asepharyana
43e35a71dd
Add tests/llmE2e.test.ts — 7 end-to-end tests driving the REAL moderation prompt pipeline (buildSystemPrompt → XML payload → llmChat → parseModerationResponse) against a live model via omniroute. Covers: clean technical content (no false positives), harassment (flagged), username-only offenses including 'Pecinta Pria' + sexual/provocative usernames + SARA-in-username (always warn/low, NEVER delete — the nickname-reset path), and spam bursts. Gated behind AI_LLM_BASE_URL + AI_LLM_API_KEY: CI (no creds) skips the file → 216 unit tests stay green, zero LLM cost. Run locally via pnpm test:e2e:live (scripts/run-llm-e2e.sh injects creds from bws). Verified: 223/223 tests pass with live LLM, stability across 4 runs, typecheck + biome clean. docs: TESTING.md. ignore .hermes/ plans.
26 lines
353 B
Plaintext
26 lines
353 B
Plaintext
node_modules
|
|
/recordings
|
|
.env
|
|
services/discord-gateway/dist/
|
|
services/backend/dist/
|
|
services/frontend/frontend/dist/
|
|
public/app/
|
|
.muxer-queue.**
|
|
.claude/
|
|
.hermes/
|
|
.env.test
|
|
logs/
|
|
.codegraph/
|
|
worktrees/
|
|
.worktrees/
|
|
target/
|
|
nix/
|
|
# Gitea CI runner logs
|
|
.gitea/workflows/*.log
|
|
|
|
# Nix build result symlink
|
|
result
|
|
|
|
# Playwright MCP artifacts
|
|
.playwright-mcp/
|