admin/OpenJarvis
1
0
Fork 0
mirror of https://github.com/open-jarvis/OpenJarvis.git synced 2026-07-30 19:02:16 +00:00
Code Issues Packages Projects Releases Wiki Activity
90 Commits 11 Branches 77 Tags
2dcd05227a09b3a3ef30cdc424ca50b5b7ace00c
Commit Graph
5 Commits
Author SHA1 Message Date
Jon Saad-FalconandClaude Opus 4.6 e417dd8efb docs: add speech-to-text implementation plan 
15 TDD tasks covering SpeechRegistry, SpeechConfig, SpeechBackend ABC,
3 backends (Faster-Whisper, OpenAI, Deepgram), discovery, SystemBuilder
wiring, API endpoints, frontend MicButton, useSpeech hook, and Tauri
commands. ~1000 lines across ~20 files.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-03 04:30:02 +00:00
Jon Saad-FalconandClaude Opus 4.6 85332ec532 docs: add speech-to-text design plan 
New Speech subsystem with SpeechBackend ABC, registry-based backends
(Faster-Whisper, OpenAI, Deepgram), API endpoints, and frontend mic
button for desktop app and browser voice input.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-03 04:19:30 +00:00
Jon Saad-FalconandClaude Opus 4.6 28a6c5e675 docs: add codebase simplification implementation plan 
13 incremental tasks covering structure cleanup, data migration,
shim removal, engine consolidation, and init.py refactoring.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-02 20:21:12 +00:00
Jon Saad-FalconandClaude Opus 4.6 ad2c186b89 docs: add codebase simplification design plan 
Outlines incremental restructuring to reduce root sprawl from 32 to 21
items, consolidate data dirs into src/ package, remove backward-compat
shims, and clean up repetitive code patterns.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-02 20:14:20 +00:00
Jon Saad-FalconandClaude Opus 4.6 2aebcd7d77 feat: Phase 23 — Differentiated functionalities 
Trace-driven learning pipeline:
- TrainingDataMiner: extract SFT/routing/agent pairs from traces
- LoRATrainer: fine-tune local models from trace-derived data
- AgentConfigEvolver: rewrite agent configs from trace analysis
- LearningOrchestrator: coordinate mine→train→evolve cycle, wired into SystemBuilder

Eval framework (15 real IPW benchmarks):
- Datasets: SuperGPQA, GPQA, MMLU-Pro, MATH-500, Natural Reasoning, HLE,
  SimpleQA, WildChat, IPW, GAIA, FRAMES, SWE-bench, SWEfficiency,
  TerminalBench, TerminalBench Native
- Scorers: MCQ extraction, LLM-judge, exact match, structural validation
- CLI: jarvis eval list|run|compare|report

Composable abstractions:
- Recipe system: TOML composition of all 5 pillars (3 built-in recipes)
- Agent templates: 15 pre-configured TOML manifests with system prompts
- Bundled skills: 20 ready-to-use TOML skill manifests
- Operator recipes: researcher (4h), correspondent (5min), sentinel (2h)

102 files changed, ~11,500 lines added. 3241 tests pass (44 skipped).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-02 05:34:46 +00:00