Update test expectations across all test modules to align with the
Rust (PyO3) backend that replaced Python implementations:
- calculator: meval uses ^/ln/floor(), returns floats, inf for 1/0
- shell_exec: output format uses "Exit code: N\n--- stdout ---\n..."
- git_tool: always --oneline, mock Rust bridge for git-not-found
- http_request: force httpx fallback so respx mocks work
- memory: UUID is 36 chars (hyphenated), BM25Memory() takes no args
- loop_guard: Rust blocks on 2nd identical call, capitalized messages
- ssrf: Rust returns "Invalid URL" for unparseable URLs
- mcp: division by zero returns inf (success), not error
- integration: calculator results are float strings ("4.0" not "4")
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The test job was failing because `openjarvis_rust` (the PyO3 module)
wasn't being built. Add Rust toolchain, cargo cache, and maturin
develop step so the extension is available when pytest runs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove unused imports (fnmatch, re, uuid, ScanFinding, Tuple) and
shorten docstrings to fix E501/F401 violations across loop_guard,
security, and storage modules.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move detailed architecture, testing, and pattern docs out of CLAUDE.md
into focused .claude/rules/ files. CLAUDE.md is now a lean routing table
that points to the right context based on what you're working on.
Also fixes stale HazyResearch links in README.md (docs URL, clone URL)
and adds CLAUDE.md to .gitignore so it stays per-developer.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The repo was transferred from HazyResearch/OpenJarvis to
open-jarvis/OpenJarvis. Update ~35 references across 12 files:
mkdocs site_url/repo_url, Tauri updater endpoints, frontend doc links,
clone URLs in docs and scripts, and agent config.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove orphaned docs/api/ pages (superseded by auto-generated
api-reference/) and update 5 broken cross-references to point to
the new api-reference/ paths. mkdocs build --strict now passes
with zero warnings.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- 5 tutorial docs pages with mermaid diagrams, admonitions, content tabs
- Deployment index page linking Docker, systemd, launchd, API server
- Learning architecture updated with optimization framework section
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- New tagline: "Composable, Programmable Systems for On-Device, Personal AI"
- Georgia font in mkdocs.yml theme and all CSS references
- Remove Google Fonts import for Merriweather/Inter
- New 6-tab nav: Home, Getting Started, Tutorials, Architecture,
API Reference, Development
- Deployment moves under Development tab
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Deep Research Assistant: multi-source research with memory-augmented orchestrator
- Scheduled Personal Ops: cron-driven agents (daily digest, code review, gym)
- Messaging Hub: smart inbox with message triage and auto-replies
- Code Companion: code review, debugging, and test generation agents
Each example includes README walkthrough, standalone CLI scripts, and
optional TOML recipe configs. All scripts work with --help without
requiring a running engine.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove the black border and flatten the horizontal logo onto a solid
white background for cleaner rendering on GitHub.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the old dark/light SVG logos with new branded PNG logos
(circular and horizontal). Use horizontal logo as the README headline image.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds three new inference engine implementations to the Rust engine crate:
- VLLMEngine: OpenAI-compatible /v1/chat/completions API
- SGLangEngine: OpenAI-compatible API with SGLang-specific features
- LlamaCppEngine: Native /completion endpoint with ChatML prompt formatting
All backends implement InferenceEngine trait with generate, stream,
list_models, and health methods. Includes comprehensive unit tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
FAISSMemory with brute-force cosine similarity. ColBERTMemory with
token-level MaxSim scoring. HybridMemory with Reciprocal Rank Fusion
combining multiple backends. All backed by SQLite for persistence.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Port optimization types, store, search space, engine, and LLM optimizer
from Python to Rust. Includes SearchDimension, SearchSpace, TrialConfig,
TrialResult, OptimizationStore (SQLite), OptimizationEngine with Pareto
frontier, LLMOptimizer with OptimizerBackend trait. 47 tests pass.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Shorten docstrings in backward-compat shims to fix E501 (line too long).
Sort imports in learning/__init__.py. Zero Ruff violations remaining.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move 12 optimize-related test files from tests/ root into tests/learning/
to match the module reorganization. All 305 tests pass from new locations.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move the optimization module under the Learning pillar where it
conceptually belongs. All internal imports updated to
openjarvis.learning.optimize. Backward-compatibility shims at the old
openjarvis.optimize path re-export everything. External consumers
(CLI optimize_cmd, server api_routes) updated to import from new location.
All 305 optimize-related tests pass.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove NFS lock artifacts, empty research output files, results/ and
site/ build artifacts. Add .ruff_cache/, .nfs*, research_mining_* to
.gitignore.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix all ruff E501 line-length violations
- Add noqa: E402 for intentional late imports in runner scripts
- Remove unused imports in tb_agent.py
- Update test_llm_optimizer assertions to expect fixed params in
unparseable/missing-params cases (intended behavior change)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Keep both system_prompt (optimization) and episode_mode (Phase 25) in
RunConfig. Merge terminalbench_native metadata using v2 task_data dict
API while preserving new create_task_env/verify_requirements methods.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove duplicate config structs in Rust config.rs and Python config.py
- Remove duplicate match arms in Rust discovery.rs
- Fix E501 line-too-long in evals/cli.py
- Fix E402 imports-not-at-top in test_ama_bench.py and test_loghub.py
- Fix E501 long lines in test_loghub.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add four new OpenAI-compatible inference engines across the full stack:
Rust backend:
- Config structs with serde defaults (ExoEngineConfig, NexaEngineConfig,
UzuEngineConfig, AppleFmEngineConfig) in openjarvis-core
- Factory constructors on OpenAICompatEngine (exo, nexa, uzu, apple_fm)
- Engine enum variants with delegate_engine! macro dispatch
- Discovery and resolution in get_engine_static()
- PyO3 bridge support in PyEngine
Python frontend:
- Data-driven engine class registration in openai_compat_engines.py
- Config dataclasses with backward-compat host properties
- Discovery host map entries
- DEFAULT_SEARCH_SPACE updated with new engine backends
- Apple FM shim (FastAPI wrapper for python-apple-fm-sdk, macOS only)
Config & tests:
- TOML config sections for all four engines
- Unit tests for factory methods, enum variants, and search space
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
