + sys.argv[1:])
+        argv = [sys.executable, "-m", "nanobot"] + sys.argv[1:]
+        mode = getattr(ctx.loop, "restart_mode", "auto") or "auto"
+        if mode == "auto":
+            mode = "spawn" if sys.platform == "win32" else "exec"
+        if mode == "exec":
+            os.execv(sys.executable, argv)
+            return
+        if mode == "spawn":
+            kwargs = {}
+            if sys.platform == "win32":
+                kwargs["creationflags"] = subprocess.CREATE_NEW_PROCESS_GROUP
+            subprocess.Popen(argv, **kwargs)
+        os._exit(0)
 
     asyncio.create_task(_do_restart())
     return OutboundMessage(

nanobot/config/loader.py

@@ -7,6 +7,7 @@ from pathlib import Path
 from typing import Any
 
 import pydantic
+from loguru import logger
 from pydantic import BaseModel
 
 from nanobot.config.schema import Config, _resolve_tool_config_refs
@@ -79,6 +80,10 @@ def save_config(config: Config, config_path: Path | None = None) -> None:
     path.parent.mkdir(parents=True, exist_ok=True)
 
     data = config.model_dump(mode="json", by_alias=True)
+    if config.providers.openai_codex.proxy is not None:
+        data.setdefault("providers", {})["openaiCodex"] = {
+            "proxy": config.providers.openai_codex.proxy,
+        }
 
     with open(path, "w", encoding="utf-8") as f:
         json.dump(data, f, indent=2, ensure_ascii=False)
@@ -152,6 +157,23 @@ def _env_replace(match: re.Match[str]) -> str:
 
 def _migrate_config(data: dict) -> dict:
     """Migrate old config formats to current."""
+    agents = data.get("agents", {})
+    defaults = agents.get("defaults", {}) if isinstance(agents, dict) else {}
+    if isinstance(defaults, dict):
+        had_legacy_max_messages = (
+            "maxMessages" in defaults or "max_messages" in defaults
+        )
+        defaults.pop("maxMessages", None)
+        defaults.pop("max_messages", None)
+        if had_legacy_max_messages:
+            # TODO(next version): Remove this legacy cleanup branch; the schema
+            # will silently ignore this field once the warning grace period ends.
+            logger.warning(
+                "agents.defaults.maxMessages/max_messages is legacy and ignored; "
+                "replay max messages is now an internal safety cap. Remove it from "
+                "config. This compatibility warning will be removed in the next version."
+            )
+
     # Move tools.exec.restrictToWorkspace → tools.restrictToWorkspace
     tools = data.get("tools", {})
     exec_cfg = tools.get("exec", {})

nanobot/config/schema.py

@@ -154,10 +154,6 @@ class AgentDefaults(Base):
         validation_alias=AliasChoices("idleCompactAfterMinutes", "sessionTtlMinutes"),
         serialization_alias="idleCompactAfterMinutes",
     )  # Auto-compact idle threshold in minutes (0 = disabled)
-    max_messages: int = Field(
-        default=120,
-        ge=0,
-    )  # Max messages to replay from session history (0 = use default 120, respects token budget)
     consolidation_ratio: float = Field(
         default=0.5,
         ge=0.1,
@@ -183,6 +179,7 @@ class ProviderConfig(Base):
     extra_headers: dict[str, str] | None = None  # Custom headers (e.g. APP-Code for AiHubMix)
     extra_body: dict[str, Any] | None = None  # Extra provider request fields; shape depends on provider/API surface
     extra_query: dict[str, str] | None = None  # Extra query params (e.g. api-version for Azure-style gateways)
+    proxy: str | None = None  # OpenAI-compatible/Codex HTTP proxy URL
     thinking_style: str | None = None  # Thinking/reasoning style for custom providers
 
     # Valid values mirror the keys of _THINKING_STYLE_MAP in
@@ -310,6 +307,18 @@ class ApiConfig(Base):
     host: str = "127.0.0.1"  # Safer default: local-only bind.
     port: int = 8900
     timeout: float = 120.0  # Per-request timeout in seconds.
+    api_key: str = Field(default="", repr=False)
+
+    @model_validator(mode="after")
+    def wildcard_host_requires_auth(self) -> "ApiConfig":
+        if self.host not in ("0.0.0.0", "::"):
+            return self
+        if self.api_key.strip():
+            return self
+        raise ValueError(
+            "host is 0.0.0.0 (all interfaces) but api_key is not set "
+            "- set api.api_key to prevent unauthenticated access"
+        )
 
 
 class GatewayConfig(Base):
@@ -317,6 +326,7 @@ class GatewayConfig(Base):
 
     host: str = "127.0.0.1"  # Safer default: local-only bind.
     port: int = 18790
+    restart_mode: Literal["auto", "exec", "spawn", "exit"] = "auto"
     heartbeat: HeartbeatConfig = Field(default_factory=HeartbeatConfig)
 
 

nanobot/cron/service.py

@@ -1,6 +1,7 @@
 """Cron service for scheduling agent tasks."""
 
 import asyncio
+import errno
 import json
 import os
 import time
@@ -357,6 +358,25 @@ class CronService:
 
         return self._store
 
+    def _require_store(self) -> CronStore:
+        """Return a usable store or raise a clear error.
+
+        ``_load_store`` deliberately returns ``None`` when the first load sees
+        a corrupt on-disk store and no previous in-memory snapshot exists.  The
+        public API requires a concrete store object before touching
+        ``store.jobs``; raising here keeps callers from seeing an accidental
+        ``AttributeError`` and, more importantly, prevents follow-up saves from
+        treating a corrupt store as an empty one.
+        """
+        store = self._load_store()
+        if store is None:
+            raise RuntimeError(
+                f"cron store at {self.store_path} could not be loaded and was preserved "
+                "as a .corrupt-<ts> backup; refusing to operate to avoid overwriting "
+                "scheduled jobs. Inspect the corrupt backup and restore jobs.json manually."
+            )
+        return store
+
     def _save_store(self) -> None:
         """Save jobs to disk."""
         if not self._store:
@@ -437,11 +457,15 @@ class CronService:
             os.replace(tmp_path, path)
             # fsync the parent directory so the rename itself is durable.
             # Skip on Windows where opening a directory raises PermissionError;
-            # NTFS journals metadata synchronously so this is a no-op there.
+            # some shared filesystems reject directory fsync with EINVAL.
             with suppress(PermissionError):
                 fd = os.open(str(path.parent), os.O_RDONLY)
+                try:
                     try:
                         os.fsync(fd)
+                    except OSError as exc:
+                        if exc.errno != errno.EINVAL:
+                            raise
                 finally:
                     os.close(fd)
         except BaseException:
@@ -622,7 +646,7 @@ class CronService:
 
     def list_jobs(self, include_disabled: bool = False) -> list[CronJob]:
         """List all jobs."""
-        store = self._load_store()
+        store = self._require_store()
         jobs = store.jobs if include_disabled else [j for j in store.jobs if j.enabled]
         return sorted(jobs, key=lambda j: j.state.next_run_at_ms or float('inf'))
 
@@ -684,7 +708,7 @@ class CronService:
         _normalize_agent_turn_job(job)
         self._enforce_agent_binding(job)
         if self._running:
-            store = self._load_store()
+            store = self._require_store()
             store.jobs.append(job)
             self._save_store()
             self._arm_timer()
@@ -696,7 +720,7 @@ class CronService:
 
     def register_system_job(self, job: CronJob) -> CronJob:
         """Register an internal system job (idempotent on restart)."""
-        store = self._load_store()
+        store = self._require_store()
         now = _now_ms()
         job.state = CronJobState(next_run_at_ms=_compute_next_run(job.schedule, now))
         job.created_at_ms = now
@@ -710,7 +734,7 @@ class CronService:
 
     def remove_job(self, job_id: str) -> Literal["removed", "protected", "not_found"]:
         """Remove a job by ID, unless it is a protected system job."""
-        store = self._load_store()
+        store = self._require_store()
         job = next((j for j in store.jobs if j.id == job_id), None)
         if job is None:
             return "not_found"
@@ -735,7 +759,7 @@ class CronService:
 
     def enable_job(self, job_id: str, enabled: bool = True) -> CronJob | None:
         """Enable or disable a job."""
-        store = self._load_store()
+        store = self._require_store()
         for job in store.jobs:
             if job.id == job_id:
                 job.enabled = enabled
@@ -770,7 +794,7 @@ class CronService:
         For ``channel`` and ``to``, pass an explicit value (including ``None``)
         to update; omit (sentinel ``...``) to leave unchanged.
         """
-        store = self._load_store()
+        store = self._require_store()
         job = next((j for j in store.jobs if j.id == job_id), None)
         if job is None:
             return "not_found"
@@ -815,7 +839,7 @@ class CronService:
         was_running = self._running
         self._running = True
         try:
-            store = self._load_store()
+            store = self._require_store()
             for job in store.jobs:
                 if job.id == job_id:
                     if self._is_unbound_agent_job(job):
@@ -835,12 +859,12 @@ class CronService:
 
     def get_job(self, job_id: str) -> CronJob | None:
         """Get a job by ID."""
-        store = self._load_store()
+        store = self._require_store()
         return next((j for j in store.jobs if j.id == job_id), None)
 
     def status(self) -> dict:
         """Get service status."""
-        store = self._load_store()
+        store = self._require_store()
         return {
             "enabled": self._running,
             "jobs": len(store.jobs),

nanobot/providers/anthropic_provider.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import asyncio
 import hashlib
+import json
 import re
 import secrets
 import string
@@ -275,7 +276,19 @@ class AnthropicProvider(LLMProvider):
             blocks.append({"type": "text", "text": content})
         elif isinstance(content, list):
             for item in content:
-                blocks.append(item if isinstance(item, dict) else {"type": "text", "text": str(item)})
+                if isinstance(item, dict):
+                    if not item.get("type"):
+                        # Anthropic requires every content block to declare a "type".
+                        # A tool that returned a bare dict lands here; coerce it to
+                        # a text block instead of emitting one that the API rejects.
+                        blocks.append({
+                            "type": "text",
+                            "text": AnthropicProvider._stringify_typeless_block(item),
+                        })
+                    else:
+                        blocks.append(item)
+                else:
+                    blocks.append({"type": "text", "text": str(item)})
 
         for tc in msg.get("tool_calls") or []:
             if not isinstance(tc, dict):
@@ -315,11 +328,18 @@ class AnthropicProvider(LLMProvider):
                 # A tool that returned a bare dict (or a list of dicts) lands
                 # here; coerce it to a text block instead of emitting a block
                 # the API rejects with "content.0.type: Field required".
-                result.append({"type": "text", "text": str(item)})
+                result.append({
+                    "type": "text",
+                    "text": AnthropicProvider._stringify_typeless_block(item),
+                })
                 continue
             result.append(item)
         return result or "(empty)"
 
+    @staticmethod
+    def _stringify_typeless_block(block: dict[str, Any]) -> str:
+        return json.dumps(block, ensure_ascii=False, sort_keys=True, default=str)
+
     @staticmethod
     def _convert_image_block(block: dict[str, Any]) -> dict[str, Any] | None:
         """Convert OpenAI image_url block to Anthropic image block."""

nanobot/providers/base.py

@@ -54,6 +54,18 @@ class ToolCallRequest:
     provider_specific_fields: dict[str, Any] | None = None
     function_provider_specific_fields: dict[str, Any] | None = None
 
+    def has_valid_name(self) -> bool:
+        """Whether this call carries a usable (non-empty string) tool name.
+
+        ToolCallRequest.name is typed ``str`` but not enforced at runtime: a
+        model/gateway can emit a degenerate call with ``name=None`` or ``""``.
+        Such a call cannot be executed and, if persisted and replayed, makes
+        upstream APIs reject the whole request (e.g. Anthropic-style
+        ``messages.content.N.tool_use.name: Input should be a valid string``),
+        which permanently wedges the session.
+        """
+        return isinstance(self.name, str) and bool(self.name)
+
     def to_openai_tool_call(self) -> dict[str, Any]:
         """Serialize to an OpenAI-style tool_call payload."""
         arguments = (

nanobot/providers/factory.py

@@ -58,6 +58,11 @@ def _make_provider_core(
     if spec and spec.is_transcription_only:
         raise ValueError(f"Provider '{provider_name}' only supports transcription.")
     backend = spec.backend if spec else "openai_compat"
+    if p and p.proxy and backend not in {"openai_compat", "openai_codex"}:
+        raise ValueError(
+            f"providers.{provider_name}.proxy is only supported for "
+            "OpenAI-compatible providers and OpenAI Codex."
+        )
 
     if backend == "azure_openai":
         if not p or not p.api_base:
@@ -79,7 +84,10 @@ def _make_provider_core(
     if backend == "openai_codex":
         from nanobot.providers.openai_codex_provider import OpenAICodexProvider
 
-        provider = OpenAICodexProvider(default_model=model)
+        provider = OpenAICodexProvider(
+            default_model=model,
+            proxy=getattr(p, "proxy", None) if p else None,
+        )
     elif backend == "azure_openai":
         from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
 
@@ -124,6 +132,7 @@ def _make_provider_core(
             extra_body=p.extra_body if p else None,
             api_type=p.api_type if p and provider_name == "openai" else "auto",
             extra_query=p.extra_query if p else None,
+            proxy=p.proxy if p else None,
         )
 
     provider.generation = resolved.to_generation_settings()
@@ -218,6 +227,7 @@ def provider_signature(
             fallback.temperature,
             fallback.reasoning_effort,
             fallback.context_window_tokens,
+            getattr(fp, "proxy", None) if fp else None,
         )
 
     provider_name = config.get_provider_name(resolved.model, preset=resolved)
@@ -237,6 +247,7 @@ def provider_signature(
         resolved.temperature,
         resolved.reasoning_effort,
         resolved.context_window_tokens,
+        getattr(p, "proxy", None) if p else None,
         tuple(_fallback_signature(fallback) for fallback in fallback_presets),
     )
 

nanobot/providers/github_copilot_provider.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import os
 import time
 import webbrowser
 from collections.abc import Awaitable, Callable
@@ -29,6 +30,12 @@ _EXPIRY_SKEW_SECONDS = 60
 _LONG_LIVED_TOKEN_SECONDS = 315360000
 
 
+def _resolve(env_var: str, default: str) -> str:
+    """Allow GitHub Enterprise / Copilot for Business deployments to override defaults via env."""
+    value = os.environ.get(env_var)
+    return value.strip() if value and value.strip() else default
+
+
 def get_storage() -> FileTokenStorage:
     return FileTokenStorage(
         token_filename=TOKEN_FILENAME,
@@ -68,11 +75,16 @@ def login_github_copilot(
     printer = print_fn or print
     timeout = httpx.Timeout(20.0, connect=20.0)
 
+    client_id = _resolve("NANOBOT_GITHUB_COPILOT_CLIENT_ID", GITHUB_COPILOT_CLIENT_ID)
+    device_code_url = _resolve("NANOBOT_GITHUB_DEVICE_CODE_URL", DEFAULT_GITHUB_DEVICE_CODE_URL)
+    access_token_url = _resolve("NANOBOT_GITHUB_ACCESS_TOKEN_URL", DEFAULT_GITHUB_ACCESS_TOKEN_URL)
+    user_url = _resolve("NANOBOT_GITHUB_USER_URL", DEFAULT_GITHUB_USER_URL)
+
     with httpx.Client(timeout=timeout, follow_redirects=True, trust_env=True) as client:
         response = client.post(
-            DEFAULT_GITHUB_DEVICE_CODE_URL,
+            device_code_url,
             headers={"Accept": "application/json", "User-Agent": USER_AGENT},
-            data={"client_id": GITHUB_COPILOT_CLIENT_ID, "scope": GITHUB_COPILOT_SCOPE},
+            data={"client_id": client_id, "scope": GITHUB_COPILOT_SCOPE},
         )
         response.raise_for_status()
         payload = response.json()
@@ -96,10 +108,10 @@ def login_github_copilot(
         token_expires_in = _LONG_LIVED_TOKEN_SECONDS
         while time.time() < deadline:
             poll = client.post(
-                DEFAULT_GITHUB_ACCESS_TOKEN_URL,
+                access_token_url,
                 headers={"Accept": "application/json", "User-Agent": USER_AGENT},
                 data={
-                    "client_id": GITHUB_COPILOT_CLIENT_ID,
+                    "client_id": client_id,
                     "device_code": device_code,
                     "grant_type": "urn:ietf:params:oauth:grant-type:device_code",
                 },
@@ -132,7 +144,7 @@ def login_github_copilot(
             raise RuntimeError("GitHub device flow timed out.")
 
         user = client.get(
-            DEFAULT_GITHUB_USER_URL,
+            user_url,
             headers={
                 "Authorization": f"Bearer {access_token}",
                 "Accept": "application/vnd.github+json",
@@ -164,7 +176,7 @@ class GitHubCopilotProvider(OpenAICompatProvider):
         self._copilot_expires_at: float = 0.0
         super().__init__(
             api_key="no-key",
-            api_base=DEFAULT_COPILOT_BASE_URL,
+            api_base=_resolve("NANOBOT_COPILOT_BASE_URL", DEFAULT_COPILOT_BASE_URL),
             default_model=default_model,
             extra_headers={
                 "Editor-Version": EDITOR_VERSION,
@@ -186,7 +198,7 @@ class GitHubCopilotProvider(OpenAICompatProvider):
         timeout = httpx.Timeout(20.0, connect=20.0)
         async with httpx.AsyncClient(timeout=timeout, follow_redirects=True, trust_env=True) as client:
             response = await client.get(
-                DEFAULT_COPILOT_TOKEN_URL,
+                _resolve("NANOBOT_COPILOT_TOKEN_URL", DEFAULT_COPILOT_TOKEN_URL),
                 headers=_copilot_headers(github_token.access),
             )
             response.raise_for_status()

nanobot/providers/openai_codex_provider.py

@@ -33,9 +33,14 @@ class OpenAICodexProvider(LLMProvider):
 
     supports_progress_deltas = True
 
-    def __init__(self, default_model: str = "openai-codex/gpt-5.1-codex"):
+    def __init__(
+        self,
+        default_model: str = "openai-codex/gpt-5.1-codex",
+        proxy: str | None = None,
+    ):
         super().__init__(api_key=None, api_base=None)
         self.default_model = default_model
+        self.proxy = proxy or None
 
     async def _call_codex(
         self,
@@ -52,9 +57,6 @@ class OpenAICodexProvider(LLMProvider):
         model = model or self.default_model
         system_prompt, input_items = convert_messages(messages)
 
-        token = await asyncio.to_thread(get_codex_token)
-        headers = _build_headers(token.account_id, token.access)
-
         body: dict[str, Any] = {
             "model": _strip_model_prefix(model),
             "store": False,
@@ -74,9 +76,13 @@ class OpenAICodexProvider(LLMProvider):
             body["tools"] = convert_tools(tools)
 
         try:
+            token = await asyncio.to_thread(get_codex_token, proxy=self.proxy)
+            headers = _build_headers(token.account_id, token.access)
+
             try:
                 content, tool_calls, finish_reason, usage, reasoning_content = await _request_codex(
                     DEFAULT_CODEX_URL, headers, body, verify=True,
+                    proxy=self.proxy,
                     on_content_delta=on_content_delta,
                     on_thinking_delta=on_thinking_delta,
                     on_tool_call_delta=on_tool_call_delta,
@@ -87,6 +93,7 @@ class OpenAICodexProvider(LLMProvider):
                 logger.warning("SSL verification failed for Codex API; retrying with verify=False")
                 content, tool_calls, finish_reason, usage, reasoning_content = await _request_codex(
                     DEFAULT_CODEX_URL, headers, body, verify=False,
+                    proxy=self.proxy,
                     on_content_delta=on_content_delta,
                     on_thinking_delta=on_thinking_delta,
                     on_tool_call_delta=on_tool_call_delta,
@@ -199,12 +206,17 @@ async def _request_codex(
     headers: dict[str, str],
     body: dict[str, Any],
     verify: bool,
+    proxy: str | None = None,
     on_content_delta: Callable[[str], Awaitable[None]] | None = None,
     on_thinking_delta: Callable[[str], Awaitable[None]] | None = None,
     on_tool_call_delta: Callable[[dict[str, Any]], Awaitable[None]] | None = None,
 ) -> tuple[str, list[ToolCallRequest], str, dict[str, int], str | None]:
     idle_timeout_s = resolve_stream_idle_timeout_s()
-    async with httpx.AsyncClient(timeout=idle_timeout_s, verify=verify) as client:
+    client_kwargs: dict[str, Any] = {"timeout": idle_timeout_s, "verify": verify}
+    if proxy:
+        client_kwargs["proxy"] = proxy
+        client_kwargs["trust_env"] = False
+    async with httpx.AsyncClient(**client_kwargs) as client:
         async with client.stream("POST", url, headers=headers, json=body) as response:
             if response.status_code != 200:
                 text = await response.aread()

nanobot/providers/openai_compat_provider.py

@@ -358,6 +358,7 @@ class OpenAICompatProvider(LLMProvider):
         extra_body: dict[str, Any] | None = None,
         api_type: str = "auto",
         extra_query: dict[str, str] | None = None,
+        proxy: str | None = None,
     ):
         super().__init__(api_key, api_base)
         self.default_model = default_model
@@ -366,6 +367,7 @@ class OpenAICompatProvider(LLMProvider):
         self._extra_body = extra_body or {}
         self._api_type = api_type if spec and spec.name == "openai" else "auto"
         self._extra_query = extra_query or {}
+        self._proxy = proxy or None
 
         if api_key and spec and spec.env_key:
             self._setup_env(api_key, api_base)
@@ -396,7 +398,14 @@ class OpenAICompatProvider(LLMProvider):
 
         timeout_s = _openai_compat_timeout_s()
         http_client: httpx.AsyncClient | None = None
-        if self._is_local:
+        if self._proxy:
+            http_client = httpx.AsyncClient(
+                timeout=timeout_s,
+                proxy=self._proxy,
+                trust_env=False,
+                follow_redirects=True,
+            )
+        elif self._is_local:
             # Local model servers (Ollama, llama.cpp, vLLM) often close idle
             # HTTP connections before the client-side keepalive expires. When
             # two LLM calls happen seconds apart (e.g. heartbeat _decide then
@@ -1131,14 +1140,21 @@ class OpenAICompatProvider(LLMProvider):
                 if reasoning_content is None:
                     reasoning_content = m.get("reasoning_content")
 
+            # Deduplicate tool call IDs (same pattern as streaming path)
+            # Some providers reuse the same ID for parallel tool calls.
+            _seen_tc_ids: set[str] = set()
             parsed_tool_calls = []
             for tc in raw_tool_calls:
                 tc_map = self._maybe_mapping(tc) or {}
                 fn = self._maybe_mapping(tc_map.get("function")) or {}
                 args = parse_tool_arguments(fn.get("arguments", {}))
                 ec, prov, fn_prov = _extract_tc_extras(tc)
+                raw_id = str(tc_map.get("id") or _short_tool_id())
+                if not raw_id or raw_id in _seen_tc_ids:
+                    raw_id = _short_tool_id()
+                _seen_tc_ids.add(raw_id)
                 parsed_tool_calls.append(ToolCallRequest(
-                    id=str(tc_map.get("id") or _short_tool_id()),
+                    id=raw_id,
                     name=str(fn.get("name") or ""),
                     arguments=args,
                     extra_content=ec,

nanobot/providers/registry.py

@@ -32,6 +32,7 @@ class ProviderSpec:
     keywords: tuple[str, ...]  # model-name keywords for matching (lowercase)
     env_key: str  # env var for API key, e.g. "DASHSCOPE_API_KEY"
     display_name: str = ""  # shown in `nanobot status`
+    model_catalog: str = "auto"  # WebUI model-list source
 
     # which provider implementation to use
     # "openai_compat" | "anthropic" | "azure_openai" | "openai_codex" | "github_copilot" | "bedrock"
@@ -221,6 +222,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         keywords=("skywork", "skyclaw", "apifree"),
         env_key="SKYWORK_API_KEY",
         display_name="Skywork",
+        model_catalog="official",
         backend="openai_compat",
         env_extras=(("APIFREE_API_KEY", "{api_key}"),),
         is_gateway=True,

nanobot/session/manager.py

@@ -1,5 +1,6 @@
 """Session management for conversation history."""
 
+import base64
 import json
 import os
 import re
@@ -26,6 +27,8 @@ from nanobot.utils.helpers import (
 from nanobot.utils.subagent_channel_display import scrub_subagent_announce_body
 
 FILE_MAX_MESSAGES = 2000
+MIN_REPLAY_MAX_MESSAGES = 120
+REPLAY_TOKENS_PER_MESSAGE = 100
 _MESSAGE_TIME_PREFIX_RE = re.compile(r"^\[Message Time: [^\]]+\]\n?")
 _LOCAL_IMAGE_BREADCRUMB_RE = re.compile(r"^\[image: (?:/|~)[^\]]+\]\s*$")
 _TOOL_CALL_ECHO_RE = re.compile(r'^\s*(?:generate_image|message)\([^)]*\)\s*$')
@@ -42,6 +45,15 @@ _FORK_VOLATILE_METADATA_KEYS = {
 }
 
 
+def replay_max_messages_for_context(context_window_tokens: int | None) -> int:
+    if not context_window_tokens or context_window_tokens <= 0:
+        return FILE_MAX_MESSAGES
+    return min(
+        FILE_MAX_MESSAGES,
+        max(MIN_REPLAY_MAX_MESSAGES, context_window_tokens // REPLAY_TOKENS_PER_MESSAGE),
+    )
+
+
 def _sanitize_assistant_replay_text(content: str) -> str:
     """Remove internal replay artifacts that the model may have copied before.
 
@@ -98,6 +110,12 @@ def _metadata_title(metadata: Any) -> str:
     return strip_think(title)
 
 
+@dataclass
+class RetentionResult:
+    dropped: list[dict]
+    already_consolidated_count: int
+
+
 @dataclass
 class Session:
     """A conversation session."""
@@ -131,7 +149,7 @@ class Session:
 
     def get_history(
         self,
-        max_messages: int = 120,
+        max_messages: int = FILE_MAX_MESSAGES,
         *,
         max_tokens: int = 0,
         extend_to_user: bool = False,
@@ -142,7 +160,7 @@ class Session:
         token budget from the tail (``max_tokens``) when provided.
         """
         unconsolidated = self.messages[self.last_consolidated:]
-        max_messages = max_messages if max_messages > 0 else 120
+        max_messages = max_messages if max_messages > 0 else FILE_MAX_MESSAGES
         start_idx = recent_message_start_index(
             unconsolidated,
             max_messages,
@@ -277,22 +295,26 @@ class Session:
         max_messages: int,
         *,
         extend_to_user: bool = False,
-    ) -> tuple[list[dict], int]:
+    ) -> RetentionResult:
         """Keep a legal recent suffix, optionally extending it back to a user turn.
 
-        Returns ``(dropped, already_consolidated_count)`` where *dropped* is
+        Returns a RetentionResult with dropped messages and how many of those
-        the list of removed messages (in original order) and
+        were in the already-consolidated prefix. This method mutates
-        *already_consolidated_count* is how many of those were inside the
+        self.messages and self.last_consolidated in place.
-        pre-existing ``last_consolidated`` prefix and therefore do not need
-        raw archiving.
         """
         if max_messages <= 0:
             dropped = list(self.messages)
             lc = self.last_consolidated
             self.clear()
-            return dropped, min(lc, len(dropped))
+            return RetentionResult(
+                dropped=dropped,
+                already_consolidated_count=min(lc, len(dropped)),
+            )
         if len(self.messages) <= max_messages:
-            return [], 0
+            return RetentionResult(
+                dropped=[],
+                already_consolidated_count=0,
+            )
 
         original = list(self.messages)
         before_lc = self.last_consolidated
@@ -358,7 +380,10 @@ class Session:
         self.messages = retained
         self.last_consolidated = new_lc
         self.updated_at = datetime.now()
-        return dropped, already_consolidated
+        return RetentionResult(
+            dropped=dropped,
+            already_consolidated_count=already_consolidated,
+        )
 
     def enforce_file_cap(
         self,
@@ -369,17 +394,17 @@ class Session:
         if limit <= 0 or len(self.messages) <= limit:
             return
 
-        dropped, already_consolidated = self.retain_recent_legal_suffix(limit)
+        result = self.retain_recent_legal_suffix(limit)
-        if not dropped:
+        if not result.dropped:
             return
 
-        archive_chunk = dropped[already_consolidated:]
+        archive_chunk = result.dropped[result.already_consolidated_count:]
         if archive_chunk and on_archive:
             on_archive(archive_chunk)
         logger.info(
             "Session file cap hit for {}: dropped {}, raw-archived {}, kept {}",
             self.key,
-            len(dropped),
+            len(result.dropped),
             len(archive_chunk),
             len(self.messages),
         )
@@ -403,14 +428,53 @@ class SessionManager:
         """Public helper used by HTTP handlers to map an arbitrary key to a stable filename stem."""
         return safe_filename(key.replace(":", "_"))
 
+    @staticmethod
+    def _storage_key(key: str) -> str:
+        """Collision-resistant encoding for internal session storage filenames."""
+        return base64.urlsafe_b64encode(key.encode()).decode().rstrip("=")
+
+    @staticmethod
+    def _decode_storage_key(stem: str) -> str | None:
+        """Reverse _storage_key(): decode a base64url (no-padding) stem back to the original key."""
+        try:
+            # Restore padding stripped by rstrip("=")
+            padding = 4 - len(stem) % 4
+            if padding != 4:
+                stem += "=" * padding
+            return base64.urlsafe_b64decode(stem).decode("utf-8")
+        except Exception:
+            return None
+
     def _get_session_path(self, key: str) -> Path:
-        """Get the file path for a session."""
+        """Get the collision-resistant workspace path for a session."""
-        return self.sessions_dir / f"{self.safe_key(key)}.jsonl"
+        return self.sessions_dir / f"{self._storage_key(key)}.jsonl"
+
+    def _get_legacy_lossy_path(self, key: str) -> Path:
+        """Previous workspace session path using lossy ':' to '_' replacement."""
+        return self.sessions_dir / f"{safe_filename(key.replace(':', '_'))}.jsonl"
 
     def _get_legacy_session_path(self, key: str) -> Path:
         """Legacy global session path (~/.nanobot/sessions/)."""
         return self.legacy_sessions_dir / f"{self.safe_key(key)}.jsonl"
 
+    @staticmethod
+    def _stored_key_for_path(path: Path) -> str | None:
+        """Read the stored session key from a JSONL metadata row, if present."""
+        try:
+            with open(path, encoding="utf-8") as f:
+                for line in f:
+                    line = line.strip()
+                    if not line:
+                        continue
+                    data = json.loads(line)
+                    if data.get("_type") == "metadata":
+                        stored_key = data.get("key")
+                        return stored_key if isinstance(stored_key, str) else None
+                    return None
+        except Exception:
+            return None
+        return None
+
     def get_or_create(self, key: str) -> Session:
         """
         Get an existing session or create a new one.
@@ -435,13 +499,28 @@ class SessionManager:
         """Load a session from disk."""
         path = self._get_session_path(key)
         if not path.exists():
-            legacy_path = self._get_legacy_session_path(key)
+            fallback_paths = [
-            if legacy_path.exists():
+                (self._get_legacy_lossy_path(key), "legacy lossy path"),
+                (self._get_legacy_session_path(key), "legacy path"),
+            ]
+            for fallback_path, description in fallback_paths:
+                if not fallback_path.exists():
+                    continue
+                stored_key = self._stored_key_for_path(fallback_path)
+                if stored_key and stored_key != key:
+                    logger.info(
+                        "Skipping migration for {} from {} because it belongs to {}",
+                        key,
+                        description,
+                        stored_key,
+                    )
+                    continue
                 try:
-                    shutil.move(str(legacy_path), str(path))
+                    shutil.move(str(fallback_path), str(path))
-                    logger.info("Migrated session {} from legacy path", key)
+                    logger.info("Migrated session {} from {}", key, description)
                 except Exception:
                     logger.exception("Failed to migrate session {}", key)
+                break
 
         if not path.exists():
             return None
@@ -484,8 +563,9 @@ class SessionManager:
                 logger.info("Recovered session {} from corrupt file ({} messages)", key, len(repaired.messages))
             return repaired
 
-    def _repair(self, key: str) -> Session | None:
+    def _repair(self, key: str, *, path: Path | None = None) -> Session | None:
         """Attempt to recover a session from a corrupt JSONL file."""
+        if path is None:
             path = self._get_session_path(key)
         if not path.exists():
             return None
@@ -623,7 +703,11 @@ class SessionManager:
 
         Returns True if at least one JSONL file was found and unlinked.
         """
-        paths = [self._get_session_path(key), self._get_legacy_session_path(key)]
+        paths = [
+            self._get_session_path(key),
+            self._get_legacy_lossy_path(key),
+            self._get_legacy_session_path(key),
+        ]
         self.invalidate(key)
         deleted = False
         for path in paths:
@@ -784,7 +868,8 @@ class SessionManager:
         sessions = []
 
         for path in self.sessions_dir.glob("*.jsonl"):
-            fallback_key = path.stem.replace("_", ":", 1)
+            decoded = self._decode_storage_key(path.stem)
+            fallback_key = decoded or path.stem.replace("_", ":", 1)
             try:
                 # Read the metadata line and a small preview for session lists.
                 with open(path, encoding="utf-8") as f:
@@ -792,7 +877,7 @@ class SessionManager:
                     if first_line:
                         data = json.loads(first_line)
                         if data.get("_type") == "metadata":
-                            key = data.get("key") or path.stem.replace("_", ":", 1)
+                            key = data.get("key") or fallback_key
                             metadata = data.get("metadata", {})
                             title = _metadata_title(metadata)
                             preview = ""
@@ -833,7 +918,7 @@ class SessionManager:
                                 }
                             )
             except Exception:
-                repaired = self._repair(fallback_key)
+                repaired = self._repair(fallback_key, path=path)
                 if repaired is not None:
                     sessions.append(
                         {

nanobot/session/turn_continuation.py

@@ -29,10 +29,6 @@ _GOAL_CONTINUATION_SENDER = "system:continuation"
 _GOAL_CONTINUATION_ROUNDS_KEY = "_sustained_goal_continuation_rounds"
 _MAX_GOAL_CONTINUATION_ROUNDS = 12
 _STRIPPED_INBOUND_META_KEYS = {
-    "_stream_id",
-    "_stream_delta",
-    "_stream_end",
-    "_resuming",
     INTERNAL_CONTINUATION_PENDING_META,
 }
 

nanobot/session/webui_turns.py

@@ -11,7 +11,15 @@ from typing import Any
 from loguru import logger
 
 from nanobot.bus import progress as bus_progress
-from nanobot.bus.events import InboundMessage, OutboundMessage
+from nanobot.bus.events import InboundMessage
+from nanobot.bus.outbound_events import (
+    GoalStateSyncEvent,
+    GoalStatusEvent,
+    RuntimeModelUpdatedEvent,
+    SessionUpdatedEvent,
+    TurnEndEvent,
+    outbound_message_for_event,
+)
 from nanobot.bus.queue import MessageBus
 from nanobot.bus.runtime_events import (
     GoalStateChanged,
@@ -206,26 +214,22 @@ async def publish_turn_run_status(
     if msg.channel != "websocket":
         return
     cid = str(msg.chat_id)
-    meta: dict[str, Any] = {
+    started_at_event: float | None = None
-        **dict(msg.metadata or {}),
-        "_goal_status": True,
-        "goal_status": status,
-    }
     if status == "running":
         if isinstance(started_at, int | float) and started_at > 0:
             t0 = float(started_at)
         else:
             t0 = time.time()
-        meta["started_at"] = t0
+        started_at_event = t0
         _WEBSOCKET_TURN_WALL_STARTED_AT[cid] = t0
     else:
         _WEBSOCKET_TURN_WALL_STARTED_AT.pop(cid, None)
     await bus.publish_outbound(
-        OutboundMessage(
+        outbound_message_for_event(
             channel=msg.channel,
             chat_id=cid,
-            content="",
+            event=GoalStatusEvent(status=status, started_at=started_at_event),
-            metadata=meta,
+            metadata=msg.metadata,
         ),
     )
 
@@ -318,28 +322,25 @@ class WebuiTurnCoordinator:
         if not cid:
             return
         await self.bus.publish_outbound(
-            OutboundMessage(
+            outbound_message_for_event(
                 channel=event.context.channel,
                 chat_id=cid,
-                content="",
+                event=GoalStateSyncEvent(
-                metadata={
+                    goal_state=goal_state_ws_blob(event.session_metadata),
-                    "_goal_state_sync": True,
+                ),
-                    "goal_state": goal_state_ws_blob(event.session_metadata),
+                metadata=event.context.metadata,
-                },
             ),
         )
 
     async def _handle_runtime_model_changed(self, event: RuntimeModelChanged) -> None:
         await self.bus.publish_outbound(
-            OutboundMessage(
+            outbound_message_for_event(
                 channel="websocket",
                 chat_id="*",
-                content="",
+                event=RuntimeModelUpdatedEvent(
-                metadata={
+                    model=event.model,
-                    "_runtime_model_updated": True,
+                    model_preset=event.model_preset,
-                    "model": event.model,
+                ),
-                    "model_preset": event.model_preset,
-                },
             )
         )
 
@@ -374,17 +375,18 @@ class WebuiTurnCoordinator:
         if msg.channel != "websocket":
             return
 
-        turn_metadata: dict[str, Any] = {**msg.metadata, "_turn_end": True}
-        if latency_ms is not None:
-            turn_metadata["latency_ms"] = int(latency_ms)
         session = self.sessions.get_or_create(session_key)
-        turn_metadata["goal_state"] = goal_state_ws_blob(session.metadata)
+        await self.bus.publish_outbound(
-        await self.bus.publish_outbound(OutboundMessage(
+            outbound_message_for_event(
                 channel=msg.channel,
                 chat_id=msg.chat_id,
-            content="",
+                event=TurnEndEvent(
-            metadata=turn_metadata,
+                    latency_ms=latency_ms,
-        ))
+                    goal_state=goal_state_ws_blob(session.metadata),
+                ),
+                metadata=msg.metadata,
+            )
+        )
         self._schedule_title_update(msg, session_key=session_key)
 
     def _schedule_title_update(self, msg: InboundMessage, *, session_key: str) -> None:
@@ -404,16 +406,11 @@ class WebuiTurnCoordinator:
                 model=title_llm.model,
             )
             if generated:
-                await self.bus.publish_outbound(OutboundMessage(
+                await self._publish_session_metadata_updated(
                     channel=msg.channel,
                     chat_id=msg.chat_id,
-                    content="",
+                    metadata=msg.metadata,
-                    metadata={
+                )
-                        **msg.metadata,
-                        "_session_updated": True,
-                        "_session_update_scope": "metadata",
-                    },
-                ))
 
         self.schedule_background(_generate_title_and_notify())
 
@@ -438,15 +435,26 @@ class WebuiTurnCoordinator:
                 model=title_llm.model,
             )
             if generated:
-                await self.bus.publish_outbound(OutboundMessage(
+                await self._publish_session_metadata_updated(
                     channel=event.context.channel,
                     chat_id=event.context.chat_id,
-                    content="",
+                    metadata=event.context.metadata,
-                    metadata={
+                )
-                        **event.context.metadata,
-                        "_session_updated": True,
-                        "_session_update_scope": "metadata",
-                    },
-                ))
 
         self.schedule_background(_generate_title_and_notify())
+
+    async def _publish_session_metadata_updated(
+        self,
+        *,
+        channel: str,
+        chat_id: str,
+        metadata: dict[str, Any],
+    ) -> None:
+        await self.bus.publish_outbound(
+            outbound_message_for_event(
+                channel=channel,
+                chat_id=chat_id,
+                event=SessionUpdatedEvent(scope="metadata"),
+                metadata=metadata,
+            )
+        )

nanobot/utils/file_edit_events.py

@@ -529,6 +529,9 @@ class StreamingFileEditTracker:
         """Keep final start/end events keyed to any earlier streamed placeholder."""
         used_canonicals: set[str] = set()
         for tool_call in final_tool_calls:
+            name = getattr(tool_call, "name", None)
+            if not is_file_edit_tool(name):
+                continue
             canonical = self.canonical_call_id_for(tool_call)
             if canonical and canonical not in used_canonicals:
                 try:

nanobot/utils/tool_hints.py

@@ -35,10 +35,15 @@ def format_tool_hints(tool_calls: list, max_length: int = 40) -> str:
 
     formatted = []
     for tc in tool_calls:
-        fmt = _TOOL_FORMATS.get(tc.name)
+        name = getattr(tc, "name", None)
+        if not isinstance(name, str) or not name:
+            # Degenerate/malformed tool call (e.g. a model emits name=None);
+            # skip it instead of raising AttributeError on the whole turn.
+            continue
+        fmt = _TOOL_FORMATS.get(name)
         if fmt:
             formatted.append(_fmt_known(tc, fmt, max_length))
-        elif tc.name.startswith("mcp_"):
+        elif name.startswith("mcp_"):
             formatted.append(_fmt_mcp(tc, max_length))
         else:
             formatted.append(_fmt_fallback(tc, max_length))

nanobot/webui/session_list_index.py

@@ -26,10 +26,11 @@ from nanobot.session.manager import (
     _metadata_title,
 )
 
-_INDEX_VERSION = 1
+_INDEX_VERSION = 2
 _INDEX_FILENAME = ".webui_session_index.json"
 _WEBUI_ACTIVITY_MTIME_NS = "webui_activity_mtime_ns"
 _WEBUI_ACTIVITY_SIZE = "webui_activity_size"
+_VISIBLE_TRANSCRIPT_ROLES = {"user", "assistant"}
 
 
 def list_webui_sessions(session_manager: SessionManager) -> list[dict[str, Any]]:
@@ -214,14 +215,45 @@ def _latest_updated_at(stored: str | None, activity: str | None) -> str | None:
     return stored
 
 
+def _visible_message_timestamp(item: dict[str, Any]) -> str | None:
+    if item.get(CRON_HISTORY_META) is True:
+        return None
+    if item.get("role") not in _VISIBLE_TRANSCRIPT_ROLES:
+        return None
+    timestamp = item.get("timestamp")
+    return timestamp if isinstance(timestamp, str) else None
+
+
+def _last_visible_message_at(messages: list[dict[str, Any]]) -> str | None:
+    latest: str | None = None
+    for item in messages:
+        timestamp = _visible_message_timestamp(item)
+        if timestamp is not None:
+            latest = _latest_updated_at(latest, timestamp)
+    return latest
+
+
+def _visible_activity_updated_at(
+    stored: str | None,
+    visible_message_at: str | None,
+    webui_activity: str | None,
+) -> str | None:
+    return _latest_updated_at(visible_message_at, webui_activity) or stored
+
+
 def _indexed_row_for_session(session: Session, path: Path) -> dict[str, Any]:
     signature = _file_signature(path)
     activity_signature = _webui_activity_signature(session.key)
     activity_updated_at = _webui_activity_updated_at(activity_signature)
+    visible_message_at = _last_visible_message_at(session.messages)
     return {
         "key": session.key,
         "created_at": session.created_at.isoformat(),
-        "updated_at": _latest_updated_at(session.updated_at.isoformat(), activity_updated_at),
+        "updated_at": _visible_activity_updated_at(
+            session.updated_at.isoformat(),
+            visible_message_at,
+            activity_updated_at,
+        ),
         "title": _metadata_title(session.metadata),
         "preview": _preview_from_messages(session.messages),
         "file": path.name,
@@ -232,7 +264,8 @@ def _indexed_row_for_session(session: Session, path: Path) -> dict[str, Any]:
 
 
 def _scan_session_row(session_manager: SessionManager, path: Path) -> dict[str, Any] | None:
-    fallback_key = path.stem.replace("_", ":", 1)
+    storage_key = SessionManager._decode_storage_key(path.stem)
+    fallback_key = storage_key or path.stem.replace("_", ":", 1)
     try:
         with open(path, encoding="utf-8") as f:
             first_line = f.readline().strip()
@@ -243,20 +276,25 @@ def _scan_session_row(session_manager: SessionManager, path: Path) -> dict[str,
                 return None
             preview = ""
             fallback_preview = ""
+            visible_message_at = None
+            preview_done = False
             scanned_records = 0
             scanned_chars = 0
             for line in f:
                 if not line.strip():
                     continue
+                item = json.loads(line)
+                timestamp = _visible_message_timestamp(item)
+                if timestamp is not None:
+                    visible_message_at = _latest_updated_at(visible_message_at, timestamp)
+                if not preview_done:
                     scanned_records += 1
                     scanned_chars += len(line)
                     if (
                         scanned_records > _SESSION_LIST_PREVIEW_MAX_RECORDS
                         or scanned_chars > _SESSION_LIST_PREVIEW_MAX_CHARS
                     ):
-                    break
+                        preview_done = True
-                item = json.loads(line)
-                if item.get("_type") == "metadata":
                         continue
                     if item.get(CRON_HISTORY_META) is True:
                         continue
@@ -265,7 +303,8 @@ def _scan_session_row(session_manager: SessionManager, path: Path) -> dict[str,
                         continue
                     if item.get("role") == "user":
                         preview = text
-                    break
+                        preview_done = True
+                        continue
                     if not fallback_preview and item.get("role") == "assistant":
                         fallback_preview = text
             signature = _file_signature(path)
@@ -281,7 +320,11 @@ def _scan_session_row(session_manager: SessionManager, path: Path) -> dict[str,
             return {
                 "key": key,
                 "created_at": created_at_s,
-                "updated_at": _latest_updated_at(updated_at_s, activity_updated_at),
+                "updated_at": _visible_activity_updated_at(
+                    updated_at_s,
+                    visible_message_at,
+                    activity_updated_at,
+                ),
                 "title": _metadata_title(data.get("metadata", {})),
                 "preview": preview or fallback_preview,
                 "file": path.name,

nanobot/webui/settings_api.py

@@ -22,7 +22,7 @@ from nanobot.audio.transcription_registry import (
     resolve_transcription_provider,
     transcription_provider_names,
 )
-from nanobot.config.loader import get_config_path, load_config, save_config
+from nanobot.config.loader import get_config_path, load_config, resolve_config_env_vars, save_config
 from nanobot.config.schema import ModelPresetConfig, ProviderConfig
 from nanobot.providers.image_generation import (
     get_image_gen_provider,
@@ -99,47 +99,6 @@ _CONTEXT_WINDOW_TOKEN_OPTIONS = {65_536, 200_000, 262_144}
 _MODEL_CONFIGURATION_SLUG_RE = re.compile(r"[^a-z0-9_-]+")
 _ENV_REF_RE = re.compile(r"\$\{([A-Za-z_][A-Za-z0-9_]*)\}")
 
-_MODEL_LIST_UNSUPPORTED_BACKENDS = {
-    "anthropic",
-    "azure_openai",
-    "bedrock",
-    "github_copilot",
-    "openai_codex",
-}
-
-_MODEL_LIST_CATALOG_PROVIDERS = {
-    "aihubmix",
-    "byteplus",
-    "byteplus_coding_plan",
-    "huggingface",
-    "novita",
-    "openrouter",
-    "siliconflow",
-    "volcengine",
-    "volcengine_coding_plan",
-}
-
-_MODEL_LIST_OFFICIAL_PROVIDERS = {
-    "ant_ling",
-    "dashscope",
-    "deepseek",
-    "gemini",
-    "groq",
-    "longcat",
-    "minimax",
-    "minimax_anthropic",
-    "mistral",
-    "moonshot",
-    "nvidia",
-    "openai",
-    "qianfan",
-    "skywork",
-    "stepfun",
-    "xiaomi_mimo",
-    "zhipu",
-}
-
-
 class WebUISettingsError(ValueError):
     """User-facing settings validation failure."""
 
@@ -394,10 +353,13 @@ def _provider_settings_row(
 
 
 def _model_catalog_kind(spec: Any) -> str:
-    if spec.name in _MODEL_LIST_CATALOG_PROVIDERS:
+    catalog = getattr(spec, "model_catalog", "auto")
-        return "catalog"
+    if catalog != "auto":
-    if spec.name in _MODEL_LIST_OFFICIAL_PROVIDERS:
+        return catalog
-        return "official"
+    if spec.is_transcription_only or spec.is_oauth:
+        return "unsupported"
+    if spec.backend != "openai_compat" and spec.name != "minimax_anthropic":
+        return "unsupported"
     if spec.is_local:
         return "local"
     if spec.is_direct:
@@ -490,27 +452,20 @@ def provider_models_payload(query: QueryParams) -> dict[str, Any]:
         raise WebUISettingsError("unknown provider")
     spec, provider_key, provider_config = resolved_provider
 
+    catalog_kind = _model_catalog_kind(spec)
     base_payload: dict[str, Any] = {
         "provider": provider_key,
         "label": spec.label,
-        "catalog_kind": _model_catalog_kind(spec),
+        "catalog_kind": catalog_kind,
         "models": [],
         "model_count": 0,
         "message": None,
         "fetched_at": time.time(),
     }
-    if (
+    if catalog_kind == "unsupported":
-        spec.is_transcription_only
-        or (
-            spec.backend in _MODEL_LIST_UNSUPPORTED_BACKENDS
-            and spec.name != "minimax_anthropic"
-        )
-        or spec.is_oauth
-    ):
         return {
             **base_payload,
             "status": "unsupported",
-            "catalog_kind": "unsupported",
             "message": "Model list is not available for this provider. Type a model ID manually.",
         }
 
@@ -1166,14 +1121,19 @@ def login_oauth_provider(query: QueryParams) -> dict[str, Any]:
         except ImportError:
             raise WebUISettingsError("oauth_cli_kit is not installed", status=500) from None
 
+        try:
+            proxy = resolve_config_env_vars(load_config()).providers.openai_codex.proxy or None
+        except ValueError as e:
+            raise WebUISettingsError(str(e), status=400) from e
         token = None
         with suppress(Exception):
-            token = get_token()
+            token = get_token(proxy=proxy)
         if not (token and token.access):
             messages: list[str] = []
             token = login_oauth_interactive(
                 print_fn=lambda message: messages.append(str(message)),
                 prompt_fn=lambda _prompt: "",
+                proxy=proxy,
             )
         if not (token and token.access):
             raise WebUISettingsError("OAuth login failed", status=401)

pyproject.toml

@@ -31,7 +31,7 @@ dependencies = [
     "websocket-client>=1.9.0,<2.0.0",
     "httpx>=0.28.0,<1.0.0",
     "ddgs>=9.5.5,<10.0.0",
-    "oauth-cli-kit>=0.1.3,<1.0.0",
+    "oauth-cli-kit>=0.1.6,<1.0.0",
     "loguru>=0.7.3,<1.0.0",
     "readability-lxml>=0.8.4,<1.0.0",
     "lxml-html-clean>=0.4.0,<1.0.0",

scripts/install.sh

@@ -269,7 +269,15 @@ if [ "${NANOBOT_SKIP_WIZARD:-}" = "1" ]; then
   exit 0
 fi
 
-info "Starting setup wizard..."
+if [ -t 0 ]; then
-run_nanobot onboard --wizard
+  info "Starting setup wizard..."
+  run_nanobot onboard --wizard
+elif : 2>/dev/null < /dev/tty; then
+  info "Starting setup wizard..."
+  run_nanobot onboard --wizard < /dev/tty
+else
+  info "Skipping setup wizard because no interactive terminal is available."
+  info "Run this later: $(nanobot_try_command) onboard --wizard"
+fi
 
 info "Done. Try: $(nanobot_try_command) agent -m \"Hello!\""

tests/agent/conftest.py

@@ -38,7 +38,6 @@ def make_loop(
     model: str = "test-model",
     context_window_tokens: int = 128_000,
     session_ttl_minutes: int = 0,
-    max_messages: int = 120,
     unified_session: bool = False,
     mcp_servers: dict | None = None,
     tools_config=None,
@@ -64,7 +63,6 @@ def make_loop(
         model=model,
         context_window_tokens=context_window_tokens,
         session_ttl_minutes=session_ttl_minutes,
-        max_messages=max_messages,
         unified_session=unified_session,
     )
     if mcp_servers is not None:
@@ -79,8 +77,8 @@ def make_loop(
     if patch_deps:
         with patch("nanobot.agent.loop.ContextBuilder"), \
              patch("nanobot.agent.loop.SessionManager"), \
-             patch("nanobot.agent.loop.SubagentManager") as MockSubMgr:
+             patch("nanobot.agent.loop.SubagentManager") as mock_sub_mgr:
-            MockSubMgr.return_value.cancel_by_session = AsyncMock(return_value=0)
+            mock_sub_mgr.return_value.cancel_by_session = AsyncMock(return_value=0)
             return AgentLoop(**kwargs)
     return AgentLoop(**kwargs)
 

tests/agent/test_auto_compact.py

@@ -91,7 +91,6 @@ def _make_fake_compact(
 
         tail = list(session.messages[session.last_consolidated:])
         if not tail:
-            session.updated_at = datetime.now()
             loop.sessions.save(session)
             return ""
 
@@ -103,15 +102,14 @@ def _make_fake_compact(
             metadata={},
             last_consolidated=0,
         )
-        dropped, already_consolidated = probe.retain_recent_legal_suffix(
+        result = probe.retain_recent_legal_suffix(
             max_suffix,
             extend_to_user=True,
         )
         kept = probe.messages
-        archive_msgs = dropped[already_consolidated:]
+        archive_msgs = result.dropped[result.already_consolidated_count:]
 
         if not archive_msgs and not kept:
-            session.updated_at = datetime.now()
             loop.sessions.save(session)
             return ""
 
@@ -132,7 +130,6 @@ def _make_fake_compact(
 
         session.messages = kept
         session.last_consolidated = 0
-        session.updated_at = datetime.now()
         loop.sessions.save(session)
         return s
 
@@ -1021,27 +1018,28 @@ class TestProactiveAutoCompact:
         await self._run_check_expired(loop)
         assert _fake_compact.state["count"] == 1
 
-        # Second tick: should NOT re-schedule (updated_at is fresh after clear)
+        # Second tick: should NOT re-schedule because the session has no removable tail.
         await self._run_check_expired(loop)
         assert _fake_compact.state["count"] == 1  # Still 1, not re-scheduled
         await loop.close_mcp()
 
     @pytest.mark.asyncio
-    async def test_empty_skip_refreshes_updated_at_prevents_reschedule(self, tmp_path):
+    async def test_empty_session_does_not_schedule_idle_compact(self, tmp_path):
-        """Empty session skip refreshes updated_at, preventing immediate re-scheduling."""
+        """Empty expired sessions have no removable tail and should not schedule."""
         loop = _make_loop(tmp_path, session_ttl_minutes=15)
         session = loop.sessions.get_or_create("cli:test")
         session.updated_at = datetime.now() - timedelta(minutes=20)
         loop.sessions.save(session)
 
-        loop.consolidator.compact_idle_session = _make_fake_compact(loop)
+        _fake_compact = _make_fake_compact(loop)
+        loop.consolidator.compact_idle_session = _fake_compact
 
-        # First tick: skips (no messages), refreshes updated_at
         await self._run_check_expired(loop)
+        assert _fake_compact.state["count"] == 0
         assert "cli:test" not in loop.auto_compact._summaries
 
-        # Second tick: should NOT re-schedule because updated_at is fresh
         await self._run_check_expired(loop)
+        assert _fake_compact.state["count"] == 0
         assert "cli:test" not in loop.auto_compact._summaries
         await loop.close_mcp()
 

tests/agent/test_autocompact_unit.py

@@ -200,8 +200,11 @@ class TestCheckExpired:
         """Expired session should trigger schedule_background."""
         ac = _make_autocompact(ttl=15)
         mock_sm = MagicMock(spec=SessionManager)
-        old_ts = (datetime.now() - timedelta(minutes=20)).isoformat()
+        old_dt = datetime.now() - timedelta(minutes=20)
-        mock_sm.list_sessions.return_value = [{"key": "cli:old", "updated_at": old_ts}]
+        session = _make_session("cli:old", updated_at=old_dt)
+        _add_turns(session, 5)
+        mock_sm.list_sessions.return_value = [{"key": "cli:old", "updated_at": old_dt.isoformat()}]
+        mock_sm.get_or_create.return_value = session
         ac.sessions = mock_sm
 
         scheduled = []
@@ -273,6 +276,24 @@ class TestCheckExpired:
         scheduler.assert_not_called()
         assert "dream:20260602-155256" not in ac._archiving
 
+    def test_already_trimmed_session_skips(self):
+        """Expired session with no removable tail should not be re-scheduled."""
+        ac = _make_autocompact(ttl=15)
+        mock_sm = MagicMock(spec=SessionManager)
+        last_active = datetime(2026, 1, 1, 10, 0, 0)
+        session = _make_session("cli:done", updated_at=last_active)
+        _add_turns(session, 2)
+        mock_sm.list_sessions.return_value = [
+            {"key": "cli:done", "updated_at": last_active.isoformat()},
+        ]
+        mock_sm.get_or_create.return_value = session
+        ac.sessions = mock_sm
+
+        scheduler = MagicMock()
+        ac.check_expired(scheduler)
+
+        scheduler.assert_not_called()
+
 
 # ---------------------------------------------------------------------------
 # _archive

tests/agent/test_consolidator.py

@@ -430,9 +430,11 @@ class TestCompactIdleSession:
         )
         sessions = real_consolidator.sessions
         session = sessions.get_or_create("cli:test")
+        old_ts = session.updated_at
         for i in range(20):
             session.add_message("user", f"user msg {i}")
             session.add_message("assistant", f"assistant msg {i}")
+        session.updated_at = old_ts
         sessions.save(session)
 
         result = await real_consolidator.compact_idle_session("cli:test", max_suffix=8)
@@ -445,6 +447,7 @@ class TestCompactIdleSession:
         assert meta is not None
         assert meta["text"] == "Summary of old conversation."
         assert "last_active" in meta
+        assert reloaded.updated_at == old_ts
 
     @pytest.mark.asyncio
     async def test_summarizes_retained_suffix_not_just_dropped_prefix(
@@ -518,8 +521,10 @@ class TestCompactIdleSession:
         assert entries[0]["session_key"] == "cli:test"
 
     @pytest.mark.asyncio
-    async def test_empty_session_refreshes_timestamp(self, real_consolidator):
+    async def test_empty_session_does_not_refresh_timestamp(
-        """Empty session with old updated_at → refreshed after call, returns ''."""
+        self, real_consolidator
+    ):
+        """Empty session with old updated_at does not look active after compaction."""
         from datetime import datetime, timedelta
 
         sessions = real_consolidator.sessions
@@ -532,7 +537,8 @@ class TestCompactIdleSession:
         assert result == ""
 
         reloaded = sessions.get_or_create("cli:empty")
-        assert reloaded.updated_at > old_ts
+        assert reloaded.updated_at == old_ts
+        assert reloaded.metadata == {}
 
     @pytest.mark.asyncio
     async def test_nothing_summary_not_stored(self, real_consolidator, mock_provider):

tests/agent/test_dream_session.py

@@ -24,9 +24,14 @@ class TestDreamSessionKey:
 
 class TestPruneDreamSessions:
     def test_keeps_n_most_recent(self, tmp_path):
+        import os
+        import time
+
         sessions_dir = tmp_path / "sessions"
         sessions_dir.mkdir()
 
+        base_time = time.time() - 100
+
         for i in range(15):
             key = f"dream:20260528-{100000 + i:06d}"
             safe_key = key.replace(":", "_")
@@ -37,6 +42,7 @@ class TestPruneDreamSessions:
                 f'"updated_at": "2026-05-28T10:00:{i:02d}"}}\n',
                 encoding="utf-8",
             )
+            os.utime(path, (base_time + i, base_time + i))
 
         normal_path = sessions_dir / "telegram_123.jsonl"
         normal_path.write_text('{"_type": "metadata"}\n', encoding="utf-8")

tests/agent/test_gemini_thought_signature.py

@@ -11,7 +11,6 @@ from unittest.mock import patch
 from nanobot.providers.base import ToolCallRequest
 from nanobot.providers.openai_compat_provider import OpenAICompatProvider
 
-
 GEMINI_EXTRA = {"google": {"thought_signature": "sig-abc-123"}}
 
 
@@ -125,6 +124,47 @@ def test_parse_dict_preserves_extra_content() -> None:
     assert payload["extra_content"] == GEMINI_EXTRA
 
 
+def test_parse_dict_deduplicates_duplicate_tool_call_ids() -> None:
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider()
+
+    response_dict = {
+        "choices": [
+            {
+                "message": {
+                    "content": None,
+                    "tool_calls": [{
+                        "id": "call_same",
+                        "type": "function",
+                        "function": {"name": "read_file", "arguments": '{"path":"a.txt"}'},
+                    }],
+                },
+                "finish_reason": "tool_calls",
+            },
+            {
+                "message": {
+                    "content": None,
+                    "tool_calls": [{
+                        "id": "call_same",
+                        "type": "function",
+                        "function": {"name": "read_file", "arguments": '{"path":"b.txt"}'},
+                    }],
+                },
+                "finish_reason": "tool_calls",
+            },
+        ],
+    }
+
+    result = provider._parse(response_dict)
+
+    ids = [tc.id for tc in result.tool_calls]
+    assert len(ids) == 2
+    assert ids[0] == "call_same"
+    assert ids[1] != "call_same"
+    assert len(set(ids)) == 2
+    assert [tc.arguments for tc in result.tool_calls] == [{"path": "a.txt"}, {"path": "b.txt"}]
+
+
 # ── _parse_chunks: streaming round-trip ───────────────────────────────
 
 def test_parse_chunks_sdk_preserves_extra_content() -> None:

tests/agent/test_loop_direct_websocket_status.py

@@ -5,6 +5,7 @@ import pytest
 
 from nanobot.agent.loop import AgentLoop
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import GoalStatusEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.providers.base import GenerationSettings, LLMResponse
 from nanobot.session.webui_turns import WebuiTurnCoordinator
@@ -54,13 +55,13 @@ async def test_process_direct_websocket_clears_run_status(tmp_path) -> None:
         events.append(await loop.bus.consume_outbound())
 
     statuses = [
-        event.metadata
+        event.event
         for event in events
-        if event.metadata.get("_goal_status") is True
+        if isinstance(event.event, GoalStatusEvent)
     ]
-    assert [status["goal_status"] for status in statuses] == ["running", "idle"]
+    assert [status.status for status in statuses] == ["running", "idle"]
-    assert isinstance(statuses[0].get("started_at"), float)
+    assert isinstance(statuses[0].started_at, float)
-    assert "started_at" not in statuses[1]
+    assert statuses[1].started_at is None
 
 
 @pytest.mark.asyncio

tests/agent/test_loop_progress.py

@@ -9,6 +9,15 @@ import pytest
 import nanobot.agent.runner as runner_module
 from nanobot.agent.loop import AgentLoop
 from nanobot.bus.events import InboundMessage
+from nanobot.bus.outbound_events import (
+    GoalStatusEvent,
+    ProgressEvent,
+    SessionUpdatedEvent,
+    StreamDeltaEvent,
+    StreamedResponseEvent,
+    StreamEndEvent,
+    TurnEndEvent,
+)
 from nanobot.bus.queue import MessageBus
 from nanobot.providers.base import LLMResponse, ToolCallRequest
 from nanobot.session.webui_turns import WebuiTurnCoordinator
@@ -260,25 +269,45 @@ class TestToolEventProgress:
         )
         await loop._dispatch(msg)
 
-        # Drain all outbound messages and find the one carrying _tool_events
+        # Drain all outbound messages and find the one carrying tool events.
         outbound = []
         while bus.outbound_size > 0:
             outbound.append(await bus.consume_outbound())
 
-        tool_event_msgs = [m for m in outbound if m.metadata and m.metadata.get("_tool_events")]
+        tool_event_msgs = [
-        assert tool_event_msgs, "expected at least one outbound message with _tool_events"
+            m
+            for m in outbound
+            if isinstance(m.event, ProgressEvent) and m.event.tool_events
+        ]
+        assert tool_event_msgs, "expected at least one outbound message with tool events"
 
-        start_msgs = [m for m in tool_event_msgs if m.metadata["_tool_events"][0]["phase"] == "start"]
+        start_msgs = [
-        finish_msgs = [m for m in tool_event_msgs if m.metadata["_tool_events"][0]["phase"] in ("end", "error")]
+            m
+            for m in tool_event_msgs
+            if isinstance(m.event, ProgressEvent)
+            and m.event.tool_events
+            and m.event.tool_events[0]["phase"] == "start"
+        ]
+        finish_msgs = [
+            m
+            for m in tool_event_msgs
+            if isinstance(m.event, ProgressEvent)
+            and m.event.tool_events
+            and m.event.tool_events[0]["phase"] in ("end", "error")
+        ]
         assert start_msgs, "expected a start-phase tool event"
         assert finish_msgs, "expected a finish-phase tool event"
 
-        start = start_msgs[0].metadata["_tool_events"][0]
+        assert isinstance(start_msgs[0].event, ProgressEvent)
+        assert start_msgs[0].event.tool_events is not None
+        start = start_msgs[0].event.tool_events[0]
         assert start["name"] == "exec"
         assert start["call_id"] == "tc1"
         assert start["result"] is None
 
-        finish = finish_msgs[0].metadata["_tool_events"][0]
+        assert isinstance(finish_msgs[0].event, ProgressEvent)
+        assert finish_msgs[0].event.tool_events is not None
+        finish = finish_msgs[0].event.tool_events[0]
         assert finish["phase"] == "end"
         assert finish["result"] == "file.txt"
 
@@ -309,7 +338,8 @@ class TestToolEventProgress:
         await invoke_file_edit_progress(progress, edit_events)
         outbound = await bus.consume_outbound()
         assert outbound.channel == "telegram"
-        assert outbound.metadata["_file_edit_events"] == edit_events
+        assert isinstance(outbound.event, ProgressEvent)
+        assert outbound.event.file_edit_events == edit_events
 
     @pytest.mark.asyncio
     async def test_goal_turn_keeps_live_file_edit_progress_for_webui(self, tmp_path: Path) -> None:
@@ -389,7 +419,8 @@ class TestToolEventProgress:
         edit_events = [
             event
             for msg in outbound
-            for event in msg.metadata.get("_file_edit_events", [])
+            if isinstance(msg.event, ProgressEvent)
+            for event in msg.event.file_edit_events or []
         ]
         assert any(
             event["status"] == "editing"
@@ -433,8 +464,8 @@ class TestToolEventProgress:
             outbound.append(await bus.consume_outbound())
 
         assert [m.content for m in outbound] == ["Hello"]
-        assert not any(m.metadata.get("_progress") for m in outbound)
+        assert not any(isinstance(m.event, ProgressEvent) for m in outbound)
-        assert not any(m.metadata.get("_streamed") for m in outbound)
+        assert not any(isinstance(m.event, StreamedResponseEvent) for m in outbound)
         provider.chat_stream_with_retry.assert_not_awaited()
         provider.chat_with_retry.assert_awaited_once()
 
@@ -443,7 +474,7 @@ class TestToolEventProgress:
         self,
         tmp_path: Path,
     ) -> None:
-        """Streaming channels still receive provider deltas through _stream_delta messages."""
+        """Streaming channels still receive provider deltas through stream events."""
         bus = MessageBus()
         provider = MagicMock()
         provider.supports_progress_deltas = True
@@ -473,21 +504,19 @@ class TestToolEventProgress:
         while bus.outbound_size > 0:
             outbound.append(await bus.consume_outbound())
 
-        deltas = [m for m in outbound if m.metadata.get("_stream_delta")]
+        deltas = [m for m in outbound if isinstance(m.event, StreamDeltaEvent)]
-        stream_end = [m for m in outbound if m.metadata.get("_stream_end")]
+        stream_end = [m for m in outbound if isinstance(m.event, StreamEndEvent)]
         final = [
             m for m in outbound
-            if not m.metadata.get("_stream_delta")
+            if not isinstance(m.event, StreamDeltaEvent | StreamEndEvent)
-            and not m.metadata.get("_stream_end")
+            and not isinstance(m.event, TurnEndEvent | GoalStatusEvent)
-            and not m.metadata.get("_turn_end")
-            and not m.metadata.get("_goal_status")
         ]
 
         assert [m.content for m in deltas] == ["Hel", "lo"]
         assert len(stream_end) == 1
         assert final[-1].content == "Hello"
-        assert final[-1].metadata.get("_streamed") is True
+        assert isinstance(final[-1].event, StreamedResponseEvent)
-        turn_end_msgs = [m for m in outbound if m.metadata.get("_turn_end")]
+        turn_end_msgs = [m for m in outbound if isinstance(m.event, TurnEndEvent)]
         assert len(turn_end_msgs) == 1
         assert turn_end_msgs[0].content == ""
         provider.chat_with_retry.assert_not_awaited()
@@ -528,23 +557,28 @@ class TestToolEventProgress:
         while bus.outbound_size > 0:
             outbound.append(await bus.consume_outbound())
 
-        deltas = [m for m in outbound if m.metadata.get("_stream_delta")]
+        deltas = [m for m in outbound if isinstance(m.event, StreamDeltaEvent)]
-        stream_end = [m for m in outbound if m.metadata.get("_stream_end")]
+        stream_end = [m for m in outbound if isinstance(m.event, StreamEndEvent)]
         final = [
             m for m in outbound
-            if not m.metadata.get("_stream_delta")
+            if not isinstance(m.event, StreamDeltaEvent | StreamEndEvent)
-            and not m.metadata.get("_stream_end")
+            and not isinstance(m.event, TurnEndEvent | GoalStatusEvent)
-            and not m.metadata.get("_turn_end")
-            and not m.metadata.get("_goal_status")
         ]
 
         assert [m.content for m in deltas] == ["partial", "full retry response"]
-        assert [m.metadata.get("_resuming") for m in stream_end] == [True, False]
+        assert [m.event.resuming for m in stream_end if isinstance(m.event, StreamEndEvent)] == [
-        assert deltas[0].metadata.get("_stream_id") == stream_end[0].metadata.get("_stream_id")
+            True,
-        assert deltas[1].metadata.get("_stream_id") == stream_end[1].metadata.get("_stream_id")
+            False,
-        assert deltas[0].metadata.get("_stream_id") != deltas[1].metadata.get("_stream_id")
+        ]
+        assert isinstance(deltas[0].event, StreamDeltaEvent)
+        assert isinstance(deltas[1].event, StreamDeltaEvent)
+        assert isinstance(stream_end[0].event, StreamEndEvent)
+        assert isinstance(stream_end[1].event, StreamEndEvent)
+        assert deltas[0].event.stream_id == stream_end[0].event.stream_id
+        assert deltas[1].event.stream_id == stream_end[1].event.stream_id
+        assert deltas[0].event.stream_id != deltas[1].event.stream_id
         assert final[-1].content == "full retry response"
-        assert final[-1].metadata.get("_streamed") is True
+        assert isinstance(final[-1].event, StreamedResponseEvent)
         provider.chat_with_retry.assert_not_awaited()
 
     @pytest.mark.asyncio
@@ -623,9 +657,9 @@ class TestToolEventProgress:
 
         done_msgs = [m for m in outbound if m.content == "Done"]
         assert len(done_msgs) == 1
-        assert not done_msgs[0].metadata.get("_turn_end")
+        assert not isinstance(done_msgs[0].event, TurnEndEvent)
 
-        turn_end_msgs = [m for m in outbound if m.metadata.get("_turn_end")]
+        turn_end_msgs = [m for m in outbound if isinstance(m.event, TurnEndEvent)]
         assert len(turn_end_msgs) == 1
         assert turn_end_msgs[0].content == ""
         assert turn_end_msgs[0].chat_id == "chat1"
@@ -659,14 +693,14 @@ class TestToolEventProgress:
             outbound.append(await bus.consume_outbound())
 
         error_msgs = [m for m in outbound if m.content == "Sorry, I encountered an error."]
-        turn_end_msgs = [m for m in outbound if m.metadata.get("_turn_end")]
+        turn_end_msgs = [m for m in outbound if isinstance(m.event, TurnEndEvent)]
-        statuses = [m for m in outbound if m.metadata.get("_goal_status")]
+        statuses = [m for m in outbound if isinstance(m.event, GoalStatusEvent)]
 
         assert len(error_msgs) == 1
         assert len(turn_end_msgs) == 1
         assert turn_end_msgs[0].content == ""
         assert turn_end_msgs[0].chat_id == "chat1"
-        assert [m.metadata["goal_status"] for m in statuses] == ["idle"]
+        assert [m.event.status for m in statuses if isinstance(m.event, GoalStatusEvent)] == ["idle"]
         assert outbound.index(error_msgs[0]) < outbound.index(turn_end_msgs[0])
         assert outbound.index(turn_end_msgs[0]) < outbound.index(statuses[-1])
 
@@ -705,27 +739,27 @@ class TestToolEventProgress:
         outbound: list = []
         for _ in range(12):
             outbound.append(await asyncio.wait_for(bus.consume_outbound(), timeout=0.5))
-            if outbound[-1].metadata.get("_turn_end"):
+            if isinstance(outbound[-1].event, TurnEndEvent):
                 break
         else:
-            raise AssertionError("_turn_end message not found")
+            raise AssertionError("turn-end event not found")
 
         done_with_body = [m for m in outbound if m.content == "Done"]
         assert len(done_with_body) == 1
-        assert outbound[-1].metadata.get("_turn_end") is True
+        assert isinstance(outbound[-1].event, TurnEndEvent)
 
         await asyncio.wait_for(title_started.wait(), timeout=0.5)
         release_title.set()
         session_updated = None
         for _ in range(10):
             candidate = await asyncio.wait_for(bus.consume_outbound(), timeout=0.5)
-            if (candidate.metadata or {}).get("_session_updated"):
+            if isinstance(candidate.event, SessionUpdatedEvent):
                 session_updated = candidate
                 break
         assert session_updated is not None
 
-        assert (session_updated.metadata or {}).get("_session_updated") is True
+        assert isinstance(session_updated.event, SessionUpdatedEvent)
-        assert (session_updated.metadata or {}).get("_session_update_scope") == "metadata"
+        assert session_updated.event.scope == "metadata"
         assert provider.chat_with_retry.await_count == 2
 
     @pytest.mark.asyncio
@@ -837,4 +871,4 @@ class TestToolEventProgress:
 
         assert len(outbound) == 1
         assert outbound[0].content == "Done"
-        assert (outbound[0].metadata or {}).get("_turn_end") is not True
+        assert not isinstance(outbound[0].event, TurnEndEvent)

tests/agent/test_loop_runner_integration.py

@@ -7,6 +7,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
+from nanobot.bus.outbound_events import StreamedResponseEvent
 from nanobot.config.schema import AgentDefaults
 from nanobot.providers.base import LLMResponse, ToolCallRequest
 
@@ -23,8 +24,8 @@ def _make_loop(tmp_path):
 
     with patch("nanobot.agent.loop.ContextBuilder"), \
          patch("nanobot.agent.loop.SessionManager"), \
-         patch("nanobot.agent.loop.SubagentManager") as MockSubMgr:
+         patch("nanobot.agent.loop.SubagentManager") as mock_sub_mgr:
-        MockSubMgr.return_value.cancel_by_session = AsyncMock(return_value=0)
+        mock_sub_mgr.return_value.cancel_by_session = AsyncMock(return_value=0)
         loop = AgentLoop(bus=bus, provider=provider, workspace=tmp_path)
     return loop
 
@@ -193,8 +194,9 @@ async def test_streamed_flag_not_set_on_llm_error(tmp_path):
 
     assert result is not None
     assert "503" in result.content
-    assert not result.metadata.get("_streamed"), \
+    assert not isinstance(result.event, StreamedResponseEvent), (
-        "_streamed must not be set when stop_reason is error"
+        "streamed response event must not be set when stop_reason is error"
+    )
 
 
 @pytest.mark.asyncio
@@ -239,7 +241,7 @@ async def test_ssrf_soft_block_can_finalize_after_streamed_tool_call(tmp_path):
 
     assert result is not None
     assert result.content == "I cannot access private URLs. Please share the local file."
-    assert result.metadata.get("_streamed") is True
+    assert isinstance(result.event, StreamedResponseEvent)
 
 
 @pytest.mark.asyncio

tests/agent/test_loop_save_turn.py

@@ -8,6 +8,13 @@ import pytest
 from nanobot.agent.context import ContextBuilder
 from nanobot.agent.loop import AgentLoop
 from nanobot.bus.events import InboundMessage
+from nanobot.bus.outbound_events import (
+    GoalStatusEvent,
+    StreamDeltaEvent,
+    StreamedResponseEvent,
+    StreamEndEvent,
+    TurnEndEvent,
+)
 from nanobot.bus.queue import MessageBus
 from nanobot.cron.session_turns import CRON_HISTORY_META, CRON_TRIGGER_META
 from nanobot.providers.base import LLMResponse
@@ -765,7 +772,6 @@ async def test_internal_continuation_preserves_streaming_route_metadata(
             "_wants_stream": True,
             "message_id": "om_001",
             "origin_message_id": "root_001",
-            "_stream_id": "old-stream",
         },
     ))
 
@@ -775,23 +781,23 @@ async def test_internal_continuation_preserves_streaming_route_metadata(
     assert queued.metadata["_wants_stream"] is True
     assert queued.metadata["message_id"] == "om_001"
     assert queued.metadata["origin_message_id"] == "root_001"
-    assert "_stream_id" not in queued.metadata
 
     await loop._dispatch(queued)
 
     outbound = []
     while loop.bus.outbound_size:
         outbound.append(await loop.bus.consume_outbound())
-    deltas = [m for m in outbound if m.metadata.get("_stream_delta")]
+    deltas = [m for m in outbound if isinstance(m.event, StreamDeltaEvent)]
-    ends = [m for m in outbound if m.metadata.get("_stream_end")]
+    ends = [m for m in outbound if isinstance(m.event, StreamEndEvent)]
-    streamed_markers = [m for m in outbound if m.metadata.get("_streamed")]
+    streamed_markers = [m for m in outbound if isinstance(m.event, StreamedResponseEvent)]
 
     assert [m.content for m in deltas] == ["done"]
     assert len(ends) == 1
-    assert ends[0].metadata["_resuming"] is False
+    assert isinstance(ends[0].event, StreamEndEvent)
+    assert ends[0].event.resuming is False
     assert ends[0].metadata["message_id"] == "om_001"
     assert ends[0].metadata["origin_message_id"] == "root_001"
-    assert isinstance(ends[0].metadata.get("_stream_id"), str)
+    assert isinstance(ends[0].event.stream_id, str)
     assert streamed_markers and streamed_markers[-1].content == "done"
 
 
@@ -842,10 +848,10 @@ async def test_websocket_internal_continuation_keeps_single_visible_run(
     first_outbound = []
     while loop.bus.outbound_size:
         first_outbound.append(await loop.bus.consume_outbound())
-    first_statuses = [m.metadata for m in first_outbound if m.metadata.get("_goal_status")]
+    first_statuses = [m.event for m in first_outbound if isinstance(m.event, GoalStatusEvent)]
-    assert [m["goal_status"] for m in first_statuses] == ["running"]
+    assert [m.status for m in first_statuses] == ["running"]
-    assert not [m for m in first_outbound if m.metadata.get("_turn_end")]
+    assert not [m for m in first_outbound if isinstance(m.event, TurnEndEvent)]
-    started_at = first_statuses[0]["started_at"]
+    started_at = first_statuses[0].started_at
 
     queued = await asyncio.wait_for(loop.bus.consume_inbound(), timeout=0.5)
     assert queued.metadata[INTERNAL_CONTINUATION_META] is True
@@ -856,12 +862,13 @@ async def test_websocket_internal_continuation_keeps_single_visible_run(
     second_outbound = []
     while loop.bus.outbound_size:
         second_outbound.append(await loop.bus.consume_outbound())
-    second_statuses = [m.metadata for m in second_outbound if m.metadata.get("_goal_status")]
+    second_statuses = [m.event for m in second_outbound if isinstance(m.event, GoalStatusEvent)]
-    assert [m["goal_status"] for m in second_statuses] == ["running", "idle"]
+    assert [m.status for m in second_statuses] == ["running", "idle"]
-    assert second_statuses[0]["started_at"] == started_at
+    assert second_statuses[0].started_at == started_at
-    turn_end = [m for m in second_outbound if m.metadata.get("_turn_end")]
+    turn_end = [m for m in second_outbound if isinstance(m.event, TurnEndEvent)]
     assert len(turn_end) == 1
-    assert isinstance(turn_end[0].metadata.get("latency_ms"), int)
+    assert isinstance(turn_end[0].event, TurnEndEvent)
+    assert isinstance(turn_end[0].event.latency_ms, int)
 
 
 @pytest.mark.asyncio

tests/agent/test_max_messages_config.py

@@ -1,4 +1,4 @@
-"""Tests for max_messages config wiring into session history replay."""
+"""Tests for the internal max_messages replay cap."""
 
 from __future__ import annotations
 
@@ -11,20 +11,27 @@ from nanobot.agent.loop import AgentLoop
 from nanobot.bus.events import InboundMessage
 from nanobot.bus.queue import MessageBus
 from nanobot.providers.base import LLMResponse
-from nanobot.session.manager import Session
+from nanobot.providers.factory import ProviderSnapshot
-
+from nanobot.session.manager import (
-DEFAULT_MAX_MESSAGES = 120
+    FILE_MAX_MESSAGES,
+    Session,
+    replay_max_messages_for_context,
+)
 
 
-def _make_loop(tmp_path: Path, max_messages: int = DEFAULT_MAX_MESSAGES) -> AgentLoop:
+def _make_loop(
+    tmp_path: Path,
+    context_window_tokens: int = 200_000,
+) -> AgentLoop:
     provider = MagicMock()
     provider.get_default_model.return_value = "test-model"
+    provider.generation.max_tokens = 4096
     return AgentLoop(
         bus=MessageBus(),
         provider=provider,
         workspace=tmp_path,
         model="test-model",
-        max_messages=max_messages,
+        context_window_tokens=context_window_tokens,
     )
 
 
@@ -51,24 +58,44 @@ def _tool_round(call_id: str) -> list[dict]:
 
 
 class TestMaxMessagesInit:
-    """Verify AgentLoop stores the config value correctly."""
+    """Verify AgentLoop derives the internal replay cap correctly."""
 
-    def test_default_is_builtin_limit(self, tmp_path: Path) -> None:
+    def test_context_formula(self) -> None:
+        assert replay_max_messages_for_context(8_000) == 120
+        assert replay_max_messages_for_context(32_768) == 327
+        assert replay_max_messages_for_context(200_000) == FILE_MAX_MESSAGES
+
+    def test_default_for_200k_context_reaches_file_cap(self, tmp_path: Path) -> None:
         loop = _make_loop(tmp_path)
-        assert loop._max_messages == DEFAULT_MAX_MESSAGES
+        assert loop._max_messages == FILE_MAX_MESSAGES
 
-    def test_positive_value_stored(self, tmp_path: Path) -> None:
+    def test_default_scales_with_context_window(self, tmp_path: Path) -> None:
-        loop = _make_loop(tmp_path, max_messages=25)
+        loop = _make_loop(tmp_path, context_window_tokens=32_768)
-        assert loop._max_messages == 25
+        assert loop._max_messages == 327
 
-    def test_zero_uses_builtin_limit(self, tmp_path: Path) -> None:
+    def test_provider_refresh_resyncs_context_derived_limit(self, tmp_path: Path) -> None:
-        loop = _make_loop(tmp_path, max_messages=0)
+        old_provider = MagicMock()
-        assert loop._max_messages == DEFAULT_MAX_MESSAGES
+        old_provider.get_default_model.return_value = "old-model"
+        old_provider.generation.max_tokens = 4096
+        new_provider = MagicMock()
+        new_provider.generation.max_tokens = 4096
+        loop = AgentLoop(
+            bus=MessageBus(),
+            provider=old_provider,
+            workspace=tmp_path,
+            model="old-model",
+            context_window_tokens=32_768,
+            provider_snapshot_loader=lambda: ProviderSnapshot(
+                provider=new_provider,
+                model="new-model",
+                context_window_tokens=200_000,
+                signature=("new-model",),
+            ),
+        )
 
-    def test_negative_treated_as_builtin_limit(self, tmp_path: Path) -> None:
+        assert loop._max_messages == 327
-        """Negative values should not produce negative slicing."""
+        loop._refresh_provider_snapshot()
-        loop = _make_loop(tmp_path, max_messages=-5)
+        assert loop._max_messages == FILE_MAX_MESSAGES
-        assert loop._max_messages == DEFAULT_MAX_MESSAGES
 
 
 class TestGetHistoryWithMaxMessages:
@@ -77,7 +104,7 @@ class TestGetHistoryWithMaxMessages:
     def test_default_uses_builtin_limit(self) -> None:
         session = _populated_session(80)
         history = session.get_history()
-        assert len(history) <= DEFAULT_MAX_MESSAGES
+        assert len(history) <= FILE_MAX_MESSAGES
 
     def test_explicit_max_messages_limits_output(self) -> None:
         session = _populated_session(40)  # 80 messages total
@@ -93,7 +120,7 @@ class TestGetHistoryWithMaxMessages:
     def test_max_messages_zero_uses_builtin_limit(self) -> None:
         session = _populated_session(80)  # 160 messages total
         history = session.get_history(max_messages=0)
-        assert len(history) <= DEFAULT_MAX_MESSAGES
+        assert len(history) <= FILE_MAX_MESSAGES
 
     def test_small_session_unaffected(self) -> None:
         """When session has fewer messages than max_messages, all are returned."""
@@ -103,12 +130,13 @@ class TestGetHistoryWithMaxMessages:
 
 
 class TestMaxMessagesIntegration:
-    """Verify the config flows from AgentLoop into get_history calls."""
+    """Verify AgentLoop passes the replay cap into get_history calls."""
 
     @pytest.mark.asyncio
-    async def test_process_message_passes_config_to_history_call(self, tmp_path: Path) -> None:
+    async def test_process_message_passes_limit_to_history_call(self, tmp_path: Path) -> None:
         """The real message path should pass max_messages into session history replay."""
-        loop = _make_loop(tmp_path, max_messages=25)
+        loop = _make_loop(tmp_path)
+        loop._max_messages = 25
         loop.provider.chat_with_retry = AsyncMock(
             return_value=LLMResponse(content="ok", tool_calls=[], usage={})
         )
@@ -127,8 +155,11 @@ class TestMaxMessagesIntegration:
         assert mock_hist.call_args.kwargs["extend_to_user"] is False
 
     @pytest.mark.asyncio
-    async def test_zero_config_passes_builtin_limit_to_history_call(self, tmp_path: Path) -> None:
+    async def test_default_limit_passes_context_derived_limit_to_history_call(
-        loop = _make_loop(tmp_path, max_messages=0)
+        self,
+        tmp_path: Path,
+    ) -> None:
+        loop = _make_loop(tmp_path)
         loop.provider.chat_with_retry = AsyncMock(
             return_value=LLMResponse(content="ok", tool_calls=[], usage={})
         )
@@ -142,7 +173,7 @@ class TestMaxMessagesIntegration:
             )
 
         assert result is not None
-        assert mock_hist.call_args.kwargs["max_messages"] == DEFAULT_MAX_MESSAGES
+        assert mock_hist.call_args.kwargs["max_messages"] == FILE_MAX_MESSAGES
         assert mock_hist.call_args.kwargs["extend_to_user"] is False
 
     @pytest.mark.asyncio
@@ -151,7 +182,8 @@ class TestMaxMessagesIntegration:
         tmp_path: Path,
     ) -> None:
         """A live user turn should not extend history to an older long tool turn."""
-        loop = _make_loop(tmp_path, max_messages=6)
+        loop = _make_loop(tmp_path)
+        loop._max_messages = 6
         loop.provider.chat_with_retry = AsyncMock(
             return_value=LLMResponse(content="ok", tool_calls=[], usage={})
         )
@@ -182,31 +214,3 @@ class TestMaxMessagesIntegration:
         sent_text = "\n".join(str(message.get("content")) for message in sent_messages)
         assert "new question" in sent_text
         assert "long older turn" not in sent_text
-
-
-class TestSchemaConfig:
-    """Verify the config schema accepts max_messages."""
-
-    def test_schema_default(self) -> None:
-        from nanobot.config.schema import AgentDefaults
-
-        defaults = AgentDefaults()
-        assert defaults.max_messages == DEFAULT_MAX_MESSAGES
-
-    def test_schema_accepts_zero_as_builtin_limit(self) -> None:
-        from nanobot.config.schema import AgentDefaults
-
-        defaults = AgentDefaults(max_messages=0)
-        assert defaults.max_messages == 0
-
-    def test_schema_accepts_positive(self) -> None:
-        from nanobot.config.schema import AgentDefaults
-
-        defaults = AgentDefaults(max_messages=25)
-        assert defaults.max_messages == 25
-
-    def test_schema_rejects_negative(self) -> None:
-        from nanobot.config.schema import AgentDefaults
-
-        with pytest.raises(Exception):  # Pydantic validation error
-            AgentDefaults(max_messages=-1)

tests/agent/test_onboard_logic.py

@@ -853,10 +853,11 @@ class TestApiServerRegistration:
         config = Config()
         from nanobot.config.schema import ApiConfig
 
-        new_api = ApiConfig(host="0.0.0.0", port=9999)
+        new_api = ApiConfig(host="0.0.0.0", port=9999, api_key="secret")
         _SETTINGS_SETTER["API Server"](config, new_api)
         assert config.api.host == "0.0.0.0"
         assert config.api.port == 9999
+        assert config.api.api_key == "secret"
 
 
 class TestMainMenuUpdate:

tests/agent/test_runner_errors.py

@@ -135,6 +135,46 @@ async def test_runner_tool_error_sets_final_content():
     assert result.stop_reason == "tool_error"
 
 
+@pytest.mark.asyncio
+async def test_runner_preserves_successful_exec_output_that_starts_with_error():
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock(spec=LLMProvider)
+
+    async def chat_with_retry(*, messages, **kwargs):
+        if not any(msg.get("role") == "tool" for msg in messages):
+            return LLMResponse(
+                content="working",
+                tool_calls=[
+                    ToolCallRequest(id="call_1", name="exec", arguments={"command": "report"})
+                ],
+                usage={},
+            )
+        return LLMResponse(content="done", usage={})
+
+    provider.chat_with_retry = chat_with_retry
+    output = "Error: generated report successfully\n\nExit code: 0"
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    tools.execute = AsyncMock(return_value=output)
+
+    runner = AgentRunner(provider)
+    result = await runner.run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "run report"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=2,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        fail_on_tool_error=True,
+    ))
+
+    assert result.final_content == "done"
+    assert result.stop_reason == "completed"
+    assert result.tool_events == [
+        {"name": "exec", "status": "ok", "detail": "Error: generated report successfully  Exit code: 0"}
+    ]
+
+
 @pytest.mark.asyncio
 async def test_runner_tool_error_preserves_tool_results_in_messages():
     """When a tool raises a fatal error, its results must still be appended

tests/agent/test_runner_governance.py

@@ -15,7 +15,7 @@ from nanobot.agent.context_governance import (
 )
 from nanobot.agent.runner import AgentRunSpec
 from nanobot.config.schema import AgentDefaults
-from nanobot.providers.base import LLMResponse
+from nanobot.providers.base import LLMResponse, ToolCallRequest
 
 _MAX_TOOL_RESULT_CHARS = AgentDefaults().max_tool_result_chars
 
@@ -877,3 +877,162 @@ def test_snip_history_no_user_at_all_falls_back_gracefully(monkeypatch):
         assert non_system[0]["role"] in ("user", "tool"), (
             f"Safety net should ensure first non-system is user/tool, got {non_system[0]['role']}"
         )
+
+
+# ---------------------------------------------------------------------------
+# Malformed tool_call name guard (missing/non-string name wedges the session
+# upstream: messages.content.N.tool_use.name: Input should be a valid string)
+# ---------------------------------------------------------------------------
+
+
+def test_drop_malformed_tool_calls_trims_response():
+    """LLM response tool_calls with a missing/empty name are dropped in place."""
+    from nanobot.agent.runner import AgentRunner
+
+    response = LLMResponse(
+        content=None,
+        tool_calls=[
+            ToolCallRequest(id="1", name=None, arguments={}),
+            ToolCallRequest(id="2", name="", arguments={}),
+            ToolCallRequest(id="3", name="read_file", arguments={}),
+        ],
+        finish_reason="tool_calls",
+    )
+    dropped, all_dropped, orig = AgentRunner._drop_malformed_tool_calls(response)
+    assert [tc.name for tc in response.tool_calls] == ["read_file"]
+    assert response.finish_reason == "tool_calls"
+    assert response.should_execute_tools is True
+    assert dropped == 2
+    assert all_dropped is False
+    assert orig == "tool_calls"
+
+
+def test_drop_malformed_tool_calls_all_bad_disables_execution():
+    """If every tool call is malformed, execution is disabled (no empty exec)."""
+    from nanobot.agent.runner import AgentRunner
+
+    response = LLMResponse(
+        content="some text",
+        tool_calls=[ToolCallRequest(id="1", name=None, arguments={})],
+        finish_reason="tool_calls",
+    )
+    dropped, all_dropped, orig = AgentRunner._drop_malformed_tool_calls(response)
+    assert response.tool_calls == []
+    assert response.finish_reason == "stop"
+    assert response.should_execute_tools is False
+    assert dropped == 1
+    assert all_dropped is True
+    assert orig == "tool_calls"
+
+
+def test_drop_malformed_returns_tuple_no_calls():
+    """No tool calls returns (0, False, current_finish_reason)."""
+    from nanobot.agent.runner import AgentRunner
+
+    response = LLMResponse(content="hi", finish_reason="stop")
+    dropped, all_dropped, orig = AgentRunner._drop_malformed_tool_calls(response)
+    assert dropped == 0
+    assert all_dropped is False
+    assert orig == "stop"
+
+
+def test_strip_malformed_tool_calls_keeps_valid_calls_in_history():
+    """A mixed assistant turn keeps only its valid tool_calls."""
+    messages = [
+        {"role": "user", "content": "hi"},
+        {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {"id": "bad", "type": "function", "function": {"name": None, "arguments": "{}"}},
+                {"id": "ok", "type": "function", "function": {"name": "exec", "arguments": "{}"}},
+            ],
+        },
+        {"role": "tool", "tool_call_id": "ok", "name": "exec", "content": "done"},
+    ]
+    result = ContextGovernor.strip_malformed_tool_calls(messages)
+    assert result is not messages  # copied, original untouched
+    assert len(messages[1]["tool_calls"]) == 2  # original preserved
+    kept = result[1]["tool_calls"]
+    assert [tc["function"]["name"] for tc in kept] == ["exec"]
+
+
+def test_strip_malformed_tool_calls_drops_empty_assistant_turn():
+    """An assistant turn that is only a malformed call is removed entirely;
+    the existing orphan-result cleanup then drops its dangling tool result,
+    so a polluted session self-heals."""
+    messages = [
+        {"role": "user", "content": "hi"},
+        {
+            "role": "assistant",
+            "content": None,
+            "tool_calls": [
+                {"id": "bad", "type": "function", "function": {"name": None, "arguments": "{}"}},
+            ],
+        },
+        {"role": "tool", "tool_call_id": "bad", "name": "", "content": "r"},
+    ]
+    stripped = ContextGovernor.strip_malformed_tool_calls(messages)
+    assert [m["role"] for m in stripped] == ["user", "tool"]
+    healed = ContextGovernor.drop_orphan_tool_results(stripped)
+    assert [m["role"] for m in healed] == ["user"]
+
+
+def test_strip_malformed_tool_calls_noop_when_clean():
+    """Clean history is returned unchanged (same object)."""
+    messages = [
+        {"role": "user", "content": "hi"},
+        {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {"id": "ok", "type": "function", "function": {"name": "exec", "arguments": "{}"}},
+            ],
+        },
+        {"role": "tool", "tool_call_id": "ok", "name": "exec", "content": "done"},
+    ]
+    assert ContextGovernor.strip_malformed_tool_calls(messages) is messages
+
+
+def test_strip_placeholder_assistant_messages_removes_omitted():
+    """Placeholder assistant messages are removed; real messages kept."""
+    messages = [
+        {"role": "user", "content": "hi"},
+        {"role": "assistant", "content": "real response"},
+        {"role": "user", "content": "ok"},
+        {"role": "assistant", "content": "[Previous assistant message omitted.]"},
+        {"role": "user", "content": "?"},
+        {"role": "assistant", "content": "[Previous assistant message omitted.]"},
+        {"role": "user", "content": "hello"},
+    ]
+    result = ContextGovernor.strip_placeholder_assistant_messages(messages)
+    assert [m["role"] for m in result] == [
+        "user", "assistant", "user", "user", "user",
+    ]
+    assert result[1]["content"] == "real response"
+
+
+def test_strip_placeholder_noop_when_clean():
+    """Clean history is returned unchanged (same object)."""
+    messages = [
+        {"role": "user", "content": "hi"},
+        {"role": "assistant", "content": "hello back"},
+    ]
+    assert ContextGovernor.strip_placeholder_assistant_messages(messages) is messages
+
+
+def test_strip_placeholder_keeps_assistant_with_tool_calls():
+    """A placeholder assistant that also carries tool_calls is kept."""
+    messages = [
+        {"role": "user", "content": "hi"},
+        {
+            "role": "assistant",
+            "content": "[Previous assistant message omitted.]",
+            "tool_calls": [
+                {"id": "1", "type": "function", "function": {"name": "exec", "arguments": "{}"}},
+            ],
+        },
+        {"role": "tool", "tool_call_id": "1", "name": "exec", "content": "done"},
+    ]
+    result = ContextGovernor.strip_placeholder_assistant_messages(messages)
+    assert result is messages

tests/agent/test_runner_safety.py

@@ -6,6 +6,8 @@ from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
+from nanobot.agent.runner import AgentRunner, AgentRunSpec
+from nanobot.agent.tools import ToolResult
 from nanobot.config.schema import AgentDefaults
 from nanobot.providers.base import LLMResponse, ToolCallRequest
 
@@ -20,8 +22,6 @@ async def test_runner_does_not_abort_on_workspace_violation_anymore():
     we now hand the error back to the LLM as a recoverable tool result and
     rely on ``repeated_workspace_violation_error`` to throttle bypass loops.
     """
-    from nanobot.agent.runner import AgentRunSpec, AgentRunner
-
     provider = MagicMock()
     provider.chat_with_retry = AsyncMock(side_effect=[
         LLMResponse(
@@ -64,8 +64,6 @@ async def test_runner_does_not_abort_on_workspace_violation_anymore():
 
 def test_is_ssrf_violation_recognizes_private_url_blocks():
     """SSRF rejections are classified separately from workspace boundaries."""
-    from nanobot.agent.runner import AgentRunner
-
     ssrf_msg = "Error: Command blocked by safety guard (internal/private URL detected)"
     assert AgentRunner._is_ssrf_violation(ssrf_msg) is True
     assert AgentRunner._is_ssrf_violation(
@@ -88,8 +86,6 @@ def test_is_ssrf_violation_recognizes_private_url_blocks():
 @pytest.mark.asyncio
 async def test_runner_returns_non_retryable_hint_on_ssrf_violation():
     """SSRF stays blocked, but the runtime gives the LLM a final chance to recover."""
-    from nanobot.agent.runner import AgentRunSpec, AgentRunner
-
     provider = MagicMock()
     provider.chat_with_retry = AsyncMock(side_effect=[
         LLMResponse(
@@ -107,7 +103,7 @@ async def test_runner_returns_non_retryable_hint_on_ssrf_violation():
     ])
     tools = MagicMock()
     tools.get_definitions.return_value = []
-    tools.execute = AsyncMock(return_value=(
+    tools.execute = AsyncMock(return_value=ToolResult.error(
         "Error: Command blocked by safety guard (internal/private URL detected)"
     ))
 
@@ -141,8 +137,6 @@ async def test_runner_lets_llm_recover_from_shell_guard_path_outside():
     turn (silent hang on Telegram per #3605); now the LLM gets the soft
     error back and can finalize on the next iteration.
     """
-    from nanobot.agent.runner import AgentRunSpec, AgentRunner
-
     provider = MagicMock()
     captured_second_call: list[dict] = []
 
@@ -163,7 +157,9 @@ async def test_runner_lets_llm_recover_from_shell_guard_path_outside():
     tools = MagicMock()
     tools.get_definitions.return_value = []
     tools.execute = AsyncMock(
-        return_value="Error: Command blocked by safety guard (path outside working dir)"
+        return_value=ToolResult.error(
+            "Error: Command blocked by safety guard (path outside working dir)"
+        )
     )
 
     runner = AgentRunner(provider)
@@ -195,8 +191,6 @@ async def test_runner_throttles_repeated_workspace_bypass_attempts():
     the runner replaces the tool result with a hard "stop trying" message
     so the model finally gives up and surfaces the boundary to the user.
     """
-    from nanobot.agent.runner import AgentRunSpec, AgentRunner
-
     bypass_attempts = [
         ToolCallRequest(
             id=f"a{i}", name="exec",
@@ -215,7 +209,9 @@ async def test_runner_throttles_repeated_workspace_bypass_attempts():
     tools = MagicMock()
     tools.get_definitions.return_value = []
     tools.execute = AsyncMock(
-        return_value="Error: Command blocked by safety guard (path outside working dir)"
+        return_value=ToolResult.error(
+            "Error: Command blocked by safety guard (path outside working dir)"
+        )
     )
 
     runner = AgentRunner(provider)

tests/agent/test_runner_tool_execution.py

@@ -8,7 +8,9 @@ from unittest.mock import AsyncMock, MagicMock, patch
 import pytest
 
 from nanobot.agent.runner import AgentRunner, AgentRunSpec
-from nanobot.agent.tools.base import Tool
+from nanobot.agent.tools.base import Tool, ToolResult
+from nanobot.agent.tools.context import ToolContext
+from nanobot.agent.tools.loader import ToolLoader
 from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.config.schema import AgentDefaults
 from nanobot.providers.base import LLMResponse, ToolCallRequest
@@ -61,6 +63,40 @@ class _DelayTool(Tool):
         return self._name
 
 
+class _LegacyErrorPluginTool(Tool):
+    @property
+    def name(self) -> str:
+        return "legacy_plugin"
+
+    @property
+    def description(self) -> str:
+        return "legacy entry-point plugin"
+
+    @property
+    def parameters(self) -> dict:
+        return {"type": "object", "properties": {}, "required": []}
+
+    async def execute(self, **kwargs):
+        return "Error: legacy plugin failed"
+
+
+class _StructuredSuccessPluginTool(Tool):
+    @property
+    def name(self) -> str:
+        return "structured_success_plugin"
+
+    @property
+    def description(self) -> str:
+        return "structured entry-point plugin"
+
+    @property
+    def parameters(self) -> dict:
+        return {"type": "object", "properties": {}, "required": []}
+
+    async def execute(self, **kwargs):
+        return ToolResult("Error: generated report successfully")
+
+
 async def _run_optional_tool_response(response: LLMResponse):
     provider = MagicMock()
     calls = {"n": 0}
@@ -91,6 +127,20 @@ async def _run_optional_tool_response(response: LLMResponse):
     return result, shared_events
 
 
+def _load_entry_point_plugin(tool_cls: type[Tool], tmp_path) -> ToolRegistry:
+    mock_ep = MagicMock()
+    mock_ep.name = tool_cls.__name__
+    mock_ep.load.return_value = tool_cls
+
+    registry = ToolRegistry()
+    with patch("nanobot.agent.tools.loader.entry_points", return_value=[mock_ep]):
+        ToolLoader(test_classes=[]).load(
+            ToolContext(config=None, workspace=str(tmp_path)),
+            registry,
+        )
+    return registry
+
+
 def _tool_message(result, tool_call_id: str) -> dict:
     return [
         msg for msg in result.messages
@@ -320,6 +370,63 @@ async def test_runner_rejects_openai_responses_array_arguments_without_executing
     assert "parameters must be a JSON object" in tool_message["content"]
 
 
+@pytest.mark.asyncio
+async def test_runner_treats_legacy_entry_point_error_prefix_as_tool_error(tmp_path):
+    provider = MagicMock()
+    provider.chat_with_retry = AsyncMock(return_value=LLMResponse(
+        content="working",
+        tool_calls=[ToolCallRequest(id="call_1", name="legacy_plugin", arguments={})],
+        usage={},
+    ))
+
+    result = await AgentRunner(provider).run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "run plugin"}],
+        tools=_load_entry_point_plugin(_LegacyErrorPluginTool, tmp_path),
+        model="test-model",
+        max_iterations=1,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        fail_on_tool_error=True,
+    ))
+
+    assert result.stop_reason == "tool_error"
+    assert result.tool_events == [
+        {"name": "legacy_plugin", "status": "error", "detail": "Error: legacy plugin failed"}
+    ]
+
+
+@pytest.mark.asyncio
+async def test_runner_preserves_structured_plugin_success_that_starts_with_error(tmp_path):
+    provider = MagicMock()
+    provider.chat_with_retry = AsyncMock(side_effect=[
+        LLMResponse(
+            content="working",
+            tool_calls=[
+                ToolCallRequest(id="call_1", name="structured_success_plugin", arguments={})
+            ],
+            usage={},
+        ),
+        LLMResponse(content="done", tool_calls=[], usage={}),
+    ])
+
+    result = await AgentRunner(provider).run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "run plugin"}],
+        tools=_load_entry_point_plugin(_StructuredSuccessPluginTool, tmp_path),
+        model="test-model",
+        max_iterations=2,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        fail_on_tool_error=True,
+    ))
+
+    assert result.stop_reason == "completed"
+    assert result.tool_events == [
+        {
+            "name": "structured_success_plugin",
+            "status": "ok",
+            "detail": "Error: generated report successfully",
+        }
+    ]
+
+
 @pytest.mark.asyncio
 async def test_runner_blocks_repeated_external_fetches():
     provider = MagicMock()

tests/agent/test_session_collision.py

@@ -0,0 +1,170 @@
+"""Regression tests for collision-resistant session filenames."""
+
+import json
+from datetime import datetime
+from pathlib import Path
+
+from nanobot.session.manager import Session, SessionManager
+from nanobot.utils.helpers import safe_filename
+
+
+def _manager(tmp_path: Path, monkeypatch) -> SessionManager:
+    monkeypatch.setattr(
+        "nanobot.session.manager.get_legacy_sessions_dir",
+        lambda: tmp_path / "legacy_sessions",
+    )
+    return SessionManager(tmp_path / "workspace")
+
+
+def _write_session_file(path: Path, key: str, content: str) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    metadata = {
+        "_type": "metadata",
+        "key": key,
+        "created_at": datetime(2025, 1, 1).isoformat(),
+        "updated_at": datetime(2025, 1, 1).isoformat(),
+        "metadata": {"source": "test"},
+        "last_consolidated": 0,
+    }
+    message = {"role": "user", "content": content}
+    path.write_text(
+        json.dumps(metadata) + "\n" + json.dumps(message) + "\n",
+        encoding="utf-8",
+    )
+
+
+def test_distinct_keys_have_distinct_filenames(tmp_path: Path, monkeypatch) -> None:
+    sm = _manager(tmp_path, monkeypatch)
+
+    first = sm._get_session_path("telegram:a_b")
+    second = sm._get_session_path("telegram:a:b")
+
+    assert first.name != second.name
+    assert sm.safe_key("telegram:a_b") == sm.safe_key("telegram:a:b")
+    assert sm._storage_key("telegram:a_b") != sm._storage_key("telegram:a:b")
+
+
+def test_save_uses_new_path_not_lossy(tmp_path: Path, monkeypatch) -> None:
+    sm = _manager(tmp_path, monkeypatch)
+    key = "telegram:a:b"
+    session = Session(key=key)
+    session.add_message("user", "first")
+    sm.save(session)
+
+    new_path = sm._get_session_path(key)
+    lossy_path = sm._get_legacy_lossy_path(key)
+    _write_session_file(lossy_path, key, "stale lossy content")
+    stale_lossy = lossy_path.read_text(encoding="utf-8")
+
+    session.add_message("assistant", "latest content")
+    sm.save(session)
+
+    assert new_path.exists()
+    assert lossy_path.exists()
+    assert "latest content" in new_path.read_text(encoding="utf-8")
+    assert lossy_path.read_text(encoding="utf-8") == stale_lossy
+
+
+def test_load_falls_back_to_lossy_path(tmp_path: Path, monkeypatch) -> None:
+    sm = _manager(tmp_path, monkeypatch)
+    key = "telegram:legacy:lossy"
+    lossy_path = sm._get_legacy_lossy_path(key)
+    _write_session_file(lossy_path, key, "loaded from lossy")
+
+    session = sm._load(key)
+
+    assert session is not None
+    assert session.metadata == {"source": "test"}
+    assert session.messages[0]["content"] == "loaded from lossy"
+
+
+def test_load_migrates_lossy_to_new_path(tmp_path: Path, monkeypatch) -> None:
+    sm = _manager(tmp_path, monkeypatch)
+    key = "telegram:migrate:lossy"
+    new_path = sm._get_session_path(key)
+    lossy_path = sm._get_legacy_lossy_path(key)
+    _write_session_file(lossy_path, key, "migrate me")
+
+    session = sm._load(key)
+
+    assert session is not None
+    assert session.messages[0]["content"] == "migrate me"
+    assert new_path.exists()
+    assert not lossy_path.exists()
+
+
+def test_load_does_not_migrate_lossy_path_for_different_stored_key(
+    tmp_path: Path,
+    monkeypatch,
+) -> None:
+    sm = _manager(tmp_path, monkeypatch)
+    first_key = "telegram:a_b"
+    second_key = "telegram:a:b"
+    lossy_path = sm._get_legacy_lossy_path(first_key)
+    assert lossy_path == sm._get_legacy_lossy_path(second_key)
+    _write_session_file(lossy_path, first_key, "belongs to first")
+
+    loaded_second = sm._load(second_key)
+
+    assert loaded_second is None
+    assert lossy_path.exists()
+    assert not sm._get_session_path(second_key).exists()
+
+    loaded_first = sm._load(first_key)
+
+    assert loaded_first is not None
+    assert loaded_first.messages[0]["content"] == "belongs to first"
+    assert sm._get_session_path(first_key).exists()
+    assert not lossy_path.exists()
+
+
+def test_safe_key_is_lossy() -> None:
+    assert SessionManager.safe_key("telegram:a_b") == SessionManager.safe_key("telegram:a:b")
+
+
+def test_storage_key_is_collision_resistant() -> None:
+    encoded = {
+        SessionManager._storage_key("a:b"),
+        SessionManager._storage_key("a_b"),
+        SessionManager._storage_key("a:b:c"),
+    }
+
+    assert len(encoded) == 3
+    assert SessionManager._storage_key("telegram:a_b") != SessionManager._storage_key("telegram:a:b")
+
+
+def test_lossy_path_helper_returns_expected_path(tmp_path: Path, monkeypatch) -> None:
+    sm = _manager(tmp_path, monkeypatch)
+    key = "telegram:a:b"
+    expected = sm.sessions_dir / f"{safe_filename(key.replace(':', '_'))}.jsonl"
+
+    assert sm._get_legacy_lossy_path(key) == expected
+
+
+def test_storage_paths_are_distinct_when_keys_collide_under_safe_key(
+    tmp_path: Path,
+    monkeypatch,
+) -> None:
+    sm = _manager(tmp_path, monkeypatch)
+    first = Session(key="telegram:a_b")
+    first.add_message("user", "underscore history")
+    second = Session(key="telegram:a:b")
+    second.add_message("user", "colon history")
+
+    sm.save(first)
+    sm.save(second)
+
+    assert sm.safe_key(first.key) == sm.safe_key(second.key)
+    assert sm._get_session_path(first.key).exists()
+    assert sm._get_session_path(second.key).exists()
+    assert sm._get_session_path(first.key) != sm._get_session_path(second.key)
+
+    sm.invalidate(first.key)
+    sm.invalidate(second.key)
+    loaded_first = sm._load(first.key)
+    loaded_second = sm._load(second.key)
+
+    assert loaded_first is not None
+    assert loaded_second is not None
+    assert loaded_first.messages[0]["content"] == "underscore history"
+    assert loaded_second.messages[0]["content"] == "colon history"

tests/agent/test_session_delete.py

@@ -58,11 +58,11 @@ def test_read_session_file_missing(tmp_path: Path) -> None:
     assert sm.read_session_file("nope:none") is None
 
 
-def test_safe_key_matches_internal_path(tmp_path: Path) -> None:
+def test_storage_key_matches_internal_path(tmp_path: Path) -> None:
     sm = SessionManager(tmp_path)
     key = "telegram:abc/def"
     expected = sm._get_session_path(key).name
-    assert SessionManager.safe_key(key) + ".jsonl" == expected
+    assert SessionManager._storage_key(key) + ".jsonl" == expected
 
 
 def _write_legacy_session(legacy_dir: Path, key: str, roles: list[str]) -> Path:

tests/agent/test_session_manager_history.py

@@ -685,12 +685,12 @@ def test_retain_recent_legal_suffix_returns_dropped_messages():
     for i in range(10):
         session.messages.append({"role": "user", "content": f"msg{i}"})
 
-    dropped, already_cons = session.retain_recent_legal_suffix(4)
+    result = session.retain_recent_legal_suffix(4)
 
-    assert len(dropped) == 6
+    assert len(result.dropped) == 6
-    assert [m["content"] for m in dropped] == [f"msg{i}" for i in range(6)]
+    assert [m["content"] for m in result.dropped] == [f"msg{i}" for i in range(6)]
     assert len(session.messages) == 4
-    assert already_cons == 0
+    assert result.already_consolidated_count == 0
 
 
 def test_retain_recent_legal_suffix_returns_empty_when_no_drop():
@@ -699,10 +699,10 @@ def test_retain_recent_legal_suffix_returns_empty_when_no_drop():
     for i in range(3):
         session.messages.append({"role": "user", "content": f"msg{i}"})
 
-    dropped, already_cons = session.retain_recent_legal_suffix(4)
+    result = session.retain_recent_legal_suffix(4)
 
-    assert dropped == []
+    assert result.dropped == []
-    assert already_cons == 0
+    assert result.already_consolidated_count == 0
     assert len(session.messages) == 3
 
 
@@ -713,10 +713,10 @@ def test_retain_recent_legal_suffix_returns_all_on_zero():
         session.messages.append({"role": "user", "content": f"msg{i}"})
     session.last_consolidated = 3
 
-    dropped, already_cons = session.retain_recent_legal_suffix(0)
+    result = session.retain_recent_legal_suffix(0)
 
-    assert len(dropped) == 5
+    assert len(result.dropped) == 5
-    assert already_cons == 3
+    assert result.already_consolidated_count == 3
     assert session.messages == []
 
 
@@ -820,11 +820,11 @@ def test_retain_recent_legal_suffix_last_consolidated_correct_in_else_branch():
         session.messages.append({"role": "assistant", "content": f"a{i}"})
     session.last_consolidated = 12  # u0..u9, a0, a1 consolidated
 
-    dropped, already_cons = session.retain_recent_legal_suffix(4)
+    result = session.retain_recent_legal_suffix(4)
 
     # Retained messages start from latest user (u9) + max_messages forward
     # so retained = [u9, a0..a9][:4] → but these are from original indices 9..12
     # Of those, indices 9,10,11 are < 12 (before_lc), so new_lc = 3
     assert session.last_consolidated == 3
     # already_cons should count dropped messages with original index < 12
-    assert already_cons == 9
+    assert result.already_consolidated_count == 9

tests/agent/test_task_cancel.py

@@ -127,6 +127,7 @@ class TestDispatch:
     @pytest.mark.asyncio
     async def test_dispatch_streaming_preserves_message_metadata(self):
         from nanobot.bus.events import InboundMessage
+        from nanobot.bus.outbound_events import StreamDeltaEvent, StreamEndEvent
 
         loop, bus = _make_loop()
         msg = InboundMessage(
@@ -156,10 +157,10 @@ class TestDispatch:
 
         assert first.metadata["thread_root_event_id"] == "$root1"
         assert first.metadata["thread_reply_to_event_id"] == "$reply1"
-        assert first.metadata["_stream_delta"] is True
+        assert isinstance(first.event, StreamDeltaEvent)
         assert second.metadata["thread_root_event_id"] == "$root1"
         assert second.metadata["thread_reply_to_event_id"] == "$reply1"
-        assert second.metadata["_stream_end"] is True
+        assert isinstance(second.event, StreamEndEvent)
 
     @pytest.mark.asyncio
     async def test_processing_lock_serializes(self):

tests/agent/test_tool_hint.py

@@ -1,7 +1,7 @@
 """Tests for tool hint formatting (nanobot.utils.tool_hints)."""
 
-from nanobot.utils.tool_hints import format_tool_hints
 from nanobot.providers.base import ToolCallRequest
+from nanobot.utils.tool_hints import format_tool_hints
 
 
 def _tc(name: str, args) -> ToolCallRequest:
@@ -306,3 +306,22 @@ class TestToolHintMaxLength:
         short = _hint([_tc("list_dir", {"path": long_path})], max_length=40)
         long = _hint([_tc("list_dir", {"path": long_path})], max_length=120)
         assert len(long) > len(short)
+
+
+class TestToolHintMalformedCalls:
+    """Malformed tool calls must not crash hint formatting (see HKUDS/nanobot)."""
+
+    def test_none_name_is_skipped(self):
+        """A tool call with name=None should be skipped, not raise AttributeError."""
+        result = _hint([_tc(None, None)])
+        assert result == ""
+
+    def test_empty_name_is_skipped(self):
+        """A tool call with an empty name should be skipped."""
+        result = _hint([_tc("", {"path": "foo.txt"})])
+        assert result == ""
+
+    def test_none_name_mixed_with_valid_call(self):
+        """A degenerate call must not suppress hints for the valid calls beside it."""
+        result = _hint([_tc(None, None), _tc("read_file", {"path": "foo.txt"})])
+        assert result == "read foo.txt"

tests/agent/test_tool_loader_entrypoints.py

@@ -1,7 +1,11 @@
 from unittest.mock import MagicMock, patch
 
+import pytest
+
 from nanobot.agent.tools.base import Tool
+from nanobot.agent.tools.context import ToolContext
 from nanobot.agent.tools.loader import ToolLoader
+from nanobot.agent.tools.registry import ToolRegistry, is_tool_error_result
 
 
 def test_loader_discovers_entry_point_tools():
@@ -74,3 +78,67 @@ def test_loader_skips_abstract_entry_point_tools():
         discovered = loader._discover_plugins()
 
     assert "abstract_plugin" not in discovered
+
+
+@pytest.mark.asyncio
+async def test_loader_entry_point_error_wrapper_preserves_tool_api(tmp_path):
+    """Only adapt legacy plugin error strings; keep the wrapped tool API intact."""
+    mock_ep = MagicMock()
+    mock_ep.name = "api_plugin"
+
+    class _ApiPluginTool(Tool):
+        config_key = "api_plugin"
+
+        @property
+        def name(self) -> str:
+            return "api_plugin"
+
+        @property
+        def description(self) -> str:
+            return "Entry-point plugin with custom tool API methods."
+
+        @property
+        def parameters(self) -> dict:
+            return {"type": "object", "properties": {"value": {"type": "string"}}}
+
+        @property
+        def read_only(self) -> bool:
+            return True
+
+        @property
+        def concurrency_safe(self) -> bool:
+            return False
+
+        def cast_params(self, params: dict) -> dict:
+            return {"value": str(params["value"])}
+
+        def validate_params(self, params: dict) -> list[str]:
+            return [] if params == {"value": "1"} else ["bad value"]
+
+        def to_schema(self) -> dict:
+            return {"name": self.name, "custom": True}
+
+        async def execute(self, **_):
+            return "Error: plugin failed"
+
+    mock_ep.load.return_value = _ApiPluginTool
+
+    registry = ToolRegistry()
+    with patch("nanobot.agent.tools.loader.entry_points", return_value=[mock_ep]):
+        ToolLoader(test_classes=[]).load(
+            ToolContext(config=None, workspace=str(tmp_path)),
+            registry,
+        )
+
+    tool = registry.get("api_plugin")
+    assert tool is not None
+    assert tool.config_key == "api_plugin"
+    assert tool.read_only is True
+    assert tool.concurrency_safe is False
+    assert tool.cast_params({"value": 1}) == {"value": "1"}
+    assert tool.validate_params({"value": "1"}) == []
+    assert tool.to_schema() == {"name": "api_plugin", "custom": True}
+
+    result = await tool.execute(value="1")
+    assert is_tool_error_result("api_plugin", result) is True
+    assert str(result) == "Error: plugin failed"

tests/agent/tools/test_long_task.py

@@ -13,6 +13,7 @@ from nanobot.agent.tools.long_task import (
     CompleteGoalTool,
     LongTaskTool,
 )
+from nanobot.bus.outbound_events import GoalStateSyncEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.bus.runtime_events import RuntimeEventBus
 from nanobot.session.goal_state import GOAL_STATE_KEY
@@ -144,8 +145,8 @@ async def test_long_task_publishes_goal_state_ws_after_save(tmp_path):
     call = bus.publish_outbound.await_args.args[0]
     assert call.channel == "websocket"
     assert call.chat_id == "chat-99"
-    assert call.metadata.get("_goal_state_sync") is True
+    assert isinstance(call.event, GoalStateSyncEvent)
-    assert call.metadata["goal_state"] == {
+    assert call.event.goal_state == {
         "active": True,
         "ui_summary": "alpha",
         "objective": "Objective alpha",
@@ -180,7 +181,8 @@ async def test_complete_goal_publishes_inactive_goal_state_ws(tmp_path):
 
     bus.publish_outbound.assert_awaited_once()
     call = bus.publish_outbound.await_args.args[0]
-    assert call.metadata["goal_state"] == {"active": False}
+    assert isinstance(call.event, GoalStateSyncEvent)
+    assert call.event.goal_state == {"active": False}
 
 
 @pytest.mark.asyncio

tests/agent/tools/test_self_tool.py

@@ -236,10 +236,12 @@ class TestModifyRestricted:
 
     @pytest.mark.asyncio
     async def test_modify_context_window_valid(self):
-        tool = _make_tool()
+        loop = _make_mock_loop(_sync_replay_max_messages=MagicMock())
+        tool = _make_tool(runtime_state=loop)
         result = await tool.execute(action="set", key="context_window_tokens", value=131072)
         assert "Set context_window_tokens" in result
-        assert tool._runtime_state.context_window_tokens == 131072
+        assert loop.context_window_tokens == 131072
+        loop._sync_replay_max_messages.assert_called_once_with()
 
     @pytest.mark.asyncio
     async def test_modify_none_value_for_restricted_int(self):

tests/bus/test_outbound_events.py

@@ -0,0 +1,244 @@
+from __future__ import annotations
+
+from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import (
+    GoalStateSyncEvent,
+    GoalStatusEvent,
+    ProgressEvent,
+    RetryWaitEvent,
+    RuntimeModelUpdatedEvent,
+    SessionUpdatedEvent,
+    StreamDeltaEvent,
+    StreamedResponseEvent,
+    StreamEndEvent,
+    TurnEndEvent,
+    outbound_event_from_message,
+    outbound_message_for_event,
+    replace_outbound_event,
+)
+
+
+def test_progress_event_lives_on_outbound_message_event_field() -> None:
+    tool_events = [{"phase": "start", "name": "read_file"}]
+    file_edit_events = [{"phase": "end", "path": "app.py"}]
+
+    msg = outbound_message_for_event(
+        channel="websocket",
+        chat_id="chat-1",
+        event=ProgressEvent(
+            content="working",
+            tool_hint=True,
+            reasoning_delta=True,
+            stream_id="r1",
+            tool_events=tool_events,
+            file_edit_events=file_edit_events,
+        ),
+        metadata={"origin_message_id": "m1"},
+    )
+
+    assert msg.content == "working"
+    assert msg.metadata == {"origin_message_id": "m1"}
+
+    event = outbound_event_from_message(msg)
+    assert isinstance(event, ProgressEvent)
+    assert event.content == "working"
+    assert event.tool_hint is True
+    assert event.reasoning_delta is True
+    assert event.stream_id == "r1"
+    assert event.tool_events == tool_events
+    assert event.file_edit_events == file_edit_events
+
+
+def test_normal_outbound_message_has_no_runtime_event() -> None:
+    msg = OutboundMessage(channel="websocket", chat_id="chat-1", content="hello")
+
+    assert outbound_event_from_message(msg) is None
+
+
+def test_legacy_progress_metadata_flags_create_runtime_event() -> None:
+    tool_events = [{"phase": "start", "name": "read_file"}]
+    file_edit_events = [{"phase": "end", "path": "app.py"}]
+    msg = OutboundMessage(
+        channel="websocket",
+        chat_id="chat-1",
+        content="legacy progress",
+        metadata={
+            "_progress": True,
+            "_tool_hint": True,
+            "_reasoning_delta": True,
+            "_stream_id": "r1",
+            "_tool_events": tool_events,
+            "_file_edit_events": file_edit_events,
+            "message_id": "platform-routing-context",
+        },
+    )
+
+    event = outbound_event_from_message(msg)
+    assert isinstance(event, ProgressEvent)
+    assert event.content == "legacy progress"
+    assert event.tool_hint is True
+    assert event.reasoning_delta is True
+    assert event.stream_id == "r1"
+    assert event.tool_events == tool_events
+    assert event.file_edit_events == file_edit_events
+
+
+def test_legacy_stream_metadata_flags_create_runtime_events() -> None:
+    delta = OutboundMessage(
+        channel="websocket",
+        chat_id="chat-1",
+        content="hello",
+        metadata={"_stream_delta": True, "_stream_id": "s1"},
+    )
+    end = OutboundMessage(
+        channel="websocket",
+        chat_id="chat-1",
+        content="",
+        metadata={"_stream_end": True, "_stream_id": "s1", "_resuming": True},
+    )
+
+    delta_event = outbound_event_from_message(delta)
+    assert isinstance(delta_event, StreamDeltaEvent)
+    assert delta_event.content == "hello"
+    assert delta_event.stream_id == "s1"
+
+    end_event = outbound_event_from_message(end)
+    assert isinstance(end_event, StreamEndEvent)
+    assert end_event.stream_id == "s1"
+    assert end_event.resuming is True
+
+
+def test_legacy_webui_runtime_metadata_flags_create_runtime_events() -> None:
+    runtime = OutboundMessage(
+        channel="websocket",
+        chat_id="*",
+        content="",
+        metadata={
+            "_runtime_model_updated": True,
+            "model": "gpt-5.5",
+            "model_preset": "high",
+        },
+    )
+    goal_state = OutboundMessage(
+        channel="websocket",
+        chat_id="chat-1",
+        content="",
+        metadata={"_goal_state_sync": True, "goal_state": {"active": True}},
+    )
+    goal_status = OutboundMessage(
+        channel="websocket",
+        chat_id="chat-1",
+        content="",
+        metadata={"_goal_status": True, "goal_status": "running", "started_at": 1.25},
+    )
+    turn_end = OutboundMessage(
+        channel="websocket",
+        chat_id="chat-1",
+        content="",
+        metadata={"_turn_end": True, "latency_ms": 42.0, "goal_state": {"active": False}},
+    )
+    session_updated = OutboundMessage(
+        channel="websocket",
+        chat_id="chat-1",
+        content="",
+        metadata={"_session_updated": True, "_session_update_scope": "metadata"},
+    )
+
+    runtime_event = outbound_event_from_message(runtime)
+    assert isinstance(runtime_event, RuntimeModelUpdatedEvent)
+    assert runtime_event.model == "gpt-5.5"
+    assert runtime_event.model_preset == "high"
+
+    goal_state_event = outbound_event_from_message(goal_state)
+    assert isinstance(goal_state_event, GoalStateSyncEvent)
+    assert goal_state_event.goal_state == {"active": True}
+
+    goal_status_event = outbound_event_from_message(goal_status)
+    assert isinstance(goal_status_event, GoalStatusEvent)
+    assert goal_status_event.status == "running"
+    assert goal_status_event.started_at == 1.25
+
+    turn_end_event = outbound_event_from_message(turn_end)
+    assert isinstance(turn_end_event, TurnEndEvent)
+    assert turn_end_event.latency_ms == 42
+    assert turn_end_event.goal_state == {"active": False}
+
+    session_updated_event = outbound_event_from_message(session_updated)
+    assert isinstance(session_updated_event, SessionUpdatedEvent)
+    assert session_updated_event.scope == "metadata"
+
+
+def test_legacy_metadata_numbers_ignore_bool_values() -> None:
+    goal_status = OutboundMessage(
+        channel="websocket",
+        chat_id="chat-1",
+        content="",
+        metadata={"_goal_status": True, "goal_status": "running", "started_at": True},
+    )
+    turn_end = OutboundMessage(
+        channel="websocket",
+        chat_id="chat-1",
+        content="",
+        metadata={"_turn_end": True, "latency_ms": True},
+    )
+
+    goal_status_event = outbound_event_from_message(goal_status)
+    assert isinstance(goal_status_event, GoalStatusEvent)
+    assert goal_status_event.started_at is None
+
+    turn_end_event = outbound_event_from_message(turn_end)
+    assert isinstance(turn_end_event, TurnEndEvent)
+    assert turn_end_event.latency_ms is None
+
+
+def test_legacy_retry_wait_and_streamed_flags_create_runtime_events() -> None:
+    retry = OutboundMessage(
+        channel="cli",
+        chat_id="direct",
+        content="waiting",
+        metadata={"_retry_wait": True},
+    )
+    streamed = OutboundMessage(
+        channel="cli",
+        chat_id="direct",
+        content="final answer",
+        metadata={"_streamed": True},
+    )
+
+    retry_event = outbound_event_from_message(retry)
+    assert isinstance(retry_event, RetryWaitEvent)
+    assert retry_event.content == "waiting"
+    assert isinstance(outbound_event_from_message(streamed), StreamedResponseEvent)
+
+
+def test_replace_outbound_event_keeps_routing_metadata() -> None:
+    msg = outbound_message_for_event(
+        channel="websocket",
+        chat_id="chat-1",
+        event=StreamDeltaEvent(content="hello", stream_id="s1"),
+        metadata={"message_id": "m1"},
+    )
+
+    updated = replace_outbound_event(
+        msg,
+        StreamEndEvent(stream_id="s1", resuming=True),
+        content="hello world",
+    )
+
+    assert updated.content == "hello world"
+    assert updated.metadata == {"message_id": "m1"}
+    assert isinstance(updated.event, StreamEndEvent)
+    assert updated.event.stream_id == "s1"
+    assert updated.event.resuming is True
+
+
+def test_streamed_response_event_keeps_final_content_outside_event_payload() -> None:
+    msg = outbound_message_for_event(
+        channel="cli",
+        chat_id="direct",
+        event=StreamedResponseEvent(),
+        content="final answer",
+    )
+
+    assert msg.content == "final answer"
+    assert isinstance(outbound_event_from_message(msg), StreamedResponseEvent)

tests/channels/test_channel_manager_delta_coalescing.py

@@ -1,10 +1,19 @@
 """Tests for ChannelManager delta coalescing to reduce streaming latency."""
+
 import asyncio
 from unittest.mock import AsyncMock
 
 import pytest
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import (
+    ProgressEvent,
+    RetryWaitEvent,
+    StreamDeltaEvent,
+    StreamEndEvent,
+    outbound_event_from_message,
+    outbound_message_for_event,
+)
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.channels.manager import ChannelManager
@@ -29,196 +38,187 @@ class MockChannel(BaseChannel):
         pass
 
     async def send(self, msg):
-        """Implement abstract method."""
         return await self._send_mock(msg)
 
-    async def send_delta(self, chat_id, delta, metadata=None):
+    async def send_delta(
-        """Override send_delta for testing."""
+        self,
-        return await self._send_delta_mock(chat_id, delta, metadata)
+        chat_id,
+        delta,
+        metadata=None,
+        *,
+        stream_id=None,
+        stream_end=False,
+        resuming=False,
+    ):
+        return await self._send_delta_mock(
+            chat_id,
+            delta,
+            metadata,
+            stream_id=stream_id,
+            stream_end=stream_end,
+            resuming=resuming,
+        )
 
 
 @pytest.fixture
 def config():
-    """Create a minimal config for testing."""
     return Config()
 
 
 @pytest.fixture
 def bus():
-    """Create a message bus for testing."""
     return MessageBus()
 
 
 @pytest.fixture
 def manager(config, bus):
-    """Create a channel manager with a mock channel."""
     manager = ChannelManager(config, bus)
     manager.channels["mock"] = MockChannel({}, bus)
     return manager
 
 
+def _delta(content: str, *, chat_id: str = "chat1", stream_id: str | None = None):
+    return outbound_message_for_event(
+        channel="mock",
+        chat_id=chat_id,
+        event=StreamDeltaEvent(content=content, stream_id=stream_id),
+    )
+
+
+def _end(
+    content: str = "",
+    *,
+    chat_id: str = "chat1",
+    stream_id: str | None = None,
+    resuming: bool = False,
+):
+    return outbound_message_for_event(
+        channel="mock",
+        chat_id=chat_id,
+        event=StreamEndEvent(content=content, stream_id=stream_id, resuming=resuming),
+    )
+
+
 class TestDeltaCoalescing:
-    """Tests for _stream_delta message coalescing."""
+    """Tests for stream delta message coalescing."""
 
     @pytest.mark.asyncio
     async def test_single_delta_not_coalesced(self, manager, bus):
-        """A single delta should be sent as-is."""
+        msg = _delta("Hello")
-        msg = OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content="Hello",
-            metadata={"_stream_delta": True},
-        )
         await bus.publish_outbound(msg)
 
-        # Process one message
         async def process_one():
             try:
                 m = await asyncio.wait_for(bus.consume_outbound(), timeout=0.1)
-                if m.metadata.get("_stream_delta"):
+                event = outbound_event_from_message(m)
+                if isinstance(event, StreamDeltaEvent):
                     m, pending = manager._coalesce_stream_deltas(m)
-                    # Put pending back (none expected)
                     for p in pending:
                         await bus.publish_outbound(p)
                 channel = manager.channels.get(m.channel)
-                if channel:
+                event = outbound_event_from_message(m)
-                    await channel.send_delta(m.chat_id, m.content, m.metadata)
+                if channel and isinstance(event, StreamDeltaEvent):
+                    await channel.send_delta(
+                        m.chat_id,
+                        m.content,
+                        m.metadata,
+                        stream_id=event.stream_id,
+                    )
             except asyncio.TimeoutError:
                 pass
 
         await process_one()
 
         manager.channels["mock"]._send_delta_mock.assert_called_once_with(
-            "chat1", "Hello", {"_stream_delta": True}
+            "chat1",
+            "Hello",
+            {},
+            stream_id=None,
+            stream_end=False,
+            resuming=False,
         )
 
     @pytest.mark.asyncio
     async def test_multiple_deltas_coalesced(self, manager, bus):
-        """Multiple consecutive deltas for same chat should be merged."""
-        # Put multiple deltas in queue
         for text in ["Hello", " ", "world", "!"]:
-            await bus.publish_outbound(OutboundMessage(
+            await bus.publish_outbound(_delta(text))
-                channel="mock",
-                chat_id="chat1",
-                content=text,
-                metadata={"_stream_delta": True},
-            ))
 
-        # Process using coalescing logic
         first_msg = await bus.consume_outbound()
         merged, pending = manager._coalesce_stream_deltas(first_msg)
 
-        # Should have merged all deltas
         assert merged.content == "Hello world!"
-        assert merged.metadata.get("_stream_delta") is True
+        assert isinstance(merged.event, StreamDeltaEvent)
-        # No pending messages (all were coalesced)
         assert len(pending) == 0
 
     @pytest.mark.asyncio
     async def test_deltas_different_chats_not_coalesced(self, manager, bus):
-        """Deltas for different chats should not be merged."""
+        await bus.publish_outbound(_delta("Hello", chat_id="chat1"))
-        # Put deltas for different chats
+        await bus.publish_outbound(_delta("World", chat_id="chat2"))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content="Hello",
-            metadata={"_stream_delta": True},
-        ))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat2",
-            content="World",
-            metadata={"_stream_delta": True},
-        ))
 
         first_msg = await bus.consume_outbound()
         merged, pending = manager._coalesce_stream_deltas(first_msg)
 
-        # First chat should not include second chat's content
         assert merged.content == "Hello"
         assert merged.chat_id == "chat1"
-        # Second chat should be in pending
         assert len(pending) == 1
         assert pending[0].chat_id == "chat2"
         assert pending[0].content == "World"
 
     @pytest.mark.asyncio
+    async def test_deltas_different_stream_ids_not_coalesced(self, manager, bus):
+        await bus.publish_outbound(_delta("A1", stream_id="stream-a"))
+        await bus.publish_outbound(_delta("B1", stream_id="stream-b"))
+
+        first_msg = await bus.consume_outbound()
+        merged, pending = manager._coalesce_stream_deltas(first_msg)
+
+        assert merged.content == "A1"
+        assert isinstance(merged.event, StreamDeltaEvent)
+        assert merged.event.stream_id == "stream-a"
+        assert len(pending) == 1
+        assert pending[0].content == "B1"
+        assert isinstance(pending[0].event, StreamDeltaEvent)
+        assert pending[0].event.stream_id == "stream-b"
+
+    @pytest.mark.asyncio
     async def test_stream_end_terminates_coalescing(self, manager, bus):
-        """_stream_end should stop coalescing and be included in final message."""
+        await bus.publish_outbound(_delta("Hello"))
-        # Put deltas with stream_end at the end
+        await bus.publish_outbound(_end(" world"))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content="Hello",
-            metadata={"_stream_delta": True},
-        ))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content=" world",
-            metadata={"_stream_delta": True, "_stream_end": True},
-        ))
 
         first_msg = await bus.consume_outbound()
         merged, pending = manager._coalesce_stream_deltas(first_msg)
 
-        # Should have merged content
         assert merged.content == "Hello world"
-        # Should have stream_end flag
+        assert isinstance(merged.event, StreamEndEvent)
-        assert merged.metadata.get("_stream_end") is True
-        # No pending
         assert len(pending) == 0
 
     @pytest.mark.asyncio
     async def test_coalescing_stops_at_first_non_matching_boundary(self, manager, bus):
-        """Only consecutive deltas should be merged; later deltas stay queued."""
+        await bus.publish_outbound(_delta("Hello", stream_id="seg-1"))
-        await bus.publish_outbound(OutboundMessage(
+        await bus.publish_outbound(_end(stream_id="seg-1"))
-            channel="mock",
+        await bus.publish_outbound(_delta("world", stream_id="seg-2"))
-            chat_id="chat1",
-            content="Hello",
-            metadata={"_stream_delta": True, "_stream_id": "seg-1"},
-        ))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content="",
-            metadata={"_stream_end": True, "_stream_id": "seg-1"},
-        ))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content="world",
-            metadata={"_stream_delta": True, "_stream_id": "seg-2"},
-        ))
 
         first_msg = await bus.consume_outbound()
         merged, pending = manager._coalesce_stream_deltas(first_msg)
 
         assert merged.content == "Hello"
-        assert merged.metadata.get("_stream_end") is None
+        assert isinstance(merged.event, StreamDeltaEvent)
         assert len(pending) == 1
-        assert pending[0].metadata.get("_stream_end") is True
+        assert isinstance(pending[0].event, StreamEndEvent)
-        assert pending[0].metadata.get("_stream_id") == "seg-1"
+        assert pending[0].event.stream_id == "seg-1"
 
-        # The next stream segment must remain in queue order for later dispatch.
         remaining = await bus.consume_outbound()
         assert remaining.content == "world"
-        assert remaining.metadata.get("_stream_id") == "seg-2"
+        assert isinstance(remaining.event, StreamDeltaEvent)
+        assert remaining.event.stream_id == "seg-2"
 
     @pytest.mark.asyncio
     async def test_non_delta_message_preserved(self, manager, bus):
-        """Non-delta messages should be preserved in pending list."""
+        await bus.publish_outbound(_delta("Delta"))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content="Delta",
-            metadata={"_stream_delta": True},
-        ))
         await bus.publish_outbound(OutboundMessage(
             channel="mock",
             chat_id="chat1",
             content="Final message",
-            metadata={},  # Not a delta
         ))
 
         first_msg = await bus.consume_outbound()
@@ -227,17 +227,11 @@ class TestDeltaCoalescing:
         assert merged.content == "Delta"
         assert len(pending) == 1
         assert pending[0].content == "Final message"
-        assert pending[0].metadata.get("_stream_delta") is None
+        assert pending[0].event is None
 
     @pytest.mark.asyncio
     async def test_empty_queue_stops_coalescing(self, manager, bus):
-        """Coalescing should stop when queue is empty."""
+        await bus.publish_outbound(_delta("Only message"))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content="Only message",
-            metadata={"_stream_delta": True},
-        ))
 
         first_msg = await bus.consume_outbound()
         merged, pending = manager._coalesce_stream_deltas(first_msg)
@@ -251,49 +245,35 @@ class TestDispatchOutboundWithCoalescing:
 
     @pytest.mark.asyncio
     async def test_dispatch_coalesces_and_processes_pending(self, manager, bus):
-        """_dispatch_outbound should coalesce deltas and process pending messages."""
+        await bus.publish_outbound(_delta("A"))
-        # Put multiple deltas followed by a regular message
+        await bus.publish_outbound(_delta("B"))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content="A",
-            metadata={"_stream_delta": True},
-        ))
-        await bus.publish_outbound(OutboundMessage(
-            channel="mock",
-            chat_id="chat1",
-            content="B",
-            metadata={"_stream_delta": True},
-        ))
         await bus.publish_outbound(OutboundMessage(
             channel="mock",
             chat_id="chat1",
             content="Final",
-            metadata={},  # Regular message
         ))
 
-        # Run one iteration of dispatch logic manually
         pending = []
         processed = []
 
-        # First iteration: should coalesce A+B
+        msg = pending.pop(0) if pending else await bus.consume_outbound()
-        if pending:
+        event = outbound_event_from_message(msg)
-            msg = pending.pop(0)
+        if isinstance(event, StreamDeltaEvent):
-        else:
-            msg = await bus.consume_outbound()
-
-        if msg.metadata.get("_stream_delta") and not msg.metadata.get("_stream_end"):
             msg, extra_pending = manager._coalesce_stream_deltas(msg)
             pending.extend(extra_pending)
 
         channel = manager.channels.get(msg.channel)
-        if channel:
+        event = outbound_event_from_message(msg)
-            await channel.send_delta(msg.chat_id, msg.content, msg.metadata)
+        if channel and isinstance(event, StreamDeltaEvent):
+            await channel.send_delta(
+                msg.chat_id,
+                msg.content,
+                msg.metadata,
+                stream_id=event.stream_id,
+            )
             processed.append(("delta", msg.content))
 
-        # Should have sent coalesced delta
         assert processed == [("delta", "AB")]
-        # Should have pending regular message
         assert len(pending) == 1
         assert pending[0].content == "Final"
 
@@ -329,23 +309,20 @@ class TestProgressFiltering:
 
         assert manager._resolve_bool_override(FakeSection(), "send_progress", True) is False
         assert manager._resolve_bool_override(FakeSection(), "send_tool_hints", False) is True
-        # Missing attribute falls back to default
         assert manager._resolve_bool_override(FakeSection(), "unknown_key", True) is True
 
     @pytest.mark.asyncio
     async def test_channel_override_can_drop_progress_message(self, manager, bus):
         manager.channels["mock"].send_progress = False
-        await bus.publish_outbound(OutboundMessage(
+        await bus.publish_outbound(outbound_message_for_event(
             channel="mock",
             chat_id="chat1",
-            content="thinking",
+            event=ProgressEvent(content="thinking"),
-            metadata={"_progress": True},
         ))
         await bus.publish_outbound(OutboundMessage(
             channel="mock",
             chat_id="chat1",
             content="final answer",
-            metadata={},
         ))
 
         task = asyncio.create_task(manager._dispatch_outbound())
@@ -366,13 +343,37 @@ class TestProgressFiltering:
         assert send_mock.await_args_list[0].args[0].content == "final answer"
 
     @pytest.mark.asyncio
-    async def test_channel_override_can_enable_tool_hints(self, manager, bus):
+    async def test_legacy_progress_flag_uses_runtime_progress_filter(self, manager, bus):
-        manager.channels["mock"].send_tool_hints = True
+        manager.channels["mock"].send_progress = False
         await bus.publish_outbound(OutboundMessage(
             channel="mock",
             chat_id="chat1",
-            content="read_file(foo.py)",
+            content="legacy progress-shaped message",
-            metadata={"_progress": True, "_tool_hint": True},
+            metadata={"_progress": True},
+        ))
+
+        task = asyncio.create_task(manager._dispatch_outbound())
+        try:
+            for _ in range(30):
+                if manager.channels["mock"]._send_mock.await_count >= 1:
+                    break
+                await asyncio.sleep(0.05)
+        finally:
+            task.cancel()
+            try:
+                await task
+            except asyncio.CancelledError:
+                pass
+
+        assert manager.channels["mock"]._send_mock.await_count == 0
+
+    @pytest.mark.asyncio
+    async def test_channel_override_can_enable_tool_hints(self, manager, bus):
+        manager.channels["mock"].send_tool_hints = True
+        await bus.publish_outbound(outbound_message_for_event(
+            channel="mock",
+            chat_id="chat1",
+            event=ProgressEvent(content="read_file(foo.py)", tool_hint=True),
         ))
 
         task = asyncio.create_task(manager._dispatch_outbound())
@@ -398,24 +399,15 @@ class TestRetryWaitFiltering:
 
     @pytest.mark.asyncio
     async def test_retry_wait_message_dropped(self, manager, bus):
-        """A ``_retry_wait`` message must be filtered before channel dispatch.
+        retry_msg = outbound_message_for_event(
-
-        Regression: provider retry diagnostics like
-        ``Model request failed, retry in 1s (attempt 1).`` were being
-        delivered to end-user channels because the runner bound
-        ``on_retry_wait`` to the progress callback.
-        """
-        retry_msg = OutboundMessage(
             channel="mock",
             chat_id="chat1",
-            content="Model request failed, retry in 1s (attempt 1).",
+            event=RetryWaitEvent(content="Model request failed, retry in 1s (attempt 1)."),
-            metadata={"_retry_wait": True},
         )
         real_msg = OutboundMessage(
             channel="mock",
             chat_id="chat1",
             content="final answer",
-            metadata={},
         )
         await bus.publish_outbound(retry_msg)
         await bus.publish_outbound(real_msg)
@@ -437,4 +429,4 @@ class TestRetryWaitFiltering:
         assert send_mock.await_count == 1
         sent = send_mock.await_args_list[0].args[0]
         assert sent.content == "final answer"
-        assert not sent.metadata.get("_retry_wait")
+        assert sent.event is None

tests/channels/test_channel_manager_reasoning.py

@@ -8,10 +8,9 @@ channels that opt in via ``channel.show_reasoning``; plugins without a
 low-emphasis UI primitive keep the base no-op and the content silently
 drops at dispatch.
 
-One-shot ``_reasoning`` frames are accepted for back-compat with hooks
+One-shot reasoning frames are represented as typed progress events and
-that haven't migrated yet — ``BaseChannel.send_reasoning`` expands them
+``BaseChannel.send_reasoning`` expands them to a single delta + end pair so
-to a single delta + end pair so plugins only implement the streaming
+plugins only implement the streaming primitives.
-primitives.
 """
 
 from __future__ import annotations
@@ -22,6 +21,7 @@ from unittest.mock import AsyncMock
 import pytest
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent, outbound_message_for_event
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.channels.manager import ChannelManager
@@ -48,11 +48,11 @@ class _MockChannel(BaseChannel):
     async def send(self, msg):
         return await self._send_mock(msg)
 
-    async def send_reasoning_delta(self, chat_id, delta, metadata=None):
+    async def send_reasoning_delta(self, chat_id, delta, metadata=None, *, stream_id=None):
-        return await self._delta_mock(chat_id, delta, metadata)
+        return await self._delta_mock(chat_id, delta, metadata, stream_id=stream_id)
 
-    async def send_reasoning_end(self, chat_id, metadata=None):
+    async def send_reasoning_end(self, chat_id, metadata=None, *, stream_id=None):
-        return await self._end_mock(chat_id, metadata)
+        return await self._end_mock(chat_id, metadata, stream_id=stream_id)
 
     async def send_file_edit_events(self, chat_id, edits, metadata=None):
         return await self._file_edit_mock(chat_id, edits, metadata)
@@ -94,17 +94,17 @@ def test_websocket_gateway_uses_configured_workspace_restriction(tmp_path, monke
 @pytest.mark.asyncio
 async def test_reasoning_delta_routes_to_send_reasoning_delta(manager):
     channel = manager.channels["mock"]
-    msg = OutboundMessage(
+    msg = outbound_message_for_event(
         channel="mock",
         chat_id="c1",
-        content="step-by-step",
+        event=ProgressEvent(content="step-by-step", reasoning_delta=True, stream_id="r1"),
-        metadata={"_progress": True, "_reasoning_delta": True, "_stream_id": "r1"},
     )
     await manager._send_once(channel, msg)
     channel._delta_mock.assert_awaited_once()
     args = channel._delta_mock.await_args.args
     assert args[0] == "c1"
     assert args[1] == "step-by-step"
+    assert channel._delta_mock.await_args.kwargs["stream_id"] == "r1"
     channel._send_mock.assert_not_awaited()
     channel._end_mock.assert_not_awaited()
 
@@ -112,11 +112,10 @@ async def test_reasoning_delta_routes_to_send_reasoning_delta(manager):
 @pytest.mark.asyncio
 async def test_reasoning_end_routes_to_send_reasoning_end(manager):
     channel = manager.channels["mock"]
-    msg = OutboundMessage(
+    msg = outbound_message_for_event(
         channel="mock",
         chat_id="c1",
-        content="",
+        event=ProgressEvent(reasoning_end=True, stream_id="r1"),
-        metadata={"_progress": True, "_reasoning_end": True, "_stream_id": "r1"},
     )
     await manager._send_once(channel, msg)
     channel._end_mock.assert_awaited_once()
@@ -124,16 +123,13 @@ async def test_reasoning_end_routes_to_send_reasoning_end(manager):
 
 
 @pytest.mark.asyncio
-async def test_legacy_one_shot_reasoning_expands_to_delta_plus_end(manager):
+async def test_one_shot_reasoning_expands_to_delta_plus_end(manager):
-    """`_reasoning` (no delta/end pair) falls back through `send_reasoning`
+    """One-shot reasoning expands to a single delta + end."""
-    which the base class expands to a single delta + end. Hooks that haven't
-    migrated still surface in WebUI as a complete stream segment."""
     channel = manager.channels["mock"]
-    msg = OutboundMessage(
+    msg = outbound_message_for_event(
         channel="mock",
         chat_id="c1",
-        content="one-shot reasoning",
+        event=ProgressEvent(content="one-shot reasoning", reasoning=True),
-        metadata={"_progress": True, "_reasoning": True},
     )
     await manager._send_once(channel, msg)
     channel._delta_mock.assert_awaited_once()
@@ -144,11 +140,10 @@ async def test_legacy_one_shot_reasoning_expands_to_delta_plus_end(manager):
 async def test_dispatch_drops_reasoning_when_channel_opts_out(manager):
     channel = manager.channels["mock"]
     channel.show_reasoning = False
-    msg = OutboundMessage(
+    msg = outbound_message_for_event(
         channel="mock",
         chat_id="c1",
-        content="hidden thinking",
+        event=ProgressEvent(content="hidden thinking", reasoning_delta=True),
-        metadata={"_progress": True, "_reasoning_delta": True},
     )
     await manager.bus.publish_outbound(msg)
 
@@ -164,17 +159,15 @@ async def test_dispatch_delivers_reasoning_when_channel_opts_in(manager):
     channel = manager.channels["mock"]
     channel.show_reasoning = True
     for chunk in ("first ", "second"):
-        await manager.bus.publish_outbound(OutboundMessage(
+        await manager.bus.publish_outbound(outbound_message_for_event(
             channel="mock",
             chat_id="c1",
-            content=chunk,
+            event=ProgressEvent(content=chunk, reasoning_delta=True, stream_id="r1"),
-            metadata={"_progress": True, "_reasoning_delta": True, "_stream_id": "r1"},
         ))
-    await manager.bus.publish_outbound(OutboundMessage(
+    await manager.bus.publish_outbound(outbound_message_for_event(
         channel="mock",
         chat_id="c1",
-        content="",
+        event=ProgressEvent(reasoning_end=True, stream_id="r1"),
-        metadata={"_progress": True, "_reasoning_end": True, "_stream_id": "r1"},
     ))
 
     await _pump_one(manager)
@@ -185,11 +178,10 @@ async def test_dispatch_delivers_reasoning_when_channel_opts_in(manager):
 
 @pytest.mark.asyncio
 async def test_dispatch_silently_drops_reasoning_for_unknown_channel(manager):
-    msg = OutboundMessage(
+    msg = outbound_message_for_event(
         channel="ghost",
         chat_id="c1",
-        content="nobody home",
+        event=ProgressEvent(content="nobody home", reasoning_delta=True),
-        metadata={"_progress": True, "_reasoning_delta": True},
     )
     await manager.bus.publish_outbound(msg)
 
@@ -229,17 +221,34 @@ async def test_base_channel_reasoning_primitives_are_noop_safe():
 async def test_file_edit_events_route_to_channel_capability(manager):
     channel = manager.channels["mock"]
     edits = [{"version": 1, "phase": "start", "path": "src/app.py"}]
-    msg = OutboundMessage(
+    msg = outbound_message_for_event(
         channel="mock",
         chat_id="c1",
-        content="",
+        event=ProgressEvent(file_edit_events=edits),
-        metadata={"_progress": True, "_file_edit_events": edits},
     )
 
     await manager._send_once(channel, msg)
 
     channel._file_edit_mock.assert_awaited_once_with(
-        "c1", edits, {"_progress": True, "_file_edit_events": edits}
+        "c1", edits, msg.metadata
+    )
+    channel._send_mock.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_typed_file_edit_event_routes_to_channel_capability(manager):
+    channel = manager.channels["mock"]
+    edits = [{"version": 1, "phase": "start", "path": "src/app.py"}]
+    msg = outbound_message_for_event(
+        channel="mock",
+        chat_id="c1",
+        event=ProgressEvent(file_edit_events=edits),
+    )
+
+    await manager._send_once(channel, msg)
+
+    channel._file_edit_mock.assert_awaited_once_with(
+        "c1", edits, msg.metadata
     )
     channel._send_mock.assert_not_awaited()
 
@@ -270,11 +279,10 @@ async def test_reasoning_routing_does_not_consult_send_progress(manager):
     channel = manager.channels["mock"]
     channel.send_progress = False
     channel.show_reasoning = True
-    await manager.bus.publish_outbound(OutboundMessage(
+    await manager.bus.publish_outbound(outbound_message_for_event(
         channel="mock",
         chat_id="c1",
-        content="still surfaces",
+        event=ProgressEvent(content="still surfaces", reasoning_delta=True),
-        metadata={"_progress": True, "_reasoning_delta": True},
     ))
 
     await _pump_one(manager)

tests/channels/test_channel_plugins.py

@@ -9,6 +9,13 @@ from unittest.mock import AsyncMock, patch
 import pytest
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import (
+    ProgressEvent,
+    StreamDeltaEvent,
+    StreamedResponseEvent,
+    StreamEndEvent,
+    outbound_message_for_event,
+)
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.channels.manager import ChannelManager
@@ -718,7 +725,7 @@ async def test_send_with_retry_no_retry_when_max_is_zero():
 
 @pytest.mark.asyncio
 async def test_send_with_retry_calls_send_delta():
-    """_send_with_retry should call send_delta when metadata has _stream_delta."""
+    """_send_with_retry should call send_delta for stream delta events."""
     send_delta_called = False
 
     class _StreamingChannel(BaseChannel):
@@ -734,7 +741,16 @@ async def test_send_with_retry_calls_send_delta():
         async def send(self, msg: OutboundMessage) -> None:
             pass  # Should not be called
 
-        async def send_delta(self, chat_id: str, delta: str, metadata: dict | None = None) -> None:
+        async def send_delta(
+            self,
+            chat_id: str,
+            delta: str,
+            metadata: dict | None = None,
+            *,
+            stream_id: str | None = None,
+            stream_end: bool = False,
+            resuming: bool = False,
+        ) -> None:
             nonlocal send_delta_called
             send_delta_called = True
 
@@ -749,18 +765,147 @@ async def test_send_with_retry_calls_send_delta():
     mgr.channels = {"streaming": _StreamingChannel(fake_config, mgr.bus)}
     mgr._dispatch_task = None
 
-    msg = OutboundMessage(
+    msg = outbound_message_for_event(
-        channel="streaming", chat_id="123", content="test delta",
+        channel="streaming",
-        metadata={"_stream_delta": True}
+        chat_id="123",
+        event=StreamDeltaEvent(content="test delta"),
     )
     await mgr._send_with_retry(mgr.channels["streaming"], msg)
 
     assert send_delta_called is True
 
 
+@pytest.mark.asyncio
+async def test_send_with_retry_supports_legacy_stream_delta_signature():
+    """External plugins with the old send_delta signature should keep working."""
+    calls: list[tuple[str, str, dict]] = []
+
+    class _LegacyStreamingChannel(BaseChannel):
+        name = "legacy_streaming"
+        display_name = "Legacy Streaming"
+
+        async def start(self) -> None:
+            pass
+
+        async def stop(self) -> None:
+            pass
+
+        async def send(self, msg: OutboundMessage) -> None:
+            pass
+
+        async def send_delta(
+            self,
+            chat_id: str,
+            delta: str,
+            metadata: dict | None = None,
+        ) -> None:
+            calls.append((chat_id, delta, dict(metadata or {})))
+
+    fake_config = SimpleNamespace(
+        channels=ChannelsConfig(send_max_retries=3),
+        providers=SimpleNamespace(groq=SimpleNamespace(api_key="")),
+    )
+    mgr = ChannelManager.__new__(ChannelManager)
+    mgr.config = fake_config
+    mgr.bus = MessageBus()
+    mgr.channels = {"legacy_streaming": _LegacyStreamingChannel(fake_config, mgr.bus)}
+    mgr._dispatch_task = None
+
+    await mgr._send_with_retry(
+        mgr.channels["legacy_streaming"],
+        outbound_message_for_event(
+            channel="legacy_streaming",
+            chat_id="123",
+            event=StreamDeltaEvent(content="hello", stream_id="s1"),
+        ),
+    )
+    await mgr._send_with_retry(
+        mgr.channels["legacy_streaming"],
+        outbound_message_for_event(
+            channel="legacy_streaming",
+            chat_id="123",
+            event=StreamEndEvent(content="", stream_id="s1", resuming=True),
+        ),
+    )
+
+    assert calls == [
+        ("123", "hello", {"_stream_id": "s1", "_stream_delta": True}),
+        ("123", "", {"_stream_id": "s1", "_stream_end": True}),
+    ]
+
+
+@pytest.mark.asyncio
+async def test_send_with_retry_supports_legacy_reasoning_signature():
+    """External plugins with the old reasoning hook signature should keep working."""
+    deltas: list[tuple[str, str, dict]] = []
+    ends: list[tuple[str, dict]] = []
+
+    class _LegacyReasoningChannel(BaseChannel):
+        name = "legacy_reasoning"
+        display_name = "Legacy Reasoning"
+
+        async def start(self) -> None:
+            pass
+
+        async def stop(self) -> None:
+            pass
+
+        async def send(self, msg: OutboundMessage) -> None:
+            pass
+
+        async def send_reasoning_delta(
+            self,
+            chat_id: str,
+            delta: str,
+            metadata: dict | None = None,
+        ) -> None:
+            deltas.append((chat_id, delta, dict(metadata or {})))
+
+        async def send_reasoning_end(
+            self,
+            chat_id: str,
+            metadata: dict | None = None,
+        ) -> None:
+            ends.append((chat_id, dict(metadata or {})))
+
+    fake_config = SimpleNamespace(
+        channels=ChannelsConfig(send_max_retries=3),
+        providers=SimpleNamespace(groq=SimpleNamespace(api_key="")),
+    )
+    mgr = ChannelManager.__new__(ChannelManager)
+    mgr.config = fake_config
+    mgr.bus = MessageBus()
+    mgr.channels = {"legacy_reasoning": _LegacyReasoningChannel(fake_config, mgr.bus)}
+    mgr._dispatch_task = None
+
+    await mgr._send_with_retry(
+        mgr.channels["legacy_reasoning"],
+        outbound_message_for_event(
+            channel="legacy_reasoning",
+            chat_id="123",
+            event=ProgressEvent(content="thinking", reasoning_delta=True, stream_id="r1"),
+        ),
+    )
+    await mgr._send_with_retry(
+        mgr.channels["legacy_reasoning"],
+        outbound_message_for_event(
+            channel="legacy_reasoning",
+            chat_id="123",
+            event=ProgressEvent(reasoning_end=True, stream_id="r1"),
+        ),
+    )
+
+    assert deltas == [
+        ("123", "thinking", {"_reasoning_delta": True, "_stream_id": "r1"}),
+    ]
+    assert ends == [
+        ("123", {"_reasoning_end": True, "_stream_id": "r1"}),
+    ]
+
+
 @pytest.mark.asyncio
 async def test_send_with_retry_skips_send_when_streamed():
-    """_send_with_retry should not call send when metadata has _streamed flag."""
+    """_send_with_retry should not call send for streamed response events."""
     send_called = False
     send_delta_called = False
 
@@ -778,7 +923,16 @@ async def test_send_with_retry_skips_send_when_streamed():
             nonlocal send_called
             send_called = True
 
-        async def send_delta(self, chat_id: str, delta: str, metadata: dict | None = None) -> None:
+        async def send_delta(
+            self,
+            chat_id: str,
+            delta: str,
+            metadata: dict | None = None,
+            *,
+            stream_id: str | None = None,
+            stream_end: bool = False,
+            resuming: bool = False,
+        ) -> None:
             nonlocal send_delta_called
             send_delta_called = True
 
@@ -793,10 +947,11 @@ async def test_send_with_retry_skips_send_when_streamed():
     mgr.channels = {"streamed": _StreamedChannel(fake_config, mgr.bus)}
     mgr._dispatch_task = None
 
-    # _streamed means message was already sent via send_delta, so skip send
+    msg = outbound_message_for_event(
-    msg = OutboundMessage(
+        channel="streamed",
-        channel="streamed", chat_id="123", content="test",
+        chat_id="123",
-        metadata={"_streamed": True}
+        event=StreamedResponseEvent(),
+        content="test",
     )
     await mgr._send_with_retry(mgr.channels["streamed"], msg)
 

tests/channels/test_discord_channel.py

@@ -10,6 +10,7 @@ pytest.importorskip("discord")
 import discord
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.discord import (
     MAX_MESSAGE_LEN,
@@ -718,9 +719,9 @@ async def test_send_delta_streams_by_editing_message(monkeypatch) -> None:
     times = iter([1.0, 3.0, 5.0])
     monkeypatch.setattr("nanobot.channels.discord.time.monotonic", lambda: next(times, 5.0))
 
-    await owner.send_delta("123", "hel", {"_stream_delta": True, "_stream_id": "s1"})
+    await owner.send_delta("123", "hel", stream_id="s1")
-    await owner.send_delta("123", "lo", {"_stream_delta": True, "_stream_id": "s1"})
+    await owner.send_delta("123", "lo", stream_id="s1")
-    await owner.send_delta("123", "", {"_stream_end": True, "_stream_id": "s1"})
+    await owner.send_delta("123", "", stream_id="s1", stream_end=True)
 
     assert target.sent_payloads[0] == {"content": "hel"}
     assert target.sent_messages[0].edits == [{"content": "hello"}, {"content": "hello"}]
@@ -745,9 +746,9 @@ async def test_send_delta_stream_end_splits_oversized_reply(monkeypatch) -> None
     times = iter([1.0, 3.0])
     monkeypatch.setattr("nanobot.channels.discord.time.monotonic", lambda: next(times, 3.0))
 
-    await owner.send_delta("123", prefix, {"_stream_delta": True, "_stream_id": "s1"})
+    await owner.send_delta("123", prefix, stream_id="s1")
-    await owner.send_delta("123", suffix, {"_stream_delta": True, "_stream_id": "s1"})
+    await owner.send_delta("123", suffix, stream_id="s1")
-    await owner.send_delta("123", "", {"_stream_end": True, "_stream_id": "s1"})
+    await owner.send_delta("123", "", stream_id="s1", stream_end=True)
 
     assert target.sent_payloads == [{"content": prefix}, {"content": chunks[1]}]
     assert target.sent_messages[0].edits == [{"content": chunks[0]}, {"content": chunks[0]}]
@@ -1073,7 +1074,7 @@ async def test_send_stops_typing_after_send() -> None:
             channel="discord",
             chat_id="123",
             content="progress",
-            metadata={"_progress": True},
+            event=ProgressEvent(content="progress"),
         )
     )
 

tests/channels/test_email_channel.py

@@ -6,6 +6,7 @@ from pathlib import Path
 import pytest
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.email import EmailChannel, EmailConfig
 
@@ -868,10 +869,7 @@ async def test_send_skips_progress_messages_before_smtp(monkeypatch) -> None:
             channel="email",
             chat_id="alice@example.com",
             content="",
-            metadata={
+            event=ProgressEvent(tool_events=[{"phase": "end", "name": "exec"}]),
-                "_progress": True,
-                "_tool_events": [{"phase": "end", "name": "exec"}],
-            },
         )
     )
 

tests/channels/test_feishu_reaction.py

@@ -193,7 +193,8 @@ class TestStreamEndReactionCleanup:
 
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"_stream_end": True, "message_id": "om_001"},
+            metadata={"message_id": "om_001"},
+            stream_end=True,
         )
 
         ch._remove_reaction.assert_called_once_with("om_001", "rx_42")
@@ -210,7 +211,7 @@ class TestStreamEndReactionCleanup:
 
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"_stream_end": True},
+            stream_end=True,
         )
 
         ch._remove_reaction.assert_not_called()
@@ -227,7 +228,8 @@ class TestStreamEndReactionCleanup:
 
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"_stream_end": True, "message_id": "om_001"},
+            metadata={"message_id": "om_001"},
+            stream_end=True,
         )
 
         ch._remove_reaction.assert_not_called()
@@ -242,7 +244,7 @@ class TestStreamEndReactionCleanup:
         ch._client.cardkit.v1.card.settings.return_value = MagicMock(success=MagicMock(return_value=True))
         ch._remove_reaction = AsyncMock()
 
-        await ch.send_delta("oc_chat1", "", metadata={"_stream_end": True})
+        await ch.send_delta("oc_chat1", "", stream_end=True)
 
         ch._remove_reaction.assert_not_called()
 
@@ -260,7 +262,7 @@ class TestStreamEndReactionCleanup:
 
     @pytest.mark.asyncio
     async def test_no_removal_when_resuming(self):
-        """_resuming=True means more tool-call rounds follow; reaction must persist."""
+        """resuming=True means more tool-call rounds follow; reaction must persist."""
         ch = _make_channel()
         ch.config.done_emoji = "DONE"
         ch._stream_bufs["oc_chat1"] = _FeishuStreamBuf(
@@ -274,7 +276,9 @@ class TestStreamEndReactionCleanup:
 
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"_stream_end": True, "_resuming": True, "message_id": "om_001"},
+            metadata={"message_id": "om_001"},
+            stream_end=True,
+            resuming=True,
         )
 
         ch._remove_reaction.assert_not_called()
@@ -299,19 +303,23 @@ class TestStreamEndReactionCleanup:
         # Intermediate stream end (more tool calls coming).
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"_stream_end": True, "_resuming": True, "message_id": "om_001"},
+            metadata={"message_id": "om_001"},
+            stream_end=True,
+            resuming=True,
         )
         ch._remove_reaction.assert_not_called()
         ch._add_reaction.assert_not_called()
 
-        # Re-prime the stream buffer for the final round (the previous _stream_end popped it).
+        # Re-prime the stream buffer for the final round (the previous stream end popped it).
         ch._stream_bufs["oc_chat1"] = _FeishuStreamBuf(
             text="t", card_id="card_1", sequence=5, last_edit=0.0,
         )
         # Final stream end (resuming=False): OnIt removed, done_emoji added.
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"_stream_end": True, "_resuming": False, "message_id": "om_001"},
+            metadata={"message_id": "om_001"},
+            stream_end=True,
+            resuming=False,
         )
         ch._remove_reaction.assert_called_once_with("om_001", "rx_42")
         ch._add_reaction.assert_called_once_with("om_001", "DONE")

tests/channels/test_feishu_reply.py

@@ -18,6 +18,7 @@ if not FEISHU_AVAILABLE:
     pytest.skip("Feishu dependencies not installed (lark-oapi)", allow_module_level=True)
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.feishu import FeishuChannel, FeishuConfig
 
@@ -332,7 +333,8 @@ async def test_send_skips_reply_for_progress_messages() -> None:
         channel="feishu",
         chat_id="oc_abc",
         content="thinking...",
-        metadata={"message_id": "om_001", "_progress": True},
+        event=ProgressEvent(content="thinking..."),
+        metadata={"message_id": "om_001"},
     ))
 
     channel._client.im.v1.message.create.assert_called_once()

tests/channels/test_feishu_streaming.py

@@ -6,6 +6,7 @@ from unittest.mock import MagicMock
 import pytest
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.feishu import FeishuChannel, FeishuConfig, _FeishuStreamBuf
 
@@ -272,7 +273,7 @@ class TestSendDelta:
         ch._client.cardkit.v1.card_element.content.return_value = _mock_content_response()
         ch._client.cardkit.v1.card.settings.return_value = _mock_content_response()
 
-        await ch.send_delta("oc_chat1", "", metadata={"_stream_end": True})
+        await ch.send_delta("oc_chat1", "", stream_end=True)
 
         assert "oc_chat1" not in ch._stream_bufs
         ch._client.cardkit.v1.card_element.content.assert_called_once()
@@ -289,7 +290,7 @@ class TestSendDelta:
         )
         ch._client.im.v1.message.create.return_value = _mock_send_response("om_fb")
 
-        await ch.send_delta("oc_chat1", "", metadata={"_stream_end": True})
+        await ch.send_delta("oc_chat1", "", stream_end=True)
 
         assert "oc_chat1" not in ch._stream_bufs
         ch._client.cardkit.v1.card_element.content.assert_not_called()
@@ -306,7 +307,8 @@ class TestSendDelta:
         await ch.send_delta(
             "oc_chat1",
             "",
-            metadata={"_stream_end": True, "message_id": "om_001", "chat_type": "group"},
+            metadata={"message_id": "om_001", "chat_type": "group"},
+            stream_end=True,
         )
 
         ch._client.im.v1.message.create.assert_called_once()
@@ -326,11 +328,11 @@ class TestSendDelta:
             "oc_chat1",
             "",
             metadata={
-                "_stream_end": True,
                 "message_id": "om_001",
                 "chat_type": "group",
                 "thread_id": "ot_001",
             },
+            stream_end=True,
         )
 
         ch._client.im.v1.message.reply.assert_called_once()
@@ -351,7 +353,8 @@ class TestSendDelta:
         await ch.send_delta(
             "oc_chat1",
             "",
-            metadata={"_stream_end": True, "message_id": "om_001", "chat_type": "group"},
+            metadata={"message_id": "om_001", "chat_type": "group"},
+            stream_end=True,
         )
 
         ch._client.im.v1.message.reply.assert_called_once()
@@ -369,7 +372,7 @@ class TestSendDelta:
         ch._client.cardkit.v1.card_element.content.return_value = _mock_content_response(success=False)
         ch._client.im.v1.message.create.return_value = _mock_send_response("om_fb")
 
-        await ch.send_delta("oc_chat1", "", metadata={"_stream_end": True})
+        await ch.send_delta("oc_chat1", "", stream_end=True)
 
         assert "oc_chat1" not in ch._stream_bufs
         assert ch._client.cardkit.v1.card.settings.call_count == 2
@@ -388,7 +391,7 @@ class TestSendDelta:
         ]
         ch._client.cardkit.v1.card.settings.return_value = _mock_content_response(True)
 
-        await ch.send_delta("oc_chat1", "", metadata={"_stream_end": True})
+        await ch.send_delta("oc_chat1", "", stream_end=True)
 
         assert "oc_chat1" not in ch._stream_bufs
         assert ch._client.cardkit.v1.card_element.content.call_count == 2
@@ -398,7 +401,7 @@ class TestSendDelta:
     @pytest.mark.asyncio
     async def test_stream_end_without_buf_is_noop(self):
         ch = _make_channel()
-        await ch.send_delta("oc_chat1", "", metadata={"_stream_end": True})
+        await ch.send_delta("oc_chat1", "", stream_end=True)
         ch._client.cardkit.v1.card_element.content.assert_not_called()
 
     @pytest.mark.asyncio
@@ -446,7 +449,7 @@ class TestToolHintInlineStreaming:
         msg = OutboundMessage(
             channel="feishu", chat_id="oc_chat1",
             content='web_fetch("https://example.com")',
-            metadata={"_tool_hint": True},
+            event=ProgressEvent(content='web_fetch("https://example.com")', tool_hint=True),
         )
         await ch.send(msg)
 
@@ -482,7 +485,7 @@ class TestToolHintInlineStreaming:
         msg = OutboundMessage(
             channel="feishu", chat_id="oc_chat1",
             content='read_file("path")',
-            metadata={"_tool_hint": True},
+            event=ProgressEvent(content='read_file("path")', tool_hint=True),
         )
         await ch.send(msg)
 
@@ -497,7 +500,8 @@ class TestToolHintInlineStreaming:
         msg = OutboundMessage(
             channel="feishu", chat_id="oc_chat1",
             content='read_file("path")',
-            metadata={"_tool_hint": True, "message_id": "om_001", "chat_type": "group"},
+            event=ProgressEvent(content='read_file("path")', tool_hint=True),
+            metadata={"message_id": "om_001", "chat_type": "group"},
         )
         await ch.send(msg)
 
@@ -514,8 +518,8 @@ class TestToolHintInlineStreaming:
         msg = OutboundMessage(
             channel="feishu", chat_id="oc_chat1",
             content='read_file("path")',
+            event=ProgressEvent(content='read_file("path")', tool_hint=True),
             metadata={
-                "_tool_hint": True,
                 "message_id": "om_001",
                 "chat_type": "group",
                 "thread_id": "ot_001",
@@ -538,7 +542,8 @@ class TestToolHintInlineStreaming:
         msg = OutboundMessage(
             channel="feishu", chat_id="oc_chat1",
             content='read_file("path")',
-            metadata={"_tool_hint": True, "message_id": "om_001", "chat_type": "group"},
+            event=ProgressEvent(content='read_file("path")', tool_hint=True),
+            metadata={"message_id": "om_001", "chat_type": "group"},
         )
         await ch.send(msg)
 
@@ -558,13 +563,15 @@ class TestToolHintInlineStreaming:
 
         msg1 = OutboundMessage(
             channel="feishu", chat_id="oc_chat1",
-            content='$ cd /project', metadata={"_tool_hint": True},
+            content='$ cd /project',
+            event=ProgressEvent(content='$ cd /project', tool_hint=True),
         )
         await ch.send(msg1)
 
         msg2 = OutboundMessage(
             channel="feishu", chat_id="oc_chat1",
-            content='$ git status', metadata={"_tool_hint": True},
+            content='$ git status',
+            event=ProgressEvent(content='$ git status', tool_hint=True),
         )
         await ch.send(msg2)
 
@@ -577,7 +584,7 @@ class TestToolHintInlineStreaming:
 
     @pytest.mark.asyncio
     async def test_tool_hint_preserved_on_final_stream_end(self):
-        """When final _stream_end closes the card, tool hint is kept in the final text."""
+        """When stream end closes the card, tool hint is kept in the final text."""
         ch = _make_channel()
         ch._stream_bufs["oc_chat1"] = _FeishuStreamBuf(
             text="Final content\n\n🔧 web_fetch(\"url\")\n\n",
@@ -586,7 +593,7 @@ class TestToolHintInlineStreaming:
         ch._client.cardkit.v1.card_element.content.return_value = _mock_content_response()
         ch._client.cardkit.v1.card.settings.return_value = _mock_content_response()
 
-        await ch.send_delta("oc_chat1", "", metadata={"_stream_end": True})
+        await ch.send_delta("oc_chat1", "", stream_end=True)
 
         assert "oc_chat1" not in ch._stream_bufs
         update_call = ch._client.cardkit.v1.card_element.content.call_args[0][0]
@@ -603,7 +610,8 @@ class TestToolHintInlineStreaming:
         for content in ("", "   ", "\t\n"):
             msg = OutboundMessage(
                 channel="feishu", chat_id="oc_chat1",
-                content=content, metadata={"_tool_hint": True},
+                content=content,
+                event=ProgressEvent(content=content, tool_hint=True),
             )
             await ch.send(msg)
 

tests/channels/test_feishu_tool_hint_code_block.py

@@ -1,7 +1,6 @@
 """Tests for FeishuChannel tool hint formatting."""
 
 import json
-from types import SimpleNamespace
 from unittest.mock import MagicMock, patch
 
 import pytest
@@ -18,6 +17,7 @@ if not FEISHU_AVAILABLE:
     pytest.skip("Feishu dependencies not installed (lark-oapi)", allow_module_level=True)
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.channels.feishu import FeishuChannel
 
 
@@ -51,7 +51,7 @@ async def test_tool_hint_sends_interactive_card(mock_feishu_channel):
         channel="feishu",
         chat_id="oc_123456",
         content='web_search("test query")',
-        metadata={"_tool_hint": True}
+        event=ProgressEvent(tool_hint=True),
     )
 
     with patch.object(mock_feishu_channel, '_send_message_sync') as mock_send:
@@ -72,7 +72,7 @@ async def test_tool_hint_empty_content_does_not_send(mock_feishu_channel):
         channel="feishu",
         chat_id="oc_123456",
         content="   ",  # whitespace only
-        metadata={"_tool_hint": True}
+        event=ProgressEvent(tool_hint=True),
     )
 
     with patch.object(mock_feishu_channel, '_send_message_sync') as mock_send:
@@ -107,7 +107,7 @@ async def test_tool_hint_multiple_tools_in_one_message(mock_feishu_channel):
         channel="feishu",
         chat_id="oc_123456",
         content='web_search("query"), read_file("/path/to/file")',
-        metadata={"_tool_hint": True}
+        event=ProgressEvent(tool_hint=True),
     )
 
     with patch.object(mock_feishu_channel, '_send_message_sync') as mock_send:
@@ -127,7 +127,7 @@ async def test_tool_hint_new_format_basic(mock_feishu_channel):
         channel="feishu",
         chat_id="oc_123456",
         content='read src/main.py, grep "TODO"',
-        metadata={"_tool_hint": True}
+        event=ProgressEvent(tool_hint=True),
     )
 
     with patch.object(mock_feishu_channel, '_send_message_sync') as mock_send:
@@ -146,7 +146,7 @@ async def test_tool_hint_new_format_with_comma_in_quotes(mock_feishu_channel):
         channel="feishu",
         chat_id="oc_123456",
         content='grep "hello, world", $ echo test',
-        metadata={"_tool_hint": True}
+        event=ProgressEvent(tool_hint=True),
     )
 
     with patch.object(mock_feishu_channel, '_send_message_sync') as mock_send:
@@ -165,7 +165,7 @@ async def test_tool_hint_new_format_with_folding(mock_feishu_channel):
         channel="feishu",
         chat_id="oc_123456",
         content='read path × 3, grep "pattern"',
-        metadata={"_tool_hint": True}
+        event=ProgressEvent(tool_hint=True),
     )
 
     with patch.object(mock_feishu_channel, '_send_message_sync') as mock_send:
@@ -184,7 +184,7 @@ async def test_tool_hint_new_format_mcp(mock_feishu_channel):
         channel="feishu",
         chat_id="oc_123456",
         content='4_5v::analyze_image("photo.jpg")',
-        metadata={"_tool_hint": True}
+        event=ProgressEvent(tool_hint=True),
     )
 
     with patch.object(mock_feishu_channel, '_send_message_sync') as mock_send:
@@ -202,7 +202,7 @@ async def test_tool_hint_keeps_commas_inside_arguments(mock_feishu_channel):
         channel="feishu",
         chat_id="oc_123456",
         content='web_search("foo, bar"), read_file("/path/to/file")',
-        metadata={"_tool_hint": True}
+        event=ProgressEvent(tool_hint=True),
     )
 
     with patch.object(mock_feishu_channel, '_send_message_sync') as mock_send:

tests/channels/test_matrix_channel.py

@@ -11,6 +11,7 @@ from nio import RoomSendResponse, SyncError
 
 import nanobot.channels.matrix as matrix_module
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.outbound_events import ProgressEvent
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.matrix import (
     MATRIX_HTML_FORMAT,
@@ -1522,7 +1523,7 @@ async def test_send_progress_keeps_typing_keepalive_running() -> None:
             channel="matrix",
             chat_id="!room:matrix.org",
             content="working...",
-            metadata={"_progress": True, "_progress_kind": "reasoning"},
+            event=ProgressEvent(content="working..."),
         )
     )
 
@@ -1544,7 +1545,7 @@ async def test_send_empty_content_does_not_call_room_send() -> None:
             channel="matrix",
             chat_id="!room:matrix.org",
             content="",
-            metadata={"_progress": True},
+            event=ProgressEvent(),
         )
     )
 
@@ -1563,7 +1564,7 @@ async def test_send_whitespace_only_content_does_not_call_room_send() -> None:
             channel="matrix",
             chat_id="!room:matrix.org",
             content="   \n\n  ",
-            metadata={"_progress": True},
+            event=ProgressEvent(content="   \n\n  "),
         )
     )
 
@@ -1883,7 +1884,7 @@ async def test_send_delta_stream_end_replaces_existing_message() -> None:
         last_edit=100.0,
     )
 
-    await channel.send_delta("!room:matrix.org", "", {"_stream_end": True})
+    await channel.send_delta("!room:matrix.org", "", stream_end=True)
 
     assert "!room:matrix.org" not in channel._stream_bufs
     assert client.typing_calls[-1] == ("!room:matrix.org", False, TYPING_NOTICE_TIMEOUT_MS)
@@ -1933,7 +1934,7 @@ async def test_send_delta_threaded_edit_keeps_replace_and_thread_relation(monkey
     }
     await channel.send_delta("!room:matrix.org", "Hello", metadata)
     await channel.send_delta("!room:matrix.org", " world", metadata)
-    await channel.send_delta("!room:matrix.org", "", {"_stream_end": True, **metadata})
+    await channel.send_delta("!room:matrix.org", "", metadata, stream_end=True)
 
     edit_content = client.room_send_calls[1]["content"]
     final_content = client.room_send_calls[2]["content"]
@@ -1966,7 +1967,7 @@ async def test_send_delta_stream_end_noop_when_buffer_missing() -> None:
     client = _FakeAsyncClient("", "", "", None)
     channel.client = client
 
-    await channel.send_delta("!room:matrix.org", "", {"_stream_end": True})
+    await channel.send_delta("!room:matrix.org", "", stream_end=True)
 
     assert client.room_send_calls == []
     assert client.typing_calls == []