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

@@ -11,7 +11,7 @@ import os from 'node:os';
import path from 'node:path';
import chalk from 'chalk';
import { MindDB, WaggleConfig, createLiteLLMEmbedder } from '@waggle/core';
import { Orchestrator, ModelRouter, runAgentLoop, createSystemTools, createPlanTools, createGitTools, Workspace, ensureIdentity, loadSystemPromptWithOverrides, assertOverridesReachActiveSpec, loadSkills, CostTracker, HookRegistry, loadHooksFromConfig, needsConfirmation } from '@waggle/agent';
import { Orchestrator, ModelRouter, runAgentLoop, createSystemTools, createPlanTools, createGitTools, Workspace, ensureIdentity, loadSystemPromptWithOverrides, loadSkills, CostTracker, HookRegistry, loadHooksFromConfig, needsConfirmation } from '@waggle/agent';
import { parseCommand, COMMANDS } from './commands.js';
import { renderMarkdown } from './renderer.js';
import { AdminClient, formatTable } from './commands/admin.js';
@@ -65,13 +65,10 @@ export async function startRepl(options: ReplOptions = {}): Promise<void> {
const workspace = new Workspace(process.cwd());
workspace.init();
// Load user customizations from ~/.waggle/ — H-08 G2: override-aware,
// so any deployed behavioral-spec or persona evolution takes effect at
// startup.
// Load user customizations from ~/.waggle/.
const waggleHome = path.join(os.homedir(), '.waggle');
const composedPrompt = loadSystemPromptWithOverrides(waggleHome);
const userSystemPrompt = composedPrompt.userPromptMd;
assertOverridesReachActiveSpec(waggleHome, composedPrompt.behavioralSpec);
const skills = loadSkills(waggleHome);
// Load user-configurable hooks from ~/.waggle/hooks.json