feat: Propagate task summaries and input context to execution agents

Execution agents were spawning blind — no input files, no knowledge of
what predecessor tasks accomplished. This adds three capabilities:

1. summary column on tasks table — completeTask() reads the finishing
   agent's result.message and stores it on the task record
2. dispatchNext() gathers full initiative context (initiative, phase,
   sibling tasks, pages) and passes it as inputContext so agents get
   .cw/input/task.md, initiative.md, phase.md, and context directories
3. context/tasks/*.md files now include the summary field in frontmatter
   so dependent agents can see what prior agents accomplished

docs/database.md

@@ -51,6 +51,7 @@ All adapters use nanoid() for IDs, auto-manage timestamps, and use Drizzle's `.r
 | status | text enum | 'pending_approval' \| 'pending' \| 'in_progress' \| 'completed' \| 'blocked' |
 | requiresApproval | integer/boolean nullable | null = inherit from initiative |
 | order | integer | default 0 |
+| summary | text nullable | Agent result summary — propagated to dependent tasks as context |
 | createdAt, updatedAt | integer/timestamp | |
 
 ### task_dependencies
@@ -191,4 +192,4 @@ Key rules:
 - See [database-migrations.md](database-migrations.md) for full workflow
 - Snapshots stale after 0008; migrations 0008+ are hand-written
 
-Current migrations: 0000 through 0024 (25 total).
+Current migrations: 0000 through 0026 (27 total).