Skip to content

feat(agents): add the-user coordinator agent#2

Open
qwertystars wants to merge 4 commits into
devfrom
claude/create-user-coordinator-agent-ki6Dg
Open

feat(agents): add the-user coordinator agent#2
qwertystars wants to merge 4 commits into
devfrom
claude/create-user-coordinator-agent-ki6Dg

Conversation

@qwertystars

@qwertystars qwertystars commented Feb 2, 2026

Copy link
Copy Markdown
Owner

Introduces a new lightweight coordinator agent that acts as an intelligent
intermediary between users and specialized AI agents. Key features:

  • Uses cheaper models (haiku/flash/nano) for cost-effective coordination
  • Understands user intent and routes to appropriate agents
  • Relays questions from agents back to users for decision-making
  • Includes comprehensive system prompt with decision trees and examples
  • Supports session continuation for multi-turn agent interactions

https://claude.ai/code/session_01VK8KpJng69ry31LhwuFmzp

Summary by CodeRabbit

Release Notes

  • New Features
    • Introduced "The User" agent—a new coordinator agent that orchestrates requests across specialized agents and intelligently delegates tasks based on user needs.
    • The User agent integrates with existing agents to relay questions and aggregate results for improved task execution.

Introduces a new lightweight coordinator agent that acts as an intelligent
intermediary between users and specialized AI agents. Key features:

- Uses cheaper models (haiku/flash/nano) for cost-effective coordination
- Understands user intent and routes to appropriate agents
- Relays questions from agents back to users for decision-making
- Includes comprehensive system prompt with decision trees and examples
- Supports session continuation for multi-turn agent interactions

https://claude.ai/code/session_01VK8KpJng69ry31LhwuFmzp
…n workflow

Enhances the-user coordinator agent with Planning & Execution workflow:

- Prometheus integration for strategic planning of complex features
- Atlas for structured execution with verification and parallel tasks
- Hephaestus for autonomous deep work and complex exploration
- Decision tree updated to route big features through planning workflow
- Added examples for planning workflow and executor selection
- Updated boundaries section with clear agent responsibilities

https://claude.ai/code/session_01VK8KpJng69ry31LhwuFmzp
…ork only)

Atlas is reserved for the /start-work command. Updated the-user agent to:
- Use only Hephaestus for plan execution
- Remove Atlas from decision tree and examples
- Add note clarifying Atlas is /start-work only

https://claude.ai/code/session_01VK8KpJng69ry31LhwuFmzp
@coderabbitai

coderabbitai Bot commented Feb 2, 2026

Copy link
Copy Markdown
📝 Walkthrough

Walkthrough

A new "the-user" coordinator agent is introduced, orchestrating user requests by delegating to specialized agents and aggregating results. The implementation spans type definitions, schema validation, agent utilities, model configuration, and a primary agent file with dynamic prompt generation and delegation logic.

Changes

Cohort / File(s) Summary
Type and Schema Definitions
src/agents/types.ts, src/config/schema.ts
Added "the-user" as a new BuiltinAgentName type literal and extended corresponding schema enums to support the agent with override configuration.
Agent Implementation
src/agents/the-user.ts, src/agents/index.ts
Introduced full The User Coordinator Agent with TheUserContext interface, dynamic prompt assembly via table builders, delegation workflow logic, prompt metadata, and factory function. Exported publicly via index.
Integration and Model Configuration
src/agents/utils.ts, src/shared/model-requirements.ts
Integrated the-user into built-in agent registry with dedicated creation path, model resolution, and override handling. Added fallback model chain for provider compatibility.

Sequence Diagram

sequenceDiagram
    participant User as User
    participant Coordinator as The User Coordinator
    participant Agents as Specialized Agents<br/>(Prometheus, Hephaestus, etc.)
    
    User->>Coordinator: Send request with category/intent
    Note over Coordinator: Parse request<br/>Determine category
    Coordinator->>Agents: Delegate to specialized agent(s)<br/>based on category & skills
    Agents-->>Coordinator: Agent response
    Coordinator->>Coordinator: Aggregate & format results
    Coordinator-->>User: Return orchestrated response
Loading

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Poem

🐰 A coordinator hops into place,
The User agent shows its grace,
Delegating tasks left and right,
Gathering wisdom, burning bright!
Where agents dance, it leads the way,
Orchestrating code today! 🌟

🚥 Pre-merge checks | ✅ 1 | ❌ 2
❌ Failed checks (2 warnings)
Check name Status Explanation Resolution
Description check ⚠️ Warning The PR description provides a helpful summary of the coordinator agent's purpose and features, though it does not follow the repository's template structure with required sections like Changes, Testing, and Related Issues. Restructure the description to match the template: add a Changes section detailing specific files modified, include Testing section with verification steps (bun run typecheck, bun test), and add Related Issues section if applicable.
Docstring Coverage ⚠️ Warning Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. Write docstrings for the functions missing them to satisfy the coverage threshold.
✅ Passed checks (1 passed)
Check name Status Explanation
Title check ✅ Passed The title 'feat(agents): add the-user coordinator agent' clearly and concisely describes the main change, accurately summarizing the addition of a new coordinator agent.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing touches
  • 📝 Generate docstrings
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch claude/create-user-coordinator-agent-ki6Dg

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Repository owner deleted a comment from github-actions Bot Feb 2, 2026
qwertystars pushed a commit that referenced this pull request Feb 26, 2026
Update all fallback chains to match current model-requirements.ts:
- Librarian: now minimax-m2.5-free -> gemini-flash -> big-pickle (free-tier first)
- Explore: add minimax-m2.5-free as #2 after grok-code-fast-1
- Multimodal Looker: reorder to kimi-first (k2p5 -> kimi-free -> flash -> gpt-5.2)
- Atlas: remove gemini-3-pro, keep kimi k2.5 -> sonnet -> gpt-5.2
- GLM 4.7 -> GLM 5 everywhere
- Add venice provider for grok, opencode provider for glm-5

Add design philosophy section explaining the intelligence hierarchy:
premium models for core agents, free-tier for utility agents, balanced
for orchestrators. Document why utility agents intentionally use cheap
models and why Kimi K2.5 appears as primary for multiple agents.
qwertystars pushed a commit that referenced this pull request Feb 26, 2026
- Create gpt.ts with XML-tagged, principle-driven prompt (Codex plan mode style)
- Add getPrometheusPrompt() routing: GPT models → GPT prompt, others → default
- Promote gpt-5.2 (high) to #2 in prometheus fallback chain
- Follow Atlas GPT variant pattern (isGptModel detection)
qwertystars pushed a commit that referenced this pull request Feb 26, 2026
qwertystars pushed a commit that referenced this pull request Mar 10, 2026
Restructure from 13 scattered XML blocks to 8 dense blocks with 9
named sub-anchors, following OpenAI GPT-5.4 prompting guidance and
Oracle-reviewed context preservation strategy.

Key changes:
- Merge think_first + intent_gate + autonomy into unified <intent>
  with domain_guess classification and <ask_gate> sub-anchor
- Add <execution_loop> as central workflow: EXPLORE -> PLAN -> ROUTE ->
  EXECUTE_OR_SUPERVISE -> VERIFY -> RETRY -> DONE
- Add mandatory manual QA in <verification_loop> (conditional on
  runnable behavior)
- Move <constraints> to position #2 for GPT-5.4 attention pattern
- Add <completeness_contract> as explicit loop exit gate
- Add <output_contract> and <verbosity_controls> per GPT-5.4 guidance
- Add domain_guess (provisional) in intent, finalized in ROUTE after
  exploration -- visual domain always routes to visual-engineering
- Preserve all named sub-anchors: ask_gate, tool_persistence,
  parallel_tools, tool_method, dependency_checks, verification_loop,
  failure_recovery, completeness_contract
- Add skill loading emphasis at intent/route/delegation layers
- Rename EXECUTE to EXECUTE_OR_SUPERVISE to preserve orchestrator
  identity with non-execution exits (answer/ask/challenge)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants