fix(cli): preserve gateway log stream boundaries

* refactor(agent): extract tool execution boundary

* test(agent): use extracted tool execution boundary

README.md

@@ -146,7 +146,7 @@ Activate it with `source .venv/bin/activate` on macOS/Linux or
 python -m pip install -e .
 ```
 
-After that, the normal commands are identical to a stable install. `nanobot agent` runs the TUI
+After that, the normal commands are identical to a stable install. `nanobot` runs the TUI
 from this checkout, and `nanobot webui` rebuilds stale frontend assets automatically. A later
 `git pull --ff-only` updates the Python, TUI, and WebUI source together; rerun
 `python -m pip install -e .` when Python dependencies change. Contributors should also read
@@ -206,10 +206,10 @@ Use `nanobot gateway --background` for the same direct entry point without keepi
 **Prefer to work entirely in the terminal?**
 
 ```bash
-nanobot agent
+nanobot
 ```
 
-This opens the native terminal client with the launch directory as its workspace. It shares saved conversations and the local gateway with the WebUI.
+This opens the native terminal client with the launch directory as its workspace. It shares saved conversations and the local gateway with the WebUI. The explicit `nanobot agent` form remains available for compatibility.
 
 - Type `/` to discover commands, `/sessions` to switch conversations, or `@` to mention an app, MCP server, or saved session.
 - Press `Enter` to send. While nanobot is working, `Enter` sends now and `Tab` sends after the current response. Press `Shift+Enter` to add a newline (`Ctrl+J` works in terminals that cannot distinguish modified Enter keys).
@@ -220,7 +220,7 @@ Each launch starts a new session by default. Use `--session` to resume one and `
 For one request and an immediate exit, use:
 
 ```bash
-nanobot agent -m "Hello!"
+nanobot -m "Hello!"
 ```
 
 The one-shot form is useful for a quick provider check, shell scripts, and local automation. If you have not configured a model yet, run `nanobot webui` and open **Settings → Models** first.

docs/cli-reference.md

@@ -12,8 +12,8 @@ Use this page when you know what you want to run and need the command shape. For
 | Use guided setup | `nanobot onboard --wizard` | Best when you prefer prompts over hand-editing JSON |
 | Open the browser workbench | `nanobot webui` | Prepares local WebUI settings, starts the gateway, and opens the browser |
 | Check readiness without calling a model | `nanobot status` | Summarizes config/workspace and validates the active provider/model configuration |
-| Send one test message | `nanobot agent -m "Hello!"` | First proof that install, config, provider, model, and workspace all work |
-| Chat in the terminal | `nanobot agent` | Interactive local chat; exit with `exit`, `/exit`, `:q`, or `Ctrl+D` |
+| Send one test message | `nanobot -m "Hello!"` | First proof that install, config, provider, model, and workspace all work |
+| Chat in the terminal | `nanobot` | Interactive local chat; `nanobot agent` remains an explicit alias |
 | Run the gateway directly | `nanobot gateway` | Service/ops command for WebUI, chat apps, cron, and heartbeat |
 | Deliver a local trigger | `nanobot trigger <id> "message"` | Created first with `/trigger <name>` in the target chat/session |
 | Serve an OpenAI-compatible API | `nanobot serve` | Starts `/v1/chat/completions`, `/v1/models`, and `/health` |
@@ -86,15 +86,15 @@ follow the printed WebUI **Settings → Models** or `nanobot onboard --wizard` r
 
 | Command | Description |
 |---|---|
-| `nanobot agent -m "Hello!"` | Send one message and exit |
-| `nanobot agent` | Start interactive terminal chat |
-| `nanobot agent --session <id>` | Use a WebSocket session key; add `--classic` for another channel |
-| `nanobot agent --workspace <path>` | Override workspace |
-| `nanobot agent --config <path>` | Use a specific config file |
-| `nanobot agent --classic` | Use the classic Python prompt instead of the native terminal UI |
-| `nanobot agent --theme auto\|dark\|light` | Auto-detect the terminal appearance or force a TUI palette |
-| `nanobot agent --no-markdown` | Use the classic prompt and print plain text instead of Markdown |
-| `nanobot agent --logs` | Use the classic prompt and show runtime logs while chatting |
+| `nanobot -m "Hello!"` | Send one message and exit |
+| `nanobot` | Start interactive terminal chat |
+| `nanobot --session <id>` | Use a WebSocket session key; add `--classic` for another channel |
+| `nanobot --workspace <path>` | Override workspace |
+| `nanobot --config <path>` | Use a specific config file |
+| `nanobot --classic` | Use the classic Python prompt instead of the native terminal UI |
+| `nanobot --theme auto\|dark\|light` | Auto-detect the terminal appearance or force a TUI palette |
+| `nanobot --no-markdown` | Use the classic prompt and print plain text instead of Markdown |
+| `nanobot --logs` | Use the classic prompt and show runtime logs while chatting |
 
 Inside the native TUI, `/sessions` switches saved conversations, `/new-chat` starts another saved
 conversation, and `/context` explains the compacted summary and raw session suffix available to
@@ -139,7 +139,7 @@ Interactive mode exits with `exit`, `quit`, `/exit`, `/quit`, `:q`, or `Ctrl+D`.
 
 | Command | Description |
 |---|---|
-| `nanobot webui` | Create config/workspace if needed, enable the local WebUI channel after confirmation, start the gateway, and open `http://127.0.0.1:8765` |
+| `nanobot webui` | Create config/workspace if needed, enable the local WebUI channel after confirmation, start the gateway, open `http://127.0.0.1:8765`, and follow new gateway logs |
 | `nanobot webui --background` | Deprecated; prints the equivalent explicit `nanobot gateway --background` command and exits |
 | `nanobot webui --dev` | Start the gateway and Vite together at `http://127.0.0.1:5173`, with live frontend updates |
 | `nanobot webui --no-open` | Prepare and start the WebUI without opening a browser |
@@ -344,7 +344,7 @@ remain accepted as no-op compatibility aliases.
 | Command | Description |
 |---|---|
 | `nanobot provider login openai-codex --set-main` | Authenticate Codex and select its current default model |
-| `nanobot provider login xai-grok --set-main` | Authenticate an eligible X Premium / Grok subscription and select Grok 4.5; hosted X Search is enabled for models that advertise support |
+| `nanobot provider login xai-grok --set-main` | Authenticate an eligible X Premium / Grok subscription and select Grok 4.6; hosted X Search is enabled for models that advertise support |
 | `nanobot provider login github-copilot --set-main` | Authenticate GitHub Copilot and select its current default model |
 | `nanobot provider logout openai-codex` | Remove OpenAI Codex OAuth state |
 | `nanobot provider logout xai-grok --config <path>` | Remove the selected nanobot instance's xAI OAuth state |

docs/configuration.md

@@ -729,6 +729,11 @@ Then run:
 nanobot agent -m "Hello!"
 ```
 
+The WebUI model selector loads the models available to the signed-in account
+from Codex's online catalog. Context-window and reasoning-effort metadata come
+from that response; if discovery is unavailable, nanobot keeps a small built-in
+fallback instead of emptying the selector.
+
 Codex Fast mode can be enabled from the WebUI provider settings, or with:
 
 ```json
@@ -764,11 +769,14 @@ nanobot provider login xai-grok --set-main
 nanobot agent -m "Hello from Grok."
 ```
 
-The default model is `xai-grok/grok-4.5` with a 500,000-token context window.
-The provider reads xAI's model catalog and includes the server-hosted `x_search`
-tool only when the selected model advertises `supportsBackendSearch`. Models
-without that capability continue normally without hosted X Search. When enabled,
-searches run inside xAI's Responses API and citations arrive as inline links.
+The default model is `xai-grok/grok-4.6` with a 500,000-token context window.
+The provider reads and caches xAI's online model catalog for both WebUI model
+selection and runtime capabilities. Newly available models appear automatically;
+when discovery fails, the last successful catalog or built-in fallback remains
+available. The server-hosted `x_search` tool is included only when the selected
+model advertises support. Models without that capability continue normally
+without hosted X Search. When enabled, searches run inside xAI's Responses API
+and citations arrive as inline links.
 Hosted X Search is on by default to preserve this behavior. It can be turned off in the
 WebUI provider settings or with `providers.xaiGrok.extraBody.tools: []`.
 
@@ -805,6 +813,10 @@ a nanobot update.
 
 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.
 
+After login, the WebUI loads the account-specific Copilot model catalog online.
+Only models compatible with nanobot's current chat-completions or Responses
+transport are shown.
+
 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"

docs/providers.md

@@ -572,15 +572,23 @@ For OpenAI Codex:
 nanobot provider login openai-codex --set-main
 ```
 
+The WebUI reads the account's Codex model catalog online, including current
+context-window and reasoning-effort metadata. A small compatible catalog remains
+available when the service cannot be reached.
+
 For an eligible X Premium / Grok subscription:
 
 ```bash
 nanobot provider login xai-grok --set-main
 ```
 
-This selects `xai-grok/grok-4.5`. The provider reads xAI's model catalog and
-exposes the hosted `x_search` tool only when the selected model advertises
-`supportsBackendSearch`; otherwise the model runs without hosted X Search.
+This selects `xai-grok/grok-4.6`. The WebUI model selector reads xAI's online
+model catalog, so newly available subscription models appear without a nanobot
+release. Online metadata is cached and enriched with nanobot's curated labels;
+if xAI is temporarily unavailable, nanobot uses the last successful catalog or
+a small built-in fallback instead of emptying the selector. The same catalog
+controls whether the provider exposes the hosted `x_search` tool; models that do
+not advertise support continue without hosted X Search.
 When enabled, Grok can search current X posts and return inline source links
 without invoking a local nanobot tool. Credentials are stored under the
 active instance's `auth/xai.json` (normally `~/.nanobot/auth/xai.json`), not in
@@ -599,6 +607,10 @@ For GitHub Copilot:
 nanobot provider login github-copilot --set-main
 ```
 
+The WebUI reads the models enabled for the signed-in Copilot account. nanobot
+lists entries that support its current Copilot chat-completions or Responses
+transport and hides models that it cannot route safely.
+
 Each command authenticates the selected provider and makes its current default model active. OpenAI Codex and eligible GitHub Copilot models participate in [Responses state retention](./configuration.md#responses-state-and-compaction), while native compaction remains provider-capability-specific. OAuth providers are not valid automatic fallbacks. See [`troubleshooting.md`](./troubleshooting.md#provider-and-model-problems) for proxy, headless-login, model-name, and config-key errors.
 
 ## Provider Resolution

docs/quick-start.md

@@ -103,13 +103,13 @@ Use `nanobot gateway logs`, `restart`, and `stop` to manage that background gate
 If you do not want the browser or need to isolate a WebUI problem, send one message directly:
 
 ```bash
-nanobot agent -m "Hello!"
+nanobot -m "Hello!"
 ```
 
 Then start an interactive terminal chat with:
 
 ```bash
-nanobot agent
+nanobot
 ```
 
 In interactive mode, `Enter` sends and `Shift+Enter` inserts a newline (`Ctrl+J` is the
@@ -173,7 +173,7 @@ nanobot webui
 ```
 
 The source path follows current `main` and can be newer than the published package. The editable
-install keeps Python pointed at the checkout; `nanobot agent` runs `tui/` with Bun, and
+install keeps Python pointed at the checkout; `nanobot` runs `tui/` with Bun, and
 `nanobot webui` automatically rebuilds `webui/` when its bundled assets are stale. All normal
 commands remain the same as a stable install. For development details, follow
 [`../CONTRIBUTING.md`](../CONTRIBUTING.md).

docs/webui.md

@@ -23,7 +23,9 @@ one is missing, starts or joins the same on-demand gateway used by the native
 TUI, and opens the browser. With a fresh config,
 it can open before a model is configured so you can finish setup in **Settings
 → Models**. The first-run path binds the WebUI to `127.0.0.1` by default, so
-it is not available from other devices on your LAN.
+it is not available from other devices on your LAN. While the launcher remains
+attached, it mirrors new log output from that exact gateway instance in the
+terminal without replaying older logs.
 
 After model setup, explicitly promote the shared gateway when you do not want to keep a client open:
 

nanobot/agent/runner.py

@@ -19,7 +19,8 @@ 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.execution import execute_tool_calls
+from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.llm_usage.context import (
     LLMUsageSource,
     bind_llm_usage_source,
@@ -32,7 +33,6 @@ from nanobot.providers.base import (
     LLMUsage,
     ProviderCallContext,
     ProviderConversationState,
-    ToolCallRequest,
 )
 from nanobot.providers.conversation_state import (
     ProviderConversationStateController,
@@ -60,8 +60,6 @@ from nanobot.utils.runtime import (
     build_finalization_retry_message,
     build_length_recovery_message,
     is_blank_text,
-    repeated_external_lookup_error,
-    repeated_workspace_violation_error,
 )
 
 ContinuationCallback = Callable[[], str | None]
@@ -586,13 +584,14 @@ class AgentRunner:
 
                 await hook.before_execute_tools(context)
 
-                results, new_events = await self._execute_tools(
-                    spec,
+                results, new_events = await execute_tool_calls(
+                    spec.tools,
                     response.tool_calls,
-                    external_lookup_counts,
-                    workspace_violation_counts,
-                    hook,
-                    context,
+                    concurrent=spec.concurrent_tools,
+                    external_lookup_counts=external_lookup_counts,
+                    workspace_violation_counts=workspace_violation_counts,
+                    hook=hook,
+                    context=context,
                 )
                 tool_events.extend(new_events)
                 tools_used.extend(
@@ -1385,253 +1384,6 @@ class AgentRunner:
             return left
         return left + right
 
-    async def _execute_tools(
-        self,
-        spec: AgentRunSpec,
-        tool_calls: list[ToolCallRequest],
-        external_lookup_counts: dict[str, int],
-        workspace_violation_counts: dict[str, int],
-        hook: AgentHook | None = None,
-        context: AgentHookContext | None = None,
-    ) -> tuple[list[Any], list[dict[str, str]]]:
-        hook = hook or AgentHook()
-        context = context or AgentHookContext(iteration=0, messages=[])
-        batches = self._partition_tool_batches(spec, tool_calls)
-        tool_results: list[tuple[Any, dict[str, str]]] = []
-        for batch in batches:
-            if spec.concurrent_tools and len(batch) > 1:
-                batch_results = await asyncio.gather(*(
-                    self._run_tool(
-                        spec,
-                        tool_call,
-                        external_lookup_counts,
-                        workspace_violation_counts,
-                        hook,
-                        context,
-                    )
-                    for tool_call in batch
-                ))
-                tool_results.extend(batch_results)
-            else:
-                batch_results: list[tuple[Any, dict[str, str]]] = []
-                for tool_call in batch:
-                    result = await self._run_tool(
-                        spec,
-                        tool_call,
-                        external_lookup_counts,
-                        workspace_violation_counts,
-                        hook,
-                        context,
-                    )
-                    tool_results.append(result)
-                    batch_results.append(result)
-
-        results: list[Any] = []
-        events: list[dict[str, str]] = []
-        for result, event in tool_results:
-            results.append(result)
-            events.append(event)
-        return results, events
-
-    async def _run_tool(
-        self,
-        spec: AgentRunSpec,
-        tool_call: ToolCallRequest,
-        external_lookup_counts: dict[str, int],
-        workspace_violation_counts: dict[str, int],
-        hook: AgentHook | None = None,
-        context: AgentHookContext | None = None,
-    ) -> tuple[Any, dict[str, str]]:
-        hook = hook or AgentHook()
-        context = context or AgentHookContext(iteration=0, messages=[])
-        hint = "\n\n[Analyze the error above and try a different approach.]"
-        lookup_error = repeated_external_lookup_error(
-            tool_call.name,
-            tool_call.arguments,
-            external_lookup_counts,
-        )
-        if lookup_error:
-            event = {
-                "name": tool_call.name,
-                "status": "error",
-                "detail": "repeated external lookup blocked",
-            }
-            return lookup_error + hint, event
-        prepare_call = cast(
-            Callable[[str, Any], object] | None,
-            getattr(spec.tools, "prepare_call", None),
-        )
-        tool, params, prep_error = None, tool_call.arguments, None
-        if callable(prepare_call):
-            prepared = prepare_call(tool_call.name, tool_call.arguments)
-            if isinstance(prepared, tuple):
-                prepared_tuple = cast(tuple[object, ...], prepared)
-                if len(prepared_tuple) == 3:
-                    tool, params, prep_error = cast(tuple[Any, Any, str | None], prepared_tuple)
-        if prep_error:
-            event = {
-                "name": tool_call.name,
-                "status": "error",
-                "detail": prep_error.split(": ", 1)[-1][:120],
-            }
-            handled = self._classify_violation(
-                raw_text=prep_error,
-                soft_payload=prep_error + hint,
-                event=event,
-                tool_call=tool_call,
-                workspace_violation_counts=workspace_violation_counts,
-            )
-            if handled is not None:
-                return handled
-            return prep_error + hint, event
-        await hook.before_execute_tool(context, tool_call, tool, params)
-        try:
-            if tool is not None:
-                result = await tool.execute(**params)
-            else:
-                result = await spec.tools.execute(tool_call.name, params)
-        except asyncio.CancelledError:
-            raise
-        except Exception as exc:
-            await hook.on_execute_tool_error(context, tool_call, tool, params, exc)
-            event = {
-                "name": tool_call.name,
-                "status": "error",
-                "detail": str(exc),
-            }
-            payload = f"Error: {type(exc).__name__}: {exc}"
-            handled = self._classify_violation(
-                raw_text=str(exc),
-                # Preserve legacy exception payloads without the retry hint.
-                soft_payload=payload,
-                event=event,
-                tool_call=tool_call,
-                workspace_violation_counts=workspace_violation_counts,
-            )
-            if handled is not None:
-                return handled
-            return payload, event
-
-        if is_tool_error_result(result):
-            await hook.on_execute_tool_error(context, tool_call, tool, params, result)
-            event = {
-                "name": tool_call.name,
-                "status": "error",
-                "detail": result.replace("\n", " ").strip()[:120],
-            }
-            handled = self._classify_violation(
-                raw_text=result,
-                soft_payload=result + hint,
-                event=event,
-                tool_call=tool_call,
-                workspace_violation_counts=workspace_violation_counts,
-            )
-            if handled is not None:
-                return handled
-            return result + hint, event
-
-        await hook.after_execute_tool(context, tool_call, tool, params, result)
-
-        detail = "" if result is None else str(result)
-        detail = detail.replace("\n", " ").strip()
-        if not detail:
-            detail = "(empty)"
-        elif len(detail) > 120:
-            detail = detail[:120] + "..."
-        return result, {"name": tool_call.name, "status": "ok", "detail": detail}
-
-    # SSRF is a hard security block at the tool boundary, but the agent turn
-    # should recover conversationally instead of aborting the runtime.
-    _SSRF_MARKERS: tuple[str, ...] = (
-        "internal/private url detected",
-        "private/internal address",
-        "private address",
-    )
-    _SSRF_BOUNDARY_NOTE: str = (
-        "This is a non-bypassable security boundary. Stop trying to access "
-        "private/internal URLs. Do not retry with curl, wget, encoded IPs, "
-        "alternate DNS, redirects, proxies, or another tool. Ask the user for "
-        "local files, logs, screenshots, or an explicit safe public URL instead. "
-        "If the user explicitly trusts this private URL, ask them to whitelist "
-        "the exact IP/CIDR via tools.ssrfWhitelist."
-    )
-
-    # Non-SSRF boundary markers returned to the LLM as recoverable tool errors.
-    _WORKSPACE_VIOLATION_MARKERS: tuple[str, ...] = (
-        "outside the configured workspace",
-        "outside allowed directory",
-        "working_dir is outside",
-        "working_dir could not be resolved",
-        "path outside working dir",
-        "path traversal detected",
-    )
-
-    @classmethod
-    def _is_ssrf_violation(cls, text: str) -> bool:
-        if not text:
-            return False
-        lowered = text.lower()
-        return any(marker in lowered for marker in cls._SSRF_MARKERS)
-
-    @classmethod
-    def _is_workspace_violation(cls, text: str) -> bool:
-        """True when *text* looks like any policy boundary rejection."""
-        if not text:
-            return False
-        lowered = text.lower()
-        if cls._is_ssrf_violation(lowered):
-            return True
-        return any(marker in lowered for marker in cls._WORKSPACE_VIOLATION_MARKERS)
-
-    def _classify_violation(
-        self,
-        *,
-        raw_text: str,
-        soft_payload: str,
-        event: dict[str, str],
-        tool_call: ToolCallRequest,
-        workspace_violation_counts: dict[str, int],
-    ) -> tuple[Any, dict[str, str]] | None:
-        """Classify safety-boundary failures, or return ``None`` to pass through."""
-        if self._is_ssrf_violation(raw_text):
-            logger.warning(
-                "Tool {} blocked by SSRF guard; returning non-retryable tool error: {}",
-                tool_call.name,
-                raw_text.replace("\n", " ").strip()[:200],
-            )
-            event["detail"] = self._event_detail("ssrf_violation: ", raw_text)
-            return self._ssrf_soft_payload(raw_text), event
-
-        if self._is_workspace_violation(raw_text):
-            escalation = repeated_workspace_violation_error(
-                tool_call.name,
-                tool_call.arguments,
-                workspace_violation_counts,
-            )
-            event["detail"] = self._event_detail("workspace_violation: ", raw_text)
-            if escalation is not None:
-                logger.warning(
-                    "Tool {} hit workspace boundary repeatedly; escalating hint",
-                    tool_call.name,
-                )
-                event["detail"] = self._event_detail(
-                    "workspace_violation_escalated: ",
-                    raw_text,
-                )
-                return escalation, event
-            return soft_payload, event
-
-        return None
-
-    @classmethod
-    def _ssrf_soft_payload(cls, raw_text: str) -> str:
-        text = raw_text.strip() or "Error: request blocked by SSRF guard"
-        return f"{text}\n\n{cls._SSRF_BOUNDARY_NOTE}"
-
-    @staticmethod
-    def _event_detail(prefix: str, text: str, limit: int = 160) -> str:
-        return (prefix + text.replace("\n", " ").strip())[:limit]
-
     async def _emit_checkpoint(
         self,
         spec: AgentRunSpec,
@@ -1661,28 +1413,3 @@ class AgentRunner:
         if messages and messages[-1].get("role") == "assistant" and not messages[-1].get("tool_calls"):
             return
         messages.append(build_assistant_message(_PERSISTED_MODEL_ERROR_PLACEHOLDER))
-
-    def _partition_tool_batches(
-        self,
-        spec: AgentRunSpec,
-        tool_calls: list[ToolCallRequest],
-    ) -> list[list[ToolCallRequest]]:
-        if not spec.concurrent_tools:
-            return [[tool_call] for tool_call in tool_calls]
-
-        batches: list[list[ToolCallRequest]] = []
-        current: list[ToolCallRequest] = []
-        for tool_call in tool_calls:
-            get_tool = cast(Callable[[str], Any] | None, getattr(spec.tools, "get", None))
-            tool = get_tool(tool_call.name) if callable(get_tool) else None
-            can_batch = bool(tool and tool.concurrency_safe)
-            if can_batch:
-                current.append(tool_call)
-                continue
-            if current:
-                batches.append(current)
-                current = []
-            batches.append([tool_call])
-        if current:
-            batches.append(current)
-        return batches

nanobot/agent/tools/execution.py

@@ -0,0 +1,285 @@
+"""Execute tool calls and turn their outcomes into model observations."""
+
+from __future__ import annotations
+
+import asyncio
+from collections.abc import Callable
+from typing import Any, cast
+
+from loguru import logger
+
+from nanobot.agent.hook import AgentHook, AgentHookContext
+from nanobot.agent.tools.registry import ToolRegistry, is_tool_error_result
+from nanobot.providers.base import ToolCallRequest
+from nanobot.utils.runtime import (
+    repeated_external_lookup_error,
+    repeated_workspace_violation_error,
+)
+
+_RETRY_HINT = "\n\n[Analyze the error above and try a different approach.]"
+# SSRF is a hard security block at the tool boundary, but the agent turn
+# should recover conversationally instead of aborting the runtime.
+_SSRF_MARKERS: tuple[str, ...] = (
+    "internal/private url detected",
+    "private/internal address",
+    "private address",
+)
+_SSRF_BOUNDARY_NOTE = (
+    "This is a non-bypassable security boundary. Stop trying to access "
+    "private/internal URLs. Do not retry with curl, wget, encoded IPs, "
+    "alternate DNS, redirects, proxies, or another tool. Ask the user for "
+    "local files, logs, screenshots, or an explicit safe public URL instead. "
+    "If the user explicitly trusts this private URL, ask them to whitelist "
+    "the exact IP/CIDR via tools.ssrfWhitelist."
+)
+# Non-SSRF boundary markers returned to the model as recoverable tool errors.
+_WORKSPACE_VIOLATION_MARKERS: tuple[str, ...] = (
+    "outside the configured workspace",
+    "outside allowed directory",
+    "working_dir is outside",
+    "working_dir could not be resolved",
+    "path outside working dir",
+    "path traversal detected",
+)
+
+
+async def execute_tool_calls(
+    tools: ToolRegistry,
+    tool_calls: list[ToolCallRequest],
+    *,
+    concurrent: bool,
+    external_lookup_counts: dict[str, int],
+    workspace_violation_counts: dict[str, int],
+    hook: AgentHook,
+    context: AgentHookContext,
+) -> tuple[list[Any], list[dict[str, str]]]:
+    """Execute one model response's tool calls in stable result order."""
+    tool_results: list[tuple[Any, dict[str, str]]] = []
+    for batch in _partition_tool_batches(tools, tool_calls, concurrent=concurrent):
+        if concurrent and len(batch) > 1:
+            batch_results = await asyncio.gather(*(
+                _execute_tool_call(
+                    tools,
+                    tool_call,
+                    external_lookup_counts,
+                    workspace_violation_counts,
+                    hook,
+                    context,
+                )
+                for tool_call in batch
+            ))
+            tool_results.extend(batch_results)
+        else:
+            for tool_call in batch:
+                result = await _execute_tool_call(
+                    tools,
+                    tool_call,
+                    external_lookup_counts,
+                    workspace_violation_counts,
+                    hook,
+                    context,
+                )
+                tool_results.append(result)
+
+    results = [result for result, _event in tool_results]
+    events = [event for _result, event in tool_results]
+    return results, events
+
+
+async def _execute_tool_call(
+    tools: ToolRegistry,
+    tool_call: ToolCallRequest,
+    external_lookup_counts: dict[str, int],
+    workspace_violation_counts: dict[str, int],
+    hook: AgentHook,
+    context: AgentHookContext,
+) -> tuple[Any, dict[str, str]]:
+    lookup_error = repeated_external_lookup_error(
+        tool_call.name,
+        tool_call.arguments,
+        external_lookup_counts,
+    )
+    if lookup_error:
+        event = {
+            "name": tool_call.name,
+            "status": "error",
+            "detail": "repeated external lookup blocked",
+        }
+        return lookup_error + _RETRY_HINT, event
+
+    prepare_call = cast(
+        Callable[[str, Any], object] | None,
+        getattr(tools, "prepare_call", None),
+    )
+    tool, params, prep_error = None, tool_call.arguments, None
+    if callable(prepare_call):
+        prepared = prepare_call(tool_call.name, tool_call.arguments)
+        if isinstance(prepared, tuple):
+            prepared_tuple = cast(tuple[object, ...], prepared)
+            if len(prepared_tuple) == 3:
+                tool, params, prep_error = cast(tuple[Any, Any, str | None], prepared_tuple)
+    if prep_error:
+        event = {
+            "name": tool_call.name,
+            "status": "error",
+            "detail": prep_error.split(": ", 1)[-1][:120],
+        }
+        handled = _classify_violation(
+            raw_text=prep_error,
+            soft_payload=prep_error + _RETRY_HINT,
+            event=event,
+            tool_call=tool_call,
+            workspace_violation_counts=workspace_violation_counts,
+        )
+        if handled is not None:
+            return handled
+        return prep_error + _RETRY_HINT, event
+
+    await hook.before_execute_tool(context, tool_call, tool, params)
+    try:
+        if tool is not None:
+            result = await tool.execute(**params)
+        else:
+            result = await tools.execute(tool_call.name, params)
+    except asyncio.CancelledError:
+        raise
+    except Exception as exc:
+        await hook.on_execute_tool_error(context, tool_call, tool, params, exc)
+        event = {
+            "name": tool_call.name,
+            "status": "error",
+            "detail": str(exc),
+        }
+        payload = f"Error: {type(exc).__name__}: {exc}"
+        handled = _classify_violation(
+            raw_text=str(exc),
+            # Preserve legacy exception payloads without the retry hint.
+            soft_payload=payload,
+            event=event,
+            tool_call=tool_call,
+            workspace_violation_counts=workspace_violation_counts,
+        )
+        if handled is not None:
+            return handled
+        return payload, event
+
+    if is_tool_error_result(result):
+        await hook.on_execute_tool_error(context, tool_call, tool, params, result)
+        event = {
+            "name": tool_call.name,
+            "status": "error",
+            "detail": result.replace("\n", " ").strip()[:120],
+        }
+        handled = _classify_violation(
+            raw_text=result,
+            soft_payload=result + _RETRY_HINT,
+            event=event,
+            tool_call=tool_call,
+            workspace_violation_counts=workspace_violation_counts,
+        )
+        if handled is not None:
+            return handled
+        return result + _RETRY_HINT, event
+
+    await hook.after_execute_tool(context, tool_call, tool, params, result)
+
+    detail = "" if result is None else str(result)
+    detail = detail.replace("\n", " ").strip()
+    if not detail:
+        detail = "(empty)"
+    elif len(detail) > 120:
+        detail = detail[:120] + "..."
+    return result, {"name": tool_call.name, "status": "ok", "detail": detail}
+
+
+def is_ssrf_violation(text: str) -> bool:
+    """Return whether a tool error describes a blocked private-network request."""
+    if not text:
+        return False
+    lowered = text.lower()
+    return any(marker in lowered for marker in _SSRF_MARKERS)
+
+
+def _is_workspace_violation(text: str) -> bool:
+    """Return whether text describes any workspace or network boundary rejection."""
+    if not text:
+        return False
+    lowered = text.lower()
+    if is_ssrf_violation(lowered):
+        return True
+    return any(marker in lowered for marker in _WORKSPACE_VIOLATION_MARKERS)
+
+
+def _classify_violation(
+    *,
+    raw_text: str,
+    soft_payload: str,
+    event: dict[str, str],
+    tool_call: ToolCallRequest,
+    workspace_violation_counts: dict[str, int],
+) -> tuple[Any, dict[str, str]] | None:
+    if is_ssrf_violation(raw_text):
+        logger.warning(
+            "Tool {} blocked by SSRF guard; returning non-retryable tool error: {}",
+            tool_call.name,
+            raw_text.replace("\n", " ").strip()[:200],
+        )
+        event["detail"] = _event_detail("ssrf_violation: ", raw_text)
+        return _ssrf_soft_payload(raw_text), event
+
+    if _is_workspace_violation(raw_text):
+        escalation = repeated_workspace_violation_error(
+            tool_call.name,
+            tool_call.arguments,
+            workspace_violation_counts,
+        )
+        event["detail"] = _event_detail("workspace_violation: ", raw_text)
+        if escalation is not None:
+            logger.warning(
+                "Tool {} hit workspace boundary repeatedly; escalating hint",
+                tool_call.name,
+            )
+            event["detail"] = _event_detail(
+                "workspace_violation_escalated: ",
+                raw_text,
+            )
+            return escalation, event
+        return soft_payload, event
+
+    return None
+
+
+def _ssrf_soft_payload(raw_text: str) -> str:
+    text = raw_text.strip() or "Error: request blocked by SSRF guard"
+    return f"{text}\n\n{_SSRF_BOUNDARY_NOTE}"
+
+
+def _event_detail(prefix: str, text: str, limit: int = 160) -> str:
+    return (prefix + text.replace("\n", " ").strip())[:limit]
+
+
+def _partition_tool_batches(
+    tools: ToolRegistry,
+    tool_calls: list[ToolCallRequest],
+    *,
+    concurrent: bool,
+) -> list[list[ToolCallRequest]]:
+    if not concurrent:
+        return [[tool_call] for tool_call in tool_calls]
+
+    batches: list[list[ToolCallRequest]] = []
+    current: list[ToolCallRequest] = []
+    for tool_call in tool_calls:
+        get_tool = cast(Callable[[str], Any] | None, getattr(tools, "get", None))
+        tool = get_tool(tool_call.name) if callable(get_tool) else None
+        can_batch = bool(tool and tool.concurrency_safe)
+        if can_batch:
+            current.append(tool_call)
+            continue
+        if current:
+            batches.append(current)
+            current = []
+        batches.append([tool_call])
+    if current:
+        batches.append(current)
+    return batches

nanobot/cli/commands.py

@@ -87,7 +87,12 @@ app = typer.Typer(
     name="nanobot",
     context_settings={"help_option_names": ["-h", "--help"]},
     help=f"{__logo__} nanobot - Personal AI Assistant",
-    no_args_is_help=True,
+    epilog=(
+        "Run `nanobot` without a subcommand to start the terminal agent. "
+        "Use `nanobot agent --help` for agent options."
+    ),
+    invoke_without_command=True,
+    no_args_is_help=False,
 )
 
 console = Console()
@@ -98,7 +103,7 @@ def version_callback(value: bool):
         raise typer.Exit()
 
 
-@app.callback()
+@app.callback(invoke_without_command=True)
 def main(
     ctx: typer.Context,
     version: bool = typer.Option(
@@ -110,7 +115,11 @@ def main(
     # imports this Typer app directly instead of ``nanobot.cli.entry``. Keep the
     # role identity correct until that launcher is regenerated.
     command = ctx.invoked_subcommand
-    set_cli_process_identity([command] if command else sys.argv[1:])
+    set_cli_process_identity([command] if command else ["agent"])
+    if command is None:
+        from nanobot.cli.entry import _run_agent
+
+        _run_agent([], prog_name="nanobot")
 
 
 # ============================================================================

nanobot/cli/entry.py

@@ -8,6 +8,28 @@ from contextlib import suppress
 
 from nanobot.cli.process_identity import set_cli_process_identity
 
+_ROOT_OPTIONS = frozenset(
+    {
+        "-h",
+        "--help",
+        "-v",
+        "--version",
+        "--install-completion",
+        "--show-completion",
+    }
+)
+
+
+def _agent_invocation_args(args: list[str]) -> list[str] | None:
+    """Return agent arguments when the root command should act as ``agent``."""
+    if not args:
+        return []
+    if args[0] == "agent":
+        return args[1:]
+    if args[0].startswith("-") and args[0].split("=", 1)[0] not in _ROOT_OPTIONS:
+        return args
+    return None
+
 
 def _native_tui_candidate(args: list[str]) -> bool:
     """Return whether ``agent`` can start without the classic agent stack."""
@@ -34,19 +56,35 @@ def _configure_windows_console() -> None:
                 reconfigure(encoding="utf-8", errors="replace")
 
 
-def main() -> None:
-    """Dispatch native TUI startup without importing the complete CLI graph."""
-    set_cli_process_identity(sys.argv[1:])
-    _configure_windows_console()
-    if _native_tui_candidate(sys.argv[1:]):
+def _run_agent(args: list[str], *, prog_name: str) -> None:
+    """Run the shared agent command without importing the complete CLI graph."""
     import typer
 
     from nanobot.cli.agent import agent
 
-        fast_app = typer.Typer(add_completion=False)
-        fast_app.command()(agent)
-        command = typer.main.get_command(fast_app)
-        command.main(args=sys.argv[2:], prog_name="nanobot agent")
+    agent_app = typer.Typer(add_completion=False)
+    agent_app.command()(agent)
+    command = typer.main.get_command(agent_app)
+    command.main(args=args, prog_name=prog_name)
+
+
+def main() -> None:
+    """Dispatch native TUI startup without importing the complete CLI graph."""
+    raw_args = sys.argv[1:]
+    # Installed completion scripts call ``nanobot`` without positional arguments
+    # and pass the request through this environment variable. Keep those requests
+    # on the root command so subcommands remain discoverable.
+    shell_completion = bool(os.environ.get("_NANOBOT_COMPLETE"))
+    agent_args = None if shell_completion else _agent_invocation_args(raw_args)
+    dispatch_args = ["agent", *agent_args] if agent_args is not None else raw_args
+    set_cli_process_identity(dispatch_args)
+    _configure_windows_console()
+    root_agent_alias = agent_args is not None and raw_args[:1] != ["agent"]
+    if agent_args is not None and (
+        root_agent_alias or _native_tui_candidate(dispatch_args)
+    ):
+        prog_name = "nanobot" if root_agent_alias else "nanobot agent"
+        _run_agent(agent_args, prog_name=prog_name)
         return
 
     from nanobot.cli.commands import app

nanobot/cli/provider.py

@@ -29,7 +29,7 @@ _PROVIDER_DISPLAY: dict[str, str] = {
 
 _OAUTH_PROVIDER_DEFAULT_MODELS: dict[str, str] = {
     "openai_codex": "openai-codex/gpt-5.6-sol",
-    "xai_grok": "xai-grok/grok-4.5",
+    "xai_grok": "xai-grok/grok-4.6",
     "github_copilot": "github-copilot/gpt-5.4-mini",
 }
 
@@ -134,7 +134,10 @@ def _set_oauth_provider_as_main(
     config.agents.defaults.model_preset = None
     config.agents.defaults.provider = provider_name
     config.agents.defaults.model = selected_model
-    if provider_name == "xai_grok" and selected_model == "xai-grok/grok-4.5":
+    if provider_name == "xai_grok" and selected_model in {
+        "xai-grok/grok-4.5",
+        "xai-grok/grok-4.6",
+    }:
         config.agents.defaults.context_window_tokens = 500_000
     save_config(config, resolved_config_path)
 

nanobot/cli/webui_support.py

@@ -1,12 +1,14 @@
 """Shared WebUI setup, URL, health, and browser helpers."""
 
+import os
 import subprocess
 import sys
 import time
 import webbrowser
 from collections.abc import Callable
+from dataclasses import dataclass
 from pathlib import Path
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING, Any, BinaryIO
 
 import typer
 from pydantic import ValidationError
@@ -457,27 +459,104 @@ def _print_webui_foreground_lifecycle(*, attached: bool) -> None:
         console.print("[green]WebUI is attached to the shared gateway.[/green]")
     console.print("[dim]Closing the browser does not stop channels or automations.[/dim]")
     console.print(
-        "[dim]Press Ctrl+C to detach; the gateway stops only when the last local client exits.[/dim]"
+        "[dim]Following live gateway logs. Press Ctrl+C to detach; the gateway stops "
+        "only when the last local client exits.[/dim]"
     )
 
 
+_LOG_ANCHOR_BYTES = 64
+
+
+@dataclass
+class _GatewayLogCursor:
+    offset: int = 0
+    identity: tuple[int, int] | None = None
+    anchor: bytes = b""
+    pending: bytes = b""
+
+
+def _log_anchor(handle: BinaryIO, offset: int) -> bytes:
+    size = min(offset, _LOG_ANCHOR_BYTES)
+    handle.seek(offset - size)
+    return handle.read(size)
+
+
+def _start_gateway_log_cursor(log_path: Path) -> _GatewayLogCursor:
+    """Start following at the current end of *log_path*."""
+    try:
+        with log_path.open("rb") as handle:
+            stat = os.fstat(handle.fileno())
+            offset = stat.st_size
+            return _GatewayLogCursor(
+                offset=offset,
+                identity=(stat.st_dev, stat.st_ino),
+                anchor=_log_anchor(handle, offset),
+            )
+    except OSError:
+        return _GatewayLogCursor()
+
+
+def _read_new_gateway_logs(
+    log_path: Path,
+    cursor: _GatewayLogCursor,
+    *,
+    flush: bool = False,
+) -> list[str]:
+    """Read complete gateway log lines appended after *cursor*."""
+    try:
+        with log_path.open("rb") as handle:
+            stat = os.fstat(handle.fileno())
+            identity = (stat.st_dev, stat.st_ino)
+            reset = cursor.identity != identity or stat.st_size < cursor.offset
+            if not reset and cursor.offset:
+                reset = _log_anchor(handle, cursor.offset) != cursor.anchor
+            if reset:
+                cursor.offset = 0
+                cursor.pending = b""
+
+            handle.seek(cursor.offset)
+            chunk = handle.read()
+            cursor.offset = handle.tell()
+            cursor.identity = identity
+            cursor.anchor = _log_anchor(handle, cursor.offset)
+    except OSError:
+        return []
+
+    parts = (cursor.pending + chunk).split(b"\n")
+    cursor.pending = parts.pop()
+    if flush and cursor.pending:
+        parts.append(cursor.pending)
+        cursor.pending = b""
+    return [part.removesuffix(b"\r").decode("utf-8", errors="replace") for part in parts]
+
+
 def _attach_to_background_gateway(
     runtime: "GatewayRuntime",
     *,
     poll_hook: Callable[[], None] | None = None,
     sleep: Callable[[float], None] = time.sleep,
 ) -> None:
-    """Keep a WebUI launcher attached without taking ownership of the gateway."""
+    """Keep the launcher attached and mirror this gateway's new log output."""
+    status = runtime.status()
+    log_path = status.log_path
+    cursor = _start_gateway_log_cursor(log_path)
     _print_webui_foreground_lifecycle(attached=True)
     try:
-        while runtime.status().running:
+        while status.running:
+            for line in _read_new_gateway_logs(log_path, cursor):
+                console.print(line, markup=False, highlight=False)
             if poll_hook is not None:
                 poll_hook()
             sleep(0.5)
+            status = runtime.status()
     except KeyboardInterrupt:
+        for line in _read_new_gateway_logs(log_path, cursor, flush=True):
+            console.print(line, markup=False, highlight=False)
         console.print("\n[yellow]WebUI launcher detached.[/yellow]")
         return
 
+    for line in _read_new_gateway_logs(log_path, cursor, flush=True):
+        console.print(line, markup=False, highlight=False)
     console.print("[yellow]Gateway stopped.[/yellow]")
 
 

nanobot/providers/github_copilot_provider.py

@@ -5,6 +5,7 @@
 from __future__ import annotations
 
 import asyncio
+import hashlib
 import os
 import time
 import webbrowser
@@ -17,7 +18,12 @@ from oauth_cli_kit.models import OAuthToken
 from oauth_cli_kit.storage import FileTokenStorage
 
 from nanobot.providers.base import LLMResponse, ProviderCallContext
+from nanobot.providers.oauth_model_catalog import (
+    OAuthModelCatalog,
+    OAuthModelCatalogSnapshot,
+)
 from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+from nanobot.providers.registry import ProviderModelSpec, find_by_name
 
 DEFAULT_GITHUB_DEVICE_CODE_URL = "https://github.com/login/device/code"
 DEFAULT_GITHUB_ACCESS_TOKEN_URL = "https://github.com/login/oauth/access_token"
@@ -96,7 +102,9 @@ def login_github_copilot(
 
         device_code = str(payload["device_code"])
         user_code = str(payload["user_code"])
-        verify_url = str(payload.get("verification_uri") or payload.get("verification_uri_complete") or "")
+        verify_url = str(
+            payload.get("verification_uri") or payload.get("verification_uri_complete") or ""
+        )
         verify_complete = str(payload.get("verification_uri_complete") or verify_url)
         interval = max(1, int(payload.get("interval") or 5))
         expires_in = int(payload.get("expires_in") or 900)
@@ -180,8 +188,6 @@ class GitHubCopilotProvider(OpenAICompatProvider):
         *,
         provider_name: str = "github_copilot",
     ):
-        from nanobot.providers.registry import find_by_name
-
         self._copilot_access_token: str | None = None
         self._copilot_expires_at: float = 0.0
         self._copilot_token_lock: asyncio.Lock = asyncio.Lock()
@@ -217,7 +223,9 @@ 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:
+            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),
                     headers=_copilot_headers(github_token.access),
@@ -296,3 +304,174 @@ class GitHubCopilotProvider(OpenAICompatProvider):
             on_tool_call_delta=on_tool_call_delta,
             provider_context=provider_context,
         )
+
+
+def get_github_copilot_model_catalog(
+    proxy: str | None = None,
+) -> OAuthModelCatalogSnapshot:
+    storage = get_storage()
+    token = storage.load()
+    account_key = _catalog_account_key(getattr(token, "account_id", None))
+    cache_key = (
+        f"{storage.get_token_path()}\0{account_key}\0"
+        f"{_resolve('NANOBOT_COPILOT_BASE_URL', DEFAULT_COPILOT_BASE_URL)}\0{proxy or ''}"
+    )
+    return _GITHUB_COPILOT_MODEL_CATALOG.get(cache_key=cache_key, proxy=proxy)
+
+
+def invalidate_github_copilot_model_catalog() -> None:
+    _GITHUB_COPILOT_MODEL_CATALOG.invalidate()
+
+
+def _fetch_github_copilot_models(proxy: str | None) -> tuple[ProviderModelSpec, ...]:
+    github_token = get_storage().load()
+    if not github_token or not github_token.access:
+        raise RuntimeError("GitHub Copilot is not logged in")
+
+    common_headers = {
+        "Accept": "application/json",
+        "User-Agent": USER_AGENT,
+        "Editor-Version": EDITOR_VERSION,
+        "Editor-Plugin-Version": EDITOR_PLUGIN_VERSION,
+    }
+    client_kwargs: dict[str, Any] = {"timeout": 20.0, "follow_redirects": True}
+    if proxy:
+        client_kwargs.update(proxy=proxy, trust_env=False)
+    with httpx.Client(**client_kwargs) as client:
+        exchange = client.get(
+            _resolve("NANOBOT_COPILOT_TOKEN_URL", DEFAULT_COPILOT_TOKEN_URL),
+            headers={**common_headers, "Authorization": f"token {github_token.access}"},
+        )
+        exchange.raise_for_status()
+        exchange_mapping = _catalog_mapping(exchange.json())
+        copilot_token = exchange_mapping.get("token")
+        if not isinstance(copilot_token, str) or not copilot_token:
+            raise RuntimeError("GitHub Copilot token exchange returned no token")
+        endpoint_base = _catalog_first_text(
+            _catalog_mapping(exchange_mapping.get("endpoints")),
+            "api",
+        )
+        base_url = endpoint_base or _resolve(
+            "NANOBOT_COPILOT_BASE_URL",
+            DEFAULT_COPILOT_BASE_URL,
+        )
+        models_url = (
+            base_url
+            if base_url.rstrip("/").endswith("/models")
+            else f"{base_url.rstrip('/')}/models"
+        )
+        response = client.get(
+            models_url,
+            headers={**common_headers, "Authorization": f"Bearer {copilot_token}"},
+        )
+    response.raise_for_status()
+    return _parse_github_copilot_models(response.json())
+
+
+def _parse_github_copilot_models(payload: Any) -> tuple[ProviderModelSpec, ...]:
+    rows = cast(dict[str, Any], payload).get("data") if isinstance(payload, dict) else None
+    if not isinstance(rows, list):
+        return ()
+
+    fallback_models = _oauth_fallback_models("github_copilot")
+    fallback_by_id = {model.id.split("/", 1)[-1]: model for model in fallback_models}
+    models: list[ProviderModelSpec] = []
+    seen: set[str] = set()
+    for value in cast(list[object], rows):
+        if not isinstance(value, dict):
+            continue
+        row = cast(dict[str, Any], value)
+        wire_id = _catalog_first_text(row, "id")
+        policy = _catalog_mapping(row.get("policy"))
+        endpoints = row.get("supported_endpoints")
+        if (
+            not wire_id
+            or wire_id in seen
+            or row.get("model_picker_enabled") is not True
+            or policy.get("state") == "disabled"
+            or not _copilot_transport_supported(wire_id, endpoints)
+        ):
+            continue
+        seen.add(wire_id)
+        capabilities = _catalog_mapping(row.get("capabilities"))
+        supports = _catalog_mapping(capabilities.get("supports"))
+        limits = _catalog_mapping(capabilities.get("limits"))
+        fallback = fallback_by_id.get(wire_id)
+        models.append(
+            ProviderModelSpec(
+                id=f"github-copilot/{wire_id}",
+                label=(
+                    _catalog_first_text(row, "name")
+                    or (fallback.label if fallback is not None else wire_id)
+                ),
+                description=(fallback.description if fallback is not None else ""),
+                owned_by="GitHub Copilot",
+                context_window=(
+                    _catalog_positive_int(limits, "max_context_window_tokens")
+                    or (fallback.context_window if fallback is not None else None)
+                ),
+                reasoning_efforts=_catalog_reasoning_efforts(supports.get("reasoning_effort")),
+            )
+        )
+    return tuple(models)
+
+
+def _copilot_transport_supported(wire_id: str, endpoints: object) -> bool:
+    if not isinstance(endpoints, list):
+        return True
+    supported = cast(list[object], endpoints)
+    if "/chat/completions" in supported:
+        return True
+    model = wire_id.lower()
+    return "/responses" in supported and any(
+        token in model for token in ("gpt-5", "o1", "o3", "o4")
+    )
+
+
+def _oauth_fallback_models(provider_name: str) -> tuple[ProviderModelSpec, ...]:
+    spec = find_by_name(provider_name)
+    assert spec is not None
+    return spec.builtin_models
+
+
+def _catalog_account_key(account_id: object) -> str:
+    value = account_id if isinstance(account_id, str) else ""
+    return hashlib.sha256(value.encode()).hexdigest()[:16] if value else "anonymous"
+
+
+def _catalog_mapping(value: Any) -> dict[str, Any]:
+    return cast(dict[str, Any], value) if isinstance(value, dict) else {}
+
+
+def _catalog_first_text(row: dict[str, Any], *keys: str) -> str:
+    for key in keys:
+        value = row.get(key)
+        if isinstance(value, str) and value.strip():
+            return value.strip()
+    return ""
+
+
+def _catalog_positive_int(row: dict[str, Any], *keys: str) -> int | None:
+    for key in keys:
+        value = row.get(key)
+        if isinstance(value, (int, float)) and not isinstance(value, bool) and value > 0:
+            return int(value)
+    return None
+
+
+def _catalog_reasoning_efforts(value: Any) -> tuple[str, ...]:
+    if not isinstance(value, list):
+        return ()
+    return tuple(
+        dict.fromkeys(
+            item.strip()
+            for item in cast(list[object], value)
+            if isinstance(item, str) and item.strip()
+        )
+    )
+
+
+_GITHUB_COPILOT_MODEL_CATALOG = OAuthModelCatalog(
+    fallback_models=_oauth_fallback_models("github_copilot"),
+    fetch=_fetch_github_copilot_models,
+)

nanobot/providers/oauth_model_catalog.py

@@ -0,0 +1,224 @@
+"""Shared cache seam for OAuth provider model discovery."""
+
+from __future__ import annotations
+
+import threading
+import time
+from collections.abc import Callable, Sequence
+from dataclasses import dataclass, replace
+from typing import Literal
+
+from loguru import logger
+
+from nanobot.providers.registry import ProviderModelSpec
+
+CatalogSource = Literal["remote", "cache", "stale", "fallback"]
+
+
+@dataclass(frozen=True, slots=True)
+class OAuthModelCatalogSnapshot:
+    """One usable catalog view, including where it came from."""
+
+    models: tuple[ProviderModelSpec, ...]
+    source: CatalogSource
+    fetched_at: float
+    message: str | None = None
+
+    def find(self, model: str) -> ProviderModelSpec | None:
+        wire_id = model.split("/", 1)[-1]
+        return next(
+            (item for item in self.models if item.id.split("/", 1)[-1] == wire_id),
+            None,
+        )
+
+
+@dataclass(frozen=True, slots=True)
+class _CacheEntry:
+    snapshot: OAuthModelCatalogSnapshot
+    stored_at: float
+
+
+class OAuthModelCatalog:
+    """Cache one provider's discovery behind a small failure-tolerant interface."""
+
+    def __init__(
+        self,
+        *,
+        fallback_models: Sequence[ProviderModelSpec],
+        fetch: Callable[[str | None], Sequence[ProviderModelSpec]],
+        fresh_ttl_s: float = 5 * 60,
+        stale_ttl_s: float = 24 * 60 * 60,
+        failure_ttl_s: float = 30,
+        max_entries: int = 8,
+        monotonic: Callable[[], float] = time.monotonic,
+        wall_clock: Callable[[], float] = time.time,
+    ) -> None:
+        if fresh_ttl_s < 0 or stale_ttl_s < fresh_ttl_s or failure_ttl_s < 0:
+            raise ValueError("catalog cache TTLs are invalid")
+        if max_entries < 1:
+            raise ValueError("catalog cache must allow at least one entry")
+        self._fallback_models = tuple(fallback_models)
+        self._fetch = fetch
+        self._fresh_ttl_s = fresh_ttl_s
+        self._stale_ttl_s = stale_ttl_s
+        self._failure_ttl_s = failure_ttl_s
+        self._max_entries = max_entries
+        self._monotonic = monotonic
+        self._wall_clock = wall_clock
+        self._condition = threading.Condition()
+        self._entries: dict[str, _CacheEntry] = {}
+        self._failures: dict[str, float] = {}
+        self._inflight: set[str] = set()
+        self._generation = 0
+
+    def get(self, *, cache_key: str, proxy: str | None = None) -> OAuthModelCatalogSnapshot:
+        """Return a fresh catalog, sharing concurrent work and retaining a fallback."""
+        with self._condition:
+            generation = self._generation
+            cached = self._cached_result(cache_key)
+            if cached is not None:
+                return cached
+            while cache_key in self._inflight:
+                self._condition.wait()
+                if generation != self._generation:
+                    return self._stale_or_fallback(None, self._monotonic())
+                cached = self._cached_result(cache_key)
+                if cached is not None:
+                    return cached
+            self._inflight.add(cache_key)
+
+        try:
+            models = tuple(self._fetch(proxy))
+            if not models:
+                raise ValueError("provider returned an empty model catalog")
+        except Exception as exc:
+            logger.warning("OAuth model catalog refresh failed: type={}", type(exc).__name__)
+            with self._condition:
+                result = (
+                    self._stale_or_fallback(None, self._monotonic())
+                    if generation != self._generation
+                    else self._failure_result(cache_key)
+                )
+        else:
+            now = self._monotonic()
+            result = OAuthModelCatalogSnapshot(
+                models=models,
+                source="remote",
+                fetched_at=self._wall_clock(),
+            )
+            with self._condition:
+                if generation != self._generation:
+                    result = self._stale_or_fallback(None, now)
+                else:
+                    self._store(cache_key, _CacheEntry(snapshot=result, stored_at=now))
+                    self._failures.pop(cache_key, None)
+        finally:
+            with self._condition:
+                self._inflight.discard(cache_key)
+                self._condition.notify_all()
+
+        return result
+
+    def invalidate(self) -> None:
+        """Drop cached work and prevent an older identity refresh from being stored."""
+        with self._condition:
+            self._generation += 1
+            self._entries.clear()
+            self._failures.clear()
+            self._condition.notify_all()
+
+    def _cached_result(self, cache_key: str) -> OAuthModelCatalogSnapshot | None:
+        now = self._monotonic()
+        entry = self._entries.get(cache_key)
+        if entry is not None and now - entry.stored_at < self._fresh_ttl_s:
+            return replace(entry.snapshot, source="cache")
+        failure_until = self._failures.get(cache_key)
+        if failure_until is not None and failure_until <= now:
+            self._failures.pop(cache_key, None)
+        elif failure_until is not None:
+            return self._stale_or_fallback(entry, now)
+        return None
+
+    def _failure_result(self, cache_key: str) -> OAuthModelCatalogSnapshot:
+        now = self._monotonic()
+        self._reserve(cache_key)
+        self._failures[cache_key] = now + self._failure_ttl_s
+        return self._stale_or_fallback(self._entries.get(cache_key), now)
+
+    def _stale_or_fallback(
+        self,
+        entry: _CacheEntry | None,
+        now: float,
+    ) -> OAuthModelCatalogSnapshot:
+        if entry is not None and now - entry.stored_at < self._stale_ttl_s:
+            return replace(
+                entry.snapshot,
+                source="stale",
+                message="Could not refresh the online model list; showing cached models.",
+            )
+        return OAuthModelCatalogSnapshot(
+            models=self._fallback_models,
+            source="fallback",
+            fetched_at=self._wall_clock(),
+            message="Could not load the online model list; showing built-in fallback models.",
+        )
+
+    def _store(self, cache_key: str, entry: _CacheEntry) -> None:
+        self._reserve(cache_key)
+        self._entries[cache_key] = entry
+
+    def _reserve(self, cache_key: str) -> None:
+        known = set(self._entries) | set(self._failures)
+        if cache_key in known or len(known) < self._max_entries:
+            return
+        oldest = min(
+            known,
+            key=lambda key: (
+                self._entries[key].stored_at
+                if key in self._entries
+                else self._failures[key] - self._failure_ttl_s
+            ),
+        )
+        self._entries.pop(oldest, None)
+        self._failures.pop(oldest, None)
+
+
+def get_oauth_model_catalog(
+    provider_name: str,
+    *,
+    proxy: str | None = None,
+) -> OAuthModelCatalogSnapshot:
+    """Discover models through the owning provider module."""
+    if provider_name == "openai_codex":
+        from nanobot.providers.openai_codex_provider import get_openai_codex_model_catalog
+
+        return get_openai_codex_model_catalog(proxy)
+    if provider_name == "xai_grok":
+        from nanobot.providers.xai_grok_provider import get_xai_grok_model_catalog
+
+        return get_xai_grok_model_catalog(proxy)
+    if provider_name == "github_copilot":
+        from nanobot.providers.github_copilot_provider import get_github_copilot_model_catalog
+
+        return get_github_copilot_model_catalog(proxy)
+    raise ValueError(f"OAuth model discovery is not available for {provider_name}")
+
+
+def invalidate_oauth_model_catalog(provider_name: str) -> None:
+    """Invalidate provider discovery after its OAuth identity changes."""
+    if provider_name == "openai_codex":
+        from nanobot.providers.openai_codex_provider import (
+            invalidate_openai_codex_model_catalog,
+        )
+
+        invalidate_openai_codex_model_catalog()
+    elif provider_name == "xai_grok":
+        from nanobot.providers.xai_grok_provider import invalidate_xai_grok_model_catalog
+
+        invalidate_xai_grok_model_catalog()
+    elif provider_name == "github_copilot":
+        from nanobot.providers.github_copilot_provider import (
+            invalidate_github_copilot_model_catalog,
+        )
+
+        invalidate_github_copilot_model_catalog()

nanobot/providers/openai_codex_provider.py

@@ -14,7 +14,10 @@ from typing import Any, cast
 import httpx
 from loguru import logger
 from oauth_cli_kit import get_token as get_codex_token
+from oauth_cli_kit.providers import OPENAI_CODEX_PROVIDER
+from oauth_cli_kit.storage import FileTokenStorage
 
+from nanobot import __version__
 from nanobot.providers.base import (
     LLMProvider,
     LLMResponse,
@@ -22,6 +25,10 @@ from nanobot.providers.base import (
     ProviderConversationState,
     resolve_stream_idle_timeout_s,
 )
+from nanobot.providers.oauth_model_catalog import (
+    OAuthModelCatalog,
+    OAuthModelCatalogSnapshot,
+)
 from nanobot.providers.openai_responses import (
     ResponsesStreamCapture,
     build_responses_state,
@@ -35,8 +42,11 @@ from nanobot.providers.openai_responses import (
     responses_state_items,
     responses_state_matches,
 )
+from nanobot.providers.registry import ProviderModelSpec, find_by_name
 
 DEFAULT_CODEX_URL = "https://chatgpt.com/backend-api/codex/responses"
+DEFAULT_OPENAI_CODEX_MODELS_URL = "https://chatgpt.com/backend-api/codex/models"
+OPENAI_CODEX_CATALOG_CLIENT_VERSION = "0.144.0"
 DEFAULT_ORIGINATOR = "nanobot"
 _COMPACTION_RETAINED_CHAR_BUDGET = 256_000
 
@@ -87,9 +97,7 @@ class OpenAICodexProvider(LLMProvider):
         model = model or self.default_model
         sanitized_messages = self._sanitize_empty_content(messages)
         sanitized_state = (
-            provider_context.conversation_state
-            if provider_context is not None
-            else None
+            provider_context.conversation_state if provider_context is not None else None
         )
         if sanitized_state is not None:
             sanitized_state = sanitized_state.with_pending_messages(
@@ -168,11 +176,7 @@ class OpenAICodexProvider(LLMProvider):
                     )
 
             compact_threshold = resolve_compact_threshold(
-                (
-                    provider_context.context_window_tokens
-                    if provider_context is not None
-                    else None
-                ),
+                (provider_context.context_window_tokens if provider_context is not None else None),
                 max_tokens,
             )
             if (
@@ -236,8 +240,12 @@ class OpenAICodexProvider(LLMProvider):
             return response
 
     async def chat(
-        self, messages: list[dict[str, Any]], tools: list[dict[str, Any]] | None = None,
-        model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7,
+        self,
+        messages: list[dict[str, Any]],
+        tools: list[dict[str, Any]] | None = None,
+        model: str | None = None,
+        max_tokens: int = 4096,
+        temperature: float = 0.7,
         reasoning_effort: str | None = None,
         tool_choice: str | dict[str, Any] | None = None,
         provider_context: ProviderCallContext | None = None,
@@ -264,8 +272,12 @@ class OpenAICodexProvider(LLMProvider):
         )
 
     async def chat_stream(
-        self, messages: list[dict[str, Any]], tools: list[dict[str, Any]] | None = None,
-        model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7,
+        self,
+        messages: list[dict[str, Any]],
+        tools: list[dict[str, Any]] | None = None,
+        model: str | None = None,
+        max_tokens: int = 4096,
+        temperature: float = 0.7,
         reasoning_effort: str | None = None,
         tool_choice: str | dict[str, Any] | None = None,
         on_content_delta: Callable[[str], Awaitable[None]] | None = None,
@@ -344,11 +356,7 @@ def _without_response_item_ids(
             sanitized_input.append(raw_item)
             continue
         item = cast(dict[str, Any], raw_item)
-        sanitized_input.append({
-            key: value
-            for key, value in item.items()
-            if key != "id"
-        })
+        sanitized_input.append({key: value for key, value in item.items() if key != "id"})
 
     body = dict(request_body)
     body["input"] = sanitized_input
@@ -444,9 +452,7 @@ async def _request_codex(
                 raw = text.decode("utf-8", "ignore")
                 retry_after = LLMProvider._extract_retry_after_from_headers(response.headers)
                 error_type, error_code = LLMProvider._extract_error_type_code(raw)
-                compaction_unsupported = (
-                    response.status_code in {400, 404, 422}
-                    and any(
+                compaction_unsupported = response.status_code in {400, 404, 422} and any(
                     marker in raw.lower()
                     for marker in (
                         "context_management",
@@ -454,14 +460,15 @@ async def _request_codex(
                         "compaction_trigger",
                     )
                 )
-                )
                 raise _CodexHTTPError(
                     _friendly_error(response.status_code, raw),
                     status_code=response.status_code,
                     retry_after=retry_after,
                     error_type=error_type,
                     error_code=error_code,
-                    should_retry=_should_retry_status(response.status_code, error_type, error_code, raw),
+                    should_retry=_should_retry_status(
+                        response.status_code, error_type, error_code, raw
+                    ),
                     compaction_unsupported=compaction_unsupported,
                 )
             capture = ResponsesStreamCapture()
@@ -534,7 +541,9 @@ def _codex_error_response(exc: Exception) -> LLMResponse:
         default_detail = "HTTP request failed"
 
     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
+        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),
@@ -592,3 +601,139 @@ def _should_retry_status(
             )
         )
     return status_code in LLMProvider._RETRYABLE_STATUS_CODES or status_code >= 500
+
+
+def get_openai_codex_model_catalog(
+    proxy: str | None = None,
+) -> OAuthModelCatalogSnapshot:
+    storage = FileTokenStorage(token_filename=OPENAI_CODEX_PROVIDER.token_filename)
+    token = storage.load()
+    account_id = getattr(token, "account_id", None)
+    account_key = _catalog_account_key(account_id)
+    cache_key = f"{storage.get_token_path()}\0{account_key}\0{proxy or ''}"
+    return _OPENAI_CODEX_MODEL_CATALOG.get(cache_key=cache_key, proxy=proxy)
+
+
+def invalidate_openai_codex_model_catalog() -> None:
+    _OPENAI_CODEX_MODEL_CATALOG.invalidate()
+
+
+def _fetch_openai_codex_models(proxy: str | None) -> tuple[ProviderModelSpec, ...]:
+    token = get_codex_token(proxy=proxy)
+    account_id = getattr(token, "account_id", None)
+    if not isinstance(account_id, str) or not account_id:
+        raise RuntimeError("OpenAI Codex OAuth token has no account ID")
+    client_kwargs: dict[str, Any] = {"timeout": 10.0, "follow_redirects": False}
+    if proxy:
+        client_kwargs.update(proxy=proxy, trust_env=False)
+    with httpx.Client(**client_kwargs) as client:
+        response = client.get(
+            DEFAULT_OPENAI_CODEX_MODELS_URL,
+            params={"client_version": OPENAI_CODEX_CATALOG_CLIENT_VERSION},
+            headers={
+                "Authorization": f"Bearer {token.access}",
+                "chatgpt-account-id": account_id,
+                "originator": DEFAULT_ORIGINATOR,
+                "User-Agent": f"nanobot/{__version__} (python)",
+                "accept": "application/json",
+            },
+        )
+    response.raise_for_status()
+    return _parse_openai_codex_models(response.json())
+
+
+def _parse_openai_codex_models(payload: Any) -> tuple[ProviderModelSpec, ...]:
+    rows = cast(dict[str, Any], payload).get("models") if isinstance(payload, dict) else None
+    if not isinstance(rows, list):
+        return ()
+
+    fallback_models = _oauth_fallback_models("openai_codex")
+    fallback_by_id = {model.id.split("/", 1)[-1]: model for model in fallback_models}
+    parsed: list[tuple[int, ProviderModelSpec]] = []
+    seen: set[str] = set()
+    for value in cast(list[object], rows):
+        if not isinstance(value, dict):
+            continue
+        row = cast(dict[str, Any], value)
+        wire_id = _catalog_first_text(row, "slug", "id")
+        if not wire_id or wire_id in seen or row.get("visibility") in {"hide", "none"}:
+            continue
+        seen.add(wire_id)
+        fallback = fallback_by_id.get(wire_id)
+        priority = row.get("priority")
+        parsed.append(
+            (
+                priority if isinstance(priority, int) and not isinstance(priority, bool) else 2**31,
+                ProviderModelSpec(
+                    id=f"openai-codex/{wire_id}",
+                    label=(
+                        _catalog_first_text(row, "display_name", "name")
+                        or (fallback.label if fallback is not None else wire_id)
+                    ),
+                    description=(
+                        _catalog_first_text(row, "description")
+                        or (fallback.description if fallback is not None else "")
+                    ),
+                    owned_by="OpenAI Codex",
+                    context_window=(
+                        _catalog_positive_int(row, "context_window")
+                        or (fallback.context_window if fallback is not None else None)
+                    ),
+                    reasoning_efforts=(
+                        _catalog_reasoning_efforts(row.get("supported_reasoning_levels"))
+                        or (fallback.reasoning_efforts if fallback is not None else ())
+                    ),
+                ),
+            )
+        )
+    parsed.sort(key=lambda item: item[0])
+    return tuple(model for _, model in parsed)
+
+
+def _oauth_fallback_models(provider_name: str) -> tuple[ProviderModelSpec, ...]:
+    spec = find_by_name(provider_name)
+    assert spec is not None
+    return spec.builtin_models
+
+
+def _catalog_account_key(account_id: object) -> str:
+    value = account_id if isinstance(account_id, str) else ""
+    return hashlib.sha256(value.encode()).hexdigest()[:16] if value else "anonymous"
+
+
+def _catalog_first_text(row: dict[str, Any], *keys: str) -> str:
+    for key in keys:
+        value = row.get(key)
+        if isinstance(value, str) and value.strip():
+            return value.strip()
+    return ""
+
+
+def _catalog_positive_int(row: dict[str, Any], *keys: str) -> int | None:
+    for key in keys:
+        value = row.get(key)
+        if isinstance(value, (int, float)) and not isinstance(value, bool) and value > 0:
+            return int(value)
+    return None
+
+
+def _catalog_reasoning_efforts(value: Any) -> tuple[str, ...]:
+    if not isinstance(value, list):
+        return ()
+    efforts: list[str] = []
+    for item in cast(list[object], value):
+        if isinstance(item, str):
+            effort = item.strip()
+        elif isinstance(item, dict):
+            effort = _catalog_first_text(cast(dict[str, Any], item), "effort", "value", "id")
+        else:
+            effort = ""
+        if effort and effort not in efforts:
+            efforts.append(effort)
+    return tuple(efforts)
+
+
+_OPENAI_CODEX_MODEL_CATALOG = OAuthModelCatalog(
+    fallback_models=_oauth_fallback_models("openai_codex"),
+    fetch=_fetch_openai_codex_models,
+)

nanobot/providers/registry.py

@@ -20,12 +20,15 @@ from pydantic.alias_generators import to_snake
 
 @dataclass(frozen=True)
 class ProviderModelSpec:
-    """A curated model exposed by providers without a model-list endpoint."""
+    """Curated model metadata used for fixed catalogs or online fallback."""
 
     id: str
     label: str = ""
     description: str = ""
+    owned_by: str = ""
     context_window: int | None = None
+    reasoning_efforts: tuple[str, ...] = ()
+    supports_backend_search: bool = False
 
 
 @dataclass(frozen=True)
@@ -42,7 +45,7 @@ class ProviderSpec:
     keywords: tuple[str, ...]  # model-name keywords for matching (lowercase)
     env_key: str  # env var for API key, e.g. "DASHSCOPE_API_KEY"
     display_name: str = ""  # shown in `nanobot status`
-    model_catalog: str = "auto"  # WebUI model-list source
+    model_catalog: str = "auto"  # WebUI model-list source, including builtin/hybrid
     builtin_models: tuple[ProviderModelSpec, ...] = ()
     settings_alias_for: str = ""  # compatibility alias grouped under this provider in Settings
 
@@ -407,45 +410,56 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         keywords=("openai-codex",),
         env_key="",
         display_name="OpenAI Codex",
-        model_catalog="builtin",
+        model_catalog="hybrid",
         builtin_models=(
             ProviderModelSpec(
                 id="openai-codex/gpt-5.6-sol",
                 label="GPT-5.6-Sol",
                 description="Latest frontier agentic coding model.",
-                context_window=372000,
+                context_window=272_000,
+                reasoning_efforts=("low", "medium", "high", "xhigh", "max", "ultra"),
             ),
             ProviderModelSpec(
                 id="openai-codex/gpt-5.6-terra",
                 label="GPT-5.6-Terra",
                 description="Balanced agentic coding model for everyday work.",
-                context_window=372000,
+                context_window=272_000,
+                reasoning_efforts=("low", "medium", "high", "xhigh", "max", "ultra"),
             ),
             ProviderModelSpec(
                 id="openai-codex/gpt-5.6-luna",
                 label="GPT-5.6-Luna",
                 description="Fast and affordable agentic coding model.",
-                context_window=372000,
+                context_window=272_000,
+                reasoning_efforts=("low", "medium", "high", "xhigh", "max"),
             ),
             ProviderModelSpec(
                 id="openai-codex/gpt-5.5",
                 label="GPT-5.5",
                 description="Frontier model for complex coding, research, and real-world work.",
+                context_window=272_000,
+                reasoning_efforts=("low", "medium", "high", "xhigh"),
             ),
             ProviderModelSpec(
                 id="openai-codex/gpt-5.4",
                 label="GPT-5.4",
                 description="Strong model for everyday coding.",
+                context_window=272_000,
+                reasoning_efforts=("low", "medium", "high", "xhigh"),
             ),
             ProviderModelSpec(
                 id="openai-codex/gpt-5.4-mini",
                 label="GPT-5.4-Mini",
                 description="Small, fast, and cost-efficient model for simpler coding tasks.",
+                context_window=272_000,
+                reasoning_efforts=("low", "medium", "high", "xhigh"),
             ),
             ProviderModelSpec(
                 id="openai-codex/gpt-5.3-codex-spark",
                 label="GPT-5.3-Codex-Spark",
                 description="Ultra-fast coding model.",
+                context_window=128_000,
+                reasoning_efforts=("low", "medium", "high", "xhigh"),
             ),
         ),
         backend="openai_codex",
@@ -459,13 +473,19 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         keywords=("xai-grok", "xai_grok"),
         env_key="",
         display_name="xAI Grok",
-        model_catalog="builtin",
+        model_catalog="hybrid",
         builtin_models=(
+            ProviderModelSpec(
+                id="xai-grok/grok-4.6",
+                label="Grok 4.6",
+                description="Grok via xAI subscription; X Search is enabled when supported.",
+                context_window=500_000,
+            ),
             ProviderModelSpec(
                 id="xai-grok/grok-4.5",
                 label="Grok 4.5",
                 description="Grok via xAI subscription; X Search is enabled when supported.",
-                context_window=500000,
+                context_window=500_000,
             ),
         ),
         backend="xai_grok",
@@ -478,6 +498,19 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         keywords=("github_copilot", "copilot"),
         env_key="",
         display_name="Github Copilot",
+        model_catalog="hybrid",
+        builtin_models=(
+            ProviderModelSpec(
+                id="github-copilot/gpt-5.4-mini",
+                label="GPT-5.4 Mini",
+                description="GitHub Copilot Responses model.",
+            ),
+            ProviderModelSpec(
+                id="github-copilot/gpt-4.1",
+                label="GPT-4.1",
+                description="GitHub Copilot chat model.",
+            ),
+        ),
         backend="github_copilot",
         default_api_base="https://api.githubcopilot.com",
         strip_model_prefix=True,

nanobot/providers/xai_grok_provider.py

@@ -4,9 +4,9 @@ from __future__ import annotations
 
 import asyncio
 import base64
+import hashlib
 import json
 import re
-import time
 import uuid
 from collections.abc import Awaitable, Callable
 from typing import Any, cast
@@ -22,21 +22,24 @@ from nanobot.providers.base import (
     ToolCallRequest,
     resolve_stream_idle_timeout_s,
 )
+from nanobot.providers.oauth_model_catalog import OAuthModelCatalog, OAuthModelCatalogSnapshot
 from nanobot.providers.openai_responses import (
     consume_sse_with_reasoning,
     convert_messages,
     convert_tools,
 )
+from nanobot.providers.registry import ProviderModelSpec, find_by_name
 from nanobot.providers.xai_oauth import (
     XAI_CLIENT_VERSION,
-    XAIToken,
+    get_xai_oauth_login_status,
+    get_xai_oauth_storage_path,
     get_xai_oauth_token,
 )
 
+DEFAULT_XAI_GROK_MODEL = "xai-grok/grok-4.6"
 DEFAULT_XAI_GROK_URL = "https://cli-chat-proxy.grok.com/v1/responses"
 DEFAULT_XAI_GROK_MODELS_URL = "https://cli-chat-proxy.grok.com/v1/models"
-DEFAULT_XAI_GROK_MODEL = "xai-grok/grok-4.5"
-_MODEL_CAPABILITIES_TTL_S = 5 * 60
+_HOSTED_SEARCH_MAX_TURNS = 5
 _MAX_ERROR_BODY_CHARS = 1000
 _SENSITIVE_ERROR_KEYS = {
     "accesstoken",
@@ -63,6 +66,10 @@ def _is_named_x_search_tool(value: object) -> bool:
 class XAIGrokProvider(LLMProvider):
     """Call xAI's subscription proxy and expose supported hosted tools."""
 
+    # An incomplete hosted-tool stream can already have emitted answer text. Let the
+    # provider close that stream segment before its one bounded recovery attempt.
+    supports_stream_recover_callback = True
+
     def __init__(
         self,
         default_model: str = DEFAULT_XAI_GROK_MODEL,
@@ -75,37 +82,19 @@ class XAIGrokProvider(LLMProvider):
         self.default_model = default_model
         self.proxy = proxy or None
         self._extra_body = dict(extra_body or {})
-        self._model_capabilities: dict[str, bool] | None = None
-        self._model_capabilities_fetched_at = 0.0
 
-    async def _supports_backend_search(self, token: XAIToken, model: str) -> bool:
-        now = time.monotonic()
-        capabilities = self._model_capabilities
-        if (
-            capabilities is None
-            or now - self._model_capabilities_fetched_at >= _MODEL_CAPABILITIES_TTL_S
-        ):
-            try:
-                capabilities = await _fetch_xai_model_capabilities(
-                    DEFAULT_XAI_GROK_MODELS_URL,
-                    _build_model_headers(token),
-                    proxy=self.proxy,
+    async def _supports_backend_search(self, model: str) -> bool:
+        catalog = await asyncio.to_thread(
+            get_xai_grok_model_catalog,
+            self.proxy,
         )
-            except Exception as exc:
+        if catalog.message:
             logger.warning(
-                    "xAI model capability lookup failed; hosted X Search disabled for model {}: "
-                    "type={} error={}",
-                    model,
-                    type(exc).__name__,
-                    str(exc).strip() or "unexpected error",
+                "xAI model catalog unavailable; hosted X Search disabled unless cached: {}",
+                catalog.message,
             )
-                capabilities = {}
-                self._model_capabilities = capabilities
-                self._model_capabilities_fetched_at = now
-            else:
-                self._model_capabilities = capabilities
-                self._model_capabilities_fetched_at = now
-        return capabilities.get(model, False)
+        info = catalog.find(model)
+        return bool(info and info.supports_backend_search)
 
     async def _call_xai(
         self,
@@ -119,6 +108,7 @@ class XAIGrokProvider(LLMProvider):
         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,
+        on_stream_recover: Callable[[], Awaitable[None]] | None = None,
     ) -> LLMResponse:
         wire_model = _strip_model_prefix(model or self.default_model)
         system_prompt, input_items = convert_messages(messages)
@@ -128,17 +118,13 @@ class XAIGrokProvider(LLMProvider):
             token = await asyncio.to_thread(get_xai_oauth_token, proxy=self.proxy)
             configured_tools = self._extra_body.get("tools")
             tools_are_explicit = "tools" in self._extra_body
-            configured_hosted_search = (
-                isinstance(configured_tools, list)
-                and any(
-                    _is_hosted_x_search_tool(tool)
-                    for tool in cast(list[object], configured_tools)
-                )
+            configured_hosted_search = isinstance(configured_tools, list) and any(
+                _is_hosted_x_search_tool(tool) for tool in cast(list[object], configured_tools)
             )
             supports_backend_search = False
             if not tools_are_explicit:
                 stage = "model_capabilities"
-                supports_backend_search = await self._supports_backend_search(token, wire_model)
+                supports_backend_search = await self._supports_backend_search(wire_model)
             converted_tools = convert_tools(tools or [])
             if isinstance(configured_tools, list):
                 converted_tools.extend(cast(list[dict[str, Any]], configured_tools))
@@ -149,6 +135,8 @@ class XAIGrokProvider(LLMProvider):
             if supports_backend_search:
                 converted_tools.append({"type": "x_search"})
 
+            hosted_search_enabled = supports_backend_search or configured_hosted_search
+
             body: dict[str, Any] = {
                 "model": wire_model,
                 "store": False,
@@ -164,17 +152,24 @@ class XAIGrokProvider(LLMProvider):
                 "temperature": temperature,
                 "reasoning": _build_reasoning_options(reasoning_effort),
             }
+            if hosted_search_enabled:
+                # xAI's global default is intentionally unspecified. Five turns is
+                # their documented balanced setting and prevents a search from
+                # stopping after a single unsuccessful lookup.
+                body["max_turns"] = _HOSTED_SEARCH_MAX_TURNS
             if self._extra_body:
-                body.update({
-                    key: value
-                    for key, value in self._extra_body.items()
-                    if key != "tools"
-                })
+                body.update(
+                    {key: value for key, value in self._extra_body.items() if key != "tools"}
+                )
                 if tools_are_explicit and not isinstance(configured_tools, list):
                     body["tools"] = configured_tools
 
             headers = _build_headers(token.access, wire_model)
             stage = "xai_request"
+            auth_retried = False
+            hosted_tool_retried = False
+            retry_usage: LLMUsage | None = None
+            while True:
                 try:
                     result = await _request_xai(
                         DEFAULT_XAI_GROK_URL,
@@ -185,30 +180,37 @@ class XAIGrokProvider(LLMProvider):
                         on_thinking_delta=on_thinking_delta,
                         on_tool_call_delta=on_tool_call_delta,
                     )
+                    break
                 except _XAIHTTPError as exc:
-                if exc.status_code != 401:
+                    if exc.status_code != 401 or auth_retried:
                         raise
+                    auth_retried = True
                     stage = "oauth_refresh"
                     token = await asyncio.to_thread(
                         get_xai_oauth_token,
                         proxy=self.proxy,
                         force_refresh=True,
                     )
-                self._model_capabilities = None
-                self._model_capabilities_fetched_at = 0.0
                     headers = _build_headers(token.access, wire_model)
-                stage = "xai_request_retry"
-                result = await _request_xai(
-                    DEFAULT_XAI_GROK_URL,
-                    headers,
-                    body,
-                    proxy=self.proxy,
-                    on_content_delta=on_content_delta,
-                    on_thinking_delta=on_thinking_delta,
-                    on_tool_call_delta=on_tool_call_delta,
+                    stage = "xai_request_after_oauth_refresh"
+                except _XAIIncompleteHostedToolError as exc:
+                    retry_usage = _combine_usage(retry_usage, exc.usage)
+                    cannot_recover_stream = exc.stream_output_emitted and on_stream_recover is None
+                    if hosted_tool_retried or cannot_recover_stream:
+                        exc.usage = retry_usage
+                        raise
+                    hosted_tool_retried = True
+                    stage = "hosted_tool_recovery"
+                    logger.warning(
+                        "xAI response ended with unfinished hosted tool(s): {}; retrying once",
+                        ", ".join(exc.tool_names),
                     )
+                    if on_stream_recover is not None:
+                        await on_stream_recover()
+                    headers = _build_headers(token.access, wire_model)
 
             content, tool_calls, finish_reason, usage, reasoning_content = result
+            usage = _combine_usage(retry_usage, usage)
             return LLMResponse(
                 content=content,
                 tool_calls=tool_calls,
@@ -257,6 +259,7 @@ class XAIGrokProvider(LLMProvider):
         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,
+        on_stream_recover: Callable[[], Awaitable[None]] | None = None,
     ) -> LLMResponse:
         return await self._call_xai(
             messages,
@@ -269,6 +272,7 @@ class XAIGrokProvider(LLMProvider):
             on_content_delta,
             on_thinking_delta,
             on_tool_call_delta,
+            on_stream_recover,
         )
 
     def get_default_model(self) -> str:
@@ -288,6 +292,14 @@ def _build_reasoning_options(reasoning_effort: str | None) -> dict[str, str]:
     return options
 
 
+def _combine_usage(left: LLMUsage | None, right: LLMUsage | None) -> LLMUsage | None:
+    if left is None:
+        return right
+    if right is None:
+        return left
+    return left + right
+
+
 def _build_headers(token: str, model: str) -> dict[str, str]:
     conversation_id = str(uuid.uuid4())
     return {
@@ -308,44 +320,6 @@ def _build_headers(token: str, model: str) -> dict[str, str]:
     }
 
 
-def _build_model_headers(token: XAIToken) -> dict[str, str]:
-    headers = {
-        "Authorization": f"Bearer {token.access}",
-        "X-XAI-Token-Auth": "xai-grok-cli",
-        "x-grok-client-version": XAI_CLIENT_VERSION,
-        "x-grok-client-identifier": "nanobot",
-        "x-grok-client-mode": "headless",
-        "User-Agent": f"nanobot/{__version__} (python)",
-        "accept": "application/json",
-    }
-    claims = _decode_access_token_claims(token.access)
-    user_id = claims.get("sub")
-    if claims.get("principal_type") == "Team":
-        user_id = claims.get("principal_id") or user_id
-    if isinstance(user_id, str) and user_id:
-        headers["x-userid"] = user_id
-    email = claims.get("email")
-    if not isinstance(email, str) or "@" not in email:
-        email = token.account_id if token.account_id and "@" in token.account_id else None
-    if email:
-        headers["x-email"] = email
-    return headers
-
-
-def _decode_access_token_claims(token: str) -> dict[str, Any]:
-    """Read identity hints from the signed token; the server still authenticates it."""
-    parts = token.split(".")
-    if len(parts) < 2 or not parts[1]:
-        return {}
-    payload = parts[1]
-    try:
-        decoded = base64.urlsafe_b64decode(payload + "=" * (-len(payload) % 4))
-        claims = json.loads(decoded)
-    except (ValueError, TypeError):
-        return {}
-    return cast(dict[str, Any], claims) if isinstance(claims, dict) else {}
-
-
 class _XAIHTTPError(RuntimeError):
     def __init__(
         self,
@@ -367,65 +341,25 @@ class _XAIHTTPError(RuntimeError):
         self.response_body = response_body
 
 
-async def _fetch_xai_model_capabilities(
-    url: str,
-    headers: dict[str, str],
+class _XAIIncompleteHostedToolError(RuntimeError):
+    """A nominally successful xAI stream ended before a hosted tool did."""
+
+    should_retry = False  # _call_xai already performs the one safe recovery attempt.
+
+    def __init__(
+        self,
+        active_tools: list[dict[str, Any]],
         *,
-    proxy: str | None = None,
-) -> dict[str, bool]:
-    client_kwargs: dict[str, Any] = {"timeout": 10.0, "follow_redirects": False}
-    if proxy:
-        client_kwargs.update(proxy=proxy, trust_env=False)
-    async with httpx.AsyncClient(**client_kwargs) as client:
-        response = await client.get(url, headers=headers)
-    if response.status_code != 200:
-        raw = response.content.decode("utf-8", "ignore")
-        raise _build_xai_http_error(response.status_code, response.headers, raw)
-    try:
-        payload = response.json()
-    except ValueError as exc:
-        raise RuntimeError("xAI model catalog returned invalid JSON.") from exc
-    return _parse_xai_model_capabilities(payload)
-
-
-def _parse_xai_model_capabilities(payload: Any) -> dict[str, bool]:
-    if isinstance(payload, dict):
-        payload = cast(dict[str, Any], payload)
-        rows: object = payload.get("data")
-        if not isinstance(rows, list):
-            rows = payload.get("models")
-    else:
-        rows = payload
-    if not isinstance(rows, list):
-        return {}
-
-    capabilities: dict[str, bool] = {}
-    for row_value in cast(list[object], rows):
-        if not isinstance(row_value, dict):
-            continue
-        row = cast(dict[str, Any], row_value)
-        meta_value = row.get("_meta")
-        meta = cast(dict[str, Any], meta_value) if isinstance(meta_value, dict) else {}
-        support_value = row.get("supportsBackendSearch")
-        if not isinstance(support_value, bool):
-            support_value = row.get("supports_backend_search")
-        if not isinstance(support_value, bool):
-            support_value = meta.get("supportsBackendSearch")
-        if not isinstance(support_value, bool):
-            support_value = meta.get("supports_backend_search")
-        supports_backend_search = support_value if isinstance(support_value, bool) else False
-
-        identifiers = (
-            row.get("model"),
-            row.get("modelId"),
-            row.get("id"),
-            meta.get("model"),
-            meta.get("modelId"),
+        usage: LLMUsage | None,
+        stream_output_emitted: bool = False,
+    ) -> None:
+        names = [str(event.get("name") or "hosted_tool") for event in active_tools]
+        super().__init__(
+            "xAI ended the response before its hosted tool completed: " + ", ".join(names)
         )
-        for identifier in identifiers:
-            if isinstance(identifier, str) and identifier.strip():
-                capabilities[_strip_model_prefix(identifier.strip())] = supports_backend_search
-    return capabilities
+        self.tool_names = tuple(names)
+        self.usage = usage
+        self.stream_output_emitted = stream_output_emitted
 
 
 async def _request_xai(
@@ -438,10 +372,39 @@ async def _request_xai(
     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, LLMUsage | None, str | None]:
+    active_hosted_tools: dict[str, dict[str, Any]] = {}
+    stream_output_emitted = False
+
+    async def _forward_content_delta(delta: str) -> None:
+        nonlocal stream_output_emitted
+        if delta:
+            stream_output_emitted = True
+        if on_content_delta is not None:
+            await on_content_delta(delta)
+
+    async def _forward_thinking_delta(delta: str) -> None:
+        nonlocal stream_output_emitted
+        if delta:
+            stream_output_emitted = True
+        if on_thinking_delta is not None:
+            await on_thinking_delta(delta)
+
+    async def _track_and_forward_tool_event(event: dict[str, Any]) -> None:
+        if event.get("kind") == "hosted_tool":
+            call_id = event.get("call_id")
+            if call_id:
+                call_id = str(call_id)
+                if event.get("phase") == "start":
+                    active_hosted_tools[call_id] = dict(event)
+                elif event.get("phase") in {"end", "error"}:
+                    active_hosted_tools.pop(call_id, None)
+        if on_tool_call_delta is not None:
+            await on_tool_call_delta(event)
+
     async def _on_response_event(event: dict[str, Any]) -> None:
         hosted_event = _xai_hosted_tool_event(event)
-        if hosted_event is not None and on_tool_call_delta is not None:
-            await on_tool_call_delta(hosted_event)
+        if hosted_event is not None:
+            await _track_and_forward_tool_event(hosted_event)
 
     client_kwargs: dict[str, Any] = {"timeout": resolve_stream_idle_timeout_s()}
     if proxy:
@@ -452,13 +415,34 @@ async def _request_xai(
                 content = await response.aread()
                 raw = content.decode("utf-8", "ignore")
                 raise _build_xai_http_error(response.status_code, response.headers, raw)
-            return await consume_sse_with_reasoning(
+            result = await consume_sse_with_reasoning(
                 response,
-                on_content_delta=on_content_delta,
-                on_tool_call_delta=on_tool_call_delta,
-                on_reasoning_delta=on_thinking_delta,
-                on_response_event=_on_response_event if on_tool_call_delta else None,
+                on_content_delta=(_forward_content_delta if on_content_delta is not None else None),
+                # Always observe tool events so protocol validation also works for
+                # non-streaming callers that did not request UI progress callbacks.
+                on_tool_call_delta=_track_and_forward_tool_event,
+                on_reasoning_delta=(
+                    _forward_thinking_delta if on_thinking_delta is not None else None
+                ),
+                on_response_event=_on_response_event,
             )
+            if result[2] != "error" and active_hosted_tools:
+                active = list(active_hosted_tools.values())
+                for event in active:
+                    await _track_and_forward_tool_event(
+                        {
+                            **event,
+                            "phase": "error",
+                            "result": None,
+                            "error": "xAI ended the response before this hosted tool completed.",
+                        }
+                    )
+                raise _XAIIncompleteHostedToolError(
+                    active,
+                    usage=result[3],
+                    stream_output_emitted=stream_output_emitted,
+                )
+            return result
 
 
 def _xai_hosted_tool_event(event: dict[str, Any]) -> dict[str, Any] | None:
@@ -472,19 +456,33 @@ def _xai_hosted_tool_event(event: dict[str, Any]) -> dict[str, Any] | None:
             "phase": "start",
             "call_id": str(call_id),
             "name": "x_search",
-            "arguments": _xai_hosted_tool_arguments(
-                event.get("input", event.get("arguments"))
-            ),
+            "arguments": _xai_hosted_tool_arguments(event.get("input", event.get("arguments"))),
             "result": None,
         }
 
-    if event_type != "response.output_item.done":
+    if event_type not in {"response.output_item.added", "response.output_item.done"}:
         return None
     item = event.get("item")
     if not isinstance(item, dict):
         return None
     item = cast(dict[str, Any], item)
-    if item.get("type") != "custom_tool_call":
+    item_type = item.get("type")
+    if item_type == "x_search_call":
+        call_id = item.get("id") or item.get("call_id") or event.get("item_id")
+        if not call_id:
+            return None
+        phase = "start" if event_type == "response.output_item.added" else "end"
+        return {
+            "kind": "hosted_tool",
+            "phase": phase,
+            "call_id": str(call_id),
+            "name": "x_search",
+            "arguments": _xai_hosted_tool_arguments(item.get("action")),
+            "result": (
+                {"status": str(item.get("status") or "completed")} if phase == "end" else None
+            ),
+        }
+    if event_type != "response.output_item.done" or item_type != "custom_tool_call":
         return None
     tool_name = item.get("name")
     if not isinstance(tool_name, str) or not tool_name.startswith("x_"):
@@ -497,9 +495,7 @@ def _xai_hosted_tool_event(event: dict[str, Any]) -> dict[str, Any] | None:
         "phase": "end",
         "call_id": str(call_id),
         "name": "x_search",
-        "arguments": _xai_hosted_tool_arguments(
-            item.get("input", item.get("arguments"))
-        ),
+        "arguments": _xai_hosted_tool_arguments(item.get("input", item.get("arguments"))),
         # Keep the useful search subtype, but do not persist large hosted results
         # in WebUI activity messages. The model answer already carries citations.
         "result": {"name": tool_name},
@@ -608,6 +604,8 @@ def _xai_error_response(exc: Exception) -> LLMResponse:
         should_retry = True if should_retry is None else should_retry
     elif isinstance(exc, _XAIHTTPError):
         error_kind = "http"
+    elif isinstance(exc, _XAIIncompleteHostedToolError):
+        error_kind = "provider"
     if status_code is not None and should_retry is None:
         should_retry = _should_retry_status(
             int(status_code),
@@ -617,9 +615,11 @@ def _xai_error_response(exc: Exception) -> LLMResponse:
         )
     message = str(exc).strip() or "unexpected error"
     retry_after = getattr(exc, "retry_after", None)
+    usage = getattr(exc, "usage", None)
     return LLMResponse(
         content=f"Error calling xAI ({type(exc).__name__}): {message}",
         finish_reason="error",
+        usage=usage if isinstance(usage, LLMUsage) else None,
         retry_after=retry_after,
         error_status_code=int(status_code) if status_code is not None else None,
         error_kind=error_kind,
@@ -647,3 +647,209 @@ def _should_retry_status(
             )
         )
     return status_code in LLMProvider._RETRYABLE_STATUS_CODES or status_code >= 500  # pyright: ignore[reportPrivateUsage]
+
+
+def get_xai_grok_model_catalog(proxy: str | None = None) -> OAuthModelCatalogSnapshot:
+    token = get_xai_oauth_login_status()
+    account_key = _catalog_account_key(getattr(token, "account_id", None))
+    cache_key = f"{get_xai_oauth_storage_path()}\0{account_key}\0{proxy or ''}"
+    return _XAI_GROK_MODEL_CATALOG.get(cache_key=cache_key, proxy=proxy)
+
+
+def invalidate_xai_grok_model_catalog() -> None:
+    _XAI_GROK_MODEL_CATALOG.invalidate()
+
+
+def _fetch_xai_grok_models(proxy: str | None) -> tuple[ProviderModelSpec, ...]:
+    token = get_xai_oauth_token(proxy=proxy)
+    client_kwargs: dict[str, Any] = {"timeout": 10.0, "follow_redirects": False}
+    if proxy:
+        client_kwargs.update(proxy=proxy, trust_env=False)
+    with httpx.Client(**client_kwargs) as client:
+        response = client.get(
+            DEFAULT_XAI_GROK_MODELS_URL,
+            headers=_build_xai_model_headers(token.access, token.account_id),
+        )
+    response.raise_for_status()
+    return _parse_xai_grok_models(response.json())
+
+
+def _parse_xai_grok_models(payload: Any) -> tuple[ProviderModelSpec, ...]:
+    if isinstance(payload, dict):
+        payload_mapping = cast(dict[str, Any], payload)
+        rows: object = payload_mapping.get("data")
+        if not isinstance(rows, list):
+            rows = payload_mapping.get("models")
+    else:
+        rows = payload
+    if not isinstance(rows, list):
+        return ()
+
+    fallback_models = _oauth_fallback_models("xai_grok")
+    fallback_by_id = {model.id.split("/", 1)[-1]: model for model in fallback_models}
+    models: list[ProviderModelSpec] = []
+    seen: set[str] = set()
+    for value in cast(list[object], rows):
+        if not isinstance(value, dict):
+            continue
+        row = cast(dict[str, Any], value)
+        meta = _catalog_mapping(row.get("_meta"))
+        raw_id = next(
+            (
+                candidate.strip()
+                for candidate in (
+                    row.get("id"),
+                    row.get("model"),
+                    row.get("modelId"),
+                    row.get("name"),
+                    meta.get("id"),
+                    meta.get("model"),
+                    meta.get("modelId"),
+                )
+                if isinstance(candidate, str) and candidate.strip()
+            ),
+            None,
+        )
+        if raw_id is None:
+            continue
+        wire_id = raw_id.split("/", 1)[-1]
+        if wire_id in seen:
+            continue
+        seen.add(wire_id)
+        fallback = fallback_by_id.get(wire_id)
+        label = _catalog_first_text(row, "display_name", "label", "name") or _catalog_first_text(
+            meta,
+            "display_name",
+            "label",
+            "name",
+        )
+        if not label or label == raw_id:
+            label = fallback.label if fallback is not None else wire_id
+        models.append(
+            ProviderModelSpec(
+                id=f"xai-grok/{wire_id}",
+                label=label,
+                description=(
+                    _catalog_first_text(row, "description")
+                    or _catalog_first_text(meta, "description")
+                    or (fallback.description if fallback is not None else "")
+                ),
+                owned_by=(
+                    _catalog_first_text(row, "owned_by", "owner", "organization")
+                    or _catalog_first_text(meta, "owned_by", "owner", "organization")
+                    or (fallback.owned_by if fallback is not None else "xAI")
+                ),
+                context_window=(
+                    _catalog_positive_int(row, "context_window", "context_length")
+                    or _catalog_positive_int(meta, "context_window", "context_length")
+                    or (fallback.context_window if fallback is not None else None)
+                ),
+                reasoning_efforts=_catalog_reasoning_efforts(
+                    row.get("reasoning_efforts", meta.get("reasoning_efforts"))
+                ),
+                supports_backend_search=_catalog_bool_field(
+                    row,
+                    "supports_backend_search",
+                    "supportsBackendSearch",
+                ),
+            )
+        )
+    return tuple(models)
+
+
+def _build_xai_model_headers(access_token: str, account_id: str | None) -> dict[str, str]:
+    headers = {
+        "Authorization": f"Bearer {access_token}",
+        "X-XAI-Token-Auth": "xai-grok-cli",
+        "x-grok-client-version": XAI_CLIENT_VERSION,
+        "x-grok-client-identifier": "nanobot",
+        "x-grok-client-mode": "headless",
+        "User-Agent": f"nanobot/{__version__} (python)",
+        "accept": "application/json",
+    }
+    claims = _decode_access_token_claims(access_token)
+    user_id = claims.get("sub")
+    if claims.get("principal_type") == "Team":
+        user_id = claims.get("principal_id") or user_id
+    if isinstance(user_id, str) and user_id:
+        headers["x-userid"] = user_id
+    email = claims.get("email")
+    if not isinstance(email, str) or "@" not in email:
+        email = account_id if account_id and "@" in account_id else None
+    if email:
+        headers["x-email"] = email
+    return headers
+
+
+def _decode_access_token_claims(token: str) -> dict[str, Any]:
+    parts = token.split(".")
+    if len(parts) < 2 or not parts[1]:
+        return {}
+    try:
+        decoded = base64.urlsafe_b64decode(parts[1] + "=" * (-len(parts[1]) % 4))
+        claims = json.loads(decoded)
+    except (ValueError, TypeError):
+        return {}
+    return cast(dict[str, Any], claims) if isinstance(claims, dict) else {}
+
+
+def _oauth_fallback_models(provider_name: str) -> tuple[ProviderModelSpec, ...]:
+    spec = find_by_name(provider_name)
+    assert spec is not None
+    return spec.builtin_models
+
+
+def _catalog_account_key(account_id: object) -> str:
+    value = account_id if isinstance(account_id, str) else ""
+    return hashlib.sha256(value.encode()).hexdigest()[:16] if value else "anonymous"
+
+
+def _catalog_mapping(value: Any) -> dict[str, Any]:
+    return cast(dict[str, Any], value) if isinstance(value, dict) else {}
+
+
+def _catalog_first_text(row: dict[str, Any], *keys: str) -> str:
+    for key in keys:
+        value = row.get(key)
+        if isinstance(value, str) and value.strip():
+            return value.strip()
+    return ""
+
+
+def _catalog_positive_int(row: dict[str, Any], *keys: str) -> int | None:
+    for key in keys:
+        value = row.get(key)
+        if isinstance(value, (int, float)) and not isinstance(value, bool) and value > 0:
+            return int(value)
+    return None
+
+
+def _catalog_bool_field(row: dict[str, Any], *keys: str) -> bool:
+    for key in keys:
+        value = row.get(key)
+        if isinstance(value, bool):
+            return value
+    meta = row.get("_meta")
+    return _catalog_bool_field(_catalog_mapping(meta), *keys) if isinstance(meta, dict) else False
+
+
+def _catalog_reasoning_efforts(value: Any) -> tuple[str, ...]:
+    if not isinstance(value, list):
+        return ()
+    efforts: list[str] = []
+    for item in cast(list[object], value):
+        if isinstance(item, str):
+            effort = item.strip()
+        elif isinstance(item, dict):
+            effort = _catalog_first_text(cast(dict[str, Any], item), "effort", "value", "id")
+        else:
+            effort = ""
+        if effort and effort not in efforts:
+            efforts.append(effort)
+    return tuple(efforts)
+
+
+_XAI_GROK_MODEL_CATALOG = OAuthModelCatalog(
+    fallback_models=_oauth_fallback_models("xai_grok"),
+    fetch=_fetch_xai_grok_models,
+)

nanobot/webui/settings_models.py

@@ -28,6 +28,10 @@ from nanobot.config.loader import resolve_config_env_vars
 from nanobot.config.schema import Config, FallbackCandidate, ModelPresetConfig, ProviderConfig
 from nanobot.providers.image_generation import get_image_gen_provider
 from nanobot.providers.oauth_guidance import OAUTH_CLI_KIT_MISSING_MESSAGE
+from nanobot.providers.oauth_model_catalog import (
+    get_oauth_model_catalog,
+    invalidate_oauth_model_catalog,
+)
 from nanobot.providers.registry import PROVIDERS, create_dynamic_spec, find_by_name
 from nanobot.webui.settings_contracts import (
     QueryParams,
@@ -661,6 +665,30 @@ def provider_models_payload(
             "models": rows,
             "model_count": len(rows),
         }
+    if catalog_kind == "hybrid":
+        proxy = _resolve_env_placeholders(provider_config.proxy)
+        catalog = get_oauth_model_catalog(spec.name, proxy=proxy)
+        rows = [
+            {
+                "id": model.id,
+                "label": model.label or None,
+                "description": model.description or None,
+                "owned_by": model.owned_by or spec.label,
+                "context_window": model.context_window,
+                "reasoning_efforts": list(model.reasoning_efforts),
+                "supports_backend_search": model.supports_backend_search,
+            }
+            for model in catalog.models
+        ]
+        return {
+            **base_payload,
+            "status": "available",
+            "source": catalog.source,
+            "models": rows,
+            "model_count": len(rows),
+            "message": catalog.message,
+            "fetched_at": catalog.fetched_at,
+        }
 
     api_base = _resolve_env_placeholders(provider_config.api_base) or spec.default_api_base
     if spec.name == "openai" and not api_base:
@@ -1506,6 +1534,7 @@ def login_oauth_provider(
             token = login_github_copilot(print_fn=lambda _message: None)
         if not (token and token.access):
             raise WebUISettingsError("OAuth login failed", status=401)
+        invalidate_oauth_model_catalog(spec.name)
         return settings_payload(config_path=config_path)
 
     if spec.name == "xai_grok":
@@ -1591,6 +1620,7 @@ def complete_oauth_provider(
     oauth_flows.remove(spec.name, flow_id, flow, cancel=False)
     if not token.access:
         raise WebUISettingsError("OAuth login failed", status=401)
+    invalidate_oauth_model_catalog(spec.name)
     return settings_payload(config_path=config_path)
 
 
@@ -1629,6 +1659,7 @@ def logout_oauth_provider(
 
         oauth_flows.clear(spec.name)
         logout_xai_oauth()
+        invalidate_oauth_model_catalog(spec.name)
         return settings_payload(config_path=config_path)
     else:
         raise WebUISettingsError("OAuth logout is not supported for this provider")
@@ -1636,6 +1667,7 @@ def logout_oauth_provider(
     for path in (token_path, token_path.with_suffix(".lock")):
         with suppress(FileNotFoundError):
             path.unlink()
+    invalidate_oauth_model_catalog(spec.name)
     return settings_payload(config_path=config_path)
 
 

tests/agent/test_runner_errors.py

@@ -9,7 +9,9 @@ from unittest.mock import AsyncMock, MagicMock
 import pytest
 
 from agent.runner_helpers import make_run_spec
+from nanobot.agent.hook import AgentHook, AgentHookContext
 from nanobot.agent.tools import ToolResult
+from nanobot.agent.tools.execution import execute_tool_calls
 from nanobot.config.schema import AgentDefaults
 from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
 
@@ -55,11 +57,7 @@ async def test_runner_returns_tool_exception_to_model_for_recovery():
 
 @pytest.mark.asyncio
 @pytest.mark.parametrize("control_error", [KeyboardInterrupt, SystemExit])
-async def test_runner_propagates_tool_control_flow_exceptions(control_error: type[BaseException]):
-    from nanobot.agent.runner import AgentRunner
-
-    provider = MagicMock(spec=LLMProvider)
-
+async def test_tool_execution_propagates_control_flow_exceptions(control_error: type[BaseException]):
     async def execute(_name, _args):
         raise control_error("stop")
 
@@ -67,22 +65,15 @@ async def test_runner_propagates_tool_control_flow_exceptions(control_error: typ
         get_definitions=lambda: [],
         execute=execute,
     )
-    runner = AgentRunner()
-    spec = make_run_spec(
-        provider,
-        initial_messages=[],
-        tools=tools,
-        model="test-model",
-        max_iterations=1,
-        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-    )
-
     with pytest.raises(control_error):
-        await runner._run_tool(
-            spec,
-            ToolCallRequest(id="call_1", name="list_dir", arguments={}),
+        await execute_tool_calls(
+            tools,
+            [ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+            concurrent=False,
             external_lookup_counts={},
             workspace_violation_counts={},
+            hook=AgentHook(),
+            context=AgentHookContext(iteration=0, messages=[]),
         )
 
 

tests/agent/test_runner_safety.py

@@ -9,6 +9,7 @@ import pytest
 from agent.runner_helpers import make_run_spec
 from nanobot.agent.runner import AgentRunner
 from nanobot.agent.tools import ToolResult
+from nanobot.agent.tools.execution import is_ssrf_violation
 from nanobot.config.schema import AgentDefaults
 from nanobot.providers.base import LLMResponse, ToolCallRequest
 
@@ -66,20 +67,20 @@ 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."""
     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(
+    assert is_ssrf_violation(ssrf_msg) is True
+    assert is_ssrf_violation(
         "URL validation failed: Blocked: host resolves to private/internal address 192.168.1.2"
     ) is True
 
     # Workspace-bound markers are NOT classified as SSRF.
-    assert AgentRunner._is_ssrf_violation(
+    assert is_ssrf_violation(
         "Error: Command blocked by safety guard (path outside working dir)"
     ) is False
-    assert AgentRunner._is_ssrf_violation(
+    assert is_ssrf_violation(
         "Path /tmp/x is outside allowed directory /ws"
     ) is False
     # Deny / allowlist filter messages stay non-fatal too.
-    assert AgentRunner._is_ssrf_violation(
+    assert is_ssrf_violation(
         "Error: Command blocked by deny pattern filter"
     ) is False
 

tests/agent/test_runner_tool_execution.py

@@ -3,14 +3,17 @@
 from __future__ import annotations
 
 import asyncio
+from typing import Any
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
 from agent.runner_helpers import make_run_spec
+from nanobot.agent.hook import AgentHook, AgentHookContext
 from nanobot.agent.runner import AgentRunner
 from nanobot.agent.tools.base import Tool, ToolResult
 from nanobot.agent.tools.context import ToolContext
+from nanobot.agent.tools.execution import execute_tool_calls
 from nanobot.agent.tools.loader import ToolLoader
 from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.config.schema import AgentDefaults
@@ -150,31 +153,69 @@ def _tool_message(result, tool_call_id: str) -> dict:
 
 
 @pytest.mark.asyncio
-async def test_runner_propagates_tool_preparation_failure():
+async def test_tool_execution_propagates_preparation_failure():
     tools = MagicMock()
     tools.prepare_call.side_effect = RuntimeError("tool preparation failed")
     tools.execute = AsyncMock()
 
     with pytest.raises(RuntimeError, match="tool preparation failed"):
-        await AgentRunner()._run_tool(
-            make_run_spec(
-                MagicMock(),
-                initial_messages=[],
-                tools=tools,
-                model="test-model",
-                max_iterations=1,
-                max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-            ),
-            ToolCallRequest(id="call-1", name="demo", arguments={}),
-            {},
-            {},
+        await execute_tool_calls(
+            tools,
+            [ToolCallRequest(id="call-1", name="demo", arguments={})],
+            concurrent=False,
+            external_lookup_counts={},
+            workspace_violation_counts={},
+            hook=AgentHook(),
+            context=AgentHookContext(iteration=0, messages=[]),
         )
 
     tools.execute.assert_not_awaited()
 
 
 @pytest.mark.asyncio
-async def test_runner_batches_read_only_tools_before_exclusive_work():
+async def test_tool_execution_propagates_cancellation_without_error_hook():
+    tools = MagicMock()
+    tools.prepare_call.return_value = (None, {}, None)
+    tools.execute = AsyncMock(side_effect=asyncio.CancelledError)
+
+    events: list[str] = []
+
+    class RecordingHook(AgentHook):
+        async def before_execute_tool(
+            self,
+            context: AgentHookContext,
+            tool_call: ToolCallRequest,
+            tool: Any,
+            params: Any,
+        ) -> None:
+            events.append("before")
+
+        async def on_execute_tool_error(
+            self,
+            context: AgentHookContext,
+            tool_call: ToolCallRequest,
+            tool: Any,
+            params: Any,
+            error: Any,
+        ) -> None:
+            events.append("error")
+
+    with pytest.raises(asyncio.CancelledError):
+        await execute_tool_calls(
+            tools,
+            [ToolCallRequest(id="call-1", name="demo", arguments={})],
+            concurrent=False,
+            external_lookup_counts={},
+            workspace_violation_counts={},
+            hook=RecordingHook(),
+            context=AgentHookContext(iteration=0, messages=[]),
+        )
+
+    assert events == ["before"]
+
+
+@pytest.mark.asyncio
+async def test_tool_execution_batches_read_only_tools_before_exclusive_work():
     tools = ToolRegistry()
     shared_events: list[str] = []
     read_a = _DelayTool("read_a", delay=0.05, read_only=True, shared_events=shared_events)
@@ -184,24 +225,18 @@ async def test_runner_batches_read_only_tools_before_exclusive_work():
     tools.register(read_b)
     tools.register(write_a)
 
-    provider = MagicMock()
-    runner = AgentRunner()
-    await runner._execute_tools(
-        make_run_spec(provider,
-            initial_messages=[],
-            tools=tools,
-            model="test-model",
-            max_iterations=1,
-            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-            concurrent_tools=True,
-        ),
+    await execute_tool_calls(
+        tools,
         [
             ToolCallRequest(id="ro1", name="read_a", arguments={}),
             ToolCallRequest(id="ro2", name="read_b", arguments={}),
             ToolCallRequest(id="rw1", name="write_a", arguments={}),
         ],
-        {},
-        {},
+        concurrent=True,
+        external_lookup_counts={},
+        workspace_violation_counts={},
+        hook=AgentHook(),
+        context=AgentHookContext(iteration=0, messages=[]),
     )
 
     assert shared_events[0:2] == ["start:read_a", "start:read_b"]
@@ -212,7 +247,7 @@ async def test_runner_batches_read_only_tools_before_exclusive_work():
 
 
 @pytest.mark.asyncio
-async def test_runner_does_not_batch_exclusive_read_only_tools():
+async def test_tool_execution_does_not_batch_exclusive_read_only_tools():
     tools = ToolRegistry()
     shared_events: list[str] = []
     read_a = _DelayTool("read_a", delay=0.03, read_only=True, shared_events=shared_events)
@@ -228,24 +263,18 @@ async def test_runner_does_not_batch_exclusive_read_only_tools():
     tools.register(ddg_like)
     tools.register(read_b)
 
-    provider = MagicMock()
-    runner = AgentRunner()
-    await runner._execute_tools(
-        make_run_spec(provider,
-            initial_messages=[],
-            tools=tools,
-            model="test-model",
-            max_iterations=1,
-            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-            concurrent_tools=True,
-        ),
+    await execute_tool_calls(
+        tools,
         [
             ToolCallRequest(id="ro1", name="read_a", arguments={}),
             ToolCallRequest(id="ddg1", name="ddg_like", arguments={}),
             ToolCallRequest(id="ro2", name="read_b", arguments={}),
         ],
-        {},
-        {},
+        concurrent=True,
+        external_lookup_counts={},
+        workspace_violation_counts={},
+        hook=AgentHook(),
+        context=AgentHookContext(iteration=0, messages=[]),
     )
 
     assert shared_events[0] == "start:read_a"

tests/agent/tools/test_subagent_tools.py

@@ -376,9 +376,10 @@ async def test_inline_spawn_waits_for_concurrency_capacity(tmp_path):
 @pytest.mark.asyncio
 async def test_runner_executes_inline_spawn_batch_concurrently(tmp_path):
     """Adjacent blocking consultations should share one concurrent tool batch."""
-    from nanobot.agent.runner import AgentRunner, AgentRunSpec
+    from nanobot.agent.hook import AgentHook, AgentHookContext
     from nanobot.agent.subagent import SubagentManager
     from nanobot.agent.tools.context import RequestContext, request_context
+    from nanobot.agent.tools.execution import execute_tool_calls
     from nanobot.agent.tools.registry import ToolRegistry
     from nanobot.agent.tools.spawn import SpawnTool
     from nanobot.bus.queue import MessageBus
@@ -410,14 +411,6 @@ async def test_runner_executes_inline_spawn_batch_concurrently(tmp_path):
     tools = ToolRegistry()
     tools.register(SpawnTool(manager))
     runtime = _runtime(MagicMock())
-    spec = AgentRunSpec(
-        initial_messages=[],
-        tools=tools,
-        runtime=runtime,
-        max_iterations=1,
-        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        concurrent_tools=True,
-    )
     calls = [
         ToolCallRequest(
             id="spawn-1",
@@ -437,7 +430,15 @@ async def test_runner_executes_inline_spawn_batch_concurrently(tmp_path):
         session_key="test:c1",
         runtime=runtime,
     )):
-        execution = asyncio.create_task(AgentRunner()._execute_tools(spec, calls, {}, {}))
+        execution = asyncio.create_task(execute_tool_calls(
+            tools,
+            calls,
+            concurrent=True,
+            external_lookup_counts={},
+            workspace_violation_counts={},
+            hook=AgentHook(),
+            context=AgentHookContext(iteration=0, messages=[], session_key="test:c1"),
+        ))
         await asyncio.wait_for(both_entered.wait(), timeout=1.0)
         release.set()
         results, events = await execution

tests/cli/test_commands.py

@@ -799,7 +799,7 @@ def test_provider_login_can_set_xai_grok_as_main_provider(tmp_path):
 
     saved = Config.model_validate(json.loads(config_path.read_text(encoding="utf-8")))
     assert saved.agents.defaults.provider == "xai_grok"
-    assert saved.agents.defaults.model == "xai-grok/grok-4.5"
+    assert saved.agents.defaults.model == "xai-grok/grok-4.6"
     assert saved.agents.defaults.context_window_tokens == 500_000
     assert saved.agents.defaults.model_preset is None
     assert make_provider(saved).__class__.__name__ == "XAIGrokProvider"
@@ -2654,12 +2654,14 @@ def test_webui_foreground_attaches_to_existing_managed_gateway(monkeypatch, tmp_
     assert seen["lease_release_wait_for_stop"] is False
 
 
-def test_attach_to_background_gateway_detaches_on_ctrl_c(capsys) -> None:
+def test_attach_to_background_gateway_detaches_on_ctrl_c(capsys, tmp_path: Path) -> None:
     stopped = False
+    log_path = tmp_path / "gateway.log"
+    log_path.touch()
 
     class _FakeRuntime:
         def status(self):
-            return SimpleNamespace(running=True)
+            return SimpleNamespace(running=True, log_path=log_path)
 
         def stop(self):
             nonlocal stopped
@@ -2679,10 +2681,88 @@ def test_attach_to_background_gateway_detaches_on_ctrl_c(capsys) -> None:
     assert "WebUI launcher detached" in rendered
 
 
-def test_attach_to_background_gateway_checks_owned_sidecar() -> None:
+def test_attach_to_background_gateway_follows_only_new_logs(capsys, tmp_path: Path) -> None:
+    log_path = tmp_path / "gateway.log"
+    log_path.write_text("historical log\n", encoding="utf-8")
+    polls = 0
+
     class _FakeRuntime:
         def status(self):
-            return SimpleNamespace(running=True)
+            return SimpleNamespace(running=True, log_path=log_path)
+
+    def _append_then_interrupt(_seconds: float) -> None:
+        nonlocal polls
+        if polls == 0:
+            with log_path.open("a", encoding="utf-8") as handle:
+                handle.write("[websocket] live log\n")
+            polls += 1
+            return
+        raise KeyboardInterrupt
+
+    cli_webui_support._attach_to_background_gateway(
+        _FakeRuntime(),
+        sleep=_append_then_interrupt,
+    )
+
+    output = capsys.readouterr().out
+    assert "[websocket] live log" in output
+    assert "historical log" not in output
+
+
+def test_read_new_gateway_logs_recovers_after_truncation(tmp_path: Path) -> None:
+    log_path = tmp_path / "gateway.log"
+    log_path.write_text("a much longer historical log line\n", encoding="utf-8")
+    cursor = cli_webui_support._start_gateway_log_cursor(log_path)
+    log_path.write_text("fresh log\n", encoding="utf-8")
+
+    lines = cli_webui_support._read_new_gateway_logs(log_path, cursor)
+
+    assert lines == ["fresh log"]
+    assert cursor.offset == log_path.stat().st_size
+
+
+def test_read_new_gateway_logs_detects_fast_rewrite_past_offset(tmp_path: Path) -> None:
+    log_path = tmp_path / "gateway.log"
+    log_path.write_text("historical log\n", encoding="utf-8")
+    cursor = cli_webui_support._start_gateway_log_cursor(log_path)
+    log_path.write_text("first fresh log\nsecond fresh log\n", encoding="utf-8")
+
+    lines = cli_webui_support._read_new_gateway_logs(log_path, cursor)
+
+    assert lines == ["first fresh log", "second fresh log"]
+
+
+def test_read_new_gateway_logs_waits_for_complete_utf8_line(tmp_path: Path) -> None:
+    log_path = tmp_path / "gateway.log"
+    log_path.touch()
+    cursor = cli_webui_support._start_gateway_log_cursor(log_path)
+    encoded = "模型 ready\n".encode()
+    log_path.write_bytes(encoded[:2])
+
+    assert cli_webui_support._read_new_gateway_logs(log_path, cursor) == []
+
+    with log_path.open("ab") as handle:
+        handle.write(encoded[2:])
+
+    assert cli_webui_support._read_new_gateway_logs(log_path, cursor) == ["模型 ready"]
+
+
+def test_read_new_gateway_logs_tolerates_missing_file(tmp_path: Path) -> None:
+    log_path = tmp_path / "missing.log"
+    cursor = cli_webui_support._start_gateway_log_cursor(log_path)
+    lines = cli_webui_support._read_new_gateway_logs(log_path, cursor)
+
+    assert lines == []
+    assert cursor.offset == 0
+
+
+def test_attach_to_background_gateway_checks_owned_sidecar(tmp_path: Path) -> None:
+    log_path = tmp_path / "gateway.log"
+    log_path.touch()
+
+    class _FakeRuntime:
+        def status(self):
+            return SimpleNamespace(running=True, log_path=log_path)
 
     def sidecar_exited() -> None:
         raise WebUIDevError("WebUI development server exited unexpectedly (code 23)")

tests/cli/test_entry.py

@@ -1,4 +1,85 @@
-from nanobot.cli.entry import _native_tui_candidate
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+from nanobot.cli import entry
+from nanobot.cli.entry import _agent_invocation_args, _native_tui_candidate
+
+
+def test_root_command_routes_to_agent_without_copying_agent_options() -> None:
+    assert _agent_invocation_args([]) == []
+    assert _agent_invocation_args(["agent", "--theme", "dark"]) == ["--theme", "dark"]
+    assert _agent_invocation_args(["--workspace", "./project"]) == [
+        "--workspace",
+        "./project",
+    ]
+    assert _agent_invocation_args(["-mhello"]) == ["-mhello"]
+
+
+def test_root_metadata_and_subcommands_keep_the_root_cli() -> None:
+    for args in (
+        ["--help"],
+        ["--version"],
+        ["--install-completion"],
+        ["gateway"],
+        ["webui"],
+    ):
+        assert _agent_invocation_args(args) is None
+
+
+def test_root_shell_completion_keeps_root_subcommands() -> None:
+    env = os.environ.copy()
+    env.update(
+        {
+            "_NANOBOT_COMPLETE": "complete_bash",
+            "COMP_WORDS": "nanobot ",
+            "COMP_CWORD": "1",
+        }
+    )
+    script = (
+        "import sys; "
+        "from nanobot.cli.entry import main; "
+        "sys.argv = ['nanobot']; "
+        "main()"
+    )
+
+    result = subprocess.run(
+        [sys.executable, "-c", script],
+        cwd=Path(__file__).parents[2],
+        env=env,
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+
+    assert result.returncode == 0, result.stderr
+    assert {"agent", "gateway", "webui"} <= set(result.stdout.splitlines())
+    assert "not supported" not in result.stderr
+
+
+def test_root_alias_dispatches_the_shared_agent_command(monkeypatch) -> None:
+    calls: dict[str, object] = {}
+    monkeypatch.setattr(entry.sys, "argv", ["nanobot", "-m", "hello"])
+    monkeypatch.setattr(
+        entry,
+        "set_cli_process_identity",
+        lambda args: calls.__setitem__("identity", args),
+    )
+    monkeypatch.setattr(entry, "_configure_windows_console", lambda: None)
+    monkeypatch.setattr(
+        entry,
+        "_run_agent",
+        lambda args, *, prog_name: calls.update(args=args, prog_name=prog_name),
+    )
+
+    entry.main()
+
+    assert calls == {
+        "identity": ["agent", "-m", "hello"],
+        "args": ["-m", "hello"],
+        "prog_name": "nanobot",
+    }
 
 
 def test_native_agent_invocations_use_the_lightweight_entrypoint() -> None:

tests/cli/test_process_identity.py

@@ -58,6 +58,24 @@ def test_legacy_console_entrypoint_still_sets_subcommand_identity(
     assert commands == [["webui"]]
 
 
+def test_legacy_console_entrypoint_routes_bare_command_to_agent(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    identities: list[list[str]] = []
+    launches: list[tuple[list[str], str]] = []
+    monkeypatch.setattr("nanobot.cli.commands.set_cli_process_identity", identities.append)
+    monkeypatch.setattr(
+        "nanobot.cli.entry._run_agent",
+        lambda args, *, prog_name: launches.append((args, prog_name)),
+    )
+
+    result = CliRunner().invoke(app, [])
+
+    assert result.exit_code == 0
+    assert identities == [["agent"]]
+    assert launches == [([], "nanobot")]
+
+
 def test_named_executable_creates_stable_role_symlink(
     tmp_path: Path,
 ) -> None:

tests/providers/test_oauth_model_catalog.py

@@ -0,0 +1,504 @@
+from __future__ import annotations
+
+import base64
+import json
+import threading
+import time
+from concurrent.futures import ThreadPoolExecutor
+from pathlib import Path
+from types import SimpleNamespace
+
+import httpx
+import pytest
+
+from nanobot.providers.oauth_model_catalog import (
+    OAuthModelCatalog,
+    get_oauth_model_catalog,
+    invalidate_oauth_model_catalog,
+)
+from nanobot.providers.openai_codex_provider import (
+    DEFAULT_OPENAI_CODEX_MODELS_URL,
+    OPENAI_CODEX_CATALOG_CLIENT_VERSION,
+)
+from nanobot.providers.registry import ProviderModelSpec
+from nanobot.providers.xai_grok_provider import DEFAULT_XAI_GROK_MODELS_URL
+from nanobot.providers.xai_oauth import XAIToken
+
+
+@pytest.fixture(autouse=True)
+def _clear_oauth_catalogs() -> None:
+    for provider in ("openai_codex", "xai_grok", "github_copilot"):
+        invalidate_oauth_model_catalog(provider)
+    yield
+    for provider in ("openai_codex", "xai_grok", "github_copilot"):
+        invalidate_oauth_model_catalog(provider)
+
+
+def _fallback_model() -> ProviderModelSpec:
+    return ProviderModelSpec(id="provider/fallback", label="Fallback")
+
+
+def test_xai_catalog_fetches_remote_models_and_reuses_capability_metadata(
+    monkeypatch: pytest.MonkeyPatch,
+    tmp_path: Path,
+) -> None:
+    original_client = httpx.Client
+    captured: dict[str, object] = {}
+    payload = (
+        base64.urlsafe_b64encode(
+            json.dumps({"sub": "user-42", "email": "user@example.com"}).encode()
+        )
+        .decode()
+        .rstrip("=")
+    )
+    token = XAIToken(
+        access=f"header.{payload}.signature",
+        refresh="refresh-token",
+        expires=int(time.time() * 1000) + 3_600_000,
+        account_id="user@example.com",
+    )
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        captured["request"] = request
+        return httpx.Response(
+            200,
+            json={
+                "data": [
+                    {
+                        "id": "grok-4.6",
+                        "name": "Grok 4.6",
+                        "description": "Latest frontier model",
+                        "owned_by": "xAI",
+                        "context_window": 500_000,
+                        "supports_backend_search": True,
+                        "reasoning_efforts": [
+                            {"value": "xhigh"},
+                            {"value": "high"},
+                            {"value": "low"},
+                        ],
+                    },
+                    {
+                        "id": "grok-next",
+                        "_meta": {
+                            "name": "Grok Next",
+                            "context_window": 750_000,
+                            "reasoning_efforts": ["high", "low"],
+                        },
+                    },
+                ]
+            },
+            request=request,
+        )
+
+    def fake_client(**kwargs: object) -> httpx.Client:
+        captured["kwargs"] = kwargs
+        return original_client(
+            transport=httpx.MockTransport(handler),
+            timeout=kwargs["timeout"],
+            follow_redirects=kwargs["follow_redirects"],
+        )
+
+    monkeypatch.setattr(
+        "nanobot.providers.xai_grok_provider.get_xai_oauth_storage_path",
+        lambda: tmp_path / "auth" / "xai.json",
+    )
+    monkeypatch.setattr(
+        "nanobot.providers.xai_grok_provider.get_xai_oauth_login_status",
+        lambda: token,
+    )
+    monkeypatch.setattr(
+        "nanobot.providers.xai_grok_provider.get_xai_oauth_token",
+        lambda **_kwargs: token,
+    )
+    monkeypatch.setattr("nanobot.providers.xai_grok_provider.httpx.Client", fake_client)
+
+    catalog = get_oauth_model_catalog("xai_grok")
+
+    assert catalog.source == "remote"
+    assert [model.id for model in catalog.models] == [
+        "xai-grok/grok-4.6",
+        "xai-grok/grok-next",
+    ]
+    grok = catalog.find("grok-4.6")
+    assert grok is not None
+    assert grok.description == "Latest frontier model"
+    assert grok.context_window == 500_000
+    assert grok.reasoning_efforts == ("xhigh", "high", "low")
+    assert grok.supports_backend_search is True
+    next_model = catalog.find("xai-grok/grok-next")
+    assert next_model is not None
+    assert next_model.label == "Grok Next"
+    assert next_model.context_window == 750_000
+    assert next_model.reasoning_efforts == ("high", "low")
+
+    request = captured["request"]
+    assert isinstance(request, httpx.Request)
+    assert str(request.url) == DEFAULT_XAI_GROK_MODELS_URL
+    assert request.headers["Authorization"] == f"Bearer {token.access}"
+    assert request.headers["X-XAI-Token-Auth"] == "xai-grok-cli"
+    assert request.headers["x-userid"] == "user-42"
+    assert request.headers["x-email"] == "user@example.com"
+    assert captured["kwargs"] == {"timeout": 10.0, "follow_redirects": False}
+    assert get_oauth_model_catalog("xai_grok").source == "cache"
+
+
+def test_openai_codex_catalog_uses_account_catalog_and_filters_hidden_models(
+    monkeypatch: pytest.MonkeyPatch,
+    tmp_path: Path,
+) -> None:
+    original_client = httpx.Client
+    captured: dict[str, object] = {}
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        captured["request"] = request
+        return httpx.Response(
+            200,
+            json={
+                "models": [
+                    {
+                        "slug": "gpt-new",
+                        "display_name": "GPT New",
+                        "description": "New model",
+                        "context_window": 300_000,
+                        "priority": 2,
+                        "visibility": "list",
+                        "supported_reasoning_levels": [
+                            {"effort": "low"},
+                            {"effort": "high"},
+                        ],
+                    },
+                    {
+                        "slug": "gpt-first",
+                        "display_name": "GPT First",
+                        "priority": 1,
+                    },
+                    {
+                        "slug": "internal-model",
+                        "display_name": "Internal",
+                        "visibility": "hide",
+                        "priority": 0,
+                    },
+                ]
+            },
+            request=request,
+        )
+
+    def fake_client(**kwargs: object) -> httpx.Client:
+        captured["kwargs"] = kwargs
+        return original_client(
+            transport=httpx.MockTransport(handler),
+            timeout=kwargs["timeout"],
+            follow_redirects=kwargs["follow_redirects"],
+        )
+
+    class Storage:
+        def load(self) -> SimpleNamespace:
+            return SimpleNamespace(access="secret", account_id="account-42")
+
+        def get_token_path(self) -> Path:
+            return tmp_path / "auth" / "openai-codex.json"
+
+    monkeypatch.setattr(
+        "nanobot.providers.openai_codex_provider.FileTokenStorage",
+        lambda **_kwargs: Storage(),
+    )
+    monkeypatch.setattr(
+        "nanobot.providers.openai_codex_provider.get_codex_token",
+        lambda **_kwargs: SimpleNamespace(access="secret", account_id="account-42"),
+    )
+    monkeypatch.setattr("nanobot.providers.openai_codex_provider.httpx.Client", fake_client)
+
+    catalog = get_oauth_model_catalog("openai_codex")
+
+    assert catalog.source == "remote"
+    assert [model.id for model in catalog.models] == [
+        "openai-codex/gpt-first",
+        "openai-codex/gpt-new",
+    ]
+    assert catalog.models[1].context_window == 300_000
+    assert catalog.models[1].reasoning_efforts == ("low", "high")
+    request = captured["request"]
+    assert isinstance(request, httpx.Request)
+    assert request.url.copy_with(query=None) == httpx.URL(DEFAULT_OPENAI_CODEX_MODELS_URL)
+    assert request.url.params["client_version"] == OPENAI_CODEX_CATALOG_CLIENT_VERSION
+    assert request.headers["Authorization"] == "Bearer secret"
+    assert request.headers["chatgpt-account-id"] == "account-42"
+
+
+def test_github_copilot_catalog_only_lists_compatible_chat_models(
+    monkeypatch: pytest.MonkeyPatch,
+    tmp_path: Path,
+) -> None:
+    original_client = httpx.Client
+    captured: list[httpx.Request] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        captured.append(request)
+        if request.url.path.endswith("/copilot_internal/v2/token"):
+            return httpx.Response(
+                200,
+                json={
+                    "token": "copilot-secret",
+                    "endpoints": {"api": "https://api.individual.githubcopilot.com"},
+                },
+                request=request,
+            )
+        return httpx.Response(
+            200,
+            json={
+                "data": [
+                    {
+                        "id": "claude-sonnet",
+                        "name": "Claude Sonnet",
+                        "model_picker_enabled": True,
+                        "policy": {"state": "enabled"},
+                        "supported_endpoints": ["/chat/completions"],
+                        "capabilities": {
+                            "supports": {"reasoning_effort": ["low", "high"]},
+                            "limits": {"max_context_window_tokens": 200_000},
+                        },
+                    },
+                    {
+                        "id": "gpt-5.4-mini",
+                        "name": "GPT-5.4 Mini",
+                        "model_picker_enabled": True,
+                        "supported_endpoints": ["/responses"],
+                    },
+                    {
+                        "id": "unknown-responses-only",
+                        "name": "Unknown Responses only",
+                        "model_picker_enabled": True,
+                        "supported_endpoints": ["/responses"],
+                    },
+                    {
+                        "id": "disabled",
+                        "model_picker_enabled": True,
+                        "policy": {"state": "disabled"},
+                        "supported_endpoints": ["/chat/completions"],
+                    },
+                ]
+            },
+            request=request,
+        )
+
+    def fake_client(**kwargs: object) -> httpx.Client:
+        return original_client(
+            transport=httpx.MockTransport(handler),
+            timeout=kwargs["timeout"],
+            follow_redirects=kwargs["follow_redirects"],
+        )
+
+    class Storage:
+        def load(self) -> SimpleNamespace:
+            return SimpleNamespace(access="github-secret", account_id="octocat")
+
+        def get_token_path(self) -> Path:
+            return tmp_path / "auth" / "github-copilot.json"
+
+    monkeypatch.setattr(
+        "nanobot.providers.github_copilot_provider.get_storage",
+        lambda: Storage(),
+    )
+    monkeypatch.setattr("nanobot.providers.github_copilot_provider.httpx.Client", fake_client)
+
+    catalog = get_oauth_model_catalog("github_copilot")
+
+    assert catalog.source == "remote"
+    assert [model.id for model in catalog.models] == [
+        "github-copilot/claude-sonnet",
+        "github-copilot/gpt-5.4-mini",
+    ]
+    assert catalog.models[0].context_window == 200_000
+    assert catalog.models[0].reasoning_efforts == ("low", "high")
+    assert len(captured) == 2
+    assert captured[0].headers["Authorization"] == "token github-secret"
+    assert captured[1].headers["Authorization"] == "Bearer copilot-secret"
+    assert str(captured[1].url) == "https://api.individual.githubcopilot.com/models"
+    assert get_oauth_model_catalog("github_copilot").source == "cache"
+    assert get_oauth_model_catalog(
+        "github_copilot",
+        proxy="http://proxy.example:8080",
+    ).source == "remote"
+    assert len(captured) == 4
+
+
+def test_catalog_single_flights_concurrent_refreshes() -> None:
+    calls = 0
+    calls_lock = threading.Lock()
+    barrier = threading.Barrier(8)
+
+    def fetch(_proxy: str | None) -> tuple[ProviderModelSpec, ...]:
+        nonlocal calls
+        with calls_lock:
+            calls += 1
+        time.sleep(0.05)
+        return (ProviderModelSpec(id="provider/remote", label="Remote"),)
+
+    catalog = OAuthModelCatalog(fallback_models=(_fallback_model(),), fetch=fetch)
+
+    def get_catalog(_index: int):
+        barrier.wait()
+        return catalog.get(cache_key="shared")
+
+    with ThreadPoolExecutor(max_workers=8) as pool:
+        results = list(pool.map(get_catalog, range(8)))
+
+    assert calls == 1
+    assert {result.models[0].id for result in results} == {"provider/remote"}
+    assert [result.source for result in results].count("remote") == 1
+    assert [result.source for result in results].count("cache") == 7
+
+
+def test_catalog_invalidation_discards_an_inflight_account_refresh() -> None:
+    started = threading.Event()
+    release = threading.Event()
+    identity = ["old-account"]
+
+    def fetch(_proxy: str | None) -> tuple[ProviderModelSpec, ...]:
+        current = identity[0]
+        if current == "old-account":
+            started.set()
+            assert release.wait(timeout=2)
+        return (ProviderModelSpec(id=f"provider/{current}", label=current),)
+
+    catalog = OAuthModelCatalog(fallback_models=(_fallback_model(),), fetch=fetch)
+    with ThreadPoolExecutor(max_workers=2) as pool:
+        old_future = pool.submit(catalog.get, cache_key="old-key")
+        assert started.wait(timeout=2)
+        identity[0] = "new-account"
+        catalog.invalidate()
+        new_future = pool.submit(catalog.get, cache_key="new-key")
+        new_result = new_future.result(timeout=2)
+        release.set()
+        old_result = old_future.result(timeout=2)
+
+    assert old_result.source == "fallback"
+    assert new_result.models[0].id == "provider/new-account"
+
+    identity[0] = "old-account"
+    assert catalog.get(cache_key="old-key").models[0].id == "provider/old-account"
+
+
+def test_catalog_bounds_failure_only_keys() -> None:
+    calls = 0
+
+    def fetch(_proxy: str | None) -> tuple[ProviderModelSpec, ...]:
+        nonlocal calls
+        calls += 1
+        raise httpx.ConnectError("offline")
+
+    catalog = OAuthModelCatalog(
+        fallback_models=(_fallback_model(),),
+        fetch=fetch,
+        max_entries=2,
+    )
+
+    for key in ("one", "two", "three"):
+        assert catalog.get(cache_key=key).source == "fallback"
+
+    assert calls == 3
+    assert catalog.get(cache_key="one").source == "fallback"
+    assert calls == 4
+
+
+def test_catalog_returns_stale_then_negative_caches_refresh_failure() -> None:
+    now = [0.0]
+    calls = 0
+
+    def fetch(_proxy: str | None) -> tuple[ProviderModelSpec, ...]:
+        nonlocal calls
+        calls += 1
+        if calls > 1:
+            raise httpx.ConnectError("offline")
+        return (ProviderModelSpec(id="provider/remote", label="Remote"),)
+
+    catalog = OAuthModelCatalog(
+        fallback_models=(_fallback_model(),),
+        fetch=fetch,
+        fresh_ttl_s=10,
+        stale_ttl_s=100,
+        failure_ttl_s=30,
+        monotonic=lambda: now[0],
+        wall_clock=lambda: 123.0,
+    )
+
+    assert catalog.get(cache_key="one").source == "remote"
+    now[0] = 11
+    stale = catalog.get(cache_key="one")
+    assert stale.source == "stale"
+    assert stale.models[0].id == "provider/remote"
+    assert catalog.get(cache_key="one").source == "stale"
+    assert calls == 2
+
+    now[0] = 101
+    fallback = catalog.get(cache_key="one")
+    assert fallback.source == "fallback"
+    assert fallback.models[0].id == "provider/fallback"
+    assert calls == 3
+
+
+@pytest.mark.parametrize(
+    "failure",
+    [
+        httpx.ConnectError("offline"),
+        ValueError("invalid JSON"),
+        httpx.HTTPStatusError(
+            "unauthorized",
+            request=httpx.Request("GET", DEFAULT_XAI_GROK_MODELS_URL),
+            response=httpx.Response(401),
+        ),
+        httpx.HTTPStatusError(
+            "rate limited",
+            request=httpx.Request("GET", DEFAULT_XAI_GROK_MODELS_URL),
+            response=httpx.Response(429),
+        ),
+        httpx.HTTPStatusError(
+            "upstream failure",
+            request=httpx.Request("GET", DEFAULT_XAI_GROK_MODELS_URL),
+            response=httpx.Response(503),
+        ),
+    ],
+)
+def test_catalog_falls_back_for_remote_failures(failure: Exception) -> None:
+    calls = 0
+
+    def fetch(_proxy: str | None) -> tuple[ProviderModelSpec, ...]:
+        nonlocal calls
+        calls += 1
+        raise failure
+
+    catalog = OAuthModelCatalog(
+        fallback_models=(_fallback_model(),),
+        fetch=fetch,
+        failure_ttl_s=30,
+    )
+
+    first = catalog.get(cache_key="one")
+    second = catalog.get(cache_key="one")
+
+    assert first.source == "fallback"
+    assert second.source == "fallback"
+    assert first.models == (_fallback_model(),)
+    assert calls == 1
+
+
+def test_catalog_treats_empty_remote_list_as_failure_and_can_be_invalidated() -> None:
+    calls = 0
+
+    def fetch(_proxy: str | None) -> tuple[ProviderModelSpec, ...]:
+        nonlocal calls
+        calls += 1
+        return () if calls == 1 else (ProviderModelSpec(id="provider/new", label="New"),)
+
+    catalog = OAuthModelCatalog(
+        fallback_models=(_fallback_model(),),
+        fetch=fetch,
+        failure_ttl_s=30,
+    )
+
+    assert catalog.get(cache_key="one").source == "fallback"
+    catalog.invalidate()
+    refreshed = catalog.get(cache_key="one")
+    assert refreshed.source == "remote"
+    assert refreshed.models[0].id == "provider/new"
+    assert calls == 2

tests/providers/test_xai_grok_provider.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import base64
 import json
 import time
 from types import SimpleNamespace
@@ -12,21 +11,19 @@ import pytest
 from nanobot.config.schema import Config
 from nanobot.providers.base import LLMUsage
 from nanobot.providers.factory import make_provider
-from nanobot.providers.registry import find_by_name
+from nanobot.providers.oauth_model_catalog import OAuthModelCatalogSnapshot
+from nanobot.providers.registry import ProviderModelSpec, find_by_name
 from nanobot.providers.xai_grok_provider import (
     DEFAULT_XAI_GROK_MODEL,
-    DEFAULT_XAI_GROK_MODELS_URL,
     XAIGrokProvider,
     _bounded_error_body,
     _build_headers,
-    _build_model_headers,
     _build_reasoning_options,
     _build_xai_http_error,
-    _fetch_xai_model_capabilities,
-    _parse_xai_model_capabilities,
     _request_xai,
     _xai_error_response,
     _XAIHTTPError,
+    _XAIIncompleteHostedToolError,
 )
 
 
@@ -51,22 +48,41 @@ def _mock_model_capabilities(
     *,
     supports_backend_search: bool,
 ) -> None:
-    async def fake_fetch(*_args, **_kwargs):
-        return {"grok-4.5": supports_backend_search}
+    def fake_catalog(*_args, **_kwargs):
+        return OAuthModelCatalogSnapshot(
+            models=(
+                ProviderModelSpec(
+                    id="xai-grok/grok-4.5",
+                    label="Grok 4.5",
+                    supports_backend_search=supports_backend_search,
+                ),
+                ProviderModelSpec(
+                    id="xai-grok/grok-4.6",
+                    label="Grok 4.6",
+                    supports_backend_search=supports_backend_search,
+                ),
+            ),
+            source="remote",
+            fetched_at=1,
+        )
 
     monkeypatch.setattr(
-        "nanobot.providers.xai_grok_provider._fetch_xai_model_capabilities",
-        fake_fetch,
+        "nanobot.providers.xai_grok_provider.get_xai_grok_model_catalog",
+        fake_catalog,
     )
 
 
-def test_xai_grok_registry_exposes_curated_x_search_model() -> None:
+def test_xai_grok_registry_exposes_curated_x_search_models() -> None:
     spec = find_by_name("xai_grok")
 
     assert spec is not None
     assert spec.is_oauth is True
     assert spec.backend == "xai_grok"
     assert spec.builtin_models[0].id == DEFAULT_XAI_GROK_MODEL
+    assert [model.id for model in spec.builtin_models] == [
+        "xai-grok/grok-4.6",
+        "xai-grok/grok-4.5",
+    ]
     assert spec.builtin_models[0].context_window == 500000
     assert "when supported" in spec.builtin_models[0].description
 
@@ -117,7 +133,7 @@ async def test_provider_injects_hosted_x_search_and_required_proxy_headers(monke
     assert response.content == "answer [[1]](https://x.com/example/status/1)"
     url, headers, body = calls[0]
     assert url == "https://cli-chat-proxy.grok.com/v1/responses"
-    assert body["model"] == "grok-4.5"
+    assert body["model"] == "grok-4.6"
     assert body["tools"] == [
         {
             "type": "function",
@@ -132,12 +148,13 @@ async def test_provider_injects_hosted_x_search_and_required_proxy_headers(monke
     assert body["stream_tool_calls"] is True
     assert body["reasoning"] == {"summary": "concise", "effort": "high"}
     assert body["store"] is False
+    assert body["max_turns"] == 5
     assert headers["Authorization"] == "Bearer subscription-token"
     assert headers["X-XAI-Token-Auth"] == "xai-grok-cli"
     assert headers["x-authenticateresponse"] == "authenticate-response"
     assert headers["x-grok-client-identifier"] == "nanobot"
     assert headers["x-grok-client-mode"] == "headless"
-    assert headers["x-grok-model-override"] == "grok-4.5"
+    assert headers["x-grok-model-override"] == "grok-4.6"
 
 
 @pytest.mark.asyncio
@@ -147,7 +164,7 @@ async def test_explicit_parameterized_x_search_is_preserved_without_catalog_look
     _mock_token(monkeypatch)
     bodies: list[dict[str, Any]] = []
 
-    async def unexpected_catalog_lookup(*_args, **_kwargs):
+    def unexpected_catalog_lookup(*_args, **_kwargs):
         raise AssertionError("explicit raw tools must not depend on model catalog metadata")
 
     async def fake_request(_url, _headers, body, **_kwargs):
@@ -155,7 +172,7 @@ async def test_explicit_parameterized_x_search_is_preserved_without_catalog_look
         return "ok", [], "stop", {}, None
 
     monkeypatch.setattr(
-        "nanobot.providers.xai_grok_provider._fetch_xai_model_capabilities",
+        "nanobot.providers.xai_grok_provider.get_xai_grok_model_catalog",
         unexpected_catalog_lookup,
     )
     monkeypatch.setattr("nanobot.providers.xai_grok_provider._request_xai", fake_request)
@@ -164,10 +181,12 @@ async def test_explicit_parameterized_x_search_is_preserved_without_catalog_look
         "allowed_x_handles": ["nanobot_ai"],
         "from_date": "2026-01-01",
     }
-    provider = XAIGrokProvider(extra_body={
+    provider = XAIGrokProvider(
+        extra_body={
             "parallel_tool_calls": False,
             "tools": [hosted_tool, {"type": "code_interpreter", "container": "auto"}],
-    })
+        }
+    )
 
     response = await provider.chat(
         [{"role": "user", "content": "search"}],
@@ -210,7 +229,7 @@ async def test_explicit_empty_tools_disables_catalog_lookup_and_hosted_tool(monk
     _mock_token(monkeypatch)
     bodies: list[dict[str, Any]] = []
 
-    async def unexpected_catalog_lookup(*_args, **_kwargs):
+    def unexpected_catalog_lookup(*_args, **_kwargs):
         raise AssertionError("explicitly disabled X Search must not fetch model capabilities")
 
     async def fake_request(_url, _headers, body, **_kwargs):
@@ -218,7 +237,7 @@ async def test_explicit_empty_tools_disables_catalog_lookup_and_hosted_tool(monk
         return "ok", [], "stop", {}, None
 
     monkeypatch.setattr(
-        "nanobot.providers.xai_grok_provider._fetch_xai_model_capabilities",
+        "nanobot.providers.xai_grok_provider.get_xai_grok_model_catalog",
         unexpected_catalog_lookup,
     )
     monkeypatch.setattr("nanobot.providers.xai_grok_provider._request_xai", fake_request)
@@ -226,23 +245,28 @@ async def test_explicit_empty_tools_disables_catalog_lookup_and_hosted_tool(monk
 
     response = await provider.chat(
         [{"role": "user", "content": "hello"}],
-        tools=[{
+        tools=[
+            {
                 "type": "function",
                 "function": {
                     "name": "read_file",
                     "description": "Read a file",
                     "parameters": {"type": "object"},
                 },
-        }],
+            }
+        ],
     )
 
     assert response.content == "ok"
-    assert bodies[0]["tools"] == [{
+    assert bodies[0]["tools"] == [
+        {
             "type": "function",
             "name": "read_file",
             "description": "Read a file",
             "parameters": {"type": "object"},
-    }]
+        }
+    ]
+    assert "max_turns" not in bodies[0]
 
 
 @pytest.mark.asyncio
@@ -281,35 +305,8 @@ async def test_provider_keeps_local_x_search_when_model_does_not_support_hosted_
             "parameters": {"type": "object"},
         }
     ]
-
-
-@pytest.mark.asyncio
-async def test_provider_fails_closed_and_caches_model_catalog_failure(monkeypatch) -> None:
-    _mock_token(monkeypatch)
-    fetch_calls = 0
-    bodies: list[dict[str, Any]] = []
-
-    async def failing_fetch(*_args, **_kwargs):
-        nonlocal fetch_calls
-        fetch_calls += 1
-        raise httpx.ConnectError("catalog unavailable")
-
-    async def fake_request(_url, _headers, body, **_kwargs):
-        bodies.append(body)
-        return "ok", [], "stop", {}, None
-
-    monkeypatch.setattr(
-        "nanobot.providers.xai_grok_provider._fetch_xai_model_capabilities",
-        failing_fetch,
-    )
-    monkeypatch.setattr("nanobot.providers.xai_grok_provider._request_xai", fake_request)
-    provider = XAIGrokProvider()
-
-    await provider.chat([{"role": "user", "content": "first"}])
-    await provider.chat([{"role": "user", "content": "second"}])
-
-    assert fetch_calls == 1
-    assert all({"type": "x_search"} not in body["tools"] for body in bodies)
+    assert "max_turns" not in bodies[0]
+    assert bodies[0]["instructions"] == ""
 
 
 @pytest.mark.asyncio
@@ -395,7 +392,10 @@ async def test_factory_builds_xai_provider_and_applies_explicit_body_overrides(m
             "providers": {
                 "xaiGrok": {
                     "proxy": "http://127.0.0.1:7890",
-                    "extraBody": {"parallel_tool_calls": False},
+                    "extraBody": {
+                        "parallel_tool_calls": False,
+                        "max_turns": 2,
+                    },
                 }
             },
         }
@@ -408,6 +408,7 @@ async def test_factory_builds_xai_provider_and_applies_explicit_body_overrides(m
     assert provider.proxy == "http://127.0.0.1:7890"
     assert response.content == "ok"
     assert bodies[0]["parallel_tool_calls"] is False
+    assert bodies[0]["max_turns"] == 2
     assert {"type": "x_search"} in bodies[0]["tools"]
 
 
@@ -527,75 +528,183 @@ async def test_raw_response_request_streams_hosted_x_search_lifecycle(monkeypatc
     assert "large hosted result" not in json.dumps(tool_events)
 
 
-def test_model_capabilities_follow_upstream_aliases_and_default_to_disabled() -> None:
-    capabilities = _parse_xai_model_capabilities(
-        {
-            "data": [
-                {"id": "grok-4.5", "supportsBackendSearch": False},
-                {
-                    "model": "grok-search",
-                    "supports_backend_search": True,
-                },
-                {
-                    "modelId": "grok-meta",
-                    "_meta": {"supportsBackendSearch": True},
-                },
-                {"id": "grok-unknown"},
-            ]
-        }
-    )
-
-    assert capabilities == {
-        "grok-4.5": False,
-        "grok-search": True,
-        "grok-meta": True,
-        "grok-unknown": False,
-    }
-
-
 @pytest.mark.asyncio
-async def test_model_capability_request_uses_subscription_headers(monkeypatch) -> None:
+async def test_raw_response_request_streams_official_x_search_lifecycle(monkeypatch) -> None:
     original_client = httpx.AsyncClient
-    captured: dict[str, Any] = {}
+    events = [
+        {
+            "type": "response.output_item.added",
+            "item": {
+                "type": "x_search_call",
+                "id": "x-search-1",
+                "status": "in_progress",
+                "action": {"query": "nanobot oauth"},
+            },
+        },
+        {
+            "type": "response.output_item.done",
+            "item": {
+                "type": "x_search_call",
+                "id": "x-search-1",
+                "status": "completed",
+                "action": {"query": "nanobot oauth"},
+            },
+        },
+        {
+            "type": "response.completed",
+            "response": {"status": "completed", "usage": {}},
+        },
+    ]
+    content = "".join(f"data: {json.dumps(event)}\n\n" for event in events)
 
     def handler(request: httpx.Request) -> httpx.Response:
-        captured["request"] = request
-        return httpx.Response(
-            200,
-            json={"data": [{"id": "grok-search", "supportsBackendSearch": True}]},
-            request=request,
-        )
+        return httpx.Response(200, content=content, request=request)
 
     def fake_client(**kwargs) -> httpx.AsyncClient:
-        captured["kwargs"] = kwargs
         return original_client(
             transport=httpx.MockTransport(handler),
             timeout=kwargs["timeout"],
-            follow_redirects=kwargs["follow_redirects"],
         )
 
     monkeypatch.setattr("nanobot.providers.xai_grok_provider.httpx.AsyncClient", fake_client)
-    payload = base64.urlsafe_b64encode(
-        json.dumps({"sub": "user-42", "email": "user@example.com"}).encode()
-    ).decode().rstrip("=")
-    access_token = f"header.{payload}.signature"
-    headers = _build_model_headers(_token(access_token))
+    tool_events: list[dict[str, Any]] = []
 
-    capabilities = await _fetch_xai_model_capabilities(
-        DEFAULT_XAI_GROK_MODELS_URL,
-        headers,
+    await _request_xai(
+        "https://cli-chat-proxy.grok.com/v1/responses",
+        _build_headers("secret", "grok-4.6"),
+        {"model": "grok-4.6", "tools": [{"type": "x_search"}]},
+        on_tool_call_delta=lambda event: _append(tool_events, event),
     )
 
-    request = captured["request"]
-    assert isinstance(request, httpx.Request)
-    assert request.method == "GET"
-    assert str(request.url) == DEFAULT_XAI_GROK_MODELS_URL
-    assert request.headers["Authorization"] == f"Bearer {access_token}"
-    assert request.headers["X-XAI-Token-Auth"] == "xai-grok-cli"
-    assert request.headers["x-userid"] == "user-42"
-    assert request.headers["x-email"] == "user@example.com"
-    assert captured["kwargs"] == {"timeout": 10.0, "follow_redirects": False}
-    assert capabilities == {"grok-search": True}
+    assert [(event["phase"], event["name"]) for event in tool_events] == [
+        ("start", "x_search"),
+        ("end", "x_search"),
+    ]
+    assert tool_events[-1]["result"] == {"status": "completed"}
+
+
+@pytest.mark.asyncio
+async def test_raw_response_rejects_unfinished_hosted_tool_and_closes_progress(
+    monkeypatch,
+) -> None:
+    original_client = httpx.AsyncClient
+    events = [
+        {
+            "type": "response.custom_tool_call_input.done",
+            "item_id": "x-search-1",
+            "input": '{"query":"nanobot oauth"}',
+        },
+        {"type": "response.output_text.delta", "delta": "I will keep searching."},
+        {
+            "type": "response.completed",
+            "response": {
+                "status": "completed",
+                "usage": {"input_tokens": 8, "output_tokens": 4, "total_tokens": 12},
+            },
+        },
+    ]
+    content = "".join(f"data: {json.dumps(event)}\n\n" for event in events)
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(200, content=content, request=request)
+
+    def fake_client(**kwargs) -> httpx.AsyncClient:
+        return original_client(
+            transport=httpx.MockTransport(handler),
+            timeout=kwargs["timeout"],
+        )
+
+    monkeypatch.setattr("nanobot.providers.xai_grok_provider.httpx.AsyncClient", fake_client)
+    tool_events: list[dict[str, Any]] = []
+
+    with pytest.raises(_XAIIncompleteHostedToolError) as caught:
+        await _request_xai(
+            "https://cli-chat-proxy.grok.com/v1/responses",
+            _build_headers("secret", "grok-4.6"),
+            {"model": "grok-4.6", "tools": [{"type": "x_search"}]},
+            on_tool_call_delta=lambda event: _append(tool_events, event),
+        )
+
+    assert caught.value.usage == LLMUsage.reported(input_tokens=8, output_tokens=4)
+    assert [event["phase"] for event in tool_events] == ["start", "error"]
+    assert "before this hosted tool completed" in tool_events[-1]["error"]
+
+
+@pytest.mark.asyncio
+async def test_provider_recovers_unfinished_hosted_tool_once_and_preserves_usage(
+    monkeypatch,
+) -> None:
+    _mock_token(monkeypatch)
+    _mock_model_capabilities(monkeypatch, supports_backend_search=True)
+    attempts = 0
+    request_ids: list[str] = []
+    streamed: list[str] = []
+    recovered: list[bool] = []
+    first_usage = LLMUsage.reported(input_tokens=10, output_tokens=2)
+    second_usage = LLMUsage.reported(input_tokens=11, output_tokens=4)
+
+    async def fake_request(_url, headers, body, **kwargs):
+        nonlocal attempts
+        attempts += 1
+        request_ids.append(headers["x-grok-req-id"])
+        assert body["max_turns"] == 5
+        if attempts == 1:
+            await kwargs["on_content_delta"]("I will keep searching.")
+            raise _XAIIncompleteHostedToolError(
+                [{"name": "x_search", "call_id": "search-1"}],
+                usage=first_usage,
+            )
+        await kwargs["on_content_delta"]("Final researched answer.")
+        return "Final researched answer.", [], "stop", second_usage, None
+
+    async def on_recover() -> None:
+        recovered.append(True)
+
+    monkeypatch.setattr("nanobot.providers.xai_grok_provider._request_xai", fake_request)
+    provider = XAIGrokProvider()
+
+    response = await provider.chat_stream_with_retry(
+        [{"role": "user", "content": "Search X"}],
+        on_content_delta=lambda delta: _append(streamed, delta),
+        on_stream_recover=on_recover,
+    )
+
+    assert attempts == 2
+    assert len(set(request_ids)) == 2
+    assert recovered == [True]
+    assert streamed == ["I will keep searching.", "Final researched answer."]
+    assert response.content == "Final researched answer."
+    assert response.usage == first_usage + second_usage
+
+
+@pytest.mark.asyncio
+async def test_provider_preserves_usage_when_hosted_tool_recovery_also_fails(
+    monkeypatch,
+) -> None:
+    _mock_token(monkeypatch)
+    _mock_model_capabilities(monkeypatch, supports_backend_search=True)
+    attempts = 0
+    usage = LLMUsage.reported(input_tokens=10, output_tokens=2)
+
+    async def fake_request(*_args, **_kwargs):
+        nonlocal attempts
+        attempts += 1
+        raise _XAIIncompleteHostedToolError(
+            [{"name": "x_search", "call_id": f"search-{attempts}"}],
+            usage=usage,
+        )
+
+    monkeypatch.setattr("nanobot.providers.xai_grok_provider._request_xai", fake_request)
+    provider = XAIGrokProvider()
+
+    response = await provider.chat_stream_with_retry(
+        [{"role": "user", "content": "Search X"}],
+        on_stream_recover=lambda: _append([], True),
+    )
+
+    assert attempts == 2
+    assert response.finish_reason == "error"
+    assert response.usage == usage + usage
 
 
 @pytest.mark.asyncio

tests/webui/test_settings_api.py

@@ -13,7 +13,8 @@ from nanobot.config.schema import Config, InlineFallbackConfig, ModelPresetConfi
 from nanobot.llm_usage import get_llm_usage_store
 from nanobot.llm_usage.models import LLMCallRecord
 from nanobot.providers.base import LLMUsage
-from nanobot.providers.registry import find_by_name
+from nanobot.providers.oauth_model_catalog import OAuthModelCatalogSnapshot
+from nanobot.providers.registry import ProviderModelSpec, find_by_name
 from nanobot.session.manager import SessionManager
 from nanobot.session.model_selection import SESSION_MODEL_PRESET_METADATA_KEY
 from nanobot.webui.settings_api import (
@@ -183,11 +184,13 @@ def test_update_api_settings_requires_key_for_network_access(
     with pytest.raises(WebUISettingsError, match="API key"):
         update_api_settings({"host": ["0.0.0.0"], "port": ["8900"]})
 
-    payload = update_api_settings({
+    payload = update_api_settings(
+        {
             "host": ["0.0.0.0"],
             "port": ["9900"],
             "api_key": ["secret-token"],
-    })
+        }
+    )
     saved = load_config(config_path)
     assert saved.api.host == "0.0.0.0"
     assert saved.api.port == 9900
@@ -346,13 +349,15 @@ def test_create_model_configuration_rejects_dynamic_custom_provider_without_api_
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     config_path = tmp_path / "config.json"
-    config = Config.model_validate({
+    config = Config.model_validate(
+        {
             "providers": {
                 DYNAMIC_PROVIDER_NAME: {
                     "apiKey": "sk-test",
                 }
             }
-    })
+        }
+    )
     save_config(config, config_path)
     monkeypatch.setattr("nanobot.config.loader._current_config_path", config_path)
 
@@ -497,9 +502,7 @@ def test_update_model_configuration_rolls_back_sessions_when_config_save_fails(
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     config_path = tmp_path / "config.json"
-    config = Config(
-        model_presets={"openai": ModelPresetConfig(model="openai/gpt-4.1")}
-    )
+    config = Config(model_presets={"openai": ModelPresetConfig(model="openai/gpt-4.1")})
     save_config(config, config_path)
     calls: list[tuple[str, str]] = []
 
@@ -890,11 +893,13 @@ def test_update_provider_settings_updates_and_clears_oauth_proxy(
         },
     )
 
-    payload = update_provider_settings({
+    payload = update_provider_settings(
+        {
             "provider": [provider_name],
             "proxy": [" http://127.0.0.1:7890 "],
             "extraBody": [json.dumps({"tools": []})],
-    })
+        }
+    )
 
     providers = {row["name"]: row for row in payload["providers"]}
     assert providers[provider_name]["proxy"] == "http://127.0.0.1:7890"
@@ -1099,7 +1104,8 @@ def test_settings_payload_groups_opencode_compatibility_alias(tmp_path, monkeypa
 
 def test_settings_payload_keeps_configured_opencode_legacy_alias(tmp_path, monkeypatch) -> None:
     config_path = tmp_path / "config.json"
-    config = Config.model_validate({
+    config = Config.model_validate(
+        {
             "providers": {"opencodeZen": {"apiKey": "legacy-key"}},
             "agents": {
                 "defaults": {
@@ -1107,7 +1113,8 @@ def test_settings_payload_keeps_configured_opencode_legacy_alias(tmp_path, monke
                     "model": "opencode/deepseek-v4-pro",
                 }
             },
-    })
+        }
+    )
     save_config(config, config_path)
     monkeypatch.setattr("nanobot.config.loader._current_config_path", config_path)
 
@@ -1124,13 +1131,15 @@ def test_settings_payload_marks_dynamic_custom_provider_without_api_base_unconfi
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
     config_path = tmp_path / "config.json"
-    config = Config.model_validate({
+    config = Config.model_validate(
+        {
             "providers": {
                 DYNAMIC_PROVIDER_NAME: {
                     "apiKey": "sk-test",
                 }
             }
-    })
+        }
+    )
     save_config(config, config_path)
     monkeypatch.setattr("nanobot.config.loader._current_config_path", config_path)
 
@@ -1466,7 +1475,8 @@ def test_settings_payload_includes_token_usage_summary(
     config = Config()
     save_config(config, config_path)
     monkeypatch.setattr("nanobot.config.loader._current_config_path", config_path)
-    get_llm_usage_store().record(LLMCallRecord(
+    get_llm_usage_store().record(
+        LLMCallRecord(
             started_at_ms=int(time.time() * 1000),
             duration_ms=1,
             provider="openai",
@@ -1475,7 +1485,8 @@ def test_settings_payload_includes_token_usage_summary(
             stream=False,
             finish_reason="stop",
             usage=LLMUsage.reported(input_tokens=10, output_tokens=5),
-    ))
+        )
+    )
 
     payload = settings_payload()
 
@@ -1496,7 +1507,8 @@ def test_settings_usage_payload_returns_lightweight_token_usage(
     config = Config()
     save_config(config, config_path)
     monkeypatch.setattr("nanobot.config.loader._current_config_path", config_path)
-    get_llm_usage_store().record(LLMCallRecord(
+    get_llm_usage_store().record(
+        LLMCallRecord(
             started_at_ms=int(time.time() * 1000),
             duration_ms=1,
             provider="openai",
@@ -1505,7 +1517,8 @@ def test_settings_usage_payload_returns_lightweight_token_usage(
             stream=False,
             finish_reason="stop",
             usage=LLMUsage.reported(input_tokens=20, output_tokens=2),
-    ))
+        )
+    )
 
     payload = settings_usage_payload()
 
@@ -1929,9 +1942,7 @@ def test_xai_grok_login_reports_upstream_failure_as_bad_gateway(
         )
 
     assert exc.value.status == 502
-    assert str(exc.value) == (
-        "xAI OAuth login failed: Could not reach xAI sign-in: ConnectError."
-    )
+    assert str(exc.value) == ("xAI OAuth login failed: Could not reach xAI sign-in: ConnectError.")
     assert exc.value.__cause__ is failure
 
 
@@ -1995,39 +2006,126 @@ def test_provider_models_payload_fetches_openai_compatible_models(
     assert payload["models"][1]["context_window"] == 65536
 
 
-def test_provider_models_payload_returns_curated_openai_codex_models() -> None:
+def test_provider_models_payload_returns_online_openai_codex_models(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setattr(
+        "nanobot.webui.settings_models.get_oauth_model_catalog",
+        lambda *_args, **_kwargs: OAuthModelCatalogSnapshot(
+            models=(
+                ProviderModelSpec(
+                    id="openai-codex/gpt-5.6-sol",
+                    label="GPT-5.6-Sol",
+                    description="Latest frontier agentic coding model.",
+                    owned_by="OpenAI Codex",
+                    context_window=272_000,
+                    reasoning_efforts=("low", "medium", "high", "xhigh", "max", "ultra"),
+                ),
+            ),
+            source="remote",
+            fetched_at=123,
+        ),
+    )
+
     payload = provider_models_payload({"provider": ["openai_codex"]})
 
     assert payload["status"] == "available"
-    assert payload["catalog_kind"] == "builtin"
-    assert payload["model_count"] == 7
+    assert payload["catalog_kind"] == "hybrid"
+    assert payload["source"] == "remote"
+    assert payload["model_count"] == 1
     assert payload["models"][0] == {
         "id": "openai-codex/gpt-5.6-sol",
         "label": "GPT-5.6-Sol",
         "description": "Latest frontier agentic coding model.",
         "owned_by": "OpenAI Codex",
-        "context_window": 372000,
+        "context_window": 272000,
+        "reasoning_efforts": ["low", "medium", "high", "xhigh", "max", "ultra"],
+        "supports_backend_search": False,
     }
-    assert [model["id"] for model in payload["models"][:3]] == [
-        "openai-codex/gpt-5.6-sol",
-        "openai-codex/gpt-5.6-terra",
-        "openai-codex/gpt-5.6-luna",
-    ]
 
 
-def test_provider_models_payload_returns_xai_grok_model() -> None:
+def test_provider_models_payload_returns_online_github_copilot_models(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setattr(
+        "nanobot.webui.settings_models.get_oauth_model_catalog",
+        lambda *_args, **_kwargs: OAuthModelCatalogSnapshot(
+            models=(
+                ProviderModelSpec(
+                    id="github-copilot/claude-sonnet",
+                    label="Claude Sonnet",
+                    owned_by="GitHub Copilot",
+                    context_window=200_000,
+                ),
+            ),
+            source="remote",
+            fetched_at=123,
+        ),
+    )
+
+    payload = provider_models_payload({"provider": ["github_copilot"]})
+
+    assert payload["status"] == "available"
+    assert payload["catalog_kind"] == "hybrid"
+    assert payload["source"] == "remote"
+    assert payload["models"][0]["id"] == "github-copilot/claude-sonnet"
+
+
+def test_provider_models_payload_returns_online_xai_grok_models(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setattr(
+        "nanobot.webui.settings_models.get_oauth_model_catalog",
+        lambda *_args, **_kwargs: OAuthModelCatalogSnapshot(
+            models=(
+                ProviderModelSpec(
+                    id="xai-grok/grok-4.6",
+                    label="Grok 4.6",
+                    description="Latest frontier model",
+                    owned_by="xAI",
+                    context_window=500_000,
+                    reasoning_efforts=("xhigh", "high", "medium", "low"),
+                    supports_backend_search=True,
+                ),
+                ProviderModelSpec(
+                    id="xai-grok/grok-4.5",
+                    label="Grok 4.5",
+                    owned_by="xAI",
+                    context_window=500_000,
+                    reasoning_efforts=("high", "medium", "low"),
+                    supports_backend_search=True,
+                ),
+            ),
+            source="remote",
+            fetched_at=123,
+        ),
+    )
+
     payload = provider_models_payload({"provider": ["xai_grok"]})
 
     assert payload["status"] == "available"
-    assert payload["catalog_kind"] == "builtin"
+    assert payload["catalog_kind"] == "hybrid"
+    assert payload["source"] == "remote"
+    assert payload["fetched_at"] == 123
     assert payload["models"] == [
+        {
+            "id": "xai-grok/grok-4.6",
+            "label": "Grok 4.6",
+            "description": "Latest frontier model",
+            "owned_by": "xAI",
+            "context_window": 500000,
+            "reasoning_efforts": ["xhigh", "high", "medium", "low"],
+            "supports_backend_search": True,
+        },
         {
             "id": "xai-grok/grok-4.5",
             "label": "Grok 4.5",
-            "description": "Grok via xAI subscription; X Search is enabled when supported.",
-            "owned_by": "xAI Grok",
+            "description": None,
+            "owned_by": "xAI",
             "context_window": 500000,
-        }
+            "reasoning_efforts": ["high", "medium", "low"],
+            "supports_backend_search": True,
+        },
     ]
 
 
@@ -2160,7 +2258,9 @@ def test_model_catalog_kind_uses_provider_spec_metadata() -> None:
     assert _model_catalog_kind(find_by_name("anthropic")) == "unsupported"
     assert _model_catalog_kind(find_by_name("openrouter")) == "catalog"
     assert _model_catalog_kind(find_by_name("orcarouter")) == "catalog"
-    assert _model_catalog_kind(find_by_name("openai_codex")) == "builtin"
+    assert _model_catalog_kind(find_by_name("openai_codex")) == "hybrid"
+    assert _model_catalog_kind(find_by_name("xai_grok")) == "hybrid"
+    assert _model_catalog_kind(find_by_name("github_copilot")) == "hybrid"
 
 
 def test_create_model_configuration_accepts_configured_oauth_provider(

tui/README.md

@@ -9,19 +9,17 @@ bun run --cwd tui test
 bun run --cwd tui build
 ```
 
-`nanobot agent` launches this client, leases the shared local gateway or starts it on demand, and passes the local bootstrap endpoint through environment variables. The client paints before gateway readiness, retries bootstrap in the background, and obtains fresh WebSocket and REST credentials for each connection. Other terminals and the WebUI keep that gateway alive; the final interactive launcher to exit releases the on-demand process. `/detach` closes the TUI after promoting the gateway to persistent background mode, keeping any active agent turn running without clients; the restored terminal prints the exact stop command for that config and explicit workspace. `nanobot gateway --background` can start or promote it persistently before opening a client. Source checkouts automatically align dependencies with `bun.lock` before launch; released installs use a version-matched, checksum-verified archive that keeps the executable together with its licenses, notices, corresponding application source, source offer, and relinking instructions. Startup fails explicitly if the native client is unavailable. The legacy Python prompt is only selected with `nanobot agent --classic`.
+`nanobot` (or the explicit `nanobot agent` form) launches this client, leases the shared local gateway or starts it on demand, and passes the local bootstrap endpoint through environment variables. The client paints before gateway readiness, retries bootstrap in the background, and obtains fresh WebSocket and REST credentials for each connection. Other terminals and the WebUI keep that gateway alive; the final interactive launcher to exit releases the on-demand process. `/detach` closes the TUI after promoting the gateway to persistent background mode, keeping any active agent turn running without clients; the restored terminal prints the exact stop command for that config and explicit workspace. `nanobot gateway --background` can start or promote it persistently before opening a client. Source checkouts automatically align dependencies with `bun.lock` before launch; released installs use a version-matched, checksum-verified archive that keeps the executable together with its licenses, notices, corresponding application source, source offer, and relinking instructions. Startup fails explicitly if the native client is unavailable. The legacy Python prompt is selected with `nanobot --classic` or `nanobot agent --classic`.
 
-Standalone terminals use OpenTUI's retained full-screen layout: the transcript reflows with the terminal while the composer stays fixed at the bottom. Mouse and keyboard scrolling operate inside the transcript, and leaving the TUI restores the previous terminal screen.
+The TUI uses OpenTUI's retained full-screen layout: the transcript reflows with the terminal while the composer stays fixed at the bottom. Mouse and keyboard scrolling operate inside the transcript, and leaving the TUI restores the previous terminal screen.
 
 Assistant math written with `$...$`, `$$...$$`, `\\(...\\)`, or `\\[...\\]` is presented as
 Unicode plain text so formulas remain readable in terminals without a math renderer. Currency and
 LaTeX inside inline or fenced code remain literal.
 
-## Herdr host mode
+## Herdr pane titles
 
-When Herdr supplies `HERDR_ENV=1` and `HERDR_PANE_ID`, nanobot becomes a quiet hosted client. It uses OpenTUI's main-screen mode instead of hiding the whole run in a temporary alternate screen, removes the launch card and persistent session/model/task chrome, and keeps only the transcript, compact progress, and composer. Herdr remains responsible for workspace, tab, pane, task, and attention navigation, while nanobot keeps its application-level session, new-chat, and branch commands.
-
-The TUI reports its WebSocket session ID, model, Git branch, workspace, last task, and current action through Herdr's supported pane CLI. Sending work reports `working`; a persisted explicit nanobot goal block reports `blocked`; a completed turn reports `idle`; exit releases lifecycle authority. The gateway session remains the durable transcript and resume path. Standalone terminals keep the richer full-screen navigation described below.
+When Herdr supplies `HERDR_ENV=1` and `HERDR_PANE_ID`, nanobot keeps the same full-screen layout, controls, and navigation available in any other terminal. Its only host-specific behavior is reporting the latest user task as the Herdr pane title through the supported pane CLI. Creating a new chat, switching to a chat without a task, and exiting the TUI clear that title. Nanobot does not report agent lifecycle, session, model, Git branch, workspace, or action metadata to Herdr.
 
 The model preset and workspace access labels above the composer are live controls. Click either
 label, then click a choice; arrow keys, `Enter`, and `Esc` provide the same flow without a mouse.

tui/src/app.test.ts

@@ -21,7 +21,7 @@ import type {
   SlashCommand,
   WorkspaceScopePayload,
 } from "./protocol"
-import type { HostAgentState, HostMetadata, TuiHost } from "./host"
+import type { TuiHost } from "./host"
 import type { ClipboardImageReader } from "./clipboard-image"
 import { userMessageText, type Transcript } from "./transcript"
 
@@ -415,8 +415,7 @@ describe("NanobotTui layout", () => {
 
     await setup.mockInput.typeText("这是什么？ ")
     setup.mockInput.pressKey("v", { ctrl: true })
-    await waitUntil(() => ui.status.plainText.includes("Pasted Image #1"), 3_000)
-    expect(ui.composer.plainText).toBe("这是什么？ [Image #1] ")
+    await waitUntil(() => ui.composer.plainText === "这是什么？ [Image #1] ")
     setup.mockInput.pressTab()
     expect(ui.status.plainText).toContain("Images cannot be queued")
     expect(ui.composer.plainText).toBe("这是什么？ [Image #1] ")
@@ -3075,23 +3074,18 @@ describe("NanobotTui layout", () => {
   })
 })
 
-describe("NanobotTui in a Herdr pane", () => {
-  test("keeps local navigation while reporting task, session, lifecycle, and metadata", async () => {
-    const setup = await createTestRenderer({ width: 80, height: 22, screenMode: "main-screen" })
-    const states: Array<{ state: HostAgentState; message?: string }> = []
-    const metadata: HostMetadata[] = []
-    const sessions: string[] = []
+describe("NanobotTui with a Herdr pane title reporter", () => {
+  test("keeps the full terminal experience while reporting task titles", async () => {
+    const setup = await createTestRenderer({ width: 80, height: 22, screenMode: "alternate-screen" })
+    const titles: string[] = []
     let released = false
     const host: TuiHost = {
-      hosted: true,
-      reportState(state, message) { states.push({ state, ...(message ? { message } : {}) }) },
-      reportSession(sessionId) { sessions.push(sessionId) },
-      reportMetadata(value) { metadata.push(value) },
+      reportTitle(title) { titles.push(title) },
       release() { released = true },
     }
     const app = NanobotTui.mount(
       setup.renderer,
-      { ...options, branch: "feat/herdr" },
+      options,
       client(),
       new MockTreeSitterClient({ autoResolveTimeout: 0 }),
       host,
@@ -3127,10 +3121,14 @@ describe("NanobotTui in a Herdr pane", () => {
     })
     await setup.flush()
     const activeFrame = setup.captureCharFrame()
+    expect(activeFrame).toContain(">_  nanobot")
+    expect(activeFrame).toContain("test/model")
     expect(occurrences(activeFrame, "› Ship the Herdr integration")).toBe(1)
     expect(occurrences(activeFrame, "app.ts")).toBe(1)
     expect(ui.composer.placeholder).toBe("Enter send now · Tab send next")
     expect(ui.composerFrame.height).toBe(3)
+    expect(titles).toEqual(["Ship the Herdr integration"])
+
     app.accept({
       event: "turn_end",
       chat_id: "chat",
@@ -3141,27 +3139,6 @@ describe("NanobotTui in a Herdr pane", () => {
         ui_summary: "Approval required",
       },
     })
-    await setup.flush()
-    const frame = setup.captureCharFrame()
-
-    expect(sessions).toEqual(["chat"])
-    expect(occurrences(frame, "› Ship the Herdr integration")).toBe(1)
-    expect(frame).not.toContain(">_  nanobot")
-    expect(frame).not.toContain("test/model")
-    expect(states.some(({ state }) => state === "working")).toBe(true)
-    expect(states.at(-1)).toEqual({ state: "blocked", message: "Approval required" })
-    expect(metadata.at(-1)).toMatchObject({
-      model: "default · test/model",
-      branch: "feat/herdr",
-      workspace: "/tmp/nanobot-workspace",
-      task: "Ship the Herdr integration",
-      action: "Approval required",
-    })
-
-    setup.resize(42, 6)
-    await setup.renderOnce()
-    expect(setup.captureCharFrame()).toContain("› Ship the Herdr integration")
-
     app.accept({
       event: "user_message",
       chat_id: "chat",
@@ -3169,13 +3146,8 @@ describe("NanobotTui in a Herdr pane", () => {
       turn_id: "turn-2",
       starts_turn: true,
     })
-    app.accept({
-      event: "turn_end",
-      chat_id: "chat",
-      turn_id: "turn-2",
-      goal_state: { active: false },
-    })
-    expect(states.at(-1)?.state).toBe("idle")
+
+    expect(titles).toEqual(["Ship the Herdr integration", "Approved"])
 
     app.stop()
     expect(released).toBe(true)

tui/src/app.ts

@@ -94,7 +94,7 @@ import {
   type FooterMode,
   type FooterHintTheme,
 } from "./footer-hints"
-import { createTuiHost, currentGitBranch, type TuiHost } from "./host"
+import { createTuiHost, type TuiHost } from "./host"
 
 interface AppOptions {
   wsUrl?: string
@@ -107,8 +107,6 @@ interface AppOptions {
   model: string
   modelPreset: string
   workspace: string
-  hostWorkspace?: string
-  branch?: string
   version: string
   access: string
   theme: "auto" | ThemeMode
@@ -404,10 +402,6 @@ function connectionStatusText(
   return "Session ended"
 }
 
-function singleLine(value: string, limit = 120): string {
-  return value.replace(/\s+/gu, " ").trim().slice(0, limit)
-}
-
 export function sessionExitMessage(chatId: string): string {
   const sessionId = `websocket:${chatId}`
   return `Resume with: nanobot agent --session ${sessionId}\n`
@@ -465,7 +459,6 @@ export class NanobotTui {
   private activeTurnId: string | null = null
   private activeLabel = "Thinking"
   private activeStartedAt = 0
-  private lastProgress = ""
   private finalMessage = ""
   private turnHadAnswer = false
   private historyLoaded = false
@@ -514,13 +507,8 @@ export class NanobotTui {
   private readonly silentCommandTurns = new Set<string>()
   private currentFileEdits: FileEditEvent[] = []
   private lastFileEdits: FileEditEvent[] = []
-  private currentTask = ""
-  private currentAction = ""
-  private hostBlocked = false
   private recoveryState: RecoveryState | null = null
   private recoveryPending = false
-  private hostWorkspace: string
-  private hostBranch: string
   private readonly apiReauthenticator: ApiReauthenticator | undefined
   private readonly clipboardImageReader: ClipboardImageReader
   private apiRefreshPromise: Promise<GatewayApiConnection> | null = null
@@ -545,8 +533,6 @@ export class NanobotTui {
     this.defaultModelPreset = options.modelPreset
     this.modelName = options.model
     this.modelPreset = options.modelPreset
-    this.hostWorkspace = options.hostWorkspace || options.workspace
-    this.hostBranch = options.branch || ""
     this.apiReauthenticator = options.bootstrapUrl
       ? (rejectedApiToken) => this.refreshApiConnection(rejectedApiToken)
       : undefined
@@ -561,7 +547,6 @@ export class NanobotTui {
       transcriptTheme(this.palette, this.backgroundKnown),
       treeSitterClient,
       (state) => this.handleTranscriptNavigation(state),
-      !host.hosted,
       options.workspace,
     )
     this.commandMenu = new CommandMenu(renderer, commandMenuTheme(this.palette))
@@ -672,7 +657,6 @@ export class NanobotTui {
       truncate: true,
       fg: this.palette.muted,
       selectable: false,
-      ...(host.hosted ? {} : {
       onMouseOver: () => { this.titleText.fg = this.palette.accent },
       onMouseOut: () => this.renderTitleColor(),
       onMouseDown: (event) => {
@@ -686,7 +670,6 @@ export class NanobotTui {
         }
         void this.openSessions()
       },
-      }),
     })
     this.runtimeControls = new RuntimeControls(
       renderer,
@@ -721,11 +704,9 @@ export class NanobotTui {
       },
     )
     this.title.add(this.titleText)
-    if (!host.hosted) {
     this.title.add(this.runtimeControls.modelText)
     this.title.add(this.runtimeControls.accessText)
     this.title.add(this.runtimeControls.contextText)
-    }
     const composerSurface = this.composerSurface()
     this.composerFrame = new BoxRenderable(renderer, {
       id: "nanobot-tui-composer-frame",
@@ -819,7 +800,7 @@ export class NanobotTui {
     this.shell.add(this.branchMenu.root)
     this.shell.add(this.contextPanel.root)
     this.shell.add(this.runtimeControls.menuRoot)
-    if (!host.hosted) this.shell.add(this.title)
+    this.shell.add(this.title)
     this.shell.add(this.queuePreview.root)
     this.shell.add(this.recoveryNotice.root)
     this.shell.add(this.composerFrame)
@@ -836,7 +817,6 @@ export class NanobotTui {
     this.handleResize()
     this.composer.focus()
     this.transcript.header(options)
-    this.syncHostMetadata()
   }
 
   static async create(options: AppOptions): Promise<NanobotTui> {
@@ -845,7 +825,7 @@ export class NanobotTui {
       targetFps: 30,
       exitOnCtrlC: false,
       useMouse: true,
-      screenMode: host.hosted ? "main-screen" : "alternate-screen",
+      screenMode: "alternate-screen",
       externalOutputMode: "passthrough",
       consoleMode: "disabled",
     })
@@ -874,7 +854,6 @@ export class NanobotTui {
     // Network setup and small menu payloads do not depend on terminal colors.
     // Start them while OSC theme detection is in flight instead of serializing
     // up to one second of otherwise independent startup work.
-    this.host.reportState("unknown", "Getting ready")
     this.client.connect()
     void this.loadCommands()
     void this.loadMentions()
@@ -1021,8 +1000,7 @@ export class NanobotTui {
       prompt.options.media,
       prompt.displayContent,
     )
-    this.hostBlocked = false
-    this.setCurrentTask(prompt.content)
+    this.host.reportTitle(prompt.content)
     if (steering) {
       this.renderActiveStatus()
       this.updateMeta()
@@ -1037,12 +1015,9 @@ export class NanobotTui {
     this.readyDetail = ""
     this.finalMessage = ""
     this.turnHadAnswer = false
-    this.lastProgress = ""
     this.activeLabel = "Thinking"
     this.currentFileEdits = []
-    this.setCurrentAction("Thinking")
     this.setActive(true, startedAt)
-    this.reportHostWorking()
   }
 
   private reconcileTurnOwnership(event: {
@@ -1065,7 +1040,6 @@ export class NanobotTui {
     if (event.event === "attached") {
       const switchedSession = Boolean(this.currentChatId && this.currentChatId !== event.chat_id)
       this.currentChatId = event.chat_id
-      this.host.reportSession(event.chat_id)
       if (event.usage) this.lastUsage = event.usage
       if (event.model_preset !== undefined) {
         this.applyModelPreset(event.model_preset)
@@ -1117,17 +1091,13 @@ export class NanobotTui {
         )) {
           this.recordPrompt(event.text)
         }
-        this.hostBlocked = false
-        this.setCurrentTask(event.text)
+        this.host.reportTitle(event.text)
         this.reconcileTurnOwnership(event)
-        if (this.activeTurn) this.reportHostWorking()
         return
       }
       case "delta":
         this.setActive(true)
         this.activeLabel = "Writing"
-        if (!this.currentAction) this.setCurrentAction("Writing")
-        this.reportHostWorking()
         this.turnHadAnswer = true
         this.transcript.stream(event.text)
         return
@@ -1147,11 +1117,8 @@ export class NanobotTui {
         }
         if (event.kind) {
           this.activeLabel = event.kind === "tool_hint" ? "Working" : "Thinking"
-          this.lastProgress = this.transcript.progress(event.text, event.tool_events)
-          if (this.lastProgress) this.setCurrentAction(this.lastProgress)
-          else if (!this.currentAction) this.setCurrentAction(this.activeLabel)
+          this.transcript.progress(event.text, event.tool_events)
           this.setActive(true)
-          this.reportHostWorking()
         } else {
           this.finalMessage = event.text
         }
@@ -1160,10 +1127,8 @@ export class NanobotTui {
         this.activeLabel = "Editing"
         this.currentFileEdits = mergeFileEdits(this.currentFileEdits, event.edits)
         if (this.diffViewer.visible) this.diffViewer.update(this.currentFileEdits)
-        this.lastProgress = this.transcript.fileEdits(event.edits)
-        this.setCurrentAction(this.lastProgress || "Editing")
+        this.transcript.fileEdits(event.edits)
         this.setActive(true)
-        this.reportHostWorking()
         return
       case "reasoning_delta":
         this.activeLabel = "Thinking"
@@ -1197,7 +1162,6 @@ export class NanobotTui {
         if (typeof event.context_window_tokens === "number") {
           this.contextWindowTokens = event.context_window_tokens
         }
-        this.applyHostGoalState(event.goal_state)
         this.updateTitle()
         this.setActive(false)
         // A synthetic/rehydrated turn may already be idle, in which case
@@ -1207,7 +1171,6 @@ export class NanobotTui {
           ? `${(event.latency_ms / 1000).toFixed(1)}s`
           : ""
         this.status.content = this.readyStatus()
-        this.reportHostResting()
         if (this.contextTokens !== null) void this.refreshContextEstimate(event.chat_id)
         this.sendNextFollowUp()
         return
@@ -1216,17 +1179,12 @@ export class NanobotTui {
         if (event.status === "running") {
           if (event.turn_id) this.activeTurnId = event.turn_id
           this.activeLabel = "Working"
-          if (!this.currentAction) this.setCurrentAction("Working")
           this.setActive(true, typeof event.started_at === "number" ? event.started_at * 1000 : undefined)
-          this.reportHostWorking()
         } else {
           this.setActive(false)
-          this.reportHostResting()
         }
         return
       case "goal_state":
-        this.applyHostGoalState(event.goal_state)
-        if (!this.activeTurn) this.reportHostResting()
         return
       case "recovery_state":
         this.applyRecoveryState(event)
@@ -1273,8 +1231,6 @@ export class NanobotTui {
         this.turnHadAnswer = false
         this.restoreQueuedPrompts()
         this.setActive(false)
-        this.setCurrentAction(event.reason || event.detail || "Error")
-        this.reportHostResting()
         return
     }
   }
@@ -1312,11 +1268,7 @@ export class NanobotTui {
         this.restorePromptHistory(history.messages)
         const reversedHistory = [...history.messages].reverse()
         const lastUser = reversedHistory.find((message) => message.role === "user")
-        if (lastUser) this.setCurrentTask(lastUser.content)
-        const lastActivity = reversedHistory.find((message) => message.role === "activity")
-        if (lastActivity) {
-          this.setCurrentAction(lastActivity.fileEdits?.length ? "Edited" : lastActivity.content)
-        }
+        if (lastUser) this.host.reportTitle(lastUser.content)
         this.lastFileEdits = latestTurnFileEdits(history.messages)
         if (this.diffViewer.visible) this.diffViewer.update(this.lastFileEdits)
       }
@@ -1328,7 +1280,6 @@ export class NanobotTui {
       this.ready = true
       if (!this.activeTurn) {
         this.status.content = this.readyStatus()
-        this.reportHostResting()
       }
     }
   }
@@ -1354,35 +1305,24 @@ export class NanobotTui {
     this.recoveryPending = false
     if (state.status === "resuming") {
       this.recoveryNotice.hide()
-      this.hostBlocked = false
       this.activeLabel = "Continuing"
-      this.setCurrentAction("Continuing interrupted task")
       this.setActive(true)
-      this.reportHostWorking()
       return
     }
     if (state.status === "awaiting_user" || state.status === "failed") {
       this.activeTurnId = null
       this.setActive(false)
-      this.hostBlocked = true
       this.recoveryNotice.show(state)
-      const detail = state.reason || (state.status === "failed"
-        ? "Recovery failed"
-        : "Task interrupted")
-      this.setCurrentAction(detail)
       this.status.content = state.can_continue === false
         ? "Interrupted · dismiss to start a new message"
         : "Interrupted · continue or dismiss"
-      this.host.reportState("blocked", detail)
       this.composer.focus()
       return
     }
     this.clearRecoveryState()
     this.activeTurnId = null
-    this.hostBlocked = false
     this.setActive(false)
     if (this.ready) this.status.content = this.readyStatus()
-    this.reportHostResting()
   }
 
   private async updateRecovery(action: "continue" | "dismiss"): Promise<void> {
@@ -1414,7 +1354,6 @@ export class NanobotTui {
       this.recoveryPending = false
       this.recoveryNotice.setBusy(false)
       this.status.content = error instanceof Error ? error.message : String(error)
-      this.host.reportState("blocked", state.reason || "Task interrupted")
     } finally {
       this.composer.focus()
     }
@@ -1468,13 +1407,11 @@ export class NanobotTui {
     this.connectionMessage = connectionStatusText(status, info)
     if (status === "connected") {
       this.ready = false
-      this.host.reportState("unknown", "Getting ready")
       this.renderConnectionMessage()
       return
     }
     if (["starting", "connecting", "reconnecting", "unavailable"].includes(status)) {
       this.ready = false
-      this.host.reportState("unknown", this.connectionMessage)
       if (status === "reconnecting" || status === "unavailable") this.setActive(false)
       this.renderConnectionMessage()
       return
@@ -1482,14 +1419,12 @@ export class NanobotTui {
     if (status === "error") {
       if (info) this.ready = false
       this.setActive(false)
-      this.host.reportState("unknown", this.connectionMessage)
       this.renderConnectionMessage()
       return
     }
     if (!this.quitting) {
       this.ready = false
       this.setActive(false)
-      this.host.reportState("unknown", "Disconnected")
       this.renderConnectionMessage()
     }
   }
@@ -1529,7 +1464,6 @@ export class NanobotTui {
     }
     if (this.shimmerTimer) clearInterval(this.shimmerTimer)
     this.shimmerTimer = null
-    this.lastProgress = ""
     this.status.content = this.readyStatus()
   }
 
@@ -1953,7 +1887,7 @@ export class NanobotTui {
     this.syncComposerPlaceholder()
     this.contextPanel.resize(this.renderer.height)
     this.diffViewer.resize(this.renderer.width)
-    if (!this.host.hosted) this.title.visible = this.renderer.height >= 14
+    this.title.visible = this.renderer.height >= 14
     this.runtimeControls.resize(this.renderer.width)
     this.updateTitle()
     this.updateMeta()
@@ -2022,10 +1956,6 @@ export class NanobotTui {
   }
 
   private updateTitle(): void {
-    if (this.host.hosted) {
-      this.syncHostMetadata()
-      return
-    }
     const identity = this.sessionTitle.trim() || "nanobot"
     this.titleText.maxWidth = Math.max(8, Math.floor(this.renderer.width * 0.38))
     this.titleText.content = identity
@@ -2036,69 +1966,14 @@ export class NanobotTui {
         : ""} ctx`
     this.runtimeControls.updateModel(this.modelName, this.modelPreset)
     this.runtimeControls.updateContext(context)
-    this.syncHostMetadata()
   }
 
   private renderTitleColor(): void {
-    this.titleText.fg = !this.host.hosted && (this.sessionLoading || this.sessionMenu.visible)
+    this.titleText.fg = this.sessionLoading || this.sessionMenu.visible
       ? this.palette.accent
       : this.palette.muted
   }
 
-  private setCurrentTask(task: string): void {
-    const next = singleLine(task)
-    if (!next || next === this.currentTask) return
-    this.currentTask = next
-    this.updateTitle()
-  }
-
-  private setCurrentAction(action: string): void {
-    const next = singleLine(action.replace(/^\s*[·›✓×]\s*/u, ""), 80)
-    if (!next || next === this.currentAction) return
-    this.currentAction = next
-    this.syncHostMetadata()
-  }
-
-  private clearHostContext(): void {
-    this.currentTask = ""
-    this.currentAction = ""
-    this.hostBlocked = false
-    this.updateTitle()
-  }
-
-  private syncHostMetadata(): void {
-    const model = [this.modelPreset, this.modelName].filter(Boolean).join(" · ")
-    this.host.reportMetadata({
-      model,
-      branch: this.hostBranch,
-      workspace: this.hostWorkspace,
-      task: this.currentTask,
-      action: this.currentAction,
-    })
-  }
-
-  private applyHostGoalState(state: Record<string, unknown> | undefined): void {
-    if (!state) return
-    this.hostBlocked = state.status === "blocked"
-    if (!this.hostBlocked) return
-    const summary = typeof state.ui_summary === "string" ? state.ui_summary : ""
-    const recap = typeof state.recap === "string" ? state.recap : ""
-    const objective = typeof state.objective === "string" ? state.objective : ""
-    this.setCurrentAction(summary || recap || objective || "Needs input")
-    this.host.reportState("blocked", summary || recap || objective || this.currentTask)
-  }
-
-  private reportHostResting(): void {
-    this.host.reportState(
-      this.hostBlocked ? "blocked" : "idle",
-      this.hostBlocked ? this.currentAction || this.currentTask : this.currentAction,
-    )
-  }
-
-  private reportHostWorking(): void {
-    if (!this.hostBlocked) this.host.reportState("working", this.currentTask)
-  }
-
   private resizeComposer(): void {
     const verticalPadding = this.renderer.height >= 12 ? 1 : 0
     const maxContentHeight = Math.max(1, Math.min(12, Math.floor(this.renderer.height / 3)))
@@ -2384,11 +2259,6 @@ export class NanobotTui {
   }
 
   private applyWorkspaceScope(scope: WorkspaceScopePayload): void {
-    if (scope.project_path) {
-      this.hostWorkspace = scope.project_path
-      this.hostBranch = currentGitBranch(scope.project_path)
-      this.syncHostMetadata()
-    }
     this.runtimeControls.updateWorkspaceScope(scope)
     this.updateTitle()
     if (!this.activeTurn && this.ready) this.status.content = this.readyStatus()
@@ -2480,8 +2350,7 @@ export class NanobotTui {
       this.clearPromptQueue()
       this.sessionMetadataId += 1
       this.sessionTitle = `Fork · ${preview.slice(0, 48)}`
-      this.clearHostContext()
-      this.setCurrentTask(preview)
+      this.host.reportTitle(preview)
       this.contextTokens = null
       this.lastUsage = null
       this.readyDetail = ""
@@ -2578,7 +2447,7 @@ export class NanobotTui {
       this.clearRecoveryState()
       this.queuePreview.update([])
       this.sessionMetadataId += 1
-      this.clearHostContext()
+      this.host.reportTitle("")
       this.sessionTitle = sessionLabel(session)
       this.applySessionModel(session)
       this.applySessionScope(session)
@@ -2614,7 +2483,7 @@ export class NanobotTui {
       this.clearRecoveryState()
       this.clearPromptQueue()
       this.sessionMetadataId += 1
-      this.clearHostContext()
+      this.host.reportTitle("")
       this.sessionTitle = "New chat"
       this.sessionModelPreset = null
       this.modelName = this.defaultModelName
@@ -2661,17 +2530,13 @@ export class NanobotTui {
     if (!silent) this.recordPrompt(content)
 
     if (lifecycle === "agent_turn") {
-      this.hostBlocked = false
-      this.setCurrentTask(content)
+      this.host.reportTitle(content)
       this.activeTurnId = turnId
       this.finalMessage = ""
       this.turnHadAnswer = false
-      this.lastProgress = ""
       this.activeLabel = "Thinking"
       this.currentFileEdits = []
-      this.setCurrentAction("Thinking")
       this.setActive(true)
-      this.reportHostWorking()
     } else if (lifecycle === "finalize_active_turn") {
       this.activeTurnId = null
       this.transcript.finishStream(this.turnHadAnswer ? "" : this.finalMessage)
@@ -2679,12 +2544,10 @@ export class NanobotTui {
       this.finalMessage = ""
       this.turnHadAnswer = false
       this.setActive(false)
-      this.reportHostResting()
       this.status.content = "Resetting chat…"
     } else if (lifecycle === "stop_active_turn") {
       this.activeTurnId = null
       this.setActive(false)
-      this.reportHostResting()
       this.status.content = "Stopping…"
     } else if (!this.activeTurn) {
       this.status.content = `Running ${content.split(/\s+/u, 1)[0]}…`

tui/src/host.test.ts

@@ -1,82 +1,67 @@
 import { describe, expect, test } from "bun:test"
 
-import { createTuiHost, currentGitBranch } from "./host"
+import { createTuiHost } from "./host"
 
 async function settle(): Promise<void> {
-  await Bun.sleep(40)
+  await Bun.sleep(0)
   await Bun.sleep(0)
 }
 
 describe("TUI host integration", () => {
-  test("reads the current workspace branch without leaking git errors", () => {
-    expect(currentGitBranch(process.cwd())).not.toBe("")
-    expect(currentGitBranch("/definitely/not/a/repository")).toBe("")
-  })
-
   test("standalone terminals remain a no-op", async () => {
     const commands: string[][] = []
     const host = createTuiHost({}, async (command) => { commands.push([...command]) })
 
-    host.reportState("working", "task")
-    host.reportSession("chat")
-    host.reportMetadata({ model: "gpt", task: "task" })
+    host.reportTitle("task")
     host.release()
     await settle()
 
-    expect(host.hosted).toBe(false)
     expect(commands).toEqual([])
   })
 
-  test("reports semantic lifecycle, session identity, metadata, and release", async () => {
+  test("requires both Herdr environment markers", async () => {
+    const commands: string[][] = []
+    const run = async (command: readonly string[]) => { commands.push([...command]) }
+
+    createTuiHost({ HERDR_ENV: "1" }, run).reportTitle("missing pane")
+    createTuiHost({ HERDR_PANE_ID: "w1:p2" }, run).reportTitle("missing host")
+    await settle()
+
+    expect(commands).toEqual([])
+  })
+
+  test("reports only normalized pane title changes and clears the title on release", async () => {
     const commands: string[][] = []
     const host = createTuiHost(
       { HERDR_ENV: "1", HERDR_PANE_ID: "w1:p2", HERDR_BIN_PATH: "/bin/herdr" },
       async (command) => { commands.push([...command]) },
     )
 
-    host.reportMetadata({
-      model: "openai/gpt",
-      branch: "feat/host",
-      workspace: "/repo",
-      task: "  Fix\nHerdr  integration ",
-      action: "Testing",
-    })
-    host.reportSession("chat-1")
-    host.reportState("working", "Fix Herdr integration")
-    host.reportState("working", "Fix Herdr integration")
-    host.reportState("blocked", "Approval required")
+    host.reportTitle("  Fix\nHerdr  integration ")
+    host.reportTitle("Fix Herdr integration")
+    host.reportTitle("Review results")
     host.release()
+    host.reportTitle("ignored after release")
     await settle()
 
-    expect(host.hosted).toBe(true)
-    expect(commands).toHaveLength(6)
-    expect(commands[0]).toContain("pane")
-    expect(commands[0]).toContain("report-metadata")
-    expect(commands[0]).toContain("task=Fix Herdr integration")
-    expect(commands[1]).toContain("report-agent-session")
-    expect(commands[1]).toContain("chat-1")
-    expect(commands[2]).toContain("working")
-    expect(commands[2]).toContain("--agent-session-id")
-    expect(commands[3]).toContain("blocked")
-    expect(commands[4]).toContain("--clear-token")
-    expect(commands[5]).toContain("release-agent")
-  })
-
-  test("metadata patches only changed tokens", async () => {
-    const commands: string[][] = []
-    const host = createTuiHost(
-      { HERDR_ENV: "1", HERDR_PANE_ID: "w1:p2" },
-      async (command) => { commands.push([...command]) },
-    )
-
-    host.reportMetadata({ model: "gpt", branch: "main" })
-    host.reportMetadata({ model: "gpt", branch: "main" })
-    host.reportMetadata({ model: "gpt", branch: "" })
-    await settle()
-
-    expect(commands).toHaveLength(1)
-    expect(commands[0]).toContain("model=gpt")
-    expect(commands[0]).toContain("--clear-token")
-    expect(commands[0]).toContain("branch")
+    expect(commands).toEqual([
+      [
+        "/bin/herdr", "pane", "report-metadata", "w1:p2",
+        "--source", "nanobot:tui:metadata", "--seq", "1",
+        "--title", "Fix Herdr integration",
+      ],
+      [
+        "/bin/herdr", "pane", "report-metadata", "w1:p2",
+        "--source", "nanobot:tui:metadata", "--seq", "2",
+        "--title", "Review results",
+      ],
+      [
+        "/bin/herdr", "pane", "report-metadata", "w1:p2",
+        "--source", "nanobot:tui:metadata", "--seq", "3", "--clear-title",
+      ],
+    ])
+    expect(commands.flat()).not.toContain("report-agent")
+    expect(commands.flat()).not.toContain("report-agent-session")
+    expect(commands.flat()).not.toContain("--token")
   })
 })

tui/src/host.ts

@@ -1,60 +1,22 @@
-export type HostAgentState = "idle" | "working" | "blocked" | "unknown"
-
-export interface HostMetadata {
-  model?: string
-  branch?: string
-  workspace?: string
-  task?: string
-  action?: string
-}
-
 export interface TuiHost {
-  readonly hosted: boolean
-  reportState(state: HostAgentState, message?: string): void
-  reportSession(sessionId: string): void
-  reportMetadata(metadata: HostMetadata): void
+  reportTitle(title: string): void
   release(): void
 }
 
-export function currentGitBranch(workspace: string): string {
-  const path = workspace.trim()
-  if (!path) return ""
-  try {
-    const branch = spawnText(["git", "-C", path, "branch", "--show-current"])
-    if (branch) return branch
-    const revision = spawnText(["git", "-C", path, "rev-parse", "--short", "HEAD"])
-    return revision ? `@${revision}` : ""
-  } catch {
-    return ""
-  }
-}
-
 type Environment = Record<string, string | undefined>
 type CommandRunner = (command: readonly string[]) => Promise<void>
 
-const AGENT = "nanobot"
-const LIFECYCLE_SOURCE = "nanobot:tui"
 const METADATA_SOURCE = "nanobot:tui:metadata"
-const METADATA_KEYS = ["model", "branch", "workspace", "task", "action"] as const
-const METADATA_FLUSH_MS = 32
 
 class StandaloneHost implements TuiHost {
-  readonly hosted = false
-  reportState(): void {}
-  reportSession(): void {}
-  reportMetadata(): void {}
+  reportTitle(): void {}
   release(): void {}
 }
 
 class HerdrHost implements TuiHost {
-  readonly hosted = true
   private sequence = 0
   private released = false
-  private lastState = ""
-  private lastSession = ""
-  private metadata: HostMetadata = {}
-  private readonly pendingMetadata = new Set<typeof METADATA_KEYS[number]>()
-  private metadataTimer: ReturnType<typeof setTimeout> | null = null
+  private lastTitle = ""
   private queue: Promise<void> = Promise.resolve()
 
   constructor(
@@ -63,97 +25,25 @@ class HerdrHost implements TuiHost {
     private readonly run: CommandRunner,
   ) {}
 
-  reportState(state: HostAgentState, message = ""): void {
+  reportTitle(title: string): void {
     if (this.released) return
-    const cleanMessage = normalize(message)
-    const fingerprint = `${state}\0${cleanMessage}\0${this.lastSession}`
-    if (fingerprint === this.lastState) return
-    this.lastState = fingerprint
-    // Preserve causal ordering when a semantic state transition follows a
-    // pending metadata snapshot; repeated working heartbeats still stay free.
-    this.flushMetadata()
-    const args = [
-      "pane", "report-agent", this.paneId,
-      "--source", LIFECYCLE_SOURCE,
-      "--agent", AGENT,
-      "--state", state,
-      "--seq", String(this.nextSequence()),
-    ]
-    if (cleanMessage) args.push("--message", cleanMessage)
-    if (this.lastSession) args.push("--agent-session-id", this.lastSession)
-    this.enqueue(args)
-  }
-
-  reportSession(sessionId: string): void {
-    if (this.released) return
-    const cleanSession = normalize(sessionId, 256)
-    if (!cleanSession || cleanSession === this.lastSession) return
-    this.lastSession = cleanSession
-    this.lastState = ""
-    this.flushMetadata()
-    this.enqueue([
-      "pane", "report-agent-session", this.paneId,
-      "--source", LIFECYCLE_SOURCE,
-      "--agent", AGENT,
-      "--agent-session-id", cleanSession,
-      "--seq", String(this.nextSequence()),
-    ])
-  }
-
-  reportMetadata(next: HostMetadata): void {
-    if (this.released) return
-    for (const key of METADATA_KEYS) {
-      if (!(key in next)) continue
-      const value = normalize(next[key])
-      if (value === normalize(this.metadata[key])) continue
-      this.pendingMetadata.add(key)
-    }
-    if (!this.pendingMetadata.size) return
-    this.metadata = { ...this.metadata, ...next }
-    if (this.metadataTimer) return
-    this.metadataTimer = setTimeout(() => this.flushMetadata(), METADATA_FLUSH_MS)
-  }
-
-  private flushMetadata(): void {
-    if (this.metadataTimer) clearTimeout(this.metadataTimer)
-    this.metadataTimer = null
-    if (!this.pendingMetadata.size) return
+    const cleanTitle = normalize(title)
+    if (cleanTitle === this.lastTitle) return
+    this.lastTitle = cleanTitle
     const args = [
       "pane", "report-metadata", this.paneId,
       "--source", METADATA_SOURCE,
-      "--agent", AGENT,
-      "--display-agent", AGENT,
       "--seq", String(this.nextSequence()),
+      cleanTitle ? "--title" : "--clear-title",
     ]
-    const task = normalize(this.metadata.task)
-    args.push(task ? "--title" : "--clear-title")
-    if (task) args.push(task)
-    for (const key of this.pendingMetadata) {
-      const value = normalize(this.metadata[key])
-      args.push(value ? "--token" : "--clear-token", value ? `${key}=${value}` : key)
-    }
-    this.pendingMetadata.clear()
+    if (cleanTitle) args.push(cleanTitle)
     this.enqueue(args)
   }
 
   release(): void {
     if (this.released) return
-    this.flushMetadata()
+    this.reportTitle("")
     this.released = true
-    const clear = [
-      "pane", "report-metadata", this.paneId,
-      "--source", METADATA_SOURCE,
-      "--clear-title", "--clear-display-agent", "--clear-state-labels",
-      "--seq", String(this.nextSequence()),
-    ]
-    for (const key of METADATA_KEYS) clear.push("--clear-token", key)
-    this.enqueue(clear)
-    this.enqueue([
-      "pane", "release-agent", this.paneId,
-      "--source", LIFECYCLE_SOURCE,
-      "--agent", AGENT,
-      "--seq", String(this.nextSequence()),
-    ])
   }
 
   private nextSequence(): number {
@@ -167,8 +57,8 @@ class HerdrHost implements TuiHost {
   }
 }
 
-function normalize(value: string | undefined, limit = 80): string {
-  return (value || "").replace(/[\u0000-\u001f\u007f]+/gu, " ").replace(/\s+/gu, " ").trim().slice(0, limit)
+function normalize(value: string, limit = 80): string {
+  return value.replace(/[\u0000-\u001f\u007f]+/gu, " ").replace(/\s+/gu, " ").trim().slice(0, limit)
 }
 
 async function runCommand(command: readonly string[]): Promise<void> {
@@ -176,12 +66,6 @@ async function runCommand(command: readonly string[]): Promise<void> {
   await child.exited
 }
 
-function spawnText(command: readonly string[]): string {
-  const result = Bun.spawnSync([...command], { stdout: "pipe", stderr: "ignore" })
-  if (result.exitCode !== 0) return ""
-  return new TextDecoder().decode(result.stdout).trim()
-}
-
 export function createTuiHost(
   environment: Environment = process.env,
   run: CommandRunner = runCommand,

tui/src/index.ts

@@ -1,5 +1,4 @@
 import { NanobotTui, sessionExitMessage, type AppOptions } from "./app"
-import { currentGitBranch } from "./host"
 
 // Keep in sync with _TUI_DETACH_EXIT_CODE in nanobot/cli/tui_launcher.py.
 const TUI_DETACH_EXIT_CODE = 90
@@ -11,7 +10,6 @@ function themePreference(): AppOptions["theme"] {
 }
 
 const workspace = process.env.NANOBOT_TUI_WORKSPACE?.trim() || ""
-const hostWorkspace = process.cwd()
 const bootstrapUrl = process.env.NANOBOT_TUI_BOOTSTRAP_URL?.trim() || ""
 const wsUrl = process.env.NANOBOT_TUI_WS_URL?.trim() || ""
 const healthUrl = process.env.NANOBOT_TUI_HEALTH_URL?.trim() || ""
@@ -34,8 +32,6 @@ const options: AppOptions = {
   model: process.env.NANOBOT_TUI_MODEL?.trim() || "unknown model",
   modelPreset: process.env.NANOBOT_TUI_MODEL_PRESET?.trim() || "default",
   workspace,
-  hostWorkspace,
-  branch: currentGitBranch(hostWorkspace),
   version: process.env.NANOBOT_TUI_VERSION?.trim() || "dev",
   access: process.env.NANOBOT_TUI_ACCESS?.trim() || "workspace access",
   theme: themePreference(),

tui/src/transcript.ts

@@ -145,7 +145,6 @@ export class Transcript {
     private theme: TranscriptTheme,
     private readonly treeSitterClient: TreeSitterClient,
     private readonly onNavigationChange?: (state: TranscriptNavigation) => void,
-    private readonly showHeader = true,
     private readonly workspace = "",
   ) {
     this.root = new ScrollBoxRenderable(renderer, {
@@ -198,7 +197,6 @@ export class Transcript {
   }
 
   header(options: TranscriptHeader): void {
-    if (!this.showHeader) return
     const row = new BoxRenderable(this.renderer, {
       id: this.id("header-row"),
       width: "100%",
@@ -265,7 +263,7 @@ export class Transcript {
     if (messages.length === 0) return
     const previousTop = this.root.scrollTop
     const previousHeight = this.root.scrollHeight
-    let index = this.showHeader ? 1 : 0
+    let index = 1 // Keep the launch header first.
     for (const message of messages) {
       if (message.role === "user") {
         if (message.turnId && this.userTurnIds.has(message.turnId)) continue

webui/src/App.tsx

@@ -2154,9 +2154,16 @@ function Shell({
     const hasAutomations = (pendingDelete.automations?.length ?? 0) > 0;
     const deletingActive = activeKey !== null && deletingKeys.has(activeKey);
     const currentIndex = topicSessions.findIndex((s) => s.key === activeKey);
+    const availableKeys = new Set(topicSessions.map((session) => session.key));
+    const siblingFallbackKey = deletingActive
+      ? activeTabState?.paneKeys.find((key) => (
+          !deletingKeys.has(key) && availableKeys.has(key)
+        )) ?? null
+      : null;
     const fallbackKey = deletingActive
       ? (
-          topicSessions.slice(currentIndex + 1).find((session) => (
+          siblingFallbackKey
+          ?? topicSessions.slice(currentIndex + 1).find((session) => (
             !deletingKeys.has(session.key)
           ))?.key
           ?? topicSessions.slice(0, Math.max(0, currentIndex)).reverse().find((session) => (
@@ -2191,7 +2198,7 @@ function Shell({
     } catch (e) {
       console.error("Failed to delete session", e);
     }
-  }, [pendingDelete, deleteChat, activeKey, navigate, topicSessions]);
+  }, [pendingDelete, deleteChat, activeKey, activeTabState, navigate, topicSessions]);
 
   const onRequestDeleteMany = useCallback(async (items: SidebarDeleteItem[]) => {
     const uniqueItems = Array.from(new Map(items.map((item) => [item.key, item])).values());

webui/src/components/settings/SkillsMarketplace.tsx

@@ -527,6 +527,8 @@ function MarketplaceSkillRow({
         <div className="mt-1 flex min-w-0 items-center gap-1.5 truncate text-[12px] text-muted-foreground">
           {skill.source}
           {skill.version ? <span>· v{skill.version}</span> : null}
+          {skill.provider === "skills_sh" ? (
+            <>
               <span>·</span>
               {skill.metric === "installs_24h"
                 ? t("settings.skills.marketplaceInstalls24h", {
@@ -539,6 +541,8 @@ function MarketplaceSkillRow({
                     formattedCount: skill.installs.toLocaleString(),
                     defaultValue: "{{formattedCount}} installs",
                   })}
+            </>
+          ) : null}
         </div>
       </div>
       {skill.provider === "skills_sh" ? <TrendSparkline values={trend} /> : null}

webui/src/components/settings/models/ModelsSettings.tsx

@@ -546,7 +546,7 @@ export function ModelsSettings({
           >
             {saving || creatingSaving
               ? tx("settings.actions.saving", "Saving...")
-              : tx("settings.actions.savePreset", "Save preset")}
+              : tx("settings.actions.savePreset", "Save")}
           </Button>
         </div>
       </div>

webui/src/components/settings/shared/ModelControls.tsx

@@ -204,13 +204,15 @@ export function ModelIdPicker({
   const providerConfigured = settingsProviderConfigured(settings, effectiveProvider);
   const providerRequiresConfiguration =
     !hasStaticModels && hasConcreteProvider && !providerConfigured;
-  const providerHasBuiltinModels = providerRow?.model_catalog === "builtin";
+  const providerHasManagedModels = ["builtin", "hybrid"].includes(
+    providerRow?.model_catalog ?? "",
+  );
   const providerUsesManualModelIds =
     !hasStaticModels &&
     hasConcreteProvider &&
     providerConfigured &&
     providerRow?.auth_type === "oauth" &&
-    !providerHasBuiltinModels;
+    !providerHasManagedModels;
   const canFetchModels =
     !hasStaticModels &&
     hasConcreteProvider && providerConfigured && !providerUsesManualModelIds;

webui/src/components/workbench/workbench-model.ts

@@ -72,9 +72,10 @@ function normalizeTab(value: unknown): WorkbenchTabState {
     ...requestedLayoutPaneKeys,
     ...paneKeys.filter((key) => !requestedLayoutPaneKeys.includes(key)),
   ];
+  const title = normalizeTitle(candidate.title);
   return {
-    explicit: candidate.explicit === true,
-    title: normalizeTitle(candidate.title),
+    explicit: candidate.explicit === true || title !== null,
+    title,
     paneKeys,
     layoutPaneKeys,
     layout: isLayout(candidate.layout) ? candidate.layout : "columns",
@@ -309,7 +310,9 @@ export function renameWorkbenchTab(
   const normalized = normalizeTitle(title);
   if (!normalized) return state;
   return updateTab(state, tabKey, (tab) => (
-    tab.title === normalized ? tab : { ...tab, title: normalized }
+    tab.title === normalized && tab.explicit
+      ? tab
+      : { ...tab, explicit: true, title: normalized }
   ));
 }
 

webui/src/i18n/locales/en/common.json

@@ -483,7 +483,7 @@
       "save": "Save",
       "saving": "Saving",
       "saveOrder": "Save order",
-      "savePreset": "Save preset",
+      "savePreset": "Save",
       "edit": "Edit",
       "delete": "Delete",
       "deleting": "Deleting...",

webui/src/i18n/locales/es/common.json

@@ -271,7 +271,7 @@
       "save": "Guardar",
       "saving": "Guardando",
       "saveOrder": "Guardar orden",
-      "savePreset": "Guardar preajuste",
+      "savePreset": "Guardar",
       "delete": "Eliminar",
       "deleting": "Eliminando...",
       "edit": "Editar",

webui/src/i18n/locales/fr/common.json

@@ -271,7 +271,7 @@
       "save": "Enregistrer",
       "saving": "Enregistrement",
       "saveOrder": "Enregistrer l’ordre",
-      "savePreset": "Enregistrer le préréglage",
+      "savePreset": "Enregistrer",
       "delete": "Supprimer",
       "deleting": "Suppression...",
       "edit": "Modifier",

webui/src/i18n/locales/id/common.json

@@ -271,7 +271,7 @@
       "save": "Simpan",
       "saving": "Menyimpan",
       "saveOrder": "Simpan urutan",
-      "savePreset": "Simpan prasetel",
+      "savePreset": "Simpan",
       "delete": "Hapus",
       "deleting": "Menghapus...",
       "edit": "Ubah",

webui/src/i18n/locales/ja/common.json

@@ -271,7 +271,7 @@
       "save": "保存",
       "saving": "保存中",
       "saveOrder": "順序を保存",
-      "savePreset": "プリセットを保存",
+      "savePreset": "保存",
       "delete": "削除",
       "deleting": "削除中...",
       "edit": "編集",

webui/src/i18n/locales/ko/common.json

@@ -271,7 +271,7 @@
       "save": "저장",
       "saving": "저장 중",
       "saveOrder": "순서 저장",
-      "savePreset": "프리셋 저장",
+      "savePreset": "저장",
       "delete": "삭제",
       "deleting": "삭제 중...",
       "edit": "편집",

webui/src/i18n/locales/pt-BR/common.json

@@ -483,7 +483,7 @@
       "save": "Salvar",
       "saving": "Salvando",
       "saveOrder": "Salvar ordem",
-      "savePreset": "Salvar predefinição",
+      "savePreset": "Salvar",
       "delete": "Excluir",
       "deleting": "Excluindo...",
       "edit": "Editar",

webui/src/i18n/locales/vi/common.json

@@ -271,7 +271,7 @@
       "save": "Lưu",
       "saving": "Đang lưu",
       "saveOrder": "Lưu thứ tự",
-      "savePreset": "Lưu cấu hình đặt trước",
+      "savePreset": "Lưu",
       "delete": "Xóa",
       "deleting": "Đang xóa...",
       "edit": "Sửa",

webui/src/i18n/locales/zh-CN/common.json

@@ -483,7 +483,7 @@
       "save": "保存",
       "saving": "正在保存",
       "saveOrder": "保存顺序",
-      "savePreset": "保存预设",
+      "savePreset": "保存",
       "edit": "编辑",
       "delete": "删除",
       "deleting": "正在删除...",

webui/src/i18n/locales/zh-TW/common.json

@@ -271,7 +271,7 @@
       "save": "儲存",
       "saving": "正在儲存",
       "saveOrder": "儲存順序",
-      "savePreset": "儲存預設",
+      "savePreset": "儲存",
       "delete": "刪除",
       "deleting": "正在刪除…",
       "edit": "編輯",

webui/src/lib/types.ts

@@ -510,6 +510,8 @@ interface ProviderModelInfo {
   description?: string | null;
   owned_by?: string | null;
   context_window?: number | null;
+  reasoning_efforts?: string[];
+  supports_backend_search?: boolean;
 }
 
 export interface ProviderModelsPayload {
@@ -521,7 +523,15 @@ export interface ProviderModelsPayload {
     | "not_configured"
     | "missing_api_base"
     | "error";
-  catalog_kind: "builtin" | "official" | "catalog" | "local" | "custom" | "unsupported";
+  catalog_kind:
+    | "builtin"
+    | "hybrid"
+    | "official"
+    | "catalog"
+    | "local"
+    | "custom"
+    | "unsupported";
+  source?: "remote" | "cache" | "stale" | "fallback";
   models: ProviderModelInfo[];
   model_count: number;
   message?: string | null;

webui/src/tests/app-layout.test.tsx

@@ -1201,6 +1201,7 @@ describe("App layout", () => {
     expect(screen.getAllByText("SkillHub")).toHaveLength(2);
     expect(screen.getAllByText("skills.sh")).toHaveLength(2);
     expect(screen.getByText(/14,481 installs \/ 24h/)).toBeInTheDocument();
+    expect(screen.queryByText(/11,831 installs/)).not.toBeInTheDocument();
     fireEvent.click(screen.getByRole("tab", { name: "SkillHub" }));
     expect(screen.getByText("ima-skills")).toBeInTheDocument();
     expect(screen.queryByText("find-skills")).not.toBeInTheDocument();
@@ -2530,7 +2531,7 @@ describe("App layout", () => {
     ).toBe(true);
     await user.click(screen.getByRole("button", { name: "Select model" }));
     await user.click(await screen.findByRole("option", { name: /openai\/gpt-4o-mini/ }));
-    expect(screen.getByRole("button", { name: "Save preset" })).toBeEnabled();
+    expect(screen.getByRole("button", { name: "Save" })).toBeEnabled();
     fireEvent.click(screen.getByRole("button", { name: "Cancel" }));
     expect(screen.queryByText("Up to date.")).not.toBeInTheDocument();
     fireEvent.click(
@@ -3414,6 +3415,23 @@ describe("App layout", () => {
       expect(restoredGrid).toHaveAttribute("data-layout", "rows");
     });
 
+    const alphaGroupButton = within(sidebar).getByRole("button", {
+      name: "Group: Alpha",
+    });
+    const alphaGroup = alphaGroupButton.closest("[data-sidebar-tab-group]") as HTMLElement;
+    fireEvent.pointerDown(within(alphaGroup).getByLabelText("Topic actions for Alpha"), {
+      button: 0,
+      ctrlKey: false,
+    });
+    fireEvent.click(await screen.findByRole("menuitem", { name: "Rename" }));
+    const renameDialog = await screen.findByRole("dialog", { name: "Rename group" });
+    fireEvent.change(within(renameDialog).getByPlaceholderText("Group name"), {
+      target: { value: "Research" },
+    });
+    fireEvent.click(within(renameDialog).getByRole("button", { name: "Save" }));
+    expect(await within(sidebar).findByRole("button", { name: "Group: Research" }))
+      .toBeInTheDocument();
+
     fireEvent.pointerDown(within(sidebar).getByRole("button", {
       name: "New topic pane actions",
     }), { button: 0, ctrlKey: false });
@@ -3421,9 +3439,93 @@ describe("App layout", () => {
       name: "Remove",
     }));
     await waitFor(() => expect(screen.getByTestId("pane-grid").children).toHaveLength(1));
+    const researchGroup = within(sidebar).getByRole("button", {
+      name: "Group: Research",
+    }).closest("[data-sidebar-tab-group]") as HTMLElement;
+    expect(within(researchGroup).getByRole("list", { name: "Panes in Research" }))
+      .toBeInTheDocument();
+    expect(within(researchGroup).getByRole("button", { name: "Alpha" }))
+      .toBeInTheDocument();
     expect(within(sidebar).getAllByRole("button", { name: "New topic" })).toHaveLength(2);
   });
 
+  it("keeps a named group and its remaining pane active after deleting a pane", async () => {
+    mockSessions = [
+      {
+        key: "websocket:new-pane",
+        channel: "websocket",
+        chatId: "new-pane",
+        createdAt: "2026-08-05T12:00:00Z",
+        updatedAt: "2026-08-05T12:00:00Z",
+        title: "New topic",
+        preview: "",
+      },
+      {
+        key: "websocket:unrelated",
+        channel: "websocket",
+        chatId: "unrelated",
+        createdAt: "2026-08-05T11:00:00Z",
+        updatedAt: "2026-08-05T11:00:00Z",
+        title: "Unrelated",
+        preview: "",
+      },
+      {
+        key: "websocket:alpha",
+        channel: "websocket",
+        chatId: "alpha",
+        createdAt: "2026-08-05T10:00:00Z",
+        updatedAt: "2026-08-05T10:00:00Z",
+        title: "Alpha",
+        preview: "",
+      },
+    ];
+    window.history.replaceState(null, "", "/#/chat/websocket%3Anew-pane");
+    vi.stubGlobal("fetch", vi.fn().mockImplementation(async (url: string | URL | Request) => {
+      if (String(url) === "/api/webui/sidebar-state") {
+        return {
+          ok: true,
+          json: async () => ({
+            workbench: {
+              version: 1,
+              tabs: {
+                "tab:websocket:alpha": {
+                  explicit: false,
+                  title: "Research",
+                  paneKeys: ["websocket:alpha", "websocket:new-pane"],
+                  layoutPaneKeys: ["websocket:alpha", "websocket:new-pane"],
+                  layout: "columns",
+                  splitRatios: [],
+                },
+              },
+            },
+          }),
+        };
+      }
+      return { ok: false, status: 404 };
+    }));
+
+    render(<App />);
+
+    await waitFor(() => expect(connectSpy).toHaveBeenCalled());
+    const sidebar = screen.getByRole("navigation", { name: "Sidebar navigation" });
+    expect(await within(sidebar).findByRole("button", { name: "Group: Research" }))
+      .toBeInTheDocument();
+    fireEvent.pointerDown(within(sidebar).getByRole("button", {
+      name: "New topic pane actions",
+    }), { button: 0, ctrlKey: false });
+    fireEvent.click(await screen.findByRole("menuitem", { name: "Delete" }));
+    expect(await screen.findByText("Delete this topic?")).toBeInTheDocument();
+    fireEvent.click(screen.getByRole("button", { name: "Delete" }));
+
+    await waitFor(() => expect(deleteChatSpy).toHaveBeenCalledWith("websocket:new-pane"));
+    await waitFor(() => expect(window.location.hash).toBe("#/chat/websocket%3Aalpha"));
+    expect(within(sidebar).getByRole("button", { name: "Group: Research" }))
+      .toBeInTheDocument();
+    expect(screen.getByTestId("pane-grid").children).toHaveLength(1);
+    expect(screen.getByTestId("pane-grid").firstElementChild)
+      .toHaveAttribute("aria-label", "Alpha");
+  }, 15_000);
+
   it("opens search from the keyboard shortcut", async () => {
     mockSessions = [
       {

webui/src/tests/settings-models.test.tsx

@@ -141,7 +141,7 @@ describe("Settings models", () => {
     fireEvent.change(screen.getByLabelText("Temperature"), {
       target: { value: "0.4" },
     });
-    fireEvent.click(screen.getByRole("button", { name: "Save preset" }));
+    fireEvent.click(screen.getByRole("button", { name: "Save" }));
 
     await waitFor(() => {
       expect(requestMutationMock).toHaveBeenCalledWith(
@@ -173,7 +173,7 @@ describe("Settings models", () => {
 
     const nameInput = screen.getByRole("textbox", { name: "Preset name" });
     fireEvent.change(nameInput, { target: { value: "Codex" } });
-    fireEvent.click(screen.getByRole("button", { name: "Save preset" }));
+    fireEvent.click(screen.getByRole("button", { name: "Save" }));
 
     await waitFor(() => {
       expect(requestMutationMock).toHaveBeenCalledWith(
@@ -196,7 +196,7 @@ describe("Settings models", () => {
 
     const nameInput = screen.getByRole("textbox", { name: "Preset name" });
     fireEvent.change(nameInput, { target: { value: "Codex" } });
-    fireEvent.click(screen.getByRole("button", { name: "Save preset" }));
+    fireEvent.click(screen.getByRole("button", { name: "Save" }));
 
     expect(await screen.findByRole("alert")).toHaveTextContent(
       "A preset with this name already exists.",
@@ -368,7 +368,7 @@ describe("Settings models", () => {
 
     expect(screen.queryByRole("button", { name: "Save order" })).not.toBeInTheDocument();
     expect(screen.getByLabelText("Temperature")).toHaveValue(0.4);
-    expect(screen.getByRole("button", { name: "Save preset" })).toBeEnabled();
+    expect(screen.getByRole("button", { name: "Save" })).toBeEnabled();
   });
 
   it("keeps repeated fallback preset rows stable when changing the primary preset", async () => {
@@ -604,7 +604,7 @@ describe("Settings models", () => {
     );
     fireEvent.click(screen.getByRole("button", { name: "New model preset" }));
     expect(screen.queryByRole("dialog", { name: "New model preset" })).not.toBeInTheDocument();
-    expect(screen.getByRole("button", { name: "Save preset" })).toBeDisabled();
+    expect(screen.getByRole("button", { name: "Save" })).toBeDisabled();
     expect(
       screen.queryByText("Complete the preset before saving."),
     ).not.toBeInTheDocument();
@@ -619,7 +619,7 @@ describe("Settings models", () => {
       target: { value: "openai/gpt-4o-mini" },
     });
     fireEvent.keyDown(modelSearch, { key: "Enter" });
-    const saveButton = screen.getByRole("button", { name: "Save preset" });
+    const saveButton = screen.getByRole("button", { name: "Save" });
     expect(saveButton).toBeEnabled();
     fireEvent.click(saveButton);
 
@@ -656,7 +656,7 @@ describe("Settings models", () => {
     });
     fireEvent.change(modelSearch, { target: { value: "openai/gpt-4o-mini" } });
     fireEvent.keyDown(modelSearch, { key: "Enter" });
-    fireEvent.click(screen.getByRole("button", { name: "Save preset" }));
+    fireEvent.click(screen.getByRole("button", { name: "Save" }));
 
     expect(requestMutationMock).not.toHaveBeenCalled();
     expect(nameInput).toHaveAttribute("aria-invalid", "true");
@@ -1295,6 +1295,88 @@ describe("Settings models", () => {
     );
   });
 
+  it("loads hybrid online models for configured OAuth providers", async () => {
+    const base = settingsPayload();
+    const payload: SettingsPayload = {
+      ...base,
+      agent: {
+        ...base.agent,
+        model: "xai-grok/grok-4.5",
+        provider: "xai_grok",
+        resolved_provider: "xai_grok",
+      },
+      model_presets: [
+        {
+          ...base.model_presets[0],
+          model: "xai-grok/grok-4.5",
+          provider: "xai_grok",
+        },
+      ],
+      providers: [
+        {
+          name: "xai_grok",
+          label: "xAI Grok",
+          configured: true,
+          auth_type: "oauth",
+          api_key_required: false,
+          api_key_hint: null,
+          api_base: null,
+          default_api_base: "https://cli-chat-proxy.grok.com/v1",
+          model_catalog: "hybrid",
+          oauth_account: "acct-test",
+          oauth_expires_at: null,
+          oauth_login_supported: true,
+        },
+      ],
+    };
+    const fetchMock = vi.fn(async (input: RequestInfo | URL) => {
+      const url = String(input);
+      if (url === "/api/settings/provider-models?provider=xai_grok") {
+        return jsonResponse({
+          provider: "xai_grok",
+          label: "xAI Grok",
+          status: "available",
+          catalog_kind: "hybrid",
+          source: "remote",
+          models: [
+            {
+              id: "xai-grok/grok-4.6",
+              label: "Grok 4.6",
+              description: "Latest frontier model",
+              owned_by: "xAI",
+              context_window: 500_000,
+            },
+            {
+              id: "xai-grok/grok-4.5",
+              label: "Grok 4.5",
+              owned_by: "xAI",
+              context_window: 500_000,
+            },
+          ],
+          model_count: 2,
+          fetched_at: 1,
+        });
+      }
+      return { ok: false, status: 404, json: async () => ({}) } as Response;
+    });
+    vi.stubGlobal("fetch", fetchMock);
+
+    renderSettingsView({ initialSection: "models", initialSettings: payload });
+
+    await togglePresetEditor();
+    const modelButtons = await screen.findAllByRole("button", {
+      name: /xai-grok\/grok-4\.5/i,
+    });
+    await openPopover(modelButtons[modelButtons.length - 1]);
+
+    expect(await screen.findByText("Grok 4.6")).toBeInTheDocument();
+    expect(screen.getByText(/Latest frontier model/)).toBeInTheDocument();
+    expect(fetchMock).toHaveBeenCalledWith(
+      "/api/settings/provider-models?provider=xai_grok",
+      expect.objectContaining({ headers: { Authorization: "Bearer tok" } }),
+    );
+  });
+
   it("creates presets in the inline editor and can cancel without opening a dialog", async () => {
     vi.stubGlobal(
       "fetch",
@@ -1417,7 +1499,7 @@ describe("Settings models", () => {
     fireEvent.change(screen.getByLabelText("Reasoning effort"), {
       target: { value: "provider-native-mode" },
     });
-    fireEvent.click(screen.getByRole("button", { name: "Save preset" }));
+    fireEvent.click(screen.getByRole("button", { name: "Save" }));
 
     await waitFor(() =>
       expect(fetchMock).toHaveBeenCalledWith(

webui/src/tests/workbench-model.test.ts

@@ -53,7 +53,7 @@ describe("workbench model", () => {
     state = renameWorkbenchTab(state, tabKey, "Research");
 
     expect(workbenchTab(state, tabKey)).toEqual({
-      explicit: false,
+      explicit: true,
       title: "Research",
       paneKeys: ["pane-a", "pane-b"],
       layoutPaneKeys: ["pane-a", "pane-b"],
@@ -62,6 +62,24 @@ describe("workbench model", () => {
     });
   });
 
+  it("preserves a named group when a pane is detached", () => {
+    let state = addWorkbenchPane(EMPTY_WORKBENCH_STATE, "pane-a", "pane-b");
+    const tabKey = workbenchTabForPane(state, "pane-a").tabKey;
+    state = renameWorkbenchTab(state, tabKey, "Research");
+    state = detachWorkbenchPane(state, tabKey, "pane-b");
+
+    expect(workbenchTab(state, tabKey)).toEqual({
+      explicit: true,
+      title: "Research",
+      paneKeys: ["pane-a"],
+      layoutPaneKeys: ["pane-a"],
+      layout: "columns",
+      splitRatios: [],
+    });
+    expect(normalizeWorkbenchState(state)).toEqual(state);
+    expect(reconcileWorkbench(state, new Set(["pane-a"]))).toEqual(state);
+  });
+
   it("detaches a pane without persisting its standalone projection", () => {
     let state = addWorkbenchPane(EMPTY_WORKBENCH_STATE, "pane-a", "pane-b");
     const tabKey = workbenchTabForPane(state, "pane-a").tabKey;
@@ -198,7 +216,7 @@ describe("workbench model", () => {
     );
 
     expect(workbenchTab(reconciled, "alpha")).toEqual({
-      explicit: false,
+      explicit: true,
       title: "Alpha",
       paneKeys: ["pane-a", "pane-b"],
       layoutPaneKeys: ["pane-a", "pane-b"],