ToolUniverse Self-Evolution Orchestrator

The Cycle

Discover → Create → Test → Fix → Optimize → Ship → Repeat

devtu-auto-discover-apis

devtu-create-tool

devtu-fix-tool

devtu-optimize-skills

devtu-optimize-descriptions

devtu-docs-quality

devtu-github

Quick Start

• "Run a test round" → jump to Testing Phase
• "Expand coverage" → invoke

  Skill(skill="devtu-auto-discover-apis")

• "Create a new tool" → invoke

  Skill(skill="devtu-create-tool")

• "Fix a broken tool" → invoke

  Skill(skill="devtu-fix-tool")

• "Improve skills" → invoke

  Skill(skill="devtu-optimize-skills")

• "Full cycle" → follow all phases below in order

Phase 1: Discovery (optional)

Skill(skill="devtu-auto-discover-apis")

1. Run gap analysis on current tool categories
2. Search for life science APIs in underrepresented domains
3. Score and prioritize APIs by coverage, reliability, documentation

Phase 2: Tool Creation (optional)

Skill(skill="devtu-create-tool")

1. Create Python tool class implementing the API
2. Create JSON config with parameters, descriptions, test examples
3. Register in

   _lazy_registry_static.py

   and

   default_config.py

4. Validate:

   python -m tooluniverse.cli test <ToolName>

Phase 3: Testing Phase

Setup

1. Check for open PRs:

   gh pr list --state open

2. If unmerged PR → use that branch; if merged → new branch from

   origin/main

3. Rebase:

   git fetch origin && git rebase origin/main

Researcher Persona Agents

• Domain specialty (oncology, genomics, pharmacology, etc.)
• Research question (specific biological question)
• 5-7 test scenarios exercising different tools
• Instructions to report issues with severity (HIGH/MEDIUM/LOW)
• Issue IDs:

  Feature-{round}{letter}-{num}

  (e.g.,

  Feature-59A-001

  )

Verification (CRITICAL)

python3 -m tooluniverse.cli run <ToolName> '<json_args>'

Fix Principles

1. Prevent, don't recover — fix root cause, not symptoms
2. Validate at input — reject bad params early with clear guidance
3. Distinguish "no data" from "bad query" — different messages for each
4. Fix the abstraction — don't add alias lists that grow forever

Phase 4: Fix & Commit

1. Implement verified fixes (see references/bug-patterns.md for code-level patterns)
2. Run code-simplifier:

   Skill(skill="simplify")

   — always after writing or modifying code
3. Lint:

   ruff check src/tooluniverse/<file>.py

4. Verify syntax:

   python -c "from tooluniverse.<module> import <Class>"

5. Test:

   python -m tooluniverse.cli run <Tool> '<json>'

6. Pre-commit hook pattern: stage → commit (fails, reformats) → re-stage → commit
7. Push:

   git push origin <branch>

Also see

Skill(skill="devtu-code-optimization")

for reusable fix patterns and anti-patterns.

Phase 5: Optimize (optional)

• Skill(skill="devtu-optimize-descriptions")

  — improve tool descriptions

• Skill(skill="devtu-optimize-skills")

  — improve research skill quality

• Skill(skill="devtu-docs-quality")

  — validate docs accuracy

Phase 6: Ship

Skill(skill="devtu-github")

1. Rebase:

   git fetch origin && git stash && git rebase origin/main && git stash pop

2. git push --force-with-lease origin <branch>

3. Create or update PR:

   gh pr create

   / verify with

   gh pr view <N> --json mergeable

4. Verify

   "mergeable": "MERGEABLE"

   before reporting done

mims-harvard/ToolUniverse

git remote -v

Git Rules (CRITICAL)

• NEVER push to main — all work on feature branches
• NEVER have multiple open fix PRs — keep adding to current branch
• Always rebase before push:

  git fetch origin && git rebase origin/main

• Commit message format: no "BUG" terminology, use "Feature" or "Fix"
• No AI attribution in commits

Common Issue Categories

.get("field")