Commit Graph

55 Commits

Author SHA1 Message Date
Claude 6a1255dfdb feat: LLM router with local (Ollama) and cloud (OpenAI) backends
- lyra.config.load() reads env into a frozen Config dataclass
- lyra.llm.complete(messages, backend) routes to Ollama /api/chat or
  OpenAI chat completions
- lyra.llm.embed(texts) calls OpenAI embeddings
- .env.example switched from Anthropic to OpenAI to match available key
2026-05-16 06:10:48 +00:00
Claude b2523c2561 chore: project scaffold (uv, .env.example, README, lyra package) 2026-05-16 06:01:08 +00:00
Claude faf4e8a1aa chore: nuke legacy code, keep design docs for restart
Preserved on the archive branch. Keeping only the architecture and
design thinking that survives the rewrite:

- docs/ARCH_v0-6-1.md (Inner Self / Executive / Chat / Persona model)
- docs/ARCHITECTURE_v0-6-0.md (predecessor architecture)
- docs/PROJECT_SUMMARY.md (project history and rationale)
- docs/PROJECT_LYRA_COMPLETE_BREAKDOWN.md (detailed design notes)
- docs/ENVIRONMENT_VARIABLES.md (multi-backend env conventions)
- docs/LLMS.md
- docs/TRILLIUM_API.md (for future tool integration)

Removed: all service code (cortex, core/relay, neomem, rag, sandbox,
persona-sidecar), docker-compose, migration/logging docs, stale root
test scripts, CHANGELOG.
2026-05-16 05:57:07 +00:00
claude 4b951f3be8 Merge pull request #16 from serversdwn/dev
update to 0.9.0
2025-12-29 01:59:14 -05:00
claude 6b5580a80e 0.9.0 - Added Trilium ETAPI integration.
Lyra can now: Search trilium notes and create new notes. with proper ETAPI auth.
2025-12-29 01:58:20 -05:00
claude 86b37ab874 feat: Implement Trillium notes executor for searching and creating notes via ETAPI
- Added `trillium.py` for searching and creating notes with Trillium's ETAPI.
- Implemented `search_notes` and `create_note` functions with appropriate error handling and validation.

feat: Add web search functionality using DuckDuckGo

- Introduced `web_search.py` for performing web searches without API keys.
- Implemented `search_web` function with result handling and validation.

feat: Create provider-agnostic function caller for iterative tool calling

- Developed `function_caller.py` to manage LLM interactions with tools.
- Implemented iterative calling logic with error handling and tool execution.

feat: Establish a tool registry for managing available tools

- Created `registry.py` to define and manage tool availability and execution.
- Integrated feature flags for enabling/disabling tools based on environment variables.

feat: Implement event streaming for tool calling processes

- Added `stream_events.py` to manage Server-Sent Events (SSE) for tool calling.
- Enabled real-time updates during tool execution for enhanced user experience.

test: Add tests for tool calling system components

- Created `test_tools.py` to validate functionality of code execution, web search, and tool registry.
- Implemented asynchronous tests to ensure proper execution and result handling.

chore: Add Dockerfile for sandbox environment setup

- Created `Dockerfile` to set up a Python environment with necessary dependencies for code execution.

chore: Add debug regex script for testing XML parsing

- Introduced `debug_regex.py` to validate regex patterns against XML tool calls.

chore: Add HTML template for displaying thinking stream events

- Created `test_thinking_stream.html` for visualizing tool calling events in a user-friendly format.

test: Add tests for OllamaAdapter XML parsing

- Developed `test_ollama_parser.py` to validate XML parsing with various test cases, including malformed XML.
2025-12-26 03:49:20 -05:00
claude 8b66cd1e1d update to 0.7.0
Standard Mode Implementation - Complete documentation of the new simple chatbot mode
Backend Selection System - UI settings modal and routing changes
Session Management Overhaul - File-based persistence with CRUD API
UI Improvements - Settings modal, light/dark mode, modal fixes
Context Retention - Integration with Intake for conversation history
Architecture & Routing Changes - Updates to Relay, Cortex, Intake, LLM router
Fixed Critical Issues - DeepSeek R1, context retention, OpenAI errors, modal formatting, session persistence
Technical Improvements - Backward compatibility, code quality, performance
Architecture Diagrams - Data flow for Standard Mode, Cortex Mode, and sessions
Known Limitations - Standard Mode constraints, session management limits
Migration Notes - For users and developers upgrading
2025-12-22 01:41:21 -05:00
claude 7cb7033bb6 docs updated v0.7.0 2025-12-22 01:40:24 -05:00
claude 9226b2480b sessions improved, v0.7.0 2025-12-21 15:50:52 -05:00
claude 58d0afd1c6 mode selection, settings added to ui 2025-12-21 14:30:32 -05:00
claude 9c03b23a6d simple context added to standard mode 2025-12-21 13:01:00 -05:00
claude fdc51e598c v0.7.0 - Standard non cortex mode enabled 2025-12-20 04:15:22 -05:00
claude 092ac4d181 Cortex debugging logs cleaned up 2025-12-20 02:49:20 -05:00
claude a4f5308f9b Merge pull request #9 from serversdwn/dev
Update to 0.6.0. Docs updated.
2025-12-19 17:44:11 -05:00
claude 34aff34038 Docs updated v0.6.0 2025-12-19 17:43:22 -05:00
claude a41e342dbd cleanup ignore stuff 2025-12-17 02:46:23 -05:00
claude 09c00848b9 Merge branch 'dev' of https://github.com/serversdwn/project-lyra into dev 2025-12-17 01:47:30 -05:00
claude ec5f17694e ignore 2025-12-17 01:47:19 -05:00
claude b74658c000 complete breakdown for AI agents added 2025-12-15 11:49:49 -05:00
claude 0a03546039 neomem disabled 2025-12-15 04:10:03 -05:00
claude 0528d10081 autonomy phase 2.5 - tightening up some stuff in the pipeline 2025-12-15 01:56:57 -05:00
claude e2e55a0fda autonomy phase 2 2025-12-14 14:43:08 -05:00
claude ae41b51888 autonomy build, phase 1 2025-12-14 01:44:05 -05:00
claude 70e57ba5d2 cortex pipeline stablized, inner monologue is now determining user intent and tone 2025-12-13 04:13:12 -05:00
claude 7693bc4080 autonomy scaffold 2025-12-13 02:55:49 -05:00
claude 628edb681a v0.5.2 update
Dev
2025-12-12 08:04:20 +00:00
claude 58d6520056 v0.5.2 - fixed: llm router async, relay-UI mismatch, intake summarization failure, among others.
Memory relevance thresh. increased.
2025-12-12 02:58:23 -05:00
claude 77429ca6e0 v0.6.1 - reinstated UI, relay > cortex pipeline working 2025-12-11 16:28:25 -05:00
claude 67b7f9594c autonomy, initial scaffold 2025-12-11 13:12:44 -05:00
claude 875e660e31 docs updated for v0.5.1 2025-12-11 03:49:23 -05:00
claude 09b6b364e5 v0.5.1-Major cortex rework. clean up done too. Merge from dev
v0.5.1-Major cortex rework. clean up done too.
2025-12-11 03:48:29 -05:00
claude 832fea78d0 gitignore updated, to ignore vscode settings 2025-12-11 03:42:30 -05:00
claude 3b5ec9c974 cleaning up deprecated files 2025-12-11 03:40:47 -05:00
claude 3eb19d30f0 cortex rework continued. 2025-12-11 02:50:23 -05:00
claude 8428e5e04e deprecated old intake folder 2025-12-06 04:38:11 -05:00
claude 04f4ed6b51 intake/relay rewire 2025-12-06 04:32:42 -05:00
claude 03450b5f70 add. cleanup 2025-11-30 03:58:15 -05:00
claude 6312f2ae92 intake internalized by cortex, removed intake route in relay 2025-11-29 19:08:15 -05:00
claude 5db0614cdc cortex 0.2.... i think? 2025-11-29 05:14:32 -05:00
claude 26f5a6b972 fixed neomem URL request failure, now using correct variable 2025-11-28 19:50:53 -05:00
claude c3fffcdd80 context added, wired in. first attempt 2025-11-28 19:29:41 -05:00
claude 1dd84613cf Merge pull request #4 from serversdwn/dev
Big clean up to v0.5.0, docs updated, restructured throughout.
2025-11-28 18:14:18 -05:00
claude 211328aba9 docs updated 2025-11-28 18:05:59 -05:00
claude 50f95a1f59 Major rewire, all modules connected. Intake still wonkey 2025-11-28 15:14:47 -05:00
claude 7e34307b31 Cortex rework in progress 2025-11-26 18:01:48 -05:00
claude ca5f582f9c Fixin' crap so relay works again. pre llm redo 2025-11-26 14:20:47 -05:00
claude a5f3e0248a env cleanup round 2 2025-11-26 03:18:15 -05:00
claude 3b128ac7f6 Merge pull request #3 from serversdwn/dev
Dev branch reorganizing.
2025-11-26 02:32:31 -05:00
claude 8128b45fe5 reorganizing and restructuring 2025-11-26 02:28:00 -05:00
claude 6d5d442f96 intital file restructure 2025-11-25 20:50:05 -05:00