feat(token-tracking): record AI token consumption per task (CUST-WP-0029)

Introduces end-to-end token consumption tracking so agent work is
visible as a cost/effort metric alongside tasks and workplans.

- Migration o2j3k4l5m6n7: token_events table with FK indexes on
  task_id, workstream_id, repo_id, created_at
- ORM model, Pydantic schemas (TokenEventCreate, TokenEventRead with
  computed tokens_total, TokenSummary)
- Router: POST /token-events/, GET /token-events/ (7 filters),
  GET /token-events/summary/ (task|workstream|repo|commit|release scope)
- MCP tools: record_token_event, get_token_summary (formatted table)
- update_task_status enriched with optional tokens_in/tokens_out
  passthrough — one call creates status update + token event
- Dashboard token-cost.md page: by-repo bar, by-workplan table,
  by-model bar, top-10 tasks by tokens
- ralph-workplan skill updated with token reporting guidance and
  per-task heuristics for estimating counts
- Tests: test_token_events.py + test_token_passthrough.py (182 pass)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

api/schemas/task.py

@@ -38,6 +38,12 @@ class TaskUpdate(BaseModel):
     needs_human: bool | None = None
     intervention_note: str | None = None
     parent_task_id: uuid.UUID | None = None
+    # Optional token passthrough — when provided, a token_event is created
+    tokens_in: int | None = None
+    tokens_out: int | None = None
+    model: str | None = None
+    agent: str | None = None
+    session_id: str | None = None
 
     @model_validator(mode="after")
     def blocking_reason_required_when_blocked(self) -> Self: