Jobdori
8cc7d4c641
chore: additional AI slop cleanup and enforcer wiring from sessions 1/5
...
Session 1 (ses_2ad65873): with_enforcer builders + 2 regression tests
Session 5 (ses_2ad67e8e): continued AI slop cleanup pass — redundant
comments, unused_self suppressions, unreachable! tightening
Session cleanup (ses_2ad6b26c): Python placeholder centralization
Workspace tests: 363+ passed, 0 failed.
2026-04-03 18:35:27 +09:00
Jobdori
618a79a9f4
feat: ultraclaw session outputs — registry tests, MCP bridge, PARITY.md, cleanup
...
Ultraclaw mode results from 10 parallel opencode sessions:
- PARITY.md: Updated both copies with all 9 landed lanes, commit hashes,
line counts, and test counts. All checklist items marked complete.
- MCP bridge: McpToolRegistry.call_tool now wired to real McpServerManager
via async JSON-RPC (discover_tools -> tools/call -> shutdown)
- Registry tests: Added coverage for TaskRegistry, TeamRegistry,
CronRegistry, PermissionEnforcer, LspRegistry (branch-focused tests)
- Permissions refactor: Simplified authorize_with_context, extracted helpers,
added characterization tests (185 runtime tests pass)
- AI slop cleanup: Removed redundant comments, unused_self suppressions,
tightened unreachable branches
- CLI fixes: Minor adjustments in main.rs and hooks.rs
All 363+ tests pass. Workspace compiles clean.
2026-04-03 18:23:03 +09:00
Jobdori
66283f4dc9
feat(runtime+tools): PermissionEnforcer — permission mode enforcement layer
...
Add PermissionEnforcer in crates/runtime/src/permission_enforcer.rs
and wire enforce_permission_check() into crates/tools/src/lib.rs.
Runtime additions:
- PermissionEnforcer: wraps PermissionPolicy with enforcement API
- check(tool, input): validates tool against active mode via policy.authorize()
- check_file_write(path, workspace_root): workspace boundary enforcement
- ReadOnly: deny all writes
- WorkspaceWrite: allow within workspace, deny outside
- DangerFullAccess/Allow: permit all
- Prompt: deny (no prompter available)
- check_bash(command): read-only command heuristic (60+ safe commands)
- Detects -i/--in-place/redirect operators as non-read-only
- is_within_workspace(): string-prefix boundary check
- is_read_only_command(): conservative allowlist of safe CLI commands
Tool wiring:
- enforce_permission_check() public API for gating execute_tool() calls
- Maps EnforcementResult::Denied to Err(reason) for tool dispatch
9 new tests covering all permission modes + workspace boundary + bash heuristic.
2026-04-03 17:55:04 +09:00
