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

@@ -8,8 +8,8 @@ import { buildLocalServer } from '../../src/local/index.js';
/**
* Integration test for the pre:memory-write lint handler registered in chat.ts.
* Fires the real hook through the server's shared HookRegistry and asserts that
* capability-failure symptoms are cancelled (and routed to the improvement-signal
* path) while normal memories and dramatic-but-legitimate claims pass through.
* capability-failure symptoms are cancelled while normal memories and
* dramatic-but-legitimate claims pass through.
*/
describe('pre:memory-write capability-symptom lint (handler integration)', () => {
let server: FastifyInstance;
@@ -30,10 +30,8 @@ describe('pre:memory-write capability-symptom lint (handler integration)', () =>
}
});
it('cancels a capability-failure symptom write and records an improvement signal', async () => {
const { hookRegistry, orchestrator } = server.agentState;
const store = orchestrator.getImprovementSignals();
const before = store.getByCategory('capability_gap').length;
it('cancels a capability-failure symptom write', async () => {
const { hookRegistry } = server.agentState;
const result = await hookRegistry.fire('pre:memory-write', {
toolName: 'save_memory',
@@ -43,9 +41,6 @@ describe('pre:memory-write capability-symptom lint (handler integration)', () =>
expect(result.cancelled).toBe(true);
expect(result.reason).toMatch(/capability/i);
expect(result.reason).toMatch(/acquire_capability/);
const after = store.getByCategory('capability_gap');
expect(after.length).toBe(before + 1);
});
it('allows a normal memory (tool preference) to pass', async () => {