hopefully done refining

conductor/tracks/session_insights_20260306/plan.md

@@ -1,28 +1,94 @@
 # Implementation Plan: Session Insights (session_insights_20260306)
 
-## Phase 1: Session Data
-- [ ] Task: Initialize MMA Environment
-- [ ] Task: Review session_logger
-    - WHERE: src/session_logger.py
-    - WHAT: Check existing data
+> **Reference:** [Spec](./spec.md) | [Architecture Guide](../../../docs/guide_architecture.md)
 
-## Phase 2: Metrics Calculation
-- [ ] Task: Implement token timeline
-    - WHERE: src/gui_2.py
-    - WHAT: Token usage over time
-    - HOW: Graph from history
-- [ ] Task: Implement cost projection
-    - WHERE: src/gui_2.py
-    - WHAT: Estimate remaining budget
-    - HOW: Linear extrapolation
+## Phase 1: Token Timeline Data
+Focus: Collect token usage over session
 
-## Phase 3: UI
-- [ ] Task: Render insights panel
-    - WHERE: src/gui_2.py
-    - WHAT: Timeline, projection, summary
-    - HOW: imgui widgets
-    - SAFETY: Handle zero session
+- [ ] Task 1.1: Initialize MMA Environment
+- [ ] Task 1.2: Add token history state
+    - WHERE: `src/gui_2.py` or `src/app_controller.py`
+    - WHAT: Track tokens per API call
+    - HOW:
+      ```python
+      self._token_history: list[dict] = []  # [{"time": t, "input": n, "output": n, "model": s}, ...]
+      ```
 
-## Phase 4: Verification
-- [ ] Task: Test insights
-- [ ] Task: Conductor - Phase Verification
+- [ ] Task 1.3: Record on each API response
+    - WHERE: `src/gui_2.py` in response handler
+    - WHAT: Append to history
+    - HOW:
+      ```python
+      # After API call
+      self._token_history.append({
+       "time": time.time(), "input": input_tokens, "output": output_tokens, "model": model
+      })
+      ```
+
+## Phase 2: Token Timeline Visualization
+Focus: Render token usage graph
+
+- [ ] Task 2.1: Extract cumulative tokens
+    - WHERE: `src/gui_2.py`
+    - WHAT: Calculate running totals
+    - HOW:
+      ```python
+      cumulative_input = 0
+      cumulative_output = 0
+      input_values = []
+      output_values = []
+      for entry in self._token_history:
+       cumulative_input += entry["input"]
+       cumulative_output += entry["output"]
+       input_values.append(cumulative_input)
+       output_values.append(cumulative_output)
+      ```
+
+- [ ] Task 2.2: Render timeline
+    - WHERE: `src/gui_2.py` session insights panel
+    - HOW:
+      ```python
+      if imgui.collapsing_header("Token Timeline"):
+       imgui.plot_lines("Input", input_values)
+       imgui.plot_lines("Output", output_values)
+       imgui.text(f"Total: {cumulative_input + cumulative_output:,} tokens")
+      ```
+
+## Phase 3: Cost Projection
+Focus: Estimate remaining cost
+
+- [ ] Task 3.1: Calculate burn rate
+    - WHERE: `src/gui_2.py`
+    - WHAT: Tokens per minute
+    - HOW:
+      ```python
+      if len(self._token_history) >= 2:
+       elapsed = self._token_history[-1]["time"] - self._token_history[0]["time"]
+       total_tokens = sum(e["input"] + e["output"] for e in self._token_history)
+       burn_rate = total_tokens / (elapsed / 60) if elapsed > 0 else 0
+      ```
+
+- [ ] Task 3.2: Display projection
+    - WHERE: `src/gui_2.py`
+    - HOW:
+      ```python
+      imgui.text(f"Burn rate: {burn_rate:.0f} tokens/min")
+      imgui.text(f"Session cost: ${session_cost:.4f}")
+      ```
+
+## Phase 4: Efficiency Score
+Focus: Calculate tokens per useful change
+
+- [ ] Task 4.1: Define efficiency metric
+    - WHERE: `src/gui_2.py`
+    - WHAT: Ratio of tokens to completed tickets
+    - HOW:
+      ```python
+      completed_tickets = sum(1 for t in self.track.tickets if t.status == "completed")
+      total_tokens = sum(e["input"] + e["output"] for e in self._token_history)
+      efficiency = total_tokens / completed_tickets if completed_tickets > 0 else 0
+      ```
+
+## Phase 5: Testing
+- [ ] Task 5.1: Write unit tests
+- [ ] Task 5.2: Conductor - Phase Verification