> This PR was authored by Mux on behalf of Mike.
Adds AWS Bedrock ambient credential support to the Agents provider path.
Bedrock providers can now be saved without a stored API key and
authenticated via the standard AWS SDK credential chain on the Coder
server (IAM roles, `AWS_ACCESS_KEY_ID`, etc.). Also fixes missing `Base
URL` forwarding for Bedrock.
## Changes
**Backend runtime** (`coderd/x/chatd/chatprovider/chatprovider.go`):
- New `ProviderAllowsAmbientCredentials(provider)` helper. Currently
returns true only for Bedrock.
- `ModelFromConfig` no longer errors on an empty API key when the
provider is in the ambient-allowed set AND was explicitly resolved via
`ByProvider`. This preserves the policy gate: unresolvable providers
(disabled central key, user-key-required without a user key) still
error.
- `setResolvedProviderAPIKey` internalizes the ambient-credentials
contract via `ProviderAllowsAmbientCredentials`, so a
resolved-but-keyless Bedrock provider is represented as an empty
`ByProvider` entry rather than a post-hoc sentinel patch in the caller.
- `WithAPIKey` is only appended when a token is present.
- `WithBaseURL(baseURL)` is now forwarded for Bedrock (was previously
missing).
**Backend admin API** (`coderd/exp_chats.go`):
- `validateChatProviderCentralAPIKey` exempts Bedrock from requiring a
stored API key when central credentials are enabled.
- AI Gateway separation (`ChatProviderAPIKeysFromDeploymentValues`) is
unchanged. No silent reuse of `CODER_AIBRIDGE_BEDROCK_*` flags.
**Frontend**
(`site/src/pages/AgentsPage/components/ChatModelAdminPanel/*`):
- API Key field is optional for Bedrock when central credentials are
enabled.
- Bedrock-specific descriptions on API Key and Base URL fields
(bearer-token vs ambient modes, `AWS_REGION` guidance).
- Right-aligned "Clear stored token" action switches an existing Bedrock
provider back to ambient mode.
- `hasEffectiveAPIKey` treats Bedrock with central credentials enabled
as configured, so the provider list shows the correct status icon.
- Three new stories: `ProviderFormBedrockAmbientCredentials`,
`ProviderFormBedrockBearerToken`, `ProviderFormBedrockClearBearerToken`.
**Docs** (`docs/ai-coder/agents/models.md`,
`docs/ai-coder/ai-gateway/setup.md`):
- New "Configuring AWS Bedrock" section covering both credential modes,
region resolution, and the Base URL override.
- Explicit note that the `us-east-1` region fallback only applies to
bearer-token mode; ambient credentials require a region from the
standard AWS SDK chain.
- Cross-reference in AI Gateway docs clarifying that
`CODER_AIBRIDGE_BEDROCK_*` flags are a separate configuration path from
Agents.
## Not in scope
- Reusing AI Gateway Bedrock flags as an implicit Agents fallback.
- Per-provider AWS access key, secret, or region fields (would need a
migration and audit-table review).
- IMDS or network-backed credential probes in admin/listing request
paths.
## Related
Dogfood deployment integration:
https://github.com/coder/dogfood/pull/324
Unify the three subagent spawn tools (`spawn_agent`,
`spawn_explore_agent`, `spawn_computer_use_agent`) behind a single
`spawn_subagent` tool keyed by a `subagent_type` discriminant
(`general`, `explore`, `computer_use`). Mirrors the single-entry-point
pattern already used by `task` in mux while keeping `wait_agent`,
`message_agent`, and `close_agent` as separate lifecycle tools.
A new backend subagent definition catalog
(`coderd/x/chatd/subagent_catalog.go`) is the source of truth for tool
description, prompt guidance, availability rules (plan mode,
desktop/Anthropic gating), and child-chat option building.
`spawn_subagent` advertises only the types available in the current
context and validates `subagent_type` server-side; context inheritance
still flows through the existing `createChildSubagentChatWithOptions`
path. `wait_agent`, `message_agent`, and `close_agent` responses now
include a server-derived `subagent_type` so the UI stops inferring
lifecycle state from tool names.
The frontend gets a shared normalization helper
(`site/src/pages/AgentsPage/components/ChatElements/tools/subagentDescriptor.ts`)
that maps either legacy tool names or new `spawn_subagent` args into a
common descriptor (action, variant, icon, fallback copy). Legacy
transcripts still render identically; `Tool.tsx`, `SubagentTool.tsx`,
`ToolLabel.tsx`, `ToolIcon.tsx`, and `messageParsing.ts` now key off the
descriptor instead of hard-coded names. Existing UI copy is preserved
(`Spawning Explore agent...`, `Using the computer...`, computer-use
monitor icon and Open Desktop affordance).
> This PR was opened by Mux working on Mike's behalf.
## Summary
Allow root plan-mode chats to use MCP tools from external servers that
an admin has explicitly approved for plan mode. Workspace MCP and
plan-mode subagents remain blocked.
## Problem
`chatd.go` excluded every MCP tool when `isPlanModeTurn` was true, so
planning had no access to tools like docs search, ticketing, etc.
Lifting that guard wholesale was unsafe: `mcp_server_configs` already
has centralized admin governance, but workspace-local MCP (discovered
from agent `.mcp.json`) does not, and subagents use a narrower trust
boundary.
## Fix
Add an admin-controlled per-server `allow_in_plan_mode` flag (default
`false`) and gate plan-mode MCP access on it.
### Backend / schema
- New migration `000472_mcp_server_allow_in_plan_mode.{up,down}.sql` and
matching fixture update.
- `mcpserverconfigs.sql` + generated code: persist and read the new
column.
- `codersdk/mcp.go`: thread the field through `MCPServerConfig`,
`Create*`, and `Update*` request types.
- `coderd/mcp.go`: validate, persist, and return the flag in
get/list/create/update handlers.
### chatd
- `coderd/x/chatd/chatd.go`: pre-filter selected external MCP configs by
`AllowInPlanMode` before calling `mcpclient.ConnectAll` on plan-mode
root turns. Workspace MCP discovery is skipped entirely on plan-mode
turns.
- Single helper decides whether a tool is available in plan mode, used
both at construction and for active-tool filtering (defense in depth).
Plan-mode subagents, dynamic tools, provider-native tools, computer-use,
and workspace MCP stay unchanged.
- `coderd/x/chatd/prompt.go`: update the root plan-mode overlay text to
match the new boundary.
### UI
- `MCPServerAdminPanel.tsx`: add an explicit toggle ("Allow all tools
from this MCP server in root plan mode") next to the existing governance
controls.
- Regenerated `site/src/api/typesGenerated.ts`.
### Docs
- `docs/ai-coder/agents/architecture.md`: replace the blanket "MCP is
unavailable in plan mode" note with the new root-only, external-only,
admin-approved policy. Explicitly call out that workspace MCP and
plan-mode subagents are still excluded.
### Tests
- Plan-mode visibility (approved vs non-approved external server).
- Plan-mode invocation of an approved external MCP tool.
- End-to-end plan-mode workflow that uses an approved MCP tool and then
reaches `propose_plan`.
- Regressions: workspace MCP still excluded in plan mode; plan-mode
subagents still on the restricted tool boundary; existing tool
allow/deny list filtering still applies.
## Policy precedence
`allow_in_plan_mode` is an **additional** requirement on top of existing
`enabled`, availability, chat-selected / forced server IDs, and tool
allow/deny lists. It approves **all tools on that server** for root plan
mode; a per-tool plan allowlist is deliberately deferred.
## Follow-ups (explicitly out of scope)
- Whether plan-mode subagents should inherit approved external MCP
tools.
- Workspace-local MCP safety model (agent-side `.mcp.json` schema vs. a
coderd-managed workspace MCP config).
## Validation
- `go vet ./coderd/x/chatd/...`
- `go test ./coderd/x/chatd -run 'TestPlan.*|TestMCP.*' -count=1`
- `go test ./coderd/x/chatd -count=1 -timeout 5m` (full chatd suite)
- `make fmt` (no diff)
> Mux opened this PR on Mike's behalf.
Adds two new documentation pages under platform controls for Coder
Agents:
- **Git Providers** (`git-providers.md`) — documents the `API_BASE_URL`
configuration required for self-hosted GitHub Enterprise deployments.
Positions it as an extension of the existing [external
auth](https://coder.com/docs/admin/external-auth) setup to support Coder
Agents features that need richer git host API access: the in-chat diff
viewer and PR Insights.
- **PR Insights** (`pr-insights.md`) — documents the PR analytics
dashboard, requirements for PR data to appear, and troubleshooting.
Links to git-providers for GHE setup.
Also updates the platform controls index and docs manifest.
---
> PR generated with Coder Agents
Add a `chat_client_type` enum (`ui` | `api`) and `client_type` column to
the `chats` table. The column defaults to `api` for new rows so API
callers don't need to set it explicitly. Existing rows are backfilled to
`ui`.
The field flows through `CreateChatRequest`, `chatd.CreateOptions`,
`InsertChat`, and is returned in the `Chat` response via `db2sdk`.
<details>
<summary>Implementation notes (Coder Agents generated)</summary>
### Changes
**Database migration (000469)**
- New enum `chat_client_type` with values `ui`, `api`.
- New `client_type` column, `NOT NULL DEFAULT 'api'`.
- Backfill: `UPDATE chats SET client_type = 'ui'`.
**SQL query** — `InsertChat` now includes `client_type`.
**SDK** — `ChatClientType` type added; `ClientType` field added to both
`CreateChatRequest` (optional, defaults server-side to `api`) and `Chat`
response.
**Handler** — `postChats` maps the request field (defaulting to `api`)
and passes it through `chatd.CreateOptions`.
**Sub-agent** — Child chats inherit their parent's `client_type`.
**db2sdk** — Maps the database value to the SDK type.
### Decision log
- Default is `api` (not `ui`) so existing API integrations get the
correct value without code changes.
- Backfill sets existing rows to `ui` per requirement.
- Child chats inherit `client_type` from parent rather than defaulting.
</details>
> This PR was authored by Mux on behalf of Mike.
## Summary
- add persistent plan mode for chats and the chat-specific plan file
flow
- add structured planning tools such as `ask_user_question` and
`propose_plan`
- keep `write_file` and `edit_files` constrained to the chat-specific
plan file during plan turns
- allow shell exploration in plan mode, including subagents, via
`execute` and `process_output`
- block implementation-oriented, provider-native, MCP, dynamic, and
computer-use tools during plan turns
- update the chat UI, tests, and docs for the new planning flow
Removes the claim that users can fork a chat to explore a different
direction — this is not a supported feature and the reference is
misleading.
---
*PR generated with Coder Agents*
* Removes experiment `web-push`.
* Falls back to NoopWebpusher in case of error
* Checks browser capability in FE
* Adds note to agents getting-started docs regarding webpush without TLS
> 🤖
Fixes https://github.com/coder/internal/issues/1436
* Adds organization_id to chats with backfill (workspace org → user org membership → default org)
* No support yet for ACLs (follow-up issue)
- Cross-org workspace binding rejected (both in `CreateChatRequest` and in `create_workspace` tool
- Adds `OrganizationAutocomplete` to `AgentCreateForm`
- Docs updated with `organization_id` in chats-api.md
> 🤖 Written by a Coder Agent. Reviewed by many humans and many agents.
---------
Co-authored-by: Mathias Fredriksson <mafredri@gmail.com>
Renames the "Security implications" section to "Security posture" and
reframes the intro paragraph. "Implications" reads as a caveat or
warning; the section actually describes built-in structural guarantees
of the control plane architecture.
> PR generated with Coder Agents
Fixes several documentation gaps and inaccuracies in the Coder Agents
docs identified during a deep review against the current product state.
## BYOK (User API Keys)
`models.md` stated *"Developers cannot add their own providers, models,
or API keys"* — this has been incorrect since the provider key policy
system shipped (Apr 2, #23751/#23781).
- Added **Key policy** section documenting the three admin toggles
(`central_api_key_enabled`, `allow_user_api_key`,
`allow_central_api_key_fallback`) with a truth table showing all
resolution outcomes
- Added **User API keys (BYOK)** section covering the developer-facing
key management page, status indicators, selection priority, and key
removal
- Updated `platform-controls/index.md` to reference BYOK instead of
claiming keys are admin-only
## Reasoning effort enum fixes
- **OpenAI**: removed `none` — code accepts `minimal, low, medium, high,
xhigh`
- **OpenRouter**: narrowed to `low, medium, high` per
`ReasoningEffortFromChat` in `chatprovider.go`
## Tool table completeness
- Added `spawn_computer_use_agent`, `read_skill`, `read_skill_file` to
`index.md` tool table
- Added "Workspace extension tools" section to `architecture.md` for
`read_skill`/`read_skill_file`
- Fixed orchestration restriction note to list all 5 gated tools instead
of just `spawn_agent`
- Added conditional availability notes for desktop and skills tools
## Platform controls
Three admin-only settings existed in the Behavior tab with no
documentation:
- **Virtual desktop** — admin toggle, Anthropic + portabledesktop
requirements
- **Workspace autostop fallback** — default TTL for agent workspaces
without template-defined autostop
- **Data retention** — moved `chat-retention.md` into
`platform-controls/` since it's admin-only, fixed nav path
---
> PR generated with Coder Agents
Fixes https://github.com/coder/coder/issues/23910
Adds periodic cleanup of chats and chat files to the dbpurge background
goroutine, with a configurable retention period exposed in the Agent
settings UI.
> 🤖 Written by a Coder Agent. Reviewed by a human.
Needed by #23833
Adds a `chat_file_links` association table to track which files are
associated with each chat.
- `AppendChatFileIDs` query links a file to a chat with deduplication
- `GetChatFileMetadataByIDs` query returns lightweight file metadata by
IDs
- Tool-created files (e.g. `propose_plan`) are linked to the chat after
insert
- User-uploaded files are linked to the chat when the referencing
message is sent
- Single-chat GET endpoint hydrates `files: ChatFileMetadata[]` on the
response
> 🤖 Created by Coder Agents and massaged into shape by a human.
When the `agents` experiment is enabled, new users are automatically
granted the `agents-access` role at creation time so they can use Coder
Agents without manual admin intervention.
- Auto-assigns in `CreateUser()` — covers admin API, OAuth, and OIDC
creation paths
- Skips auto-assign for OIDC users when enterprise site role sync is
enabled (sync overwrites roles on every login; those admins should use
`--oidc-user-role-default` instead)
- CLI `create-admin-user` bypasses `CreateUser()` but creates `owner`
users who already have all permissions
> 🤖 Written by a Coder Agent. Will be reviewed by a human.
Refs #23897
- Rename user-facing "chats" to "Coder Agents" (feature name) or
"conversations" (individual instances)
- Covers UI strings, docs prose, Storybook stories, and aria labels
- API paths, internal code identifiers, and the "Chats API" docs page
name are intentionally left unchanged
- TaskPage / AI Tasks are out of scope
> 🤖 Written by a Coder Agent. Will be reviewed by a human.
Replaces the generic red `ErrorAlert` ("Forbidden.") with a proactive
permission check and friendly info alert when a user lacks the
`agents-access` role.
- Add `createChat` permission check to `permissions.json` using
`owner_id: "me"`
- Handle `"me"` owner substitution in `renderPermissions` (SSR path)
- Pass `canCreateChat` from `useAuthenticated().permissions` into
`AgentCreateForm`
- Show `ChatAccessDeniedAlert` and disable input immediately (no need to
trigger a 403 first)
- Also catch 403 errors as a fallback in case permissions aren't yet
loaded
- Add `ForbiddenNoAgentsRole` Storybook story with `play` assertions
- Add `TestRenderPermissionsResolvesMe` Go test to pin the `"me"`
sentinel substitution
<details><summary>Implementation plan & decision log</summary>
- Uses the existing `permissions.json` + `checkAuthorization` system
rather than a separate API call
- `owner_id: "me"` is resolved to the actor's ID by both the auth-check
API endpoint and the SSR `renderPermissions` function
- Go test uses a real `rbac.StrictCachingAuthorizer` (not a mock) so it
verifies both the sentinel substitution and the RBAC role evaluation
end-to-end
- Alert follows the exact same `Alert` pattern as the 409 usage-limit
block
- Uses `severity="info"` and links to the getting-started docs Step 3
- Textarea is disabled proactively so the user never sees the scary
generic error
</details>
> 🤖 Created by a Coder Agent and will be reviewed by a human.
- Add `chat-access` built-in role granting chat CRUD at User scope
- Exclude `ResourceChat` from member, org member, and org service
account `allPermsExcept` calls
- Allow system, owner, and user-admin to assign the new role
- Migration auto-assigns role to users who have ever created a chat
- Update RBAC test matrix: `memberMe` denied, `chatAccessUser` allowed
**Breaking change**: Members without `chat-access` lose chat creation
ability. Migration covers existing chat creators. Members who have never
created a chat do not get this role automatically applied.
> 🤖 This PR was created by a Coder Agent and reviewed by me.
Fixes factual errors found during a review of all pages under
`/docs/ai-coder/agents/`.
## Tool tables (`index.md`, `architecture.md`)
Both pages had incomplete tool tables. Added:
- `process_output`, `process_list`, `process_signal` — core workspace
tools always registered alongside `execute`, missing from both pages
- `propose_plan` — platform tool (root chats only), missing from both
pages
- `spawn_computer_use_agent` — orchestration tool (conditional), missing
from architecture.md
Also fixed the architecture.md claim that the agent is "restricted to
the tool set defined in this section" — it now mentions skills and MCP
tools with links to the relevant pages.
## Model options (`models.md`)
- **OpenAI / OpenRouter Reasoning Effort**: docs listed `low`, `medium`,
`high` — code has `none`, `minimal`, `low`, `medium`, `high`, `xhigh`.
Fixed both.
- **Removed hidden fields** that never appear in the admin UI:
- Google: Safety Settings (`hidden:"true"`)
- OpenRouter: Provider Order, Allow Fallbacks (parent struct
`hidden:"true"`)
- Vercel: Provider Options (`hidden:"true"`)
---
*PR generated with Coder Agents*
Adds three new documentation pages for major shipped features that had
no docs, and updates the platform controls index to reflect current
state.
## New pages
### Extending Agents (`extending-agents.md`)
Covers two workspace-level extension mechanisms:
- **Skills** — `.agents/skills/<name>/SKILL.md` directory structure,
frontmatter format, auto-discovery, `read_skill`/`read_skill_file`
tools, size limits, lazy loading
- **Workspace MCP tools** — `.mcp.json` format, stdio and HTTP
transports, tool name prefixing, discovery lifecycle and caching
### MCP Servers (`platform-controls/mcp-servers.md`)
Admin MCP server configuration:
- CRUD via **Agents** > **Settings** > **MCP Servers**
- Four auth modes: none, OAuth2 (with auto-discovery), API key, custom
headers
- Availability policies: `force_on`, `default_on`, `default_off`
- Tool governance via allow/deny lists
- Permission model and secret redaction
### Usage & Insights (`platform-controls/usage-insights.md`)
Three admin dashboards:
- **Usage limits** — spend caps with per-user and per-group overrides,
priority hierarchy, enforcement behavior
- **Cost tracking** — per-user rollup with token breakdowns, date
filtering, per-model and per-chat drill-down
## Updated files
- **`platform-controls/index.md`** — Moved MCP servers, usage limits,
and analytics from "Where we are headed" into "What platform teams
control today" with links to the new pages. Removed the tool
customization roadmap section (now covered by MCP servers page).
- **`manifest.json`** — Added nav entries for all three new pages.
## Resulting nav hierarchy
```
Coder Agents
├── Getting Started
├── Early Access
├── Architecture
├── Models
├── Platform Controls
│ ├── Template Optimization
│ ├── MCP Servers ← NEW
│ └── Usage & Insights ← NEW
├── Extending Agents ← NEW
└── Chats API
```
---
*PR generated with Coder Agents*
The tool descriptions pushed agents toward backgrounding anything over
5 seconds, including builds, tests, and installs where you actually
want to wait for the result. This led to unnecessary process_output
round-trips and missed the foreground timeout-to-reattach workflow
entirely.
Reframe background mode as the exception (persistent processes with
no natural exit) and foreground with an appropriate timeout as the
default. Replace "background process" with "tracked process" in
process_output, process_list, and process_signal since they work on
all tracked processes regardless of how they were started.
Addresses five documentation gaps identified from an internal agents
briefing Q&A, specifically around what permissions an agent inherits
from the user:
1. **No privilege escalation** — Added explicit statement that the agent
has the exact same permissions as the user. No escalation, no shared
service account.
2. **Cross-user workspace isolation** — Added statement that agents
cannot access workspaces belonging to other users.
3. **Default-state warning** — Added WARNING callouts that agent
workspaces inherit the user's full network access unless templates
explicitly restrict it.
4. **Tool boundary statement** — Added explicit statement that the agent
cannot act outside its defined tool set and has no direct access to the
Coder API.
5. **Template visibility scoped to user RBAC** — Clarified that template
selection respects the user's role and permissions.
Changes across 3 files:
- `docs/ai-coder/agents/index.md`
- `docs/ai-coder/agents/architecture.md`
- `docs/ai-coder/agents/platform-controls/template-optimization.md`
---
PR generated with Coder Agents
Renames the page title from "Template Routing" to "Template
Optimization" in both the markdown H1 header and the docs manifest
entry.
---
PR generated with Coder Agents
Add a new docs page under /docs/ai-coder/agents/ covering best practices
for creating templates that are discoverable and useful to Coder Agents.
Covers template descriptions, dedicated agent templates, network
boundaries, credential scoping, parameter design, pre-installed tooling,
and prebuilt workspaces for reducing provisioning latency.
<!--
If you have used AI to produce some or all of this PR, please ensure you
have read our [AI Contribution
guidelines](https://coder.com/docs/about/contributing/AI_CONTRIBUTING)
before submitting.
-->
Adds `docs/ai-coder/agents/chat-api.md` — a concise guide for the
experimental `/api/experimental/chats` endpoints.
**What's included:**
- Authentication
- Quick start curl example
- Core workflow (create → stream → follow-up)
- All major endpoints: create, messages, stream, list, get, archive,
interrupt
- File uploads
- Chat status reference
Also marks all Coder Agents child pages as `early access` in
`docs/manifest.json`.
Adds a new **Enable Coder Agents** section to the Early Access doc
explaining how to activate the `agents` experiment flag via
`CODER_EXPERIMENTS` or `--experiments`.
## Changes
### `docs/ai-coder/agents/early-access.md`
- New **Enable Coder Agents** section with env var and CLI flag
examples.
- Note that the `agents` flag is excluded from wildcard (`*`) opt-in.
- Quick-start checklist: dashboard → Admin → configure provider/model →
start chatting.
- Link to GitHub issues for feedback.
### `docs/ai-coder/agents/index.md`
- Updated **Product status** from "internal preview" to "Early Access"
with a link to the early-access page for enablement instructions.
## Summary
- add chat model pricing metadata to the agents admin form and SDK
metadata
- split pricing into its own section and show default pricing as
placeholders
- apply default pricing when admins leave pricing fields blank
## Changes
- Add `"state": ["early access"]` to all child pages under Coder Agents
in `docs/manifest.json` (Architecture, Models, Platform Controls, Early
Access).
- Point the Coder Agents video `<source>` directly at
`raw.githubusercontent.com` instead of the `github.com/blob/` URL with
`?raw=true`.
Adds a new child page at `/docs/ai-coder/agents/early-access` describing
the Coder Agents Early Access, including what it includes, what it does
not include, feature scope, licensing, and how to provide feedback.
This change adds support for image attachments to chat via add button
and clipboard paste. Files are stored in a new `chat_files` table and
referenced by ID in message content. File data is resolved from storage
at LLM dispatch time, keeping the message content column small.
Upload validates MIME types via content type or content sniffing against
an allowlist (png, jpeg, gif, webp). The retrieval endpoint serves files
with immutable caching headers. On the frontend, uploads start eagerly
on attach with a background fetch to pre-warm the browser HTTP cache so
the timeline renders instantly after send.
Adds a docs page under /docs/ai-coder/agents describing our philosophy
on platform team control over agent behavior: admin-level configuration,
zero developer options, enforcement over defaults. Covers what's
available today (providers, models, system prompt, template routing) and
where we're headed (usage analytics, infra-level enforcement, tool
customization).
Cian Johnston