feat(controller): expose instance-level fleet identity and health snapshots

Add a pure fleet snapshot assessor and a read-only controller/reconciler
MCP tool so multi-instance fleets can be enumerated by client_instance_id
without treating shared client_type as duplication. Trusted launcher
instance IDs, classification (missing/unmanifested/collisions/historical),
registry schema extensions, docs, and regression tests for #978.

Closes #978

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
This commit is contained in:
2026-07-30 03:14:15 -04:00
co-authored by Claude Opus 4.8
parent 6596b259fc
commit 4a1cc63e94
8 changed files with 2402 additions and 8 deletions
+217 -6
View File
@@ -15733,6 +15733,7 @@ _WORKER_HEARTBEAT_SUPERVISOR = None
CLIENT_NAME_ENV = "GITEA_MCP_CLIENT"
CLIENT_INSTANCE_ENV = "GITEA_MCP_CLIENT_INSTANCE"
CLIENT_SESSION_ENV = "GITEA_MCP_CLIENT_SESSION"
FLEET_RUN_ENV = "GITEA_MCP_FLEET_RUN_ID"
def _worker_registry():
@@ -15756,13 +15757,34 @@ def _worker_registry():
def _client_identity_hints() -> dict:
"""What the launcher told us about itself. Unset fields stay unset."""
"""What the launcher told us about itself (#948 / #975 / #978).
``client_instance_id`` is established by the trusted application launcher
once per launch and shared by all five namespace workers. When the launcher
key is absent we still register under an explicit *legacy* placeholder so
diagnostic reads work, but the registration is marked incomplete and cannot
authorize multi-instance fleet mutation safety.
"""
import mcp_fleet_snapshot
client_name = (os.environ.get(CLIENT_NAME_ENV) or "").strip() or None
raw_instance = (os.environ.get(CLIENT_INSTANCE_ENV) or "").strip() or None
instance = mcp_fleet_snapshot.assess_instance_identity(raw_instance)
# Legacy placeholder only when the launcher omitted the key — never invent a
# trusted ID from PID proximity.
if not instance["client_instance_id"]:
placeholder = f"legacy-pid-{os.getpid()}"
instance = mcp_fleet_snapshot.assess_instance_identity(
placeholder, source="pid_fallback"
)
return {
"client_name": (os.environ.get(CLIENT_NAME_ENV) or "").strip() or None,
"client_instance_id": (os.environ.get(CLIENT_INSTANCE_ENV) or "").strip()
or f"pid-{os.getpid()}",
"client_name": client_name,
"client_instance_id": instance["client_instance_id"],
"instance_id_provenance": instance["provenance"],
"instance_identity_trusted": instance["trusted"],
"session_id": (os.environ.get(CLIENT_SESSION_ENV) or "").strip()
or f"proc-{os.getpid()}-{_process_boot_head_sha or 'nohead'}",
"fleet_run_id": (os.environ.get(FLEET_RUN_ENV) or "").strip() or None,
}
@@ -15794,20 +15816,43 @@ def _active_worker_identity() -> str | None:
identity = mcp_worker_identity.generate_worker_identity(
hints["client_name"], hints["session_id"]
)
role = _active_role_kind_safe()
profile_name = (
(os.environ.get(gitea_config.ENV_PROFILE) or "").strip() or None
)
# Namespace is the role namespace (author/reviewer/…) when known.
namespace = role if role in {
"author", "reviewer", "merger", "controller", "reconciler"
} else None
parity = None
try:
parity = _current_master_parity()
except Exception:
parity = None
outcome = registry.register(
worker_identity=identity,
client_name=hints["client_name"],
client_instance_id=hints["client_instance_id"],
session_id=hints["session_id"],
generation_id=generation,
role=_active_role_kind_safe(),
profile=(os.environ.get(gitea_config.ENV_PROFILE) or "").strip() or None,
role=role,
profile=profile_name,
namespace=namespace,
remote=(os.environ.get("GITEA_MCP_REMOTE") or "").strip() or None,
repository_binding=PROJECT_ROOT,
pid=os.getpid(),
transport=native.get("bound_transport"),
token_fingerprint=native.get("token_fingerprint"),
pid_alive_probe=issue_lock_store.is_process_alive,
fleet_run_id=hints.get("fleet_run_id"),
process_identity=f"pid-{os.getpid()}",
startup_revision=(parity or {}).get("startup_head")
or _process_boot_head_sha,
loaded_revision=(parity or {}).get("local_head")
or (parity or {}).get("current_head"),
parity_revision=(parity or {}).get("current_head"),
live_revision=(parity or {}).get("live_remote_head"),
instance_id_provenance=hints.get("instance_id_provenance"),
)
if outcome.get("registered"):
_WORKER_IDENTITY = identity
@@ -19373,6 +19418,172 @@ def gitea_validate_review_final_report(
)
@mcp.tool()
def gitea_snapshot_instance_fleet(
remote: str = "dadeschools",
host: str | None = None,
org: str | None = None,
repo: str | None = None,
expected_manifest: list | dict | str | None = None,
include_historical: bool = True,
canonical_repository: str | None = None,
expected_live_revision: str | None = None,
) -> dict:
"""Read-only: authoritative instance-level fleet identity and health snapshot (#978).
Controller and reconciler only. Returns a point-in-time snapshot of every
registered namespace worker with instance attribution, heartbeat freshness,
and structured classification (expected/missing/unmanifested, duplicate
namespace workers, identity collisions, foreign repository, old revision,
historical dead rows). Sharing only a client type is never a duplicate.
Does not grant any mutation capability. Does not scan process tables or
open foreign databases for production evidence the worker registry is
the sole authority.
Args:
remote: Known instance 'dadeschools' or 'prgs'.
host: Optional host override.
org: Optional org override (audit context only).
repo: Optional repo override (audit context only).
expected_manifest: Optional approved fleet enrollment list
(list of dicts with client_instance_id / client_type / fleet_run_id).
When supplied, missing and unmanifested instances are classified.
include_historical: Include released/superseded rows (default True);
historical rows never make the live fleet unsafe by themselves.
canonical_repository: Expected repository binding path/slug for
foreign-repository classification.
expected_live_revision: When set, workers whose recorded revisions
differ are classified as old-revision.
"""
import json as _json
import mcp_fleet_snapshot
read_block = _profile_operation_gate("gitea.read")
if read_block:
return {
"success": False,
"read_only": True,
"reasons": read_block,
"permission_report": _permission_block_report("gitea.read"),
}
profile = get_profile()
role = _profile_role_kind(profile)
if role not in {"controller", "reconciler"}:
return {
"success": False,
"read_only": True,
"allowed": False,
"denied_role": role,
"required_roles": ["controller", "reconciler"],
"mutation_performed": False,
"reasons": [
f"gitea_snapshot_instance_fleet is restricted to controller and "
f"reconciler roles; active role_kind is {role!r}. Author, "
"reviewer, and merger profiles keep gitea.read for diagnosis "
"elsewhere but do not receive this fleet surface, and no "
"unrelated mutation permission is granted."
],
"exact_next_action": (
"Re-run from a prgs-controller or prgs-reconciler namespace."
),
}
manifest: list | None = None
if expected_manifest is not None:
raw = expected_manifest
if isinstance(raw, str):
try:
raw = _json.loads(raw)
except Exception as exc:
return {
"success": False,
"read_only": True,
"reasons": [
f"expected_manifest is not valid JSON: {type(exc).__name__}"
],
}
if isinstance(raw, dict):
# Accept {"instances": [...]} or a single instance object.
if "instances" in raw and isinstance(raw["instances"], list):
raw = raw["instances"]
else:
raw = [raw]
if not isinstance(raw, list):
return {
"success": False,
"read_only": True,
"reasons": ["expected_manifest must be a list of instance objects"],
}
manifest = raw
registry = _worker_registry()
if registry is None:
return {
"success": False,
"read_only": True,
"reasons": [
"worker registry is unavailable; cannot produce an authoritative "
"fleet snapshot (fail closed)"
],
"exact_next_action": (
"Ensure GITEA_WORKER_REGISTRY_DB is writable and re-run after "
"workers have registered."
),
}
try:
if include_historical:
records = registry.list_workers(status=None)
else:
records = registry.list_workers(status=mcp_worker_identity.STATUS_ACTIVE)
except Exception as exc:
return {
"success": False,
"read_only": True,
"reasons": [
f"failed to read worker registry: {type(exc).__name__}: {_redact(str(exc))}"
],
}
parity = None
try:
parity = _current_master_parity()
except Exception:
parity = None
live_rev = expected_live_revision or (parity or {}).get("live_remote_head")
canon = canonical_repository or PROJECT_ROOT
snapshot = mcp_fleet_snapshot.snapshot_instance_fleet(
records,
expected_manifest=manifest,
pid_alive_probe=issue_lock_store.is_process_alive,
canonical_repository=canon,
expected_live_revision=live_rev,
)
snapshot["role_kind"] = role
snapshot["profile"] = profile.get("profile_name")
snapshot["remote"] = _effective_remote(remote)
snapshot["repository"] = {
"org": org,
"repo": repo,
"canonical_repository": canon,
}
snapshot["mutation_performed"] = False
snapshot["permission_scope"] = {
"read_only": True,
"granted_operations": ["gitea.read"],
"denied_unrelated_mutations": True,
"note": (
"This capability is strictly observational. It does not authorize "
"branch, issue, PR, review, merge, or restart mutations."
),
}
return snapshot
@mcp.tool()
def gitea_get_runtime_context(
remote: str = "dadeschools",