3 Commits

Author	SHA1	Message	Date
curo1305	c0c0156468	feat(plugins): Stage 2.1 — plugin framework and AI tool-use ... Introduces a standalone plugin system where every integration lives as an independent Python script in ~/.pyra/plugins/, not hardcoded in core. Plugin framework (src/pyra/plugins/): - base.py: Tool dataclass, PyraPlugin Protocol, BasePlugin helper - loader.py: importlib-based discovery; one bad plugin never crashes pyra - registry.py: singleton aggregating tools, slash commands, system prompts - executor.py: approval gate — scans args, prompts y/N, scans result, logs - install.py: copies bundled_plugins/ to ~/.pyra/plugins/ on install Chat integration: - AI tool-use loop (litellm function calling, up to 10 iterations) - Plugin system prompt additions injected per session - Plugin slash commands merged with static commands CLI additions: - pyra plugin list/install/enable/disable/setup - pyra daemon start/stop/status/restart/install/uninstall (stubs for 2.4) Config: PluginConfig + DaemonConfig added to PyraConfig (backwards-compatible) Bootstrap: ~/.pyra/plugins/ and ~/.pyra/logs/ created on startup Security: tool args and results always injection-scanned; plugin dirs validated with assert_safe_path() before loading (symlink protection) Tests: 37 new tests (loader, registry, executor, plugin isolation security) 161 total, all passing. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-05-17 15:35:20 +02:00
curo1305	251e509ee0	test: comprehensive test suite ... Unit tests: - test_security_boundaries.py: vault block, vault lock sentinel - test_security_injection.py: all 4 injection categories, case-insensitive - test_vault_rw.py: roundtrip, file permissions (chmod 400), no key in config - test_config.py: schema roundtrip, no api_key field, chmod 600 on config.yaml - test_memory_reader.py: list, read, sandboxing, context loading - test_memory_writer.py: write, append, index update, traversal blocked, chmod 600 - test_providers.py: required fields, unique IDs, litellm prefix format - test_renderer.py: key redaction for sk-ant-, sk-, AIza patterns Security tests: - test_vault_ai_isolation.py: 7 traversal patterns blocked via memory read/write - test_path_traversal.py: 20+ traversal patterns — all rejected for read and write - test_prompt_injection.py: 21-item corpus + 5 clean texts (no false positives) Integration tests: - test_lmstudio.py: live call to localhost:1234, streaming, full stack session, injection scan on real output (skips if LM Studio not running) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-05-17 12:55:06 +02:00
curo1305	0a04e04490	chore: init project skeleton ... Directory structure, pyproject.toml with hatchling build, and all subpackage stubs for pyra Stage 1. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-05-17 12:48:32 +02:00