merge: AgentProject membership — the junction is now load-bearing

Merges feat/agent-project-membership (task 166/152). An agent can finally join
many projects: membership routes, per-membership role and optional brain
override, chat resolving context from the membership, and CLI attach-agent /
detach-agent / get memberships. The legacy Agent.projectId fallback is kept for
this release as the schema comment promises.

Conflict resolved in main.ts: that branch added its RBAC case to
mapUrlToPermission inline, while this branch had extracted the function to
middleware/url-permission.ts so it could be tested. Kept the extraction and
ported the case into it — joining a team is `edit:agents:<name>`, not
`create:agents`, which is the authority to mint a whole agent.

Also fixes something the extraction makes possible. security.test.ts contained a
hand-copied reproduction of mapUrlToPermission, because main.ts self-invokes
main() and nothing in it was importable. A security test asserting against a
copy stops testing the system the moment the real one changes, and this copy had
already drifted. It now imports the real function; all 18 assertions still pass,
against the code that actually runs.

Local: build clean, workspace 2550 passed, lint unchanged at 794 errors.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4wNHWf7xSwnZCWpJcyv9p
This commit is contained in:
Michal
2026-08-09 23:34:18 +01:00
169 changed files with 8677 additions and 87 deletions

View File

@@ -0,0 +1,27 @@
# Task ID: 147
**Title:** Headless coding agent runtime adapter
**Status:** pending
**Dependencies:** 143, 146
**Priority:** medium
**Description:** Implement AgentRuntime adapter that runs a headless coding agent inside the session pod
**Details:**
Create src/mcpd/src/services/agent-runtime/headless-adapter.ts:
1. Implement AgentRuntime interface
2. startSession: create AgentSession, provision pod with coding agent image, inject persona as prompt files in container
3. send: exec into container to send message to agent process (implementation depends on chosen agent's IPC)
4. status: check agent process state via exec or container status
5. result: read agent output (branch, commit, summary) from known output location
6. endSession: stop container, update session state
7. The coding agent handles git, branching, MCP tools, streaming internally
8. Persona delivered via mounted files the agent reads
**Test Strategy:**
Integration tests against test cluster: start session, send simple task, verify branch created and pushed.