Ethan c4ef94aacf fix(coderd/x/chatd): prevent chat hang when workspace agent is unavailable (#23707)
## Problem

Chats with a persisted `agent_id` binding hang indefinitely when the
workspace is stopped. The stale agent row still exists in the DB, so
`ensureWorkspaceAgent` succeeds, but the dial blocks forever in
`AwaitReachable`. The MCP discovery goroutine used an unbounded context,
so `g2.Wait()` never returned and the LLM never started.

## Fix

Three targeted changes restore the pre-binding behavior where stopped
workspaces degrade gracefully instead of blocking:

1. **`dialWithLazyValidation`**: "no agents in latest build" is now a
terminal fast-fail — the hanging dial is canceled and
`errChatHasNoWorkspaceAgent` returned immediately, instead of falling
through to `waitForOriginalDial`.

2. **Pre-LLM workspace setup**: MCP discovery and instruction
persistence gate on `workspaceAgentIDForConn` before attempting any
dial. MCP discovery is bounded by a 5s timeout and checks the in-memory
tool cache first (using the cheap cached agent from
`ensureWorkspaceAgent`), so the common subsequent-turn path has zero DB
queries.

3. **`persistInstructionFiles`**: tracks whether the workspace
connection succeeded and skips sentinel persistence on failure, so the
next turn retries if the workspace is restarted.

## Scenarios

**Running workspace, subsequent turn (hot path):** MCP cache hit via
in-memory cached agent. Zero DB queries, zero dials. Unchanged from
#23274.

**Stopped workspace, persisted binding (the bug):** MCP cache hit (stale
descriptors, fine — they fail at invocation). Pre-LLM setup completes
instantly. Tool invocation enters `dialWithLazyValidation`, dial fails
or hangs, validation discovers no agents, returns
`errChatHasNoWorkspaceAgent`. Model sees the error and can call
`start_workspace`.

**New chat, running workspace:** `ensureWorkspaceAgent` resolves via
latest-build, persists binding. MCP discovery dials and caches tools.

**New chat, stopped workspace:** `ensureWorkspaceAgent` finds no agents,
returns `errChatHasNoWorkspaceAgent`. Pre-LLM setup skips. LLM starts
with built-in tools only.

**Rebuilt workspace (agent switched):** MCP cache hit with stale agent
(harmless for one turn). Tool invocation dials stale agent, fails fast,
`dialWithLazyValidation` switches to new agent, persists updated
binding.

**Workspace restarted after stop:** No sentinel was persisted during the
stopped turn, so instruction persistence retries. Agent binding switches
to the new agent via `workspaceAgentIDForConn`.

**Transient DB error during validation:** Not
`errChatHasNoWorkspaceAgent`, so `dialWithLazyValidation` falls through
to `waitForOriginalDial` (cannot prove stale). No false positive.

**Tool invocation on stopped workspace:** `getWorkspaceConn` calls
`ensureWorkspaceAgent` (returns stale row), then
`dialWithLazyValidation` validation discovers no agents, returns
`errChatHasNoWorkspaceAgent`, cached state cleared, error returned to
model.
2026-03-27 18:47:39 +11:00
2026-03-25 14:17:56 -04:00
2026-03-25 14:17:56 -04:00
2022-04-04 11:55:06 -05:00

Coder Logo Light Coder Logo Dark

Self-Hosted Cloud Development Environments

Coder Banner Light Coder Banner Dark

Quickstart | Docs | Why Coder | Premium

discord release godoc Go Report Card OpenSSF Best Practices OpenSSF Scorecard license

Coder enables organizations to set up development environments in their public or private cloud infrastructure. Cloud development environments are defined with Terraform, connected through a secure high-speed Wireguard® tunnel, and automatically shut down when not used to save on costs. Coder gives engineering teams the flexibility to use the cloud for workloads most beneficial to them.

  • Define cloud development environments in Terraform
    • EC2 VMs, Kubernetes Pods, Docker Containers, etc.
  • Automatically shutdown idle resources to save on costs
  • Onboard developers in seconds instead of days

Coder Hero Image

Quickstart

The most convenient way to try Coder is to install it on your local machine and experiment with provisioning cloud development environments using Docker (works on Linux, macOS, and Windows).

# First, install Coder
curl -L https://coder.com/install.sh | sh

# Start the Coder server (caches data in ~/.cache/coder)
coder server

# Navigate to http://localhost:3000 to create your initial user,
# create a Docker template and provision a workspace

Install

The easiest way to install Coder is to use our install script for Linux and macOS. For Windows, use the latest ..._installer.exe file from GitHub Releases.

curl -L https://coder.com/install.sh | sh

You can run the install script with --dry-run to see the commands that will be used to install without executing them. Run the install script with --help for additional flags.

See install for additional methods.

Once installed, you can start a production deployment with a single command:

# Automatically sets up an external access URL on *.try.coder.app
coder server

# Requires a PostgreSQL instance (version 13 or higher) and external access URL
coder server --postgres-url <url> --access-url <url>

Use coder --help to get a list of flags and environment variables. Use our install guides for a complete walkthrough.

Documentation

Browse our docs here or visit a specific section below:

  • Templates: Templates are written in Terraform and describe the infrastructure for workspaces
  • Workspaces: Workspaces contain the IDEs, dependencies, and configuration information needed for software development
  • IDEs: Connect your existing editor to a workspace
  • Administration: Learn how to operate Coder
  • Premium: Learn about our paid features built for large teams

Support

Feel free to open an issue if you have questions, run into bugs, or have a feature request.

Join our Discord to provide feedback on in-progress features and chat with the community using Coder!

Integrations

We are always working on new integrations. Please feel free to open an issue and ask for an integration. Contributions are welcome in any official or community repositories.

Official

Community

Contributing

We are always happy to see new contributors to Coder. If you are new to the Coder codebase, we have a guide on how to get started. We'd love to see your contributions!

Hiring

Apply here if you're interested in joining our team.

S
Description
Provision remote development environments via Terraform
Readme AGPL-3.0
928 MiB
Languages
Go 74.9%
TypeScript 23.1%
Shell 0.8%
HCL 0.3%
PLpgSQL 0.3%
Other 0.4%