diff options
| author | Claude <noreply@anthropic.com> | 2026-05-26 07:18:07 +0000 |
|---|---|---|
| committer | Claude <noreply@anthropic.com> | 2026-05-26 07:18:07 +0000 |
| commit | fb7f8a4c07a8bf6539566aacbc8a92310c555992 (patch) | |
| tree | dceb87f179823939c5a11f390921b7b185a56cf0 /.gitignore | |
| parent | 301e7a66387f99ab76754d08bca42f4a9930d3b1 (diff) | |
test(spike): manual agent-MCP validation harness + Phase 2 validation findings
Adds cmd/spike, a manual (never run by CI) harness that starts the agent MCP
server on the host and points a real agent CLI at it to confirm tool calls reach
the AgentChannel. Validates Phase 2 end-to-end without Docker.
Findings against real claude 2.1.150 (sonnet-4-6):
- PASS: claude discovers the server via --mcp-config (streamable HTTP + bearer)
and calls record_progress + report_summary; both reach the AgentChannel,
zero permission denials.
- PASS: claude calls ask_user, gets the ErrAgentBlocked "end your turn"
response, and ends its turn cleanly (human-in-the-loop path).
- PRODUCTION NOTE: claude rejects --permission-mode bypassPermissions under
root — the in-container agent must run non-root (ContainerRunner sets
--user to the host uid), or tools must be pre-allowed via --allowedTools.
- GEMINI spike could not run (no gemini binary); the harness's gemini path
writes the production mcpServers/httpUrl settings and is ready to run where
a binary exists.
https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39
Diffstat (limited to '.gitignore')
| -rw-r--r-- | .gitignore | 1 |
1 files changed, 1 insertions, 0 deletions
@@ -45,3 +45,4 @@ SESSION_STATE.md .claude/ credentials/ scripts/.claude/ +/spike |