[codex] Add copy action to conversation error banner by neubig · Pull Request #1432 · OpenHands/agent-canvas

neubig · 2026-06-19T17:22:57Z

HUMAN:

I have tested and this works

A human has tested these changes.

AGENT:

Why

Long conversation error banners can contain details that are difficult to select and copy, especially when the message is collapsed or spans many lines.

Summary

Added an icon-only copy button next to the dismiss control in ErrorMessageBanner.
Copy writes the full resolved error text, including content hidden by the collapsed long-message view.
Shows a temporary copied state after a successful clipboard write.
Added unit coverage for copying long error messages.

Issue Number

N/A

How to Test

npx vitest run __tests__/components/chat/error-message-banner.test.tsx
npm run typecheck
npm run build
Served the PR build through the existing Agent Canvas frontend tunnel and confirmed the frontend, static server, ngrok frontend, and backend settings endpoints returned 200.

Video/Screenshots

See the screenshot in the HUMAN section above.

Type

Notes

The copy action uses the browser Clipboard API and resets its copied indicator after two seconds or when the error text changes.

🐳 Docker images for this PR

• GHCR package: https://github.com/OpenHands/agent-canvas/pkgs/container/agent-canvas

Component	Value
Image	`ghcr.io/openhands/agent-canvas`
Architectures	amd64, arm64
Agent Server	`ghcr.io/openhands/agent-server:1.28.1-python`
Automation	`openhands-automation==1.0.0a10`
Commit	`9c781b7ba7247bc701cf7946633a18fe2f43e2d7`

Pull (multi-arch manifest)

# Multi-arch manifest — Docker automatically pulls the correct architecture
docker pull ghcr.io/openhands/agent-canvas:sha-9c781b7

Run

docker run -it --rm \
  -p 8000:8000 \
  ghcr.io/openhands/agent-canvas:sha-9c781b7

All tags pushed for this build

ghcr.io/openhands/agent-canvas:sha-9c781b7-amd64
ghcr.io/openhands/agent-canvas:codex-copy-conversation-error-amd64
ghcr.io/openhands/agent-canvas:pr-1432-amd64
ghcr.io/openhands/agent-canvas:sha-9c781b7-arm64
ghcr.io/openhands/agent-canvas:codex-copy-conversation-error-arm64
ghcr.io/openhands/agent-canvas:pr-1432-arm64
ghcr.io/openhands/agent-canvas:sha-9c781b7
ghcr.io/openhands/agent-canvas:codex-copy-conversation-error
ghcr.io/openhands/agent-canvas:pr-1432

About Multi-Architecture Support

Each tag (e.g., sha-9c781b7) is a multi-arch manifest supporting both amd64 and arm64
Docker automatically pulls the correct architecture for your platform
Individual architecture tags (e.g., sha-9c781b7-amd64) are also available if needed

vercel · 2026-06-19T17:23:03Z

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
agent-canvas	Ready	Preview, Comment	Jun 19, 2026 5:47pm

github-actions · 2026-06-19T17:25:41Z

✅ Mock-LLM E2E Tests

10/10 passed

Commit: 5a5d2ac3 · Workflow run · Test artifacts

Status	Test	Duration
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 1: create an LLM profile pointing at the mock LLM server	6.5s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 2: activate the mock-llm profile and verify settings API	6.5s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 3: run a conversation with the mock LLM	7.6s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 4: resume conversation from sidebar after navigating away	5.8s
✅	conversations/mock-llm-image-upload.spec.ts › mock-LLM image upload › attaching an image embeds it as base64 in the LLM completion call	13.3s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › scopes standalone styles to the agent-server-ui shell	1.3s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › renders critic results on agent messages and finish actions	1.5s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › loads older events when scrolling up	1.6s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › selected workspace persists after navigating away and returning	2.4s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › cleared sessionStorage yields empty workspace selection	1.3s

_{Posted by the Mock-LLM E2E workflow · results are deterministic (scripted LLM responses)}

all-hands-bot · 2026-06-19T17:37:10Z

✅ Review complete.

This review was performed through OpenHands Cloud Automation. You can log in and view the conversation here.

github-actions · 2026-06-19T17:38:20Z

✅ Mock-LLM Docker E2E Test Results

60/60 passed

Commit: 5a5d2ac3 · Workflow run · Test artifacts

Status	Test	Duration
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 1: setup LLM profile and register automation trajectory	7.3s
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 2: create automation and dispatch run via the UI	32.5s
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 3: verify automation and run on the automations page	6.4s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › automation card sends the correct slash command to a conversation	15.9s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › direct slash command from home page triggers skill activation	13.4s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: fresh install with runtime-injected key › reaches the onboarding modal without pre-seeded localStorage	1.3s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: non-public key rotation › recovers when localStorage has a stale session API key	5.3s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › shows first-run onboarding before the auth screen when no key is configured	1.4s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › rejects an incorrect key with an inline error	1.6s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › allows access after pasting the correct key	1.8s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › skips auth screen for returning user with valid stored key	1.2s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › re-prompts when the server rotates its key (stale localStorage)	1.5s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → backend-only › frontend-only connects to a separate backend-only instance	22.0s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → multiple backends › connects to two separate backends and switches between them	20.8s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: --frontend-only › serves the frontend but returns 503 for backend routes	7.4s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: --backend-only › serves backend APIs but returns 503 for the frontend root	14.1s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › fails with a clear error when the ingress port is occupied	101ms
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › starts successfully on a free port after a conflict	6.0s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 1: create an LLM profile pointing at the mock LLM server	6.3s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 2: activate the mock-llm profile and verify settings API	6.2s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 3: run a conversation with the mock LLM	6.4s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 4: resume conversation from sidebar after navigating away	5.8s
✅	conversations/mock-llm-image-upload.spec.ts › mock-LLM image upload › attaching an image embeds it as base64 in the LLM completion call	13.4s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 1: ensure mock LLM profile is configured	7.4s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 2: start conversation and attach workspace metadata	11.5s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 3: git control bar shows workspace pill and git actions	25.4s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 4: files tab defaults to diff view for attached workspace	5.9s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 5: browser tab shows empty state	6.3s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 6: files tab defaults to file-tree view without attached workspace	7.4s
✅	home/mock-llm-folder-workspace.spec.ts › mock-LLM folder browser → workspace → conversation › step 1: browse to a folder, add it as a workspace, and launch a conversation with the correct working_dir	7.3s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 1: GitHub card is visible on the MCP marketplace page	5.6s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 2: clicking GitHub card opens the install modal with correct fields	5.8s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 3: full install flow — fill PAT, submit, verify installed	13.1s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 4: installed GitHub server can be deleted	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: invalid Slack credentials are blocked with a credential-check error	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: a valid token missing only a scope still installs (missing_scope is not a credential failure)	6.0s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: an older agent server that omits tool_result still installs (compat)	6.0s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection verifies the stored credentials and surfaces a credential failure	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection reports success for valid stored credentials	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › custom (non-catalog) server: Test Connection attaches no verification probe	5.8s
✅	onboarding/mock-llm-onboarding-happy-path.spec.ts › onboarding happy path › completes the full onboarding flow and launches a conversation	3.5s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › keeps the modal open on backdrop click and Escape	1.4s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › defaults the LLM setup step to OpenAI GPT-5.5	1.6s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › scopes standalone styles to the agent-server-ui shell	1.4s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › renders critic results on agent messages and finish actions	1.6s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › loads older events when scrolling up	1.7s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › selected workspace persists after navigating away and returning	2.6s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › cleared sessionStorage yields empty workspace selection	1.1s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 1: configure ACP agent via Settings → Agent UI	13.9s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 2: reload and verify ACP settings are persisted in UI	5.5s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 3: start ACP conversation and verify agent reply	6.7s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 4: resume ACP conversation from sidebar after navigating away	5.8s
✅	settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 1: configure LLM, create switch-target profile, register trajectory	13.4s
✅	settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 2: start conversation, switch profile via /model, verify switch	6.7s
✅	settings/mock-llm-profile-management.spec.ts › active profile deletion + reconciliation › active profile is deletable and reconciliation activates another profile	8.8s
✅	settings/mock-llm-profile-management.spec.ts › same-model profile identity › chat header shows the correct profile when two profiles share the same model	15.3s
✅	settings/mock-llm-profile-management.spec.ts › OpenHands provider hidden base_url preservation › re-saving an OpenHands profile from Basic view preserves hidden base_url	8.0s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › project skill in workspace/.agents/skills/ triggers on matching keyword	13.7s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › user skill in ~/.openhands/skills/ triggers on matching keyword	13.5s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › deleting a user skill removes it from subsequent conversations	13.4s

_{Posted by the Mock-LLM E2E workflow · results are deterministic (scripted LLM responses)}

all-hands-bot

🟡 Acceptable — Clean, focused feature that does exactly what it says. A copy button that exposes the full error text (including collapsed content) is genuinely useful UX and is implemented cleanly. One real improvement opportunity noted inline.

[IMPROVEMENT OPPORTUNITIES]

See inline comment on handleCopy re: missing error handling.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW
Small, isolated UI addition to a single component. No API surface, routing, or shared state changes. Worst case is a silent clipboard failure, which is not a regression.

VERDICT:
✅ Worth merging — Core logic is sound; the improvement suggestion can be addressed as a follow-up or inline.

KEY INSIGHT:
A shared useCopyToClipboard hook would eliminate duplication between this component and the existing CopyableContentWrapper, but that's a refactor that can come separately.

Improve this review? If any feedback above seems incorrect or irrelevant to this repository, you can teach the reviewer to do better:

Add a .agents/skills/custom-codereview-guide.md file to your branch (or edit it if one already exists) with the /codereview trigger and the context the reviewer is missing. See the customization docs for the required frontmatter format.

Re-request a review - the reviewer reads guidelines from the PR branch, so your changes take effect immediately.

When your PR is merged, the guideline file goes through normal code review by repository maintainers.

Resolve with AI? Install the iterate skill in your agent and run /iterate to automatically drive this PR through CI, review, and QA until it's merge-ready.

Was this review helpful? React with 👍 or 👎 to give feedback.

This review was generated by an AI agent (OpenHands) on behalf of the user through OpenHands Automation. View conversation

neubig · 2026-06-19T17:47:15Z

Addressed the review feedback in 9c781b7b:

Wrapped navigator.clipboard.writeText in ErrorMessageBanner with error handling.
On clipboard failure, the UI now shows the existing localized copy-failed error toast instead of producing an unhandled rejection or appearing inert.
Added a unit test covering the rejected clipboard write path.

Local validation passed:

npx vitest run __tests__/components/chat/error-message-banner.test.tsx
npm run typecheck
npm run build

I am re-adding the review-this label now. If the updated PR looks good, please approve it on the next review.

all-hands-bot · 2026-06-19T17:48:15Z

✅ Review complete.

This review was performed through OpenHands Cloud Automation. You can log in and view the conversation here.

github-actions · 2026-06-19T17:49:41Z

✅ Mock-LLM E2E Tests

10/10 passed

Commit: 9c781b7b · Workflow run · Test artifacts

Status	Test	Duration
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 1: create an LLM profile pointing at the mock LLM server	6.4s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 2: activate the mock-llm profile and verify settings API	6.5s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 3: run a conversation with the mock LLM	7.5s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 4: resume conversation from sidebar after navigating away	5.7s
✅	conversations/mock-llm-image-upload.spec.ts › mock-LLM image upload › attaching an image embeds it as base64 in the LLM completion call	13.3s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › scopes standalone styles to the agent-server-ui shell	1.3s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › renders critic results on agent messages and finish actions	1.5s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › loads older events when scrolling up	1.6s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › selected workspace persists after navigating away and returning	2.4s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › cleared sessionStorage yields empty workspace selection	912ms

_{Posted by the Mock-LLM E2E workflow · results are deterministic (scripted LLM responses)}

all-hands-bot

🟢 Good taste — Elegant, minimal, correct.

The implementation is solid across the board:

Correctness: displayTextForLength (the full resolved text, translated if needed) is exactly the right thing to copy — including content hidden by the collapsed line-clamp-3 view. That was the whole point of the feature.
Error handling: handleCopy wraps the async clipboard write in a try/catch and surfaces the failure via the existing displayErrorToast path. Good UX in an error banner context.
State management: The two effects (reset after 2 s, reset when message changes) are straightforward and cover the edge cases cleanly.
Accessibility: aria-label toggles between BUTTON$COPY / BUTTON$COPIED; icons are aria-hidden. Correct.
Tests: Both paths (successful write → copied state, rejected write → toast + stays on Copy) are tested with real clipboard spy calls, not just mocks-of-mocks. The vi.hoisted() pattern for the toast module is the right setup for ESM. afterEach cleanup is correct (restoreAllMocks for the spy, mockClear for the hoisted fn).
Evidence: Screenshot in the PR description confirms the UI change is visible and working.

[RISK ASSESSMENT]

[Overall PR] ⚠️ Risk Assessment: 🟢 LOW
Isolated UI addition to one component. No shared state, no routing, no API changes. Worst case is clipboard API unavailability, which is now handled gracefully with a toast.

VERDICT:
✅ Worth merging — Ready to land as-is.

KEY INSIGHT:
Copying displayTextForLength rather than message ensures i18n-keyed messages are copied in their human-readable translated form, not as raw keys — a detail that's easy to get wrong and is handled correctly here.

This review was generated by an AI agent (OpenHands) on behalf of the user through OpenHands Automation. View conversation

github-actions · 2026-06-19T18:02:02Z

✅ Mock-LLM Docker E2E Test Results

60/60 passed

Commit: 9c781b7b · Workflow run · Test artifacts

Status	Test	Duration
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 1: setup LLM profile and register automation trajectory	7.3s
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 2: create automation and dispatch run via the UI	31.6s
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 3: verify automation and run on the automations page	6.2s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › automation card sends the correct slash command to a conversation	16.4s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › direct slash command from home page triggers skill activation	13.4s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: fresh install with runtime-injected key › reaches the onboarding modal without pre-seeded localStorage	1.3s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: non-public key rotation › recovers when localStorage has a stale session API key	5.3s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › shows first-run onboarding before the auth screen when no key is configured	1.4s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › rejects an incorrect key with an inline error	1.7s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › allows access after pasting the correct key	1.7s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › skips auth screen for returning user with valid stored key	1.2s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › re-prompts when the server rotates its key (stale localStorage)	1.5s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → backend-only › frontend-only connects to a separate backend-only instance	22.9s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → multiple backends › connects to two separate backends and switches between them	21.6s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: --frontend-only › serves the frontend but returns 503 for backend routes	7.3s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: --backend-only › serves backend APIs but returns 503 for the frontend root	14.1s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › fails with a clear error when the ingress port is occupied	112ms
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › starts successfully on a free port after a conflict	6.0s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 1: create an LLM profile pointing at the mock LLM server	6.3s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 2: activate the mock-llm profile and verify settings API	6.2s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 3: run a conversation with the mock LLM	6.3s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 4: resume conversation from sidebar after navigating away	5.7s
✅	conversations/mock-llm-image-upload.spec.ts › mock-LLM image upload › attaching an image embeds it as base64 in the LLM completion call	13.4s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 1: ensure mock LLM profile is configured	7.3s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 2: start conversation and attach workspace metadata	11.4s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 3: git control bar shows workspace pill and git actions	25.3s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 4: files tab defaults to diff view for attached workspace	5.9s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 5: browser tab shows empty state	6.3s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 6: files tab defaults to file-tree view without attached workspace	7.5s
✅	home/mock-llm-folder-workspace.spec.ts › mock-LLM folder browser → workspace → conversation › step 1: browse to a folder, add it as a workspace, and launch a conversation with the correct working_dir	7.3s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 1: GitHub card is visible on the MCP marketplace page	5.6s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 2: clicking GitHub card opens the install modal with correct fields	5.7s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 3: full install flow — fill PAT, submit, verify installed	12.9s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 4: installed GitHub server can be deleted	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: invalid Slack credentials are blocked with a credential-check error	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: a valid token missing only a scope still installs (missing_scope is not a credential failure)	6.0s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: an older agent server that omits tool_result still installs (compat)	6.0s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection verifies the stored credentials and surfaces a credential failure	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection reports success for valid stored credentials	5.8s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › custom (non-catalog) server: Test Connection attaches no verification probe	5.8s
✅	onboarding/mock-llm-onboarding-happy-path.spec.ts › onboarding happy path › completes the full onboarding flow and launches a conversation	3.5s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › keeps the modal open on backdrop click and Escape	1.4s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › defaults the LLM setup step to OpenAI GPT-5.5	1.6s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › scopes standalone styles to the agent-server-ui shell	1.4s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › renders critic results on agent messages and finish actions	1.4s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › loads older events when scrolling up	1.7s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › selected workspace persists after navigating away and returning	2.6s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › cleared sessionStorage yields empty workspace selection	1.4s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 1: configure ACP agent via Settings → Agent UI	13.9s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 2: reload and verify ACP settings are persisted in UI	5.6s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 3: start ACP conversation and verify agent reply	6.8s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 4: resume ACP conversation from sidebar after navigating away	5.8s
✅	settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 1: configure LLM, create switch-target profile, register trajectory	13.4s
✅	settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 2: start conversation, switch profile via /model, verify switch	6.7s
✅	settings/mock-llm-profile-management.spec.ts › active profile deletion + reconciliation › active profile is deletable and reconciliation activates another profile	8.8s
✅	settings/mock-llm-profile-management.spec.ts › same-model profile identity › chat header shows the correct profile when two profiles share the same model	15.2s
✅	settings/mock-llm-profile-management.spec.ts › OpenHands provider hidden base_url preservation › re-saving an OpenHands profile from Basic view preserves hidden base_url	7.5s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › project skill in workspace/.agents/skills/ triggers on matching keyword	13.7s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › user skill in ~/.openhands/skills/ triggers on matching keyword	13.4s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › deleting a user skill removes it from subsequent conversations	13.5s

_{Posted by the Mock-LLM E2E workflow · results are deterministic (scripted LLM responses)}

Add copy action to conversation error banner

5a5d2ac

vercel Bot deployed to Preview June 19, 2026 17:23 View deployment

neubig added the review-this label Jun 19, 2026

neubig marked this pull request as ready for review June 19, 2026 17:36

all-hands-bot reviewed Jun 19, 2026

View reviewed changes

Comment thread src/components/features/chat/error-message-banner.tsx

Handle clipboard copy failures in error banner

9c781b7

neubig added review-this and removed review-this labels Jun 19, 2026

vercel Bot deployed to Preview June 19, 2026 17:47 View deployment

all-hands-bot approved these changes Jun 19, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[codex] Add copy action to conversation error banner#1432

[codex] Add copy action to conversation error banner#1432
neubig wants to merge 2 commits into
mainfrom
codex/copy-conversation-error

neubig commented Jun 19, 2026 •

edited by github-actions Bot

Loading

Uh oh!

vercel Bot commented Jun 19, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jun 19, 2026

Uh oh!

all-hands-bot commented Jun 19, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jun 19, 2026

Uh oh!

all-hands-bot left a comment

Uh oh!

Uh oh!

neubig commented Jun 19, 2026

Uh oh!

all-hands-bot commented Jun 19, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jun 19, 2026

Uh oh!

all-hands-bot left a comment

Uh oh!

github-actions Bot commented Jun 19, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

neubig commented Jun 19, 2026 • edited by github-actions Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Why

Summary

Issue Number

How to Test

Video/Screenshots

Type

Notes

Uh oh!

vercel Bot commented Jun 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Jun 19, 2026

✅ Mock-LLM E2E Tests

Uh oh!

all-hands-bot commented Jun 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Jun 19, 2026

✅ Mock-LLM Docker E2E Test Results

Uh oh!

all-hands-bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

neubig commented Jun 19, 2026

Uh oh!

all-hands-bot commented Jun 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Jun 19, 2026

✅ Mock-LLM E2E Tests

Uh oh!

all-hands-bot left a comment

Choose a reason for hiding this comment

Uh oh!

github-actions Bot commented Jun 19, 2026

✅ Mock-LLM Docker E2E Test Results

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

neubig commented Jun 19, 2026 •

edited by github-actions Bot

Loading

vercel Bot commented Jun 19, 2026 •

edited

Loading

all-hands-bot commented Jun 19, 2026 •

edited

Loading

all-hands-bot commented Jun 19, 2026 •

edited

Loading