agentram 0.1.13 → 0.1.15

package/agentram/cli.py

@@ -1,20 +1,20 @@
 from __future__ import annotations
 
-import argparse
-import asyncio
-from concurrent.futures import ThreadPoolExecutor
-import json
-import os
-import shlex
-import shutil
-import textwrap
-import time
+import argparse
+import asyncio
+from concurrent.futures import ThreadPoolExecutor
+import json
+import os
+import shlex
+import shutil
+import textwrap
+import time
 from pathlib import Path
 from typing import Any
 
-from .config import default_ram_root
-from .mcp_server import McpContext, call_tool
-from .orchestration import AgentModelEndpoint, MultiModelCodingOrchestrator
+from .config import default_ram_root
+from .mcp_server import McpContext, call_tool
+from .orchestration import AgentModelEndpoint, MultiModelCodingOrchestrator
 
 SUBAGENTS: dict[str, str] = {
     "memory": "Summarize important facts, decisions, files, risks, and next tasks into AgentRAM events. Do not edit code.",
@@ -38,17 +38,17 @@ SLASH_COMMANDS: list[tuple[str, str]] = [
     ("/models", "List bound coding models"),
     ("/remove-model <id>", "Remove bound coding model"),
     ("/disable-model <id>", "Disable bound coding model"),
-    ("/clear-models", "Remove all bound coding models"),
-    ("/bind-model provider model", "Bind model endpoint"),
-    ("/bind-router provider model", "Bind intent router model"),
-    ("/bind-agent slot provider model", "Bind supervisor/main/small agent"),
-    ("/workflow", "Show supervisor workflow agents"),
-    ("/route on|off|status", "Toggle auto prompt routing"),
-    ("/orchestrate <task>", "Build multi-model agent plan"),
-    ("/ask <prompt>", "Execute bound models and return outputs"),
-    ("/claude-install [path]", "Install .claude commands and agents"),
-    ("/note <text>", "Save decision note"),
-    ("/clear", "Clear chat"),
+    ("/clear-models", "Remove all bound coding models"),
+    ("/bind-model provider model", "Bind model endpoint"),
+    ("/bind-router provider model", "Bind intent router model"),
+    ("/bind-agent slot provider model", "Bind supervisor/main/small agent"),
+    ("/workflow", "Show supervisor workflow agents"),
+    ("/route on|off|status", "Toggle auto prompt routing"),
+    ("/orchestrate <task>", "Build multi-model agent plan"),
+    ("/ask <prompt>", "Execute bound models and return outputs"),
+    ("/claude-install [path]", "Install .claude commands and agents"),
+    ("/note <text>", "Save decision note"),
+    ("/clear", "Clear chat"),
     ("/exit", "Quit"),
     ("Plain text", "Capture coding chat message and retrieve context"),
 ]
@@ -69,20 +69,20 @@ SLASH_HELP = """Slash commands:
 /models                       List bound coding models
 /remove-model <id>            Remove bound coding model
 /disable-model <id>           Disable bound coding model
-/clear-models                 Remove all bound coding models
-/bind-model provider model    Bind model endpoint
-/bind-router provider model   Bind intent router model
-/bind-agent slot provider model Bind supervisor/main/small agent
-/workflow                     Show supervisor workflow agents
-/route on|off|status          Toggle auto prompt routing
-/orchestrate <task>           Build multi-model agent plan
+/clear-models                 Remove all bound coding models
+/bind-model provider model    Bind model endpoint
+/bind-router provider model   Bind intent router model
+/bind-agent slot provider model Bind supervisor/main/small agent
+/workflow                     Show supervisor workflow agents
+/route on|off|status          Toggle auto prompt routing
+/orchestrate <task>           Build multi-model agent plan
 /ask <prompt>                 Execute bound models and return outputs
-/claude-install [path]        Install .claude commands and agents
-/note <text>                  Save decision note
-/clear                        Clear chat
+/claude-install [path]        Install .claude commands and agents
+/note <text>                  Save decision note
+/clear                        Clear chat
 /exit                         Quit
-Plain text                    Capture coding chat message and retrieve context
-""".strip()
+Plain text                    Capture coding chat message and retrieve context
+""".strip()
 
 
 def build_parser() -> argparse.ArgumentParser:
@@ -105,30 +105,30 @@ def build_parser() -> argparse.ArgumentParser:
     disable_model.add_argument("id", help="Endpoint id.")
 
     bind_model = subparsers.add_parser("bind-model", help="Bind a coding model endpoint.")
-    bind_model.add_argument("provider", help="Provider name, e.g. claude, openai-compatible, groq, claude-subagent.")
-    bind_model.add_argument("model", help="Model name or Claude subagent name.")
+    bind_model.add_argument("provider", help="Provider name, e.g. claude, openai-compatible, groq, claude-subagent.")
+    bind_model.add_argument("model", help="Model name or Claude subagent name.")
     bind_model.add_argument("--role", default="coder", help="Agent role.")
     bind_model.add_argument("--base-url", default="", help="Provider base URL.")
-    bind_model.add_argument("--api-key-env", default="", help="Environment variable containing API key.")
-    bind_model.add_argument("--modalities", default="text", help="Comma-separated modalities.")
-
-    bind_router = subparsers.add_parser("bind-router", help="Bind a separate intent router model endpoint.")
-    bind_router.add_argument("provider", help="Provider name, e.g. openai-compatible, groq, claude-subagent.")
-    bind_router.add_argument("model", help="Router model name.")
-    bind_router.add_argument("--base-url", default="", help="Provider base URL or local command for claude-subagent.")
-    bind_router.add_argument("--api-key-env", default="", help="Environment variable containing API key.")
-
-    bind_agent = subparsers.add_parser("bind-agent", help="Bind supervisor/main/small workflow agent.")
-    bind_agent.add_argument("slot", choices=["supervisor", "main", "small"], help="Workflow slot.")
-    bind_agent.add_argument("provider", help="Provider name, e.g. claude-subagent, openai-compatible, groq.")
-    bind_agent.add_argument("model", help="Model or subagent name.")
-    bind_agent.add_argument("--base-url", default="", help="Provider base URL or local command for claude-subagent.")
-    bind_agent.add_argument("--api-key-env", default="", help="Environment variable containing API key.")
-
-    subparsers.add_parser("workflow", help="Show supervisor/main/small workflow agents.")
-
-    route = subparsers.add_parser("route", help="Toggle or show auto prompt routing.")
-    route.add_argument("mode", nargs="?", default="status", choices=["on", "off", "status"], help="Auto route mode.")
+    bind_model.add_argument("--api-key-env", default="", help="Environment variable containing API key.")
+    bind_model.add_argument("--modalities", default="text", help="Comma-separated modalities.")
+
+    bind_router = subparsers.add_parser("bind-router", help="Bind a separate intent router model endpoint.")
+    bind_router.add_argument("provider", help="Provider name, e.g. openai-compatible, groq, claude-subagent.")
+    bind_router.add_argument("model", help="Router model name.")
+    bind_router.add_argument("--base-url", default="", help="Provider base URL or local command for claude-subagent.")
+    bind_router.add_argument("--api-key-env", default="", help="Environment variable containing API key.")
+
+    bind_agent = subparsers.add_parser("bind-agent", help="Bind supervisor/main/small workflow agent.")
+    bind_agent.add_argument("slot", choices=["supervisor", "main", "small"], help="Workflow slot.")
+    bind_agent.add_argument("provider", help="Provider name, e.g. claude-subagent, openai-compatible, groq.")
+    bind_agent.add_argument("model", help="Model or subagent name.")
+    bind_agent.add_argument("--base-url", default="", help="Provider base URL or local command for claude-subagent.")
+    bind_agent.add_argument("--api-key-env", default="", help="Environment variable containing API key.")
+
+    subparsers.add_parser("workflow", help="Show supervisor/main/small workflow agents.")
+
+    route = subparsers.add_parser("route", help="Toggle or show auto prompt routing.")
+    route.add_argument("mode", nargs="?", default="status", choices=["on", "off", "status"], help="Auto route mode.")
 
     orchestrate = subparsers.add_parser("orchestrate", help="Build or run multi-model coding orchestration.")
     orchestrate.add_argument("task", nargs="?", default="", help="Coding task.")
@@ -209,21 +209,21 @@ def run_command(args: argparse.Namespace) -> int:
     if command == "clear-models":
         print(clear_models_text(context))
         return 0
-    if command == "bind-model":
-        print(bind_model_text(context, vars(args)))
-        return 0
-    if command == "bind-router":
-        print(bind_router_text(context, vars(args)))
-        return 0
-    if command == "bind-agent":
-        print(bind_agent_text(context, vars(args)))
-        return 0
-    if command == "workflow":
-        print(workflow_text(context))
-        return 0
-    if command == "route":
-        print(route_text(context, args.mode))
-        return 0
+    if command == "bind-model":
+        print(bind_model_text(context, vars(args)))
+        return 0
+    if command == "bind-router":
+        print(bind_router_text(context, vars(args)))
+        return 0
+    if command == "bind-agent":
+        print(bind_agent_text(context, vars(args)))
+        return 0
+    if command == "workflow":
+        print(workflow_text(context))
+        return 0
+    if command == "route":
+        print(route_text(context, args.mode))
+        return 0
     if command == "orchestrate":
         task = args.task or input("Task > ").strip()
         print(orchestrate_text(context, task, files=args.file, execute=args.execute))
@@ -238,132 +238,246 @@ def run_command(args: argparse.Namespace) -> int:
     raise SystemExit(f"unknown command: {command}")
 
 
-def run_tui(context: McpContext) -> None:
-    if run_textual_tui(context):
-        return
-    context.init_storage()
+def run_tui(context: McpContext) -> None:
+    if run_textual_tui(context):
+        return
+    context.init_storage()
     prompt_session = create_prompt_session()
     input_hint = "live slash autocomplete enabled" if prompt_session else "basic input fallback; install prompt_toolkit for live slash dropdown"
-    messages = [
-        "system > AgentRAM coding-agent CLI ready",
-        f"system > RAM root: {context.ram_root}",
-        f"system > {input_hint}",
-    ]
-    while True:
-        draw_screen(context, messages)
+    messages = [
+        "system > AgentRAM coding-agent CLI ready",
+        f"system > RAM root: {context.ram_root}",
+        f"system > {input_hint}",
+    ]
+    while True:
+        draw_screen(context, messages)
         try:
             user_input = read_tui_input(prompt_session).strip()
         except (EOFError, KeyboardInterrupt):
             return
-        if user_input in {"0", "q", "quit", "exit", "/exit", "/quit"}:
-            return
-        if user_input in BUTTONS:
-            user_input = BUTTONS[user_input]
-        if user_input:
-            messages.append(f"user > {user_input}")
-        response = run_with_activity(context, messages, user_input)
+        if user_input in {"0", "q", "quit", "exit", "/exit", "/quit"}:
+            return
+        if user_input in BUTTONS:
+            user_input = BUTTONS[user_input]
+        if user_input:
+            messages.append(f"user > {user_input}")
+        response = run_with_activity(context, messages, user_input)
         if response == "__clear__":
             messages.clear()
             messages.append("system > Chat cleared.")
         elif response:
             messages.append("agentram > " + response)
-        del messages[:-200]
-
-def run_textual_tui(context: McpContext) -> bool:
-    try:
-        from textual.app import App, ComposeResult
-        from textual.containers import Horizontal, Vertical
-        from textual.widgets import Footer, Header, Input, RichLog, Static
-    except ImportError:
-        return False
-
-    class AgentRAMTextualApp(App[None]):
-        CSS = """
-        Screen { background: #0b0f14; color: #d7dde8; }
-        #layout { height: 1fr; }
-        #sidebar { width: 32; border: solid #263241; padding: 1; }
-        #main { width: 1fr; }
-        #chat { height: 1fr; border: solid #263241; padding: 1; overflow-y: scroll; }
-        #input { dock: bottom; border: solid #3b82f6; }
-        .muted { color: #8b9bb0; }
-        """
-        BINDINGS = [("ctrl+c", "quit", "Quit")]
-
-        def __init__(self, mcp_context: McpContext) -> None:
-            super().__init__()
-            self.context = mcp_context
-            self.messages: list[str] = []
-            self.busy = False
-
-        def compose(self) -> ComposeResult:
-            yield Header(show_clock=True)
-            with Horizontal(id="layout"):
-                yield Static(id="sidebar")
-                with Vertical(id="main"):
-                    yield RichLog(id="chat", wrap=True, highlight=True, markup=False, auto_scroll=True)
-                    yield Input(placeholder="Prompt hoặc /command. Mouse wheel scroll trong khung chat.", id="input")
-            yield Footer()
-
-        def on_mount(self) -> None:
-            self.context.init_storage()
-            self.chat.write("system > AgentRAM Textual TUI ready")
-            self.chat.write(f"system > RAM root: {self.context.ram_root}")
-            self.refresh_sidebar()
-            self.set_interval(1.0, self.refresh_sidebar)
-
-        @property
-        def chat(self) -> RichLog:
-            return self.query_one("#chat", RichLog)
-
-        def refresh_sidebar(self) -> None:
-            self.query_one("#sidebar", Static).update("\n".join(sidebar_lines(self.context)))
-
-        async def on_input_submitted(self, event: Input.Submitted) -> None:
-            text = event.value.strip()
-            event.input.value = ""
-            if not text:
-                return
-            if text in {"0", "q", "quit", "exit", "/exit", "/quit"}:
-                self.exit()
-                return
-            if text in BUTTONS:
-                text = BUTTONS[text]
-            self.chat.write(f"user > {text}")
-            if text == "/clear":
-                self.chat.clear()
-                self.chat.write("system > Chat cleared.")
-                return
-            if self.busy:
-                self.chat.write("agentram > busy, wait current task")
-                return
-            self.busy = True
-            self.chat.write("agentram > thinking...")
-            try:
-                response = await asyncio.to_thread(handle_chat_input, self.context, text, self.messages)
-            except Exception as error:  # noqa: BLE001 - TUI boundary
-                response = f"error: {error}"
-            finally:
-                self.busy = False
-            if response == "__clear__":
-                self.chat.clear()
-                self.chat.write("system > Chat cleared.")
-            elif response:
-                self.chat.write("agentram > " + response)
-            self.refresh_sidebar()
-
-    AgentRAMTextualApp(context).run()
-    return True
-
-def run_with_activity(context: McpContext, messages: list[str], user_input: str) -> str:
-    with ThreadPoolExecutor(max_workers=1) as executor:
-        future = executor.submit(handle_chat_input, context, user_input, messages)
-        frames = ["thinking", "thinking.", "thinking..", "thinking...", "acting", "acting.", "acting..", "acting..."]
-        index = 0
-        while not future.done():
-            draw_screen(context, messages, activity=f"agentram > {frames[index % len(frames)]}")
-            index += 1
-            time.sleep(0.18)
-        return future.result()
+        del messages[:-200]
+
+def run_textual_tui(context: McpContext) -> bool:
+    try:
+        from textual.app import App, ComposeResult
+        from textual.containers import Horizontal, Vertical
+        from textual.widgets import Button, Footer, Header, Input, RichLog, Static
+    except ImportError:
+        return False
+
+    class AgentRAMTextualApp(App[None]):
+        CSS = """
+        Screen { background: #0b0f14; color: #d7dde8; }
+        #layout { height: 1fr; }
+        #sidebar { width: 32; border: solid #263241; padding: 1; }
+        #main { width: 1fr; }
+        #setup { height: auto; border: solid #3b82f6; padding: 1; background: #101826; }
+        #setup-title { height: auto; color: #dbeafe; }
+        #setup-actions { height: auto; }
+        .setup-input { height: 3; }
+        #chat { height: 1fr; border: solid #263241; padding: 1; overflow-y: scroll; }
+        #palette { height: auto; max-height: 12; border: solid #3b82f6; padding: 1; background: #101826; display: none; }
+        #input { dock: bottom; border: solid #3b82f6; }
+        .muted { color: #8b9bb0; }
+        """
+        BINDINGS = [("ctrl+c", "quit", "Quit"), ("tab", "accept_suggestion", "Complete slash"), ("ctrl+s", "save_setup", "Save setup")]
+
+        def __init__(self, mcp_context: McpContext) -> None:
+            super().__init__()
+            self.context = mcp_context
+            self.messages: list[str] = []
+            self.busy = False
+            self.suggestions: list[str] = []
+            self.setup_done = False
+
+        def compose(self) -> ComposeResult:
+            yield Header(show_clock=True)
+            with Horizontal(id="layout"):
+                yield Static(id="sidebar")
+                with Vertical(id="main"):
+                    yield RichLog(id="chat", wrap=True, highlight=True, markup=False, auto_scroll=True)
+                    yield Input(placeholder="Prompt hoặc /command. Mouse wheel scroll trong khung chat.", id="input")
+            yield Footer()
+
+        def on_mount(self) -> None:
+            self.context.init_storage()
+            self.chat.write("system > AgentRAM Textual TUI ready")
+            self.chat.write(f"system > RAM root: {self.context.ram_root}")
+            self.prefill_setup_from_profile()
+            self.refresh_sidebar()
+            self.set_interval(1.0, self.refresh_sidebar)
+            self.query_one("#setup-provider", Input).focus()
+
+        @property
+        def chat(self) -> RichLog:
+            return self.query_one("#chat", RichLog)
+
+        def refresh_sidebar(self) -> None:
+            self.query_one("#sidebar", Static).update("\n".join(sidebar_lines(self.context)))
+
+        def prefill_setup_from_profile(self) -> None:
+            agents = self.context.profile_store.list_agents()
+            if not agents:
+                return
+            first = next(iter(agents.values()))
+            self.query_one("#setup-provider", Input).value = first.provider
+            self.query_one("#setup-base-url", Input).value = first.base_url
+            self.query_one("#setup-api-key-env", Input).value = first.api_key_env
+            for slot in ("supervisor", "main", "small"):
+                endpoint = agents.get(slot)
+                if endpoint:
+                    self.query_one(f"#setup-{slot}", Input).value = endpoint.model
+            self.chat.write("system > Existing workflow models loaded. Save to update, or Skip to keep.")
+
+        def setup_value(self, widget_id: str) -> str:
+            return self.query_one(f"#{widget_id}", Input).value.strip()
+
+        def action_save_setup(self) -> None:
+            provider = self.setup_value("setup-provider") or "openai-compatible"
+            base_url = self.setup_value("setup-base-url")
+            api_key_env = self.setup_value("setup-api-key-env")
+            if api_key_env.startswith(("sk-", "gsk_", "sk_")):
+                self.chat.write("agentram > setup error: api key env must be variable name, not raw key")
+                return
+            role_by_slot = {"supervisor": "supervisor", "main": "coder", "small": "memory"}
+            bound: list[str] = []
+            for slot, role in role_by_slot.items():
+                model = self.setup_value(f"setup-{slot}")
+                if not model:
+                    continue
+                endpoint = AgentModelEndpoint(
+                    provider=provider,
+                    model=model,
+                    role=role,
+                    base_url=base_url,
+                    api_key_env=api_key_env,
+                    modalities=["text"],
+                )
+                self.context.profile_store.set_agent(slot, endpoint)
+                bound.append(f"{slot}={model}")
+            if not bound:
+                self.chat.write("agentram > setup skipped: no model entered")
+            else:
+                self.chat.write("agentram > setup saved: " + ", ".join(bound))
+            self.hide_setup()
+            self.refresh_sidebar()
+            self.query_one("#input", Input).focus()
+
+        def hide_setup(self) -> None:
+            self.setup_done = True
+            self.query_one("#setup", Vertical).styles.display = "none"
+
+        def on_button_pressed(self, event: Button.Pressed) -> None:
+            if event.button.id == "setup-save":
+                self.action_save_setup()
+            elif event.button.id == "setup-skip":
+                self.chat.write("system > Model setup skipped. Use /bind-agent later.")
+                self.hide_setup()
+                self.query_one("#input", Input).focus()
+
+        def hide_palette(self) -> None:
+            palette = self.query_one("#palette", Static)
+            palette.update("")
+            palette.styles.display = "none"
+
+        def show_palette(self, value: str) -> None:
+            palette = self.query_one("#palette", Static)
+            query = value.strip().lower().lstrip("/")
+            matches = []
+            for command, description in SLASH_COMMANDS:
+                if not command.startswith("/"):
+                    continue
+                command_name = command.split()[0]
+                haystack = command_name.lower().lstrip("/")
+                if query and query not in haystack:
+                    continue
+                matches.append((command_name, description))
+            self.suggestions = [command for command, _ in matches[:8]]
+            if not matches:
+                palette.update("No matching slash command")
+            else:
+                lines = ["Slash commands  ?  Tab completes first match"]
+                lines.extend(f"  {command.ljust(18)} {description}" for command, description in matches[:8])
+                palette.update("\n".join(lines))
+            palette.styles.display = "block"
+
+        def on_input_changed(self, event: Input.Changed) -> None:
+            value = event.value.strip()
+            if value.startswith("/"):
+                self.show_palette(value)
+            else:
+                self.hide_palette()
+
+        def action_accept_suggestion(self) -> None:
+            input_widget = self.query_one("#input", Input)
+            if not input_widget.value.strip().startswith("/") or not self.suggestions:
+                return
+            input_widget.value = self.suggestions[0] + " "
+            input_widget.cursor_position = len(input_widget.value)
+            self.hide_palette()
+
+        async def on_input_submitted(self, event: Input.Submitted) -> None:
+            if event.input.id and str(event.input.id).startswith("setup-"):
+                self.action_save_setup()
+                return
+            text = event.value.strip()
+            event.input.value = ""
+            self.hide_palette()
+            if not text:
+                return
+            if text in {"0", "q", "quit", "exit", "/exit", "/quit"}:
+                self.exit()
+                return
+            if text in BUTTONS:
+                text = BUTTONS[text]
+            self.chat.write(f"user > {text}")
+            if text == "/clear":
+                self.chat.clear()
+                self.chat.write("system > Chat cleared.")
+                return
+            if self.busy:
+                self.chat.write("agentram > busy, wait current task")
+                return
+            self.busy = True
+            self.chat.write("agentram > thinking...")
+            try:
+                response = await asyncio.to_thread(handle_chat_input, self.context, text, self.messages)
+            except Exception as error:  # noqa: BLE001 - TUI boundary
+                response = f"error: {error}"
+            finally:
+                self.busy = False
+            if response == "__clear__":
+                self.chat.clear()
+                self.chat.write("system > Chat cleared.")
+            elif response:
+                self.chat.write("agentram > " + response)
+            self.refresh_sidebar()
+
+    AgentRAMTextualApp(context).run()
+    return True
+
+def run_with_activity(context: McpContext, messages: list[str], user_input: str) -> str:
+    with ThreadPoolExecutor(max_workers=1) as executor:
+        future = executor.submit(handle_chat_input, context, user_input, messages)
+        frames = ["thinking", "thinking.", "thinking..", "thinking...", "acting", "acting.", "acting..", "acting..."]
+        index = 0
+        while not future.done():
+            draw_screen(context, messages, activity=f"agentram > {frames[index % len(frames)]}")
+            index += 1
+            time.sleep(0.18)
+        return future.result()
 
 
 
@@ -401,24 +515,24 @@ def read_tui_input(prompt_session: Any | None) -> str:
         return input("You > ")
     return prompt_session.prompt("You > ")
 
-def handle_chat_input(context: McpContext, text: str, messages: list[str] | None = None) -> str:
+def handle_chat_input(context: McpContext, text: str, messages: list[str] | None = None) -> str:
     if not text:
         return SLASH_HELP
     if text == "/":
         return slash_palette_text()
     if text.startswith("/"):
         return handle_slash_command(context, text, messages)
-    call_tool(
-        context,
-        "agentram_emit_event",
-        {"type": "USER_MESSAGE", "payload": {"content": text}, "task_id": "codex", "ingest": False},
-    )
-    if context.profile_store.list_agents():
-        return supervisor_workflow_text(context, text)
-    if context.profile_store.auto_route_enabled():
-        return route_plain_prompt_text(context, text)
-    context_block = retrieve_text(context, text, task_id="codex", limit=6)
-    return "Coding chat captured. Relevant context:\n" + context_block
+    call_tool(
+        context,
+        "agentram_emit_event",
+        {"type": "USER_MESSAGE", "payload": {"content": text}, "task_id": "codex", "ingest": False},
+    )
+    if context.profile_store.list_agents():
+        return supervisor_workflow_text(context, text)
+    if context.profile_store.auto_route_enabled():
+        return route_plain_prompt_text(context, text)
+    context_block = retrieve_text(context, text, task_id="codex", limit=6)
+    return "Coding chat captured. Relevant context:\n" + context_block
 
 
 def handle_slash_command(context: McpContext, text: str, messages: list[str] | None = None) -> str:
@@ -455,24 +569,24 @@ def handle_slash_command(context: McpContext, text: str, messages: list[str] | N
         return disable_model_text(context, raw_rest)
     if command == "/clear-models":
         return clear_models_text(context)
-    if command == "/bind-model":
-        if len(rest) < 2:
-            return "Usage: /bind-model <provider> <model> [--role coder] [--base-url URL_OR_COMMAND] [--api-key-env ENV_NAME]"
-        return bind_model_text(context, parse_bind_model_args(rest))
-    if command == "/bind-router":
-        if len(rest) < 2:
-            return "Usage: /bind-router <provider> <model> [--base-url URL_OR_COMMAND] [--api-key-env ENV_NAME]"
-        return bind_router_text(context, parse_bind_model_args(rest))
-    if command == "/bind-agent":
-        if len(rest) < 3:
-            return "Usage: /bind-agent <supervisor|main|small> <provider> <model> [--base-url URL_OR_COMMAND] [--api-key-env ENV_NAME]"
-        options = parse_bind_model_args(rest[1:])
-        options["slot"] = rest[0]
-        return bind_agent_text(context, options)
-    if command == "/workflow":
-        return workflow_text(context)
-    if command == "/route":
-        return route_text(context, rest[0] if rest else "status")
+    if command == "/bind-model":
+        if len(rest) < 2:
+            return "Usage: /bind-model <provider> <model> [--role coder] [--base-url URL_OR_COMMAND] [--api-key-env ENV_NAME]"
+        return bind_model_text(context, parse_bind_model_args(rest))
+    if command == "/bind-router":
+        if len(rest) < 2:
+            return "Usage: /bind-router <provider> <model> [--base-url URL_OR_COMMAND] [--api-key-env ENV_NAME]"
+        return bind_router_text(context, parse_bind_model_args(rest))
+    if command == "/bind-agent":
+        if len(rest) < 3:
+            return "Usage: /bind-agent <supervisor|main|small> <provider> <model> [--base-url URL_OR_COMMAND] [--api-key-env ENV_NAME]"
+        options = parse_bind_model_args(rest[1:])
+        options["slot"] = rest[0]
+        return bind_agent_text(context, options)
+    if command == "/workflow":
+        return workflow_text(context)
+    if command == "/route":
+        return route_text(context, rest[0] if rest else "status")
     if command == "/orchestrate":
         execute = "--execute" in rest
         task = raw_rest.replace("--execute", "").strip()
@@ -626,7 +740,7 @@ def models_text(context: McpContext) -> str:
     data = payload(call_tool(context, "agentram_read_coding_models", {}))
     endpoints = data.get("endpoints", [])
     if not endpoints:
-        return "No coding models bound. Use /bind-model claude-subagent agentram-reviewer role=reviewer or /bind-model claude claude-3-5-sonnet-latest role=reviewer api_key_env=ANTHROPIC_API_KEY"
+        return "No coding models bound. Use /bind-model claude-subagent agentram-reviewer role=reviewer or /bind-model claude claude-3-5-sonnet-latest role=reviewer api_key_env=ANTHROPIC_API_KEY"
     lines = ["Bound coding models:"]
     for endpoint in endpoints:
         lines.append(f"- {endpoint.get('id')} provider={endpoint.get('provider')} model={endpoint.get('model')} role={endpoint.get('role')} modalities={','.join(endpoint.get('modalities', []))}")
@@ -698,211 +812,211 @@ def bind_model_text(context: McpContext, options: dict[str, object]) -> str:
     return f"Bound model: {endpoint.get('id')} provider={endpoint.get('provider')} model={endpoint.get('model')} role={endpoint.get('role')}"
 
 
-def bind_agent_text(context: McpContext, options: dict[str, object]) -> str:
-    slot = str(options.get("slot", "")).strip().lower()
-    if slot not in {"supervisor", "main", "small"}:
-        return "Usage: /bind-agent <supervisor|main|small> <provider> <model>"
-    api_key_env = str(options.get("api_key_env", ""))
-    if api_key_env.startswith(("sk-", "gsk_", "sk_")):
-        return "Do not paste raw API key into api_key_env. Set env var first, then use api_key_env=ENV_NAME."
-    role = {"supervisor": "supervisor", "main": "coder", "small": "memory"}[slot]
-    endpoint = AgentModelEndpoint(
-        provider=str(options.get("provider", "openai-compatible")),
-        model=str(options.get("model", "")),
-        role=role,
-        base_url=str(options.get("base_url", "")),
-        api_key_env=api_key_env,
-        modalities=["text"],
-    )
-    context.profile_store.set_agent(slot, endpoint)
-    return f"Bound {slot} agent: provider={endpoint.provider} model={endpoint.model} role={endpoint.role}"
-
-def workflow_text(context: McpContext) -> str:
-    agents = context.profile_store.list_agents()
-    if not agents:
-        return "No supervisor workflow agents bound. Use /bind-agent supervisor|main|small <provider> <model>."
-    lines = ["Supervisor workflow agents:"]
-    for slot in ["supervisor", "main", "small"]:
-        endpoint = agents.get(slot)
-        if endpoint:
-            lines.append(f"- {slot}: {endpoint.provider}:{endpoint.model} role={endpoint.role}")
-        else:
-            lines.append(f"- {slot}: not bound")
-    return "\n".join(lines)
-
-def supervisor_workflow_text(context: McpContext, prompt: str) -> str:
-    agents = context.profile_store.list_agents()
-    supervisor = agents.get("supervisor")
-    main_agent = agents.get("main")
-    small_agent = agents.get("small")
-    memory_context = retrieve_text(context, prompt, task_id="codex", limit=8)
-    plan = supervisor_plan(supervisor, prompt, memory_context)
-    outputs: dict[str, str] = {}
-    with ThreadPoolExecutor(max_workers=2) as executor:
-        futures = {}
-        if main_agent:
-            futures[executor.submit(call_agent_endpoint, main_agent, build_main_agent_prompt(prompt, plan, memory_context))] = "main"
-        if small_agent:
-            futures[executor.submit(call_agent_endpoint, small_agent, build_small_agent_prompt(prompt, plan, memory_context))] = "small"
-        for future, slot in list(futures.items()):
-            try:
-                outputs[slot] = future.result()
-            except Exception as error:  # noqa: BLE001 - agent boundary
-                outputs[slot] = f"error: {model_error_hint(str(error))}"
-    if not main_agent:
-        outputs["main"] = "No main agent bound. Use /bind-agent main <provider> <model>."
-    persist_workflow_memory(context, prompt, plan, outputs)
-    return "\n".join(
-        [
-            "Workflow: supervisor -> main + small -> merge",
-            "Supervisor plan:",
-            plan,
-            "",
-            "Main agent result:",
-            outputs.get("main", "-"),
-            "",
-            "Small memory agent notes:",
-            outputs.get("small", "No small agent bound."),
-        ]
-    )
-
-def persist_workflow_memory(context: McpContext, prompt: str, plan: str, outputs: dict[str, str]) -> None:
-    small_notes = outputs.get("small", "").strip()
-    main_result = outputs.get("main", "").strip()
-    note_parts = [
-        f"User request: {prompt}",
-        f"Supervisor plan: {trim(plan.strip(), 1200)}" if plan.strip() else "Supervisor plan: -",
-    ]
-    if small_notes and not small_notes.startswith("error:"):
-        note_parts.append(f"Small memory notes: {trim(small_notes, 1200)}")
-    else:
-        note_parts.append("Small memory notes: unavailable; persisted supervisor plan as fallback RAM note.")
-    if main_result and not main_result.startswith("error:"):
-        note_parts.append(f"Main result summary: {trim(main_result, 600)}")
-    content = "\n".join(note_parts).strip()
-    if not content:
-        return
-    call_tool(
-        context,
-        "agentram_emit_event",
-        {"type": "DECISION", "payload": {"content": content}, "task_id": "codex", "ingest": True},
-    )
-
-def supervisor_plan(supervisor: AgentModelEndpoint | None, prompt: str, memory_context: str) -> str:
-    if not supervisor:
-        return "No supervisor bound. Fallback plan: handle user request, run main coding agent, ask small agent to update RAM notes."
-    try:
-        return call_agent_endpoint(supervisor, build_supervisor_prompt(prompt, memory_context))
-    except Exception as error:  # noqa: BLE001 - supervisor boundary
-        return f"Supervisor error: {error}\nFallback plan: handle user request, run main coding agent, ask small agent to update RAM notes."
-
-def call_agent_endpoint(endpoint: AgentModelEndpoint, prompt: str) -> str:
-    return MultiModelCodingOrchestrator([endpoint])._call_endpoint(endpoint, prompt)
-
-def build_supervisor_prompt(prompt: str, memory_context: str) -> str:
-    return "\n".join(["You are AgentRAM supervisor. Act like a senior coding-agent boss.", "Create concise plan for main coding agent and small memory agent.", "Return only actionable plan. No markdown table.", "User request:", prompt, "AgentRAM context:", memory_context])
-
-def build_main_agent_prompt(prompt: str, plan: str, memory_context: str) -> str:
-    return "\n".join(["You are AgentRAM main coding agent.", "Follow supervisor plan. Focus on planning, orchestration, coding, refactor, bug fix, and final result.", "Do not invent repo facts. Mention files to inspect/change.", "User request:", prompt, "Supervisor plan:", plan, "AgentRAM context:", memory_context])
-
-def build_small_agent_prompt(prompt: str, plan: str, memory_context: str) -> str:
-    return "\n".join(["You are AgentRAM small memory agent.", "Do not edit code. Note plans, decisions, risks, files, next tasks, and coding facts for RAM.", "Return concise memory notes only.", "User request:", prompt, "Supervisor plan:", plan, "AgentRAM context:", memory_context])
-
-def bind_router_text(context: McpContext, options: dict[str, object]) -> str:
-    api_key_env = str(options.get("api_key_env", ""))
-    if api_key_env.startswith(("sk-", "gsk_", "sk_")):
-        return "Do not paste raw API key into api_key_env. Set env var first, then use api_key_env=ENV_NAME."
-    endpoint = AgentModelEndpoint(
-        provider=str(options.get("provider", "openai-compatible")),
-        model=str(options.get("model", "")),
-        role="router",
-        base_url=str(options.get("base_url", "")),
-        api_key_env=api_key_env,
-        modalities=["text"],
-    )
-    context.profile_store.set_router(endpoint)
-    return f"Bound router: provider={endpoint.provider} model={endpoint.model}"
-
-def route_text(context: McpContext, mode: str) -> str:
-    normalized = mode.strip().lower() or "status"
-    if normalized == "on":
-        context.profile_store.set_auto_route(True)
-    elif normalized == "off":
-        context.profile_store.set_auto_route(False)
-    elif normalized != "status":
-        return "Usage: /route on|off|status"
-    router = context.profile_store.get_router()
-    return "\n".join(
-        [
-            f"Auto route: {'on' if context.profile_store.auto_route_enabled() else 'off'}",
-            f"Router model: {router.provider}:{router.model}" if router else "Router model: heuristic fallback",
-        ]
-    )
-
-def route_plain_prompt_text(context: McpContext, prompt: str) -> str:
-    decision = classify_prompt_intent(context, prompt)
-    intent = str(decision.get("intent", "chat"))
-    confidence = float(decision.get("confidence", 0.0))
-    prefix = f"Route: {intent} confidence={confidence:.2f}"
-    if intent == "coding":
-        if context.profile_store.list_endpoints():
-            return prefix + "\n" + orchestrate_text(context, prompt, execute=True)
-        context_block = retrieve_text(context, prompt, task_id="codex", limit=6)
-        return prefix + "\nNo coding models bound. Use /bind-model.\nCoding chat captured. Relevant context:\n" + context_block
-    if intent == "planning":
-        return prefix + "\n" + drift_text(context, prompt) + "\n\n" + goal_text(context)
-    if intent == "memory":
-        return prefix + "\n" + note_text(context, prompt)
-    context_block = retrieve_text(context, prompt, task_id="codex", limit=6)
-    return prefix + "\nCoding chat captured. Relevant context:\n" + context_block
-
-def classify_prompt_intent(context: McpContext, prompt: str) -> dict[str, object]:
-    router = context.profile_store.get_router()
-    if router:
-        try:
-            response = MultiModelCodingOrchestrator([router])._call_endpoint(router, build_router_prompt(prompt))
-            parsed = json.loads(extract_json_object(response))
-            if isinstance(parsed, dict) and parsed.get("intent") in {"coding", "planning", "memory", "chat"}:
-                return {"intent": parsed.get("intent"), "confidence": float(parsed.get("confidence", 0.0)), "source": "model"}
-        except Exception as error:  # noqa: BLE001 - router fallback boundary
-            return {**heuristic_intent(prompt), "source": "heuristic", "router_error": str(error)}
-    return {**heuristic_intent(prompt), "source": "heuristic"}
-
-def build_router_prompt(prompt: str) -> str:
-    return "\n".join(
-        [
-            "Classify user prompt for AgentRAM routing.",
-            "Return only JSON, no markdown.",
-            "Schema: {\"intent\":\"coding|planning|memory|chat\",\"confidence\":0.0,\"reason\":\"short\"}",
-            "coding = edit/review/debug/refactor/test/code/file requests.",
-            "planning = goal stack, milestone, mission, next task, drift, roadmap.",
-            "memory = remember/note/decision/fact to save.",
-            "chat = other normal conversation.",
-            f"Prompt: {prompt}",
-        ]
-    )
-
-def extract_json_object(text: str) -> str:
-    start = text.find("{")
-    end = text.rfind("}")
-    if start == -1 or end == -1 or end < start:
-        return "{}"
-    return text[start : end + 1]
-
-def heuristic_intent(prompt: str) -> dict[str, object]:
-    lower = prompt.lower()
-    memory_words = ["ghi nhớ", "remember", "note", "decision", "lưu lại", "save this"]
-    planning_words = ["goal", "kế hoạch", "ke hoach", "milestone", "mission", "drift", "next task", "roadmap", "mục tiêu", "muc tieu"]
-    coding_words = ["sửa", "sua", "fix", "bug", "code", "test", "refactor", "review", "file", ".py", ".js", "endpoint", "class", "function"]
-    if any(word in lower for word in memory_words):
-        return {"intent": "memory", "confidence": 0.75}
-    if any(word in lower for word in planning_words):
-        return {"intent": "planning", "confidence": 0.75}
-    if any(word in lower for word in coding_words):
-        return {"intent": "coding", "confidence": 0.72}
-    return {"intent": "chat", "confidence": 0.55}
-
-def orchestrate_text(context: McpContext, task: str, files: list[str] | None = None, execute: bool = False) -> str:
+def bind_agent_text(context: McpContext, options: dict[str, object]) -> str:
+    slot = str(options.get("slot", "")).strip().lower()
+    if slot not in {"supervisor", "main", "small"}:
+        return "Usage: /bind-agent <supervisor|main|small> <provider> <model>"
+    api_key_env = str(options.get("api_key_env", ""))
+    if api_key_env.startswith(("sk-", "gsk_", "sk_")):
+        return "Do not paste raw API key into api_key_env. Set env var first, then use api_key_env=ENV_NAME."
+    role = {"supervisor": "supervisor", "main": "coder", "small": "memory"}[slot]
+    endpoint = AgentModelEndpoint(
+        provider=str(options.get("provider", "openai-compatible")),
+        model=str(options.get("model", "")),
+        role=role,
+        base_url=str(options.get("base_url", "")),
+        api_key_env=api_key_env,
+        modalities=["text"],
+    )
+    context.profile_store.set_agent(slot, endpoint)
+    return f"Bound {slot} agent: provider={endpoint.provider} model={endpoint.model} role={endpoint.role}"
+
+def workflow_text(context: McpContext) -> str:
+    agents = context.profile_store.list_agents()
+    if not agents:
+        return "No supervisor workflow agents bound. Use /bind-agent supervisor|main|small <provider> <model>."
+    lines = ["Supervisor workflow agents:"]
+    for slot in ["supervisor", "main", "small"]:
+        endpoint = agents.get(slot)
+        if endpoint:
+            lines.append(f"- {slot}: {endpoint.provider}:{endpoint.model} role={endpoint.role}")
+        else:
+            lines.append(f"- {slot}: not bound")
+    return "\n".join(lines)
+
+def supervisor_workflow_text(context: McpContext, prompt: str) -> str:
+    agents = context.profile_store.list_agents()
+    supervisor = agents.get("supervisor")
+    main_agent = agents.get("main")
+    small_agent = agents.get("small")
+    memory_context = retrieve_text(context, prompt, task_id="codex", limit=8)
+    plan = supervisor_plan(supervisor, prompt, memory_context)
+    outputs: dict[str, str] = {}
+    with ThreadPoolExecutor(max_workers=2) as executor:
+        futures = {}
+        if main_agent:
+            futures[executor.submit(call_agent_endpoint, main_agent, build_main_agent_prompt(prompt, plan, memory_context))] = "main"
+        if small_agent:
+            futures[executor.submit(call_agent_endpoint, small_agent, build_small_agent_prompt(prompt, plan, memory_context))] = "small"
+        for future, slot in list(futures.items()):
+            try:
+                outputs[slot] = future.result()
+            except Exception as error:  # noqa: BLE001 - agent boundary
+                outputs[slot] = f"error: {model_error_hint(str(error))}"
+    if not main_agent:
+        outputs["main"] = "No main agent bound. Use /bind-agent main <provider> <model>."
+    persist_workflow_memory(context, prompt, plan, outputs)
+    return "\n".join(
+        [
+            "Workflow: supervisor -> main + small -> merge",
+            "Supervisor plan:",
+            plan,
+            "",
+            "Main agent result:",
+            outputs.get("main", "-"),
+            "",
+            "Small memory agent notes:",
+            outputs.get("small", "No small agent bound."),
+        ]
+    )
+
+def persist_workflow_memory(context: McpContext, prompt: str, plan: str, outputs: dict[str, str]) -> None:
+    small_notes = outputs.get("small", "").strip()
+    main_result = outputs.get("main", "").strip()
+    note_parts = [
+        f"User request: {prompt}",
+        f"Supervisor plan: {trim(plan.strip(), 1200)}" if plan.strip() else "Supervisor plan: -",
+    ]
+    if small_notes and not small_notes.startswith("error:"):
+        note_parts.append(f"Small memory notes: {trim(small_notes, 1200)}")
+    else:
+        note_parts.append("Small memory notes: unavailable; persisted supervisor plan as fallback RAM note.")
+    if main_result and not main_result.startswith("error:"):
+        note_parts.append(f"Main result summary: {trim(main_result, 600)}")
+    content = "\n".join(note_parts).strip()
+    if not content:
+        return
+    call_tool(
+        context,
+        "agentram_emit_event",
+        {"type": "DECISION", "payload": {"content": content}, "task_id": "codex", "ingest": True},
+    )
+
+def supervisor_plan(supervisor: AgentModelEndpoint | None, prompt: str, memory_context: str) -> str:
+    if not supervisor:
+        return "No supervisor bound. Fallback plan: handle user request, run main coding agent, ask small agent to update RAM notes."
+    try:
+        return call_agent_endpoint(supervisor, build_supervisor_prompt(prompt, memory_context))
+    except Exception as error:  # noqa: BLE001 - supervisor boundary
+        return f"Supervisor error: {error}\nFallback plan: handle user request, run main coding agent, ask small agent to update RAM notes."
+
+def call_agent_endpoint(endpoint: AgentModelEndpoint, prompt: str) -> str:
+    return MultiModelCodingOrchestrator([endpoint])._call_endpoint(endpoint, prompt)
+
+def build_supervisor_prompt(prompt: str, memory_context: str) -> str:
+    return "\n".join(["You are AgentRAM supervisor. Act like a senior coding-agent boss.", "Create concise plan for main coding agent and small memory agent.", "Return only actionable plan. No markdown table.", "User request:", prompt, "AgentRAM context:", memory_context])
+
+def build_main_agent_prompt(prompt: str, plan: str, memory_context: str) -> str:
+    return "\n".join(["You are AgentRAM main coding agent.", "Follow supervisor plan. Focus on planning, orchestration, coding, refactor, bug fix, and final result.", "Do not invent repo facts. Mention files to inspect/change.", "User request:", prompt, "Supervisor plan:", plan, "AgentRAM context:", memory_context])
+
+def build_small_agent_prompt(prompt: str, plan: str, memory_context: str) -> str:
+    return "\n".join(["You are AgentRAM small memory agent.", "Do not edit code. Note plans, decisions, risks, files, next tasks, and coding facts for RAM.", "Return concise memory notes only.", "User request:", prompt, "Supervisor plan:", plan, "AgentRAM context:", memory_context])
+
+def bind_router_text(context: McpContext, options: dict[str, object]) -> str:
+    api_key_env = str(options.get("api_key_env", ""))
+    if api_key_env.startswith(("sk-", "gsk_", "sk_")):
+        return "Do not paste raw API key into api_key_env. Set env var first, then use api_key_env=ENV_NAME."
+    endpoint = AgentModelEndpoint(
+        provider=str(options.get("provider", "openai-compatible")),
+        model=str(options.get("model", "")),
+        role="router",
+        base_url=str(options.get("base_url", "")),
+        api_key_env=api_key_env,
+        modalities=["text"],
+    )
+    context.profile_store.set_router(endpoint)
+    return f"Bound router: provider={endpoint.provider} model={endpoint.model}"
+
+def route_text(context: McpContext, mode: str) -> str:
+    normalized = mode.strip().lower() or "status"
+    if normalized == "on":
+        context.profile_store.set_auto_route(True)
+    elif normalized == "off":
+        context.profile_store.set_auto_route(False)
+    elif normalized != "status":
+        return "Usage: /route on|off|status"
+    router = context.profile_store.get_router()
+    return "\n".join(
+        [
+            f"Auto route: {'on' if context.profile_store.auto_route_enabled() else 'off'}",
+            f"Router model: {router.provider}:{router.model}" if router else "Router model: heuristic fallback",
+        ]
+    )
+
+def route_plain_prompt_text(context: McpContext, prompt: str) -> str:
+    decision = classify_prompt_intent(context, prompt)
+    intent = str(decision.get("intent", "chat"))
+    confidence = float(decision.get("confidence", 0.0))
+    prefix = f"Route: {intent} confidence={confidence:.2f}"
+    if intent == "coding":
+        if context.profile_store.list_endpoints():
+            return prefix + "\n" + orchestrate_text(context, prompt, execute=True)
+        context_block = retrieve_text(context, prompt, task_id="codex", limit=6)
+        return prefix + "\nNo coding models bound. Use /bind-model.\nCoding chat captured. Relevant context:\n" + context_block
+    if intent == "planning":
+        return prefix + "\n" + drift_text(context, prompt) + "\n\n" + goal_text(context)
+    if intent == "memory":
+        return prefix + "\n" + note_text(context, prompt)
+    context_block = retrieve_text(context, prompt, task_id="codex", limit=6)
+    return prefix + "\nCoding chat captured. Relevant context:\n" + context_block
+
+def classify_prompt_intent(context: McpContext, prompt: str) -> dict[str, object]:
+    router = context.profile_store.get_router()
+    if router:
+        try:
+            response = MultiModelCodingOrchestrator([router])._call_endpoint(router, build_router_prompt(prompt))
+            parsed = json.loads(extract_json_object(response))
+            if isinstance(parsed, dict) and parsed.get("intent") in {"coding", "planning", "memory", "chat"}:
+                return {"intent": parsed.get("intent"), "confidence": float(parsed.get("confidence", 0.0)), "source": "model"}
+        except Exception as error:  # noqa: BLE001 - router fallback boundary
+            return {**heuristic_intent(prompt), "source": "heuristic", "router_error": str(error)}
+    return {**heuristic_intent(prompt), "source": "heuristic"}
+
+def build_router_prompt(prompt: str) -> str:
+    return "\n".join(
+        [
+            "Classify user prompt for AgentRAM routing.",
+            "Return only JSON, no markdown.",
+            "Schema: {\"intent\":\"coding|planning|memory|chat\",\"confidence\":0.0,\"reason\":\"short\"}",
+            "coding = edit/review/debug/refactor/test/code/file requests.",
+            "planning = goal stack, milestone, mission, next task, drift, roadmap.",
+            "memory = remember/note/decision/fact to save.",
+            "chat = other normal conversation.",
+            f"Prompt: {prompt}",
+        ]
+    )
+
+def extract_json_object(text: str) -> str:
+    start = text.find("{")
+    end = text.rfind("}")
+    if start == -1 or end == -1 or end < start:
+        return "{}"
+    return text[start : end + 1]
+
+def heuristic_intent(prompt: str) -> dict[str, object]:
+    lower = prompt.lower()
+    memory_words = ["ghi nhớ", "remember", "note", "decision", "lưu lại", "save this"]
+    planning_words = ["goal", "kế hoạch", "ke hoach", "milestone", "mission", "drift", "next task", "roadmap", "mục tiêu", "muc tieu"]
+    coding_words = ["sửa", "sua", "fix", "bug", "code", "test", "refactor", "review", "file", ".py", ".js", "endpoint", "class", "function"]
+    if any(word in lower for word in memory_words):
+        return {"intent": "memory", "confidence": 0.75}
+    if any(word in lower for word in planning_words):
+        return {"intent": "planning", "confidence": 0.75}
+    if any(word in lower for word in coding_words):
+        return {"intent": "coding", "confidence": 0.72}
+    return {"intent": "chat", "confidence": 0.55}
+
+def orchestrate_text(context: McpContext, task: str, files: list[str] | None = None, execute: bool = False) -> str:
     if not task.strip():
         return "Usage: /orchestrate <coding task>"
     tool = "agentram_run_coding_orchestration" if execute else "agentram_build_coding_orchestration"
@@ -926,16 +1040,16 @@ def model_error_hint(message: str) -> str:
     lower = message.lower()
     if "base_url is required" in lower:
         return message + " | Fix: /remove-model <id> or re-bind with --base-url http://localhost:8000/v1"
-    if "actively refused" in lower or "connection refused" in lower or "winerror 10061" in lower:
-        return message + " | Fix: start your OpenAI-compatible server at base_url, or change --base-url."
-    if "http 404" in lower or "404: not found" in lower:
-        return message + " | Fix: verify base_url includes /v1, provider supports /chat/completions, and model name exists."
-    if "http 400" in lower and "not supported" in lower:
-        return message + " | Fix: this account/provider rejects that model. Bind a supported model name from your local endpoint."
-    if "returned non-json" in lower or "expecting value" in lower:
-        return message + " | Fix: endpoint returned empty/HTML/non-JSON. Check base_url, auth key, proxy, and server logs."
-    if "missing api key env" in lower:
-        return message + " | Fix: set environment variable, then bind using --api-key-env ENV_NAME, not raw key."
+    if "actively refused" in lower or "connection refused" in lower or "winerror 10061" in lower:
+        return message + " | Fix: start your OpenAI-compatible server at base_url, or change --base-url."
+    if "http 404" in lower or "404: not found" in lower:
+        return message + " | Fix: verify base_url includes /v1, provider supports /chat/completions, and model name exists."
+    if "http 400" in lower and "not supported" in lower:
+        return message + " | Fix: this account/provider rejects that model. Bind a supported model name from your local endpoint."
+    if "returned non-json" in lower or "expecting value" in lower:
+        return message + " | Fix: endpoint returned empty/HTML/non-JSON. Check base_url, auth key, proxy, and server logs."
+    if "missing api key env" in lower:
+        return message + " | Fix: set environment variable, then bind using --api-key-env ENV_NAME, not raw key."
     return message
 
 def claude_template_root() -> Path:
@@ -1004,7 +1118,7 @@ BUTTONS = {
 }
 
 
-def draw_screen(context: McpContext, messages: list[str], activity: str | None = None) -> None:
+def draw_screen(context: McpContext, messages: list[str], activity: str | None = None) -> None:
     clear_terminal()
     width = min(max(shutil.get_terminal_size((110, 34)).columns, 86), 132)
     left_width = 30
@@ -1013,17 +1127,17 @@ def draw_screen(context: McpContext, messages: list[str], activity: str | None =
     print(box_text("◆ AgentRAM Code  |  RAM + Claude subagents + slash commands", width))
     print("+" + "-" * (width - 2) + "+")
 
-    sidebar = sidebar_lines(context)
-    display_messages = [*messages, activity] if activity else messages
-    chat = wrap_messages(display_messages, right_width - 4)[-22:]
+    sidebar = sidebar_lines(context)
+    display_messages = [*messages, activity] if activity else messages
+    chat = wrap_messages(display_messages, right_width - 4)[-22:]
     rows = max(len(sidebar), len(chat), 22)
     for index in range(rows):
         left = sidebar[index] if index < len(sidebar) else ""
         right = chat[index] if index < len(chat) else ""
         print("| " + left[: left_width - 2].ljust(left_width - 2) + "| " + right[: right_width - 2].ljust(right_width - 2) + "|")
     print("+" + "-" * (left_width - 1) + "+" + "-" * (right_width) + "+")
-    footer = "Thinking/acting..." if activity else "Input: type / for commands. Use mouse wheel or terminal scrollbar for previous output."
-    print(box_text(footer, width))
+    footer = "Thinking/acting..." if activity else "Input: type / for commands. Use mouse wheel or terminal scrollbar for previous output."
+    print(box_text(footer, width))
     print("+" + "-" * (width - 2) + "+")
 
 
@@ -1062,8 +1176,8 @@ def sidebar_lines(context: McpContext) -> list[str]:
         "  /ask <prompt>",
     ]
 
-
-
+
+
 def trim(text: str, limit: int) -> str:
     return text if len(text) <= limit else text[: limit - 1] + "…"
 

package/package.json

@@ -1,52 +1,52 @@
-{
-  "name": "agentram",
-  "version": "0.1.13",
-  "description": "Async, model-agnostic Working RAM for coding agents.",
-  "license": "MIT",
-  "homepage": "https://github.com/trancongnghia/AGENT_RAM#readme",
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/trancongnghia/AGENT_RAM.git"
-  },
-  "bugs": {
-    "url": "https://github.com/trancongnghia/AGENT_RAM/issues"
-  },
-  "keywords": [
-    "agent",
-    "memory",
-    "codex",
-    "claude",
-    "mcp",
-    "llm"
-  ],
-  "bin": {
-    "agentram": "bin/agentram.js",
-    "agentram-mcp": "bin/agentram-mcp.js"
-  },
-  "scripts": {
-    "agentram": "node bin/agentram.js",
-    "agentram:mcp": "node bin/agentram-mcp.js",
-    "test": "python -m pytest -q",
-    "pack:dry-run": "npm pack --dry-run",
-    "prepublishOnly": "npm test",
-    "postinstall": "node bin/agentram-postinstall.js"
-  },
-  "files": [
-    "agentram/*.py",
-    "bin/*.js",
-    ".claude/agents/*.md",
-    ".claude/commands/*.md",
-    "agentram_mcp_server.py",
-    "agentram_daemon.py",
-    "codex_ram.py",
-    "pyproject.toml",
-    "README.md",
-    "LICENSE"
-  ],
-  "engines": {
-    "node": ">=16"
-  },
-  "publishConfig": {
-    "access": "public"
-  }
-}
+{
+  "name": "agentram",
+  "version": "0.1.15",
+  "description": "Async, model-agnostic Working RAM for coding agents.",
+  "license": "MIT",
+  "homepage": "https://github.com/trancongnghia/AGENT_RAM#readme",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/trancongnghia/AGENT_RAM.git"
+  },
+  "bugs": {
+    "url": "https://github.com/trancongnghia/AGENT_RAM/issues"
+  },
+  "keywords": [
+    "agent",
+    "memory",
+    "codex",
+    "claude",
+    "mcp",
+    "llm"
+  ],
+  "bin": {
+    "agentram": "bin/agentram.js",
+    "agentram-mcp": "bin/agentram-mcp.js"
+  },
+  "scripts": {
+    "agentram": "node bin/agentram.js",
+    "agentram:mcp": "node bin/agentram-mcp.js",
+    "test": "python -m pytest -q",
+    "pack:dry-run": "npm pack --dry-run",
+    "prepublishOnly": "npm test",
+    "postinstall": "node bin/agentram-postinstall.js"
+  },
+  "files": [
+    "agentram/*.py",
+    "bin/*.js",
+    ".claude/agents/*.md",
+    ".claude/commands/*.md",
+    "agentram_mcp_server.py",
+    "agentram_daemon.py",
+    "codex_ram.py",
+    "pyproject.toml",
+    "README.md",
+    "LICENSE"
+  ],
+  "engines": {
+    "node": ">=16"
+  },
+  "publishConfig": {
+    "access": "public"
+  }
+}

package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agentram"
-version = "0.1.13"
+version = "0.1.15"
 description = "Async, model-agnostic RAM layer for agentic coding tools."
 readme = "README.md"
 license = "MIT"