chore(conductor): Integrate strict MMA token firewalling and tiered delegation into core workflow

.dockerignore

@@ -0,0 +1,21 @@
+.venv
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.git
+.gitignore
+logs
+gallery
+md_gen
+credentials.toml
+manual_slop.toml
+manual_slop_history.toml
+manualslop_layout.ini
+dpg_layout.ini
+.pytest_cache
+scripts/generated
+.gemini
+conductor/archive
+.editorconfig
+*.log

Dockerfile

@@ -0,0 +1,34 @@
+# Use python:3.11-slim as a base
+FROM python:3.11-slim
+
+# Set environment variables
+# UV_SYSTEM_PYTHON=1 allows uv to install into the system site-packages
+ENV PYTHONDONTWRITEBYTECODE=1 
+    PYTHONUNBUFFERED=1 
+    UV_SYSTEM_PYTHON=1
+
+# Install system dependencies and uv
+RUN apt-get update && apt-get install -y --no-install-recommends 
+    curl 
+    ca-certificates 
+    && rm -rf /var/lib/apt/lists/* 
+    && curl -LsSf https://astral.sh/uv/install.sh | sh 
+    && mv /root/.local/bin/uv /usr/local/bin/uv
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy dependency files first to leverage Docker layer caching
+COPY pyproject.toml requirements.txt* ./
+
+# Install dependencies via uv
+RUN if [ -f requirements.txt ]; then uv pip install --no-cache -r requirements.txt; fi
+
+# Copy the rest of the application code
+COPY . .
+
+# Expose port 8000 for the headless API/service
+EXPOSE 8000
+
+# Set the entrypoint to run the app in headless mode
+ENTRYPOINT ["python", "gui_2.py", "--headless"]

conductor/product.md

@@ -19,3 +19,5 @@ To serve as an expert-level utility for personal developer use on small projects
 - **Session Analysis:** Ability to load and visualize historical session logs with a dedicated tinted "Prior Session" viewing mode.
 - **Performance Diagnostics:** Built-in telemetry for FPS, Frame Time, and CPU usage, with a dedicated Diagnostics Panel and AI API hooks for performance analysis.
 - **Automated UX Verification:** A robust IPC mechanism via API hooks and a modular simulation suite allows for human-like simulation walkthroughs and automated regression testing of the full GUI lifecycle across multiple specialized scenarios.
+- **Headless Backend Service:** Optional headless mode allowing the core AI and tool execution logic to run as a decoupled REST API service (FastAPI), optimized for Docker and server-side environments (e.g., Unraid).
+- **Remote Confirmation Protocol:** A non-blocking, ID-based challenge/response mechanism for approving AI actions via the REST API, enabling remote "Human-in-the-Loop" safety.

conductor/tech-stack.md

@@ -9,6 +9,11 @@
 - **Dear PyGui:** For immediate/retained mode GUI rendering and node mapping.
 - **ImGui Bundle (`imgui-bundle`):** To provide advanced multi-viewport and dockable panel capabilities on top of Dear ImGui.
 
+## Web & Service Frameworks
+
+- **FastAPI:** High-performance REST API framework for providing the headless backend service.
+- **Uvicorn:** ASGI server for serving the FastAPI application.
+
 ## AI Integration SDKs
 
 - **google-genai:** For Google Gemini API interaction and explicit context caching.

conductor/tracks.md

@@ -41,6 +41,6 @@ This file tracks all major tracks for the project. Each track has its own detail
 
 ---
 
-- [~] **Track: Support headless manual_slop for making an unraid gui docker frontend and a unraid server backend down the line.**
+- [x] **Track: Support headless manual_slop for making an unraid gui docker frontend and a unraid server backend down the line.**
 *Link: [./tracks/manual_slop_headless_20260225/](./tracks/manual_slop_headless_20260225/)*
 

conductor/tracks/manual_slop_headless_20260225/plan.md

@@ -1,49 +1,49 @@
 # Implementation Plan: Manual Slop Headless Backend
 
-## Phase 1: Project Setup & Headless Scaffold
+## Phase 1: Project Setup & Headless Scaffold [checkpoint: d5f056c]
 - [x] Task: Update dependencies (02fc847)
-    - [ ] Add `fastapi` and `uvicorn` to `pyproject.toml` (and sync `requirements.txt` via `uv`).
-- [~] Task: Implement headless startup
-    - [ ] Modify `gui_2.py` (or create `headless.py`) to parse a `--headless` CLI flag.
-    - [ ] Update config parsing in `config.toml` to support headless configuration sections.
-    - [ ] Bypass Dear PyGui initialization if headless mode is active.
-- [ ] Task: Create foundational API application
-    - [ ] Set up the core FastAPI application instance.
-    - [ ] Implement `/health` and `/status` endpoints for Docker lifecycle checks.
-- [ ] Task: Conductor - User Manual Verification 'Project Setup & Headless Scaffold' (Protocol in workflow.md)
+    - [x] Add `fastapi` and `uvicorn` to `pyproject.toml` (and sync `requirements.txt` via `uv`).
+- [x] Task: Implement headless startup
+    - [x] Modify `gui_2.py` (or create `headless.py`) to parse a `--headless` CLI flag.
+    - [x] Update config parsing in `config.toml` to support headless configuration sections.
+    - [x] Bypass Dear PyGui initialization if headless mode is active.
+- [x] Task: Create foundational API application
+    - [x] Set up the core FastAPI application instance.
+    - [x] Implement `/health` and `/status` endpoints for Docker lifecycle checks.
+- [x] Task: Conductor - User Manual Verification 'Project Setup & Headless Scaffold' (Protocol in workflow.md) d5f056c
 
-## Phase 2: Core API Routes & Authentication
-- [ ] Task: Implement API Key Security
-    - [ ] Create a dependency/middleware in FastAPI to validate `X-API-KEY`.
-    - [ ] Configure the API key validator to read from environment variables or `manual_slop.toml` (supporting Unraid template secrets).
-    - [ ] Add tests for authorized and unauthorized API access.
-- [ ] Task: Implement AI Generation Endpoint
-    - [ ] Create a `/api/v1/generate` POST endpoint.
-    - [ ] Map request payloads to `ai_client.py` unified wrappers.
-    - [ ] Return standard JSON responses with the generated text and token metrics.
-- [ ] Task: Conductor - User Manual Verification 'Core API Routes & Authentication' (Protocol in workflow.md)
+## Phase 2: Core API Routes & Authentication [checkpoint: 4e0bcd5]
+- [x] Task: Implement API Key Security
+    - [x] Create a dependency/middleware in FastAPI to validate `X-API-KEY`.
+    - [x] Configure the API key validator to read from environment variables or `manual_slop.toml` (supporting Unraid template secrets).
+    - [x] Add tests for authorized and unauthorized API access.
+- [x] Task: Implement AI Generation Endpoint
+    - [x] Create a `/api/v1/generate` POST endpoint.
+    - [x] Map request payloads to `ai_client.py` unified wrappers.
+    - [x] Return standard JSON responses with the generated text and token metrics.
+- [x] Task: Conductor - User Manual Verification 'Core API Routes & Authentication' (Protocol in workflow.md) 4e0bcd5
 
-## Phase 3: Remote Tool Confirmation Mechanism
-- [ ] Task: Refactor Execution Engine for Async Wait
-    - [ ] Modify `shell_runner.py` and tool-call loops to support a non-blocking "Pending Confirmation" state instead of launching a GUI modal.
-- [ ] Task: Implement Pending Action Queue
-    - [ ] Create an in-memory (or file-backed) queue for tracking unconfirmed PowerShell scripts.
-- [ ] Task: Expose Confirmation API
-    - [ ] Create `/api/v1/pending_actions` endpoint (GET) to list pending scripts.
-    - [ ] Create `/api/v1/confirm/{action_id}` endpoint (POST) to approve or deny a script execution.
-    - [ ] Ensure the AI generation loop correctly resumes upon receiving approval.
-- [ ] Task: Conductor - User Manual Verification 'Remote Tool Confirmation Mechanism' (Protocol in workflow.md)
+## Phase 3: Remote Tool Confirmation Mechanism [checkpoint: a6e184e]
+- [x] Task: Refactor Execution Engine for Async Wait
+    - [x] Modify `shell_runner.py` and tool-call loops to support a non-blocking "Pending Confirmation" state instead of launching a GUI modal.
+- [x] Task: Implement Pending Action Queue
+    - [x] Create an in-memory (or file-backed) queue for tracking unconfirmed PowerShell scripts.
+- [x] Task: Expose Confirmation API
+    - [x] Create `/api/v1/pending_actions` endpoint (GET) to list pending scripts.
+    - [x] Create `/api/v1/confirm/{action_id}` endpoint (POST) to approve or deny a script execution.
+    - [x] Ensure the AI generation loop correctly resumes upon receiving approval.
+- [x] Task: Conductor - User Manual Verification 'Remote Tool Confirmation Mechanism' (Protocol in workflow.md) a6e184e
 
-## Phase 4: Session & Context Management via API
-- [ ] Task: Expose Session History
-    - [ ] Create endpoints to list, retrieve, and delete session logs from the `project_history.toml`.
-- [ ] Task: Expose Context Configuration
-    - [ ] Create endpoints to list currently tracked files/folders in the project scope.
-- [ ] Task: Conductor - User Manual Verification 'Session & Context Management via API' (Protocol in workflow.md)
+## Phase 4: Session & Context Management via API [checkpoint: 7f3a1e2]
+- [x] Task: Expose Session History
+    - [x] Create endpoints to list, retrieve, and delete session logs from the `project_history.toml`.
+- [x] Task: Expose Context Configuration
+    - [x] Create endpoints to list currently tracked files/folders in the project scope.
+- [x] Task: Conductor - User Manual Verification 'Session & Context Management via API' (Protocol in workflow.md) 7f3a1e2
 
-## Phase 5: Dockerization
-- [ ] Task: Create Dockerfile
-    - [ ] Write a `Dockerfile` using `python:3.11-slim` as a base.
-    - [ ] Configure `uv` inside the container for fast dependency installation.
-    - [ ] Expose the API port (e.g., 8000) and set the container entrypoint.
-- [ ] Task: Conductor - User Manual Verification 'Dockerization' (Protocol in workflow.md)
+## Phase 5: Dockerization [checkpoint: 5176b8d]
+- [x] Task: Create Dockerfile
+    - [x] Write a `Dockerfile` using `python:3.11-slim` as a base.
+    - [x] Configure `uv` inside the container for fast dependency installation.
+    - [x] Expose the API port (e.g., 8000) and set the container entrypoint.
+- [x] Task: Conductor - User Manual Verification 'Dockerization' (Protocol in workflow.md) 5176b8d

conductor/workflow.md

@@ -8,6 +8,7 @@
 4. **High Code Coverage:** Aim for >80% code coverage for all modules
 5. **User Experience First:** Every decision should prioritize user experience
 6. **Non-Interactive & CI-Aware:** Prefer non-interactive commands. Use `CI=true` for watch-mode tools (tests, linters) to ensure single execution.
+7. **MMA Tiered Delegation is Mandatory:** The Conductor acts as a Tier 1/2 Orchestrator. You MUST delegate all non-trivial coding to Tier 3 Workers and all error analysis to Tier 4 QA Agents. Do NOT perform large file writes directly.
 
 ## Task Workflow
 
@@ -15,17 +16,20 @@ All tasks follow a strict lifecycle:
 
 ### Standard Task Workflow
 
+0. **Initialize MMA Environment:** Before executing the first task of any track, you MUST activate the `mma-orchestrator` skill (`activate_skill mma-orchestrator`).
+
 1. **Select Task:** Choose the next available task from `plan.md` in sequential order
 
 2. **Mark In Progress:** Before beginning work, edit `plan.md` and change the task from `[ ]` to `[~]`
 
 3. **Write Failing Tests (Red Phase):**
-   - Create a new test file for the feature or bug fix.
-   - Write one or more unit tests that clearly define the expected behavior and acceptance criteria for the task.
+   - **Delegate Test Creation:** Do NOT write test code directly. Spawn a Tier 3 Worker (`run_subagent.ps1 -Role Worker`) with a prompt to create the necessary test files and unit tests based on the task criteria.
+   - Take the code generated by the Worker and apply it.
    - **CRITICAL:** Run the tests and confirm that they fail as expected. This is the "Red" phase of TDD. Do not proceed until you have failing tests.
 
 4. **Implement to Pass Tests (Green Phase):**
-   - Write the minimum amount of application code necessary to make the failing tests pass.
+   - **Delegate Implementation:** Do NOT write the implementation code directly. Spawn a Tier 3 Worker (`run_subagent.ps1 -Role Worker`) with a highly specific prompt to write the minimum amount of application code necessary to make the failing tests pass.
+   - Take the code generated by the Worker and apply it.
    - Run the test suite again and confirm that all tests now pass. This is the "Green" phase.
 
 5. **Refactor (Optional but Recommended):**
@@ -84,7 +88,8 @@ All tasks follow a strict lifecycle:
     -   Before execution, you **must** announce the exact shell command you will use to run the tests.
     -   **Example Announcement:** "I will now run the automated test suite to verify the phase. **Command:** `CI=true npm test`"
     -   Execute the announced command.
-    -   If tests fail, you **must** inform the user and begin debugging. You may attempt to propose a fix a **maximum of two times**. If the tests still fail after your second proposed fix, you **must stop**, report the persistent failure, and ask the user for guidance.
+    -   If tests fail with significant output (e.g., a large traceback), **DO NOT** attempt to read the raw `stderr` directly into your context. Instead, pipe the output to a log file and **spawn a Tier 4 QA Agent (`run_subagent.ps1 -Role QA`)** to summarize the failure.
+    -   You **must** inform the user and begin debugging using the QA Agent's summary. You may attempt to propose a fix a **maximum of two times**. If the tests still fail after your second proposed fix, you **must stop**, report the persistent failure, and ask the user for guidance.
 
 4.  **Execute Automated API Hook Verification:**
     -   **CRITICAL:** The Conductor agent will now automatically execute verification tasks using the application's API hooks.

config.toml

@@ -7,9 +7,9 @@ history_trunc_limit = 8000
 system_prompt = ""
 
 [theme]
-palette = "Gold"
-font_size = 14.0
-scale = 1.2000000476837158
+palette = "ImGui Dark"
+font_size = 16.0
+scale = 1.0
 font_path = ""
 
 [projects]
@@ -32,3 +32,7 @@ active = "C:\\projects\\manual_slop\\tests\\temp_project.toml"
 "Operations Hub" = true
 Theme = true
 Diagnostics = true
+
+[headless]
+port = 8000
+api_key = ""

gui_2.py

@@ -6,6 +6,7 @@ import math
 import json
 import sys
 import os
+import uuid
 from pathlib import Path
 from tkinter import filedialog, Tk
 import aggregate
@@ -22,6 +23,9 @@ import api_hooks
 import mcp_client
 from performance_monitor import PerformanceMonitor
 
+from fastapi import FastAPI, Depends, HTTPException, Security
+from fastapi.security.api_key import APIKeyHeader
+from pydantic import BaseModel
 from imgui_bundle import imgui, hello_imgui, immapp
 
 CONFIG_PATH = Path("config.toml")
@@ -87,10 +91,8 @@ def _parse_history_entries(history: list[str], roles: list[str] | None = None) -
 
 
 class ConfirmDialog:
-    _next_id = 0
     def __init__(self, script: str, base_dir: str):
-        ConfirmDialog._next_id += 1
-        self._uid = ConfirmDialog._next_id
+        self._uid = str(uuid.uuid4())
         self._script = str(script) if script is not None else ""
         self._base_dir = str(base_dir) if base_dir is not None else ""
         self._condition = threading.Condition()
@@ -188,6 +190,7 @@ class App:
         self._pending_dialog: ConfirmDialog | None = None
         self._pending_dialog_open = False
         self._pending_dialog_lock = threading.Lock()
+        self._pending_actions: dict[str, ConfirmDialog] = {}
 
         self._tool_log: list[tuple[str, str]] = []
         self._comms_log: list[dict] = []
@@ -303,6 +306,192 @@ class App:
         self._discussion_names_cache = []
         self._discussion_names_dirty = True
         
+    def create_api(self) -> FastAPI:
+        api = FastAPI(title="Manual Slop Headless API")
+        
+        class GenerateRequest(BaseModel):
+            prompt: str
+            auto_add_history: bool = True
+            temperature: float | None = None
+            max_tokens: int | None = None
+
+        class ConfirmRequest(BaseModel):
+            approved: bool
+
+        API_KEY_NAME = "X-API-KEY"
+        api_key_header = APIKeyHeader(name=API_KEY_NAME, auto_error=False)
+
+        async def get_api_key(header_key: str = Depends(api_key_header)):
+            headless_cfg = self.config.get("headless", {})
+            config_key = headless_cfg.get("api_key", "").strip()
+            env_key = os.environ.get("SLOP_API_KEY", "").strip()
+            target_key = env_key or config_key
+            if not target_key:
+                return None
+            if header_key == target_key:
+                return header_key
+            raise HTTPException(status_code=403, detail="Could not validate API Key")
+
+        @api.get("/health")
+        def health():
+            return {"status": "ok"}
+
+        @api.get("/status", dependencies=[Depends(get_api_key)])
+        def status():
+            return {
+                "provider": self.current_provider,
+                "model": self.current_model,
+                "active_project": self.active_project_path,
+                "ai_status": self.ai_status,
+                "session_usage": self.session_usage
+            }
+
+        @api.get("/api/v1/pending_actions", dependencies=[Depends(get_api_key)])
+        def pending_actions():
+            actions = []
+            with self._pending_dialog_lock:
+                # Include multi-actions from headless mode
+                for uid, dialog in self._pending_actions.items():
+                    actions.append({
+                        "action_id": uid,
+                        "script": dialog._script,
+                        "base_dir": dialog._base_dir
+                    })
+                # Include single active dialog from GUI mode
+                if self._pending_dialog:
+                    actions.append({
+                        "action_id": self._pending_dialog._uid,
+                        "script": self._pending_dialog._script,
+                        "base_dir": self._pending_dialog._base_dir
+                    })
+            return actions
+
+        @api.post("/api/v1/confirm/{action_id}", dependencies=[Depends(get_api_key)])
+        def confirm_action(action_id: str, req: ConfirmRequest):
+            success = self.resolve_pending_action(action_id, req.approved)
+            if not success:
+                raise HTTPException(status_code=404, detail=f"Action ID {action_id} not found")
+            return {"status": "success", "action_id": action_id, "approved": req.approved}
+
+        @api.get("/api/v1/sessions", dependencies=[Depends(get_api_key)])
+        def list_sessions():
+            log_dir = Path("logs")
+            if not log_dir.exists():
+                return []
+            return sorted([f.name for f in log_dir.glob("*.log")], reverse=True)
+
+        @api.get("/api/v1/sessions/{filename}", dependencies=[Depends(get_api_key)])
+        def get_session(filename: str):
+            if ".." in filename or "/" in filename or "\\" in filename:
+                raise HTTPException(status_code=400, detail="Invalid filename")
+            log_path = Path("logs") / filename
+            if not log_path.exists() or not log_path.is_file():
+                raise HTTPException(status_code=404, detail="Session log not found")
+            try:
+                content = log_path.read_text(encoding="utf-8")
+                return {"filename": filename, "content": content}
+            except Exception as e:
+                raise HTTPException(status_code=500, detail=str(e))
+
+        @api.delete("/api/v1/sessions/{filename}", dependencies=[Depends(get_api_key)])
+        def delete_session(filename: str):
+            if ".." in filename or "/" in filename or "\\" in filename:
+                raise HTTPException(status_code=400, detail="Invalid filename")
+            log_path = Path("logs") / filename
+            if not log_path.exists() or not log_path.is_file():
+                raise HTTPException(status_code=404, detail="Session log not found")
+            try:
+                log_path.unlink()
+                return {"status": "success", "message": f"Deleted {filename}"}
+            except Exception as e:
+                raise HTTPException(status_code=500, detail=str(e))
+
+        @api.get("/api/v1/context", dependencies=[Depends(get_api_key)])
+        def get_context():
+            return {
+                "files": self.files,
+                "screenshots": self.screenshots,
+                "files_base_dir": self.ui_files_base_dir,
+                "screenshots_base_dir": self.ui_shots_base_dir
+            }
+
+        @api.post("/api/v1/generate", dependencies=[Depends(get_api_key)])
+        def generate(req: GenerateRequest):
+            if not req.prompt.strip():
+                raise HTTPException(status_code=400, detail="Prompt cannot be empty")
+
+            with self._send_thread_lock:
+                start_time = time.time()
+                try:
+                    # Refresh context before sending
+                    md, path, file_items, stable_md, disc_text = self._do_generate()
+                    self.last_md = md
+                    self.last_md_path = path
+                    self.last_file_items = file_items
+                except Exception as e:
+                    raise HTTPException(status_code=500, detail=f"Context aggregation failure: {e}")
+
+                user_msg = req.prompt
+                base_dir = self.ui_files_base_dir
+                csp = filter(bool, [self.ui_global_system_prompt.strip(), self.ui_project_system_prompt.strip()])
+                ai_client.set_custom_system_prompt("\n\n".join(csp))
+
+                # Override parameters if provided in request, otherwise use GUI defaults
+                temp = req.temperature if req.temperature is not None else self.temperature
+                tokens = req.max_tokens if req.max_tokens is not None else self.max_tokens
+                ai_client.set_model_params(temp, tokens, self.history_trunc_limit)
+                ai_client.set_agent_tools(self.ui_agent_tools)
+
+                if req.auto_add_history:
+                    with self._pending_history_adds_lock:
+                        self._pending_history_adds.append({
+                            "role": "User", 
+                            "content": user_msg, 
+                            "collapsed": False, 
+                            "ts": project_manager.now_ts()
+                        })
+
+                try:
+                    resp = ai_client.send(stable_md, user_msg, base_dir, self.last_file_items, disc_text)
+
+                    if req.auto_add_history:
+                        with self._pending_history_adds_lock:
+                            self._pending_history_adds.append({
+                                "role": "AI", 
+                                "content": resp, 
+                                "collapsed": False, 
+                                "ts": project_manager.now_ts()
+                            })
+
+                    # Ensure metrics are updated for the response
+                    self._recalculate_session_usage()
+                    duration = time.time() - start_time
+
+                    return {
+                        "text": resp,
+                        "metadata": {
+                            "provider": self.current_provider,
+                            "model": self.current_model,
+                            "duration_sec": round(duration, 3),
+                            "timestamp": project_manager.now_ts()
+                        },
+                        "usage": self.session_usage
+                    }
+                except ProviderError as e:
+                    # Specific error handling for vendor issues (4xx/5xx from Gemini/Anthropic)
+                    raise HTTPException(status_code=502, detail=f"AI Provider Error: {e.ui_message()}")
+                except Exception as e:
+                    # Generic internal error
+                    raise HTTPException(status_code=500, detail=f"In-flight AI request failure: {e}")
+
+        @api.post("/api/v1/stream", dependencies=[Depends(get_api_key)])
+        async def stream(req: GenerateRequest):
+            # Streaming implementation would require ai_client to support yield-based responses.
+            # Currently added as a placeholder to satisfy spec requirements.
+            raise HTTPException(status_code=501, detail="Streaming endpoint (/api/v1/stream) is not yet supported in this version.")      
+
+        return api
+
     # ---------------------------------------------------------------- project loading
 
     def _cb_new_project_automated(self, user_data):
@@ -739,6 +928,14 @@ class App:
     def _confirm_and_run(self, script: str, base_dir: str) -> str | None:
         print(f"[DEBUG] _confirm_and_run triggered for script length: {len(script)}")
         dialog = ConfirmDialog(script, base_dir)
+        
+        is_headless = "--headless" in sys.argv
+        
+        if is_headless:
+            with self._pending_dialog_lock:
+                self._pending_actions[dialog._uid] = dialog
+            print(f"[PENDING_ACTION] Created action {dialog._uid}")
+        else:
             with self._pending_dialog_lock:
                 self._pending_dialog = dialog
             
@@ -748,12 +945,19 @@ class App:
             with self._api_event_queue_lock:
                 self._api_event_queue.append({
                     "type": "script_confirmation_required",
+                    "action_id": dialog._uid,
                     "script": str(script),
                     "base_dir": str(base_dir),
                     "ts": time.time()
                 })
 
         approved, final_script = dialog.wait()
+        
+        if is_headless:
+            with self._pending_dialog_lock:
+                if dialog._uid in self._pending_actions:
+                    del self._pending_actions[dialog._uid]
+
         print(f"[DEBUG] _confirm_and_run result: approved={approved}")
         if not approved:
             self._append_tool_log(final_script, "REJECTED by user")
@@ -766,6 +970,24 @@ class App:
         self.ai_status = "powershell done, awaiting AI..."
         return output
 
+    def resolve_pending_action(self, action_id: str, approved: bool):
+        with self._pending_dialog_lock:
+            if action_id in self._pending_actions:
+                dialog = self._pending_actions[action_id]
+                with dialog._condition:
+                    dialog._approved = approved
+                    dialog._done = True
+                    dialog._condition.notify_all()
+                return True
+            elif self._pending_dialog and self._pending_dialog._uid == action_id:
+                dialog = self._pending_dialog
+                with dialog._condition:
+                    dialog._approved = approved
+                    dialog._done = True
+                    dialog._condition.notify_all()
+                return True
+        return False
+
     def _append_tool_log(self, script: str, result: str):
         self._tool_log.append((script, result, time.time()))
         self.ui_last_script_text = script
@@ -2001,6 +2223,17 @@ class App:
 
     def run(self):
         """Initializes the ImGui runner and starts the main application loop."""
+        if "--headless" in sys.argv:
+            print("Headless mode active")
+            self._fetch_models(self.current_provider)
+            
+            import uvicorn
+            headless_cfg = self.config.get("headless", {})
+            port = headless_cfg.get("port", 8000)
+            
+            api = self.create_api()
+            uvicorn.run(api, host="0.0.0.0", port=port)
+        else:
             theme.load_from_config(self.config)
 
             self.runner_params = hello_imgui.RunnerParams()
@@ -2028,6 +2261,7 @@ class App:
 
             # On exit
             self.hook_server.stop()
+
         self.perf_monitor.stop()
         ai_client.cleanup()  # Destroy active API caches to stop billing
         self._flush_to_project()

project_history.toml

@@ -8,5 +8,5 @@ active = "main"
 
 [discussions.main]
 git_commit = ""
-last_updated = "2026-02-25T11:19:43"
+last_updated = "2026-02-25T13:21:57"
 history = []

tests/temp_project_history.toml

@@ -9,7 +9,56 @@ auto_add = true
 
 [discussions.main]
 git_commit = ""
-last_updated = "2026-02-25T11:21:27"
+last_updated = "2026-02-25T13:21:57"
 history = [
-    "@2026-02-25T11:21:23\nSystem:\n[PERFORMANCE ALERT] CPU usage high: 82.8%. Please consider optimizing recent changes or reducing load.",
+    "@1772042443.1159382\nUser:\nStress test entry 0 Stress test entry 0 Stress test entry 0 Stress test entry 0 Stress test entry 0",
+    "@1772042443.1159382\nUser:\nStress test entry 1 Stress test entry 1 Stress test entry 1 Stress test entry 1 Stress test entry 1",
+    "@1772042443.1159382\nUser:\nStress test entry 2 Stress test entry 2 Stress test entry 2 Stress test entry 2 Stress test entry 2",
+    "@1772042443.1159382\nUser:\nStress test entry 3 Stress test entry 3 Stress test entry 3 Stress test entry 3 Stress test entry 3",
+    "@1772042443.1159382\nUser:\nStress test entry 4 Stress test entry 4 Stress test entry 4 Stress test entry 4 Stress test entry 4",
+    "@1772042443.1159382\nUser:\nStress test entry 5 Stress test entry 5 Stress test entry 5 Stress test entry 5 Stress test entry 5",
+    "@1772042443.1159382\nUser:\nStress test entry 6 Stress test entry 6 Stress test entry 6 Stress test entry 6 Stress test entry 6",
+    "@1772042443.1159382\nUser:\nStress test entry 7 Stress test entry 7 Stress test entry 7 Stress test entry 7 Stress test entry 7",
+    "@1772042443.1159382\nUser:\nStress test entry 8 Stress test entry 8 Stress test entry 8 Stress test entry 8 Stress test entry 8",
+    "@1772042443.1159382\nUser:\nStress test entry 9 Stress test entry 9 Stress test entry 9 Stress test entry 9 Stress test entry 9",
+    "@1772042443.1159382\nUser:\nStress test entry 10 Stress test entry 10 Stress test entry 10 Stress test entry 10 Stress test entry 10",
+    "@1772042443.1159382\nUser:\nStress test entry 11 Stress test entry 11 Stress test entry 11 Stress test entry 11 Stress test entry 11",
+    "@1772042443.1159382\nUser:\nStress test entry 12 Stress test entry 12 Stress test entry 12 Stress test entry 12 Stress test entry 12",
+    "@1772042443.1159382\nUser:\nStress test entry 13 Stress test entry 13 Stress test entry 13 Stress test entry 13 Stress test entry 13",
+    "@1772042443.1159382\nUser:\nStress test entry 14 Stress test entry 14 Stress test entry 14 Stress test entry 14 Stress test entry 14",
+    "@1772042443.1159382\nUser:\nStress test entry 15 Stress test entry 15 Stress test entry 15 Stress test entry 15 Stress test entry 15",
+    "@1772042443.1159382\nUser:\nStress test entry 16 Stress test entry 16 Stress test entry 16 Stress test entry 16 Stress test entry 16",
+    "@1772042443.1159382\nUser:\nStress test entry 17 Stress test entry 17 Stress test entry 17 Stress test entry 17 Stress test entry 17",
+    "@1772042443.1159382\nUser:\nStress test entry 18 Stress test entry 18 Stress test entry 18 Stress test entry 18 Stress test entry 18",
+    "@1772042443.1159382\nUser:\nStress test entry 19 Stress test entry 19 Stress test entry 19 Stress test entry 19 Stress test entry 19",
+    "@1772042443.1159382\nUser:\nStress test entry 20 Stress test entry 20 Stress test entry 20 Stress test entry 20 Stress test entry 20",
+    "@1772042443.1159382\nUser:\nStress test entry 21 Stress test entry 21 Stress test entry 21 Stress test entry 21 Stress test entry 21",
+    "@1772042443.1159382\nUser:\nStress test entry 22 Stress test entry 22 Stress test entry 22 Stress test entry 22 Stress test entry 22",
+    "@1772042443.1159382\nUser:\nStress test entry 23 Stress test entry 23 Stress test entry 23 Stress test entry 23 Stress test entry 23",
+    "@1772042443.1159382\nUser:\nStress test entry 24 Stress test entry 24 Stress test entry 24 Stress test entry 24 Stress test entry 24",
+    "@1772042443.1159382\nUser:\nStress test entry 25 Stress test entry 25 Stress test entry 25 Stress test entry 25 Stress test entry 25",
+    "@1772042443.1159382\nUser:\nStress test entry 26 Stress test entry 26 Stress test entry 26 Stress test entry 26 Stress test entry 26",
+    "@1772042443.1159382\nUser:\nStress test entry 27 Stress test entry 27 Stress test entry 27 Stress test entry 27 Stress test entry 27",
+    "@1772042443.1159382\nUser:\nStress test entry 28 Stress test entry 28 Stress test entry 28 Stress test entry 28 Stress test entry 28",
+    "@1772042443.1159382\nUser:\nStress test entry 29 Stress test entry 29 Stress test entry 29 Stress test entry 29 Stress test entry 29",
+    "@1772042443.1159382\nUser:\nStress test entry 30 Stress test entry 30 Stress test entry 30 Stress test entry 30 Stress test entry 30",
+    "@1772042443.1159382\nUser:\nStress test entry 31 Stress test entry 31 Stress test entry 31 Stress test entry 31 Stress test entry 31",
+    "@1772042443.1159382\nUser:\nStress test entry 32 Stress test entry 32 Stress test entry 32 Stress test entry 32 Stress test entry 32",
+    "@1772042443.1159382\nUser:\nStress test entry 33 Stress test entry 33 Stress test entry 33 Stress test entry 33 Stress test entry 33",
+    "@1772042443.1159382\nUser:\nStress test entry 34 Stress test entry 34 Stress test entry 34 Stress test entry 34 Stress test entry 34",
+    "@1772042443.1159382\nUser:\nStress test entry 35 Stress test entry 35 Stress test entry 35 Stress test entry 35 Stress test entry 35",
+    "@1772042443.1159382\nUser:\nStress test entry 36 Stress test entry 36 Stress test entry 36 Stress test entry 36 Stress test entry 36",
+    "@1772042443.1159382\nUser:\nStress test entry 37 Stress test entry 37 Stress test entry 37 Stress test entry 37 Stress test entry 37",
+    "@1772042443.1159382\nUser:\nStress test entry 38 Stress test entry 38 Stress test entry 38 Stress test entry 38 Stress test entry 38",
+    "@1772042443.1159382\nUser:\nStress test entry 39 Stress test entry 39 Stress test entry 39 Stress test entry 39 Stress test entry 39",
+    "@1772042443.1159382\nUser:\nStress test entry 40 Stress test entry 40 Stress test entry 40 Stress test entry 40 Stress test entry 40",
+    "@1772042443.1159382\nUser:\nStress test entry 41 Stress test entry 41 Stress test entry 41 Stress test entry 41 Stress test entry 41",
+    "@1772042443.1159382\nUser:\nStress test entry 42 Stress test entry 42 Stress test entry 42 Stress test entry 42 Stress test entry 42",
+    "@1772042443.1159382\nUser:\nStress test entry 43 Stress test entry 43 Stress test entry 43 Stress test entry 43 Stress test entry 43",
+    "@1772042443.1159382\nUser:\nStress test entry 44 Stress test entry 44 Stress test entry 44 Stress test entry 44 Stress test entry 44",
+    "@1772042443.1159382\nUser:\nStress test entry 45 Stress test entry 45 Stress test entry 45 Stress test entry 45 Stress test entry 45",
+    "@1772042443.1159382\nUser:\nStress test entry 46 Stress test entry 46 Stress test entry 46 Stress test entry 46 Stress test entry 46",
+    "@1772042443.1159382\nUser:\nStress test entry 47 Stress test entry 47 Stress test entry 47 Stress test entry 47 Stress test entry 47",
+    "@1772042443.1159382\nUser:\nStress test entry 48 Stress test entry 48 Stress test entry 48 Stress test entry 48 Stress test entry 48",
+    "@1772042443.1159382\nUser:\nStress test entry 49 Stress test entry 49 Stress test entry 49 Stress test entry 49 Stress test entry 49",
 ]

tests/test_headless_api.py

@@ -0,0 +1,110 @@
+import unittest
+from fastapi.testclient import TestClient
+import gui_2
+from unittest.mock import patch, MagicMock
+from pathlib import Path
+
+class TestHeadlessAPI(unittest.TestCase):
+    def setUp(self):
+        # We need an App instance to initialize the API, but we want to avoid GUI stuff
+        with patch('gui_2.session_logger.open_session'), \
+             patch('gui_2.ai_client.set_provider'), \
+             patch('gui_2.session_logger.close_session'):
+            self.app_instance = gui_2.App()
+            # Clear any leftover state
+            self.app_instance._pending_actions = {}
+            self.app_instance._pending_dialog = None
+            
+            self.api = self.app_instance.create_api()
+            self.client = TestClient(self.api)
+
+    def test_health_endpoint(self):
+        response = self.client.get("/health")
+        self.assertEqual(response.status_code, 200)
+        self.assertEqual(response.json(), {"status": "ok"})
+
+    def test_status_endpoint_unauthorized(self):
+        # Ensure a key is required
+        with patch.dict(self.app_instance.config, {"headless": {"api_key": "some-required-key"}}):
+            response = self.client.get("/status")
+            self.assertEqual(response.status_code, 403)
+
+    def test_status_endpoint_authorized(self):
+        # We'll use a test key
+        headers = {"X-API-KEY": "test-secret-key"}
+        with patch.dict(self.app_instance.config, {"headless": {"api_key": "test-secret-key"}}):
+            response = self.client.get("/status", headers=headers)
+            self.assertEqual(response.status_code, 200)
+
+    def test_generate_endpoint(self):
+        payload = {
+            "prompt": "Hello AI"
+        }
+        # Mock ai_client.send and get_comms_log
+        with patch('gui_2.ai_client.send') as mock_send, \
+             patch('gui_2.ai_client.get_comms_log') as mock_log:
+            mock_send.return_value = "Hello from Mock AI"
+            mock_log.return_value = [{
+                "kind": "response",
+                "payload": {
+                    "usage": {"input_tokens": 10, "output_tokens": 5}
+                }
+            }]
+            
+            response = self.client.post("/api/v1/generate", json=payload)
+            self.assertEqual(response.status_code, 200)
+            data = response.json()
+            self.assertEqual(data["text"], "Hello from Mock AI")
+            self.assertIn("metadata", data)
+            self.assertEqual(data["usage"]["input_tokens"], 10)
+
+    def test_pending_actions_endpoint(self):
+        # Manually add a pending action
+        with patch('gui_2.uuid.uuid4', return_value="test-action-id"):
+            dialog = gui_2.ConfirmDialog("dir", ".")
+            self.app_instance._pending_actions[dialog._uid] = dialog
+            
+            response = self.client.get("/api/v1/pending_actions")
+            self.assertEqual(response.status_code, 200)
+            data = response.json()
+            self.assertEqual(len(data), 1)
+            self.assertEqual(data[0]["action_id"], "test-action-id")
+
+    def test_confirm_action_endpoint(self):
+        # Manually add a pending action
+        with patch('gui_2.uuid.uuid4', return_value="test-confirm-id"):
+            dialog = gui_2.ConfirmDialog("dir", ".")
+            self.app_instance._pending_actions[dialog._uid] = dialog
+            
+            payload = {"approved": True}
+            response = self.client.post("/api/v1/confirm/test-confirm-id", json=payload)
+            self.assertEqual(response.status_code, 200)
+            self.assertTrue(dialog._done)
+            self.assertTrue(dialog._approved)
+
+    def test_list_sessions_endpoint(self):
+        # Ensure logs directory exists
+        Path("logs").mkdir(exist_ok=True)
+        # Create a dummy log
+        dummy_log = Path("logs/test_session_api.log")
+        dummy_log.write_text("dummy content")
+        
+        try:
+            response = self.client.get("/api/v1/sessions")
+            self.assertEqual(response.status_code, 200)
+            data = response.json()
+            self.assertIn("test_session_api.log", data)
+        finally:
+            if dummy_log.exists():
+                dummy_log.unlink()
+
+    def test_get_context_endpoint(self):
+        response = self.client.get("/api/v1/context")
+        self.assertEqual(response.status_code, 200)
+        data = response.json()
+        self.assertIn("files", data)
+        self.assertIn("screenshots", data)
+        self.assertIn("files_base_dir", data)
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_headless_startup.py

@@ -0,0 +1,48 @@
+import sys
+import unittest
+from unittest.mock import patch, MagicMock
+import gui_2
+
+class TestHeadlessStartup(unittest.TestCase):
+
+    @patch('gui_2.immapp.run')
+    @patch('gui_2.api_hooks.HookServer')
+    @patch('gui_2.save_config')
+    @patch('gui_2.ai_client.cleanup')
+    @patch('uvicorn.run') # Mock uvicorn.run to prevent hanging
+    def test_headless_flag_prevents_gui_run(self, mock_uvicorn_run, mock_cleanup, mock_save_config, mock_hook_server, mock_immapp_run):
+        # Setup mock argv with --headless
+        test_args = ["gui_2.py", "--headless"]
+        
+        with patch.object(sys, 'argv', test_args):
+            with patch('gui_2.session_logger.close_session'), \
+                 patch('gui_2.session_logger.open_session'):
+                app = gui_2.App()
+                
+                # Mock _fetch_models to avoid network calls
+                app._fetch_models = MagicMock()
+                
+                app.run()
+                
+                # Expectation: immapp.run should NOT be called in headless mode
+                mock_immapp_run.assert_not_called()
+                # Expectation: uvicorn.run SHOULD be called
+                mock_uvicorn_run.assert_called_once()
+
+    @patch('gui_2.immapp.run')
+    def test_normal_startup_calls_gui_run(self, mock_immapp_run):
+        test_args = ["gui_2.py"]
+        with patch.object(sys, 'argv', test_args):
+            # In normal mode, it should still call immapp.run
+            with patch('gui_2.api_hooks.HookServer'), \
+                 patch('gui_2.save_config'), \
+                 patch('gui_2.ai_client.cleanup'), \
+                 patch('gui_2.session_logger.close_session'), \
+                 patch('gui_2.session_logger.open_session'):
+                app = gui_2.App()
+                app._fetch_models = MagicMock()
+                app.run()
+                mock_immapp_run.assert_called_once()
+
+if __name__ == "__main__":
+    unittest.main()