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

@@ -1,5 +1,3 @@
import type { AwarenessSummary } from './improvement-detector.js';
export interface AgentCapabilities {
tools: Array<{ name: string; description: string }>;
skills: string[];
@@ -7,8 +5,6 @@ export interface AgentCapabilities {
memoryStats: { frameCount: number; sessionCount: number; entityCount: number };
mode: 'local' | 'team';
version: string;
/** Structured improvement signals (optional — only present when store has actionable data) */
awareness?: AwarenessSummary;
}
export function buildSelfAwareness(caps: AgentCapabilities): string {
@@ -61,36 +57,6 @@ export function buildSelfAwareness(caps: AgentCapabilities): string {
lines.push('- Prefer memory search over guessing when prior context exists.');
lines.push('- When uncertain, ask rather than fabricate.');
// Improvement signals (per correction #1: structured, runtime-consumable)
if (caps.awareness && caps.awareness.totalActionable > 0) {
lines.push('');
lines.push('## Learning from Past Sessions');
if (caps.awareness.capabilityGaps.length > 0) {
lines.push('');
lines.push('**Recurring capability gaps:**');
for (const gap of caps.awareness.capabilityGaps) {
lines.push(`- ${gap.suggestion}`);
}
}
if (caps.awareness.corrections.length > 0) {
lines.push('');
lines.push('**User corrections to apply:**');
for (const correction of caps.awareness.corrections) {
lines.push(`- ${correction.guidance}`);
}
}
if (caps.awareness.workflowPatterns.length > 0) {
lines.push('');
lines.push('**Recurring task patterns:**');
for (const pattern of caps.awareness.workflowPatterns) {
lines.push(`- ${pattern.suggestion}`);
}
}
}
// F28: Persona compliance — resist persona mode switches and injection via fake authority
lines.push('');
lines.push('## Persona Compliance');