## Summary
- add shared MCP annotation metadata to toolsdk tools
- emit MCP tool annotations from both coderd and CLI MCP servers
- cover annotation serialization in toolsdk, coderd MCP e2e, and CLI MCP
tests
## Why
- Coder already exposed MCP tools, but it did not populate MCP tool
annotation hints (`readOnlyHint`, `destructiveHint`, `idempotentHint`,
`openWorldHint`).
- Hosts such as Claude Desktop use those hints to classify and group
tools, so without them Coder tools can get lumped together.
- This change adds a shared annotation source in `toolsdk` and has both
MCP servers emit those hints through `mcp.Tool.Annotations`, avoiding
drift between local and remote MCP implementations.
## Testing
- Tested locally on Cladue Desktop and the tools are categorized
correctly.
<table>
<tr>
<td> Before
<td> After
<tr>
<td> <img width="613" height="183" alt="image"
src="https://github.com/user-attachments/assets/29d2e3fb-53bc-4ea7-bdb3-f10df4ef996b"
/>
<td> <img width="600" height="457" alt="image"
src="https://github.com/user-attachments/assets/cc384036-c9a7-4db9-9400-43ad51920ff5"
/>
</table>
Note: Done using Coder Agents, reviewed and tested by human locally
## Problem
The `edit_files` tool used `strings.ReplaceAll` for exact substring
matches, silently replacing **every** occurrence. When an LLM's search
string wasn't unique in the file, this caused unintended edits. Fuzzy
matches (passes 2 and 3) only replaced the first occurrence, creating
inconsistent behavior. Zero matches were also silently ignored.
## Investigation
Investigated how **coder/mux** and **openai/codex** handle this:
| Tool | Multiple matches | No match | Flag |
|---|---|---|---|
| **coder/mux** `file_edit_replace_string` | Error (default
`replace_count=1`) | Error | `replace_count` (int, default 1, -1=all) |
| **openai/codex** `apply_patch` | Uses first match after cursor
(structural disambiguation via context lines + `@@` markers) | Error |
None (different paradigm) |
| **coder/coder** `edit_files` (before) | Exact: replaces all. Fuzzy:
replaces first. | Silent success | None |
## Solution
Adopted the mux approach (error on ambiguity) with a simpler
`replace_all: bool` instead of `replace_count: int`:
- **Default (`replace_all: false`)**: search string must match exactly
once. Multiple matches → error with guidance: *"search string matches N
occurrences. Include more surrounding context to make the match unique,
or set replace_all to true"*
- **`replace_all: true`**: replaces all occurrences (opt-in for
intentional bulk operations like variable renames)
- **Zero matches**: now returns an error instead of silently succeeding
Chose `bool` over `int` count because:
1. LLMs are bad at counting occurrences
2. The real intent is binary (one specific spot vs. all occurrences)
3. Simpler error recovery loop for the LLM
## Changes
| File | Change |
|---|---|
| `codersdk/workspacesdk/agentconn.go` | Add `ReplaceAll bool` to
`FileEdit` struct |
| `agent/agentfiles/files.go` | Count matches before replacing; error if
>1 and not opted in; error on zero matches; add `countLineMatches`
helper |
| `codersdk/toolsdk/toolsdk.go` | Expose `replace_all` in tool schema
with description |
| `agent/agentfiles/files_test.go` | Update existing tests, add
`EditEditAmbiguous`, `EditEditReplaceAll`, `NoMatchErrors`,
`AmbiguousExactMatch`, `ReplaceAllExact` |
When AgentAPI is configured, `WithTaskReporter` unconditionally
overrides all self-reported states to `working`. The intent was to
distrust the agent's `idle` and rely on the screen watcher, but the
override also blocks `failure` and `complete`, which only the agent can
produce (the screen watcher only knows `running`/`stable`). Tasks get
stuck as `working` or `null` forever.
Now only `idle` is overridden to `working`; `failure`, `complete`, and
`working` pass through as-is.
Also:
- Remove misplaced unconditional `"Failed to watch screen events"` log
that fired on every startup
- Add SSE reconnection with exponential backoff (1s-30s) in
`startWatcher` so it recovers from dropped connections instead of dying
silently
- Add `complete` to the `coder_report_task` tool enum, which the
`coder/claude-code` registry module already instructs agents to use but
was missing from the schema
Refs coder/internal#1350
Fixes all our Go file imports to match the preferred spec that we've _mostly_ been using. For example:
```
import (
"context"
"time"
"github.com/prometheus/client_golang/prometheus"
"golang.org/x/xerrors"
"gopkg.in/natefinch/lumberjack.v2"
"cdr.dev/slog/v3"
"github.com/coder/coder/v2/codersdk/agentsdk"
"github.com/coder/serpent"
)
```
3 groups: standard library, 3rd partly libs, Coder libs.
This PR makes the change across the codebase. The PR in the stack above modifies our formatting to maintain this state of affairs, and is a separate PR so it's possible to review that one in detail.
I have been experimenting (via blink) and these seem to have made the
LLM behave more intelligently and consistently when it comes to creating
workspaces and manipulating files.
Partially addresses https://github.com/coder/internal/issues/1047
The input schemas of `coder_workspace_edit_file` and
`coder_workspace_edit_files` were violating the JSON Schemas of both
Anthropic and OpenAI.
Follow-up: we should add a test to ensure future compatibility with
these specs.
Signed-off-by: Danny Kopping <danny@coder.com>
Follows similarly to the bash tool (and some code to connect to an agent
was extracted from it).
There are two main parts: a new agent endpoint, and then a new MCP tool
that consumes that endpoint.
This pull request addresses a bug related to a nil pointer dereference
in the task reporting functionality.
### Bug Fixes and Error Handling:
* Updated `RegisterTools` in `mcp.go` to skip registering the
`ReportTask` tool in the remote MCP context when a task reporter is not
configured, preventing potential nil pointer dereference panics.
* Added a check in `toolsdk.go` to ensure task reporting dependencies
are available before invoking the reporter, returning an appropriate
error if not.
### Test Coverage:
* Added `TestReportTaskNilPointerDeref` in `toolsdk_test.go` to verify
that the system does not panic when task reporting dependencies are
missing and instead returns a clear error message.
* Added `TestReportTaskWithReporter` in `toolsdk_test.go` to validate
correct behavior when a task reporter is configured, ensuring the
handler processes the request as expected.
Signed-off-by: Thomas Kosiewski <tk@coder.com>
- Refactors the bash tool to use `io.Discard` instead of nil to avoid panics.
- Enhances panic recovery in `codersdk/toolsdk/toolsdk.go` by adding stack trace information in development builds. When a panic occurs in a tool handler:
- In development builds: The error includes the full stack trace for easier debugging
- In production builds: A simpler error message is shown without the stack trace
# Add SSH Command Execution Tool for Coder Workspaces
This PR adds a new AI tool `coder_workspace_ssh_exec` that allows executing commands in Coder workspaces via SSH. The tool provides functionality similar to the `coder ssh <workspace> <command>` CLI command.
Key features:
- Executes commands in workspaces via SSH and returns the output and exit code
- Automatically starts workspaces if they're stopped
- Waits for the agent to be ready before executing commands
- Trims leading and trailing whitespace from command output
- Supports various workspace identifier formats:
- `workspace` (uses current user)
- `owner/workspace`
- `owner--workspace`
- `workspace.agent` (specific agent)
- `owner/workspace.agent`
The implementation includes:
- A new tool definition with schema and handler
- Helper functions for workspace and agent discovery
- Workspace name normalization to handle different input formats
- Comprehensive test coverage including integration tests
This tool enables AI assistants to execute commands in user workspaces, making it possible to automate tasks and provide more interactive assistance.
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
* **New Features**
* Introduced the ability to execute bash commands inside a Coder workspace via SSH, supporting multiple workspace identification formats.
* **Tests**
* Added comprehensive unit and integration tests for executing bash commands in workspaces, including input validation, output handling, and error scenarios.
* **Chores**
* Registered the new bash execution tool in the global tools list.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
# Add MCP HTTP server with streamable transport support
- Add MCP HTTP server with streamable transport support
- Integrate with existing toolsdk for Coder workspace operations
- Add comprehensive E2E tests with OAuth2 bearer token support
- Register MCP endpoint at /api/experimental/mcp/http with authentication
- Support RFC 6750 Bearer token authentication for MCP clients
Change-Id: Ib9024569ae452729908797c42155006aa04330af
Signed-off-by: Thomas Kosiewski <tk@coder.com>
"Idle" is more accurate than "complete" since:
1. AgentAPI only knows if the screen is active; it has no way of knowing
if the task is complete.
2. The LLM might be done with its current prompt, but that does not mean
the task is complete either (it likely needs refinement).
The "complete" state will be reserved for future definition.
Additionally, in the case where the screen goes idle but the LLM never
reported a status update, we can get an idle icon without a message, and
it looks kinda janky in the UI so if there is no message I display the
state text.
Closes https://github.com/coder/internal/issues/699
This is meant to complement the existing task reporter since the LLM
does not call it reliably.
It also includes refactoring to use the common agent flags/env vars.
Part of #17649
---
# Allow MCP server to run without authentication
This PR enhances the MCP server to operate without requiring authentication, making it more flexible for environments where authentication isn't available or necessary. Key changes:
- Replaced `InitClient` with `TryInitClient` to allow the MCP server to start without credentials
- Added graceful handling when URL or authentication is missing
- Made authentication status visible in server logs
- Added logic to skip user-dependent tools when no authenticated user is present
- Made the `coder_report_task` tool available with just an agent token (no user token required)
- Added comprehensive tests to verify operation without authentication
These changes allow the MCP server to function in more environments while still using authentication when available, improving flexibility for CI/CD and other automated environments.
* Refactors toolsdk.Tools to remove opaque `map[string]any` argument in
favour of typed args structs.
* Refactors toolsdk.Tools to remove opaque passing of dependencies via
`context.Context` in favour of a tool dependencies struct.
* Adds panic recovery and clean context middleware to all tools.
* Adds `GenericTool` implementation to allow keeping `toolsdk.All` with
uniform type signature while maintaining type information in handlers.
* Adds stricter checks to `patchWorkspaceAgentAppStatus` handler.
https://github.com/coder/coder/pull/17163 introduced the
`workspace_app_statuses` table. Two of these fields
(`needs_user_attention`, `icon`) turned out to be surplus to
requirements.
- Removes columns `needs_user_attention` and `icon` from
`workspace_app_statuses`
- Marks the corresponding fields of `codersdk.WorkspaceAppStatus` as
deprecated.
Fixes two issues with the MCP server:
- Ensures we have a non-null schema, as the following schema was making
claude-code unhappy:
```
"inputSchema": { "type": "object", "properties": null },
```
- Skip adding the coder_report_task tool if an agent client is not
available. Otherwise the agent may try to report tasks and get confused.
- Refactors existing `mcp` package to use `kylecarbs/aisdk-go` and moves
to `codersdk/toolsdk` package.
- Updates existing MCP server implementation to use `codersdk/toolsdk`
Co-authored-by: Kyle Carberry <kyle@coder.com>
Atif Ali