PowerShell's echo aliases to Write-Output, which rejects -e as
an ambiguous parameter and exits 1. Use plain echo with spaces
instead. Remove the Windows t.Skip and TestMain exception.
TestMain untested-tools check now only fails on full-suite runs.
Filtered runs (e.g. -run TestTools) warn instead.
Closes CODAGT-518
Previously, the `CreateWorkspaceBuild` toolsdk tests only exercised a
start where the workspace's prior template version was also the
template's active version, so they did not prove that a plain start
keeps using the previously built version.
Replace that tautological coverage with an isolated fixture that
advances the template's active version and asserts a start without
`TemplateVersionID` still reuses the prior build's version.
The chat tools (`read_template`, `create_workspace`) did not surface or
respect template version presets. Presets were invisible to the LLM and
preset parameter defaults were never applied at workspace creation. The
`toolsdk` MCP surface had the same gap (ref #24695, now subsumed here).
## What this changes
- **`read_template`** returns presets with `id`, `name`, `default`,
`description`, `icon`, `parameters`, and `desired_prebuild_instances`
(when set), so the LLM can pick the right preset and prefer
prebuilt-backed ones.
- **`create_workspace`** accepts a `preset_id`. The wsbuilder applies
preset parameter defaults and may claim a prebuilt workspace.
- **`start_workspace`** does *not* accept a preset. Presets are a
creation-time choice; subsequent starts use the workspace's existing
version and parameters. Users who need a specific preset or version on
an existing chat can create the workspace out-of-band (CLI / UI / API)
with the desired configuration and attach the chat to it.
- **`toolsdk`** gains `GetTemplate` (with presets including
`desired_prebuild_instances`), preset support on `CreateWorkspace`, and
preset + `rich_parameters` support on `CreateWorkspaceBuild`. The
`template_version_preset_id` description warns about preset/version
affinity.
> 🤖 Generated with [Coder Agents](https://coder.com/agents) and reviewed by a human.
Co-authored-by: Max schwenk <maschwenk@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`namedWorkspace` in `cli/root.go` parsed workspace identifiers with
`uuid.Parse` first and returned immediately on success, even when no
workspace had that UUID as its actual ID. This caused 404 errors for any
workspace whose name was a valid 32-char hex string (dashless UUID).
- Add `codersdk.ResolveWorkspace`: tries UUID lookup first, falls back
to name lookup on 404. `NameValid` guard skips the fallback for standard
dashed UUIDs (36 chars > 32-char name limit).
- Export `codersdk.SplitWorkspaceIdentifier`, replacing the duplicate
`splitNamedWorkspace` in `cli/root.go` (uses `strings.Cut`).
- Delete `namedWorkspace` from `cli/root.go`; all 28 call sites now use
`client.ResolveWorkspace` directly.
- Delete `namedWorkspace` and `splitNameAndOwner` from
`codersdk/toolsdk/bash.go`; inline `client.ResolveWorkspace`.
- Simplify `GetWorkspace` tool handler to a single `ResolveWorkspace`
call.
- Unit tests via httptest mock cover UUID, name, owner/name, UUID-like
fallback, not-found, server error, transport error, and invalid
identifier paths.
- Integration tests in `cli/show_test.go` and `codersdk/toolsdk` for
workspaces with UUID-like names.
> Generated with Coder Agents
## Problem
Coderd can expose an MCP server at `/api/experimental/mcp/http` (we have
this enabled on dogfood). Its workspace tools dialed agents through a
per-call client-side tailnet stack. Every tool call re-created a
WireGuard device, netstack, magicsock + UDP sockets, DERP connection,
coordinator websocket, and their goroutines — in a process that already
runs a long-lived shared tailnet. The duplicate stacks drove up resource
usage under load.
## Fix
Route this server's tool calls through the existing shared tailnet, so
none of those transports are reconstructed per call. Closing an
`AgentConn` now releases a tunnel reference instead of tearing down a
transport.
## Potential follow-up
`coder exp mcp server` still builds a fresh tailnet per call. It pays
per-call latency and causes coordinator/DERP churn. A shared CLI tailnet
is more involved — unlike coderd, the CLI has no existing shared tailnet
to reuse, so it would need a new long-lived client-side tailnet with
reconnect, sleep/wake, and idle-destination handling. There's less
motivation to optimize this, given the client-side MCP does not compete
for resources with coderd.
Closes CODAGT-199
> Generated by mux, but reviewed by a human
Fixes three classes of edit_files bugs and adds structured per-file
diff output for tool callers:
- New IncludeDiff flag on FileEditRequest; when set, the agent
returns FileEditResponse.Files[]{Path, Diff} with unified diffs
computed via go-udiff v0.4.1 Lines + ToUnified (not Unified,
which calls log.Fatalf on internal error).
- Fuzzy match comparators split each line into leading whitespace,
body, trailing whitespace, and ending. The splice substitutes at
each position: on agreement between search and replace the file's
bytes win; on disagreement the replacement's bytes are spliced
verbatim. Carve-outs for empty-body lines, multi-line EOF splices,
and level-aware indent translation for inserted lines.
- Indent-unit detection (GCD for spaces, tab-priority) lets a 4sp
LLM search insert correctly into tab or 2sp files. Falls back to
the previous cLead-inheritance path when units can't be detected
cleanly.
- Empty search is rejected with "search string must not be empty".
- Duplicate file paths in one request are rejected; symlink aliases
resolved via api.resolvePath before the dedup check.
- Frontend EditFilesRenderer consumes the structured files array by
explicit path (no label munging) with per-file synthetic fallback
for older agents or mismatched paths. On error, no diff is
rendered so the synthetic fallback doesn't misrepresent a
rejected edit as applied.
Breaking change: AgentConn.EditFiles changes from (ctx, req) error
to (ctx, req) (FileEditResponse, error) in codersdk/workspacesdk.
Source-breaking for external Go consumers; no compat shim per plan
owner.
Out of scope (tracked in CODAGT-214): level-aware indent for
middle-substituted splice lines. Locked in
TestEditFiles_FuzzyIndent_InsertionLevelAware's Lock_* cases plus
TestEditFiles_ReplaceAll_FuzzyIndentGap.
## 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.
This removes the deprecated AITaskPromptParameterName constant and all
backward compatibility code that was added for v2.28.
- Remove AITaskPromptParameterName constant from codersdk/aitasks.go
- Remove backward compatibility code in coderd/aitasks.go that populated
the "AI Prompt" parameter for templates that defined it
- Remove the backward compatibility test (OK AIPromptBackCompat)
- Update dbfake to no longer set the AI Prompt parameter
- Remove AITaskPromptParameterName from frontend TypeScript types
- Remove preset prompt read-only feature from TaskPrompt component
- Update docs to reflect that pre-2.28 definition is no longer supported
Task prompts are now exclusively stored in the tasks.prompt database
column, as introduced in the migration that added the tasks table.
Provisioner steps broken into smaller granular actions.
Changes:
- `ExtractArchive` moved to `init` request (was in `configure`)
- Writing `tfstate` moved to `plan` (was in `configure`)
- Moved most plan/apply outputs to `GraphComplete`
Create task was still mentioning magic prompt parameter when checking
template task validity. This change updates it to only mention validity
of `coder_ai_task` resource.
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
Hopefully fixes https://github.com/coder/internal/issues/993
```
file path must be absolute: "/test/some/path"
```
Not sure if this is the right fix though, since I am not sure how this
only flakes rather than always failing. It looks like starting with `/`
should not be considered absolute in Windows, but then how did it ever
pass at all?
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.
Refactors Agent instance identity to be a SessionTokenProvider.
Refactors the CLI to create Agent clients via a centralized function, rather than add-hoc via individual command handlers and their flags.
This allows commands besides `coder agent`, but which still use the agent identity, to support instance identity authentication.
Fixes#19111 by unifying all API requests to go thru the SessionTokenProvider for auth credentials.
Fixes flakes on the nightly-gauntlet like:
https://github.com/coder/coder/actions/runs/16955654896
since there's no `bash` on windows...
```
=== Failed
=== FAIL: codersdk/toolsdk (0.00s)
PASS
The following tools were not tested:
- coder_workspace_bash
Please ensure that all tools are tested using testTool().
If you just added a new tool, please add a test for it.
NOTE: if you just ran an individual test, this is expected.
FAIL github.com/coder/coder/v2/codersdk/toolsdk 4.185s
```
Adds Windows compatibility to toolsdk tests
This PR adds Windows compatibility to the toolsdk tests by:
1. Adding build constraints to exclude bash_test.go from running on
Windows
2. Skipping the WorkspaceSSHExec test on Windows platforms with a clear
message
These changes ensure tests run properly across all supported platforms.
Related to https://github.com/coder/internal/issues/798
Signed-off-by: Thomas Kosiewski <tk@coder.com>
# Add timeout support to workspace bash tool
This PR adds a timeout feature to the workspace bash tool, allowing
users to specify a maximum execution time for commands. Key changes
include:
- Added a `timeout_ms` parameter to control command execution time
(defaults to 60 seconds, with a maximum of 5 minutes)
- Implemented a new `executeCommandWithTimeout` function that properly
handles command timeouts
- Added proper output capturing during timeout scenarios, returning all
output collected before the timeout
- Updated documentation to explain the timeout feature and provide usage
examples
- Added comprehensive tests for the timeout functionality, including
integration tests
When a command times out, the tool now returns all captured output up to
that point along with a cancellation message, making it clear to users
what happened.
Signed-off-by: Thomas Kosiewski <tk@coder.com>
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 -->
Closes#17791
This PR adds ability to cancel workspace builds that are in "pending"
status.
Breaking changes:
- CancelWorkspaceBuild method in codersdk now accepts an optional
request parameter
API:
- Added `expect_status` query parameter to the cancel workspace build
endpoint
- This parameter ensures the job hasn't changed state before canceling
- API returns `412 Precondition Failed` if the job is not in the
expected status
- Valid values: `running` or `pending`
- Wrapped the entire cancel method in a database transaction
UI:
- Added confirmation dialog to the `Cancel` button, since it's a
destructive operation
- Enabled cancel action for pending workspaces (`expect_status=pending`
is sent if workspace is in pending status)
---------
Co-authored-by: Dean Sheather <dean@deansheather.com>
# 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.
Mathias Fredriksson