feat: add tool call execution, stop streaming, and redesign tool call UI - #3837
Merged
Pratham-Mishra04 merged 1 commit intoMay 28, 2026
Merged
Conversation
Contributor
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Contributor
Author
This stack of pull requests is managed by Graphite. Learn more about stacking. |
impoiler
force-pushed
the
05-28-feat_enable_tool_execution_in_the_prompt_playground
branch
from
May 28, 2026 11:44
9bbc50a to
6160745
Compare
impoiler
force-pushed
the
05-28-feat_enable_tool_execution_in_the_prompt_playground
branch
from
May 28, 2026 11:59
6160745 to
dc6ef37
Compare
8 tasks
impoiler
changed the title
impoiler
marked this pull request as ready for review
May 28, 2026 12:09
Collaborator
Merge activity
|
Pratham-Mishra04
deleted the
05-28-feat_enable_tool_execution_in_the_prompt_playground
branch
May 28, 2026 12:10
Contributor
Confidence Score: 3/5The Stop button reliably aborts streaming but leaves a stale placeholder message in the conversation on every use. The abort plumbing is correct end-to-end except for one concrete gap:
Important Files Changed
Reviews (1): Last reviewed commit: "feat: enable tool execution in the promp..." | Re-trigger Greptile |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Comment on lines
+622
to
+627
| const handleStopStreaming = useCallback(() => { | ||
| abortRef.current?.abort(); | ||
| abortRef.current = null; | ||
| activeRunRef.current = null; | ||
| setIsStreaming(false); | ||
| }, []); |
Contributor
There was a problem hiding this comment.
handleStopStreaming sets activeRunRef.current = null before the AbortError propagates. When executePrompt later runs its finally block, callbacks.onFinally() calls isActive() → null === Symbol(…) → false, so setIsStreaming(false) is a no-op there — but more importantly, neither onError nor onEmptyResponse is ever invoked for an abort. The placeholder message added by onStreamingStart before the fetch is therefore never removed from the messages array, leaving a stale empty (or partially-streamed) assistant bubble in the conversation every time the user clicks Stop.
To fix, handleStopStreaming should also remove the trailing placeholder, e.g. setMessages(prev => { const last = prev[prev.length - 1]; return (last?.type === MessageType.Response && last.content === '') ? prev.slice(0, -1) : prev; });
Comment on lines
+219
to
+226
| body: JSON.stringify({ | ||
| id: toolCall.id, | ||
| type: toolCall.type, | ||
| index: 0, | ||
| function: { | ||
| name: toolCall.function.name, | ||
| arguments: toolCall.function.arguments, | ||
| }, |
Contributor
There was a problem hiding this comment.
index: 0 may misidentify the tool call
index: 0 is hardcoded regardless of which tool call is being executed. If the backend uses the index field to correlate the request to a specific call in a multi-tool-call assistant turn, this will always point to the first tool call, silently executing the wrong one when the user clicks Execute on the second or third entry in the list. Even if id is the authoritative identifier on the backend today, the intent of index here should be clarified or set to the actual position of this tool call.
Comment on lines
+249
to
+290
| <div className="animate-in fade-in-0 duration-150 motion-reduce:animate-none space-y-2"> | ||
| <div className="flex items-center gap-2"> | ||
| <div> | ||
| <div className="text-xs font-medium text-foreground">Tool result</div> | ||
| <div className="text-[10px] text-muted-foreground"> | ||
| Paste the result returned by this tool call. | ||
| </div> | ||
| </div> | ||
|
|
||
| <Button | ||
| variant="ghost" | ||
| size="sm" | ||
| className="ml-auto h-7 px-2 text-xs text-muted-foreground" | ||
| data-testid="tool-call-response-cancel" | ||
| onClick={() => hideManualEntry(tc.id)} | ||
| disabled={isExecuting} | ||
| > | ||
| Cancel | ||
| </Button> | ||
| </div> | ||
|
|
||
| <Textarea | ||
| autoFocus | ||
| placeholder="Paste tool result..." | ||
| value={responses[tc.id] ?? ""} | ||
| onChange={(e) => handleResponseChange(tc.id, e.target.value)} | ||
| data-testid="tool-call-response-textarea" | ||
| className="min-h-[84px] resize-none rounded-md bg-background font-mono text-xs" | ||
| rows={4} | ||
| disabled={isExecuting} | ||
| /> | ||
|
|
||
| <div className="flex justify-end"> | ||
| <Button | ||
| variant="secondary" | ||
| size="sm" | ||
| className="h-8 active:scale-[0.97] transition-transform" | ||
| data-testid="tool-call-response-submit" | ||
| disabled={!responses[tc.id]?.trim() || isExecuting} | ||
| onClick={() => handleSubmitResponse(tc.id)} | ||
| > | ||
| <Send className="size-3.5" /> |
Contributor
There was a problem hiding this comment.
data-testid elements now gated behind a UI interaction
tool-call-response-textarea and its sibling tool-call-response-submit are now conditionally rendered inside isManualEntryOpen, meaning any test that previously expected to find and interact with those elements directly will now need to first click tool-call-response-add-manually. No Playwright tests in tests/e2e/ currently reference these IDs, so there is no immediate breakage, but the change contracts against the preserve-e2e-testid rule — adding a comment or updating any future test scaffold would prevent silent regressions.
Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!
akshaydeo
pushed a commit
that referenced
this pull request
May 29, 2026
… UI (#3837) ## Summary Adds the ability to directly execute MCP tool calls from the prompt playground, and introduces a **Stop** button to cancel in-flight streaming requests. Previously, users could only submit tool results manually; now they can execute a tool call against the backend and have the result automatically submitted, or fall back to manual entry. ## Changes - Added `executeToolCall` in `executor.ts` that POSTs to `/v1/mcp/tool/execute` and returns the tool result as a string. Header-building logic was extracted into a shared `buildHeaders` helper to avoid duplication between `executePrompt` and `executeToolCall`. - Added `AbortController` support to `executePrompt` so streaming requests can be cancelled. `AbortError` exceptions are silently swallowed since they represent intentional user cancellation. - Added `handleExecuteToolCall` to the prompt context, which calls `executeToolCall` and then pipes the result into the existing `handleSubmitToolResult` flow. - Added `handleStopStreaming` to the prompt context, which aborts the active `AbortController` and resets streaming state. - Replaced the spinner-disabled Run button with a dedicated **Stop** button (destructive styling) that appears while streaming is active. - Redesigned `ToolCallMessageView` to show an "Awaiting tool result" state with two actions: **Execute** (runs the tool call automatically, showing a spinner while in progress) and **Add manually** (opens the existing textarea flow). The card layout, animations, and status badges were also refreshed. ## Type of change - [ ] Bug fix - [x] Feature - [ ] Refactor - [ ] Documentation - [ ] Chore/CI ## Affected areas - [ ] Core (Go) - [ ] Transports (HTTP) - [ ] Providers/Integrations - [ ] Plugins - [x] UI (React) - [ ] Docs ## How to test 1. Open the prompt playground and configure a model that supports tool/function calling. 2. Add a system prompt and user message that triggers a tool call, then click **Run**. 3. Once the assistant responds with a tool call, verify the card shows **Execute** and **Add manually** buttons. 4. Click **Execute** — confirm the spinner appears, the call is sent to `/v1/mcp/tool/execute`, and the result is automatically submitted and the conversation continues. 5. On a separate tool call, click **Add manually**, paste a result, and click **Submit result** — confirm the existing flow still works. 6. Start a streaming run and click **Stop** — confirm streaming halts immediately with no error toast. ```sh cd ui pnpm i pnpm build ``` ## Screenshots/Recordings _Before/after screenshots of the tool call card and the Stop button should be attached._ ## Breaking changes - [ ] Yes - [x] No ## Related issues ## Security considerations `buildHeaders` preserves the existing guard that prevents custom headers from overwriting `Content-Type`, `Authorization`, or `x-bf-api-key-id`, so API key handling is unchanged. The new `executeToolCall` endpoint uses the same auth headers as the rest of the playground. ## Checklist - [ ] I read `docs/contributing/README.md` and followed the guidelines - [ ] I added/updated tests where appropriate - [ ] I updated documentation where needed - [ ] I verified builds succeed (Go and UI) - [ ] I verified the CI pipeline passes locally if applicable
akshaydeo
added a commit
that referenced
this pull request
May 29, 2026
## Summary This PR releases **core v1.5.14**, **framework v1.3.14**, **transports v1.5.6**, and bumps all dependent plugins to their respective `.14` patch versions. It delivers a broad set of new capabilities across MCP authentication, key rotation, OTel metrics, Bedrock/Anthropic compatibility, and UI improvements, alongside a number of targeted bug fixes and refactors. ## Changes - **Direct API Key Header** — Providers can now receive an API key passed directly via a request header (#3817) - **MCP Per-User Auth** — Introduced `MCPCredentialStore` abstraction, per-user MCP credential reconciliation, and a new per-user header auth type with lazy-auth submission flow (#3656, #3702, #3703, #3704, #3705) - **MCP TLS Configuration** — Added configurable TLS (`insecureSkipVerify`, `caCertPem`) for HTTP/SSE MCP client connections (#3779, #3783) - **MCP Sessions Management** — Filter, search, and pagination on the MCP sessions list API and table, plus a `can_reauth` identity gate (#3823, #3824, #3825) - **Key Rotation** — Keys now rotate on 401/402/403 responses; returns `502 upstream_credentials_exhausted` when all keys are permanently exhausted. Added `triggered_rotation` to `KeyAttemptRecord` and tightened `bifrost_key_rotation_events_total` semantics (#3430, #3491) - **OTel Metrics** — Added OTel spec-compatible metrics (backward compatible) with provider cache and semantic cache attributes in metrics export (#3865, #3816) - **Opus 4.8 Support** — System message handling and general compatibility for Opus 4.8 (#3868, #3878) - **Dimension Rankings** — New `GetDimensionRankings` API and dashboard tabs for team, customer, BU, and user rankings (#3766) - **Model Pricing Attributes** — `additional_attributes` field on model pricing rows with management API and UI editor (#3829) - **Prompt Cache Retention** — Added prompt cache retention parameter on responses requests (#3810) - **Tool Call Execution UI** — Inline tool-call execution, stop streaming, bulk execute/submit, and a redesigned tool-call UI (#3837, #3843) - **Sheet Navigation** — Prev/next keyboard navigation and URL state across virtual key, MCP client, and routing rule sheets (#3739, #3740, #3744, #3745) - **Bedrock Tool Name Truncation** — Truncate Bedrock function/tool names to the provider length limit - **Bedrock Guardrails** — Set guardrail config in Bedrock requests built from responses (#3862) - **Anthropic Tool Use** — Default `tool_use` input to `{}` when arguments are absent (#3880) - **Responses Streaming** — Fixed responses stream events (#3838) - **Compat Flow** — Fixed missing parameter parsing on the compat flow (#3881) - **Passthrough API Version** — Set a default API version in passthrough requests as a fallback (#3853) - **Virtual Key Updates** — Avoid overriding optional fields during virtual key update (#3855) - **User-Mode Flows** — Gate user-mode flows on caller `user_id`, skip temp token mint, and unify flow/credential kind filtering for pending flows (#3841, #3859) - **Partial Tool Calls** — Handle partial tool call execution failures and return successful results (#3849) - **URL Query Escaping** — Support escaped characters in URL query parameters (#3826) - **MCP Auth Errors** — Inline banner and retry support for MCP auth-required errors (#3856) - **Renamed Resolvers** — `staticHeadersResolver`/`serverOAuthResolver` renamed to `sharedHeadersResolver`/`sharedOAuthResolver` (#3840) - **Starlark Nested Tool Calls** — Exposed `RunWithPluginPipeline` on `ClientManager` and routed Starlark nested tool calls through the canonical plugin gate (#3794) - **Deferred-Fill OAuth Removed** — Removed deferred-fill user-mode OAuth flow support (#3839) - **Go 1.26.3** — Upgraded toolchain to Go 1.26.3 (#3782) ## Type of change - [x] Bug fix - [x] Feature - [x] Refactor - [ ] Documentation - [x] Chore/CI ## Affected areas - [x] Core (Go) - [x] Transports (HTTP) - [x] Providers/Integrations - [x] Plugins - [x] UI (React) - [ ] Docs ## How to test ```sh # Core/Transports go version # should report go1.26.3 go test ./... # UI cd ui pnpm i || npm i pnpm test || npm test pnpm build || npm run build ``` - Validate MCP per-user auth by configuring a per-user header auth type and confirming credentials are stored and reconciled on virtual key and MCP client changes. - Validate key rotation by triggering a 401/402/403 from an upstream provider and confirming rotation occurs; exhaust all keys and confirm a `502 upstream_credentials_exhausted` is returned. - Validate OTel metrics output includes `provider_cache` and `semantic_cache` attributes. - Validate Bedrock requests with tool names exceeding the provider limit are truncated correctly. - Validate Opus 4.8 system message handling by sending a request with a system message to an Opus 4.8 endpoint. ## Breaking changes - [x] Yes - [ ] No The deferred-fill user-mode OAuth flow has been removed (#3839). Any integrations relying on that flow must migrate to the new per-user credential store approach. The `staticHeadersResolver` and `serverOAuthResolver` identifiers have been renamed to `sharedHeadersResolver` and `sharedOAuthResolver` respectively (#3840); any direct references must be updated. ## Related issues #3817, #3656, #3702, #3703, #3704, #3705, #3779, #3783, #3823, #3824, #3825, #3430, #3491, #3865, #3816, #3868, #3878, #3766, #3829, #3810, #3837, #3843, #3739, #3740, #3744, #3745, #3862, #3880, #3838, #3881, #3853, #3855, #3841, #3859, #3849, #3826, #3856, #3840, #3794, #3839, #3782, #3724, #3814, #3836, #3869, #3886 ## Security considerations - MCP per-user credentials are stored via the new `MCPCredentialStore` abstraction; ensure the backing store is appropriately access-controlled and that credential values are encrypted at rest. - The direct API key header feature passes provider secrets via HTTP headers; ensure TLS is enforced on all ingress paths and that headers are not logged in plaintext. - User-mode flows are now gated on `caller user_id` and temp token minting is skipped where appropriate, reducing the surface for privilege escalation. - TLS configuration for MCP HTTP/SSE connections supports `insecureSkipVerify`; this should only be enabled in controlled environments. ## Checklist - [x] I read `docs/contributing/README.md` and followed the guidelines - [x] I added/updated tests where appropriate - [x] I updated documentation where needed - [x] I verified builds succeed (Go and UI) - [x] I verified the CI pipeline passes locally if applicable
Merged
akshaydeo
added a commit
that referenced
this pull request
May 29, 2026
## ✨ Features - **Direct API Key Header** - Pass a provider API key directly via request header (#3817) - **MCP Per-User Authentication** - New per-user header auth type with credential storage and lazy-auth submission flow (#3703, #3704, #3705) - **MCP TLS Configuration** - Configurable TLS (insecureSkipVerify, caCertPem) for HTTP/SSE MCP client connections (#3779, #3783) - **MCP Sessions Management** - Filter, search, and pagination on the MCP sessions list API and table, plus a can_reauth identity gate (#3823, #3824, #3825) - **Tool Call Execution UI** - Inline tool-call execution, stop streaming, bulk execute/submit, and a redesigned tool-call UI (#3837, #3843) - **Dimension Rankings Dashboard** - New dashboard tabs for team, customer, BU, and user rankings, backed by a GetDimensionRankings API (#3766) - **Model Pricing Attributes** - additional_attributes on model pricing rows with management API and UI editor (#3829) - **Prompt Cache Retention** - Prompt cache retention parameter on responses requests (#3810) - **Opus 4.8 Support** - System message handling and compatibility for Opus 4.8 (#3878, #3868) - **Key Rotation** - Rotate keys on 401/402/403 and return 502 upstream_credentials_exhausted when all keys are permanently dead (#3491) - **OTel Metrics** - OTel spec compatible metrics plus provider and semantic cache attributes in metrics export (#3865, #3816) - **Sheet Navigation** - Prev/next keyboard navigation and URL state across virtual key, MCP client, and routing rule sheets (#3739, #3740, #3744, #3745) - **Go 1.26.3** - Upgraded toolchain to Go 1.26.3 (#3782) ## 🐞 Fixed - **Bedrock Tool Names** - Truncate Bedrock function/tool names to the provider length limit - **Bedrock Guardrails** - Set guardrail config in Bedrock request built from responses (#3862) - **Anthropic Tool Use** - Default Anthropic tool_use input to {} when arguments are absent (#3880) - **Responses Streaming** - Fixed responses stream events (#3838) - **Compat Flow** - Fixed missing parameter parsing on the compat flow (#3881) - **Passthrough API Version** - Set a default API version in passthrough requests as a fallback (#3853) - **Virtual Key Updates** - Avoid overriding optional fields during virtual key update (#3855) - **User-Mode Flows** - Gate user-mode flows on caller user_id, skip temp token mint, and unify flow/credential kind filtering for pending flows (#3841, #3859) - **Partial Tool Calls** - Handle partial tool call execution failures and return successful results (#3849) - **URL Query Escaping** - Support escaped characters in URL query parameters (#3826) - **MCP Auth Errors** - Inline banner and retry support for MCP auth-required errors (#3856) - **JSON Editor Height** - Cap JSON editor max height at 400px in message views (#3842)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds the ability to directly execute MCP tool calls from the prompt playground, and introduces a Stop button to cancel in-flight streaming requests. Previously, users could only submit tool results manually; now they can execute a tool call against the backend and have the result automatically submitted, or fall back to manual entry.
Changes
executeToolCallinexecutor.tsthat POSTs to/v1/mcp/tool/executeand returns the tool result as a string. Header-building logic was extracted into a sharedbuildHeadershelper to avoid duplication betweenexecutePromptandexecuteToolCall.AbortControllersupport toexecutePromptso streaming requests can be cancelled.AbortErrorexceptions are silently swallowed since they represent intentional user cancellation.handleExecuteToolCallto the prompt context, which callsexecuteToolCalland then pipes the result into the existinghandleSubmitToolResultflow.handleStopStreamingto the prompt context, which aborts the activeAbortControllerand resets streaming state.ToolCallMessageViewto show an "Awaiting tool result" state with two actions: Execute (runs the tool call automatically, showing a spinner while in progress) and Add manually (opens the existing textarea flow). The card layout, animations, and status badges were also refreshed.Type of change
Affected areas
How to test
/v1/mcp/tool/execute, and the result is automatically submitted and the conversation continues.cd ui pnpm i pnpm buildScreenshots/Recordings
Before/after screenshots of the tool call card and the Stop button should be attached.
Breaking changes
Related issues
Security considerations
buildHeaderspreserves the existing guard that prevents custom headers from overwritingContent-Type,Authorization, orx-bf-api-key-id, so API key handling is unchanged. The newexecuteToolCallendpoint uses the same auth headers as the rest of the playground.Checklist
docs/contributing/README.mdand followed the guidelines