Files
Gitea-Tools/mcp_namespace_health.py
T
sysadmin 2b3f5baaeb fix(mcp): invalidate review session state on cross-profile activation (Closes #690)
A mid-run profile switch (reviewer -> author -> reviewer) left workflow-load
proof, reviewer lease binding, the review decision lock, live namespace
health, and preflight identity/capability stamps intact, so a formal verdict
could be recorded under contaminated session state.

- gitea_activate_profile now invalidates all review-critical session state
  on a cross-profile switch, in memory and in durable state keyed by either
  profile identity, and reports the invalidation + re-preflight requirement.
- Full reviewer preflight (whoami, load_review_workflow,
  resolve_task_capability(review_pr), head re-pin, lease re-acquire) is
  required before any formal verdict after a switch; switching back cannot
  resurrect the stale run.
- Namespace provenance: optional launcher-declared GITEA_MCP_NAMESPACE is
  reported by whoami/runtime context/capability resolution, and a declared
  namespace that disagrees with a task's required namespace fails closed.
- Docs: supported pattern is separate session/namespace per role, not
  in-process profile hopping mid-review.
2026-07-25 19:17:19 -04:00

356 lines
13 KiB
Python

"""Assess live MCP namespace health without trusting static registration.
The IDE/client namespace can fail with EOF even when this Python process still
registers the Gitea tools with FastMCP. These helpers keep that distinction
explicit so reviewer/merger flows can fail closed on the live path.
Probe sources
-------------
* ``client_namespace`` — evidence from the IDE-managed MCP client path (the
only source that can prove the workflow namespace is healthy).
* ``offline_spawn`` — a separate ``subprocess.Popen`` JSON-RPC handshake
(e.g. ``test_mcp_conn.py``). Useful offline, but **never** proves the
IDE-managed namespace is callable.
* ``unknown`` — legacy/unspecified; treated as not IDE-proven.
"""
from __future__ import annotations
import os
from typing import Any
REQUIRED_NAMESPACE_TOOLS = {
"gitea-author": "gitea_whoami",
"gitea-reviewer": "gitea_whoami",
"gitea-merger": "gitea_whoami",
"gitea-tools": "gitea_list_profiles",
}
DEFAULT_NAMESPACES = tuple(REQUIRED_NAMESPACE_TOOLS)
# Namespaces that must be healthy for a given mutation task.
TASK_REQUIRED_NAMESPACES = {
"review_pr": "gitea-reviewer",
"submit_review": "gitea-reviewer",
"merge_pr": "gitea-merger",
}
PROBE_SOURCE_CLIENT = "client_namespace"
PROBE_SOURCE_OFFLINE = "offline_spawn"
PROBE_SOURCE_UNKNOWN = "unknown"
VALID_PROBE_SOURCES = frozenset(
{PROBE_SOURCE_CLIENT, PROBE_SOURCE_OFFLINE, PROBE_SOURCE_UNKNOWN}
)
EOF_PATTERNS = (
"client is closing: eof",
"transport closed",
"connection closed",
"broken pipe",
"end of file",
"eof",
)
SAFE_ENV_KEYS = (
"GITEA_MCP_PROFILE",
"GITEA_PROFILE_NAME",
"GITEA_SERVICE",
"GITEA_EXECUTION_ROLE",
"GITEA_MCP_CONFIG",
"GITEA_MCP_NAMESPACE",
)
# Optional launcher-provided env declaring the client-managed MCP namespace
# this process is registered under (e.g. ``gitea-reviewer``). The server
# cannot derive its own IDE namespace name, so the launcher declares it; when
# declared, reviewers/mergers can fail closed on a namespace/task mismatch
# (#690 AC4). Absence means "unknown" — reported, never guessed.
NAMESPACE_ENV = "GITEA_MCP_NAMESPACE"
def configured_client_namespace(env: dict[str, str] | None = None) -> str | None:
"""Return the launcher-declared client namespace, or None when unknown."""
source = os.environ if env is None else env
value = (source.get(NAMESPACE_ENV) or "").strip()
return value or None
def namespace_provenance(
task: str | None = None,
*,
active_profile: str | None = None,
env: dict[str, str] | None = None,
) -> dict[str, Any]:
"""Report configured client namespace vs active execution profile (#690).
When *task* carries a required namespace (``TASK_REQUIRED_NAMESPACES``)
and the launcher declared a different one, ``mismatch`` is True and the
caller must fail closed for that task. An undeclared namespace is
reported as unknown — never treated as proof either way.
"""
configured = configured_client_namespace(env)
required = TASK_REQUIRED_NAMESPACES.get(task or "")
mismatch = bool(configured and required and configured != required)
reasons: list[str] = []
if mismatch:
reasons.append(
f"configured client namespace '{configured}' does not match "
f"required namespace '{required}' for task '{task}' (fail closed)"
)
return {
"configured_namespace": configured,
"namespace_source": NAMESPACE_ENV if configured else "unknown",
"active_profile": active_profile,
"requested_task": task,
"required_namespace": required,
"mismatch": mismatch,
"reasons": reasons,
}
def _as_list(value: Any) -> list[str] | None:
if value is None:
return None
if isinstance(value, (list, tuple, set)):
return [str(v) for v in value]
return [str(value)]
def _contains_eof(text: str | None) -> bool:
lowered = (text or "").lower()
return any(pattern in lowered for pattern in EOF_PATTERNS)
def _normalize_probe_source(probe_source: str | None) -> str:
raw = (probe_source or PROBE_SOURCE_UNKNOWN).strip().lower()
if raw in VALID_PROBE_SOURCES:
return raw
return PROBE_SOURCE_UNKNOWN
def _safe_env_summary(process: dict[str, Any] | None) -> dict[str, str]:
if not process:
return {}
env = process.get("env") or process.get("environment") or {}
if not isinstance(env, dict):
return {}
return {
key: str(env[key])
for key in SAFE_ENV_KEYS
if key in env and env[key] not in (None, "")
}
def classify_namespace_probe(
namespace: str,
*,
required_tool: str | None = None,
registered_tools: list[str] | tuple[str, ...] | set[str] | None = None,
probe_result: dict[str, Any] | None = None,
process: dict[str, Any] | None = None,
config_path: str | None = None,
profile: str | None = None,
configured: bool = True,
probe_source: str | None = None,
) -> dict[str, Any]:
"""Classify whether a required tool is callable through a live namespace.
``registered_tools`` is static/server-side evidence. ``probe_result`` is
live invocation evidence. Only ``probe_source=client_namespace`` proves the
IDE-managed path; ``offline_spawn`` is an offline subprocess check only.
"""
ns = (namespace or "").strip()
tool = required_tool or REQUIRED_NAMESPACE_TOOLS.get(ns) or "gitea_whoami"
source = _normalize_probe_source(probe_source)
registered_list = _as_list(registered_tools)
registered = None if registered_list is None else tool in registered_list
probe = probe_result or {}
probe_success = bool(probe.get("success"))
error_message = str(
probe.get("error")
or probe.get("message")
or probe.get("stderr")
or probe.get("exception")
or ""
)
error_type = str(probe.get("error_type") or "").strip()
if not error_type and error_message:
if _contains_eof(error_message):
error_type = "namespace_eof"
elif "timeout" in error_message.lower():
error_type = "namespace_timeout"
else:
error_type = "namespace_call_failed"
if not configured:
error_type = "namespace_not_configured"
elif registered is False:
error_type = "tool_missing"
elif not probe_result:
error_type = "live_probe_missing"
elif not probe_success and not error_type:
error_type = "namespace_call_failed"
callable_live = bool(configured and probe_result and probe_success)
# Probe-path health (spawn or client). IDE-proven only for client path.
healthy = bool(configured and registered is not False and callable_live)
ide_namespace_proven = bool(healthy and source == PROBE_SOURCE_CLIENT)
process_pid = process.get("pid") if isinstance(process, dict) else None
profile_name = profile or (
process.get("profile") if isinstance(process, dict) else None
)
env_summary = _safe_env_summary(process)
reasons: list[str] = []
if not configured:
reasons.append(f"MCP namespace '{ns}' is not configured.")
if registered is False:
reasons.append(
f"Required tool '{tool}' is not registered in namespace '{ns}'."
)
if error_type == "live_probe_missing":
reasons.append(
f"No live client invocation proof was supplied for '{ns}.{tool}'."
)
elif error_type == "namespace_eof":
reasons.append(
f"Live MCP namespace '{ns}' returned EOF while invoking '{tool}'."
)
elif error_type == "namespace_timeout":
reasons.append(
f"Live MCP namespace '{ns}' timed out while invoking '{tool}'."
)
elif error_type == "namespace_call_failed":
reasons.append(
f"Live MCP namespace '{ns}' failed while invoking '{tool}'."
)
if source == PROBE_SOURCE_OFFLINE:
reasons.append(
"Probe source is offline_spawn (subprocess JSON-RPC); this does "
"not prove the IDE-managed MCP namespace is healthy."
)
elif source == PROBE_SOURCE_UNKNOWN and probe_result:
reasons.append(
"Probe source unspecified; treat as not IDE-namespace proof unless "
"re-supplied with probe_source='client_namespace'."
)
remediation = []
if not healthy or not ide_namespace_proven:
remediation.append(
"Reconnect the IDE MCP client namespace (client reconnect / "
f"relaunch), then invoke '{tool}' through namespace '{ns}' and "
"record the result with probe_source='client_namespace'."
)
remediation.append(
"Do not treat offline subprocess probes (test_mcp_conn.py) or "
"shell kill/PID respawn as proof the IDE namespace is repaired."
)
if process_pid and source != PROBE_SOURCE_OFFLINE:
remediation.append(
f"Diagnostics may include PID {process_pid}; process details "
"are informational only — recovery is client-layer reconnect."
)
else:
remediation.append(
f"IDE-managed namespace '{ns}' can invoke '{tool}' "
f"(probe_source={source})."
)
# Client-namespace broken health blocks review/merge. Offline probes never
# authorize mutations and only block when they report unhealthy (still
# fail-closed for known bad spawn evidence).
blocks = False
if source == PROBE_SOURCE_CLIENT:
blocks = namespace_health_blocks_task("merge_pr", healthy)
elif source == PROBE_SOURCE_OFFLINE:
# Offline never proves IDE health; never unblock. Unhealthy offline
# still surfaces as a soft diagnostic, not a mutation-ledger block.
blocks = False
else:
# Unknown source: only block when evidence is unhealthy (fail closed
# on bad data without treating success as IDE proof).
blocks = namespace_health_blocks_task("merge_pr", healthy)
return {
"success": healthy,
"healthy": healthy,
"namespace": ns,
"required_tool": tool,
"configured": configured,
"registered_tools_checked": registered_list is not None,
"required_tool_registered": registered,
"required_tool_callable": callable_live,
"probe_source": source,
"ide_namespace_proven": ide_namespace_proven,
"error_type": None if healthy else error_type,
"error_message": error_message or None,
"reasons": reasons,
"remediation": remediation,
"diagnostics": {
"namespace": ns,
"required_tool": tool,
"process_pid": process_pid,
"profile": profile_name,
"env": env_summary,
"config_path": config_path,
"probe_source": source,
},
"blocks_merge_workflow": blocks,
}
def namespace_health_blocks_task(task: str, healthy: bool) -> bool:
"""Return whether a broken namespace must block a workflow task."""
if healthy:
return False
return (task or "").strip() in {"merge_pr", "review_pr", "submit_review"}
def required_namespace_for_task(task: str) -> str | None:
"""Map a mutation task to the MCP namespace that must be healthy."""
return TASK_REQUIRED_NAMESPACES.get((task or "").strip())
def mutation_gate_from_session(
task: str,
session_health: dict[str, dict[str, Any]] | None,
) -> list[str]:
"""Fail-closed gate using recorded client-namespace health assessments.
* Missing session entry → no gate (caller has not assessed yet).
* Client-namespace unhealthy / not IDE-proven → block mutation.
* Offline-only session entries never authorize mutations.
"""
ns = required_namespace_for_task(task)
if not ns:
return []
store = session_health or {}
entry = store.get(ns)
if not entry:
return []
source = _normalize_probe_source(entry.get("probe_source"))
if source != PROBE_SOURCE_CLIENT:
return [
f"recorded namespace health for '{ns}' is probe_source={source}, "
"not client_namespace; re-probe through the IDE-managed path "
f"before {(task or 'mutation')}"
]
if entry.get("ide_namespace_proven") and entry.get("healthy"):
return []
if entry.get("blocks_merge_workflow") or not entry.get("healthy"):
detail = entry.get("error_type") or "unhealthy"
return [
f"live MCP namespace '{ns}' is recorded {detail} "
f"(probe_source={source}); repair the IDE namespace before "
f"{(task or 'mutation')} (fail closed, #543)"
]
if not entry.get("ide_namespace_proven"):
return [
f"live MCP namespace '{ns}' is not IDE-proven; supply a "
"client_namespace probe before mutation (fail closed, #543)"
]
return []