This repository has been archived on 2026-03-24. You can view files and clone it. You cannot open issues or pull requests or push a commit.

Alexander Whitestone 3e5a3ac05f feat: add content moderation pipeline (Llama Guard + game-context profiles) ...

Implement real-time content moderation for narration output using a
local safety model (Llama Guard 3 via Ollama). The pipeline is designed
to run in parallel with TTS preprocessing for near-zero added latency.

Key components:
- ContentModerator singleton with async check() method
- Game-context profiles (Morrowind vocabulary whitelist, fallback narrations)
- Configurable fail-open/fail-closed degradation when model unavailable
- Llama Guard response parsing (safe/unsafe with category codes)
- 40 unit tests covering profiles, parsing, whitelist, and async checks

Config settings: moderation_enabled, moderation_model, moderation_timeout_ms,
moderation_fail_open, moderation_game_profile

Fixes #987

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-22 20:43:22 -04:00

..

dashboard

[kimi] Generate daily/weekly agent scorecards (#712) (#790)

2026-03-22 01:41:52 +00:00

e2e

[loop-cycle-51] perf: mock subprocess in slow introspection test (#172) (#184)

2026-03-15 12:17:50 -04:00

fixtures

feat: code quality audit + autoresearch integration + infra hardening (#150)

2026-03-08 12:50:44 -04:00

functional

Claude/angry cerf (#173)

2026-03-11 16:55:27 -04:00

infrastructure

feat: add content moderation pipeline (Llama Guard + game-context profiles)

2026-03-22 20:43:22 -04:00

integrations

[loop-cycle-956] refactor: break up _handle_message() into focused helpers (#553) (#574)

2026-03-19 21:42:01 -04:00

loop

[kimi] Add JSON validation guard to queue.json writes (#952) (#995)

2026-03-22 22:33:40 +00:00

scripts

[kimi] Add JSON validation guard to queue.json writes (#952) (#995)

2026-03-22 22:33:40 +00:00

security

Claude/angry cerf (#173)

2026-03-11 16:55:27 -04:00

spark

[kimi] test: add comprehensive tests for spark modules (#659) (#695)

2026-03-21 13:32:53 +00:00

timmy

[claude] Add web_fetch tool (trafilatura) for full-page content extraction (#973) (#1004)

2026-03-22 23:03:38 +00:00

timmy_automations

[loop-cycle-5] fix: get_token() priority order — config before repo-root fallback (#899)

2026-03-22 01:52:40 +00:00

unit

[kimi] Implement token quest system for agents (#713) (#789)

2026-03-21 20:45:35 +00:00

__init__.py

feat: scaffold Timmy Time Mission Control (v1.0.0 Genesis)

2026-02-19 19:05:01 +00:00

conftest_markers.py

feat: code quality audit + autoresearch integration + infra hardening (#150)

2026-03-08 12:50:44 -04:00

conftest.py

[kimi] refactor: extract helpers from CSRFMiddleware.dispatch (#628) (#691)

2026-03-21 03:41:09 +00:00

test_agentic_loop.py

test: add comprehensive unit tests for agentic_loop.py (#345)

2026-03-18 20:54:02 -04:00

test_api_v1.py

feat: implement v1 API endpoints for iPad app (#312)

2026-03-18 18:20:14 -04:00

test_config_module.py

[kimi] test: add comprehensive tests for config.py (#648) (#693)

2026-03-21 03:54:54 +00:00

test_hands_git.py

feat: code quality audit + autoresearch integration + infra hardening (#150)

2026-03-08 12:50:44 -04:00

test_hands_shell.py

fix: shell hand returncode bug, delete worthless python-exec test (#140)

2026-03-15 09:56:50 -04:00

test_lazy_init.py

[loop-cycle-536] fix: validate_startup checks CORS wildcard in production (#472) (#478)

2026-03-19 15:29:26 -04:00

test_smart_read_file.py

fix: smart_read_file accepts path= kwarg from LLMs (#113)

2026-03-14 20:40:19 -04:00

test_smoke.py

[kimi] Implement quick health snapshot before coding (#710) (#828)

2026-03-21 21:53:40 +00:00