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

@@ -90,59 +90,4 @@ describe('Self-Awareness', () => {
expect(result).toContain('acquire_capability');
expect(result).toContain('uncertain');
});
it('includes improvement signals when awareness has actionable data', () => {
const caps: AgentCapabilities = {
tools: [],
skills: [],
model: 'test',
memoryStats: { frameCount: 10, sessionCount: 2, entityCount: 3 },
mode: 'local',
version: '1.0.0',
awareness: {
capabilityGaps: [{
id: 1,
toolName: 'pdf_reader',
occurrences: 3,
suggestion: 'User has needed "pdf_reader" 3 times. Consider using acquire_capability to find it.',
}],
corrections: [{
id: 2,
patternKey: 'tone:too_formal',
detail: 'Keep it casual',
occurrences: 4,
guidance: 'Keep it casual (corrected 4 times)',
}],
workflowPatterns: [],
totalActionable: 2,
},
};
const result = buildSelfAwareness(caps);
expect(result).toContain('Learning from Past Sessions');
expect(result).toContain('pdf_reader');
expect(result).toContain('Keep it casual');
expect(result).toContain('Recurring capability gaps');
expect(result).toContain('User corrections to apply');
});
it('omits improvement section when awareness has zero actionable signals', () => {
const caps: AgentCapabilities = {
tools: [],
skills: [],
model: 'test',
memoryStats: { frameCount: 10, sessionCount: 2, entityCount: 3 },
mode: 'local',
version: '1.0.0',
awareness: {
capabilityGaps: [],
corrections: [],
workflowPatterns: [],
totalActionable: 0,
},
};
const result = buildSelfAwareness(caps);
expect(result).not.toContain('Learning from Past Sessions');
});
});