SpeedyFoxAi/vera-ai-v2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
23 Commits 1 Branch 3 Tags
355986a59fdb90ca0d854d41019925819123f1da
Commit Graph

23 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Claude Code
355986a59f fix: replace deprecated datetime.utcnow() with timezone-aware alternative 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-01 16:06:00 -05:00
Claude Code
600f9deec1 chore: pin deps to production versions, replace toml with tomllib 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-01 16:03:16 -05:00
Claude Code
9774875173 fix: correct test_curator mock strategy and list content test behavior 
- make_curator() now patches app.curator.load_curator_prompt directly instead
  of env var, since PROMPTS_DIR is a module-level constant set at import time
- _append_rule_to_file tests patch app.curator.PROMPTS_DIR via patch.object
- test_list_content: document that passing a list raises TypeError (expected)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-31 19:32:27 -05:00
Claude Code
bfd0221928 test: expand coverage to 70%+ — add utils, config, curator, proxy, integration tests 
- Extend test_utils.py: filter_memories_by_time, merge_memories, calculate_token_budget, build_augmented_messages (mocked)
- Extend test_config.py: Config.load() with TOML via tmp_path, CloudConfig helpers, env var api_key
- Add test_curator.py: _parse_json_response, _is_recent, _format_raw_turns, _append_rule_to_file
- Add test_proxy_handler.py: clean_message_content, handle_chat_non_streaming (mocked httpx+qdrant)
- Add test_integration.py: health check, /api/tags, /api/chat non-streaming + streaming via TestClient
- Add pytest.ini (asyncio_mode=auto), add pytest-cov to requirements.txt

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-31 19:19:49 -05:00
Vera-AI
abfcc91eb3 v2.0.3: Improve error handling, add tests, cleanup 
- Fix bare except clauses in curator.py and main.py
- Change embedding model to snowflake-arctic-embed2
- Increase semantic_score_threshold to 0.6
- Add memory context explanation to systemprompt.md
- Add pytest dependencies to requirements.txt
- Remove unused context_handler.py and .env.example
- Add project documentation (CLAUDE.md) and test files

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-30 08:47:56 -05:00
Vera-AI
34304a79e0 v2.0.2: Production release with role parsing fix and threshold correction v2.0.2 2026-03-27 13:42:22 -05:00
Vera-AI
c78b3f2bb6 fix: parse curated turns into proper user/assistant roles 
- Added parse_curated_turn() function to correctly parse stored memories
- Fixed build_augmented_messages() to use proper message roles
- Layer 2 (semantic) and Layer 3 (context) now correctly parse
  User: X / Assistant: Y format into separate messages
- Resolves context corruption where turns were dumped as single user message

v2.0.2
 2026-03-27 13:19:08 -05:00
Vera-AI
50874eeae9 v2.0.1: Monthly curation now in curator_prompt.md, remove full_run_time/full_run_day config 2026-03-26 21:26:02 -05:00
Vera-AI
f6affc9e01 Update curator_prompt.md with monthly curation mode, remove duplicate static/ folder v2.0.1 2026-03-26 20:43:43 -05:00
Vera-AI
6e810c913c Add systemprompt.md explaining vector DB memory context 2026-03-26 16:04:30 -05:00
Vera-AI
1092526a9f Update repository URL to GitHub 2026-03-26 15:52:20 -05:00
Vera-AI
9468c10b2c Update Docker Hub image to mdkrushr/vera-ai:latest 2026-03-26 15:39:45 -05:00
Vera-AI
7db83f096f Update Gitea URL to public internet address 2026-03-26 15:34:38 -05:00
Vera-AI
53c10f3bc2 Add Ollama installation instructions with same-host deployment options 2026-03-26 15:24:33 -05:00
Vera-AI
b24f00c2e1 Add full config.toml documentation and examples 2026-03-26 13:17:44 -05:00
Vera-AI
4ff7b7b03b Add Docker run and compose instructions with all options 2026-03-26 13:14:27 -05:00
Vera-AI
f9730eec5b Update DOCKERHUB.md with API flow diagram 2026-03-26 13:11:17 -05:00
Vera-AI
5617eabeae Add API flow diagram showing how requests pass through Vera 2026-03-26 13:10:11 -05:00
Vera-AI
535265c7d2 Remove OpenClaw references 2026-03-26 13:01:30 -05:00
Vera-AI
eee192b1c1 Update attribution to SpeedyFoxAi 2026-03-26 12:56:41 -05:00
Vera-AI
46361153a9 Update README with fancy formatting and full instructions 2026-03-26 12:55:58 -05:00
Vera-AI
5a0562f2ef Update README with full setup instructions 2026-03-26 12:52:27 -05:00
Vera-AI
50593e200d Initial commit: Vera-AI v2 with async Qdrant, singleton pattern, monthly curation, and configurable UID/GID/TZ 
Features:
- AsyncQdrantClient for non-blocking Qdrant operations
- Singleton pattern for QdrantService
- Monthly full curation (day 1 at 03:00)
- Configurable UID/GID for Docker
- Timezone support via TZ env var
- Configurable log directory (VERA_LOG_DIR)
- Volume mounts for config/, prompts/, logs/
- Standard Docker format with .env file

Fixes:
- Removed unused system_token_budget
- Added semantic_score_threshold config
- Fixed streaming response handling
- Python-based healthcheck (no curl dependency)
 2026-03-26 12:37:25 -05:00