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:
shumeiko.it
2026-10-20 00:54:58 +02:00
parent b734c1d3d2
commit 2e1999a3f6
112 changed files with 336 additions and 16165 deletions

View File

@@ -20,7 +20,6 @@ const testState = vi.hoisted(() => {
process.env.WAGGLE_PROMPT_ASSEMBLER = '1';
return {
previousPromptAssembler,
optimizerExpand: vi.fn(),
runAgentLoop: vi.fn(),
};
});
@@ -41,12 +40,6 @@ vi.mock('../../src/local/model-availability.js', async (importOriginal) => {
};
});
vi.mock('../../src/local/services/optimizer-service.js', () => ({
getOptimizerService: async () => ({
expandWithChoices: testState.optimizerExpand,
}),
}));
function parseSse(raw: string): Array<{ event: string; data: Record<string, unknown> }> {
return raw.split(/\n\n/)
.filter(Boolean)
@@ -151,12 +144,6 @@ describe('persona acceptance prompt budget', () => {
beforeEach(() => {
resetRateLimiter(server);
testState.optimizerExpand.mockReset().mockResolvedValue({
expanded: null,
clarifyingQuestions: null,
intent: 'request',
isVague: false,
});
});
afterAll(async () => {
@@ -657,7 +644,6 @@ describe('persona acceptance prompt budget', () => {
expect(response.body).toContain(toolResultMarker);
expect(response.body).toContain(responseMarker);
expect(capturedConfig?.traceRecording).toBeUndefined();
expect(testState.optimizerExpand).not.toHaveBeenCalled();
const traceProjection = JSON.stringify(server.traceStore.queryParsed({ sessionId: session }));
const auditProjection = JSON.stringify(getAuditDb(tmpDir).prepare(
@@ -740,7 +726,6 @@ describe('persona acceptance prompt budget', () => {
expect(response.statusCode).toBe(200);
expect(capturedConfig?.traceRecording).toBeUndefined();
expect(testState.optimizerExpand).not.toHaveBeenCalled();
const traceProjection = JSON.stringify(server.traceStore.queryParsed({ sessionId: session }));
const auditProjection = JSON.stringify(getAuditDb(tmpDir).prepare(