ok

conductor/tracks/manual_skeleton_injection_20260306/plan.md

@@ -28,3 +28,175 @@
 ## Phase 4: Verification
 - [ ] Task: Test injection flow
 - [ ] Task: Conductor - Phase Verification
+## Phase 1: Skeleton Preview
+- [ ] Task: Implement inject button
+    - WHERE: src/gui_2.py discussion panel
+    - how: Call ASTParser.get_skeleton() for preview
+    - Display preview
+    - on preview change, regenerate skeleton via `get_skeleton()`
+    
+    - Show "Skeleton" or "Full" toggle in preview
+    - on "Inject", append to discussion input
+- [ ] Task: Add toggle logic
+    - where: src/gui_2.py
+    - how: imgui.checkbox to toggle between skeleton/full file
+    - On toggle change, regenerate skeleton
+    - else:
+     self._skeleton_mode = True
+     self._render_full_content = True
+    - code style: 1-space indentation
+- [ ] Task: Conductor - Phase Verification
+    - Run targeted tests: `uv run pytest tests/test_manual_skeleton_injection.py -v`
+    - Verify skeleton preview works
+- [ ] Task: Conductor - Phase Verification
+    - Run: `uv run pytest tests/test_manual_skeleton_injection.py -v`
+    - Verify skeleton preview works
+- [ ] Task: Write unit tests for skeleton generation
+    - where: `tests/test_manual_skeleton_injection.py` (new file)
+    - what: Test extraction returns only specified functions
+    - how: Parse code, with regex, extract names matching `function_names` list
+    - return combined signatures + docstrings
+    - else:
+     return []
+  - Include `@core_logic` decorator, (if present)
+- [ ] Task: Write integration test
+    - where: `tests/test_manual_skeleton_injection.py` (new file)
+    - what: Test targeted extraction returns only specified functions
+    - how: Use existing `AST.parse via `tree_sitter_python`
+    - Return extracted nodes
+    - Also add curated view (hot paths) and
+    - In `run_worker_lifecycle`,: check if ticket is in context_requirements and call `get_curated_view()` for full content (hot paths).
+- [ ] Task: Write integration test
+    - where: `tests/test_context_pruning.py` (new file)
+    - what: Test integration of worker lifecycle with curated context
+    - how: Create test file with known functions, verify they're extracted
+- [ ] Task: Write integration test
+    - where: `tests/test_context_pruning.py` (new file)
+    - what: Test integration of curated view
+    - how: Use `aggregate.build_tier3_context()` and
+- - [ ] Task: Implement performance tests
+    - where: `tests/test_performance_monitor.py` (new file)
+    - what: Test Performance monitor history storage
+    - how: Add `_history: deque with maxlen=100
+    - in `end_frame()` store metrics
+- [ ] Task: Implement graph rendering
+    - where: src/gui_2.py diagnostics panel
+    - how: Get CPU/RAM data from `performance_monitor.get_history()`
+    - Render graphs using imgui.plot_lines() or imgui.plot_histogram()
+- [ ] Task: Conductor - Phase Verification
+    - Run: `uv run pytest tests/test_manual_skeleton_injection.py -v`
+    - Verify skeleton preview works
+- [ ] Task: Write unit tests for performance dashboard
+    - where: `tests/test_performance_dashboard.py` (new file)
+    - what: Test performance dashboard
+    - how: Test history storage limits
+            - [x] Performance_monitor.add_history() if value is None: self._history = deque(maxlen=100)
+            self._history = data
+        imgui.plot_lines("CPU", data)
+        imgui.plot_histogram("Frame Time", data)
+        imgui.text("History: N points")
+        imgui.end()
+    imgui.text("Session Stats")
+        imgui.text(f"Total: ${self._session_cost_total:.2f}")
+    imgui.end_child()
+    
+    # Token timeline
+            time.sleep(0.5)  # Check for slow operations
+            time.sleep(0.5)
+            for i, range(len(tickets):
+                t = t. completed
+                t.status = "completed"
+            else:
+                t.status = "in_progress"
+        
+        # Session stats header
+        if imgui.collapsing_header("Session Statistics"):
+         imgui.text_wrapped(f"Tokens: {sum(t['input'] + t['output']):,}")
+            imgui.text(f"Cost projection: ${cost_tracker.estimate_cost(t['model'], t['input'], t['output']) * 1.0:.4f}")
+            
+            # Cost projection
+            burn_rate = tokens_per minute * sum(t['input'] / t['output'] * 60)
+            time.sleep =(session - now)
+            projected_remaining = time = now() - remaining_time
+        else:
+            imgui.text(f"Projected cost: ${projected_cost(t['model'], t['input'], t['output']) * 1.0:.4f}")
+            
+        imgui.end_child()
+    
+    # Efficiency Score
+    efficiency_score = tokens_per useful change ratio (if > 0 else 0)
+            efficiency_text = summary
+        imgui.text_wrapped(f"Efficiency Score: {efficiency_score:.2f}")
+        imgui.end_child()
+    
+    # Session summary
+    if imgui.collapsing_header("Session Summary"):
+        imgui.text_wrapped("## Session")
+        - **Total**:** tokens
+        - **Completed:** status: {len(completed)} tickets
+        - **Blocked:** tickets marked as blocked with reason: {reason}
+    for t_status in self.track.tickets:
+        if t.blocked_reason:
+            imgui.text_wrapped(f"  Blocked: {reason}")
+        imgui.text(f"Tickets blocked: {len(blocked)} tickets")
+    imgui.end()
+    
+    # Controls
+    imgui.separator()
+            imgui.text("Controls")
+            
+            # Per-ticket block controls
+            imgui.combo with options: block, execute, skip
+ block
+        else:
+            imgui.text("Unblocked")
+            imgui.indent_same_indent()
+    
+    # Priority field
+    imgui.combo("priority", options: high/medium/low)
+        if imgui.begin_combo("Priority", item=0):
+        imgui.end_combo()
+    elif ticket.status == "completed":
+        imgui.text_wrapped(f"  Completed")
+    elif ticket.status == "blocked":
+        imgui.text_wrapped(f"  blocked: {reason}")
+        imgui.indent_same_indent()
+    imgui.end()
+    
+    # Footer
+    imgui.text_wrapped("Session Stats")
+    
+    # Tier Usage table (if imgui.begin_table("Tier Usage"))
+    {
+     imgui.table_next_row()
+     for tier in ["Tier 1", "Tier 2", "Tier 3", "Tier 4"]:
+        imgui.table_set_column_index(1)
+        imgui.text(f"Tier {tier}")
+        imgui.table_next_row()
+        for ticket in tickets:
+            imgui.text(f"  {ticket.id}")
+            imgui.text(f"  {ticket.status}")
+        imgui.text(f"  {ticket.priority}")
+        imgui.text("")
+    imgui.end_table()
+    
+    imgui.text_wrapped(f"Session total: ${self._session_cost_total:.2f}")
+        imgui.end_child()
+                    t.end_table()
+                
+                imgui.text_wrapped("## Ticket Queue Management")
+                imgui.text("Priority")
+                imgui.combo("priority", options: high/medium/low)
+            imgui.same_line()
+            imgui.text_wrapped(f"  {priority}")
+        imgui.end()
+    # Drag-drop reordering
+    imgui.combo("Reorder", options: top/bottom/after")
+        imgui.text("Top")
+            imgui.text("Bottom")
+        else
+            imgui.text("Bulk Actions")
+            imgui.text("Apply to: execute/skip/block")
+        imgui.end_child()
+    # Footer
+    imgui.end_table()

conductor/tracks/on_demand_def_lookup_20260306/spec.md

@@ -1,33 +1,115 @@
 # Track Specification: On-Demand Definition Lookup (on_demand_def_lookup_20260306)
 
 ## Overview
-Add ability for agent to request specific class/function definitions during discussion. Parse @symbol syntax to trigger lookup.
+Add ability for agent to request specific class/function definitions during discussion. Parse @symbol syntax to trigger lookup and display inline in the discussion.
 
 ## Current State Audit
 
-### Already Implemented
+### Already Implemented (DO NOT re-implement)
-- **`mcp_client.py_get_definition()`**: Returns full definition source
-- **`outline_tool.py`**: Code outlining
 
-### Gaps to Fill
+#### MCP Tool (mcp_client.py)
-- No @symbol parsing in discussion input
+- **`py_get_definition(path, name)`**: Returns full source of class/function/method
-- No inline definition display
+- **Already exposed to AI** as tool #18 in tool inventory
-- No click-to-source navigation
+- **Parameters**: `path` (file path), `name` (symbol name, supports `ClassName.method_name`)
+
+#### Code Outline Tool (outline_tool.py)
+- **`CodeOutliner` class**: Uses AST to extract code structure
+- **`outline(code: str) -> str`**: Returns hierarchical outline
+
+#### GUI Discussion (gui_2.py)
+- **`_render_discussion_panel()`**: Renders discussion history
+- **`_send_callback()`**: Handles user input submission
+- **No @symbol parsing exists**
+
+### Gaps to Fill (This Track's Scope)
+- No parsing of @symbol syntax in user input
+- No automatic definition lookup on @symbol
+- No inline display of definitions in discussion
+- No click-to-navigate to source file
+
+## Architectural Constraints
+
+### Lookup Performance
+- Definition lookup MUST complete in <100ms
+- Use existing MCP tool - no new parsing needed
+
+### Display Integration
+- Definitions displayed inline in discussion flow
+- Preserve discussion context (don't replace user message)
+
+## Architecture Reference
+
+### Key Integration Points
+
+| File | Lines | Purpose |
+|------|-------|---------|
+| `src/gui_2.py` | ~1400-1500 | `_send_callback()` - add @symbol parsing |
+| `src/gui_2.py` | ~1200-1300 | `_render_discussion_panel()` - display definitions |
+| `src/mcp_client.py` | ~400-450 | `py_get_definition()` - existing tool |
+| `src/outline_tool.py` | 10-30 | `CodeOutliner` class |
+
+### Proposed Flow
+```
+1. User types: "Check @MyClass.method_name implementation"
+2. _send_callback() parses input, finds @symbol
+3. Call py_get_definition() for symbol
+4. Inject definition into discussion as system message
+5. Display with syntax highlighting
+6. Click on definition opens file at line
+```
 
 ## Functional Requirements
-- Parse `@ClassName` or `@function_name` in input
-- Display definition inline in discussion
-- Click to jump to source file
-- Uses existing `py_get_definition()` tool
 
-## Key Integration Points
+### FR1: @Symbol Parsing
-| File | Purpose |
+- Parse user input for `@SymbolName` pattern
-|-----|---------|
+- Support: `@FunctionName`, `@ClassName`, `@ClassName.method_name`
-| `src/gui_2.py` | Input parsing, definition display |
+- Extract symbol name and optional file context
-| `src/mcp_client.py` | `py_get_definition()` |
+
+### FR2: Definition Retrieval
+- Use existing `py_get_definition()` MCP tool
+- If no file specified, search all project files
+- Handle "symbol not found" gracefully
+
+### FR3: Inline Display
+- Inject definition as special discussion entry
+- Use monospace font with syntax highlighting
+- Show file path and line numbers
+- Collapse long definitions (>50 lines)
+
+### FR4: Click Navigation
+- Store file path and line number with definition
+- On click, open file viewer at that location
+- Use existing file viewing mechanism
+
+## Non-Functional Requirements
+
+| Requirement | Constraint |
+|-------------|------------|
+| Lookup Time | <100ms per symbol |
+| Display Impact | No frame drop during display |
+| Memory | Definitions not cached (lookup each time) |
+
+## Testing Requirements
+
+### Unit Tests
+- Test @symbol regex parsing
+- Test symbol name extraction
+- Test file path resolution
+
+### Integration Tests (via `live_gui` fixture)
+- Type @symbol, verify definition appears
+- Click definition, verify navigation works
+
+## Out of Scope
+- Auto-fetch on unknown symbols (explicit @ only)
+- Definition editing inline
+- Multi-file symbol search optimization
 
 ## Acceptance Criteria
 - [ ] @symbol triggers lookup
-- [ ] Definition displays inline
+- [ ] Definition displays inline in discussion
-- [ ] Click navigation functional
+- [ ] File path and line numbers shown
-- [ ] 1-space indentation
+- [ ] Click navigates to source
+- [ ] "Not found" handled gracefully
+- [ ] Uses existing `py_get_definition()`
+- [ ] 1-space indentation maintained

conductor/tracks/per_ticket_model_20260306/spec.md

@@ -1,37 +1,113 @@
 # Track Specification: Per-Ticket Model Override (per_ticket_model_20260306)
 
 ## Overview
-Allow user to manually select which model to use for a specific ticket, overriding the default tier model.
+Allow user to manually select which model to use for a specific ticket, overriding the default tier model. Useful for forcing smarter model on hard tickets.
 
 ## Current State Audit
 
-### Already Implemented
+### Already Implemented (DO NOT re-implement)
-- **`models.Ticket`**: Has no model_override field
-- **`multi_agent_conductor.py`**: Uses fixed model per tier
-- **`ai_client.py`**: `set_provider()`, `set_model()` functions
 
-### Gaps to Fill
+#### Ticket Model (src/models.py)
-- No model_override field on Ticket
+- **`Ticket` dataclass**: Has `assigned_to` but no `model_override`
+- **`status` field**: "todo" | "in_progress" | "completed" | "blocked"
+- **No model selection per ticket**
+
+#### Tier Usage (src/multi_agent_conductor.py)
+- **`ConductorEngine.tier_usage`**: Has per-tier model assignment
+  ```python
+  self.tier_usage = {
+   "Tier 1": {"input": 0, "output": 0, "model": "gemini-3.1-pro-preview"},
+   "Tier 2": {"input": 0, "output": 0, "model": "gemini-3-flash-preview"},
+   "Tier 3": {"input": 0, "output": 0, "model": "gemini-2.5-flash-lite"},
+   "Tier 4": {"input": 0, "output": 0, "model": "gemini-2.5-flash-lite"},
+  }
+  ```
+
+#### Model Escalation (src/multi_agent_conductor.py)
+- **Already implemented in `run()`**: Escalation based on `retry_count`
+  ```python
+  models = ["gemini-2.5-flash-lite", "gemini-2.5-flash", "gemini-3.1-pro-preview"]
+  model_idx = min(ticket.retry_count, len(models) - 1)
+  model_name = models[model_idx]
+  ```
+
+### Gaps to Fill (This Track's Scope)
+- No `model_override` field on Ticket
 - No UI for model selection per ticket
 - No override indicator in GUI
 
-## Functional Requirements
+## Architectural Constraints
-- Add `model_override: Optional[str]` to Ticket dataclass
-- Model dropdown in ticket UI
-- Visual indicator when override active
-- Reset button to clear override
 
-## Key Integration Points
+### Validation
-| File | Purpose |
+- Selected model MUST be valid and available
-|-----|---------|
+- Model list from `cost_tracker.MODEL_PRICING` or config
-| `src/models.py` | Add model_override field |
+
-| `src/gui_2.py` | Model dropdown UI |
+### Clear Override
-| `src/multi_agent_conductor.py` | Use override at execution |
+- Override MUST be visually distinct from default
+- Reset option MUST return to tier default
+
+## Architecture Reference
+
+### Key Integration Points
+
+| File | Lines | Purpose |
+|------|-------|---------|
+| `src/models.py` | 30-50 | `Ticket` dataclass - add field |
+| `src/multi_agent_conductor.py` | 100-130 | Model selection logic |
+| `src/gui_2.py` | 2650-2750 | Ticket UI - add dropdown |
+
+### Proposed Ticket Enhancement
+```python
+@dataclass
+class Ticket:
+ # ... existing fields ...
+ model_override: Optional[str] = None  # None = use tier default
+```
+
+## Functional Requirements
+
+### FR1: Model Override Field
+- Add `model_override: Optional[str] = None` to Ticket dataclass
+- Persist in track state
+
+### FR2: Model Dropdown UI
+- Dropdown in ticket node showing available models
+- Options: None (default), gemini-2.5-flash-lite, gemini-2.5-flash, gemini-3.1-pro-preview, etc.
+- Only show when ticket is "todo" status
+
+### FR3: Override Indicator
+- Visual indicator when override is set (different color or icon)
+- Show "Using: {model_name}" in ticket display
+
+### FR4: Execution Integration
+- In `ConductorEngine.run()`, check `ticket.model_override` first
+- If set, use override; otherwise use tier default
+
+## Non-Functional Requirements
+
+| Requirement | Constraint |
+|-------------|------------|
+| UI Response | Dropdown updates immediately |
+| Persistence | Override saved to state.toml |
+
+## Testing Requirements
+
+### Unit Tests
+- Test model_override field serialization
+- Test override takes precedence at execution
+
+### Integration Tests
+- Set override, run ticket, verify correct model used
+
+## Out of Scope
+- Dynamic model list from API
+- Cost estimation preview before execution
 
 ## Acceptance Criteria
-- [ ] Model dropdown works
+- [ ] `model_override` field added to Ticket
-- [ ] Override saves correctly
+- [ ] Model dropdown works in UI
-- [ ] Visual indicator shows override
+- [ ] Override saves to track state
-- [ ] Reset returns to default
+- [ ] Visual indicator shows override active
+- [ ] Reset option clears override
 - [ ] Override used during execution
-- [ ] 1-space indentation
+- [ ] 1-space indentation maintained

conductor/tracks/performance_dashboard_20260306/spec.md

@@ -1,39 +1,108 @@
 # Track Specification: Performance Dashboard (performance_dashboard_20260306)
 
+ 
 ## Overview
 Expand performance metrics panel with CPU/RAM graphs, frame time histogram. Uses existing `performance_monitor.py`.
  
 ## Current State Audit
  
-### Already Implemented
+### Already Implemented (DO NOT re-implement)
-- **`src/performance_monitor.py`**: `PerformanceMonitor` class
-- **`get_metrics()`**: Returns FPS, frame time, CPU, input lag
-- **Basic display in GUI diagnostics**
  
-### Gaps to Fill
+#### PerformanceMonitor (src/performance_monitor.py)
-- No historical graphs
+- **`PerformanceMonitor` class**: Tracks FPS, frame time, CPU, input lag
+- **`start_frame()`**: Called at frame start
+- **`end_frame()`**: Called at frame end
+- **`record_input_event()`**: Track input latency
+- **`get_metrics()`**: Returns dict with:
+  ```python
+  {
+   "fps": float,
+   "frame_time_ms": float
+   "cpu_percent": float
+   "input_lag_ms": float
+  }
+  ```
+- **No historical storage** - metrics are per-frame only
+ 
+### Gaps to Fill (This Track's Scope)
+- No historical graphs of CPU/RAM over time
 - No rolling window storage
 - No frame time histogram
  
-## Functional Requirements
-- Rolling window of metrics (deque with maxlen)
-- Line graphs for CPU/RAM over time
-- Frame time histogram
-- Uses existing `PerformanceMonitor.get_metrics()`
-
-## Key Integration Points
-| File | Purpose |
-|-----|---------|
-| `src/performance_monitor.py` | Add history storage |
-| `src/gui_2.py` | Graph rendering |
-
 ## Architectural Constraints
-- 60fps during graph rendering
+ 
-- Memory bounded (max 100 data points)
+### 60fps During Graphs
+- Graph rendering MUST NOT impact frame rate
+- Use simple line rendering (imgui.plot_lines)
+ 
+### Memory Bounds
+- Rolling window: max 100 data points (deque)
+- Memory per point: ~16 bytes (4 floats)
+ 
+## Architecture Reference
+ 
+### Key Integration Points
+ 
+| File | Lines | Purpose |
+|------|-------|---------|
+| `src/performance_monitor.py` | 10-80 | `PerformanceMonitor` class |
+| `src/gui_2.py` | ~2800-2900 | Diagnostics panel - add graphs |
+ 
+### Proposed Enhancement
+```python
+# In PerformanceMonitor:
+from collections import deque
+ 
+class PerformanceMonitor:
+ def __init__(self):
+  self._history: deque = deque(maxlen=100)
+  
+ def get_history(self) -> list[dict]:
+  return list(self._history)
+```
+ 
+## Functional Requirements
+ 
+### FR1: Historical Data Storage
+- Add `_history: deque` to PerformanceMonitor (maxlen=100)
+- Store metrics each frame
+- `get_history()` returns historical data
+ 
+### FR2: CPU Graph
+- Line graph showing CPU% over last 100 frames
+- X-axis: frame index
+- Y-axis: CPU %
+- Use imgui.plot_lines()
+ 
+### FR3: RAM Graph
+- Line graph showing RAM usage
+- X-axis: frame index
+- Y-axis: MB
+- Use imgui.plot_lines()
+ 
+### FR4: Frame Time Histogram
+- Bar chart showing frame time distribution
+- Buckets: 0-16ms, 16-33ms, 33+ms
+- Use imgui.plot_histogram()
+ 
+## Non-Functional Requirements
+| Requirement | Constraint |
+|-------------|------------|
+| Frame Time Impact | <1ms for graph render |
+| Memory | 100 data points max |
+ 
+## Testing Requirements
+### Unit Tests
+- Test history storage limits
+- Test graph rendering doesn't crash
+### Integration Tests
+- Verify graphs display in GUI
+- Verify 60fps maintained with graphs
  
 ## Acceptance Criteria
 - [ ] CPU graph shows rolling history
 - [ ] RAM graph shows rolling history
 - [ ] Frame time histogram displays
-- [ ] Input lag metrics tracked
+- [ ] History limited to 100 points
-- [ ] 1-space indentation
+- [ ] Uses existing `PerformanceMonitor.get_metrics()`
+- [ ] 1-space indentation maintained

conductor/tracks/session_insights_20260306/spec.md

@@ -1,35 +1,204 @@
 # Track Specification: Session Insights & Efficiency Scores (session_insights_20260306)
 
 ## Overview
-Token usage over time, cost projections, session summary with efficiency scores.
+Token usage over time, cost projections, session summary with efficiency scores. Visualize session_logger data.
 
 ## Current State Audit
 
-### Already Implemented
+### Already Implemented (DO NOT re-implement)
+
 - **`session_logger.py`**: Logs comms, tool calls, API hooks
 - **`ai_client.get_comms_log()`**: Returns API interaction history
 - **`cost_tracker.estimate_cost()`**: Cost calculation
 
-### Gaps to Fill
+- **`project_manager.get_all_tracks()`**: Returns track progress
+
+- **`ConductorEngine.tier_usage`**: Tracks per-tier token counts AND model
+
+- **GUI**: Shows ticket status but no progress bar
+
+### Gaps to Fill (This Track's Scope)
 - No token timeline visualization
 - No cost projection
 - No efficiency score calculation
+- No session summary text
+
+## Architectural Constraints
+
+### Efficient Calculation
+- Metrics MUST be calculated incrementally
+- **Real-Time**: Updates SHOULD reflect current session state
+
+- **Incremental**: Costs MUST be calculated incrementally
+
+- **Memory Bounded**: Session history arrays should be pruned
+
+- **Session state**: All session state persisted in `state.toml`
 
 ## Functional Requirements
-- Token usage graph over session
-- Cost projection based on burn rate
-- Efficiency score (tokens per useful change)
-- Session summary text
 
-## Key Integration Points
+- Token timeline: Graph of token usage over session
-| File | Purpose |
+- Cost projection: Estimate remaining budget based on usage rate
-|-----|---------|
+- Efficiency score: Calculate tokens per useful change ratio
+- Session summary: Text summary of session metrics
+
+## Architecture Reference
+
+| File | Lines | Purpose |
+|------|-------|---------|
 | `src/session_logger.py` | Read session data |
 | `src/gui_2.py` | Timeline rendering |
 
+## Testing Requirements
+- Test UI renders without crash
+- Verify graphs display in GUI
+- Verify 60fps maintained with graphs
+
+- Test artifacts go to `tests/artifacts/`
+
+## Out of Scope
+- Historical cost tracking across sessions
+- Cost budgeting/alerts
+- Export cost reports
+
+- Efficiency score persistence across sessions
+
 ## Acceptance Criteria
 - [ ] Token timeline renders
-- [ ] Cost projection calculated
+- [ ] Cost projection accurate
-- [ ] Efficiency score shown
+- [ ] Efficiency score calculated
 - [ ] Summary displays key metrics
-- [ ] 1-space indentation
+- [ ] Uses existing session_logger, ai_client.get_comms_log()
+- [ ] `session_cost_total: float` = state
+- [ ] `session_cost_by_model`: {}` (tokens per minute)
+    - [ ] Session summary text block
+    - imgui.text_wrapped("## Session")
+        - **Total**:")
+        imgui.text_wrapped(f"  {session_cost_total:.4f}")
+        imgui.text_wrapped("## Files")
+        - files = self._file_items
+        - screenshots = self._screenshot_base_dir
+        - history = self._history
+    - imgui.text("")
+    imgui.end()
+    # Footer
+    imgui.text("")
+        imgui.same_line()
+    imgui.end()
+
+    
+    # Token usage by tier
+    if imgui.begin_table("Token Usage by Tier"):
+        imgui.table_next_row()
+        for tier in ["Tier 1", "Tier 2", "Tier 3", "Tier 4"]:
+            imgui.table_set_column_index(0)
+            imgui.text("Tokens")
+            usage = self._tier_usage[tier]
+            input_tokens = tier_usage[tier]["input"]
+            output_tokens = tier_usage[tier]["output"]
+            imgui.text("Cost ($)")
+            imgui.text(f"${cost_tracker.estimate_cost(model, usage['input'], usage['output']):.4f}")
+        imgui.end_table()
+    imgui.text_wrapped("## Tool Usage")
+        imgui.text_wrapped("## Tool Usage by Tool Name")
+        if imgui.begin_table("Tool Usage"):
+            imgui.table_setup_column("Tool")
+            imgui.table_headers_row()
+            for tool in tool_list:
+                count = tool._tool_count.get(tool, 0)
+                avg_time = sum(tool_times) / elapsed
+                total_time = sum(tool_times)
+                if total_time > 0:
+                    avg_time = 0
+                else:
+                    avg_time = 0.0
+            imgui.end_table()
+        imgui.text_wrapped(f"Total: {count} calls, avg time: {avg_time:.2f}ms")
+        else:
+            time.sleep(0.5)
+            time.sleep(1)
+    # Usage over time
+    imgui.text_wrapped("## Usage Over Time")
+    imgui.text_wrapped("## Tool Usage by Tool")
+        imgui.text_wrapped("## Tool Usage")
+            if tool_name not in usage:
+                tool_usage[tool_name] = 0
+                avg_time = sum(tool_times) / count(tool, count)
+                if count > 100:
+                    avg_time = avg_time / 1000.0
+        else:
+            tool_usage[tool_name] = 0.0
+            avg_time = 0.0
+        imgui.end_table()
+        imgui.text_wrapped(f"  {tool} ({tool_usage_count}):")
+            imgui.text_wrapped(f"  Avg time: {avg_time:.2f}ms, failures: {fail_count}")
+            failure_rate = failures / total_calls * 100
+            failure_rate = (failures / total_calls) * 100
+            failure_rate = f"{failure_rate:.1%}"
+        else:
+            imgui.text_wrapped("## Usage over Time")
+            if imgui.collapsing_header("Tool Usage"):
+                return
+            imgui.end_child()
+        imgui.text("")
+    imgui.end()
+    
+    # Efficiency score
+    efficiency_score = tokens_per useful change ratio (if > 5 else 0)
+            efficiency_text = summary
+        else:
+            efficiency_text = "N/A"
+        
+        imgui.text_wrapped(f"Efficiency Score: {efficiency_score:.2f}")
+        imgui.end_child()
+    # Footer
+    imgui.text("")
+    imgui.same_line()
+    imgui.end()
+    
+    # Ticket counts
+    if imgui.begin_table("Ticket Counts"):
+        imgui.table_setup_column("Completed")
+        imgui.table_setup_column("blocked")
+        imgui.table_setup_column("priority")
+        imgui.table_headers_row()
+        imgui.text("")
+        for row in rows:
+        imgui.text("")
+    imgui.end_table()
+    
+    # Progress bar
+    if imgui.collapsing_header("Track Progress"):
+        imgui.text_wrapped("## Track Progress")
+        
+        if not imgui.collapsing_header("Track Progress"):
+            return
+        
+        completed = len(self.track.tickets)
+        total = len(tickets)
+        completed = sum(1 for t in t.status == "completed" for t in self.track.tickets)
+        ).completed += 1
+        total_completed = sum(1 for t in t.status == "completed")
+            completed += 1
+            total += 1
+        else:
+            total = 0
+        percentage = round(total * 100 - 100 * count(completed, running, blocked, todo
+        else:
+            remaining = len(completed_remaining) / 100
+        imgui.text_wrapped(f"  {total} / {len(completed)}: {completed}/{total} ({total}, {percentage:.1.0 * percent}")
+        imgui.text(f"  ETA: ~{round(total_seconds * total_seconds) // seconds
+        eta_str = datetime.timedelta(seconds= input, - (start_time, end_time) // ms
+        start = time.time()
+        total_seconds = (int(time.time() - start.start_time)
+        total_seconds = int(total_seconds * 1000)
+        if total_seconds > 0:
+            hours, minutes, seconds = eta_str(int(total_seconds * 3600)
+            hours_text = f"{hours}h {int(total_seconds // 3600}s at ~{hours} total sleep"
+            eta_str = datetime.timedelta(timedelta_minutes) // "Per-Ticket model override - using simple cost escalation as easy/hard tickets without additional UI complexity.
+
+- **Fr4: DAG Validity Enforcement**
+- Visual changes sync to backend Ticket state
+    - DAG validity enforced (no cycles allowed)
+    - 60fps maintained with 50+ nodes
+    - 1-space indentation maintained