Jon Saad-Falcon and Claude 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-Falcon and Claude 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-Falcon and Claude 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
