refactor: remove self-learning and the optimizer package (P1.4)
Self-learning is excluded from the community edition (ADR-0004); the project owner reworks it separately. Cost tracking stays. - agent: delete behaviour evolution (evolve-schema, iterative GEPA, compose-evolution, evolution gates, orchestrator and deploy), improvement and correction detection, AgentLearning, the eval-dataset builder, optimization-capture and the agent_insights tool. Secret detection moves from eval-dataset to secret-patterns. The LLM wiring keeps only the Haiku adapter and judge call used by skill audit and hygiene, so @ax-llm/ax is now declared by agent instead of server. - server: delete /api/evolution/*, the evolution and optimizer services, GEPA expansion of the first chat message, the prompt_optimization and monthly_assessment jobs, the idle-session reviewer and its session-reviewer persona, prompt injection of past corrections and thumbs-down recorded as correction signals. Existing job rows of the removed types are ignored, not deleted. - core: delete OptimizationLogStore; stop re-exporting the improvement signal and evolution run stores. - web: delete the Evolution screen and the two job types in the automation editor. - delete packages/optimizer. Also logs UF-027 (self-learning loops read data nothing collects) and UF-028 (the Settings prompt-shape choice is ignored by chat).
This commit is contained in:
@@ -16,9 +16,7 @@ export type CronJobType =
|
||||
| 'agent_task'
|
||||
| 'memory_consolidation'
|
||||
| 'workspace_health'
|
||||
| 'proactive'
|
||||
| 'prompt_optimization'
|
||||
| 'monthly_assessment';
|
||||
| 'proactive';
|
||||
|
||||
export interface CronSchedulePreset {
|
||||
id: string;
|
||||
@@ -66,16 +64,6 @@ export const CRON_JOB_TYPES: readonly CronJobTypeOption[] = [
|
||||
label: 'Proactive briefing',
|
||||
description: 'Generate a short "what changed" digest to nudge attention.',
|
||||
},
|
||||
{
|
||||
id: 'prompt_optimization',
|
||||
label: 'Optimise agent prompts',
|
||||
description: 'Run the evolution loop over recent traces; deploy any wins.',
|
||||
},
|
||||
{
|
||||
id: 'monthly_assessment',
|
||||
label: 'Monthly assessment',
|
||||
description: 'Longer-form review: memory growth, entity coverage, goal progress.',
|
||||
},
|
||||
] as const;
|
||||
|
||||
export const DEFAULT_CRON_PRESET_ID = 'daily-9am';
|
||||
|
||||
@@ -27,14 +27,6 @@ describe('getPersonaTier', () => {
|
||||
it('treats unknown ids (e.g. custom personas) as specialists', () => {
|
||||
expect(getPersonaTier('my-custom-persona')).toBe('specialist');
|
||||
});
|
||||
|
||||
it('does not surface the internal session-reviewer persona in either tier', () => {
|
||||
// session-reviewer is an internal self-evolution reviewer; it must never
|
||||
// appear in the PersonaSwitcher (universal modes OR the specialist roster).
|
||||
expect(UNIVERSAL_MODE_IDS).not.toContain('session-reviewer');
|
||||
expect(ALL_SPECIALIST_IDS).not.toContain('session-reviewer');
|
||||
expect(getSpecialistsForTemplate('blank').primary).not.toContain('session-reviewer');
|
||||
});
|
||||
});
|
||||
|
||||
describe('UNIVERSAL_MODE_IDS', () => {
|
||||
|
||||
Reference in New Issue
Block a user