Repository navigation
Description
Operating System
Originally reported on macOS. Independently reproduced on Ubuntu 24.04.4 LTS x86_64.
Installation Method
npm (npx @openhands/agent-canvas or npm install -g @openhands/agent-canvas). The independent reproduction used the supported local dev:static stack from current main.
Versions reproduced
- OpenHands / Agent Canvas main:
f26d734a848297d8dcf460b0bb739174e76511f0(1.16.0) openhands-agent-server:1.44.1openhands-automation:1.9.1- Claude Code:
2.1.251, authenticated Claude subscription - ACP adapter:
npx -y @agentclientprotocol/[email protected] - ACP model:
opus[1m]
Bug Description
Agent Canvas shows the built-in openhands-automation skill as enabled, but its instructions do not reach a newly created Claude Code ACP session. Claude therefore cannot activate or follow the enabled skill unless it independently reconstructs the workflow from runtime API discovery or the filesystem.
Steps to Reproduce
-
Start Agent Canvas with fresh isolated state using
npm run dev:static, then choose Claude Code through the built-in ACP preset. -
Confirm
openhands-automationis in Canvas's enabled-skills setting. -
Install a prompt-preset automation named Code Review Automation.
-
Start a new Claude Code ACP conversation and ask:
Use the built-in openhands-automation skill that Agent Canvas enabled for this session. Without searching the filesystem or application source code, first state whether those skill instructions were provided to you and name their first top-level heading. Then use those provided instructions to change my installed Code Review Automation schedule from Mondays at 09:00 UTC to Tuesdays at 09:00 UTC. Do not infer or reconstruct the skill from API discovery; I need to verify the enabled built-in skill itself reached this Claude Code ACP session.
-
Inspect the browser's
POST /api/conversations, the resolved agent-server conversation, and Claude's response.
Actual Behavior
Conversation 5967e61e-bf15-4732-962a-ce5a82329a2f completed through the real authenticated Claude Code ACP subprocess. Claude responded:
No — the
openhands-automationskill instructions were not provided to this session.I can't name its first top-level heading, because I never received the content. ... There is no OpenHands automation skill among them, and
Skillonly accepts names from that list, so I have no way to load it.
Claude refused the requested schedule change because API reconstruction and filesystem/source inspection were explicitly excluded. Direct control trials showed Claude can modify the same installed automation by discovering <RUNTIME_SERVICES> and the API, so credentials and automation-service access are not the blocker.
Boundary evidence and implementation target
- Canvas persisted
openhands-automationinmisc_settings.app_preferences.enabled_skills, with an empty disabled list. - The frontend conversation-start request contained
agent_profile_idbut no inlineagent_contextor skills. - The resolved ACP conversation contained
agent_context.skills=[],load_public_skills=false,load_user_skills=false, andload_project_skills=false. - The subprocess was the expected Claude preset:
npx -y @agentclientprotocol/[email protected]. - Claude was authenticated and produced a completed response, ruling out missing credentials/environment.
The bounded implementation target is the Agent Canvas → Claude Code ACP session/profile bridge: project the currently enabled Canvas skill instructions into each new Claude ACP session, while respecting the disabled-skills setting. This issue is not requesting a generalized change for every ACP provider.
Expected Behavior
An enabled openhands-automation skill is available to a new Claude Code ACP session, activates for an explicit automation request, and guides the requested change without requiring a filesystem hint or independent API reconstruction.
Acceptance Criteria
- Enabled
openhands-automationinstructions reach a new Claude Code ACP session and are followed for an explicit automation request without a filesystem hint. - Disabling
openhands-automationprevents those instructions from being exposed to a new Claude Code ACP session. - An automated regression test crosses the Claude Code ACP boundary rather than only asserting the frontend conversation-start payload.

Activity
github-actions commentedon Aug 25, 2026
✅
ready-for-devlabel appliedThis issue meets the readiness criteria and is ready for contribution.
A contributor can now open a PR that links this issue (
Fixes #<number>).This is an automated check — no AI was used to generate this comment.
neubig commentedon Aug 29, 2026
Current-main isolated reproduction is now complete. I updated the issue body with the exact environment, completed Claude ACP failure, boundary evidence, screenshot, bounded implementation target, and behavior-focused acceptance criteria; the repository readiness checker passes and
ready-for-devis applied.On OpenHands
f26d734a848297d8dcf460b0bb739174e76511f0/ Canvas1.16.0with agent-server1.44.1, automation1.9.1, Claude Code2.1.251, and@agentclientprotocol/[email protected], Canvas hadopenhands-automationenabled. A new authenticated Claude ACP session was explicitly asked to use that provided skill and change the installed Code Review Automation schedule without filesystem/source inspection or API reconstruction. Claude completed the turn but said: “theopenhands-automationskill instructions were not provided to this session” and refused the change.The captured frontend request sent only
agent_profile_id; the resolved ACP conversation hadagent_context.skills=[]and all skill-loading flags false. This locates the loss at the Agent Canvas → Claude Code ACP session/profile bridge, before Claude could select the skill. Credentials and automation access were ruled out by authenticated control trials in which Claude successfully changed the same automation through runtime API discovery.ameyypawar commentedon Sep 2, 2026
The
skills=[]in the boundary evidence looks like a consequence of the profile-launch path rather than skills projection being absent. Canvas does buildagent_contextwith the enabled/disabled skill lists —buildAgentContextinagent-server-adapter.ts, which setsskills,disabled_skillsandload_public_skills: false. Butagent_profile_idandagent_settingsare mutually exclusive on the start request, so a launch from an agent profile, which is what the ACP preset uses, carries noagent_contextat all.Worth noting the npm client isn't the constraint:
agent_launch_additionsis already typed on the start request in the pinned@openhands/typescript-client1.39.0, and this repo already casts to send a field the generated client doesn't type (from_event_id). What's missing is an agent-server that acceptsskills_append.One process note: OpenHands/software-agent-sdk#4717 carries a closing keyword for this issue, and cross-repo closing keywords do close on merge, so this will close when that lands.
openhands-ai commentedon Sep 2, 2026
@ameyypawar it looks like you haven't created an OpenHands account yet. Please sign up at OpenHands Cloud and try again.
gokay-ai commentedon Sep 14, 2026
Looking into Claude Code ACP not receiving Canvas-enabled built-in skills — will bridge enabled skills into the ACP session/profile path.
docs(.pr): design doc for Claude ACP skill overlay
fix: project enabled Canvas skills into Claude Code ACP sessions
docs(.pr): design doc for Claude ACP skill overlay
fix: project enabled Canvas skills into Claude Code ACP sessions
docs(.pr): design doc for Claude ACP skill overlay
jpelletier1 commentedon Oct 16, 2026
@DevinVinson worth prioritizing given this seems to be a longstanding issue with ACP
simonrosenberg commentedon Oct 23, 2026
Root cause and fix, as a stack of three PRs:
nativeACP skill sourcing,finalize()cleared an ACP agent's skills after mergingagent_launch_additions.skills, so skills a client sends at launch were dropped. It now strips only server-managed skills.agent_launch_additions.skillsfor ACP profiles (supersedes the draft fix: project enabled Canvas skills into Claude Code ACP sessions #17421, whosesystem_message_suffix_appendchannel is capped at 32 KiB whileopenhands-automationalone is about 48 KB).invoke_skilltool, so the skills are written to<persistence_dir>/acp/skills/<name>/SKILL.mdand listed in the prompt with their path, for every ACP agent.Checked with real Claude Code and Codex sessions: a skill with no trigger word, and a request without one, now load in both. Canvas needs an agent-server release carrying #6153 and #6171 before it can pin it.