Commit Graph

3 Commits

Author SHA1 Message Date
kami ff166ed311 feat: plane-2 rules read declared param roles instead of guessing args
Add ParamRole and a defaulted Tool.paramRoles to the tool contract; built-in
tools declare which params carry effects: file_read/write/edit -> path=PATH,
shell -> argv=EXEC_COMMAND. PathContainmentRule / ExecInterpreterRule /
NetworkHostRule now inspect only the declared params when roles are present, and
fall back to the looksLikePath / leading-token / extractHost heuristic only for
un-enriched (e.g. custom) tools - so a custom FILE_WRITE tool is still
containment-checked. Shared extractParamStrings flattens String and List<*>
(argv) values. SessionOrchestrator.runPlane2Assessment resolves the tool once
and passes tool.paramRoles into the assessment input.

This retires the arg-guessing from the first-party path: a slashy edit 'content'
arg is no longer mis-flagged as a path.
2026-05-31 16:15:22 +04:00
kami ea80597cab feat: add ExecInterpreterRule and NetworkHostRule plane-2 rules 2026-05-31 07:35:18 +04:00
kami 545068d222 feat: plane-2 tool-call intent validation (path containment slice)
Implements the full vertical slice for invariant #9 tool-call assessment:
- core:toolintent — new module with ToolCallRule seam, ToolCallAssessor,
  WorldProbe/FileSystemWorldProbe, WorkspacePolicy, PathContainmentRule,
  and RiskMapping (assessment → RiskSummary / AssessedIssue)
- core:tools — ToolCallAssessmentRecord + ToolInvocationRecord.assessment
  field; DefaultToolReducer handles ToolCallAssessedEvent (replay proof)
- core:config — ToolsConfig gains workspaceRoot + privilegedLocations;
  ConfigLoader parses both; DEFAULT_PRIVILEGED_LOCATIONS built-in
- core:kernel — OrchestratorEngines gains toolCallAssessor/workspacePolicy/
  worldProbe fields; SessionOrchestrator.dispatchToolCalls runs
  runPlane2Assessment before the tier gate: BLOCK → hard-reject without
  executing; PROMPT_USER → elevates tier into approval path with plane2Risk
  in the ApprovalRequestedEvent
- apps/server — constructs PathContainmentRule + ToolCallAssessor +
  WorkspacePolicy from config and wires them into OrchestratorEngines

Assessment is recorded as ToolCallAssessedEvent (environment observed once,
facts stored, replay reads events — invariant #9). Assessor and WorldProbe
are only invoked on the live orchestrator path, never in replay.
2026-05-31 04:22:58 +04:00