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 +11,6 @@
* 2. Generates a SKILL.md via generateSkillMarkdown
* 3. Writes it to the personal scope directory (scope: personal frontmatter)
* 4. Dedups against existing skill files by filename
* 5. Optionally emits a workflow_pattern improvement signal
*
* A v2 enhancement can insert an LLM prose-improvement step between
* detectWorkflowPattern and generateSkillMarkdown without changing this
@@ -19,7 +18,6 @@
*/
import * as fs from 'node:fs';
import * as path from 'node:path';
import type { ImprovementSignalStore } from '@waggle/core';
import {
detectWorkflowPattern,
generateSkillMarkdown,
@@ -36,8 +34,6 @@ export interface AutoExtractMessage {
export interface AutoExtractDeps {
/** Directory to write personal-scope SKILL.md files into */
personalSkillsDir: string;
/** Optional signal store — records workflow_pattern signals on each extraction */
improvementSignals?: ImprovementSignalStore;
/**
* Optional LLM enrichment hook. When provided, the template is passed
* through before serialization so the SKILL.md prose can be rewritten.
@@ -117,22 +113,5 @@ export async function autoExtractAndCreateSkill(
const md = redactSkillContent(annotateWithScope(generateSkillMarkdown(finalTemplate))).content;
fs.writeFileSync(filePath, md, 'utf-8');
if (deps.improvementSignals) {
try {
deps.improvementSignals.record(
'workflow_pattern',
`auto-extract:${stem}`,
`Auto-extracted skill "${finalTemplate.name}" from session pattern (${finalTemplate.tools.join(', ')})`,
{
skillName: finalTemplate.name,
filename: stem,
tools: finalTemplate.tools,
category: finalTemplate.category,
source: 'auto_extract',
},
);
} catch { /* non-blocking */ }
}
return { filePath, template: finalTemplate };
}