Files
Gitea-Tools/docs/mcp-namespace-health.md
T
sysadminandClaude Opus 4.8 287e0c5e65 feat: enforce live-namespace block in review/merge state machine (#543 AC5)
The namespace health check (05fdcee) classified a false-ready namespace but
only returned an advisory blocks_merge_workflow flag; nothing in the merge
gate consumed it. Wire it in so a broken live namespace hard-blocks merge.

- review_merge_state_machine.assess_workflow_blockers: add live_namespace_broken
  blocker (registered-in-FastMCP but not callable-through-namespace).
- assess_state_advancement: forward **blocker_kwargs so can_approve/can_merge/
  workflow_status honor the full blocker set (also fixes latent drop of
  mcp_reconnect_failed/stale_capability_state through those paths).
- gitea_assess_review_merge_state_machine tool: accept live_namespace_broken and
  thread it through all state-machine calls.
- Tests: prove can_merge/workflow_status/tool block on live_namespace_broken even
  with every review state + pre-merge gate satisfied; bridge classify verdict.
- Docs: enforcement section wiring blocks_merge_workflow -> live_namespace_broken.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-09 11:15:02 -04:00

77 lines
3.0 KiB
Markdown

# MCP namespace EOF recovery
Gitea MCP tools can be registered in the Python FastMCP server while the IDE's
live MCP namespace is still unusable. The failure usually appears as
`client is closing: EOF`, `transport closed`, or an empty response when calling
a tool such as `gitea_whoami`.
Do not treat static tool registration as proof that review or merge workflows
can proceed. A reviewer or merger flow must have live namespace evidence that
the required tool is callable through the configured namespace.
## Required namespace probes
Run the health check after changing MCP config, switching branches that affect
server code, or seeing EOF from any Gitea namespace:
```bash
python3 test_mcp_conn.py --config ~/.gemini/config/mcp_config.json
```
By default the script checks these namespaces and required tools:
| Namespace | Required tool |
| --- | --- |
| `gitea-author` | `gitea_whoami` |
| `gitea-reviewer` | `gitea_whoami` |
| `gitea-merger` | `gitea_whoami` |
| `gitea-tools` | `gitea_list_profiles` |
Use `--namespace gitea-reviewer` to test only one namespace. A passing probe
requires:
1. The namespace exists in the MCP config.
2. JSON-RPC initialize succeeds.
3. `tools/list` returns the required tool.
4. `tools/call` successfully invokes the required tool.
## Recovery steps
When a namespace returns EOF:
1. Note the reported namespace, required tool, PID, profile, environment
summary, and config path.
2. Stop any stale MCP server process for that PID.
3. Reload or touch the MCP config so the IDE reconnects the namespace.
4. Verify the namespace command, args, profile env, and checkout path point at
the current repository.
5. Re-run `python3 test_mcp_conn.py --namespace <name>`.
6. Resume review or merge work only after the required tool call passes.
The read-only `gitea_assess_mcp_namespace_health` tool can classify probe
evidence supplied by a client. It intentionally distinguishes
`required_tool_registered=true` from `required_tool_callable=false`; the latter
must block reviewer and merger workflows until the live namespace is repaired.
## Enforcement in the review/merge state machine
The block is not advisory. Feed the `blocks_merge_workflow` verdict from
`gitea_assess_mcp_namespace_health` into
`gitea_assess_review_merge_state_machine` as `live_namespace_broken`:
```text
health = gitea_assess_mcp_namespace_health(namespace="gitea-merger", ...)
state = gitea_assess_review_merge_state_machine(
state_completion=...,
pre_merge_gates=...,
live_namespace_broken=health["blocks_merge_workflow"],
)
# state["merge"]["allowed"] is False whenever the live namespace is broken,
# even when every review state and pre-merge gate is otherwise satisfied.
```
When `live_namespace_broken=True`, `assess_workflow_blockers`,
`can_approve`, `can_merge`, and `workflow_status` all fail closed. This is the
guard that stops a merge from proceeding on a false-ready namespace, as in the
PR #418 halt that motivated this work (#543).