fix(agent): make detached exec portable on Windows

This reverts commit f56e0bea2ee0fa3dc533be1b4d4b33a5f302de10.

SECURITY.md

@@ -107,7 +107,6 @@ 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

@@ -103,8 +103,7 @@ 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 — channel routing context such as message/thread ids
-        msg.event    — typed runtime event for progress/status messages
+        msg.metadata — may contain "_progress": True for streaming chunks
         """
         logger.info("[webhook] -> {}: {}", msg.chat_id, msg.content[:80])
         # In a real plugin: POST to a callback URL, send via SDK, etc.
@@ -239,15 +238,15 @@ 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?, *, stream_id?)` | Optional hook for streamed model reasoning/thinking content. 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_delta(chat_id, delta, metadata?)` | 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(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?, *, stream_id?, stream_end=False, resuming=False)` | Override to receive streaming chunks. See [Streaming Support](#streaming-support) for details. |
+| `async send_delta(chat_id, delta, metadata?)` | Override to receive streaming chunks. See [Streaming Support](#streaming-support) for details. |
 
 ### Message Types
 
@@ -258,12 +257,10 @@ 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      # channel routing context, e.g. "message_id" for threading
-    event: object | None # typed runtime/UI event; usually inspect with isinstance()
+    metadata: dict      # may contain: "_progress" (bool) for streaming chunks,
+                        #              "message_id" for reply threading
 ```
 
-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.
@@ -282,18 +279,10 @@ 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,
-    *,
-    stream_id: str | None = None,
-    stream_end: bool = False,
-    resuming: bool = False,
-) -> None:
-    buffer_key = stream_id or chat_id
-    if stream_end:
+async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> None:
+    meta = metadata or {}
+
+    if meta.get("_stream_end"):
         # Streaming finished — do final formatting, cleanup, etc.
         return
 
@@ -301,7 +290,12 @@ async def send_delta(
     # delta contains a small chunk of text (a few tokens)
 ```
 
-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.
+**Metadata flags:**
+
+| 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
 
@@ -316,27 +310,18 @@ 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,
-        *,
-        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, "")
+    async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> None:
+        meta = metadata or {}
+        if meta.get("_stream_end"):
+            text = self._buffers.pop(chat_id, "")
             # Final delivery — format and send the complete message
             await self._deliver(chat_id, text, final=True)
             return
 
-        self._buffers.setdefault(buffer_key, "")
-        self._buffers[buffer_key] += delta
+        self._buffers.setdefault(chat_id, "")
+        self._buffers[chat_id] += delta
         # Incremental update — push partial text to the client
-        await self._deliver(chat_id, self._buffers[buffer_key], final=False)
+        await self._deliver(chat_id, self._buffers[chat_id], final=False)
 
     async def send(self, msg: OutboundMessage) -> None:
         # Non-streaming path — unchanged
@@ -365,7 +350,7 @@ When `streaming` is `false` (default) or omitted, only `send()` is called — no
 
 | Method / Property | Description |
 |-------------------|-------------|
-| `async send_delta(chat_id, delta, metadata?, *, stream_id?, stream_end=False, resuming=False)` | Override to handle streaming chunks. No-op by default. |
+| `async send_delta(chat_id, delta, metadata?)` | 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
@@ -374,20 +359,18 @@ 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.event` before rendering:
+Progress and tool hints arrive through the normal `send(msg)` path. Check `msg.metadata` before rendering:
 
 ```python
-from nanobot.bus.outbound_events import ProgressEvent
-
 async def send(self, msg: OutboundMessage) -> None:
-    event = msg.event
+    meta = msg.metadata or {}
 
-    if isinstance(event, ProgressEvent) and event.tool_hint:
+    if meta.get("_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 isinstance(event, ProgressEvent):
+    if meta.get("_progress"):
         # Generic non-final status, e.g. "Thinking..." or "Running command..."
         await self._send_trace(msg.chat_id, msg.content, kind="progress")
         return
@@ -429,33 +412,32 @@ class WebhookChannel(BaseChannel):
         chat_id: str,
         delta: str,
         metadata: dict[str, Any] | None = None,
-        *,
-        stream_id: str | None = None,
     ) -> None:
-        buffer_key = stream_id or chat_id
-        self._reasoning_buffers[buffer_key] = self._reasoning_buffers.get(buffer_key, "") + delta
-        await self._update_reasoning_block(chat_id, self._reasoning_buffers[buffer_key], final=False)
+        meta = metadata or {}
+        stream_id = str(meta.get("_stream_id") or chat_id)
+        self._reasoning_buffers[stream_id] = self._reasoning_buffers.get(stream_id, "") + delta
+        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:
-        buffer_key = stream_id or chat_id
-        text = self._reasoning_buffers.pop(buffer_key, "")
+        meta = metadata or {}
+        stream_id = str(meta.get("_stream_id") or chat_id)
+        text = self._reasoning_buffers.pop(stream_id, "")
         if text:
             await self._update_reasoning_block(chat_id, text, final=True)
 ```
 
-**Reasoning arguments:**
+**Reasoning metadata flags:**
 
-| Argument | Meaning |
+| Flag | Meaning |
 |------|---------|
-| `delta` | A reasoning/thinking chunk for `send_reasoning_delta()`. |
-| `stream_id` | Stable id for this assistant turn/segment. Use it to key buffers instead of only `chat_id`. |
-| `send_reasoning_end()` | The current reasoning block is complete. |
+| `_reasoning_delta: True` | A reasoning/thinking chunk; `delta` contains the new text. |
+| `_reasoning_end: True` | The current reasoning block is complete; `delta` is empty. |
+| `_reasoning: True` | Legacy one-shot reasoning. `BaseChannel.send_reasoning()` converts it to delta + end. |
+| `_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

@@ -240,7 +240,6 @@ 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 |
 |----------|---------|-------------|
@@ -633,37 +632,20 @@ 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. `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.
+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.
 
 **1. Login:**
 ```bash
 nanobot provider login openai-codex
 ```
 
-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`):
+**2. Set model** (merge into `~/.nanobot/config.json`):
 ```json
 {
   "modelPresets": {
     "codex": {
       "provider": "openai_codex",
-      "model": "gpt-5.1-codex",
-      "reasoningEffort": "high"
+      "model": "openai-codex/gpt-5.1-codex"
     }
   },
   "agents": {
@@ -674,9 +656,7 @@ The proxy applies to Codex OAuth token refresh, interactive token exchange, and
 }
 ```
 
-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:**
+**3. Chat:**
 ```bash
 nanobot agent -m "Hello!"
 
@@ -695,17 +675,7 @@ 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.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"
-```
+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.
 
 **1. Login:**
 ```bash
@@ -2004,7 +1974,6 @@ 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

@@ -12,32 +12,6 @@ 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

@@ -61,12 +61,9 @@ 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
@@ -425,32 +422,6 @@ 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

@@ -34,26 +34,6 @@ 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}"
@@ -72,8 +52,7 @@ class AutoCompact:
                 continue
             if key in active_session_keys:
                 continue
-            updated_at = info.get("updated_at")
-            if self._is_expired(updated_at, now) and self._has_compactable_idle_tail(key):
+            if self._is_expired(info.get("updated_at"), now):
                 self._archiving.add(key)
                 schedule_background(self._archive(key))
 

nanobot/agent/context_governance.py

@@ -36,23 +36,6 @@ 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)
@@ -78,9 +61,7 @@ class ContextGovernor:
         messages: list[dict[str, Any]],
         compacted_tool_call_ids: set[str],
     ) -> list[dict[str, Any]]:
-        updated = self.strip_placeholder_assistant_messages(messages)
-        updated = self.strip_malformed_tool_calls(updated)
-        updated = self.drop_orphan_tool_results(updated)
+        updated = self.drop_orphan_tool_results(messages)
         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)
@@ -135,99 +116,6 @@ 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

@@ -31,13 +31,6 @@ 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 (
@@ -64,11 +57,7 @@ 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,
-    replay_max_messages_for_context,
-)
+from nanobot.session.manager import Session, SessionManager
 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
@@ -212,6 +201,7 @@ 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,
@@ -225,7 +215,6 @@ 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
 
@@ -235,7 +224,6 @@ 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
@@ -304,7 +292,7 @@ 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 = replay_max_messages_for_context(self.context_window_tokens)
+        self._max_messages = max_messages if max_messages > 0 else 120
         self._running = False
         self._mcp_servers = mcp_servers or {}
         self._mcp_stacks: dict[str, AsyncExitStack] = {}
@@ -402,10 +390,10 @@ 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,
@@ -433,7 +421,6 @@ 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(
@@ -447,9 +434,6 @@ 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
@@ -574,12 +558,14 @@ 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(
-                outbound_message_for_event(
+                OutboundMessage(
                     channel=msg.channel,
                     chat_id=msg.chat_id,
-                    event=RetryWaitEvent(content=content),
-                    metadata=msg.metadata,
+                    content=content,
+                    metadata=meta,
                 )
             )
 
@@ -1004,31 +990,26 @@ class AgentLoop:
                             return f"{stream_base_id}:{stream_segment}"
 
                         async def on_stream(delta: str) -> None:
-                            await self.bus.publish_outbound(
-                                outbound_message_for_event(
-                                    channel=msg.channel,
-                                    chat_id=msg.chat_id,
-                                    event=StreamDeltaEvent(
-                                        content=delta,
-                                        stream_id=_current_stream_id(),
-                                    ),
-                                    metadata=msg.metadata,
-                                )
-                            )
+                            meta = dict(msg.metadata or {})
+                            meta["_stream_delta"] = True
+                            meta["_stream_id"] = _current_stream_id()
+                            await self.bus.publish_outbound(OutboundMessage(
+                                channel=msg.channel, chat_id=msg.chat_id,
+                                content=delta,
+                                metadata=meta,
+                            ))
 
                         async def on_stream_end(*, resuming: bool = False) -> None:
                             nonlocal stream_segment
-                            await self.bus.publish_outbound(
-                                outbound_message_for_event(
-                                    channel=msg.channel,
-                                    chat_id=msg.chat_id,
-                                    event=StreamEndEvent(
-                                        stream_id=_current_stream_id(),
-                                        resuming=resuming,
-                                    ),
-                                    metadata=msg.metadata,
-                                )
-                            )
+                            meta = dict(msg.metadata or {})
+                            meta["_stream_end"] = True
+                            meta["_resuming"] = resuming
+                            meta["_stream_id"] = _current_stream_id()
+                            await self.bus.publish_outbound(OutboundMessage(
+                                channel=msg.channel, chat_id=msg.chat_id,
+                                content="",
+                                metadata=meta,
+                            ))
                             stream_segment += 1
 
                     response = await self._process_message(
@@ -1381,10 +1362,9 @@ 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"}:
-            event = StreamedResponseEvent()
+            meta["_streamed"] = True
         if turn_latency_ms is not None:
             meta["latency_ms"] = int(turn_latency_ms)
 
@@ -1392,7 +1372,6 @@ class AgentLoop:
             channel=msg.channel,
             chat_id=msg.chat_id,
             content=final_content,
-            event=event,
             metadata=meta,
         )
 

nanobot/agent/memory.py

@@ -33,6 +33,7 @@ if TYPE_CHECKING:
     from nanobot.providers.base import LLMProvider
     from nanobot.session.manager import SessionManager
 
+
 # ---------------------------------------------------------------------------
 # MemoryStore — pure file I/O layer
 # ---------------------------------------------------------------------------
@@ -1005,6 +1006,7 @@ 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 ""
 
@@ -1016,11 +1018,12 @@ class Consolidator:
                 metadata={},
                 last_consolidated=0,
             )
-            result = probe.retain_recent_legal_suffix(max_suffix, extend_to_user=True)
+            dropped, already_consolidated = probe.retain_recent_legal_suffix(max_suffix, extend_to_user=True)
             messages_to_keep = probe.messages
-            messages_to_remove = result.dropped[result.already_consolidated_count:]
+            messages_to_remove = dropped[already_consolidated:]
 
             if not messages_to_remove and not messages_to_keep:
+                session.updated_at = datetime.now()
                 self.sessions.save(session)
                 return ""
 
@@ -1043,6 +1046,7 @@ 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, is_tool_error_result
+from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
 from nanobot.utils.file_edit_events import (
     StreamingFileEditTracker,
@@ -50,6 +50,7 @@ from nanobot.utils.runtime import (
     build_finalization_retry_message,
     build_goal_continue_message,
     build_length_recovery_message,
+    build_runtime_budget_notice_message,
     is_blank_text,
     repeated_external_lookup_error,
     repeated_workspace_violation_error,
@@ -67,6 +68,7 @@ _MAX_EMPTY_RETRIES = 2
 _MAX_LENGTH_RECOVERIES = 3
 _MAX_INJECTIONS_PER_TURN = 3
 _MAX_INJECTION_CYCLES = 5
+_BUDGET_NOTICE_MIN_ITERATIONS = 20
 # Backward-compatible module attribute for tests/extensions that monkeypatch
 # the former single-file tracker hook. Runtime uses prepare_file_edit_trackers.
 prepare_file_edit_tracker = _prepare_file_edit_tracker
@@ -357,6 +359,7 @@ class AgentRunner:
         length_recovery_count = 0
         had_injections = False
         injection_cycles = 0
+        budget_notice_level_sent = 0
         compacted_tool_call_ids: set[str] = set()
         governance_config = ContextGovernanceConfig(
             provider=self.provider,
@@ -389,15 +392,7 @@ class AgentRunner:
                     spec.session_key or "default",
                 )
                 try:
-                    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.drop_orphan_tool_results(messages)
                     messages_for_model = ContextGovernor.backfill_missing_tool_results(
                         messages_for_model
                     )
@@ -519,6 +514,12 @@ class AgentRunner:
                 )
                 if _drained:
                     had_injections = True
+                budget_notice_level_sent = self._append_runtime_budget_notice_if_needed(
+                    spec,
+                    messages,
+                    completed_iterations=iteration + 1,
+                    sent_level=budget_notice_level_sent,
+                )
                 await hook.after_iteration(context)
                 continue
 
@@ -733,8 +734,6 @@ 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:
@@ -877,94 +876,8 @@ 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,
@@ -1036,6 +949,53 @@ class AgentRunner:
         retry_messages.append(build_budget_exhausted_finalization_message())
         return retry_messages
 
+    @classmethod
+    def _append_runtime_budget_notice_if_needed(
+        cls,
+        spec: AgentRunSpec,
+        messages: list[dict[str, Any]],
+        *,
+        completed_iterations: int,
+        sent_level: int,
+    ) -> int:
+        level = cls._runtime_budget_notice_level(
+            max_iterations=spec.max_iterations,
+            completed_iterations=completed_iterations,
+        )
+        if level <= sent_level:
+            return sent_level
+
+        remaining_iterations = max(0, spec.max_iterations - completed_iterations)
+        messages.append(build_runtime_budget_notice_message(
+            level=level,
+            max_iterations=spec.max_iterations,
+            used_iterations=completed_iterations,
+            remaining_iterations=remaining_iterations,
+        ))
+        return level
+
+    @staticmethod
+    def _runtime_budget_notice_level(
+        *,
+        max_iterations: int,
+        completed_iterations: int,
+    ) -> int:
+        """Return the convergence-warning level for a long tool loop."""
+        if max_iterations < _BUDGET_NOTICE_MIN_ITERATIONS:
+            return 0
+
+        remaining_iterations = max_iterations - completed_iterations
+        if remaining_iterations <= 0:
+            return 0
+
+        convergence_threshold = max(5, (max_iterations + 9) // 10)
+        final_threshold = max(3, (max_iterations + 32) // 33)
+        if remaining_iterations <= final_threshold:
+            return 2
+        if remaining_iterations <= convergence_threshold:
+            return 1
+        return 0
+
     @staticmethod
     def _max_iterations_fallback(spec: AgentRunSpec) -> str:
         if spec.max_iterations_message:
@@ -1266,7 +1226,7 @@ class AgentRunner:
                 return payload, event, exc
             return payload, event, None
 
-        if is_tool_error_result(tool_call.name, result):
+        if isinstance(result, str) and result.startswith("Error"):
             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, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Schema, Tool, tool_parameters
 from nanobot.agent.tools.context import ToolContext
 from nanobot.agent.tools.loader import ToolLoader
 from nanobot.agent.tools.registry import ToolRegistry
@@ -25,7 +25,6 @@ __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 ToolResult, tool_parameters
+from nanobot.agent.tools.base import 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 ToolResult.error(f"Error: {exc}")
+            return f"Error: {exc}"
         except _PatchError as exc:
-            return ToolResult.error(f"Error applying patch: {exc}")
+            return f"Error applying patch: {exc}"
         except Exception as exc:
-            return ToolResult.error(f"Error applying patch: {exc}")
+            return f"Error applying patch: {exc}"

nanobot/agent/tools/base.py

@@ -128,21 +128,6 @@ 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."""
 
@@ -208,13 +193,9 @@ class Tool(ABC):
 
     @abstractmethod
     async def execute(self, **kwargs: Any) -> Any:
-        """Run the tool; return content, or ``ToolResult.error(...)`` for failures."""
+        """Run the tool; returns a string or list of content blocks."""
         ...
 
-    @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, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Tool, 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 ToolResult.error(f"Error: {exc.message}")
+            return 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, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Tool, 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 ToolResult.error(f"Error: unknown timezone '{tz}'")
+            return 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 ToolResult.error("Error: cannot schedule new jobs from within a cron job execution")
+                return "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 ToolResult.error(
+            return (
                 "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 ToolResult.error("Error: scheduled cron jobs must be created from a chat session")
+            return "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 ToolResult.error("Error: scheduled cron jobs must be created from a chat session")
+            return "Error: scheduled cron jobs must be created from a chat session"
         if tz and not cron_expr:
-            return ToolResult.error("Error: tz can only be used with cron_expr")
+            return "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 ToolResult.error(f"Error: invalid ISO datetime format '{at}'. Expected format: YYYY-MM-DDTHH:MM:SS")
+                return 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 ToolResult.error("Error: either every_seconds, cron_expr, or at is required")
+            return "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 ToolResult.error("Error: job_id is required for remove")
+            return "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, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Tool, tool_parameters
 from nanobot.agent.tools.context import current_request_session_key
 from nanobot.agent.tools.schema import (
     BooleanSchema,
@@ -17,6 +17,13 @@ from nanobot.agent.tools.schema import (
     StringSchema,
     tool_parameters_schema,
 )
+from nanobot.agent.verification_state import (
+    VerificationAnalysis,
+    analyze_verification_result,
+    append_verification_feedback,
+    record_verification_observation,
+)
+from nanobot.utils.helpers import build_structured_output_summary
 
 DEFAULT_YIELD_MS = 1000
 MAX_YIELD_MS = 30_000
@@ -37,6 +44,7 @@ class _SessionPoll:
     terminated: bool = False
     stdin_closed: bool = False
     truncated_chars: int = 0
+    analysis: VerificationAnalysis | None = None
 
 
 @dataclass(slots=True)
@@ -147,7 +155,19 @@ class _ExecSession:
             output = "".join(self._chunks)
             self._chunks.clear()
 
-        output, truncated = _truncate_output(output, max_output_chars)
+        analysis = analyze_verification_result(
+            command=self.command,
+            output=output,
+            exit_code=self.process.returncode,
+            timed_out=self._timed_out,
+        )
+        output, truncated = _truncate_output(
+            output,
+            max_output_chars,
+            analysis=analysis,
+            exit_code=self.process.returncode,
+            elapsed_s=max(0.0, time.monotonic() - self.started_at),
+        )
         return _SessionPoll(
             output=output,
             done=self.process.returncode is not None,
@@ -157,6 +177,7 @@ class _ExecSession:
             terminated=terminated,
             stdin_closed=stdin_closed,
             truncated_chars=truncated,
+            analysis=analysis,
         )
 
     async def kill(self) -> None:
@@ -320,15 +341,33 @@ def clamp_session_int(value: int | None, default: int, minimum: int, maximum: in
     return min(max(value, minimum), maximum)
 
 
-def _truncate_output(output: str, max_output_chars: int) -> tuple[str, int]:
+def _truncate_output(
+    output: str,
+    max_output_chars: int,
+    *,
+    analysis: VerificationAnalysis | None = None,
+    exit_code: int | None = None,
+    elapsed_s: float | None = None,
+) -> tuple[str, int]:
     if len(output) <= max_output_chars:
         return output, 0
-    half = max_output_chars // 2
     omitted = len(output) - max_output_chars
     return (
-        output[:half]
-        + f"\n\n... ({omitted:,} chars truncated) ...\n\n"
-        + output[-half:],
+        build_structured_output_summary(
+            "[tool output truncated]",
+            output,
+            max_chars=max_output_chars,
+            metadata=[
+                ("original_size_chars", len(output)),
+                ("exit_code", exit_code if exit_code is not None else "running"),
+                ("elapsed_s", f"{elapsed_s:.1f}" if elapsed_s is not None else "unknown"),
+            ],
+            analysis=analysis,
+            guidance=(
+                "Use the structured summary first. Poll again for new output "
+                "or rerun a narrower command instead of reading broad logs."
+            ),
+        ),
         omitted,
     )
 
@@ -351,6 +390,20 @@ def format_session_poll(session_id: str, poll: _SessionPoll) -> str:
     return "\n".join(parts) if parts else "(no output yet)"
 
 
+def _format_poll_with_verification(session_id: str, poll: _SessionPoll) -> str:
+    result = format_session_poll(session_id, poll)
+    if not poll.done:
+        return result
+    analysis = poll.analysis or analyze_verification_result(
+        command="",
+        output=result,
+        exit_code=poll.exit_code,
+        timed_out=poll.timed_out,
+    )
+    record_verification_observation(current_request_session_key(), analysis)
+    return append_verification_feedback(result, analysis)
+
+
 @tool_parameters(
     tool_parameters_schema(
         session_id=StringSchema("Session id returned by exec when yield_time_ms is used."),
@@ -492,12 +545,11 @@ class WriteStdinTool(Tool):
                 max_output_chars=output_limit,
                 owner_session_key=current_request_session_key(),
             )
-            result = format_session_poll(session_id, poll)
-            return ToolResult.error(result) if poll.timed_out else result
+            return _format_poll_with_verification(session_id, poll)
         except KeyError:
-            return ToolResult.error(f"Error: exec session not found: {session_id!r}")
+            return f"Error: exec session not found: {session_id}"
         except Exception as exc:
-            return ToolResult.error(f"Error writing to exec session: {exc}")
+            return f"Error writing to exec session: {exc}"
 
     async def _wait_for_output(
         self,
@@ -533,14 +585,13 @@ class WriteStdinTool(Tool):
                 joined = "".join(aggregate)
                 if wait_for in joined:
                     poll.output = joined
-                    result = format_session_poll(session_id, poll)
-                    return ToolResult.error(result) if poll.timed_out else result
+                    return _format_poll_with_verification(session_id, poll)
             if poll.done or remaining_ms <= 0:
                 poll.output = "".join(aggregate)
-                result = format_session_poll(session_id, poll)
+                result = _format_poll_with_verification(session_id, poll)
                 if wait_for not in poll.output:
                     result += f"\nWait target not observed: {wait_for!r}"
-                return ToolResult.error(result) if poll.timed_out else result
+                return result
 
 
 @tool_parameters(tool_parameters_schema())
@@ -608,4 +659,4 @@ class ListExecSessionsTool(Tool):
                 )
             return "\n".join(lines)
         except Exception as exc:
-            return ToolResult.error(f"Error listing exec sessions: {exc}")
+            return 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, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Tool, 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 ToolResult.error("Error reading file: Unknown path")
+                return "Error reading file: Unknown path"
 
             # Device path blacklist
             if _is_blocked_device(path):
-                return ToolResult.error(f"Error: Reading {path} is blocked (device path that could hang or produce infinite output).")
+                return 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 ToolResult.error(f"Error: Reading {fp} is blocked (device path that could hang or produce infinite output).")
+                return f"Error: Reading {fp} is blocked (device path that could hang or produce infinite output)."
             if not fp.exists():
-                return ToolResult.error(f"Error: File not found: {path}")
+                return f"Error: File not found: {path}"
             if not fp.is_file():
-                return ToolResult.error(f"Error: Not a file: {path}")
+                return 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 ToolResult.error(f"Error: Cannot read binary file {path} (MIME: {mime or 'unknown'}). Only UTF-8 text and images are supported.")
+                return 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 ToolResult.error(f"Error: offset {offset} is beyond end of file ({total} lines)")
+                return 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 ToolResult.error(f"Error: {e}")
+            return f"Error: {e}"
         except Exception as e:
-            return ToolResult.error(f"Error reading file: {e}")
+            return f"Error reading file: {e}"
 
     def _read_pdf(self, fp: Path, pages: str | None) -> str:
         try:
             import fitz  # pymupdf
         except ImportError:
-            return ToolResult.error("Error: PDF reading requires pymupdf. Install with: pip install pymupdf")
+            return "Error: PDF reading requires pymupdf. Install with: pip install pymupdf"
 
         try:
             doc = fitz.open(str(fp))
         except Exception as e:
-            return ToolResult.error(f"Error reading PDF: {e}")
+            return 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 ToolResult.error(f"Error: Invalid page range '{pages}'. Use format like '1-5'.")
+                return f"Error: Invalid page range '{pages}'. Use format like '1-5'."
             if start > end or start >= total_pages:
                 doc.close()
-                return ToolResult.error(f"Error: Page range '{pages}' is out of bounds (document has {total_pages} pages).")
+                return 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 ToolResult.error(f"Error: Unsupported file format: {fp.suffix}")
+            return f"Error: Unsupported file format: {fp.suffix}"
 
         if result.startswith("[error:"):
-            return ToolResult.error(f"Error reading {fp.suffix.upper()} file: {result}")
+            return 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 ToolResult.error(f"Error: {e}")
+            return f"Error: {e}"
         except Exception as e:
-            return ToolResult.error(f"Error writing file: {e}")
+            return 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 ToolResult.error("Error: occurrence must be >= 1.")
+                return "Error: occurrence must be >= 1."
             if line_hint is not None and line_hint < 1:
-                return ToolResult.error("Error: line_hint must be >= 1.")
+                return "Error: line_hint must be >= 1."
             if expected_replacements is not None and expected_replacements < 1:
-                return ToolResult.error("Error: expected_replacements must be >= 1.")
+                return "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 ToolResult.error(f"Error: File too large to edit ({fsize / (1024**3):.1f} GiB). Maximum is 1 GiB.")
+                return 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 ToolResult.error(f"Error: Cannot create file — {path} already exists and is not empty.")
+                    return 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 ToolResult.error("Error: occurrence cannot be used with replace_all=true.")
+                return "Error: occurrence cannot be used with replace_all=true."
             if replace_all and line_hint is not None:
-                return ToolResult.error("Error: line_hint cannot be used with replace_all=true.")
+                return "Error: line_hint cannot be used with replace_all=true."
             if occurrence is not None and line_hint is not None:
-                return ToolResult.error("Error: line_hint cannot be used with occurrence.")
+                return "Error: line_hint cannot be used with occurrence."
             if count > 1 and not replace_all:
                 if occurrence is not None:
                     if occurrence > count:
-                        return ToolResult.error(
+                        return (
                             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 ToolResult.error(
+                        return (
                             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 ToolResult.error(
+                return (
                     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 ToolResult.error(
+                return (
                     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 ToolResult.error(f"Error: {e}")
+            return f"Error: {e}"
         except Exception as e:
-            return ToolResult.error(f"Error editing file: {e}")
+            return 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 ToolResult.error("\n".join(parts))
+        return "\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 ToolResult.error(
+            return (
                 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 ToolResult.error(
+            return (
                 f"Error: old_text not found in {path}. "
                 f"Possible cause: {', '.join(hints)}. "
                 "Copy the exact text from read_file and try again."
             )
-        return ToolResult.error(f"Error: old_text not found in {path}. No similar text found. Verify the file content.")
+        return 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 ToolResult.error(f"Error: Directory not found: {path}")
+                return f"Error: Directory not found: {path}"
             if not dp.is_dir():
-                return ToolResult.error(f"Error: Not a directory: {path}")
+                return 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 ToolResult.error(f"Error: {e}")
+            return f"Error: {e}"
         except Exception as e:
-            return ToolResult.error(f"Error listing directory: {e}")
+            return 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, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Tool, 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 ToolResult.error(f"Error: unsupported image generation provider '{self.config.provider}'")
+            return f"Error: unsupported image generation provider '{self.config.provider}'"
 
         requested = count or 1
         if requested > self.config.max_images_per_turn:
-            return ToolResult.error(
+            return (
                 "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 ToolResult.error(f"Error: {exc}")
+            return 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, ToolResult
+from nanobot.agent.tools.base import Tool
 from nanobot.agent.tools.registry import ToolRegistry
 
 _SKIP_MODULES = frozenset({
@@ -96,8 +96,6 @@ 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(
@@ -116,67 +114,3 @@ 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

@@ -20,9 +20,14 @@ from contextvars import ContextVar
 from datetime import datetime
 from typing import TYPE_CHECKING, Any
 
-from nanobot.agent.tools.base import Tool, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Tool, tool_parameters
 from nanobot.agent.tools.context import ContextAware, RequestContext
 from nanobot.agent.tools.schema import StringSchema, tool_parameters_schema
+from nanobot.agent.verification_state import (
+    clear_verification_observation,
+    format_completion_gate_message,
+    latest_verification_observation,
+)
 from nanobot.bus.runtime_events import GoalStateChanged, RuntimeEventBus, RuntimeEventContext
 from nanobot.session.goal_state import (
     GOAL_STATE_KEY,
@@ -150,12 +155,12 @@ 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 ToolResult.error(
+            return (
                 "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 ToolResult.error(
+            return (
                 "Error: a sustained goal is already active. "
                 "Use complete_goal when finished, or ask the user before replacing it."
             )
@@ -187,6 +192,29 @@ class LongTaskTool(Tool, _GoalToolsMixin):
             max_length=8000,
             nullable=True,
         ),
+        verification_summary=StringSchema(
+            "For coding or file-producing tasks, summarize how the work was verified. "
+            "Mention the most relevant test/check command and whether it passed. "
+            "If no verification was possible, say why.",
+            max_length=4000,
+            nullable=True,
+        ),
+        commands_run=StringSchema(
+            "Optional concise list of verification/build commands run before completion.",
+            max_length=4000,
+            nullable=True,
+        ),
+        artifacts_created=StringSchema(
+            "Optional concise list of files, outputs, or artifacts created.",
+            max_length=4000,
+            nullable=True,
+        ),
+        remaining_failures=StringSchema(
+            "Known unresolved failures, if intentionally stopping before success. "
+            "Leave empty when verification passes.",
+            max_length=4000,
+            nullable=True,
+        ),
         required=[],
     )
 )
@@ -222,30 +250,67 @@ class CompleteGoalTool(Tool, _GoalToolsMixin):
         return (
             "End bookkeeping for the active sustained goal. "
             "Use when the objective is fully achieved and verified—recap what was delivered. "
+            "For coding/file-producing tasks, run the smallest reliable verification first and include "
+            "verification_summary / commands_run / artifacts_created. "
             "Also call when the user cancels, redirects, or replaces the goal: recap must reflect "
             "what actually happened (not necessarily success). "
+            "If recent verification failed and no later verification passed, this tool will ask you to "
+            "continue fixing unless remaining_failures describes an intentional incomplete stop. "
             "If no goal is active, the tool reports that and leaves metadata unchanged."
         )
 
-    async def execute(self, recap: str | None = None, **kwargs: Any) -> str:
+    async def execute(
+        self,
+        recap: str | None = None,
+        verification_summary: str | None = None,
+        commands_run: str | None = None,
+        artifacts_created: str | None = None,
+        remaining_failures: str | None = None,
+        **kwargs: Any,
+    ) -> str:
         sess = self._session()
         if sess is None:
-            return ToolResult.error("Error: complete_goal requires an active chat session.")
+            return "Error: complete_goal requires an active chat session."
+
+        session_key = self._request_ctx.get().session_key if self._request_ctx.get() else None
+        observation = latest_verification_observation(session_key)
+        if (
+            observation is not None
+            and observation.analysis.status == "failed"
+            and not _has_meaningful_remaining_failures(remaining_failures)
+        ):
+            return format_completion_gate_message(observation)
+
         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."
 
         ended = _iso_now()
-        sess.metadata[GOAL_STATE_KEY] = {
+        completed = {
             **prior,
             "status": "completed",
             "completed_at": ended,
             "recap": (recap or "").strip(),
         }
+        if verification_summary:
+            completed["verification_summary"] = verification_summary.strip()
+        if commands_run:
+            completed["commands_run"] = commands_run.strip()
+        if artifacts_created:
+            completed["artifacts_created"] = artifacts_created.strip()
+        if remaining_failures:
+            completed["remaining_failures"] = remaining_failures.strip()
+        sess.metadata[GOAL_STATE_KEY] = completed
         discard_legacy_goal_state_key(sess.metadata)
         self._sessions.save(sess)
+        clear_verification_observation(session_key)
         await self._publish_goal_state_changed(sess.metadata)
         tail = (recap or "").strip()
         if tail:
             return f"Goal marked complete ({ended}). Recap:\n{tail}"
         return f"Goal marked complete ({ended})."
+
+
+def _has_meaningful_remaining_failures(value: str | None) -> bool:
+    text = (value or "").strip().lower()
+    return bool(text and text not in {"none", "no", "n/a", "na", "no remaining failures"})

nanobot/agent/tools/mcp.py

@@ -1,7 +1,6 @@
 """MCP client: connects to MCP servers and wraps their tools as native nanobot tools."""
 
 import asyncio
-import json
 import os
 import re
 import shutil
@@ -14,7 +13,7 @@ from weakref import WeakKeyDictionary
 import httpx
 from loguru import logger
 
-from nanobot.agent.tools.base import Tool, ToolResult
+from nanobot.agent.tools.base import Tool
 from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.bus.events import (
     INBOUND_META_RUNTIME_CONTROL,
@@ -166,31 +165,12 @@ 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 {_redact_url(str(request.url))} ({error})",
+            f"Blocked unsafe MCP URL {request.url} ({error})",
             request=request,
         )
 
@@ -333,52 +313,6 @@ 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."""
 
@@ -406,6 +340,8 @@ 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:
@@ -460,66 +396,17 @@ class MCPToolWrapper(_MCPWrapperBase):
                 )
                 return f"(MCP tool call failed: {type(exc).__name__})"
             else:
-                # Success — extract text and persist any image content as artifacts.
-                rendered = self._render_call_result(result.content, kwargs)
-                if getattr(result, "isError", False):
-                    return ToolResult.error(rendered)
-                return rendered
+                # Success — extract result
+                parts = []
+                for block in result.content:
+                    if isinstance(block, types.TextContent):
+                        parts.append(block.text)
+                    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."""
@@ -796,7 +683,7 @@ async def connect_mcp_servers(
                     logger.warning(
                         "MCP server '{}': blocked unsafe URL {} ({})",
                         name,
-                        _redact_url(cfg.url),
+                        cfg.url,
                         error,
                     )
                     await server_stack.aclose()
@@ -817,7 +704,7 @@ 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, _redact_url(cfg.url))
+                    logger.warning("MCP server '{}': {} unreachable, skipping", name, cfg.url)
                     await server_stack.aclose()
                     return name, None
 
@@ -844,7 +731,7 @@ async def connect_mcp_servers(
                 )
             elif transport_type == "streamableHttp":
                 if not await _probe_http_url(cfg.url):
-                    logger.warning("MCP server '{}': {} unreachable, skipping", name, _redact_url(cfg.url))
+                    logger.warning("MCP server '{}': {} unreachable, skipping", name, 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, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Tool, 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 ToolResult.error("Error: buttons must be a list of list of strings")
+                return "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 ToolResult.error(
+            return (
                 "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 ToolResult.error("Error: No target channel/chat specified")
+            return "Error: No target channel/chat specified"
 
         if not self._send_callback:
-            return ToolResult.error("Error: Message sending not configured")
+            return "Error: Message sending not configured"
 
         if media:
             try:
                 media = self._resolve_media(media)
             except (OSError, PermissionError, ValueError) as e:
-                return ToolResult.error(f"Error: media path is not allowed: {str(e)}")
+                return 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 ToolResult.error(f"Error sending message: {str(e)}")
+            return f"Error sending message: {str(e)}"

nanobot/agent/tools/registry.py

@@ -3,11 +3,7 @@
 import json
 from typing import Any
 
-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
+from nanobot.agent.tools.base import Tool
 
 
 class ToolRegistry:
@@ -104,26 +100,22 @@ 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)}"
-                )
+                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.'
-                )
+                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, (
-                ToolResult.error(f"Error: Invalid parameters for tool '{name}': " + "; ".join(errors))
+                f"Error: Invalid parameters for tool '{name}': " + "; ".join(errors)
             )
         return tool, cast_params, None
 
@@ -167,16 +159,16 @@ 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 ToolResult.error(str(error) + hint)
+            return error + hint
 
         try:
             assert tool is not None  # guarded by prepare_call()
             result = await tool.execute(**params)
-            if is_tool_error_result(name, result):
-                return ToolResult.error(str(result) + hint)
+            if isinstance(result, str) and result.startswith("Error"):
+                return result + hint
             return result
         except Exception as e:
-            return ToolResult.error(f"Error executing {name}: {str(e)}" + hint)
+            return f"Error executing {name}: {str(e)}" + hint
 
     @property
     def tool_names(self) -> list[str]:

nanobot/agent/tools/search.py

@@ -9,7 +9,6 @@ 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
@@ -219,12 +218,12 @@ class FindFilesTool(_SearchTool):
         try:
             target = self._resolve(path or ".")
             if not target.exists():
-                return ToolResult.error(f"Error: Path not found: {path}")
+                return f"Error: Path not found: {path}"
             if not (target.is_dir() or target.is_file()):
-                return ToolResult.error(f"Error: Unsupported path: {path}")
+                return f"Error: Unsupported path: {path}"
 
             if sort not in {"path", "modified"}:
-                return ToolResult.error("Error: sort must be 'path' or 'modified'")
+                return "Error: sort must be 'path' or 'modified'"
 
             limit = (
                 _DEFAULT_FILE_HEAD_LIMIT
@@ -272,9 +271,9 @@ class FindFilesTool(_SearchTool):
                 result += "\n\n" + note
             return result
         except PermissionError as e:
-            return ToolResult.error(f"Error: {e}")
+            return f"Error: {e}"
         except Exception as e:
-            return ToolResult.error(f"Error finding files: {e}")
+            return f"Error finding files: {e}"
 
 
 class GrepTool(_SearchTool):
@@ -426,16 +425,16 @@ class GrepTool(_SearchTool):
         try:
             target = self._resolve(path or ".")
             if not target.exists():
-                return ToolResult.error(f"Error: Path not found: {path}")
+                return f"Error: Path not found: {path}"
             if not (target.is_dir() or target.is_file()):
-                return ToolResult.error(f"Error: Unsupported path: {path}")
+                return 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 ToolResult.error(f"Error: invalid regex pattern: {e}")
+                return f"Error: invalid regex pattern: {e}"
 
             if head_limit is not None:
                 limit = None if head_limit == 0 else head_limit
@@ -580,6 +579,6 @@ class GrepTool(_SearchTool):
                 result += "\n\n" + "\n".join(notes)
             return result
         except PermissionError as e:
-            return ToolResult.error(f"Error: {e}")
+            return f"Error: {e}"
         except Exception as e:
-            return ToolResult.error(f"Error searching files: {e}")
+            return 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, ToolResult
+from nanobot.agent.tools.base import Tool
 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 ToolResult.error(f"Error: '{label}' cannot be empty or whitespace")
+            return 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 ToolResult.error("Error: set is disabled (tools.my.allow_set is false)")
+            return "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 ToolResult.error(f"Error: '{top}' is not accessible")
+            return 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 ToolResult.error(f"Error: {err}")
+            return 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 ToolResult.error(f"Error: '{key}' not found")
+            return 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 ToolResult.error(f"Error: '{key}' is protected and cannot be modified")
+            return f"Error: '{key}' is protected and cannot be modified"
         if top in self.READ_ONLY:
             self._audit("modify", f"READ_ONLY {key}")
-            return ToolResult.error(f"Error: '{key}' is read-only and cannot be modified")
+            return 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 ToolResult.error(f"Error: '{leaf}' is not accessible")
+                return f"Error: '{leaf}' is not accessible"
             if leaf.lower() in self._SENSITIVE_NAMES:
                 self._audit("modify", f"BLOCKED sensitive leaf '{leaf}'")
-                return ToolResult.error(f"Error: '{leaf}' is not accessible")
+                return f"Error: '{leaf}' is not accessible"
             parent, err = self._resolve_path(parent_path)
             if err:
-                return ToolResult.error(f"Error: {err}")
+                return 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 ToolResult.error("Error: 'model_preset' must be a non-empty string")
+            return "Error: 'model_preset' must be a non-empty string"
         name = value.strip()
         result = self._modify_free("model_preset", name)
-        if isinstance(result, ToolResult) and result.is_error:
-            return result if result.endswith((".", "!", "?")) else ToolResult.error(f"{result}.")
+        if result.startswith("Error:"):
+            return result if result.endswith((".", "!", "?")) else 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}"
@@ -422,25 +422,22 @@ class MyTool(Tool, ContextAware):
         spec = self.RESTRICTED[key]
         expected = spec["type"]
         if expected is int and isinstance(value, bool):
-            return ToolResult.error(f"Error: '{key}' must be {expected.__name__}, got bool")
+            return f"Error: '{key}' must be {expected.__name__}, got bool"
         if not isinstance(value, expected):
             try:
                 value = expected(value)
             except (ValueError, TypeError):
-                return ToolResult.error(f"Error: '{key}' must be {expected.__name__}, got {type(value).__name__}")
+                return 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 ToolResult.error(f"Error: '{key}' must be >= {spec['min']}")
+            return f"Error: '{key}' must be >= {spec['min']}"
         if "max" in spec and value > spec["max"]:
-            return ToolResult.error(f"Error: '{key}' must be <= {spec['max']}")
+            return f"Error: '{key}' must be <= {spec['max']}"
         if "min_len" in spec and len(str(value)) < spec["min_len"]:
-            return ToolResult.error(f"Error: '{key}' must be at least {spec['min_len']} characters")
+            return 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}")
@@ -458,25 +455,25 @@ class MyTool(Tool, ContextAware):
                         "modify",
                         f"REJECTED type mismatch {key}: expects {old_t.__name__}, got {new_t.__name__}",
                     )
-                    return ToolResult.error(f"Error: '{key}' expects {old_t.__name__}, got {new_t.__name__}")
+                    return 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 ToolResult.error(f"Error: {message}")
+                return 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 ToolResult.error("Error: cannot store callable values")
+            return "Error: cannot store callable values"
         err = self._validate_json_safe(value)
         if err:
             self._audit("modify", f"REJECTED {key}: {err}")
-            return ToolResult.error(f"Error: {err}")
+            return 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 ToolResult.error(f"Error: scratchpad is full (max {self._MAX_RUNTIME_KEYS} keys). Remove unused keys first.")
+            return 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

@@ -6,17 +6,19 @@ import asyncio
 import os
 import re
 import shutil
+import subprocess
 import sys
+import time
+import uuid
 from contextlib import suppress
-from copy import deepcopy
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Any
 
 from loguru import logger
-from pydantic import Field
+from pydantic import AliasChoices, Field
 
-from nanobot.agent.tools.base import Schema, Tool, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Tool, tool_parameters
 from nanobot.agent.tools.context import current_request_session_key
 from nanobot.agent.tools.exec_session import (
     DEFAULT_EXEC_SESSION_MANAGER,
@@ -34,12 +36,19 @@ from nanobot.agent.tools.schema import (
     StringSchema,
     tool_parameters_schema,
 )
+from nanobot.agent.verification_state import (
+    analyze_verification_result,
+    append_verification_feedback,
+    record_verification_observation,
+)
 from nanobot.config.paths import get_media_dir
 from nanobot.config_base import Base
 from nanobot.security.workspace_access import current_scope_allows_loopback, current_tool_workspace
 from nanobot.security.workspace_policy import is_path_within
+from nanobot.utils.helpers import build_structured_output_summary
 
 _IS_WINDOWS = sys.platform == "win32"
+_DETACHED_EXIT_GRACE_S = 1.0 if _IS_WINDOWS else 0.2
 
 
 # Policy note appended to recoverable workspace-boundary guard errors.
@@ -56,6 +65,13 @@ class ExecToolConfig(Base):
     """Shell exec tool configuration."""
     enable: bool = True
     timeout: int = Field(default=60, ge=0)  # Hard timeout (s); 0 = no limit. Not capped by the per-call max.
+    allow_local_service_access: bool = Field(
+        default=False,
+        validation_alias=AliasChoices(
+            "allowLocalServiceAccess",
+            "allow_local_service_access",
+        ),
+    )  # allow shell commands to reach literal localhost/loopback services
     path_prepend: str = ""
     path_append: str = ""
     sandbox: str = ""
@@ -74,55 +90,51 @@ class _PreparedCommand:
     login: bool
 
 
-_EXEC_TOOL_PARAMETERS = tool_parameters_schema(
-    command=StringSchema("The shell command to execute"),
-    working_dir=StringSchema("Optional working directory for the command"),
-    timeout=IntegerSchema(
-        60,
-        description=(
-            "Timeout in seconds. Increase for long-running commands "
-            "like compilation or installation (default 60, max 600)."
+@tool_parameters(
+    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=(
+                "Timeout in seconds. Increase for long-running commands "
+                "like compilation or installation (default 60, max 600)."
+            ),
+            minimum=1,
+            maximum=600,
         ),
-        minimum=1,
-        maximum=600,
-    ),
-    shell=StringSchema(
-        "Optional shell binary to launch. On Unix, supports sh, bash, or zsh.",
-        nullable=True,
-    ),
-    login=BooleanSchema(
-        description="Whether to run bash/zsh with login shell semantics (default false).",
-        default=False,
-        nullable=True,
-    ),
-    yield_time_ms=IntegerSchema(
-        description=(
-            "Optional milliseconds to wait before returning output. "
-            "When set, a still-running command returns a session_id that "
-            "can be polled or written to with write_stdin. Omit this field "
-            "to keep one-shot exec behavior."
+        shell=StringSchema(
+            "Optional shell binary to launch. On Unix, supports sh, bash, or zsh.",
+            nullable=True,
         ),
-        minimum=0,
-        maximum=MAX_YIELD_MS,
-        nullable=True,
-    ),
-    max_output_chars=IntegerSchema(
-        description=(
-            "Maximum output characters to return when yield_time_ms is used "
-            "(default 10000, max 50000)."
+        login=BooleanSchema(
+            description="Whether to run bash/zsh with login shell semantics (default false).",
+            default=False,
+            nullable=True,
         ),
-        minimum=1000,
-        maximum=MAX_OUTPUT_CHARS,
-        nullable=True,
-    ),
-)
-
-_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(
+        yield_time_ms=IntegerSchema(
+            description=(
+                "Optional milliseconds to wait before returning output. "
+                "When set, a still-running command returns a session_id that "
+                "can be polled or written to with write_stdin. Omit this field "
+                "to keep one-shot exec behavior."
+            ),
+            minimum=0,
+            maximum=MAX_YIELD_MS,
+            nullable=True,
+        ),
+        max_output_chars=IntegerSchema(
+            description=(
+                "Maximum output characters to return when yield_time_ms is used "
+                "(default 10000, max 50000)."
+            ),
+            minimum=1000,
+            maximum=MAX_OUTPUT_CHARS,
+            nullable=True,
+        ),
+        max_output_tokens=IntegerSchema(
             description=(
                 "Compatibility alias for max_output_chars. The current runtime "
                 "uses a character budget."
@@ -130,12 +142,19 @@ _EXEC_TOOL_COMPAT_PARAMETERS["properties"].update(
             minimum=1000,
             maximum=MAX_OUTPUT_CHARS,
             nullable=True,
-        ).to_json_schema(),
-    }
+        ),
+        detach=BooleanSchema(
+            description=(
+                "Run the command as a detached background process that can "
+                "survive after the agent finishes. Use for local servers, "
+                "dev servers, mock APIs, or other services that must remain "
+                "available for later commands or external verification."
+            ),
+            default=False,
+            nullable=True,
+        ),
+    )
 )
-
-
-@tool_parameters(_EXEC_TOOL_PARAMETERS)
 class ExecTool(Tool):
     """Tool to execute shell commands."""
     _scopes = {"core", "subagent"}
@@ -157,6 +176,7 @@ class ExecTool(Tool):
             working_dir=ctx.workspace,
             timeout=cfg.timeout,
             restrict_to_workspace=ctx.config.restrict_to_workspace,
+            allow_local_service_access=cfg.allow_local_service_access,
             webui_allow_local_service_access=ctx.config.webui_allow_local_service_access,
             sandbox=cfg.sandbox,
             path_prepend=cfg.path_prepend,
@@ -173,6 +193,7 @@ class ExecTool(Tool):
         deny_patterns: list[str] | None = None,
         allow_patterns: list[str] | None = None,
         restrict_to_workspace: bool = False,
+        allow_local_service_access: bool = False,
         webui_allow_local_service_access: bool = True,
         allow_local_preview_access: bool | None = None,
         sandbox: str = "",
@@ -205,6 +226,7 @@ class ExecTool(Tool):
         ]
         self.allow_patterns = allow_patterns or []
         self.restrict_to_workspace = restrict_to_workspace
+        self.allow_local_service_access = allow_local_service_access
         if allow_local_preview_access is not None:
             webui_allow_local_service_access = allow_local_preview_access
         self.webui_allow_local_service_access = webui_allow_local_service_access
@@ -244,26 +266,17 @@ class ExecTool(Tool):
             "Use -y or --yes flags to avoid interactive prompts. "
             "For long-running or interactive commands, pass yield_time_ms; "
             "if the command keeps running, exec returns a session_id that can "
-            "be polled or written to with write_stdin. Output is truncated at "
-            "10 000 chars; timeout defaults to 60s."
+            "be polled or written to with write_stdin. For services that "
+            "must remain available after you finish, pass detach=true instead "
+            "of yield_time_ms; detached output is written to a log file and "
+            "the tool returns a pid. Output is truncated at 10 000 chars; "
+            "timeout defaults to 60s."
         )
 
     @property
     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,
@@ -271,12 +284,13 @@ class ExecTool(Tool):
         login: bool | None = None, yield_time_ms: int | None = None,
         max_output_chars: int | None = None,
         max_output_tokens: int | None = None,
+        detach: bool | None = False,
         **kwargs: Any,
     ) -> str:
         command = command or cmd
         working_dir = working_dir or workdir
         if not command:
-            return ToolResult.error("Error: Missing command. Provide command or cmd.")
+            return "Error: Missing command. Provide command or cmd."
         if max_output_chars is None:
             max_output_chars = max_output_tokens
 
@@ -284,10 +298,14 @@ class ExecTool(Tool):
         if isinstance(prepared, str):
             return prepared
 
+        if detach:
+            return await self._execute_detached(prepared)
+
         if yield_time_ms is not None:
             return await self._execute_session(prepared, yield_time_ms, max_output_chars)
 
         try:
+            started_at = time.monotonic()
             process = await self._spawn(
                 prepared.command,
                 prepared.cwd,
@@ -303,7 +321,15 @@ class ExecTool(Tool):
                 )
             except asyncio.TimeoutError:
                 await self._kill_process(process)
-                return ToolResult.error(f"Error: Command timed out after {prepared.timeout} seconds")
+                result = f"Error: Command timed out after {prepared.timeout} seconds"
+                analysis = analyze_verification_result(
+                    command=prepared.command,
+                    output=result,
+                    exit_code=None,
+                    timed_out=True,
+                )
+                record_verification_observation(current_request_session_key(), analysis)
+                return append_verification_feedback(result, analysis)
             except asyncio.CancelledError:
                 await self._kill_process(process)
                 raise
@@ -321,20 +347,38 @@ class ExecTool(Tool):
             output_parts.append(f"\nExit code: {process.returncode}")
 
             result = "\n".join(output_parts) if output_parts else "(no output)"
+            elapsed_s = max(0.0, time.monotonic() - started_at)
+
+            analysis = analyze_verification_result(
+                command=prepared.command,
+                output=result,
+                exit_code=process.returncode,
+            )
 
             max_len = clamp_session_int(max_output_chars, self._MAX_OUTPUT, 1000, MAX_OUTPUT_CHARS)
             if len(result) > max_len:
-                half = max_len // 2
-                result = (
-                    result[:half]
-                    + f"\n\n... ({len(result) - max_len:,} chars truncated) ...\n\n"
-                    + result[-half:]
+                result = build_structured_output_summary(
+                    "[tool output truncated]",
+                    result,
+                    max_chars=max_len,
+                    metadata=[
+                        ("original_size_chars", len(result)),
+                        ("exit_code", process.returncode),
+                        ("duration_s", f"{elapsed_s:.1f}"),
+                    ],
+                    analysis=analysis,
+                    guidance=(
+                        "Use the structured summary first. Rerun a narrower "
+                        "command, grep a specific failure, or inspect the "
+                        "named artifact instead of rerunning broad noisy logs."
+                    ),
                 )
 
-            return result
+            record_verification_observation(current_request_session_key(), analysis)
+            return append_verification_feedback(result, analysis)
 
         except Exception as e:
-            return ToolResult.error(f"Error executing command: {str(e)}")
+            return f"Error executing command: {str(e)}"
 
     async def _execute_session(
         self,
@@ -360,9 +404,69 @@ class ExecTool(Tool):
                 ),
             )
             result = format_session_poll(session_id, poll)
-            return ToolResult.error(result) if poll.timed_out else result
+            if poll.done:
+                analysis = analyze_verification_result(
+                    command=prepared.command,
+                    output=result,
+                    exit_code=poll.exit_code,
+                    timed_out=poll.timed_out,
+                )
+                record_verification_observation(current_request_session_key(), analysis)
+                return append_verification_feedback(result, analysis)
+            return result
         except Exception as exc:
-            return ToolResult.error(f"Error executing command: {exc}")
+            return f"Error executing command: {exc}"
+
+    async def _execute_detached(self, prepared: _PreparedCommand) -> str:
+        log_dir = Path(prepared.cwd) / ".nanobot" / "exec-logs"
+        try:
+            log_dir.mkdir(parents=True, exist_ok=True)
+            log_path = log_dir / f"detached-{uuid.uuid4().hex[:12]}.log"
+        except Exception as exc:
+            return f"Error preparing detached command log directory: {exc}"
+
+        log_handle = None
+        try:
+            log_handle = open(log_path, "ab", buffering=0)
+            process = await self._spawn(
+                prepared.command,
+                prepared.cwd,
+                prepared.env,
+                prepared.shell_program,
+                prepared.login,
+                stdout=log_handle,
+                stderr=log_handle,
+                start_new_session=not _IS_WINDOWS,
+                creationflags=subprocess.CREATE_NEW_PROCESS_GROUP if _IS_WINDOWS else 0,
+            )
+        except Exception as exc:
+            return f"Error starting detached command: {exc}"
+        finally:
+            if log_handle is not None:
+                with suppress(Exception):
+                    log_handle.close()
+
+        try:
+            exit_code = await asyncio.wait_for(process.wait(), timeout=_DETACHED_EXIT_GRACE_S)
+        except asyncio.TimeoutError:
+            return (
+                "Detached process started.\n"
+                f"pid: {process.pid}\n"
+                f"cwd: {prepared.cwd}\n"
+                f"log: {log_path}\n"
+                "Poll the log or run a health check to verify the service is ready."
+            )
+
+        log_text = ""
+        with suppress(Exception):
+            log_text = log_path.read_text(encoding="utf-8", errors="replace")
+        if len(log_text) > 4000:
+            log_text = log_text[-4000:]
+        return (
+            f"Detached process exited immediately with code {exit_code}.\n"
+            f"log: {log_path}\n"
+            f"{log_text}"
+        )
 
     def _resolve_timeout(self, timeout: int | None) -> int | None:
         """Resolve the effective hard timeout in seconds (None = no limit).
@@ -404,12 +508,12 @@ class ExecTool(Tool):
                 requested = Path(cwd).expanduser().resolve()
                 resolved_root = Path(workspace_root).expanduser().resolve()
             except Exception:
-                return ToolResult.error(
+                return (
                     "Error: working_dir could not be resolved"
                     + _WORKSPACE_BOUNDARY_NOTE
                 )
             if not is_path_within(requested, resolved_root):
-                return ToolResult.error(
+                return (
                     "Error: working_dir is outside the configured workspace"
                     + _WORKSPACE_BOUNDARY_NOTE
                 )
@@ -485,6 +589,10 @@ class ExecTool(Tool):
         login: bool = False,
         *,
         stdin: int = asyncio.subprocess.DEVNULL,
+        stdout: Any = asyncio.subprocess.PIPE,
+        stderr: Any = asyncio.subprocess.PIPE,
+        start_new_session: bool = False,
+        creationflags: int = 0,
     ) -> asyncio.subprocess.Process:
         """Launch *command* in a platform-appropriate shell."""
         if _IS_WINDOWS:
@@ -492,18 +600,20 @@ class ExecTool(Tool):
                 return await asyncio.create_subprocess_exec(
                     "powershell", "-NoProfile", "-Command", command,
                     stdin=stdin,
-                    stdout=asyncio.subprocess.PIPE,
-                    stderr=asyncio.subprocess.PIPE,
+                    stdout=stdout,
+                    stderr=stderr,
                     cwd=cwd,
                     env=env,
+                    creationflags=creationflags,
                 )
             return await asyncio.create_subprocess_shell(
                 command,
                 stdin=stdin,
-                stdout=asyncio.subprocess.PIPE,
-                stderr=asyncio.subprocess.PIPE,
+                stdout=stdout,
+                stderr=stderr,
                 cwd=cwd,
                 env=env,
+                creationflags=creationflags,
             )
         shell_program = shell_program or shutil.which("bash") or "/bin/bash"
         args = [shell_program]
@@ -514,10 +624,11 @@ class ExecTool(Tool):
         return await asyncio.create_subprocess_exec(
             *args,
             stdin=stdin,
-            stdout=asyncio.subprocess.PIPE,
-            stderr=asyncio.subprocess.PIPE,
+            stdout=stdout,
+            stderr=stderr,
             cwd=cwd,
             env=env,
+            start_new_session=start_new_session,
         )
 
     @staticmethod
@@ -525,24 +636,24 @@ class ExecTool(Tool):
         if not shell:
             return None, None
         if _IS_WINDOWS:
-            return None, ToolResult.error("Error: shell parameter is not supported on Windows")
+            return None, "Error: shell parameter is not supported on Windows"
         if "\0" in shell or "\n" in shell or "\r" in shell:
-            return None, ToolResult.error("Error: shell contains invalid characters")
+            return None, "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, ToolResult.error(f"Error: unsupported shell {shell!r}. Allowed: bash, sh, zsh")
+                return None, 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, ToolResult.error(f"Error: shell is not executable: {shell}")
+                return None, f"Error: shell is not executable: {shell}"
             return str(path), None
         if "/" in shell or "\\" in shell:
-            return None, ToolResult.error("Error: shell must be a shell name or absolute path")
+            return None, "Error: shell must be a shell name or absolute path"
         if shell not in allowed:
-            return None, ToolResult.error(f"Error: unsupported shell {shell!r}. Allowed: bash, sh, zsh")
+            return None, f"Error: unsupported shell {shell!r}. Allowed: bash, sh, zsh"
         resolved = shutil.which(shell)
         if not resolved:
-            return None, ToolResult.error(f"Error: shell not found: {shell}")
+            return None, f"Error: shell not found: {shell}"
         return resolved, None
 
     @staticmethod
@@ -629,25 +740,26 @@ class ExecTool(Tool):
         if not explicitly_allowed:
             for pattern in self.deny_patterns:
                 if re.search(pattern, lower):
-                    return ToolResult.error("Error: Command blocked by deny pattern filter")
+                    return "Error: Command blocked by deny pattern filter"
 
             if self.allow_patterns:
-                return ToolResult.error("Error: Command blocked by allowlist filter (not in allowlist)")
+                return "Error: Command blocked by allowlist filter (not in allowlist)"
 
         from nanobot.security.network import contains_internal_url
+        allow_loopback = self.allow_local_service_access or current_scope_allows_loopback(
+            enabled=self.webui_allow_local_service_access,
+        )
         if contains_internal_url(
             cmd,
-            allow_loopback=current_scope_allows_loopback(
-                enabled=self.webui_allow_local_service_access,
-            ),
+            allow_loopback=allow_loopback,
         ):
             # The runner turns this marker into a non-retryable security hint.
-            return ToolResult.error("Error: Command blocked by safety guard (internal/private URL detected)")
+            return "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 ToolResult.error(
+                return (
                     "Error: Command blocked by safety guard (path traversal detected)"
                     + _WORKSPACE_BOUNDARY_NOTE
                 )
@@ -682,7 +794,7 @@ 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 ToolResult.error(
+                    return (
                         "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, ToolResult, tool_parameters
+from nanobot.agent.tools.base import Tool, 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 ToolResult.error(f"Error: unknown search provider '{provider}'")
+            return 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 ToolResult.error("Error: olostep package not installed. Run: pip install olostep")
+            return "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 ToolResult.error(f"Error: Olostep search error: {type(e).__name__}: {e}")
+            return f"Olostep search error: {type(e).__name__}: {e}"
         except Exception as e:
-            return ToolResult.error(f"Error: Olostep search error: {type(e).__name__}: {e}")
+            return f"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 ToolResult.error(
+                return (
                     "Error: Brave search rate limited after retry. "
                     "Retry later or reduce consecutive web_search calls."
                 )
-            return ToolResult.error(f"Error: {e}")
+            return f"Error: {e}"
         except Exception as e:
-            return ToolResult.error(f"Error: {e}")
+            return 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 ToolResult.error(f"Error: {e}")
+            return 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 ToolResult.error("Error: Keenable search rate limited. Try again later or reduce search frequency.")
-            return ToolResult.error(f"Error: Keenable search failed ({e.response.status_code}): {e}")
+                return "Error: Keenable search rate limited. Try again later or reduce search frequency."
+            return f"Error: Keenable search failed ({e.response.status_code}): {e}"
         except Exception as e:
-            return ToolResult.error(f"Error: Keenable search failed: {e}")
+            return 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 ToolResult.error(f"Error: invalid SearXNG URL: {error_msg}")
+            return 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 ToolResult.error(f"Error: {e}")
+            return 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 ToolResult.error(f"Error: {e}")
+            return 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 ToolResult.error("Error: Exa search rate limited. Try again later or reduce search frequency.")
-            return ToolResult.error(f"Error: Exa search failed ({e.response.status_code}): {e}")
+                return "Error: Exa search rate limited. Try again later or reduce search frequency."
+            return f"Error: Exa search failed ({e.response.status_code}): {e}"
         except Exception as e:
-            return ToolResult.error(f"Error: Exa search failed: {e}")
+            return 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 ToolResult.error(f"Error: {e}")
+            return 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 ToolResult.error("Error: Volcengine search rate limited. Try again later or reduce search frequency.")
-            return ToolResult.error(f"Error: Volcengine search failed ({e.response.status_code}): {e}")
+                return "Error: Volcengine search rate limited. Try again later or reduce search frequency."
+            return f"Error: Volcengine search failed ({e.response.status_code}): {e}"
         except Exception as e:
-            return ToolResult.error(f"Error: Volcengine search failed: {e}")
+            return 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 ToolResult.error(f"Error: Volcengine search error {code}: {message}")
-            return ToolResult.error(f"Error: Volcengine search error: {error}")
+                return f"Error: Volcengine search error {code}: {message}"
+            return 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 ToolResult.error(f"Error: DuckDuckGo search failed ({e})")
+            return 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 ToolResult.error("Error: Bocha search rate-limited (HTTP 429). Wait and retry.")
+                    return "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 ToolResult.error(f"Error: Bocha search HTTP {e.response.status_code}: {e.response.text[:200]}")
+            return f"Error: Bocha search HTTP {e.response.status_code}: {e.response.text[:200]}"
         except Exception as e:
-            return ToolResult.error(f"Error: {e}")
+            return f"Error: {e}"
 
 
 @tool_parameters(

nanobot/agent/verification_state.py

@@ -0,0 +1,292 @@
+"""Lightweight verification-result detection for coding workflows."""
+
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass
+from typing import Literal
+
+VerificationStatus = Literal["passed", "failed"]
+
+
+@dataclass(frozen=True, slots=True)
+class VerificationAnalysis:
+    """Structured summary of a command that appears to be verification."""
+
+    status: VerificationStatus
+    command: str
+    exit_code: int | None
+    failed_tests: tuple[str, ...] = ()
+    primary_errors: tuple[str, ...] = ()
+    missing_artifacts: tuple[str, ...] = ()
+    timed_out: bool = False
+
+
+@dataclass(frozen=True, slots=True)
+class VerificationObservation:
+    """Latest verification signal observed for a session."""
+
+    analysis: VerificationAnalysis
+    sequence: int
+
+
+_OBSERVATIONS: dict[str, VerificationObservation] = {}
+_SEQUENCE = 0
+
+_TEST_COMMAND_RE = re.compile(
+    r"(?ix)"
+    r"("
+    r"\bpytest\b|\bpy\.test\b|\bunittest\b|\bnosetests\b|"
+    r"\btest_outputs\.py\b|\brun_tests?(?:\.sh|\.py)?\b|"
+    r"\bnpm\s+(?:run\s+)?test\b|\byarn\s+test\b|\bpnpm\s+test\b|"
+    r"\bcargo\s+test\b|\bgo\s+test\b|\bctest\b|"
+    r"\bmake\s+(?:[^;&|]*\s+)?test\b"
+    r")"
+)
+_ARTIFACT_CHECK_COMMAND_RE = re.compile(
+    r"(?ix)"
+    r"("
+    r"\bcmp\b|"
+    r"\bdiff\b|"
+    r"\bsha(?:1|224|256|384|512)?sum\b|"
+    r"\bmd5sum\b|"
+    r"\bgcc\b.*(?:&&|;).*\./|"
+    r"\bclang\b.*(?:&&|;).*\./|"
+    r"\bpython3?\b.*<<['\"]?PY\b.*\bassert\b"
+    r")"
+)
+_COMPARISON_COMMAND_RE = re.compile(r"(?i)\b(?:cmp|diff)\b")
+_FAILURE_RE = re.compile(
+    r"(?im)"
+    r"("
+    r"^FAILED\s+|"
+    r"\b\d+\s+failed\b|"
+    r"\bAssertionError\b|"
+    r"\bFileNotFoundError\b|"
+    r"\bTimeoutError\b|"
+    r"\bcommand not found\b|"
+    r"\bError:\s+Command timed out\b|"
+    r"\bFAILURES?\b|"
+    r"\bTEST FAILED\b"
+    r")"
+)
+_SUCCESS_RE = re.compile(
+    r"(?im)"
+    r"("
+    r"\b\d+\s+passed\b|"
+    r"\bOK\b|"
+    r"\bTEST PASSED\b|"
+    r"\bExit code:\s*0\b"
+    r")"
+)
+_ARTIFACT_SUCCESS_RE = re.compile(
+    r"(?im)"
+    r"("
+    r"\b(?:cmp|diff|test|verify)_exit:\s*0\b|"
+    r"^\s*(?:cmp|diff|match|same|image|ppm|stdout|stderr|out|err)[\w.-]*:\s*0\s*$"
+    r")"
+)
+_ARTIFACT_FAILURE_RE = re.compile(
+    r"(?im)"
+    r"("
+    r"\b(?:cmp|diff|test|verify)_exit:\s*[1-9]\d*\b|"
+    r"^\s*(?:cmp|diff|match|same|image|ppm|stdout|stderr|out|err)[\w.-]*:\s*[1-9]\d*\s*$"
+    r")"
+)
+_FAILED_TEST_RE = re.compile(r"(?m)^FAILED\s+([^\s]+)")
+_PYTEST_SHORT_RE = re.compile(r"(?m)^_{3,}\s+([A-Za-z0-9_./:-]+)\s+_{3,}$")
+_ERROR_LINE_RE = re.compile(
+    r"(?m)"
+    r"^\s*(?:E\s+)?("
+    r"(?:AssertionError|FileNotFoundError|TimeoutError|ValueError|TypeError|RuntimeError)"
+    r"(?::[^\n]*)?|"
+    r"assert\s+[^\n]+|"
+    r"[^:\n]+:\s+line\s+\d+:\s+[^:\n]+:\s+command not found|"
+    r"Error:\s+[^\n]+|"
+    r"TEST FAILED[^\n]*"
+    r")"
+)
+_MISSING_PATH_RE = re.compile(
+    r"(?i)"
+    r"(?:No such file or directory:\s*['\"]([^'\"]+)['\"]|"
+    r"(?:file|path)\s+([^\s'\"]+)\s+does not exist|"
+    r"cannot open file\s+['\"]([^'\"]+)['\"])"
+)
+
+
+def analyze_verification_result(
+    *,
+    command: str,
+    output: str,
+    exit_code: int | None,
+    timed_out: bool = False,
+) -> VerificationAnalysis | None:
+    """Return a verification summary when a command/output looks like a test."""
+
+    command = " ".join((command or "").split())
+    looks_like_test_command = bool(_TEST_COMMAND_RE.search(command))
+    looks_like_artifact_check = bool(_ARTIFACT_CHECK_COMMAND_RE.search(command))
+    looks_like_comparison_command = bool(_COMPARISON_COMMAND_RE.search(command))
+    looks_like_verification = looks_like_test_command or looks_like_artifact_check
+    failure_seen = bool(_FAILURE_RE.search(output))
+    success_seen = bool(_SUCCESS_RE.search(output))
+    artifact_success_seen = bool(_ARTIFACT_SUCCESS_RE.search(output)) and (
+        looks_like_comparison_command or bool(re.search(r"\b(?:test|verify)_exit:\s*0\b", output, flags=re.I))
+    )
+    artifact_failure_seen = bool(_ARTIFACT_FAILURE_RE.search(output)) and (
+        looks_like_comparison_command or bool(re.search(r"\b(?:test|verify)_exit:\s*[1-9]\d*\b", output, flags=re.I))
+    )
+
+    if not looks_like_test_command and not failure_seen:
+        if not (looks_like_artifact_check and artifact_success_seen and exit_code == 0):
+            return None
+
+    if (
+        (timed_out and looks_like_verification)
+        or (exit_code not in (None, 0) and (looks_like_verification or failure_seen))
+        or failure_seen
+        or artifact_failure_seen
+    ):
+        return VerificationAnalysis(
+            status="failed",
+            command=command,
+            exit_code=exit_code,
+            failed_tests=_unique(_FAILED_TEST_RE.findall(output), limit=8),
+            primary_errors=_extract_primary_errors(output),
+            missing_artifacts=_extract_missing_artifacts(output),
+            timed_out=timed_out,
+        )
+
+    if looks_like_test_command and exit_code == 0 and success_seen:
+        return VerificationAnalysis(
+            status="passed",
+            command=command,
+            exit_code=exit_code,
+        )
+
+    if looks_like_artifact_check and exit_code == 0 and artifact_success_seen:
+        return VerificationAnalysis(
+            status="passed",
+            command=command,
+            exit_code=exit_code,
+        )
+
+    return None
+
+
+def append_verification_feedback(output: str, analysis: VerificationAnalysis | None) -> str:
+    """Append model-facing feedback for failed verification results."""
+
+    if analysis is None or analysis.status != "failed":
+        return output
+
+    lines = [
+        "",
+        "[Verification Feedback]",
+        "Verification status: failed.",
+        "Do not call complete_goal or present the task as finished until this is fixed and a verification passes.",
+    ]
+    if analysis.command:
+        lines.append(f"Command: {analysis.command[:240]}")
+    if analysis.exit_code is not None:
+        lines.append(f"Exit code: {analysis.exit_code}")
+    if analysis.timed_out:
+        lines.append("Failure type: command timeout")
+    if analysis.failed_tests:
+        lines.append("Failed tests:")
+        lines.extend(f"- {item}" for item in analysis.failed_tests)
+    if analysis.primary_errors:
+        lines.append("Primary errors:")
+        lines.extend(f"- {item}" for item in analysis.primary_errors)
+    if analysis.missing_artifacts:
+        lines.append("Missing artifacts:")
+        lines.extend(f"- {item}" for item in analysis.missing_artifacts)
+    lines.append("Next action: inspect the failing assertion, fix the implementation or artifact, then rerun the most specific verification command.")
+    lines.append("[/Verification Feedback]")
+    return output.rstrip() + "\n" + "\n".join(lines)
+
+
+def record_verification_observation(session_key: str | None, analysis: VerificationAnalysis | None) -> None:
+    """Remember the latest verification signal for a session."""
+
+    if not session_key or analysis is None:
+        return
+    global _SEQUENCE
+    _SEQUENCE += 1
+    _OBSERVATIONS[session_key] = VerificationObservation(
+        analysis=analysis,
+        sequence=_SEQUENCE,
+    )
+
+
+def latest_verification_observation(session_key: str | None) -> VerificationObservation | None:
+    if not session_key:
+        return None
+    return _OBSERVATIONS.get(session_key)
+
+
+def clear_verification_observation(session_key: str | None) -> None:
+    if session_key:
+        _OBSERVATIONS.pop(session_key, None)
+
+
+def format_completion_gate_message(observation: VerificationObservation) -> str:
+    """Build the complete_goal soft-gate message for unresolved failures."""
+
+    analysis = observation.analysis
+    lines = [
+        "Recent verification appears to have failed, so the goal is not marked complete yet.",
+        "Continue fixing the task and rerun verification before completing.",
+    ]
+    if analysis.command:
+        lines.append(f"Last failed verification command: {analysis.command[:240]}")
+    if analysis.failed_tests:
+        lines.append("Failed tests: " + ", ".join(analysis.failed_tests[:5]))
+    if analysis.primary_errors:
+        lines.append("Primary error: " + analysis.primary_errors[0])
+    if analysis.missing_artifacts:
+        lines.append("Missing artifact: " + analysis.missing_artifacts[0])
+    lines.append(
+        "If you are intentionally stopping with known failures, call complete_goal again with remaining_failures describing them honestly."
+    )
+    return "\n".join(lines)
+
+
+def _extract_primary_errors(output: str) -> tuple[str, ...]:
+    candidates: list[str] = []
+    for match in _ERROR_LINE_RE.findall(output):
+        text = " ".join(match.split())
+        if text and text not in candidates:
+            candidates.append(text[:240])
+        if len(candidates) >= 8:
+            break
+    if not candidates:
+        for match in _PYTEST_SHORT_RE.findall(output):
+            text = " ".join(match.split())
+            if text and text not in candidates:
+                candidates.append(text[:240])
+            if len(candidates) >= 4:
+                break
+    return tuple(candidates)
+
+
+def _extract_missing_artifacts(output: str) -> tuple[str, ...]:
+    paths: list[str] = []
+    for groups in _MISSING_PATH_RE.findall(output):
+        path = next((item for item in groups if item), "")
+        if path and path not in paths:
+            paths.append(path[:240])
+        if len(paths) >= 8:
+            break
+    return tuple(paths)
+
+
+def _unique(items: list[str], *, limit: int) -> tuple[str, ...]:
+    out: list[str] = []
+    for item in items:
+        text = " ".join(item.split())
+        if text and text not in out:
+            out.append(text[:240])
+        if len(out) >= limit:
+            break
+    return tuple(out)

nanobot/api/server.py

@@ -8,7 +8,6 @@ from __future__ import annotations
 
 import asyncio
 import contextlib
-import hmac
 import json as _json
 import time
 import uuid
@@ -393,10 +392,7 @@ async def handle_health(request: web.Request) -> web.Response:
 
 
 def create_app(
-    agent_loop,
-    model_name: str = "nanobot",
-    request_timeout: float = 120.0,
-    api_key: str = "",
+    agent_loop, model_name: str = "nanobot", request_timeout: float = 120.0
 ) -> web.Application:
     """Create the aiohttp application.
 
@@ -404,7 +400,6 @@ 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
@@ -412,22 +407,6 @@ 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

@@ -2,10 +2,7 @@
 
 from dataclasses import dataclass, field
 from datetime import datetime
-from typing import TYPE_CHECKING, Any
-
-if TYPE_CHECKING:
-    from nanobot.bus.outbound_events import OutboundEvent
+from typing import Any
 
 # Optional ``OutboundMessage.metadata`` key for structured, channel-agnostic UI
 # payloads. Value is JSON-serializable with at least ``kind``; rich clients may
@@ -42,9 +39,9 @@ class InboundMessage:
 class OutboundMessage:
     """Message to send to a chat channel.
 
-    ``event`` carries internal runtime/UI semantics. ``metadata`` is reserved
-    for channel routing context (``message_id``, thread ids, etc.) and optional
-    ``OUTBOUND_META_AGENT_UI`` blobs for rich clients.
+    ``metadata`` can carry routing (``message_id``, …), trace flags (``_progress``),
+    and optional ``OUTBOUND_META_AGENT_UI`` blobs for rich clients; non-WebUI
+    channels may ignore unknown keys.
     """
 
     channel: str
@@ -54,4 +51,3 @@ 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

@@ -1,226 +0,0 @@
-"""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

@@ -10,8 +10,7 @@ from __future__ import annotations
 from collections.abc import Awaitable, Callable
 from typing import Any
 
-from nanobot.bus.events import InboundMessage
-from nanobot.bus.outbound_events import ProgressEvent, outbound_message_for_event
+from nanobot.bus.events import InboundMessage, OutboundMessage
 from nanobot.bus.queue import MessageBus
 
 
@@ -30,19 +29,23 @@ 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(
-            outbound_message_for_event(
+            OutboundMessage(
                 channel=msg.channel,
                 chat_id=msg.chat_id,
-                event=ProgressEvent(
-                    content=content,
-                    tool_hint=tool_hint,
-                    reasoning_delta=reasoning,
-                    reasoning_end=reasoning_end,
-                    tool_events=tool_events,
-                    file_edit_events=file_edit_events,
-                ),
-                metadata=msg.metadata,
+                content=content,
+                metadata=meta,
             )
         )
 

nanobot/channels/base.py

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

nanobot/channels/discord.py

@@ -13,7 +13,6 @@ 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
@@ -459,7 +458,7 @@ class DiscordChannel(BaseChannel):
             self.logger.warning("client not ready; dropping outbound message")
             return
 
-        is_progress = isinstance(msg.event, ProgressEvent)
+        is_progress = bool((msg.metadata or {}).get("_progress"))
 
         try:
             await client.send_outbound(msg)
@@ -472,14 +471,7 @@ 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,
-        *,
-        stream_id: str | None = None,
-        stream_end: bool = False,
-        resuming: bool = False,
+        self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None
     ) -> None:
         """Progressive Discord delivery: send once, then edit until the stream ends."""
         client = self._client
@@ -487,7 +479,10 @@ class DiscordChannel(BaseChannel):
             self.logger.warning("client not ready; dropping stream delta")
             return
 
-        if stream_end:
+        meta = metadata or {}
+        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

@@ -23,7 +23,6 @@ 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
@@ -219,7 +218,7 @@ class EmailChannel(BaseChannel):
             return
 
         # Skip progress messages to prevent sending an empty email after each tool call
-        if isinstance(msg.event, ProgressEvent):
+        if (msg.metadata or {}).get("_progress"):
             self.logger.debug("Skip progress message to {}", msg.chat_id)
             return
 

nanobot/channels/feishu.py

@@ -22,7 +22,6 @@ 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
@@ -1798,19 +1797,14 @@ 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,
-        *,
-        stream_id: str | None = None,
-        stream_end: bool = False,
-        resuming: bool = False,
+        self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None
     ) -> None:
         """Progressive streaming via CardKit: create card on first delta, stream-update on subsequent.
 
         Supported metadata keys:
-            message_id:  Original message id (used with stream end for reaction cleanup).
+            _stream_end: Finalize the streaming card.
+            _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:
@@ -1821,14 +1815,14 @@ class FeishuChannel(BaseChannel):
         rid_type = "chat_id" if chat_id.startswith("oc_") else "open_id"
 
         # --- stream end: final update or fallback ---
-        if stream_end:
+        if meta.get("_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 resuming:
+            if message_id and not meta.get("_resuming"):
                 reaction_id = self._reaction_ids.pop(message_id, None)
                 if reaction_id:
                     await self._remove_reaction(message_id, reaction_id)
@@ -1971,9 +1965,7 @@ 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.
-            progress_event = msg.event if isinstance(msg.event, ProgressEvent) else None
-
-            if progress_event and progress_event.tool_hint:
+            if msg.metadata.get("_tool_hint"):
                 hint = (msg.content or "").strip()
                 if not hint:
                     return
@@ -1984,7 +1976,6 @@ 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
@@ -2018,7 +2009,7 @@ 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 progress_event is None:
+            if self.config.reply_to_message and not msg.metadata.get("_progress", False):
                 reply_message_id = _msg_id
             # For topic group messages, always reply to keep context in thread
             elif has_thread_id:

nanobot/channels/manager.py

@@ -4,7 +4,6 @@ from __future__ import annotations
 
 import asyncio
 import hashlib
-import inspect
 from collections.abc import Callable
 from contextlib import suppress
 from pathlib import Path
@@ -13,16 +12,6 @@ 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
@@ -277,7 +266,7 @@ class ChannelManager:
 
     def _should_suppress_outbound(self, msg: OutboundMessage) -> bool:
         metadata = msg.metadata or {}
-        if isinstance(outbound_event_from_message(msg), ProgressEvent):
+        if metadata.get("_progress"):
             return False
         fingerprint = self._fingerprint_content(msg.content)
         if not fingerprint:
@@ -316,59 +305,57 @@ class ChannelManager:
                         timeout=1.0
                     )
 
-                event = outbound_event_from_message(msg)
-                progress_event = event if isinstance(event, ProgressEvent) else None
-                if progress_event and (
-                    progress_event.reasoning_delta
-                    or progress_event.reasoning_end
-                    or progress_event.reasoning
+                if (
+                    msg.metadata.get("_reasoning_delta")
+                    or msg.metadata.get("_reasoning_end")
+                    or msg.metadata.get("_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.
+                    # content silently drops here. ``_reasoning`` (one-shot)
+                    # 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 progress_event:
-                    if progress_event.tool_hint and not self._should_send_progress(
+                if msg.metadata.get("_progress"):
+                    if msg.metadata.get("_tool_hint") and not self._should_send_progress(
                         msg.channel, tool_hint=True,
                     ):
                         continue
-                    if not progress_event.tool_hint and not self._should_send_progress(
+                    if not msg.metadata.get("_tool_hint") and not self._should_send_progress(
                         msg.channel, tool_hint=False,
                     ):
                         continue
 
-                if isinstance(event, RetryWaitEvent):
+                if msg.metadata.get("_retry_wait"):
                     continue
 
                 if (
-                    isinstance(event, RuntimeModelUpdatedEvent)
+                    msg.metadata.get("_runtime_model_updated")
                     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 isinstance(event, StreamDeltaEvent):
+                if msg.metadata.get("_stream_delta") and not msg.metadata.get("_stream_end"):
                     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 isinstance(
-                            event,
-                            StreamDeltaEvent | StreamEndEvent | StreamedResponseEvent,
-                        )
+                        not msg.metadata.get("_stream_delta")
+                        and not msg.metadata.get("_stream_end")
+                        and not msg.metadata.get("_streamed")
                     ):
                         if self._should_suppress_outbound(msg):
                             logger.info("Suppressing duplicate outbound message to {}:{}", msg.channel, msg.chat_id)
@@ -382,116 +369,34 @@ 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."""
-        event = outbound_event_from_message(msg)
-        if isinstance(event, ProgressEvent) and event.reasoning_end:
-            await ChannelManager._send_reasoning_end(channel, msg, event)
-        elif isinstance(event, ProgressEvent) and event.reasoning_delta:
-            await ChannelManager._send_reasoning_delta(channel, msg, event)
-        elif isinstance(event, ProgressEvent) and event.reasoning:
-            # BaseChannel translates one-shot reasoning to a single delta +
-            # end pair so plugins only implement the streaming primitives.
+        if msg.metadata.get("_reasoning_end"):
+            await channel.send_reasoning_end(msg.chat_id, msg.metadata)
+        elif msg.metadata.get("_reasoning_delta"):
+            await channel.send_reasoning_delta(msg.chat_id, msg.content, msg.metadata)
+        elif msg.metadata.get("_reasoning"):
+            # Back-compat: one-shot reasoning. BaseChannel translates this
+            # to a single delta + end pair so plugins only implement the
+            # streaming primitives.
             await channel.send_reasoning(msg)
-        elif isinstance(event, ProgressEvent) and event.file_edit_events:
+        elif msg.metadata.get("_file_edit_events"):
+            edits = msg.metadata.get("_file_edit_events")
             await channel.send_file_edit_events(
                 msg.chat_id,
-                event.file_edit_events,
+                edits if isinstance(edits, list) else [],
                 msg.metadata,
             )
-        elif isinstance(event, StreamDeltaEvent):
-            await ChannelManager._send_stream_event(channel, msg, event)
-        elif isinstance(event, StreamEndEvent):
-            await ChannelManager._send_stream_event(channel, msg, event)
-        elif not isinstance(event, StreamedResponseEvent):
+        elif msg.metadata.get("_stream_delta") or msg.metadata.get("_stream_end"):
+            await channel.send_delta(msg.chat_id, msg.content, msg.metadata)
+        elif not msg.metadata.get("_streamed"):
             await channel.send(msg)
 
     def _coalesce_stream_deltas(
         self, first_msg: OutboundMessage
     ) -> tuple[OutboundMessage, list[OutboundMessage]]:
-        """Merge consecutive stream deltas for the same (channel, chat_id, stream_id).
+        """Merge consecutive _stream_delta messages 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.
@@ -499,15 +404,10 @@ class ChannelManager:
         Returns:
             tuple of (merged_message, list_of_non_matching_messages)
         """
-        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)
+        first_metadata = first_msg.metadata or {}
+        target_key = (first_msg.channel, first_msg.chat_id, first_metadata.get("_stream_id"))
         combined_content = first_msg.content
-        final_event: StreamDeltaEvent | StreamEndEvent = (
-            first_event
-            if isinstance(first_event, StreamDeltaEvent)
-            else StreamDeltaEvent(stream_id=first_stream_id)
-        )
+        final_metadata = dict(first_msg.metadata or {})
         non_matching: list[OutboundMessage] = []
 
         # Only merge consecutive deltas. As soon as we hit any other message,
@@ -519,29 +419,21 @@ class ChannelManager:
                 break
 
             # Check if this message belongs to the same stream
-            next_event = outbound_event_from_message(next_msg)
-            next_stream_id = (
-                next_event.stream_id
-                if isinstance(next_event, StreamDeltaEvent | StreamEndEvent)
-                else None
-            )
+            next_metadata = next_msg.metadata or {}
             same_target = (
                 next_msg.channel,
                 next_msg.chat_id,
-                next_stream_id,
+                next_metadata.get("_stream_id"),
             ) == target_key
-            is_delta = isinstance(next_event, StreamDeltaEvent)
-            is_end = isinstance(next_event, StreamEndEvent)
+            is_delta = next_metadata.get("_stream_delta")
+            is_end = next_metadata.get("_stream_end")
 
-            if same_target and (is_delta or (is_end and next_msg.content)):
+            if same_target and is_delta and not final_metadata.get("_stream_end"):
                 # Accumulate content
                 combined_content += next_msg.content
-                # If we see stream_end, remember it and stop coalescing this stream
-                if isinstance(next_event, StreamEndEvent):
-                    final_event = StreamEndEvent(
-                        stream_id=next_stream_id,
-                        resuming=next_event.resuming,
-                    )
+                # If we see _stream_end, remember it and stop coalescing this stream
+                if is_end:
+                    final_metadata["_stream_end"] = True
                     # Stream ended - stop coalescing this stream
                     break
             else:
@@ -549,7 +441,12 @@ class ChannelManager:
                 non_matching.append(next_msg)
                 break
 
-        merged = replace_outbound_event(first_msg, final_event, content=combined_content)
+        merged = OutboundMessage(
+            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

@@ -49,7 +49,6 @@ 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
@@ -505,7 +504,7 @@ 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 = isinstance(msg.event, ProgressEvent)
+        is_progress = bool((msg.metadata or {}).get("_progress"))
         try:
             failures: list[str] = []
             if candidates:
@@ -529,19 +528,11 @@ 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,
-        *,
-        stream_id: str | None = None,
-        stream_end: bool = False,
-        resuming: bool = False,
-    ) -> None:
+    async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> None:
+        meta = metadata or {}
         relates_to = self._build_thread_relates_to(metadata)
 
-        if stream_end:
+        if meta.get("_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

@@ -18,7 +18,6 @@ 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
@@ -540,7 +539,7 @@ class SignalChannel(BaseChannel):
 
     async def send(self, msg: OutboundMessage) -> None:
         """Send a message through Signal."""
-        is_progress_message = isinstance(msg.event, ProgressEvent)
+        is_progress_message = bool(msg.metadata.get("_progress"))
         try:
             plain_text, text_styles = _markdown_to_signal(msg.content)
             if not plain_text and not msg.media:

nanobot/channels/slack.py

@@ -14,7 +14,6 @@ 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
@@ -165,7 +164,7 @@ 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 = isinstance(msg.event, ProgressEvent)
+            is_progress = (msg.metadata or {}).get("_progress", False)
             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 []):
@@ -191,7 +190,7 @@ 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 is_progress:
+            if not (msg.metadata or {}).get("_progress"):
                 event = slack_meta.get("event", {})
                 await self._update_react_emoji(origin_chat_id, event.get("ts"))
 

nanobot/channels/telegram.py

@@ -26,7 +26,6 @@ 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
@@ -37,7 +36,7 @@ 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).  On stream end, we split
+# safety margin for mid-stream edits (plain text).  For _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
@@ -707,10 +706,8 @@ 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 progress_event is None:
+        if not msg.metadata.get("_progress", False):
             self._stop_typing(msg.chat_id)
             if reply_to_message_id := msg.metadata.get("message_id"):
                 with suppress(ValueError):
@@ -795,7 +792,7 @@ class TelegramChannel(BaseChannel):
 
         # Send text content
         if msg.content and msg.content != "[empty message]":
-            render_as_blockquote = bool(progress_event and progress_event.tool_hint)
+            render_as_blockquote = bool(msg.metadata.get("_tool_hint"))
             buttons = getattr(msg, "buttons", None) or []
             reply_markup = self._build_keyboard(buttons) if buttons else None
             text = msg.content
@@ -890,23 +887,15 @@ 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,
-        *,
-        stream_id: str | None = None,
-        stream_end: bool = False,
-        resuming: bool = False,
-    ) -> None:
+    async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> 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 stream_end:
+        if meta.get("_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

@@ -19,16 +19,6 @@ 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
@@ -158,13 +148,16 @@ 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(
-        outbound_message_for_event(
-            channel="websocket",
-            chat_id="*",
-            event=RuntimeModelUpdatedEvent(model=model, model_preset=model_preset),
-        )
-    )
+    bus.outbound.put_nowait(OutboundMessage(
+        channel="websocket",
+        chat_id="*",
+        content="",
+        metadata={
+            "_runtime_model_updated": True,
+            "model": model,
+            "model_preset": model_preset,
+        },
+    ))
 
 
 def _parse_inbound_payload(raw: str) -> str | None:
@@ -858,63 +851,70 @@ class WebSocketChannel(BaseChannel):
             raise
 
     async def send(self, msg: OutboundMessage) -> None:
-        event = outbound_event_from_message(msg)
-        progress_event = event if isinstance(event, ProgressEvent) else None
-        if isinstance(event, RuntimeModelUpdatedEvent):
+        if msg.metadata.get("_runtime_model_updated"):
             await self.send_runtime_model_updated(
-                model_name=event.model,
-                model_preset=event.model_preset,
+                model_name=msg.metadata.get("model"),
+                model_preset=msg.metadata.get("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 isinstance(
-                event,
-                ProgressEvent
-                | TurnEndEvent
-                | SessionUpdatedEvent
-                | GoalStatusEvent
-                | GoalStateSyncEvent,
+            if (
+                msg.metadata.get("_progress")
+                or msg.metadata.get("_file_edit_events")
+                or msg.metadata.get("_turn_end")
+                or msg.metadata.get("_session_updated")
+                or msg.metadata.get("_goal_status")
+                or msg.metadata.get("_goal_state_sync")
             ):
                 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 isinstance(event, GoalStateSyncEvent):
+        if msg.metadata.get("_goal_state_sync"):
             if conns:
-                await self.send_goal_state(msg.chat_id, event.goal_state or {"active": False})
+                blob = msg.metadata.get("goal_state")
+                await self.send_goal_state(msg.chat_id, blob if isinstance(blob, dict) else {"active": False})
             return
-        if isinstance(event, GoalStatusEvent):
+        if msg.metadata.get("_goal_status"):
             if conns:
-                if event.status in ("running", "idle"):
+                status = msg.metadata.get("goal_status")
+                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,
-                        event.status,
-                        started_at=event.started_at,
+                        status,
+                        started_at=float(started_raw) if isinstance(started_raw, int | float) else None,
                     )
             return
         # Signal that the agent has fully finished processing the current turn.
-        if isinstance(event, TurnEndEvent):
+        if msg.metadata.get("_turn_end"):
+            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=event.latency_ms,
-                goal_state=event.goal_state,
+                latency_ms=lat_i,
+                goal_state=gs_blob,
                 metadata=msg.metadata,
             )
             await self.send_session_updated(msg.chat_id, scope="thread")
             return
-        if isinstance(event, SessionUpdatedEvent):
+        if msg.metadata.get("_session_updated"):
             if conns:
+                scope = msg.metadata.get("_session_update_scope")
                 await self.send_session_updated(
                     msg.chat_id,
-                    scope=event.scope,
+                    scope=scope if isinstance(scope, str) else None,
                 )
             return
-        if progress_event and progress_event.file_edit_events:
+        if msg.metadata.get("_file_edit_events"):
+            edits = msg.metadata.get("_file_edit_events")
             await self.send_file_edit_events(
                 msg.chat_id,
-                progress_event.file_edit_events,
+                edits if isinstance(edits, list) else [],
                 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 progress_event and progress_event.tool_events:
-            payload["tool_events"] = progress_event.tool_events
+        if msg.metadata.get("_tool_events"):
+            payload["tool_events"] = msg.metadata["_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 progress_event and progress_event.tool_hint:
+        if msg.metadata.get("_tool_hint"):
             payload["kind"] = "tool_hint"
-        elif progress_event:
+        elif msg.metadata.get("_progress"):
             payload["kind"] = "progress"
         phase = "activity" if payload.get("kind") in ("tool_hint", "progress") else "answer"
         self._transcripts.prepare_and_append(
@@ -971,8 +971,6 @@ 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 —
@@ -988,6 +986,7 @@ 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(
@@ -1006,8 +1005,6 @@ 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, ()))
@@ -1016,6 +1013,7 @@ 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(
@@ -1059,15 +1057,11 @@ 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(stream_id or ""))
-        if stream_end:
+        stream_key = (chat_id, str(meta.get("_stream_id") or ""))
+        if meta.get("_stream_end"):
             body: dict[str, Any] = {"event": "stream_end", "chat_id": chat_id}
             buffered = self._stream_text_buffers.pop(stream_key, [])
             if delta:
@@ -1083,8 +1077,8 @@ class WebSocketChannel(BaseChannel):
                 "text": delta,
             }
             self._stream_text_buffers.setdefault(stream_key, []).append(delta)
-        if stream_id is not None:
-            body["stream_id"] = stream_id
+        if meta.get("_stream_id") is not None:
+            body["stream_id"] = meta["_stream_id"]
         self._transcripts.prepare_and_append(
             chat_id,
             body,

nanobot/channels/wecom.py

@@ -13,7 +13,6 @@ 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
@@ -498,7 +497,7 @@ class WecomChannel(BaseChannel):
 
         try:
             content = (msg.content or "").strip()
-            is_progress = isinstance(msg.event, ProgressEvent)
+            is_progress = bool(msg.metadata.get("_progress"))
 
             # Get the stored frame for this chat
             frame = self._chat_frames.get(msg.chat_id)

nanobot/channels/weixin.py

@@ -29,7 +29,6 @@ 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
@@ -130,13 +129,6 @@ 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):
@@ -175,10 +167,6 @@ 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
@@ -1102,13 +1090,11 @@ class WeixinChannel(BaseChannel):
             raise RuntimeError("WeChat client not initialized or not authenticated")
         self._assert_session_active()
 
-        event = getattr(msg, "event", None)
-        progress_event = event if isinstance(event, ProgressEvent) else None
-        is_progress = progress_event is not None
+        is_progress = bool((msg.metadata or {}).get("_progress", False))
 
         # Buffer tool hints to coalesce consecutive ones and avoid burning
         # WeChat iLink rate-limit quota (~7 msgs / 5 min).
-        if progress_event and progress_event.tool_hint:
+        if is_progress and (msg.metadata or {}).get("_tool_hint"):
             if not self.send_tool_hints:
                 return
             self._pending_tool_hints.setdefault(msg.chat_id, []).append(msg.content)
@@ -1121,7 +1107,7 @@ 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 progress_event and (progress_event.reasoning_delta or progress_event.reasoning):
+        if is_progress and (msg.metadata or {}).get("_reasoning_delta"):
             self.logger.debug(
                 "Dropped invisible reasoning delta for {}", msg.chat_id
             )
@@ -1235,46 +1221,16 @@ 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,
-        *,
-        stream_id: str | None = None,
-        stream_end: bool = False,
-        resuming: bool = False,
+        self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None
     ) -> None:
-        """Deliver a streamed reply to WeChat.
+        """Weixin iLink does not support native streaming deltas.
 
-        WeChat iLink has no native incremental delivery, and the manager
-        bypasses :meth:`send` for the ``_streamed`` final answer. So we
-        accumulate content deltas and flush the full reply as a single message
-        at stream end. Reasoning deltas are invisible in WeChat and are dropped.
+        We only hook ``_stream_end`` so buffered tool hints are flushed even
+        when the final answer carries the ``_streamed`` flag and bypasses
+        :meth:`send`.
         """
-        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)
+        if metadata and metadata.get("_stream_end"):
+            await self._flush_tool_hints(chat_id)
 
     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

@@ -499,30 +499,6 @@ 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")
@@ -556,9 +532,6 @@ 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

@@ -50,14 +50,6 @@ 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
@@ -469,25 +461,25 @@ async def _maybe_print_interactive_progress(
     renderer: StreamRenderer | None = None,
     reasoning_buffer: _ReasoningBuffer | None = None,
 ) -> bool:
-    event = outbound_event_from_message(msg)
-    if isinstance(event, RetryWaitEvent):
+    metadata = msg.metadata or {}
+    if metadata.get("_retry_wait"):
         await _print_interactive_progress_line(msg.content, thinking, renderer)
         return True
 
-    if not isinstance(event, ProgressEvent):
+    if not metadata.get("_progress"):
         return False
 
     reasoning_buffer = reasoning_buffer or _ReasoningBuffer()
 
-    if event.reasoning_end:
+    if metadata.get("_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 = event.tool_hint
-    is_reasoning = event.reasoning or event.reasoning_delta
+    is_tool_hint = metadata.get("_tool_hint", False)
+    is_reasoning = metadata.get("_reasoning", False) or metadata.get("_reasoning_delta", False)
     if is_reasoning:
         if channels_config and not channels_config.show_reasoning:
             reasoning_buffer.clear()
@@ -806,24 +798,14 @@ 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(
-                "[red]Error: host is 0.0.0.0 (all interfaces) but api_key is not set. "
-                "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]"
+            "[yellow]Warning:[/yellow] API is bound to all interfaces. "
+            "Only do this behind a trusted network boundary, firewall, or reverse proxy."
         )
     console.print()
 
-    api_app = create_app(
-        agent_loop, model_name=model_name, request_timeout=timeout,
-        api_key=api_key,
-    )
+    api_app = create_app(agent_loop, model_name=model_name, request_timeout=timeout)
 
     async def on_startup(_app):
         await agent_loop._connect_mcp()
@@ -1464,7 +1446,7 @@ def agent(
             bus_task = asyncio.create_task(agent_loop.run())
             turn_done = asyncio.Event()
             turn_done.set()
-            turn_response: list[Any] = []
+            turn_response: list[tuple[str, dict]] = []
             renderer: StreamRenderer | None = None
             reasoning_buffer = _ReasoningBuffer()
 
@@ -1472,19 +1454,18 @@ def agent(
                 while True:
                     try:
                         msg = await asyncio.wait_for(bus.consume_outbound(), timeout=1.0)
-                        event = outbound_event_from_message(msg)
 
-                        if isinstance(event, StreamDeltaEvent):
+                        if msg.metadata.get("_stream_delta"):
                             if renderer:
                                 await renderer.on_delta(msg.content)
                             continue
-                        if isinstance(event, StreamEndEvent):
+                        if msg.metadata.get("_stream_end"):
                             if renderer:
                                 await renderer.on_end(
-                                    resuming=event.resuming,
+                                    resuming=msg.metadata.get("_resuming", False),
                                 )
                             continue
-                        if isinstance(event, StreamedResponseEvent):
+                        if msg.metadata.get("_streamed"):
                             turn_done.set()
                             continue
 
@@ -1499,7 +1480,7 @@ def agent(
 
                         if not turn_done.is_set():
                             if msg.content:
-                                turn_response.append(msg)
+                                turn_response.append((msg.content, dict(msg.metadata or {})))
                             turn_done.set()
                         elif msg.content:
                             await _print_interactive_response(
@@ -1552,10 +1533,8 @@ def agent(
                         await turn_done.wait()
 
                         if turn_response:
-                            response_msg = turn_response[0]
-                            content = response_msg.content
-                            meta = response_msg.metadata
-                            if content and not isinstance(response_msg.event, StreamedResponseEvent):
+                            content, meta = turn_response[0]
+                            if content and not meta.get("_streamed"):
                                 if renderer:
                                     await renderer.close()
                                 print_kwargs: dict[str, Any] = {}
@@ -1765,11 +1744,6 @@ _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."""
@@ -1801,51 +1775,9 @@ 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)
@@ -1857,8 +1789,6 @@ 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")
@@ -1882,23 +1812,14 @@ 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(proxy=proxy)
+            token = get_token()
         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

@@ -4,7 +4,6 @@ from __future__ import annotations
 
 import asyncio
 import os
-import subprocess
 import sys
 import time
 from contextlib import suppress
@@ -51,7 +50,7 @@ BUILTIN_COMMAND_SPECS: tuple[BuiltinCommandSpec, ...] = (
     BuiltinCommandSpec(
         "/restart",
         "Restart nanobot",
-        "Restart the bot process.",
+        "Restart the bot process in place.",
         "rotate-cw",
     ),
     BuiltinCommandSpec(
@@ -131,15 +130,6 @@ 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,
@@ -148,7 +138,7 @@ async def cmd_stop(ctx: CommandContext) -> OutboundMessage:
 
 
 async def cmd_restart(ctx: CommandContext) -> OutboundMessage:
-    """Restart the process."""
+    """Restart the process in-place via os.execv."""
     msg = ctx.msg
     set_restart_notice_to_env(
         channel=msg.channel,
@@ -158,19 +148,7 @@ async def cmd_restart(ctx: CommandContext) -> OutboundMessage:
 
     async def _do_restart():
         await asyncio.sleep(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)
+        os.execv(sys.executable, [sys.executable, "-m", "nanobot"] + sys.argv[1:])
 
     asyncio.create_task(_do_restart())
     return OutboundMessage(
@@ -648,7 +626,7 @@ async def cmd_history(ctx: CommandContext) -> OutboundMessage:
 
 _GOAL_PROMPT_TEMPLATE = """The user declared a sustained objective for this thread.
 
-Inspect or clarify if needed, then call `long_task` with the refined objective (and optional short ui_summary). Work proceeds as normal assistant turns using your usual tools. When the objective is fully done and verified, call `complete_goal` with a brief recap. If the user later cancels or changes direction, still call `complete_goal` with an honest recap (then `long_task` again only after there is no active goal). Do not use `long_task` / `complete_goal` for trivial one-shot answers.
+Inspect or clarify if needed, then call `long_task` with the refined objective (and optional short ui_summary). Work proceeds as normal assistant turns using your usual tools. When the objective is fully done and verified, call `complete_goal` with a brief recap plus verification_summary / commands_run / artifacts_created when applicable. If the user later cancels or changes direction, still call `complete_goal` with an honest recap (then `long_task` again only after there is no active goal). Do not use `long_task` / `complete_goal` for trivial one-shot answers.
 
 Goal:
 {goal}

nanobot/config/loader.py

@@ -7,7 +7,6 @@ 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
@@ -80,10 +79,6 @@ 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)
@@ -157,23 +152,6 @@ 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

@@ -154,6 +154,10 @@ 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,
@@ -179,7 +183,6 @@ 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
@@ -307,18 +310,6 @@ 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):
@@ -326,7 +317,6 @@ 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

@@ -1,7 +1,6 @@
 """Cron service for scheduling agent tasks."""
 
 import asyncio
-import errno
 import json
 import os
 import time
@@ -358,25 +357,6 @@ 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:
@@ -457,15 +437,11 @@ 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;
-            # some shared filesystems reject directory fsync with EINVAL.
+            # NTFS journals metadata synchronously so this is a no-op there.
             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
+                    os.fsync(fd)
                 finally:
                     os.close(fd)
         except BaseException:
@@ -646,7 +622,7 @@ class CronService:
 
     def list_jobs(self, include_disabled: bool = False) -> list[CronJob]:
         """List all jobs."""
-        store = self._require_store()
+        store = self._load_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'))
 
@@ -708,7 +684,7 @@ class CronService:
         _normalize_agent_turn_job(job)
         self._enforce_agent_binding(job)
         if self._running:
-            store = self._require_store()
+            store = self._load_store()
             store.jobs.append(job)
             self._save_store()
             self._arm_timer()
@@ -720,7 +696,7 @@ class CronService:
 
     def register_system_job(self, job: CronJob) -> CronJob:
         """Register an internal system job (idempotent on restart)."""
-        store = self._require_store()
+        store = self._load_store()
         now = _now_ms()
         job.state = CronJobState(next_run_at_ms=_compute_next_run(job.schedule, now))
         job.created_at_ms = now
@@ -734,7 +710,7 @@ 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._require_store()
+        store = self._load_store()
         job = next((j for j in store.jobs if j.id == job_id), None)
         if job is None:
             return "not_found"
@@ -759,7 +735,7 @@ class CronService:
 
     def enable_job(self, job_id: str, enabled: bool = True) -> CronJob | None:
         """Enable or disable a job."""
-        store = self._require_store()
+        store = self._load_store()
         for job in store.jobs:
             if job.id == job_id:
                 job.enabled = enabled
@@ -794,7 +770,7 @@ class CronService:
         For ``channel`` and ``to``, pass an explicit value (including ``None``)
         to update; omit (sentinel ``...``) to leave unchanged.
         """
-        store = self._require_store()
+        store = self._load_store()
         job = next((j for j in store.jobs if j.id == job_id), None)
         if job is None:
             return "not_found"
@@ -839,7 +815,7 @@ class CronService:
         was_running = self._running
         self._running = True
         try:
-            store = self._require_store()
+            store = self._load_store()
             for job in store.jobs:
                 if job.id == job_id:
                     if self._is_unbound_agent_job(job):
@@ -859,12 +835,12 @@ class CronService:
 
     def get_job(self, job_id: str) -> CronJob | None:
         """Get a job by ID."""
-        store = self._require_store()
+        store = self._load_store()
         return next((j for j in store.jobs if j.id == job_id), None)
 
     def status(self) -> dict:
         """Get service status."""
-        store = self._require_store()
+        store = self._load_store()
         return {
             "enabled": self._running,
             "jobs": len(store.jobs),

nanobot/providers/base.py

@@ -54,18 +54,6 @@ 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

@@ -58,11 +58,6 @@ 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:
@@ -84,10 +79,7 @@ def _make_provider_core(
     if backend == "openai_codex":
         from nanobot.providers.openai_codex_provider import OpenAICodexProvider
 
-        provider = OpenAICodexProvider(
-            default_model=model,
-            proxy=getattr(p, "proxy", None) if p else None,
-        )
+        provider = OpenAICodexProvider(default_model=model)
     elif backend == "azure_openai":
         from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
 
@@ -132,7 +124,6 @@ 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()
@@ -227,7 +218,6 @@ 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)
@@ -247,7 +237,6 @@ 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

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import os
 import time
 import webbrowser
 from collections.abc import Awaitable, Callable
@@ -30,12 +29,6 @@ _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,
@@ -75,16 +68,11 @@ 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(
-            device_code_url,
+            DEFAULT_GITHUB_DEVICE_CODE_URL,
             headers={"Accept": "application/json", "User-Agent": USER_AGENT},
-            data={"client_id": client_id, "scope": GITHUB_COPILOT_SCOPE},
+            data={"client_id": GITHUB_COPILOT_CLIENT_ID, "scope": GITHUB_COPILOT_SCOPE},
         )
         response.raise_for_status()
         payload = response.json()
@@ -108,10 +96,10 @@ def login_github_copilot(
         token_expires_in = _LONG_LIVED_TOKEN_SECONDS
         while time.time() < deadline:
             poll = client.post(
-                access_token_url,
+                DEFAULT_GITHUB_ACCESS_TOKEN_URL,
                 headers={"Accept": "application/json", "User-Agent": USER_AGENT},
                 data={
-                    "client_id": client_id,
+                    "client_id": GITHUB_COPILOT_CLIENT_ID,
                     "device_code": device_code,
                     "grant_type": "urn:ietf:params:oauth:grant-type:device_code",
                 },
@@ -144,7 +132,7 @@ def login_github_copilot(
             raise RuntimeError("GitHub device flow timed out.")
 
         user = client.get(
-            user_url,
+            DEFAULT_GITHUB_USER_URL,
             headers={
                 "Authorization": f"Bearer {access_token}",
                 "Accept": "application/vnd.github+json",
@@ -176,7 +164,7 @@ class GitHubCopilotProvider(OpenAICompatProvider):
         self._copilot_expires_at: float = 0.0
         super().__init__(
             api_key="no-key",
-            api_base=_resolve("NANOBOT_COPILOT_BASE_URL", DEFAULT_COPILOT_BASE_URL),
+            api_base=DEFAULT_COPILOT_BASE_URL,
             default_model=default_model,
             extra_headers={
                 "Editor-Version": EDITOR_VERSION,
@@ -198,7 +186,7 @@ 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(
-                _resolve("NANOBOT_COPILOT_TOKEN_URL", DEFAULT_COPILOT_TOKEN_URL),
+                DEFAULT_COPILOT_TOKEN_URL,
                 headers=_copilot_headers(github_token.access),
             )
             response.raise_for_status()

nanobot/providers/openai_codex_provider.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import ast
 import asyncio
 import hashlib
 import json
@@ -26,6 +27,25 @@ from nanobot.providers.openai_responses import (
 
 DEFAULT_CODEX_URL = "https://chatgpt.com/backend-api/codex/responses"
 DEFAULT_ORIGINATOR = "nanobot"
+_RESPONSE_FAILED_PREFIX = "Response failed:"
+_RETRYABLE_RESPONSE_FAILED_TOKENS = frozenset({
+    "overloaded",
+    "overloaded_error",
+    "rate_limit_exceeded",
+    "request_limit_exceeded",
+    "requests_limit_exceeded",
+    "server_error",
+    "server_is_overloaded",
+    "service_unavailable",
+    "temporarily_unavailable",
+    "too_many_requests",
+})
+_NON_RETRYABLE_RESPONSE_FAILED_TOKENS = frozenset({
+    "content_filter",
+    "content_policy_violation",
+    "cyber_policy",
+    "safety_violation",
+})
 
 
 class OpenAICodexProvider(LLMProvider):
@@ -33,14 +53,9 @@ class OpenAICodexProvider(LLMProvider):
 
     supports_progress_deltas = True
 
-    def __init__(
-        self,
-        default_model: str = "openai-codex/gpt-5.1-codex",
-        proxy: str | None = None,
-    ):
+    def __init__(self, default_model: str = "openai-codex/gpt-5.1-codex"):
         super().__init__(api_key=None, api_base=None)
         self.default_model = default_model
-        self.proxy = proxy or None
 
     async def _call_codex(
         self,
@@ -57,6 +72,9 @@ 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,
@@ -76,13 +94,9 @@ 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,
@@ -93,7 +107,6 @@ 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,
@@ -206,17 +219,12 @@ 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()
-    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 httpx.AsyncClient(timeout=idle_timeout_s, verify=verify) as client:
         async with client.stream("POST", url, headers=headers, json=body) as response:
             if response.status_code != 200:
                 text = await response.aread()
@@ -258,6 +266,8 @@ def _codex_error_response(exc: Exception) -> LLMResponse:
 
     status_code = getattr(exc, "status_code", None)
     error_kind: str | None = None
+    error_type = getattr(exc, "error_type", None)
+    error_code = getattr(exc, "error_code", None)
     default_detail: str | None = None
     should_retry: bool | None = getattr(exc, "should_retry", None)
 
@@ -277,12 +287,20 @@ def _codex_error_response(exc: Exception) -> LLMResponse:
         error_kind = "http"
         default_detail = "HTTP request failed"
 
+    failed_type, failed_code = _extract_response_failed_error(detail)
+    if failed_type or failed_code:
+        error_kind = error_kind or "provider"
+        error_type = failed_type or error_type
+        error_code = failed_code or error_code
+        if should_retry is None:
+            should_retry = _should_retry_response_failed(error_type, error_code, detail)
+
     if status_code is not None and should_retry is None:
         retry_content = None if int(status_code) == 429 and isinstance(exc, _CodexHTTPError) else detail
         should_retry = _should_retry_status(
             int(status_code),
-            getattr(exc, "error_type", None),
-            getattr(exc, "error_code", None),
+            error_type,
+            error_code,
             retry_content,
         )
 
@@ -295,13 +313,56 @@ def _codex_error_response(exc: Exception) -> LLMResponse:
         retry_after=retry_after,
         error_status_code=int(status_code) if status_code is not None else None,
         error_kind=error_kind,
-        error_type=getattr(exc, "error_type", None),
-        error_code=getattr(exc, "error_code", None),
+        error_type=error_type,
+        error_code=error_code,
         error_retry_after_s=retry_after,
         error_should_retry=should_retry,
     )
 
 
+def _extract_response_failed_error(detail: str) -> tuple[str | None, str | None]:
+    """Extract provider semantic error fields from Responses SSE failures."""
+    if _RESPONSE_FAILED_PREFIX not in detail:
+        return None, None
+
+    payload = detail.split(_RESPONSE_FAILED_PREFIX, 1)[1].strip()
+    if not payload:
+        return None, None
+
+    parsed: Any = None
+    try:
+        parsed = json.loads(payload)
+    except Exception:
+        try:
+            parsed = ast.literal_eval(payload)
+        except Exception:
+            parsed = None
+
+    error_type, error_code = LLMProvider._extract_error_type_code(parsed or payload)
+    return error_type, error_code
+
+
+def _should_retry_response_failed(
+    error_type: str | None,
+    error_code: str | None,
+    detail: str,
+) -> bool | None:
+    semantic_tokens = {
+        token for token in (
+            LLMProvider._normalize_error_token(error_type),
+            LLMProvider._normalize_error_token(error_code),
+        )
+        if token is not None
+    }
+    if any(token in _NON_RETRYABLE_RESPONSE_FAILED_TOKENS for token in semantic_tokens):
+        return False
+    if any(token in _RETRYABLE_RESPONSE_FAILED_TOKENS for token in semantic_tokens):
+        return True
+    if LLMProvider._is_transient_error(detail):
+        return True
+    return None
+
+
 def _codex_log_summary(exc_type: str, response: LLMResponse) -> str:
     """Return a bounded diagnostic summary without request body or raw upstream payload."""
     if response.error_status_code is not None:

nanobot/providers/openai_compat_provider.py

@@ -358,7 +358,6 @@ 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
@@ -367,7 +366,6 @@ 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)
@@ -398,14 +396,7 @@ class OpenAICompatProvider(LLMProvider):
 
         timeout_s = _openai_compat_timeout_s()
         http_client: httpx.AsyncClient | None = None
-        if self._proxy:
-            http_client = httpx.AsyncClient(
-                timeout=timeout_s,
-                proxy=self._proxy,
-                trust_env=False,
-                follow_redirects=True,
-            )
-        elif self._is_local:
+        if 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

nanobot/providers/registry.py

@@ -32,7 +32,6 @@ 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"
@@ -222,7 +221,6 @@ 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

@@ -27,8 +27,6 @@ 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*$')
@@ -45,15 +43,6 @@ _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.
 
@@ -110,12 +99,6 @@ 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."""
@@ -149,7 +132,7 @@ class Session:
 
     def get_history(
         self,
-        max_messages: int = FILE_MAX_MESSAGES,
+        max_messages: int = 120,
         *,
         max_tokens: int = 0,
         extend_to_user: bool = False,
@@ -160,7 +143,7 @@ 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 FILE_MAX_MESSAGES
+        max_messages = max_messages if max_messages > 0 else 120
         start_idx = recent_message_start_index(
             unconsolidated,
             max_messages,
@@ -295,26 +278,22 @@ class Session:
         max_messages: int,
         *,
         extend_to_user: bool = False,
-    ) -> RetentionResult:
+    ) -> tuple[list[dict], int]:
         """Keep a legal recent suffix, optionally extending it back to a user turn.
 
-        Returns a RetentionResult with dropped messages and how many of those
-        were in the already-consolidated prefix. This method mutates
-        self.messages and self.last_consolidated in place.
+        Returns ``(dropped, already_consolidated_count)`` where *dropped* is
+        the list of removed messages (in original order) and
+        *already_consolidated_count* is how many of those were inside the
+        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 RetentionResult(
-                dropped=dropped,
-                already_consolidated_count=min(lc, len(dropped)),
-            )
+            return dropped, min(lc, len(dropped))
         if len(self.messages) <= max_messages:
-            return RetentionResult(
-                dropped=[],
-                already_consolidated_count=0,
-            )
+            return [], 0
 
         original = list(self.messages)
         before_lc = self.last_consolidated
@@ -380,10 +359,7 @@ class Session:
         self.messages = retained
         self.last_consolidated = new_lc
         self.updated_at = datetime.now()
-        return RetentionResult(
-            dropped=dropped,
-            already_consolidated_count=already_consolidated,
-        )
+        return dropped, already_consolidated
 
     def enforce_file_cap(
         self,
@@ -394,17 +370,17 @@ class Session:
         if limit <= 0 or len(self.messages) <= limit:
             return
 
-        result = self.retain_recent_legal_suffix(limit)
-        if not result.dropped:
+        dropped, already_consolidated = self.retain_recent_legal_suffix(limit)
+        if not dropped:
             return
 
-        archive_chunk = result.dropped[result.already_consolidated_count:]
+        archive_chunk = dropped[already_consolidated:]
         if archive_chunk and on_archive:
             on_archive(archive_chunk)
         logger.info(
             "Session file cap hit for {}: dropped {}, raw-archived {}, kept {}",
             self.key,
-            len(result.dropped),
+            len(dropped),
             len(archive_chunk),
             len(self.messages),
         )
@@ -563,10 +539,9 @@ class SessionManager:
                 logger.info("Recovered session {} from corrupt file ({} messages)", key, len(repaired.messages))
             return repaired
 
-    def _repair(self, key: str, *, path: Path | None = None) -> Session | None:
+    def _repair(self, key: str) -> Session | None:
         """Attempt to recover a session from a corrupt JSONL file."""
-        if path is None:
-            path = self._get_session_path(key)
+        path = self._get_session_path(key)
         if not path.exists():
             return None
 
@@ -640,6 +615,7 @@ class SessionManager:
         the most recent writes.
         """
         path = self._get_session_path(session.key)
+        path.parent.mkdir(parents=True, exist_ok=True)
         tmp_path = path.with_suffix(".jsonl.tmp")
 
         try:
@@ -918,7 +894,7 @@ class SessionManager:
                                 }
                             )
             except Exception:
-                repaired = self._repair(fallback_key, path=path)
+                repaired = self._repair(fallback_key)
                 if repaired is not None:
                     sessions.append(
                         {

nanobot/session/turn_continuation.py

@@ -29,6 +29,10 @@ _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

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

@@ -26,7 +26,7 @@ Those belong to the execution phase after the marker is set.
 
 - **`long_task`** — Register **one** sustained objective per thread. Call it promptly once the user has asked for a sustained task. The `goal` should follow the idempotent-goal rules below, but it should be produced quickly from the user's request—not after a long hidden planning pass.
 
-- **`complete_goal`** — Close bookkeeping for the **current** active goal. Call when work is **done**, **and also** when the user **cancels**, **changes direction**, or **replaces** the objective: use **`recap`** to state honestly what happened (e.g. cancelled, partially done, superseded). Then you may call **`long_task`** again for a **new** objective after the session shows no active goal (or after the user agrees to replace).
+- **`complete_goal`** — Close bookkeeping for the **current** active goal. Call when work is **done**, **and also** when the user **cancels**, **changes direction**, or **replaces** the objective: use **`recap`** to state honestly what happened (e.g. cancelled, partially done, superseded). For coding or file-producing tasks, include **`verification_summary`**, **`commands_run`**, and **`artifacts_created`** when possible; if stopping with known unresolved issues, fill **`remaining_failures`** honestly. Then you may call **`long_task`** again for a **new** objective after the session shows no active goal (or after the user agrees to replace).
 
 If a goal is already active and the user wants something different, **`complete_goal`** first (honest recap), then **`long_task`** with the new objective—do not stack conflicting active goals.
 
@@ -68,7 +68,7 @@ Use this when the goal is to **build or reshape a codebase** (app, service, tool
 
 1. **Modular layout** — Split into **meaningful modules** (directories + files with clear responsibilities: entrypoints, domain logic, config, infra, CLI/UI routes, etc.). **Do not** default to dumping an entire project into one giant source file unless the user explicitly wants a minimal single-file artifact.
 2. **Conventional structure** — Follow normal practice for that stack (separation of concerns, sensible naming, config vs code, reusable helpers). Aim for reviewable increments, not unreadable blobs.
-3. **Verify as you go** — Run/format/lint/tests the project affords after meaningful chunks so the tree stays truthful; bake **checks or manual steps into the goal** when they matter.
+3. **Verify as you go** — Run/format/lint/tests the project affords after meaningful chunks so the tree stays truthful; bake **checks or manual steps into the goal** when they matter. Before `complete_goal`, run the smallest reliable verification you can and summarize it in `verification_summary`.
 
 ## Look things up instead of guessing
 

nanobot/utils/file_edit_events.py

@@ -529,9 +529,6 @@ 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/helpers.py

@@ -290,7 +290,8 @@ def current_time_str(timezone: str | None = None) -> str:
 
 
 _UNSAFE_CHARS = re.compile(r'[<>:"/\\|?*]')
-_TOOL_RESULT_PREVIEW_CHARS = 1200
+_TOOL_RESULT_SUMMARY_MAX_EDGE_CHARS = 800
+_TOOL_RESULT_SUMMARY_MIN_EDGE_CHARS = 80
 _TOOL_RESULTS_DIR = ".nanobot/tool-results"
 _TOOL_RESULT_RETENTION_SECS = 7 * 24 * 60 * 60
 _TOOL_RESULT_MAX_BUCKETS = 32
@@ -404,22 +405,106 @@ def stringify_text_blocks(content: list[dict[str, Any]]) -> str | None:
     return "\n".join(parts)
 
 
-def _render_tool_result_reference(
-    filepath: Path,
+def build_structured_output_summary(
+    title: str,
+    text: str,
     *,
-    original_size: int,
-    preview: str,
-    truncated_preview: bool,
+    max_chars: int,
+    metadata: list[tuple[str, Any]] | None = None,
+    analysis: Any | None = None,
+    guidance: str | None = None,
 ) -> str:
-    result = (
-        f"[tool output persisted]\n"
-        f"Full output saved to: {filepath}\n"
-        f"Original size: {original_size} chars\n"
-        f"Preview:\n{preview}"
+    """Return a compact, structured head/tail summary for oversized tool output."""
+
+    if max_chars <= 0:
+        return text
+    edge_chars = min(
+        _TOOL_RESULT_SUMMARY_MAX_EDGE_CHARS,
+        max(_TOOL_RESULT_SUMMARY_MIN_EDGE_CHARS, max_chars // 3),
+    )
+    while True:
+        head = text[:edge_chars]
+        if len(text) > edge_chars * 2:
+            tail: str | None = text[-edge_chars:]
+            omitted_middle_chars = len(text) - len(head) - len(tail)
+        else:
+            tail = None
+            omitted_middle_chars = 0
+        result = _render_structured_output_summary(
+            title,
+            metadata=metadata or [],
+            guidance=guidance,
+            analysis=analysis,
+            head=head,
+            tail=tail,
+            omitted_middle_chars=omitted_middle_chars,
+        )
+        if len(result) <= max_chars or edge_chars <= _TOOL_RESULT_SUMMARY_MIN_EDGE_CHARS:
+            return truncate_text(result, max_chars)
+        overflow = len(result) - max_chars
+        edge_chars = max(
+            _TOOL_RESULT_SUMMARY_MIN_EDGE_CHARS,
+            edge_chars - max(overflow // 2 + 1, 16),
+        )
+
+
+def _render_structured_output_summary(
+    title: str,
+    *,
+    metadata: list[tuple[str, Any]],
+    guidance: str | None,
+    analysis: Any | None,
+    head: str,
+    tail: str | None,
+    omitted_middle_chars: int,
+) -> str:
+    lines = [title]
+    lines.extend(f"{key}: {value}" for key, value in metadata)
+    if omitted_middle_chars:
+        lines.append(f"truncation: {omitted_middle_chars:,} chars truncated from the middle")
+    if guidance:
+        lines.append(f"guidance: {guidance}")
+    lines.extend(_verification_summary_lines(analysis))
+    lines.extend(["head:", head])
+    if tail is not None:
+        lines.extend(["tail:", tail])
+    return "\n".join(lines)
+
+
+def _verification_summary_lines(analysis: Any | None) -> list[str]:
+    if analysis is None or getattr(analysis, "status", None) != "failed":
+        return []
+    lines = ["verification_status: failed"]
+    if getattr(analysis, "timed_out", False):
+        lines.append("failure_type: command timeout")
+    if getattr(analysis, "failed_tests", ()):
+        lines.append("failed_tests:")
+        lines.extend(f"- {item}" for item in analysis.failed_tests)
+    if getattr(analysis, "primary_errors", ()):
+        lines.append("primary_errors:")
+        lines.extend(f"- {item}" for item in analysis.primary_errors)
+    if getattr(analysis, "missing_artifacts", ()):
+        lines.append("missing_artifacts:")
+        lines.extend(f"- {item}" for item in analysis.missing_artifacts)
+    return lines
+
+
+def _build_tool_result_reference(filepath: Path, text: str, *, max_chars: int) -> str:
+    return build_structured_output_summary(
+        "[tool output persisted]",
+        text,
+        max_chars=max_chars,
+        metadata=[
+            ("tool_output_id", filepath.stem),
+            ("original_size_chars", len(text)),
+            ("storage", "internal audit artifact"),
+        ],
+        guidance=(
+            "Use this head/tail summary first. Avoid reading persisted "
+            "tool-output files wholesale; rerun a narrower command when "
+            "more detail is needed."
+        ),
     )
-    if truncated_preview:
-        result += "\n...\n(Read the saved file if you need the full output.)"
-    return result
 
 
 def _bucket_mtime(path: Path) -> float:
@@ -494,13 +579,7 @@ def maybe_persist_tool_result(
         else:
             _write_text_atomic(path, text_payload)
 
-    preview = text_payload[:_TOOL_RESULT_PREVIEW_CHARS]
-    return _render_tool_result_reference(
-        path,
-        original_size=len(text_payload),
-        preview=preview,
-        truncated_preview=len(text_payload) > _TOOL_RESULT_PREVIEW_CHARS,
-    )
+    return _build_tool_result_reference(path, text_payload, max_chars=max_chars)
 
 
 def split_message(content: str, max_len: int = 2000) -> list[str]:

nanobot/utils/runtime.py

@@ -42,6 +42,27 @@ SUSTAINED_GOAL_CONTINUE_PROMPT = (
     "objective using your tools, or call complete_goal if the work is truly finished."
 )
 
+RUNTIME_BUDGET_CONVERGENCE_PROMPT = """\
+[Runtime Budget Notice]
+You have used {used_iterations} of {max_iterations} model/tool iterations for this turn. \
+{remaining_iterations} iteration(s) remain before NanoBot must finalize without more tools.
+
+Switch to convergence mode: stop broad exploration, choose the smallest high-signal command or edit, \
+verify the likely solution, and preserve enough budget for a final answer. For coding or \
+file-producing tasks, do not mark the work complete until the smallest reliable verification passes, \
+or clearly state remaining failures.
+[/Runtime Budget Notice]"""
+
+RUNTIME_BUDGET_FINAL_PROMPT = """\
+[Runtime Budget Notice]
+Only {remaining_iterations} of {max_iterations} model/tool iteration(s) remain before NanoBot must \
+finalize without more tools.
+
+Finalize the solution path now: avoid new broad searches or builds unless essential, make the \
+smallest final fix or artifact, run one targeted verification if possible, then answer honestly with \
+the evidence or remaining failures.
+[/Runtime Budget Notice]"""
+
 
 def empty_tool_result_message(tool_name: str) -> str:
     """Short prompt-safe marker for tools that completed without visible output."""
@@ -88,6 +109,25 @@ def build_goal_continue_message(custom: str | None = None) -> dict[str, str]:
     return {"role": "user", "content": custom or SUSTAINED_GOAL_CONTINUE_PROMPT}
 
 
+def build_runtime_budget_notice_message(
+    *,
+    level: int,
+    max_iterations: int,
+    used_iterations: int,
+    remaining_iterations: int,
+) -> dict[str, str]:
+    """Prompt the model to converge as the generic tool-iteration budget runs low."""
+    template = RUNTIME_BUDGET_FINAL_PROMPT if level >= 2 else RUNTIME_BUDGET_CONVERGENCE_PROMPT
+    return {
+        "role": "user",
+        "content": template.format(
+            max_iterations=max_iterations,
+            used_iterations=used_iterations,
+            remaining_iterations=remaining_iterations,
+        ),
+    }
+
+
 def external_lookup_signature(tool_name: str, arguments: Any) -> str | None:
     """Stable signature for repeated external lookups we want to throttle."""
     if not isinstance(arguments, dict):

nanobot/utils/tool_hints.py

@@ -35,15 +35,10 @@ def format_tool_hints(tool_calls: list, max_length: int = 40) -> str:
 
     formatted = []
     for tc in tool_calls:
-        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)
+        fmt = _TOOL_FORMATS.get(tc.name)
         if fmt:
             formatted.append(_fmt_known(tc, fmt, max_length))
-        elif name.startswith("mcp_"):
+        elif tc.name.startswith("mcp_"):
             formatted.append(_fmt_mcp(tc, max_length))
         else:
             formatted.append(_fmt_fallback(tc, max_length))

nanobot/webui/session_list_index.py

@@ -26,11 +26,10 @@ from nanobot.session.manager import (
     _metadata_title,
 )
 
-_INDEX_VERSION = 2
+_INDEX_VERSION = 1
 _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]]:
@@ -215,45 +214,14 @@ 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": _visible_activity_updated_at(
-            session.updated_at.isoformat(),
-            visible_message_at,
-            activity_updated_at,
-        ),
+        "updated_at": _latest_updated_at(session.updated_at.isoformat(), activity_updated_at),
         "title": _metadata_title(session.metadata),
         "preview": _preview_from_messages(session.messages),
         "file": path.name,
@@ -276,37 +244,31 @@ 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
+                scanned_records += 1
+                scanned_chars += len(line)
+                if (
+                    scanned_records > _SESSION_LIST_PREVIEW_MAX_RECORDS
+                    or scanned_chars > _SESSION_LIST_PREVIEW_MAX_CHARS
+                ):
+                    break
                 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
-                    ):
-                        preview_done = True
-                        continue
-                    if item.get(CRON_HISTORY_META) is True:
-                        continue
-                    text = _message_preview_text(item)
-                    if not text:
-                        continue
-                    if item.get("role") == "user":
-                        preview = text
-                        preview_done = True
-                        continue
-                    if not fallback_preview and item.get("role") == "assistant":
-                        fallback_preview = text
+                if item.get("_type") == "metadata":
+                    continue
+                if item.get(CRON_HISTORY_META) is True:
+                    continue
+                text = _message_preview_text(item)
+                if not text:
+                    continue
+                if item.get("role") == "user":
+                    preview = text
+                    break
+                if not fallback_preview and item.get("role") == "assistant":
+                    fallback_preview = text
             signature = _file_signature(path)
             created_at_s = data.get("created_at")
             updated_at_s = data.get("updated_at")
@@ -320,11 +282,7 @@ def _scan_session_row(session_manager: SessionManager, path: Path) -> dict[str,
             return {
                 "key": key,
                 "created_at": created_at_s,
-                "updated_at": _visible_activity_updated_at(
-                    updated_at_s,
-                    visible_message_at,
-                    activity_updated_at,
-                ),
+                "updated_at": _latest_updated_at(updated_at_s, 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, resolve_config_env_vars, save_config
+from nanobot.config.loader import get_config_path, load_config, save_config
 from nanobot.config.schema import ModelPresetConfig, ProviderConfig
 from nanobot.providers.image_generation import (
     get_image_gen_provider,
@@ -99,6 +99,47 @@ _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."""
 
@@ -353,13 +394,10 @@ def _provider_settings_row(
 
 
 def _model_catalog_kind(spec: Any) -> str:
-    catalog = getattr(spec, "model_catalog", "auto")
-    if catalog != "auto":
-        return catalog
-    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.name in _MODEL_LIST_CATALOG_PROVIDERS:
+        return "catalog"
+    if spec.name in _MODEL_LIST_OFFICIAL_PROVIDERS:
+        return "official"
     if spec.is_local:
         return "local"
     if spec.is_direct:
@@ -452,20 +490,27 @@ 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": catalog_kind,
+        "catalog_kind": _model_catalog_kind(spec),
         "models": [],
         "model_count": 0,
         "message": None,
         "fetched_at": time.time(),
     }
-    if catalog_kind == "unsupported":
+    if (
+        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.",
         }
 
@@ -1121,19 +1166,14 @@ 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(proxy=proxy)
+            token = get_token()
         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>=0.1.6,<1.0.0",
+    "oauth-cli-kit>=0.1.3,<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

@@ -269,15 +269,7 @@ if [ "${NANOBOT_SKIP_WIZARD:-}" = "1" ]; then
   exit 0
 fi
 
-if [ -t 0 ]; then
-  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 "Starting setup wizard..."
+run_nanobot onboard --wizard
 
 info "Done. Try: $(nanobot_try_command) agent -m \"Hello!\""

tests/agent/conftest.py

@@ -38,6 +38,7 @@ 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,
@@ -63,6 +64,7 @@ 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:
@@ -77,8 +79,8 @@ def make_loop(
     if patch_deps:
         with patch("nanobot.agent.loop.ContextBuilder"), \
              patch("nanobot.agent.loop.SessionManager"), \
-             patch("nanobot.agent.loop.SubagentManager") as mock_sub_mgr:
-            mock_sub_mgr.return_value.cancel_by_session = AsyncMock(return_value=0)
+             patch("nanobot.agent.loop.SubagentManager") as MockSubMgr:
+            MockSubMgr.return_value.cancel_by_session = AsyncMock(return_value=0)
             return AgentLoop(**kwargs)
     return AgentLoop(**kwargs)
 

tests/agent/test_auto_compact.py

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

@@ -200,11 +200,8 @@ class TestCheckExpired:
         """Expired session should trigger schedule_background."""
         ac = _make_autocompact(ttl=15)
         mock_sm = MagicMock(spec=SessionManager)
-        old_dt = datetime.now() - timedelta(minutes=20)
-        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
+        old_ts = (datetime.now() - timedelta(minutes=20)).isoformat()
+        mock_sm.list_sessions.return_value = [{"key": "cli:old", "updated_at": old_ts}]
         ac.sessions = mock_sm
 
         scheduled = []
@@ -276,24 +273,6 @@ 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

@@ -430,11 +430,9 @@ 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)
@@ -447,7 +445,6 @@ 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(
@@ -521,10 +518,8 @@ class TestCompactIdleSession:
         assert entries[0]["session_key"] == "cli:test"
 
     @pytest.mark.asyncio
-    async def test_empty_session_does_not_refresh_timestamp(
-        self, real_consolidator
-    ):
-        """Empty session with old updated_at does not look active after compaction."""
+    async def test_empty_session_refreshes_timestamp(self, real_consolidator):
+        """Empty session with old updated_at → refreshed after call, returns ''."""
         from datetime import datetime, timedelta
 
         sessions = real_consolidator.sessions
@@ -537,8 +532,7 @@ class TestCompactIdleSession:
         assert result == ""
 
         reloaded = sessions.get_or_create("cli:empty")
-        assert reloaded.updated_at == old_ts
-        assert reloaded.metadata == {}
+        assert reloaded.updated_at > old_ts
 
     @pytest.mark.asyncio
     async def test_nothing_summary_not_stored(self, real_consolidator, mock_provider):

tests/agent/test_loop_direct_websocket_status.py

@@ -5,7 +5,6 @@ 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
@@ -55,13 +54,13 @@ async def test_process_direct_websocket_clears_run_status(tmp_path) -> None:
         events.append(await loop.bus.consume_outbound())
 
     statuses = [
-        event.event
+        event.metadata
         for event in events
-        if isinstance(event.event, GoalStatusEvent)
+        if event.metadata.get("_goal_status") is True
     ]
-    assert [status.status for status in statuses] == ["running", "idle"]
-    assert isinstance(statuses[0].started_at, float)
-    assert statuses[1].started_at is None
+    assert [status["goal_status"] for status in statuses] == ["running", "idle"]
+    assert isinstance(statuses[0].get("started_at"), float)
+    assert "started_at" not in statuses[1]
 
 
 @pytest.mark.asyncio

tests/agent/test_loop_progress.py

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

tests/agent/test_loop_runner_integration.py

@@ -7,7 +7,6 @@ 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
 
@@ -24,8 +23,8 @@ def _make_loop(tmp_path):
 
     with patch("nanobot.agent.loop.ContextBuilder"), \
          patch("nanobot.agent.loop.SessionManager"), \
-         patch("nanobot.agent.loop.SubagentManager") as mock_sub_mgr:
-        mock_sub_mgr.return_value.cancel_by_session = AsyncMock(return_value=0)
+         patch("nanobot.agent.loop.SubagentManager") as MockSubMgr:
+        MockSubMgr.return_value.cancel_by_session = AsyncMock(return_value=0)
         loop = AgentLoop(bus=bus, provider=provider, workspace=tmp_path)
     return loop
 
@@ -194,9 +193,8 @@ async def test_streamed_flag_not_set_on_llm_error(tmp_path):
 
     assert result is not None
     assert "503" in result.content
-    assert not isinstance(result.event, StreamedResponseEvent), (
-        "streamed response event must not be set when stop_reason is error"
-    )
+    assert not result.metadata.get("_streamed"), \
+        "_streamed must not be set when stop_reason is error"
 
 
 @pytest.mark.asyncio
@@ -241,7 +239,7 @@ 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 isinstance(result.event, StreamedResponseEvent)
+    assert result.metadata.get("_streamed") is True
 
 
 @pytest.mark.asyncio

tests/agent/test_loop_save_turn.py

@@ -8,13 +8,6 @@ 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
@@ -772,6 +765,7 @@ 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",
         },
     ))
 
@@ -781,23 +775,23 @@ 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 isinstance(m.event, StreamDeltaEvent)]
-    ends = [m for m in outbound if isinstance(m.event, StreamEndEvent)]
-    streamed_markers = [m for m in outbound if isinstance(m.event, StreamedResponseEvent)]
+    deltas = [m for m in outbound if m.metadata.get("_stream_delta")]
+    ends = [m for m in outbound if m.metadata.get("_stream_end")]
+    streamed_markers = [m for m in outbound if m.metadata.get("_streamed")]
 
     assert [m.content for m in deltas] == ["done"]
     assert len(ends) == 1
-    assert isinstance(ends[0].event, StreamEndEvent)
-    assert ends[0].event.resuming is False
+    assert ends[0].metadata["_resuming"] is False
     assert ends[0].metadata["message_id"] == "om_001"
     assert ends[0].metadata["origin_message_id"] == "root_001"
-    assert isinstance(ends[0].event.stream_id, str)
+    assert isinstance(ends[0].metadata.get("_stream_id"), str)
     assert streamed_markers and streamed_markers[-1].content == "done"
 
 
@@ -848,10 +842,10 @@ 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.event for m in first_outbound if isinstance(m.event, GoalStatusEvent)]
-    assert [m.status for m in first_statuses] == ["running"]
-    assert not [m for m in first_outbound if isinstance(m.event, TurnEndEvent)]
-    started_at = first_statuses[0].started_at
+    first_statuses = [m.metadata for m in first_outbound if m.metadata.get("_goal_status")]
+    assert [m["goal_status"] for m in first_statuses] == ["running"]
+    assert not [m for m in first_outbound if m.metadata.get("_turn_end")]
+    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
@@ -862,13 +856,12 @@ 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.event for m in second_outbound if isinstance(m.event, GoalStatusEvent)]
-    assert [m.status for m in second_statuses] == ["running", "idle"]
-    assert second_statuses[0].started_at == started_at
-    turn_end = [m for m in second_outbound if isinstance(m.event, TurnEndEvent)]
+    second_statuses = [m.metadata for m in second_outbound if m.metadata.get("_goal_status")]
+    assert [m["goal_status"] for m in second_statuses] == ["running", "idle"]
+    assert second_statuses[0]["started_at"] == started_at
+    turn_end = [m for m in second_outbound if m.metadata.get("_turn_end")]
     assert len(turn_end) == 1
-    assert isinstance(turn_end[0].event, TurnEndEvent)
-    assert isinstance(turn_end[0].event.latency_ms, int)
+    assert isinstance(turn_end[0].metadata.get("latency_ms"), int)
 
 
 @pytest.mark.asyncio

tests/agent/test_max_messages_config.py

@@ -1,4 +1,4 @@
-"""Tests for the internal max_messages replay cap."""
+"""Tests for max_messages config wiring into session history replay."""
 
 from __future__ import annotations
 
@@ -11,27 +11,20 @@ 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.providers.factory import ProviderSnapshot
-from nanobot.session.manager import (
-    FILE_MAX_MESSAGES,
-    Session,
-    replay_max_messages_for_context,
-)
+from nanobot.session.manager import Session
+
+DEFAULT_MAX_MESSAGES = 120
 
 
-def _make_loop(
-    tmp_path: Path,
-    context_window_tokens: int = 200_000,
-) -> AgentLoop:
+def _make_loop(tmp_path: Path, max_messages: int = DEFAULT_MAX_MESSAGES) -> 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",
-        context_window_tokens=context_window_tokens,
+        max_messages=max_messages,
     )
 
 
@@ -58,44 +51,24 @@ def _tool_round(call_id: str) -> list[dict]:
 
 
 class TestMaxMessagesInit:
-    """Verify AgentLoop derives the internal replay cap correctly."""
+    """Verify AgentLoop stores the config value correctly."""
 
-    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:
+    def test_default_is_builtin_limit(self, tmp_path: Path) -> None:
         loop = _make_loop(tmp_path)
-        assert loop._max_messages == FILE_MAX_MESSAGES
+        assert loop._max_messages == DEFAULT_MAX_MESSAGES
 
-    def test_default_scales_with_context_window(self, tmp_path: Path) -> None:
-        loop = _make_loop(tmp_path, context_window_tokens=32_768)
-        assert loop._max_messages == 327
+    def test_positive_value_stored(self, tmp_path: Path) -> None:
+        loop = _make_loop(tmp_path, max_messages=25)
+        assert loop._max_messages == 25
 
-    def test_provider_refresh_resyncs_context_derived_limit(self, tmp_path: Path) -> None:
-        old_provider = MagicMock()
-        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_zero_uses_builtin_limit(self, tmp_path: Path) -> None:
+        loop = _make_loop(tmp_path, max_messages=0)
+        assert loop._max_messages == DEFAULT_MAX_MESSAGES
 
-        assert loop._max_messages == 327
-        loop._refresh_provider_snapshot()
-        assert loop._max_messages == FILE_MAX_MESSAGES
+    def test_negative_treated_as_builtin_limit(self, tmp_path: Path) -> None:
+        """Negative values should not produce negative slicing."""
+        loop = _make_loop(tmp_path, max_messages=-5)
+        assert loop._max_messages == DEFAULT_MAX_MESSAGES
 
 
 class TestGetHistoryWithMaxMessages:
@@ -104,7 +77,7 @@ class TestGetHistoryWithMaxMessages:
     def test_default_uses_builtin_limit(self) -> None:
         session = _populated_session(80)
         history = session.get_history()
-        assert len(history) <= FILE_MAX_MESSAGES
+        assert len(history) <= DEFAULT_MAX_MESSAGES
 
     def test_explicit_max_messages_limits_output(self) -> None:
         session = _populated_session(40)  # 80 messages total
@@ -120,7 +93,7 @@ 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) <= FILE_MAX_MESSAGES
+        assert len(history) <= DEFAULT_MAX_MESSAGES
 
     def test_small_session_unaffected(self) -> None:
         """When session has fewer messages than max_messages, all are returned."""
@@ -130,13 +103,12 @@ class TestGetHistoryWithMaxMessages:
 
 
 class TestMaxMessagesIntegration:
-    """Verify AgentLoop passes the replay cap into get_history calls."""
+    """Verify the config flows from AgentLoop into get_history calls."""
 
     @pytest.mark.asyncio
-    async def test_process_message_passes_limit_to_history_call(self, tmp_path: Path) -> None:
+    async def test_process_message_passes_config_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)
-        loop._max_messages = 25
+        loop = _make_loop(tmp_path, max_messages=25)
         loop.provider.chat_with_retry = AsyncMock(
             return_value=LLMResponse(content="ok", tool_calls=[], usage={})
         )
@@ -155,11 +127,8 @@ class TestMaxMessagesIntegration:
         assert mock_hist.call_args.kwargs["extend_to_user"] is False
 
     @pytest.mark.asyncio
-    async def test_default_limit_passes_context_derived_limit_to_history_call(
-        self,
-        tmp_path: Path,
-    ) -> None:
-        loop = _make_loop(tmp_path)
+    async def test_zero_config_passes_builtin_limit_to_history_call(self, tmp_path: Path) -> None:
+        loop = _make_loop(tmp_path, max_messages=0)
         loop.provider.chat_with_retry = AsyncMock(
             return_value=LLMResponse(content="ok", tool_calls=[], usage={})
         )
@@ -173,7 +142,7 @@ class TestMaxMessagesIntegration:
             )
 
         assert result is not None
-        assert mock_hist.call_args.kwargs["max_messages"] == FILE_MAX_MESSAGES
+        assert mock_hist.call_args.kwargs["max_messages"] == DEFAULT_MAX_MESSAGES
         assert mock_hist.call_args.kwargs["extend_to_user"] is False
 
     @pytest.mark.asyncio
@@ -182,8 +151,7 @@ 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)
-        loop._max_messages = 6
+        loop = _make_loop(tmp_path, max_messages=6)
         loop.provider.chat_with_retry = AsyncMock(
             return_value=LLMResponse(content="ok", tool_calls=[], usage={})
         )
@@ -214,3 +182,31 @@ 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

@@ -853,11 +853,10 @@ class TestApiServerRegistration:
         config = Config()
         from nanobot.config.schema import ApiConfig
 
-        new_api = ApiConfig(host="0.0.0.0", port=9999, api_key="secret")
+        new_api = ApiConfig(host="0.0.0.0", port=9999)
         _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

@@ -135,46 +135,6 @@ 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, ToolCallRequest
+from nanobot.providers.base import LLMResponse
 
 _MAX_TOOL_RESULT_CHARS = AgentDefaults().max_tool_result_chars
 
@@ -877,162 +877,3 @@ 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_persistence.py

@@ -48,7 +48,13 @@ async def test_runner_persists_large_tool_results_for_follow_up_calls(tmp_path):
     assert result.final_content == "done"
     tool_message = next(msg for msg in captured_second_call if msg.get("role") == "tool")
     assert "[tool output persisted]" in tool_message["content"]
-    assert "tool-results" in tool_message["content"]
+    assert "tool_output_id: call_big" in tool_message["content"]
+    assert "original_size_chars: 20000" in tool_message["content"]
+    assert "head:" in tool_message["content"]
+    assert "tail:" in tool_message["content"]
+    assert "Read the saved file" not in tool_message["content"]
+    assert str(tmp_path) not in tool_message["content"]
+    assert len(tool_message["content"]) <= 2048
     assert (tmp_path / ".nanobot" / "tool-results" / "test_runner" / "call_big.txt").exists()
 
 
@@ -76,6 +82,8 @@ def test_persist_tool_result_prunes_old_session_buckets(tmp_path):
     )
 
     assert "[tool output persisted]" in persisted
+    assert "tool_output_id: call_big" in persisted
+    assert "tool-results" not in persisted
     assert not old_bucket.exists()
     assert recent_bucket.exists()
     assert (root / "current_session" / "call_big.txt").exists()

tests/agent/test_runner_safety.py

@@ -6,8 +6,6 @@ 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
 
@@ -22,6 +20,8 @@ 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(
@@ -64,6 +64,8 @@ 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(
@@ -86,6 +88,8 @@ 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(
@@ -103,7 +107,7 @@ async def test_runner_returns_non_retryable_hint_on_ssrf_violation():
     ])
     tools = MagicMock()
     tools.get_definitions.return_value = []
-    tools.execute = AsyncMock(return_value=ToolResult.error(
+    tools.execute = AsyncMock(return_value=(
         "Error: Command blocked by safety guard (internal/private URL detected)"
     ))
 
@@ -137,6 +141,8 @@ 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] = []
 
@@ -157,9 +163,7 @@ async def test_runner_lets_llm_recover_from_shell_guard_path_outside():
     tools = MagicMock()
     tools.get_definitions.return_value = []
     tools.execute = AsyncMock(
-        return_value=ToolResult.error(
-            "Error: Command blocked by safety guard (path outside working dir)"
-        )
+        return_value="Error: Command blocked by safety guard (path outside working dir)"
     )
 
     runner = AgentRunner(provider)
@@ -191,6 +195,8 @@ 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",
@@ -209,9 +215,7 @@ async def test_runner_throttles_repeated_workspace_bypass_attempts():
     tools = MagicMock()
     tools.get_definitions.return_value = []
     tools.execute = AsyncMock(
-        return_value=ToolResult.error(
-            "Error: Command blocked by safety guard (path outside working dir)"
-        )
+        return_value="Error: Command blocked by safety guard (path outside working dir)"
     )
 
     runner = AgentRunner(provider)

tests/agent/test_runner_tool_execution.py

@@ -8,9 +8,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 import pytest
 
 from nanobot.agent.runner import AgentRunner, AgentRunSpec
-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.base import Tool
 from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.config.schema import AgentDefaults
 from nanobot.providers.base import LLMResponse, ToolCallRequest
@@ -63,40 +61,6 @@ 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}
@@ -127,20 +91,6 @@ 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
@@ -370,63 +320,6 @@ 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()
@@ -465,3 +358,79 @@ async def test_runner_blocks_repeated_external_fetches():
         if msg.get("role") == "tool" and msg.get("tool_call_id") == "call_3"
     ][0]
     assert "repeated external lookup blocked" in blocked_tool_message["content"]
+
+
+@pytest.mark.asyncio
+async def test_runner_adds_budget_notice_near_long_tool_budget():
+    provider = MagicMock()
+    captured_final_call: list[dict] = []
+    call_count = {"n": 0}
+
+    async def chat_with_retry(*, messages, **kwargs):
+        call_count["n"] += 1
+        if call_count["n"] <= 16:
+            return LLMResponse(
+                content="working",
+                tool_calls=[ToolCallRequest(id=f"call_{call_count['n']}", name="work", arguments={})],
+                usage={},
+            )
+        captured_final_call[:] = messages
+        return LLMResponse(content="done", tool_calls=[], usage={})
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    tools.execute = AsyncMock(return_value="tool result")
+
+    result = await AgentRunner(provider).run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "finish a large task"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=20,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    ))
+
+    assert result.final_content == "done"
+    notices = [
+        msg["content"]
+        for msg in captured_final_call
+        if msg.get("role") == "user" and "[Runtime Budget Notice]" in str(msg.get("content"))
+    ]
+    assert len(notices) == 1
+    assert "15 of 20 model/tool iterations" in notices[0]
+    assert "Switch to convergence mode" in notices[0]
+    assert tools.execute.await_count == 16
+
+
+@pytest.mark.asyncio
+async def test_runner_budget_notice_does_not_affect_short_runs():
+    provider = MagicMock()
+    captured_final_call: list[dict] = []
+    call_count = {"n": 0}
+
+    async def chat_with_retry(*, messages, **kwargs):
+        call_count["n"] += 1
+        if call_count["n"] <= 2:
+            return LLMResponse(
+                content="working",
+                tool_calls=[ToolCallRequest(id=f"call_{call_count['n']}", name="work", arguments={})],
+                usage={},
+            )
+        captured_final_call[:] = messages
+        return LLMResponse(content="done", tool_calls=[], usage={})
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    tools.execute = AsyncMock(return_value="tool result")
+
+    result = await AgentRunner(provider).run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "small task"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=4,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    ))
+
+    assert result.final_content == "done"
+    assert all("[Runtime Budget Notice]" not in str(msg.get("content")) for msg in captured_final_call)

tests/agent/test_session_atomic.py

@@ -1,6 +1,7 @@
 """Tests for atomic session save and corrupt-file repair."""
 
 import json
+import shutil
 from datetime import datetime
 from pathlib import Path
 
@@ -36,6 +37,17 @@ class TestAtomicSave:
         tmp_files = list(mgr.sessions_dir.glob("*.tmp"))
         assert tmp_files == []
 
+    def test_save_recreates_deleted_sessions_dir(self, tmp_path: Path):
+        mgr = SessionManager(tmp_path)
+        shutil.rmtree(mgr.sessions_dir)
+
+        session = Session(key="test:recreate")
+        session.add_message("user", "hello")
+        mgr.save(session)
+
+        path = mgr._get_session_path("test:recreate")
+        assert path.exists()
+
     def test_tmp_file_cleaned_up_on_write_failure(self, tmp_path: Path):
         mgr = SessionManager(tmp_path)
         session = Session(key="test:fail")

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}"})
 
-    result = session.retain_recent_legal_suffix(4)
+    dropped, already_cons = session.retain_recent_legal_suffix(4)
 
-    assert len(result.dropped) == 6
-    assert [m["content"] for m in result.dropped] == [f"msg{i}" for i in range(6)]
+    assert len(dropped) == 6
+    assert [m["content"] for m in dropped] == [f"msg{i}" for i in range(6)]
     assert len(session.messages) == 4
-    assert result.already_consolidated_count == 0
+    assert already_cons == 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}"})
 
-    result = session.retain_recent_legal_suffix(4)
+    dropped, already_cons = session.retain_recent_legal_suffix(4)
 
-    assert result.dropped == []
-    assert result.already_consolidated_count == 0
+    assert dropped == []
+    assert already_cons == 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
 
-    result = session.retain_recent_legal_suffix(0)
+    dropped, already_cons = session.retain_recent_legal_suffix(0)
 
-    assert len(result.dropped) == 5
-    assert result.already_consolidated_count == 3
+    assert len(dropped) == 5
+    assert already_cons == 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
 
-    result = session.retain_recent_legal_suffix(4)
+    dropped, already_cons = 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 result.already_consolidated_count == 9
+    assert already_cons == 9

tests/agent/test_task_cancel.py

@@ -127,7 +127,6 @@ 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(
@@ -157,10 +156,10 @@ class TestDispatch:
 
         assert first.metadata["thread_root_event_id"] == "$root1"
         assert first.metadata["thread_reply_to_event_id"] == "$reply1"
-        assert isinstance(first.event, StreamDeltaEvent)
+        assert first.metadata["_stream_delta"] is True
         assert second.metadata["thread_root_event_id"] == "$root1"
         assert second.metadata["thread_reply_to_event_id"] == "$reply1"
-        assert isinstance(second.event, StreamEndEvent)
+        assert second.metadata["_stream_end"] is True
 
     @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.providers.base import ToolCallRequest
 from nanobot.utils.tool_hints import format_tool_hints
+from nanobot.providers.base import ToolCallRequest
 
 
 def _tc(name: str, args) -> ToolCallRequest:
@@ -306,22 +306,3 @@ 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

@@ -1,11 +1,7 @@
 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():
@@ -78,67 +74,3 @@ 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/test_verification_state.py

@@ -0,0 +1,175 @@
+from __future__ import annotations
+
+from nanobot.agent.verification_state import (
+    analyze_verification_result,
+    append_verification_feedback,
+)
+
+
+def test_analyze_pytest_failure_extracts_actionable_summary():
+    output = """\
+FAILED ../tests/test_outputs.py::test_regex_matches_dates - AssertionError: Expected dates
+E       AssertionError: Expected ['2025-01-09'], but got ['bad']
+E       FileNotFoundError: [Errno 2] No such file or directory: '/app/out.txt'
+============================== 1 failed in 0.05s ===============================
+Exit code: 1
+"""
+
+    analysis = analyze_verification_result(
+        command="pytest /tests/test_outputs.py",
+        output=output,
+        exit_code=1,
+    )
+
+    assert analysis is not None
+    assert analysis.status == "failed"
+    assert analysis.failed_tests == ("../tests/test_outputs.py::test_regex_matches_dates",)
+    assert any("AssertionError" in item for item in analysis.primary_errors)
+    assert "/app/out.txt" in analysis.missing_artifacts
+
+
+def test_append_verification_feedback_tells_agent_not_to_finish():
+    analysis = analyze_verification_result(
+        command="python /app/test_outputs.py",
+        output="FAILED test_outputs.py::test_file\nAssertionError: missing\nExit code: 1",
+        exit_code=1,
+    )
+
+    feedback = append_verification_feedback("raw output\nExit code: 1", analysis)
+
+    assert "[Verification Feedback]" in feedback
+    assert "Do not call complete_goal" in feedback
+    assert "Next action" in feedback
+
+
+def test_analyze_passing_test_records_success_without_feedback():
+    analysis = analyze_verification_result(
+        command="pytest",
+        output="============================== 3 passed in 0.10s ==============================\nExit code: 0",
+        exit_code=0,
+    )
+
+    assert analysis is not None
+    assert analysis.status == "passed"
+    assert append_verification_feedback("ok", analysis) == "ok"
+
+
+def test_analyze_command_not_found_as_failed_check():
+    output = """\
+STDERR:
+/usr/bin/bash: line 1: python3: command not found
+
+Exit code: 127
+"""
+
+    analysis = analyze_verification_result(
+        command="python3 - <<'PY'\nprint('quick verification')\nPY",
+        output=output,
+        exit_code=127,
+    )
+
+    assert analysis is not None
+    assert analysis.status == "failed"
+    assert any("command not found" in item for item in analysis.primary_errors)
+
+
+def test_analyze_artifact_comparison_success_records_pass():
+    output = """\
+run_exit:0
+0d115b98  /app/image.ppm
+0d115b98  /tmp/orig.ppm
+cmp_exit:0
+      7      21    1024
+
+Exit code: 0
+"""
+
+    analysis = analyze_verification_result(
+        command=(
+            "cd /usr/bin && gcc -static -o /app/reversed_final /app/mystery.c -lm "
+            "&& (cd /app && ./reversed_final >/tmp/final_out 2>/tmp/final_err); "
+            "sha256sum /app/image.ppm /tmp/orig.ppm; "
+            "cmp -s /app/image.ppm /tmp/orig.ppm; echo cmp_exit:$?"
+        ),
+        output=output,
+        exit_code=0,
+    )
+
+    assert analysis is not None
+    assert analysis.status == "passed"
+    assert append_verification_feedback("ok", analysis) == "ok"
+
+
+def test_analyze_plain_checksum_without_success_marker_is_ignored():
+    analysis = analyze_verification_result(
+        command="sha256sum /app/image.ppm /tmp/orig.ppm",
+        output="0d115b98  /app/image.ppm\n0d115b98  /tmp/orig.ppm\nExit code: 0",
+        exit_code=0,
+    )
+
+    assert analysis is None
+
+
+def test_analyze_named_comparison_markers_record_pass():
+    output = """\
+ppm:0
+stderr:0
+stdout:0
+      4      26    1011
+1821 mystery.c
+
+Exit code: 0
+"""
+
+    analysis = analyze_verification_result(
+        command=(
+            "gcc -static -O2 -o reversed mystery.c -lm\n"
+            "./reversed > vrout.txt 2> vrerr.txt\n"
+            "cp image.ppm rev.ppm\n"
+            "./mystery > voout.txt 2> voerr.txt\n"
+            "cmp image.ppm rev.ppm\n"
+            "printf 'ppm:%s\\n' $?\n"
+            "cmp voerr.txt vrerr.txt\n"
+            "printf 'stderr:%s\\n' $?\n"
+            "cmp voout.txt vrout.txt\n"
+            "printf 'stdout:%s\\n' $?"
+        ),
+        output=output,
+        exit_code=0,
+    )
+
+    assert analysis is not None
+    assert analysis.status == "passed"
+
+
+def test_analyze_named_comparison_marker_failure_records_failed():
+    output = """\
+ppm:0
+stderr:1
+stdout:0
+
+Exit code: 0
+"""
+
+    analysis = analyze_verification_result(
+        command=(
+            "cmp image.ppm rev.ppm; printf 'ppm:%s\\n' $?; "
+            "cmp voerr.txt vrerr.txt; printf 'stderr:%s\\n' $?; "
+            "cmp voout.txt vrout.txt; printf 'stdout:%s\\n' $?"
+        ),
+        output=output,
+        exit_code=0,
+    )
+
+    assert analysis is not None
+    assert analysis.status == "failed"
+
+
+def test_analyze_plain_run_status_marker_without_comparison_is_ignored():
+    analysis = analyze_verification_result(
+        command="gcc -static -O2 -o reversed mystery.c -lm && ./reversed",
+        output="rc:0\nExit code: 0",
+        exit_code=0,
+    )
+
+    assert analysis is None

tests/agent/tools/test_long_task.py

@@ -13,7 +13,11 @@ from nanobot.agent.tools.long_task import (
     CompleteGoalTool,
     LongTaskTool,
 )
-from nanobot.bus.outbound_events import GoalStateSyncEvent
+from nanobot.agent.verification_state import (
+    VerificationAnalysis,
+    clear_verification_observation,
+    record_verification_observation,
+)
 from nanobot.bus.queue import MessageBus
 from nanobot.bus.runtime_events import RuntimeEventBus
 from nanobot.session.goal_state import GOAL_STATE_KEY
@@ -145,8 +149,8 @@ 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 isinstance(call.event, GoalStateSyncEvent)
-    assert call.event.goal_state == {
+    assert call.metadata.get("_goal_state_sync") is True
+    assert call.metadata["goal_state"] == {
         "active": True,
         "ui_summary": "alpha",
         "objective": "Objective alpha",
@@ -181,8 +185,7 @@ 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 isinstance(call.event, GoalStateSyncEvent)
-    assert call.event.goal_state == {"active": False}
+    assert call.metadata["goal_state"] == {"active": False}
 
 
 @pytest.mark.asyncio
@@ -194,6 +197,66 @@ async def test_complete_goal_without_active_is_noop_message(tmp_path):
     assert "No active" in out
 
 
+@pytest.mark.asyncio
+async def test_complete_goal_blocks_unresolved_verification_failure(tmp_path):
+    sm = SessionManager(tmp_path)
+    lt, cg = _tools(sm)
+    await lt.execute(goal="Fix the tests")
+    record_verification_observation(
+        "websocket:c1",
+        VerificationAnalysis(
+            status="failed",
+            command="pytest /tests/test_outputs.py",
+            exit_code=1,
+            failed_tests=("test_outputs.py::test_output",),
+            primary_errors=("AssertionError: wrong output",),
+        ),
+    )
+
+    out = await cg.execute(recap="Done.")
+
+    assert "not marked complete" in out
+    assert "test_outputs.py::test_output" in out
+    assert sm.get_or_create("websocket:c1").metadata[GOAL_STATE_KEY]["status"] == "active"
+    clear_verification_observation("websocket:c1")
+
+
+@pytest.mark.asyncio
+async def test_complete_goal_allows_after_later_successful_verification(tmp_path):
+    sm = SessionManager(tmp_path)
+    lt, cg = _tools(sm)
+    await lt.execute(goal="Fix the tests")
+    record_verification_observation(
+        "websocket:c1",
+        VerificationAnalysis(
+            status="failed",
+            command="pytest /tests/test_outputs.py",
+            exit_code=1,
+            failed_tests=("test_outputs.py::test_output",),
+        ),
+    )
+    record_verification_observation(
+        "websocket:c1",
+        VerificationAnalysis(
+            status="passed",
+            command="pytest /tests/test_outputs.py",
+            exit_code=0,
+        ),
+    )
+
+    out = await cg.execute(
+        recap="Done.",
+        verification_summary="pytest /tests/test_outputs.py passed",
+        commands_run="pytest /tests/test_outputs.py",
+        artifacts_created="/app/out.txt",
+    )
+
+    assert "marked complete" in out
+    blob = sm.get_or_create("websocket:c1").metadata[GOAL_STATE_KEY]
+    assert blob["status"] == "completed"
+    assert blob["verification_summary"] == "pytest /tests/test_outputs.py passed"
+
+
 @pytest.mark.asyncio
 async def test_long_task_skips_ws_publish_without_bus(tmp_path):
     sm = SessionManager(tmp_path)

tests/agent/tools/test_self_tool.py

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

tests/bus/test_outbound_events.py

@@ -1,244 +0,0 @@
-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

@@ -1,19 +1,10 @@
 """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
@@ -38,187 +29,221 @@ 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,
-        *,
-        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,
-        )
+    async def send_delta(self, chat_id, delta, metadata=None):
+        """Override send_delta for testing."""
+        return await self._send_delta_mock(chat_id, delta, metadata)
 
 
 @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):
-        msg = _delta("Hello")
+        """A single delta should be sent as-is."""
+        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)
-                event = outbound_event_from_message(m)
-                if isinstance(event, StreamDeltaEvent):
+                if m.metadata.get("_stream_delta"):
                     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)
-                event = outbound_event_from_message(m)
-                if channel and isinstance(event, StreamDeltaEvent):
-                    await channel.send_delta(
-                        m.chat_id,
-                        m.content,
-                        m.metadata,
-                        stream_id=event.stream_id,
-                    )
+                if channel:
+                    await channel.send_delta(m.chat_id, m.content, m.metadata)
             except asyncio.TimeoutError:
                 pass
 
         await process_one()
 
         manager.channels["mock"]._send_delta_mock.assert_called_once_with(
-            "chat1",
-            "Hello",
-            {},
-            stream_id=None,
-            stream_end=False,
-            resuming=False,
+            "chat1", "Hello", {"_stream_delta": True}
         )
 
     @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(_delta(text))
+            await bus.publish_outbound(OutboundMessage(
+                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 isinstance(merged.event, StreamDeltaEvent)
+        assert merged.metadata.get("_stream_delta") is True
+        # No pending messages (all were coalesced)
         assert len(pending) == 0
 
     @pytest.mark.asyncio
     async def test_deltas_different_chats_not_coalesced(self, manager, bus):
-        await bus.publish_outbound(_delta("Hello", chat_id="chat1"))
-        await bus.publish_outbound(_delta("World", chat_id="chat2"))
+        """Deltas for different chats should not be merged."""
+        # Put deltas for different chats
+        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"))
+        """Deltas for the same chat but different streams should not be merged."""
+        await bus.publish_outbound(OutboundMessage(
+            channel="mock",
+            chat_id="chat1",
+            content="A1",
+            metadata={"_stream_delta": True, "_stream_id": "stream-a"},
+        ))
+        await bus.publish_outbound(OutboundMessage(
+            channel="mock",
+            chat_id="chat1",
+            content="B1",
+            metadata={"_stream_delta": True, "_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 merged.metadata.get("_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"
+        assert pending[0].metadata.get("_stream_id") == "stream-b"
 
     @pytest.mark.asyncio
     async def test_stream_end_terminates_coalescing(self, manager, bus):
-        await bus.publish_outbound(_delta("Hello"))
-        await bus.publish_outbound(_end(" world"))
+        """_stream_end should stop coalescing and be included in final message."""
+        # Put deltas with stream_end at the end
+        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"
-        assert isinstance(merged.event, StreamEndEvent)
+        # Should have stream_end flag
+        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):
-        await bus.publish_outbound(_delta("Hello", stream_id="seg-1"))
-        await bus.publish_outbound(_end(stream_id="seg-1"))
-        await bus.publish_outbound(_delta("world", stream_id="seg-2"))
+        """Only consecutive deltas should be merged; later deltas stay queued."""
+        await bus.publish_outbound(OutboundMessage(
+            channel="mock",
+            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 isinstance(merged.event, StreamDeltaEvent)
+        assert merged.metadata.get("_stream_end") is None
         assert len(pending) == 1
-        assert isinstance(pending[0].event, StreamEndEvent)
-        assert pending[0].event.stream_id == "seg-1"
+        assert pending[0].metadata.get("_stream_end") is True
+        assert pending[0].metadata.get("_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 isinstance(remaining.event, StreamDeltaEvent)
-        assert remaining.event.stream_id == "seg-2"
+        assert remaining.metadata.get("_stream_id") == "seg-2"
 
     @pytest.mark.asyncio
     async def test_non_delta_message_preserved(self, manager, bus):
-        await bus.publish_outbound(_delta("Delta"))
+        """Non-delta messages should be preserved in pending list."""
+        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()
@@ -227,11 +252,17 @@ class TestDeltaCoalescing:
         assert merged.content == "Delta"
         assert len(pending) == 1
         assert pending[0].content == "Final message"
-        assert pending[0].event is None
+        assert pending[0].metadata.get("_stream_delta") is None
 
     @pytest.mark.asyncio
     async def test_empty_queue_stops_coalescing(self, manager, bus):
-        await bus.publish_outbound(_delta("Only message"))
+        """Coalescing should stop when queue is empty."""
+        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)
@@ -245,35 +276,49 @@ class TestDispatchOutboundWithCoalescing:
 
     @pytest.mark.asyncio
     async def test_dispatch_coalesces_and_processes_pending(self, manager, bus):
-        await bus.publish_outbound(_delta("A"))
-        await bus.publish_outbound(_delta("B"))
+        """_dispatch_outbound should coalesce deltas and process pending messages."""
+        # Put multiple deltas followed by a regular message
+        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 = []
 
-        msg = pending.pop(0) if pending else await bus.consume_outbound()
-        event = outbound_event_from_message(msg)
-        if isinstance(event, StreamDeltaEvent):
+        # First iteration: should coalesce A+B
+        if pending:
+            msg = pending.pop(0)
+        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)
-        event = outbound_event_from_message(msg)
-        if channel and isinstance(event, StreamDeltaEvent):
-            await channel.send_delta(
-                msg.chat_id,
-                msg.content,
-                msg.metadata,
-                stream_id=event.stream_id,
-            )
+        if channel:
+            await channel.send_delta(msg.chat_id, msg.content, msg.metadata)
             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"
 
@@ -309,20 +354,23 @@ 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(outbound_message_for_event(
+        await bus.publish_outbound(OutboundMessage(
             channel="mock",
             chat_id="chat1",
-            event=ProgressEvent(content="thinking"),
+            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())
@@ -343,37 +391,13 @@ class TestProgressFiltering:
         assert send_mock.await_args_list[0].args[0].content == "final answer"
 
     @pytest.mark.asyncio
-    async def test_legacy_progress_flag_uses_runtime_progress_filter(self, manager, bus):
-        manager.channels["mock"].send_progress = False
+    async def test_channel_override_can_enable_tool_hints(self, manager, bus):
+        manager.channels["mock"].send_tool_hints = True
         await bus.publish_outbound(OutboundMessage(
             channel="mock",
             chat_id="chat1",
-            content="legacy progress-shaped message",
-            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),
+            content="read_file(foo.py)",
+            metadata={"_progress": True, "_tool_hint": True},
         ))
 
         task = asyncio.create_task(manager._dispatch_outbound())
@@ -399,15 +423,24 @@ class TestRetryWaitFiltering:
 
     @pytest.mark.asyncio
     async def test_retry_wait_message_dropped(self, manager, bus):
-        retry_msg = outbound_message_for_event(
+        """A ``_retry_wait`` message must be filtered before channel dispatch.
+
+        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",
-            event=RetryWaitEvent(content="Model request failed, retry in 1s (attempt 1)."),
+            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)
@@ -429,4 +462,4 @@ class TestRetryWaitFiltering:
         assert send_mock.await_count == 1
         sent = send_mock.await_args_list[0].args[0]
         assert sent.content == "final answer"
-        assert sent.event is None
+        assert not sent.metadata.get("_retry_wait")

tests/channels/test_channel_manager_reasoning.py

@@ -8,9 +8,10 @@ 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 represented as typed progress events and
-``BaseChannel.send_reasoning`` expands them to a single delta + end pair so
-plugins only implement the streaming primitives.
+One-shot ``_reasoning`` frames are accepted for back-compat with hooks
+that haven't migrated yet — ``BaseChannel.send_reasoning`` expands them
+to a single delta + end pair so plugins only implement the streaming
+primitives.
 """
 
 from __future__ import annotations
@@ -21,7 +22,6 @@ 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, *, stream_id=None):
-        return await self._delta_mock(chat_id, delta, metadata, stream_id=stream_id)
+    async def send_reasoning_delta(self, chat_id, delta, metadata=None):
+        return await self._delta_mock(chat_id, delta, metadata)
 
-    async def send_reasoning_end(self, chat_id, metadata=None, *, stream_id=None):
-        return await self._end_mock(chat_id, metadata, stream_id=stream_id)
+    async def send_reasoning_end(self, chat_id, metadata=None):
+        return await self._end_mock(chat_id, metadata)
 
     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 = outbound_message_for_event(
+    msg = OutboundMessage(
         channel="mock",
         chat_id="c1",
-        event=ProgressEvent(content="step-by-step", reasoning_delta=True, stream_id="r1"),
+        content="step-by-step",
+        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()
 
@@ -112,10 +112,11 @@ 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 = outbound_message_for_event(
+    msg = OutboundMessage(
         channel="mock",
         chat_id="c1",
-        event=ProgressEvent(reasoning_end=True, stream_id="r1"),
+        content="",
+        metadata={"_progress": True, "_reasoning_end": True, "_stream_id": "r1"},
     )
     await manager._send_once(channel, msg)
     channel._end_mock.assert_awaited_once()
@@ -123,13 +124,16 @@ async def test_reasoning_end_routes_to_send_reasoning_end(manager):
 
 
 @pytest.mark.asyncio
-async def test_one_shot_reasoning_expands_to_delta_plus_end(manager):
-    """One-shot reasoning expands to a single delta + end."""
+async def test_legacy_one_shot_reasoning_expands_to_delta_plus_end(manager):
+    """`_reasoning` (no delta/end pair) falls back through `send_reasoning`
+    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 = outbound_message_for_event(
+    msg = OutboundMessage(
         channel="mock",
         chat_id="c1",
-        event=ProgressEvent(content="one-shot reasoning", reasoning=True),
+        content="one-shot reasoning",
+        metadata={"_progress": True, "_reasoning": True},
     )
     await manager._send_once(channel, msg)
     channel._delta_mock.assert_awaited_once()
@@ -140,10 +144,11 @@ async def test_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 = outbound_message_for_event(
+    msg = OutboundMessage(
         channel="mock",
         chat_id="c1",
-        event=ProgressEvent(content="hidden thinking", reasoning_delta=True),
+        content="hidden thinking",
+        metadata={"_progress": True, "_reasoning_delta": True},
     )
     await manager.bus.publish_outbound(msg)
 
@@ -159,15 +164,17 @@ 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(outbound_message_for_event(
+        await manager.bus.publish_outbound(OutboundMessage(
             channel="mock",
             chat_id="c1",
-            event=ProgressEvent(content=chunk, reasoning_delta=True, stream_id="r1"),
+            content=chunk,
+            metadata={"_progress": True, "_reasoning_delta": True, "_stream_id": "r1"},
         ))
-    await manager.bus.publish_outbound(outbound_message_for_event(
+    await manager.bus.publish_outbound(OutboundMessage(
         channel="mock",
         chat_id="c1",
-        event=ProgressEvent(reasoning_end=True, stream_id="r1"),
+        content="",
+        metadata={"_progress": True, "_reasoning_end": True, "_stream_id": "r1"},
     ))
 
     await _pump_one(manager)
@@ -178,10 +185,11 @@ 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 = outbound_message_for_event(
+    msg = OutboundMessage(
         channel="ghost",
         chat_id="c1",
-        event=ProgressEvent(content="nobody home", reasoning_delta=True),
+        content="nobody home",
+        metadata={"_progress": True, "_reasoning_delta": True},
     )
     await manager.bus.publish_outbound(msg)
 
@@ -221,34 +229,17 @@ 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 = outbound_message_for_event(
+    msg = OutboundMessage(
         channel="mock",
         chat_id="c1",
-        event=ProgressEvent(file_edit_events=edits),
+        content="",
+        metadata={"_progress": True, "_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()
-
-
-@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
+        "c1", edits, {"_progress": True, "_file_edit_events": edits}
     )
     channel._send_mock.assert_not_awaited()
 
@@ -279,10 +270,11 @@ 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(outbound_message_for_event(
+    await manager.bus.publish_outbound(OutboundMessage(
         channel="mock",
         chat_id="c1",
-        event=ProgressEvent(content="still surfaces", reasoning_delta=True),
+        content="still surfaces",
+        metadata={"_progress": True, "_reasoning_delta": True},
     ))
 
     await _pump_one(manager)

tests/channels/test_channel_plugins.py

@@ -9,13 +9,6 @@ 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
@@ -725,7 +718,7 @@ 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 for stream delta events."""
+    """_send_with_retry should call send_delta when metadata has _stream_delta."""
     send_delta_called = False
 
     class _StreamingChannel(BaseChannel):
@@ -741,16 +734,7 @@ 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,
-            *,
-            stream_id: str | None = None,
-            stream_end: bool = False,
-            resuming: bool = False,
-        ) -> None:
+        async def send_delta(self, chat_id: str, delta: str, metadata: dict | None = None) -> None:
             nonlocal send_delta_called
             send_delta_called = True
 
@@ -765,147 +749,18 @@ async def test_send_with_retry_calls_send_delta():
     mgr.channels = {"streaming": _StreamingChannel(fake_config, mgr.bus)}
     mgr._dispatch_task = None
 
-    msg = outbound_message_for_event(
-        channel="streaming",
-        chat_id="123",
-        event=StreamDeltaEvent(content="test delta"),
+    msg = OutboundMessage(
+        channel="streaming", chat_id="123", content="test delta",
+        metadata={"_stream_delta": True}
     )
     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 for streamed response events."""
+    """_send_with_retry should not call send when metadata has _streamed flag."""
     send_called = False
     send_delta_called = False
 
@@ -923,16 +778,7 @@ 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,
-            *,
-            stream_id: str | None = None,
-            stream_end: bool = False,
-            resuming: bool = False,
-        ) -> None:
+        async def send_delta(self, chat_id: str, delta: str, metadata: dict | None = None) -> None:
             nonlocal send_delta_called
             send_delta_called = True
 
@@ -947,11 +793,10 @@ async def test_send_with_retry_skips_send_when_streamed():
     mgr.channels = {"streamed": _StreamedChannel(fake_config, mgr.bus)}
     mgr._dispatch_task = None
 
-    msg = outbound_message_for_event(
-        channel="streamed",
-        chat_id="123",
-        event=StreamedResponseEvent(),
-        content="test",
+    # _streamed means message was already sent via send_delta, so skip send
+    msg = OutboundMessage(
+        channel="streamed", chat_id="123", content="test",
+        metadata={"_streamed": True}
     )
     await mgr._send_with_retry(mgr.channels["streamed"], msg)
 

tests/channels/test_discord_channel.py

@@ -10,7 +10,6 @@ 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,
@@ -719,9 +718,9 @@ 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_id="s1")
-    await owner.send_delta("123", "lo", stream_id="s1")
-    await owner.send_delta("123", "", stream_id="s1", stream_end=True)
+    await owner.send_delta("123", "hel", {"_stream_delta": True, "_stream_id": "s1"})
+    await owner.send_delta("123", "lo", {"_stream_delta": True, "_stream_id": "s1"})
+    await owner.send_delta("123", "", {"_stream_end": True, "_stream_id": "s1"})
 
     assert target.sent_payloads[0] == {"content": "hel"}
     assert target.sent_messages[0].edits == [{"content": "hello"}, {"content": "hello"}]
@@ -746,9 +745,9 @@ 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_id="s1")
-    await owner.send_delta("123", suffix, stream_id="s1")
-    await owner.send_delta("123", "", stream_id="s1", stream_end=True)
+    await owner.send_delta("123", prefix, {"_stream_delta": True, "_stream_id": "s1"})
+    await owner.send_delta("123", suffix, {"_stream_delta": True, "_stream_id": "s1"})
+    await owner.send_delta("123", "", {"_stream_end": True, "_stream_id": "s1"})
 
     assert target.sent_payloads == [{"content": prefix}, {"content": chunks[1]}]
     assert target.sent_messages[0].edits == [{"content": chunks[0]}, {"content": chunks[0]}]
@@ -1074,7 +1073,7 @@ async def test_send_stops_typing_after_send() -> None:
             channel="discord",
             chat_id="123",
             content="progress",
-            event=ProgressEvent(content="progress"),
+            metadata={"_progress": True},
         )
     )
 

tests/channels/test_email_channel.py

@@ -6,7 +6,6 @@ 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
 
@@ -869,7 +868,10 @@ async def test_send_skips_progress_messages_before_smtp(monkeypatch) -> None:
             channel="email",
             chat_id="alice@example.com",
             content="",
-            event=ProgressEvent(tool_events=[{"phase": "end", "name": "exec"}]),
+            metadata={
+                "_progress": True,
+                "_tool_events": [{"phase": "end", "name": "exec"}],
+            },
         )
     )
 

tests/channels/test_feishu_reaction.py

@@ -193,8 +193,7 @@ class TestStreamEndReactionCleanup:
 
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"message_id": "om_001"},
-            stream_end=True,
+            metadata={"_stream_end": True, "message_id": "om_001"},
         )
 
         ch._remove_reaction.assert_called_once_with("om_001", "rx_42")
@@ -211,7 +210,7 @@ class TestStreamEndReactionCleanup:
 
         await ch.send_delta(
             "oc_chat1", "",
-            stream_end=True,
+            metadata={"_stream_end": True},
         )
 
         ch._remove_reaction.assert_not_called()
@@ -228,8 +227,7 @@ class TestStreamEndReactionCleanup:
 
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"message_id": "om_001"},
-            stream_end=True,
+            metadata={"_stream_end": True, "message_id": "om_001"},
         )
 
         ch._remove_reaction.assert_not_called()
@@ -244,7 +242,7 @@ 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", "", stream_end=True)
+        await ch.send_delta("oc_chat1", "", metadata={"_stream_end": True})
 
         ch._remove_reaction.assert_not_called()
 
@@ -262,7 +260,7 @@ 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(
@@ -276,9 +274,7 @@ class TestStreamEndReactionCleanup:
 
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"message_id": "om_001"},
-            stream_end=True,
-            resuming=True,
+            metadata={"_stream_end": True, "_resuming": True, "message_id": "om_001"},
         )
 
         ch._remove_reaction.assert_not_called()
@@ -303,23 +299,19 @@ class TestStreamEndReactionCleanup:
         # Intermediate stream end (more tool calls coming).
         await ch.send_delta(
             "oc_chat1", "",
-            metadata={"message_id": "om_001"},
-            stream_end=True,
-            resuming=True,
+            metadata={"_stream_end": True, "_resuming": True, "message_id": "om_001"},
         )
         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={"message_id": "om_001"},
-            stream_end=True,
-            resuming=False,
+            metadata={"_stream_end": True, "_resuming": False, "message_id": "om_001"},
         )
         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

@@ -18,7 +18,6 @@ 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
 
@@ -333,8 +332,7 @@ async def test_send_skips_reply_for_progress_messages() -> None:
         channel="feishu",
         chat_id="oc_abc",
         content="thinking...",
-        event=ProgressEvent(content="thinking..."),
-        metadata={"message_id": "om_001"},
+        metadata={"message_id": "om_001", "_progress": True},
     ))
 
     channel._client.im.v1.message.create.assert_called_once()

tests/channels/test_feishu_streaming.py

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