John SmithandClaude 7c755caf4d feat(routing): optional LLM-assisted intent classification (iteration 10) ...

classify_with_llm() prompts the configured custom endpoint
(LLM_API/LLM_KEY/LLM_MODEL) for JSON classification into the real
IntentType enum, with layered honesty and safety:
- SAFETY_INTERVENTION always wins — keyword safety short-circuits
  before any network call; an LLM safety label overrides keyword
  disagreement
- any failure (kill-switch VTT_LLM_CLASSIFIER=0, no key, malformed or
  unknown output) falls back to the deterministic keyword classifier
  with provenance fields; never raises
- RULE_OF_COOL has no enum counterpart and is deliberately not mapped
complete_json() adds fence-tolerant JSON extraction + non-streaming
chat-completions with response_format json_object; degraded-marker
code preserved. 12 new tests, HTTP fully mocked.

Co-Authored-By: Claude <[email protected]>

2026-08-24 01:37:06 -04:00

..

fixtures/srd52_sample

feat(wave8): expand compendium with SRD 5.2 magic items, feats, origins, animals & full stat blocks

2026-08-23 00:27:49 -04:00

test_auditor_grounding.py

feat(auditor): ground truth from live engine, audit-before-yield streaming, narrative lore triples

2026-08-24 01:08:47 -04:00

test_auth.py

feat(wave15): zero-trust hardening, real WFC, write-through Postgres, RBAC, Yjs default

2026-08-23 22:41:53 -04:00

test_bundle_packager.py

fix(homebrew): fail-loud parsing, never fabricate statblocks

2026-08-24 01:08:27 -04:00

test_campaign_persistence.py

feat(wave12): Postgres persistence & campaign save/load

2026-08-23 10:53:40 -04:00

test_disposition.py

feat(simulation): NPC disposition scoring engine (iteration 2)

2026-08-24 01:20:54 -04:00

test_durability_bridge.py

feat(wave15): zero-trust hardening, real WFC, write-through Postgres, RBAC, Yjs default

2026-08-23 22:41:53 -04:00

test_dynasty.py

feat(dynasty-empirical-playtest): implement opendnd dynasty lineages, feud matrix, and dnddata empirical party benchmarks

2026-08-22 19:27:54 -04:00

test_engine_proxy.py

fix(gateway): strict CORS allowlist, forward caller identity to engine proxies

2026-08-24 00:42:52 -04:00

test_llm_intent.py

feat(routing): optional LLM-assisted intent classification (iteration 10)

2026-08-24 01:37:06 -04:00

test_lobbies_characters.py

fix(gateway): strict CORS allowlist, forward caller identity to engine proxies

2026-08-24 00:42:52 -04:00

test_lore_triples.py

feat(auditor): ground truth from live engine, audit-before-yield streaming, narrative lore triples

2026-08-24 01:08:47 -04:00

test_narrative_grounding.py

feat(wave11): SRD-grounded narration, end-to-end X-card rewind & honest voice activity

2026-08-23 01:35:50 -04:00

test_orchestrator.py

feat(gateway): honest degradation markers on SSE narrative fallback (iteration 5)

2026-08-24 01:27:11 -04:00

test_pdf_export.py

feat(character-builder-pdf): implement 5e character studio, strict modifier graph, and vector PDF exporter

2026-08-22 19:12:08 -04:00

test_quest_engine.py

feat: complete Horizons 1, 2, and 3 (Docker Compose, Procedural Quest Engine & Concordia Pacts, and 3D Elevation)

2026-08-22 19:49:55 -04:00

test_srd52_importer.py

feat(wave8): expand compendium with SRD 5.2 magic items, feats, origins, animals & full stat blocks

2026-08-23 00:27:49 -04:00

test_srd_importer.py

feat(srd): parse D&D 5e SRD markdown into hardcoded VTT core logic, schemas, and relational tables

2026-08-22 19:40:57 -04:00

test_stream_degraded.py

feat(gateway): honest degradation markers on SSE narrative fallback (iteration 5)

2026-08-24 01:27:11 -04:00