feat(skill): add inline tool executor #297

Closed
opened 2026-02-22 23:41:02 +00:00 by freemo · 0 comments
Owner

Metadata

  • Commit: feat(skill): add inline tool executor
  • Branch: feature/m3-skill-protocol

Subtasks

  • Implement inline tool execution with timeouts and restricted environment in src/cleveragents/skills/inline_executor.py.
  • Ensure inline tools conform to Tool Registry schema and return structured results.
  • Add safeguards for file/network access inside inline tools (local-only for MVP).
  • Add max runtime and max output size guards; return structured error on timeout/overflow.
  • Add docs/reference/skills_inline.md with safety constraints.
  • Tests (Behave): Add features/skill_inline.feature for execution and timeout handling.
  • Tests (Robot): Add robot/skill_inline.robot for inline tool smoke tests.
  • Tests (ASV): Add benchmarks/inline_tool_bench.py for execution overhead.
  • Verify coverage >=97% via nox -s coverage_report. If coverage is <97% then review the current unit test coverage report at build/coverage.xml and use it to write new Behave based unit tests to improve code coverage. Specifically, write Behave style unit tests that are descriptively named and specifically improves coverage on whichever file has the most uncovered lines by writing tests that will target the uncovered lines in the report. Once that is done rerun nox -s coverage_report to verify all tests pass and coverage is above >=97%. Only mark this as complete once coverage is >=97%, if not repeat this task as many times as is needed until coverage reaches >=97%.
  • Run nox (all default sessions, including benchmark), fix any errors if needed ensuring nox passes across entire code base, do not ignore any failure even if it seems unrelated to this commit, fix it.

Section: ### Section 5: Actors, Skills & Tool Execution [WORKSTREAM C - Aditya Lead]
Status: Completed

## Metadata - **Commit**: `feat(skill): add inline tool executor` - **Branch**: `feature/m3-skill-protocol` ## Subtasks - [x] Implement inline tool execution with timeouts and restricted environment in `src/cleveragents/skills/inline_executor.py`. - [x] Ensure inline tools conform to Tool Registry schema and return structured results. - [x] Add safeguards for file/network access inside inline tools (local-only for MVP). - [x] Add max runtime and max output size guards; return structured error on timeout/overflow. - [x] Add `docs/reference/skills_inline.md` with safety constraints. - [x] Tests (Behave): Add `features/skill_inline.feature` for execution and timeout handling. - [x] Tests (Robot): Add `robot/skill_inline.robot` for inline tool smoke tests. - [x] Tests (ASV): Add `benchmarks/inline_tool_bench.py` for execution overhead. - [x] Verify coverage >=97% via `nox -s coverage_report`. If coverage is <97% then review the current unit test coverage report at `build/coverage.xml` and use it to write new Behave based unit tests to improve code coverage. Specifically, write Behave style unit tests that are descriptively named and specifically improves coverage on whichever file has the most uncovered lines by writing tests that will target the uncovered lines in the report. Once that is done rerun `nox -s coverage_report` to verify all tests pass and coverage is above >=97%. Only mark this as complete once coverage is >=97%, if not repeat this task as many times as is needed until coverage reaches >=97%. - [x] Run `nox` (all default sessions, including benchmark), fix any errors if needed ensuring nox passes across **entire** code base, do not ignore any failure even if it seems unrelated to this commit, fix it. **Section**: ### Section 5: Actors, Skills & Tool Execution [WORKSTREAM C - Aditya Lead] **Status**: Completed
freemo added this to the v3.1.0 milestone 2026-02-22 23:41:02 +00:00
freemo self-assigned this 2026-02-22 23:41:02 +00:00
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Reference
cleveragents/cleveragents-core#297
No description provided.