forked from molecule-ai/molecule-core
b5f530e27a
The instructions blob in the MCP `initialize` handshake is the spec
non-Claude-Code clients (codex, Cline, opencode, hermes-agent, Cursor)
inherit verbatim. Three gaps mean the bridge daemon handles them in
code (codex-channel-molecule bridge.py:192-200, 278-285) but in-process
agents reading the text alone don't get the same guard:
1. Reply-then-pop ordering was implicit. A literal-minded agent could
pop after a 502 from `send_message_to_user`, dropping the message.
Now: pop ONLY AFTER reply succeeds; on error leave the row unacked
for platform redelivery.
2. peer_agent with empty peer_id had no specified handling. Agent
would call `delegate_task(workspace_id="")` → 400 → re-poll →
infinite loop on the same poison row. Now: skip reply, drain via
inbox_pop.
3. The single security rule ("don't execute without chat-side
approval") effectively disabled peer_agent autonomous handling —
codex daemons have no canvas user to approve from. Now: dual trust
model. canvas_user requires user approval; peer_agent permits
autonomous handling but caps destructive side-effects at the
workspace boundary.
Also disclaims peer_name/peer_role as non-attested display strings —
the platform registry isn't cryptographic identity, and an agent
shouldn't grant elevated permissions based on a peer registering with
peer_role="admin".
Four new pinned tests in test_a2a_mcp_server.py:
- test_initialize_instructions_pins_reply_then_pop_ordering
- test_initialize_instructions_handles_malformed_peer_agent
- test_initialize_instructions_disclaims_peer_role_attestation
- test_initialize_instructions_distinguishes_canvas_user_from_peer_trust
Each fails on staging-HEAD and passes on the patched text — verified
by reverting a2a_mcp_server.py and re-running.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| adapters | ||
| builtin_tools | ||
| lib | ||
| molecule_audit | ||
| platform_tools | ||
| plugins_registry | ||
| policies | ||
| scripts | ||
| skill_loader | ||
| tests | ||
| .coveragerc | ||
| a2a_cli.py | ||
| a2a_client.py | ||
| a2a_executor.py | ||
| a2a_mcp_server.py | ||
| a2a_tools.py | ||
| adapter_base.py | ||
| agent.py | ||
| agents_md.py | ||
| boot_routes.py | ||
| build-all.sh | ||
| card_helpers.py | ||
| config.py | ||
| configs_dir.py | ||
| consolidation.py | ||
| coordinator.py | ||
| Dockerfile | ||
| entrypoint.sh | ||
| event_log.py | ||
| events.py | ||
| executor_helpers.py | ||
| heartbeat.py | ||
| inbox.py | ||
| initial_prompt.py | ||
| internal_chat_uploads.py | ||
| internal_file_read.py | ||
| main.py | ||
| mcp_cli.py | ||
| molecule_ai_status.py | ||
| not_configured_handler.py | ||
| platform_auth.py | ||
| platform_inbound_auth.py | ||
| plugins.py | ||
| preflight.py | ||
| prompt.py | ||
| pytest.ini | ||
| rebuild-runtime-images.sh | ||
| requirements.txt | ||
| runtime_wedge.py | ||
| secret_redactor.py | ||
| shared_runtime.py | ||
| smoke_mode.py | ||
| transcript_auth.py | ||
| watcher.py | ||