fix(settings): keep LLM Profiles reachable while an ACP agent is active

[VascoSch92]

HUMAN:

Fixing UI-deadlock with onboarding for ACP.

• A human has tested these changes.

AGENT:

Verified against a real locally-running stack, not just unit tests.

Stack — OH_CANVAS_SAFE_BACKEND_PORT=28600 OH_CANVAS_SAFE_AUTOMATION_PORT=28601 OH_CANVAS_SAFE_VITE_PORT=28602 OH_CANVAS_SAFE_STATE_DIR=<tmp> npm run dev:static -- --skip-build --port 28603 (agent-server 1.36.1 + automation + static frontend + ingress), driven with Playwright.

Repro state — completed onboarding through the UI choosing ACP → Claude Code, which leaves exactly the state from the issue:

agent-profiles: {"profiles":[{"id":"b1c0421b…","name":"default","agent_kind":"acp","llm_profile_ref":null}],"active_agent_profile_id":"b1c0421b…"}
llm profiles:   {"profiles":[],"active_profile":null}

Before / after on that identical backend state (only build/ swapped between runs):

	pre-fix	post-fix
sidebar LLM item aria-disabled	true	null (enabled)
visiting /settings/llm lands on	/settings/agents	/settings/llm

Escape path, end to end through the UI — from the dead-locked state:

step 1 — /settings/llm landed on: http://localhost:28603/settings/llm
step 2 — llm profiles now: {"profiles":[{"name":"escape-hatch","model":"anthropic/claude-sonnet-5","api_key_set":true}],"active_profile":"escape-hatch"}
step 3 — llm-selector=1 no-llm-warning=0 save-disabled=false
step 4 — agent-profiles now: […,{"name":"openhands","agent_kind":"openhands","llm_profile_ref":"escape-hatch"}]

Suite — npm run lint (typecheck + eslint + prettier) clean; npm test → 512 files / 3950 tests passed; npm run build succeeded.

---

Why

Onboarding with an ACP agent (e.g. Claude Code) leaves the app with no LLM profile, because useApplyOnboardingAgentProfile only saves an ACP agent profile — ACP owns its own LLM.

/settings/llm was flagged disabledByAcp, so the settings loader redirected it to /settings/agents while an ACP profile was active. But that page manages the LLM profile library, not the active agent's LLM — and creating an OpenHands agent profile requires an existing LLM profile.

The result is a cycle with no UI path out: creating an LLM profile needs a page ACP blocks, and leaving ACP needs an LLM profile.

This has now been reported twice. #1795 (2026-07-14) hit it on the agent-canvas:1.4.0 Docker image; #1913 (2026-07-23) is a fresh customer report of the same lockout with the same code-level analysis. Both land on the same first suggestion — #1795 phrases it as "Allow creating LLM profiles even while an ACP agent is active (the page is only configuring profiles, not the active agent)", which is exactly what this PR does.

Summary

• Drop disabledByAcp from the /settings/llm nav item so the LLM profile library stays reachable (and un-greyed) while an ACP agent is active.
• Condenser and Verification keep their ACP gating — those genuinely have nothing to configure while an external subprocess drives the conversation.
• Update the nav-hook and settings-loader tests to assert the new split, plus a regression test that /settings/llm is not redirected under ACP.

Issue Number

Closes #1913
Closes #1795

How to Test

1. npm ci && npm run build
2. npm run dev:static and open the printed URL.
3. Complete onboarding choosing Claude Code (leave the API-key fields blank).
4. Open Settings → Agent: the active profile is default — ACP (external subprocess), and LLM is now clickable in the left nav (Condenser / Verification stay greyed).
5. Visit /settings/llm directly — it renders instead of bouncing to /settings/agents.
6. Add an LLM profile, then Settings → Agent → Add agent profile with Agent = OpenHands: the LLM profile selector appears and Save is enabled.

Video/Screenshots

Pre-fix — /settings/llm redirected to the Agent page, LLM greyed out:

Post-fix — /settings/llm reachable with the same ACP profile active:

Post-fix — an OpenHands agent profile can now be created:

Type

• Bug fix
• Feature
• Refactor
• Breaking change
• Docs / chore

Notes

This is the minimal alternative both issues propose — it unblocks /settings/llm only, leaving the rest of the ACP gating in place.

#1908 (for #1907) is the fuller cleanup: it removes disabledByAcp and redirectIfAcpActive() entirely. The two overlap on this one nav flag, so whichever lands first should absorb the other. Landing this alone fixes the twice-reported lockout with a 3-line source change; landing #1908 makes this redundant.

Related: #1907, #1908, #1888.

Evidence screenshots are committed under .pr/1913/ so they render inline here — happy to drop that commit before merge.

---

🐳 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:1.37.0-python
Automation	openhands-automation==1.2.0
Commit	5164ff257a1a6cc84061506af152908fb2085290

Pull (multi-arch manifest)

# Multi-arch manifest — Docker automatically pulls the correct architecture
docker pull ghcr.io/openhands/agent-canvas:sha-5164ff2

Run

docker run -it --rm \
  -p 8000:8000 \
  ghcr.io/openhands/agent-canvas:sha-5164ff2

All tags pushed for this build

ghcr.io/openhands/agent-canvas:sha-5164ff2-amd64
ghcr.io/openhands/agent-canvas:vasco-fix-1913-acp-llm-profile-lockout-amd64
ghcr.io/openhands/agent-canvas:pr-1915-amd64
ghcr.io/openhands/agent-canvas:sha-5164ff2-arm64
ghcr.io/openhands/agent-canvas:vasco-fix-1913-acp-llm-profile-lockout-arm64
ghcr.io/openhands/agent-canvas:pr-1915-arm64
ghcr.io/openhands/agent-canvas:sha-5164ff2
ghcr.io/openhands/agent-canvas:vasco-fix-1913-acp-llm-profile-lockout
ghcr.io/openhands/agent-canvas:pr-1915

About Multi-Architecture Support

• Each tag (e.g., sha-5164ff2) 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-5164ff2-amd64) are also available if needed

[vercel]

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

Project	Deployment	Actions	Updated (UTC)
agent-canvas	Ready	Preview, Comment	Jul 23, 2026 3:29pm

[github-actions]

PR Artifacts Notice

This PR contains a .pr/ directory with PR-specific artifacts. This directory will be automatically removed when the PR is approved.

Fork PRs require manual cleanup before merging.

[github-actions]

✅ Mock-LLM Docker E2E Test Results

60/60 passed

Commit: 5164ff25 · Workflow run · Test artifacts

Details

Status	Test	Duration
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 1: setup LLM profile and register automation trajectory	6.6s
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 2: create automation and dispatch run via the UI	33.5s
✅	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	15.5s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › direct slash command from home page triggers skill activation	12.9s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: fresh install with runtime-injected key › reaches the onboarding modal without pre-seeded localStorage	1.4s
✅	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	1.7s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › skips auth screen for returning user with valid stored key	958ms
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › re-prompts when the server rotates its key (stale localStorage)	1.6s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → backend-only › frontend-only connects to a separate backend-only instance	24.2s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → multiple backends › connects to two separate backends and switches between them	22.0s
✅	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	15.4s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › fails with a clear error when the ingress port is occupied	110ms
✅	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	5.9s
✅	conversations/mock-llm-image-upload.spec.ts › mock-LLM image upload › attaching an image embeds it as base64 in the LLM completion call	12.8s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 1: ensure mock LLM profile is configured	6.6s
✅	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 can enable diff view for attached workspace	5.8s
✅	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	7.3s
✅	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 add control 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	12.7s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 4: installed GitHub server can be deleted	5.9s
✅	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)	5.9s
✅	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	4.5s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › keeps the modal open on backdrop click and Escape	1.5s
✅	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	1.0s
✅	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	1.8s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › selected workspace persists after navigating away and returning	2.2s
✅	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	13.3s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 2: reload and verify ACP settings are persisted in UI	5.7s
✅	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	12.7s
✅	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	8.3s
✅	settings/mock-llm-profile-management.spec.ts › same-model profile identity › chat header shows the correct profile when two profiles share the same model	14.5s
✅	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	7.7s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › project skill in workspace/.agents/skills/ triggers on matching keyword	13.0s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › user skill in ~/.openhands/skills/ triggers on matching keyword	12.7s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › deleting a user skill removes it from subsequent conversations	12.7s

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

[github-actions]

✅ Mock-LLM E2E Tests

60/60 passed

Commit: 5164ff25 · Workflow run · Test artifacts

Details

Status	Test	Duration
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 1: setup LLM profile and register automation trajectory	6.6s
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 2: create automation and dispatch run via the UI	28.5s
✅	automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 3: verify automation and run on the automations page	6.3s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › automation card sends the correct slash command to a conversation	15.6s
✅	automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › direct slash command from home page triggers skill activation	13.7s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: fresh install with runtime-injected key › reaches the onboarding modal without pre-seeded localStorage	1.5s
✅	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	1.5s
✅	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	1.9s
✅	backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › skips auth screen for returning user with valid stored key	813ms
✅	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	17.0s
✅	backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → multiple backends › connects to two separate backends and switches between them	21.8s
✅	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	15.4s
✅	backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › fails with a clear error when the ingress port is occupied	109ms
✅	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	6.4s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 2: activate the mock-llm profile and verify settings API	6.3s
✅	conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 3: run a conversation with the mock LLM	7.4s
✅	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	13.7s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 1: ensure mock LLM profile is configured	6.7s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 2: start conversation and attach workspace metadata	12.5s
✅	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	25.3s
✅	files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 4: files tab can enable diff view for attached workspace	6.0s
✅	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	8.3s
✅	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	8.7s
✅	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 add control 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	12.4s
✅	mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 4: installed GitHub server can be deleted	5.9s
✅	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	5.9s
✅	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	5.9s
✅	mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection reports success for valid stored credentials	5.9s
✅	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	4.8s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › keeps the modal open on backdrop click and Escape	1.6s
✅	onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › defaults the LLM setup step to OpenAI GPT-5.5	1.7s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › scopes standalone styles to the agent-server-ui shell	1.1s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › renders critic results on agent messages and finish actions	3.7s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › loads older events when scrolling up	2.0s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › selected workspace persists after navigating away and returning	4.9s
✅	regressions/mock-llm-ui-regressions.spec.ts › UI regressions › cleared sessionStorage yields empty workspace selection	1.2s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 1: configure ACP agent via Settings → Agent UI	13.3s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 2: reload and verify ACP settings are persisted in UI	5.7s
✅	settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 3: start ACP conversation and verify agent reply	7.1s
✅	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	12.7s
✅	settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 2: start conversation, switch profile via /model, verify switch	7.8s
✅	settings/mock-llm-profile-management.spec.ts › active profile deletion + reconciliation › active profile is deletable and reconciliation activates another profile	10.2s
✅	settings/mock-llm-profile-management.spec.ts › same-model profile identity › chat header shows the correct profile when two profiles share the same model	16.5s
✅	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	7.7s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › project skill in workspace/.agents/skills/ triggers on matching keyword	13.8s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › user skill in ~/.openhands/skills/ triggers on matching keyword	13.7s
✅	skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › deleting a user skill removes it from subsequent conversations	14.5s

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