Coder Agents is a chat interface and API for delegating development work and research to coding agents in your Coder deployment. Developers describe the work they want done, and Coder Agents handles selecting a template, provisioning a workspace, and executing the task.
Administrators configure LLM providers from Admin settings > AI and Coder Agents models from Admin settings > AI > Models. Providers and centrally managed credentials are deployment-wide settings managed by platform teams. Each model belongs to an organization. Each organization has its own model list. Developers…
The Tasks API (/api/v2/tasks) and the Chats API (/api/v2/chats) serve similar goals (programmatic access to AI-powered coding agents) but they differ significantly in architecture, capabilities, and usage patterns.
Run E2E tests in a dev container for isolated, reproducible test execution. Use proactively when asked to run Playwright tests, E2E tests, or when in a worktree. Handles the full Docker container lifecycle automatically.
This document is a reference for implementing a new agent provider in Nimbalyst. It is the architectural counterpart to docs/AIPROVIDERTYPES.md (which is end-user / product oriented) and walks through every seam a new agent has to fit through: session start and resume, prompt handling, transcript output, tool calling…
Status: STUCK. Three approaches tried, none reliably solves the pre-edit race for update-kind filechange items. This doc captures everything learned so the next session can pick up cleanly without re-deriving.
Software architect agent for designing implementation plans. Use this when you need to plan the implementation strategy for a task. Returns step-by-step plans, identifies critical files, and considers architectural trade-offs.
Implementation specialist that writes production code using TDD and commits changes. Use proactively when implementing features, fixing bugs, or writing code for a confirmed plan. Delegates to planner when requirements are unclear or need updating. Hands over to qa when implementation is complete.
Planning specialist that creates structured implementation plans for Jira issues. Use proactively when starting a new task, beginning work on a Jira issue, or when asked to plan a feature. Creates the plan and hands over to the implementation agent.
QA specialist that deeply analyzes code produced by the coder agent. Runs the verification skill, traces code paths, checks logic for gaps, unintended changes, edge cases, and omissions. Use proactively after implementation is complete, when coder says "done", or when asked to review/verify code quality.
Expert code reviewer that uses IDE bridge LSP tools for deep analysis. Reviews code for correctness, security, and maintainability using type information, reference tracking, and call hierarchy analysis. Use proactively after code changes or when reviewing PRs.
Autonomous debugging agent that uses IDE bridge debug and terminal tools. Sets breakpoints, evaluates expressions, inspects runtime state, and fixes bugs. Use when encountering test failures, runtime errors, or unexpected behavior.
Long-term codebase architectural health agent. Identifies God objects, circular dependencies, tightly coupled modules, and modularization opportunities using LSP import tree and call hierarchy analysis. Use for architecture audits, pre-refactor planning, or onboarding deep-dives.