[Remove] Drop the decision-model review pre-screen and diff risk hints

apps/api/src/handlers/tasks/index.ts

@@ -19,7 +19,6 @@ import { manageSourceControl } from './manageSourceControl';
 import { updateTaskModelSelection } from './updateModelSelection';
 import { listTaskModels } from './listModels';
 import { saveTaskMemory } from './saveTaskMemory';
-import { getDiffRiskHints } from './getDiffRiskHints';
 import { recordAutomationResult } from './recordAutomationResult';
 import { updatePersonalization } from './updatePersonalization';
 
@@ -44,5 +43,4 @@ tasksRouter.post('/:taskId/task_suggestions', submitTaskSuggestions);
 tasksRouter.post('/:taskId/automation_result', recordAutomationResult);
 tasksRouter.post('/:taskId/mcp_recommendations', submitMcpRecommendations);
 tasksRouter.post('/runs/:runId/memory', saveTaskMemory);
-tasksRouter.post('/runs/:runId/diff_risk_hints', getDiffRiskHints);
 tasksRouter.post('/runs/:runId/personalization', updatePersonalization);

apps/docs/models.mdx

@@ -356,9 +356,6 @@ When a judgment model is on, Roomote asks it first for:
 - choosing the forum tag when Roomote opens a thread in a Discord forum channel
 - whether a settled session or task turn holds something worth saving to
   [Memory](/memory) that the agent did not record itself
-- an advisory ranking of a task's own changed hunks by defect risk during its
-  self-review, before it pushes or opens a pull request (the same pre-screen
-  pull request reviews use), so the agent can re-read the riskiest hunks
 
 Roomote acts on the judgment model only when it is confident. When it is
 unsure, unavailable, or returns an error, Roomote keeps the behavior it has