Compare commits

..
Author SHA1 Message Date
sysadminandClaude Opus 4.8 78cc37a977 feat(observability): optional self-hosted Sentry instrumentation for MCP workflow failures (Closes #606)
Add an env-var-gated, off-by-default Sentry SDK integration so MCP runtime
errors, fail-closed workflow blockers, lease/terminal-lock/stale-runtime
collisions, and recurring watchdog check-ins are visible in a self-hosted
Sentry at https://sentry.prgs.cc/. Gitea stays the source of truth; Sentry is
observe-only.

New module `sentry_observability.py` mirrors the `gitea_audit` conventions
(env-gated, best-effort, redacting):

- Config from MCP_SENTRY_ENABLED / SENTRY_DSN / SENTRY_ENVIRONMENT /
  SENTRY_RELEASE / MCP_SENTRY_TRACES_SAMPLE_RATE / MCP_SENTRY_ENABLE_LOGS.
  Active only when enabled AND a DSN is present; otherwise a hard no-op.
- Fail OPEN for observability (never blocks a tool success path) and fail
  CLOSED for redaction (drop a field rather than risk leaking it).
- `scrub_event` before_send/before_send_log hook + allowlisted tags: no
  tokens/passwords/keychain ids/DSNs/cookies, no raw session-state or full
  prompt bodies (session_id -> 12-char hash), no full filesystem paths
  (worktree path -> coarse category). Reuses incident_bridge + gitea_audit
  scrubbers.
- capture_exception, capture_workflow_blocker (with canonical next action),
  and monitor_checkin with six stable cron slugs (stale lease scan, terminal
  lock scan, allocator health, namespace health, dashboard freshness,
  reconciler cleanup).
- `sentry_sdk` is a lazily-imported optional dependency; the module imports
  and no-ops cleanly when the package is absent.

Wiring in gitea_mcp_server.py (additive, guarded, best-effort):
- init_sentry() in __main__ before mcp.run.
- capture_exception in the `_audited` failure path; capture_workflow_blocker
  in `_audit_pr_result` BLOCKED/FAILED path.
- allocator + namespace-health watchdog check-ins at their MCP tool sites
  (domain modules left pure).

Also: pin `sentry-sdk==2.20.0` (optional), document the six env vars in
`.env.example`, and add `docs/observability/sentry-integration.md` covering
project creation in https://sentry.prgs.cc/, DSN handling, local/dev/prod
config, redaction guarantees, and coexistence with the #612 incident bridge.

Tests: tests/test_sentry_observability.py (36 cases) cover disabled / enabled /
missing-DSN / missing-SDK, redaction, exception capture, workflow-blocker
capture, and cron check-in behaviour. Full suite: 2632 passed, 6 skipped.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-12 02:35:47 -04:00
9 changed files with 1160 additions and 2142 deletions
+21
View File
@@ -39,6 +39,27 @@ GITEA_AUDIT_LOG=/path/to/gitea-mcp-audit.log
# only — never the token value. Surfaced by gitea_get_profile.
GITEA_TOKEN_SOURCE=GITEA_TOKEN
# ── Optional self-hosted Sentry observability (#606) ────────────────────────
# Emits runtime errors, fail-closed workflow blockers, lease/terminal-lock/
# stale-runtime collisions, and watchdog cron check-ins to a SELF-HOSTED Sentry
# (https://sentry.prgs.cc/) — never Sentry Cloud. Gitea stays the source of
# truth; Sentry is observe-only. OFF by default: with MCP_SENTRY_ENABLED unset
# or SENTRY_DSN empty, nothing is initialised and no events are sent.
#
# Master gate. Truthy = 1/true/yes/on. Both this AND SENTRY_DSN are required.
MCP_SENTRY_ENABLED=0
# DSN for the self-hosted project (create a `gitea-tools-mcp` project in
# https://sentry.prgs.cc/ and copy its DSN). Never commit a real DSN.
SENTRY_DSN=
# Deployment environment tag (local/dev/prod). Defaults to "development".
SENTRY_ENVIRONMENT=development
# Optional release identifier (e.g. a git SHA or version string).
SENTRY_RELEASE=
# Performance-trace sample rate, 0.01.0 (clamped). Default 0.0 (traces off).
MCP_SENTRY_TRACES_SAMPLE_RATE=0.0
# Set to 1 to forward Python logs to Sentry as structured logs. Default off.
MCP_SENTRY_ENABLE_LOGS=0
# Optional canonical runtime-profile config (#19). Instead of the fields above,
# point every LLM launcher at ONE JSON file of named profiles and select one.
# Secrets are referenced (keychain id / env var name), never inlined. See
-807
View File
@@ -1,807 +0,0 @@
"""Common anti-stomp preflight for every MCP mutation tool (#604).
Even with leases, mutation tools need a **shared** preflight that prevents
stale sessions, wrong worktrees, wrong repos, old prompts, terminal locks,
foreign leases, contaminated approvals, and root-checkout mutations from
slipping through.
This module is the pure assessment core. Callers (MCP mutation entrypoints)
gather live facts and pass them in — nothing here performs git, network, or
durable-state I/O. Existing happy-path guards remain authoritative; this
module composes them into one typed, fail-closed result.
Required checks (issue #604):
* repo/org verification
* profile/role verification
* root checkout clean and not used for mutation (when role requires branches/)
* worktree under branches when required
* active lease ownership (when lease is required for the mutation)
* terminal lock status (when applicable)
* expected head SHA (when pinned)
* stale runtime status
* workflow hash (when a workflow load is required)
* source contamination status
* no manual state/mtime/source-file bypass
Failure returns a typed blocker and an exact next action. There is **no**
agent-facing bypass flag.
"""
from __future__ import annotations
from typing import Any
import author_mutation_worktree
import master_parity_gate
import remote_repo_guard
import root_checkout_guard
import stable_branch_push_guard
# ── public constants ──────────────────────────────────────────────────────────
# Typed blocker kinds returned in the structured result.
BLOCKER_WRONG_REPO = "wrong_repo"
BLOCKER_WRONG_ROLE = "wrong_role"
BLOCKER_ROOT_CHECKOUT = "root_checkout_mutation"
BLOCKER_WRONG_WORKTREE = "wrong_worktree"
BLOCKER_FOREIGN_LEASE = "foreign_lease"
BLOCKER_TERMINAL_LOCK = "terminal_lock"
BLOCKER_HEAD_SHA = "head_sha_mismatch"
BLOCKER_STALE_RUNTIME = "stale_runtime"
BLOCKER_WORKFLOW_HASH = "workflow_hash"
BLOCKER_SOURCE_CONTAMINATION = "source_contamination"
BLOCKER_MANUAL_BYPASS = "manual_bypass"
BLOCKER_KINDS = frozenset({
BLOCKER_WRONG_REPO,
BLOCKER_WRONG_ROLE,
BLOCKER_ROOT_CHECKOUT,
BLOCKER_WRONG_WORKTREE,
BLOCKER_FOREIGN_LEASE,
BLOCKER_TERMINAL_LOCK,
BLOCKER_HEAD_SHA,
BLOCKER_STALE_RUNTIME,
BLOCKER_WORKFLOW_HASH,
BLOCKER_SOURCE_CONTAMINATION,
BLOCKER_MANUAL_BYPASS,
})
# Mutation tasks that must invoke the shared anti-stomp preflight before
# acting (issue #604 AC1). Every member must appear as a live task= kwarg
# to verify_preflight_purity / _run_anti_stomp_preflight (or the review
# anti_task map) in gitea_mcp_server.py. Inventory↔wiring tests fail if
# a declared task is not wired.
MUTATION_TASKS = frozenset({
"create_issue",
"comment_issue",
"close_issue",
"mark_issue",
"lock_issue",
"set_issue_labels",
"create_label",
"create_pr",
"close_pr",
"edit_pr",
"commit_files",
"gitea_commit_files",
"delete_branch",
"cleanup_merged_pr_branch",
"cleanup_stale_claims",
"reconcile_merged_cleanups",
"reconcile_already_landed_pr",
"reconcile_close_superseded_pr",
"post_heartbeat",
"acquire_reviewer_pr_lease",
"gitea_acquire_reviewer_pr_lease",
"adopt_merger_pr_lease",
"review_pr",
"submit_pr_review",
"approve_pr",
"request_changes_pr",
"merge_pr",
})
# Intentionally excluded from MUTATION_TASKS. Each has a dedicated
# fail-closed gate that preserves decision-lock ownership, workflow-hash,
# head-SHA, and repository consistency. Do not re-add without either
# wiring shared preflight or updating this rationale (#604 Blocker B).
DEDICATED_GATE_MUTATIONS: dict[str, str] = {
"mark_final_review_decision": (
"Local review-decision lock only. Enforced by session lock ownership, "
"workflow-hash, expected head SHA, PR work lease, eligibility, and "
"terminal-lock gates. No Gitea review POST; shared anti-stomp would "
"duplicate without side-effect-ordering value."
),
"save_review_draft": (
"Local session-state draft save with live PR head/base consistency "
"checks. Not a Gitea review/merge mutation; dedicated head-SHA and "
"worktree resolution gates apply."
),
"resume_review_draft": (
"Live-state resume with terminal lock, lease ownership, head/base SHA, "
"and parity checks. When submit=True, delegates to gitea_submit_pr_review "
"which runs shared anti-stomp before the Gitea review POST."
),
"cleanup_stale_review_decision_lock": (
"Moot-lock cleanup with identity match, live PR merged/closed proof, "
"and reviewer capability gate (#594). Distinct from shared anti-stomp."
),
"gitea_cleanup_stale_review_decision_lock": (
"Alias of cleanup_stale_review_decision_lock; dedicated #594 path."
),
"heartbeat_reviewer_pr_lease": (
"Lease heartbeat posts via verify_preflight_purity(task='review_pr') "
"plus in-session lease ownership checks; not a separate mutation class."
),
"release_reviewer_pr_lease": (
"Lease release uses workspace binding + ownership checks; posts only "
"when the session owns the active lease."
),
}
# Roles that must mutate from a branches/ worktree (not the control checkout).
_BRANCHES_REQUIRED_ROLES = frozenset({"author"})
# Reviewer/merger mutations that require an owned lease + head pinning when
# the caller supplies those facts.
_LEASE_AWARE_TASKS = frozenset({
"review_pr",
"submit_pr_review",
"approve_pr",
"request_changes_pr",
"merge_pr",
"acquire_reviewer_pr_lease",
"gitea_acquire_reviewer_pr_lease",
"adopt_merger_pr_lease",
})
_NEXT_ACTIONS: dict[str, str] = {
BLOCKER_WRONG_REPO: (
"Pass explicit org= and repo= matching the local git remote "
"(e.g. org=Scaled-Tech-Consulting repo=Gitea-Tools) and retry."
),
BLOCKER_WRONG_ROLE: (
"Call gitea_resolve_task_capability, switch to the required "
"namespace/profile, re-verify with gitea_whoami, then retry."
),
BLOCKER_ROOT_CHECKOUT: (
"Leave the root control checkout on clean master; create or switch "
"to a session-owned worktree under branches/ and retry the mutation "
"with worktree_path set."
),
BLOCKER_WRONG_WORKTREE: (
"Create or bind a session-owned worktree under branches/, set "
"worktree_path (or GITEA_ACTIVE_WORKTREE), and retry."
),
BLOCKER_FOREIGN_LEASE: (
"Stop. Do not stomp a foreign lease. Wait for expiry, request "
"takeover through the sanctioned path, or hand off to the owner."
),
BLOCKER_TERMINAL_LOCK: (
"Stop. A terminal review-decision lock is active for this head. "
"Do not re-approve/merge; follow the #332/#620 recovery path."
),
BLOCKER_HEAD_SHA: (
"Re-fetch the live PR head with gitea_view_pr, re-pin "
"expected_head_sha to the current head, re-validate, then retry."
),
BLOCKER_STALE_RUNTIME: (
"Restart the Gitea MCP server so it reloads master's capability "
"gates, re-run gitea_whoami + gitea_resolve_task_capability, then retry."
),
BLOCKER_WORKFLOW_HASH: (
"Reload the canonical workflow via gitea_load_review_workflow, then "
"rerun the full review-merge workflow from inventory (no approve/merge replay)."
),
BLOCKER_SOURCE_CONTAMINATION: (
"Stop. Session is source-contaminated. Hand off to a reconciler for "
"audit/clear; do not clear markers by deleting session-state files."
),
BLOCKER_MANUAL_BYPASS: (
"Stop. Manual state/mtime/source-file bypass is forbidden. Use "
"sanctioned MCP tools only; never delete or rewrite session-state "
"or lock files by hand."
),
}
def is_mutation_task(task: str | None) -> bool:
"""True when *task* is in the #604 mutation set (normalized)."""
name = (task or "").strip().lower().removeprefix("gitea_")
if not name:
return False
if name in MUTATION_TASKS:
return True
# Accept gitea_ prefixed membership for aliases already in the set.
return f"gitea_{name}" in MUTATION_TASKS
def roles_compatible(active_role: str | None, required_role: str | None) -> bool:
"""Whether *active_role* may perform a task that maps to *required_role*.
Exact match always passes. Reconcilers may run author-class mutations
(comment/close/cleanup) that the capability map stamps as ``author`` —
matching the long-standing reconciler exemption for control-checkout
work. No other cross-role substitutions are allowed.
Capability-authorized multi-role tasks (e.g. reviewer holding
``gitea.issue.comment`` for ``comment_issue``) are handled by
:func:`authorization_compatible`, not by expanding this role matrix.
"""
active = (active_role or "").strip().lower()
required = (required_role or "").strip().lower()
if not active or not required:
return True
if active == required:
return True
if active == "reconciler" and required in {"author", "reconciler"}:
return True
return False
def authorization_compatible(
active_role: str | None,
required_role: str | None,
*,
required_permission: str | None = None,
allowed_operations: Any = None,
) -> bool:
"""Whether the active session may run a task given role *and* capability.
Order:
1. :func:`roles_compatible` (exact role or narrow reconciler→author).
2. Capability possession: when *required_permission* is non-empty and
present in *allowed_operations*, allow even if the nominal task role
differs (e.g. reviewer/merger with ``gitea.issue.comment`` on
``comment_issue`` / ``mark_issue`` / ``set_issue_labels`` /
``lock_issue``).
Fail closed otherwise. This is **not** a broad reviewer→author or
merger→author role rewrite: without the specific permission the check
still denies. Missing *allowed_operations* when a permission is required
also fails closed (callers must supply the live profile op list).
"""
if roles_compatible(active_role, required_role):
return True
perm = (required_permission or "").strip()
if not perm:
return False
if allowed_operations is None:
return False
try:
ops = {str(o).strip() for o in allowed_operations if o is not None}
except TypeError:
return False
return perm in ops
def _blocker(
kind: str,
reasons: list[str],
*,
exact_next_action: str | None = None,
detail: dict | None = None,
) -> dict[str, Any]:
if kind not in BLOCKER_KINDS:
raise ValueError(f"unknown anti-stomp blocker kind: {kind!r}")
return {
"kind": kind,
"reasons": list(reasons),
"exact_next_action": exact_next_action or _NEXT_ACTIONS[kind],
"detail": dict(detail or {}),
}
def _allowed_result(checks: dict[str, Any]) -> dict[str, Any]:
return {
"allowed": True,
"block": False,
"blockers": [],
"reasons": [],
"exact_next_action": "proceed",
"blocker_kind": None,
"checks": checks,
}
def _blocked_result(
blockers: list[dict[str, Any]],
checks: dict[str, Any],
) -> dict[str, Any]:
primary = blockers[0]
all_reasons: list[str] = []
for b in blockers:
for r in b.get("reasons") or []:
if r not in all_reasons:
all_reasons.append(r)
return {
"allowed": False,
"block": True,
"blockers": blockers,
"reasons": all_reasons,
"exact_next_action": primary["exact_next_action"],
"blocker_kind": primary["kind"],
"checks": checks,
}
def assess_anti_stomp_preflight(
*,
task: str | None = None,
# repo/org
remote: str | None = None,
resolved_org: str | None = None,
resolved_repo: str | None = None,
local_remote_url: str | None = None,
org_explicit: bool = False,
repo_explicit: bool = False,
check_repo: bool = True,
# profile/role + capability
profile_name: str | None = None,
profile_role: str | None = None,
required_role: str | None = None,
required_permission: str | None = None,
allowed_operations: Any = None,
check_role: bool = True,
# root checkout + worktree
workspace_path: str | None = None,
project_root: str | None = None,
current_branch: str | None = None,
root_head_sha: str | None = None,
root_porcelain: str | None = None,
remote_master_sha: str | None = None,
check_root_checkout: bool = True,
check_worktree: bool = True,
# stale runtime (master parity)
startup_head: str | None = None,
current_code_head: str | None = None,
check_stale_runtime: bool = True,
# lease ownership
lease_required: bool = False,
foreign_lease: bool | None = None,
lease_owner_session: str | None = None,
active_session_id: str | None = None,
lease_owner_identity: str | None = None,
active_identity: str | None = None,
lease_reasons: list[str] | None = None,
# terminal lock
terminal_lock_blocks: bool | None = None,
terminal_lock_reasons: list[str] | None = None,
# expected head SHA
require_head_sha: bool = False,
expected_head_sha: str | None = None,
live_head_sha: str | None = None,
# workflow hash
workflow_hash_valid: bool | None = None,
workflow_hash_reasons: list[str] | None = None,
# source contamination (stable-branch push / approval contamination)
source_contaminated: bool | None = None,
contamination_reasons: list[str] | None = None,
# manual bypass
manual_bypass_attempted: bool = False,
manual_bypass_reasons: list[str] | None = None,
) -> dict[str, Any]:
"""Fail-closed common anti-stomp assessment (pure).
Only checks for which facts are supplied (or which are required by the
mutation category) are evaluated. Unsupplied optional facts are recorded
as ``skipped`` so callers can see coverage without inventing defaults.
Returns a structured dict with ``allowed``/``block``, typed ``blockers``,
aggregated ``reasons``, ``exact_next_action``, and per-check ``checks``.
"""
task_name = (task or "").strip()
role = (profile_role or "").strip().lower() or None
req_role = (required_role or "").strip().lower() or None
req_perm = (required_permission or "").strip() or None
checks: dict[str, Any] = {
"task": task_name or None,
"profile_name": profile_name,
"profile_role": role,
"required_role": req_role,
"required_permission": req_perm,
}
blockers: list[dict[str, Any]] = []
# ── manual bypass (always first; never skippable when attempted) ─────────
if manual_bypass_attempted:
reasons = list(manual_bypass_reasons or [
"manual state/mtime/source-file bypass attempt detected (fail closed)"
])
blockers.append(_blocker(BLOCKER_MANUAL_BYPASS, reasons))
checks["manual_bypass"] = {"block": True, "reasons": reasons}
else:
checks["manual_bypass"] = {"block": False, "skipped": False}
# ── repo/org ─────────────────────────────────────────────────────────────
if check_repo and resolved_org is not None and resolved_repo is not None:
repo_assessment = remote_repo_guard.assess_remote_repo_match(
remote=remote or "",
resolved_org=resolved_org,
resolved_repo=resolved_repo,
local_remote_url=local_remote_url,
org_explicit=org_explicit,
repo_explicit=repo_explicit,
)
checks["repo"] = {
"block": bool(repo_assessment.get("block")),
"reasons": list(repo_assessment.get("reasons") or []),
"resolved_org": resolved_org,
"resolved_repo": resolved_repo,
}
if repo_assessment.get("block"):
blockers.append(
_blocker(
BLOCKER_WRONG_REPO,
list(repo_assessment.get("reasons") or ["repo/org mismatch"]),
detail={
"resolved_org": resolved_org,
"resolved_repo": resolved_repo,
"local_remote_url": local_remote_url,
},
)
)
else:
checks["repo"] = {"block": False, "skipped": True}
# ── profile/role + capability ────────────────────────────────────────────
# Role match OR possession of the task's required permission (Blocker A).
# Reviewer/merger may run issue-comment-class tasks when they hold
# gitea.issue.comment; unauthorized escalation without the permission
# still fails closed.
if check_role and req_role and role:
authorized = authorization_compatible(
role,
req_role,
required_permission=req_perm,
allowed_operations=allowed_operations,
)
if not authorized:
perm_clause = (
f", required_permission='{req_perm}'" if req_perm else ""
)
reasons = [
f"active profile role '{role}' is not authorized for task "
f"'{task_name or '(unknown)'}' (required_role='{req_role}'"
f"{perm_clause}; profile={profile_name or '(unknown)'})"
]
checks["role"] = {
"block": True,
"reasons": reasons,
"required_permission": req_perm,
"capability_authorized": False,
}
blockers.append(
_blocker(
BLOCKER_WRONG_ROLE,
reasons,
detail={
"profile_name": profile_name,
"profile_role": role,
"required_role": req_role,
"required_permission": req_perm,
},
)
)
else:
checks["role"] = {
"block": False,
"reasons": [],
"required_permission": req_perm,
"capability_authorized": bool(
req_perm
and allowed_operations is not None
and req_perm in {
str(o).strip() for o in (allowed_operations or [])
if o is not None
}
and not roles_compatible(role, req_role)
),
}
else:
checks["role"] = {"block": False, "skipped": True}
# ── stale runtime (master parity) ────────────────────────────────────────
if check_stale_runtime and (
startup_head is not None or current_code_head is not None
):
parity = master_parity_gate.assess_master_parity(
{"startup_head": startup_head},
current_code_head,
)
stale_reasons = master_parity_gate.parity_block_reasons(parity)
checks["stale_runtime"] = {
"block": bool(stale_reasons),
"reasons": list(stale_reasons),
"startup_head": startup_head,
"current_code_head": current_code_head,
"stale": bool(parity.get("stale")),
}
if stale_reasons:
blockers.append(
_blocker(
BLOCKER_STALE_RUNTIME,
list(stale_reasons),
detail={
"startup_head": startup_head,
"current_code_head": current_code_head,
},
)
)
else:
checks["stale_runtime"] = {"block": False, "skipped": True}
# ── root checkout ────────────────────────────────────────────────────────
if (
check_root_checkout
and workspace_path is not None
and project_root is not None
and root_porcelain is not None
):
root_assessment = root_checkout_guard.assess_root_checkout_guard(
workspace_path=workspace_path,
canonical_repo_root=project_root,
current_branch=current_branch,
head_sha=root_head_sha,
porcelain_status=root_porcelain,
remote_master_sha=remote_master_sha,
resolved_role=req_role or role,
actual_role=role,
)
checks["root_checkout"] = {
"block": bool(root_assessment.get("block")),
"reasons": list(root_assessment.get("reasons") or []),
}
if root_assessment.get("block"):
blockers.append(
_blocker(
BLOCKER_ROOT_CHECKOUT,
list(root_assessment.get("reasons") or [
"control checkout is not clean master"
]),
detail={
"workspace_path": workspace_path,
"project_root": project_root,
"current_branch": current_branch,
},
)
)
else:
checks["root_checkout"] = {"block": False, "skipped": True}
# ── worktree under branches (author) ─────────────────────────────────────
worktree_role = role or req_role
if (
check_worktree
and workspace_path is not None
and project_root is not None
and worktree_role in _BRANCHES_REQUIRED_ROLES
):
wt = author_mutation_worktree.assess_author_mutation_worktree(
workspace_path=workspace_path,
project_root=project_root,
current_branch=current_branch,
)
checks["worktree"] = {
"block": bool(wt.get("block")),
"reasons": list(wt.get("reasons") or []),
"under_branches": wt.get("under_branches"),
}
if wt.get("block"):
blockers.append(
_blocker(
BLOCKER_WRONG_WORKTREE,
list(wt.get("reasons") or [
"mutation worktree is not under branches/"
]),
detail={
"workspace_path": workspace_path,
"project_root": project_root,
},
)
)
else:
checks["worktree"] = {
"block": False,
"skipped": worktree_role not in _BRANCHES_REQUIRED_ROLES
or workspace_path is None,
}
# ── foreign lease ────────────────────────────────────────────────────────
lease_needed = lease_required or (
task_name.removeprefix("gitea_") in {
t.removeprefix("gitea_") for t in _LEASE_AWARE_TASKS
}
and foreign_lease is not None
)
if lease_needed or foreign_lease is True:
is_foreign = bool(foreign_lease)
if foreign_lease is None and lease_required:
# Ownership must be proven when lease_required; missing ownership
# facts fail closed.
owner_ok = (
(not lease_owner_session and not active_session_id)
or (
lease_owner_session
and active_session_id
and lease_owner_session == active_session_id
)
)
identity_ok = (
(not lease_owner_identity and not active_identity)
or (
lease_owner_identity
and active_identity
and lease_owner_identity == active_identity
)
)
if not owner_ok or not identity_ok:
is_foreign = True
reasons = list(lease_reasons or [])
if is_foreign and not reasons:
reasons = [
"active lease is owned by a foreign session or identity "
"(anti-stomp fail closed)"
]
checks["lease"] = {
"block": is_foreign,
"reasons": reasons if is_foreign else [],
"lease_owner_session": lease_owner_session,
"active_session_id": active_session_id,
}
if is_foreign:
blockers.append(
_blocker(BLOCKER_FOREIGN_LEASE, reasons)
)
else:
checks["lease"] = {"block": False, "skipped": True}
# ── terminal lock ────────────────────────────────────────────────────────
if terminal_lock_blocks is not None:
reasons = list(terminal_lock_reasons or [])
if terminal_lock_blocks and not reasons:
reasons = [
"terminal review-decision lock is active for this head "
"(anti-stomp fail closed)"
]
checks["terminal_lock"] = {
"block": bool(terminal_lock_blocks),
"reasons": reasons if terminal_lock_blocks else [],
}
if terminal_lock_blocks:
blockers.append(_blocker(BLOCKER_TERMINAL_LOCK, reasons))
else:
checks["terminal_lock"] = {"block": False, "skipped": True}
# ── expected head SHA ────────────────────────────────────────────────────
if require_head_sha or (
expected_head_sha is not None and live_head_sha is not None
):
exp = (expected_head_sha or "").strip().lower()
live = (live_head_sha or "").strip().lower()
mismatch = False
reasons: list[str] = []
if require_head_sha and not exp:
mismatch = True
reasons.append(
"expected_head_sha is required before this mutation "
"(anti-stomp fail closed)"
)
elif exp and live and exp != live:
mismatch = True
reasons.append(
f"expected_head_sha '{exp}' does not match live PR head "
f"'{live}' (anti-stomp fail closed; stale prompt data)"
)
elif require_head_sha and exp and not live:
mismatch = True
reasons.append(
"live PR head SHA could not be determined to corroborate "
"expected_head_sha (anti-stomp fail closed)"
)
checks["head_sha"] = {
"block": mismatch,
"reasons": reasons,
"expected_head_sha": expected_head_sha,
"live_head_sha": live_head_sha,
}
if mismatch:
blockers.append(_blocker(BLOCKER_HEAD_SHA, reasons))
else:
checks["head_sha"] = {"block": False, "skipped": True}
# ── workflow hash ────────────────────────────────────────────────────────
if workflow_hash_valid is not None:
reasons = list(workflow_hash_reasons or [])
if not workflow_hash_valid and not reasons:
reasons = [
"workflow load proof missing or hash stale "
"(anti-stomp fail closed)"
]
checks["workflow_hash"] = {
"block": not bool(workflow_hash_valid),
"reasons": reasons if not workflow_hash_valid else [],
}
if not workflow_hash_valid:
blockers.append(_blocker(BLOCKER_WORKFLOW_HASH, reasons))
else:
checks["workflow_hash"] = {"block": False, "skipped": True}
# ── source contamination ─────────────────────────────────────────────────
if source_contaminated is not None:
reasons = list(contamination_reasons or [])
if source_contaminated and not reasons:
reasons = [
"session is source-contaminated (stable-branch push or "
"contaminated approval path); anti-stomp fail closed"
]
checks["source_contamination"] = {
"block": bool(source_contaminated),
"reasons": reasons if source_contaminated else [],
}
if source_contaminated:
blockers.append(
_blocker(BLOCKER_SOURCE_CONTAMINATION, reasons)
)
else:
checks["source_contamination"] = {"block": False, "skipped": True}
if blockers:
return _blocked_result(blockers, checks)
return _allowed_result(checks)
def format_anti_stomp_error(assessment: dict[str, Any]) -> str:
"""Single RuntimeError message for MCP mutation gates."""
kind = assessment.get("blocker_kind") or "unknown"
reasons = "; ".join(
assessment.get("reasons")
or ["anti-stomp preflight blocked the mutation"]
)
next_action = assessment.get("exact_next_action") or "stop and diagnose"
return (
f"Anti-stomp preflight (#604) blocked mutation "
f"[{kind}]: {reasons}. "
f"exact_next_action: {next_action}"
)
def block_response(
assessment: dict[str, Any],
**extra_fields: Any,
) -> dict[str, Any]:
"""Structured tool-return payload for a blocked mutation."""
payload = {
"success": False,
"performed": False,
"blocked": True,
"anti_stomp": True,
"blocker_kind": assessment.get("blocker_kind"),
"blockers": list(assessment.get("blockers") or []),
"reasons": list(assessment.get("reasons") or []),
"exact_next_action": assessment.get("exact_next_action"),
"checks": assessment.get("checks") or {},
}
payload.update(extra_fields)
return payload
def contamination_from_stable_marker(
marker: dict | None,
*,
task: str | None,
actual_role: str | None,
) -> tuple[bool, list[str]]:
"""Derive source-contamination facts from a #671 durable marker."""
if not marker:
return False, []
gate = stable_branch_push_guard.assess_contamination_gate(
marker,
task=task,
actual_role=actual_role,
)
if gate.get("block"):
return True, list(gate.get("reasons") or [])
return False, []
+138
View File
@@ -0,0 +1,138 @@
# Self-hosted Sentry observability for the Gitea MCP server (#606)
Optional, **off-by-default** instrumentation that reports MCP runtime errors,
fail-closed workflow blockers, lease / terminal-lock / stale-runtime
collisions, and recurring watchdog check-ins to a **self-hosted** Sentry at
`https://sentry.prgs.cc/`.
> **Gitea remains the source of truth.** Sentry is observe-only. It never
> approves, merges, closes, or otherwise mutates Gitea workflow state, and it
> never bypasses leases, #332, workflow roles, or the MCP gates. Sentry alerts
> may only feed the *sanctioned* Gitea issue/comment path via the #612 incident
> bridge — never a direct write.
Implemented by [`sentry_observability.py`](../../sentry_observability.py).
---
## 1. Create the Sentry project
1. Sign in to the self-hosted Sentry at **`https://sentry.prgs.cc/`** (this is
**not** Sentry Cloud — do not use `*.ingest.sentry.io`).
2. Create a new **Python** project named **`gitea-tools-mcp`**.
3. Open **Settings → Projects → gitea-tools-mcp → Client Keys (DSN)** and copy
the DSN. It looks like `https://<publickey>@sentry.prgs.cc/<project-id>`.
4. **Never commit the DSN.** It is a runtime secret supplied via env var only.
## 2. Configure the environment
All configuration is env-var driven (see [`.env.example`](../../.env.example)):
| Variable | Purpose | Default |
|----------|---------|---------|
| `MCP_SENTRY_ENABLED` | Master gate (`1/true/yes/on`). Required. | off |
| `SENTRY_DSN` | Self-hosted DSN. Required. | *(empty)* |
| `SENTRY_ENVIRONMENT` | `local` / `dev` / `prod` tag. | `development` |
| `SENTRY_RELEASE` | Release id (git SHA or version). | *(none)* |
| `MCP_SENTRY_TRACES_SAMPLE_RATE` | Perf-trace sample rate `0.01.0` (clamped). | `0.0` |
| `MCP_SENTRY_ENABLE_LOGS` | Forward Python logs as structured logs. | off |
**The feature stays completely off unless `MCP_SENTRY_ENABLED` is truthy *and*
`SENTRY_DSN` is non-empty.** With either missing, `init_sentry()` is a no-op,
the SDK is never initialised, and no events are sent — existing tool behaviour
and API-call patterns are unchanged.
### Per-environment examples
```bash
# local (quiet: capture errors/blockers, no traces)
export MCP_SENTRY_ENABLED=1
export SENTRY_DSN="https://<key>@sentry.prgs.cc/<id>"
export SENTRY_ENVIRONMENT=local
# dev (light tracing + logs)
export MCP_SENTRY_ENABLED=1
export SENTRY_DSN="https://<key>@sentry.prgs.cc/<id>"
export SENTRY_ENVIRONMENT=dev
export MCP_SENTRY_TRACES_SAMPLE_RATE=0.2
export MCP_SENTRY_ENABLE_LOGS=1
# prod (errors/blockers + low-rate tracing, release-tagged)
export MCP_SENTRY_ENABLED=1
export SENTRY_DSN="https://<key>@sentry.prgs.cc/<id>"
export SENTRY_ENVIRONMENT=prod
export SENTRY_RELEASE="$(git rev-parse --short HEAD)"
export MCP_SENTRY_TRACES_SAMPLE_RATE=0.05
```
The optional SDK is pinned in [`requirements.txt`](../../requirements.txt)
(`sentry-sdk==2.20.0`). It is imported lazily: if the package is absent, the
module still imports and every entry point is a safe no-op.
## 3. What is instrumented
| Signal | Where | Notes |
|--------|-------|-------|
| Startup init | `gitea_mcp_server.py` `__main__`, before `mcp.run` | Prints a redaction-safe status line to stderr. |
| Failing mutations (exceptions) | `_audited(...)` context manager | `capture_exception` with scrubbed tags. |
| Fail-closed blockers / failed mutations | `_audit_pr_result(...)` (BLOCKED/FAILED) | Structured `capture_workflow_blocker` event incl. the canonical next action when available (criterion 7). |
| Allocator watchdog check-ins | `gitea_allocate_next_work` tool | `allocator_health`, `stale_lease_scan`, `terminal_lock_scan`. |
| Namespace-health check-in | `gitea_assess_mcp_namespace_health` tool | `namespace_health`. |
All capture paths are **best-effort / fail open**: a Sentry outage or capture
error never breaks an MCP tool success path.
## 4. Cron / watchdog monitors
`sentry_observability.MONITOR_SLUGS` defines stable check-in slugs:
| Registry key | Sentry monitor slug | Wired at |
|--------------|--------------------|----------|
| `stale_lease_scan` | `gitea-mcp-stale-lease-scan` | allocator run (global lease expiry) |
| `terminal_lock_scan` | `gitea-mcp-terminal-lock-scan` | allocator run (terminal-lock lookup) |
| `allocator_health` | `gitea-mcp-allocator-health` | allocator run |
| `namespace_health` | `gitea-mcp-namespace-health` | namespace-health probe |
| `dashboard_freshness` | `gitea-mcp-dashboard-freshness` | call `monitor_checkin("dashboard_freshness", ...)` from the dashboard refresh job (#605) |
| `reconciler_cleanup` | `gitea-mcp-reconciler-cleanup` | call `monitor_checkin("reconciler_cleanup", ...)` from the reconciler cleanup entrypoint |
Create matching Cron monitors in Sentry with those slugs. Emit an
`in_progress` check-in at job start and `ok`/`error` at completion via
`sentry_observability.monitor_checkin(slug_key, status)`.
## 5. Redaction guarantees (fail closed)
Redaction fails *closed*: if a field cannot be proven safe it is dropped rather
than sent. The `before_send` (and `before_send_log`) hook `scrub_event`
recursively redacts every outgoing event; on any error it drops the event
entirely. Guarantees, proven by `tests/test_sentry_observability.py`:
- **No** tokens, passwords, keychain IDs, DSNs, cookies, or `user:pass@host`.
- **No** raw session-state or full prompt/comment bodies — `session_id` is only
ever surfaced as a 12-char `session_id_hash`.
- **No** private config contents or raw credential headers.
- **No** full local filesystem paths — a worktree path collapses to a coarse
`worktree_category` (`author` / `reviewer` / `merger` / `reconciler` /
`branches` / `root` / `other`).
- Only the allowlisted tag keys in `ALLOWED_TAG_KEYS` are ever attached.
## 6. Coexistence with GlitchTip / the #612 incident bridge
This is the **outbound** path (MCP → Sentry SDK). It complements — it does not
replace — the **inbound** [`incident_bridge.py`](../../incident_bridge.py)
(#612), which turns Sentry/GlitchTip *observations* into durable Gitea issues
and `incident_links` rows.
- Prefer **one** observability path per environment. Point the MCP server's
`SENTRY_DSN` at the same self-hosted `gitea-tools-mcp` project that the #612
bridge reconciles from, so an MCP-reported error and its Gitea issue line up.
- GlitchTip is Sentry-protocol compatible; if an existing GlitchTip DSN is in
use, either migrate it to `https://sentry.prgs.cc/` or document the split
(MCP → Sentry, legacy → GlitchTip) explicitly for operators.
- The bridge remains the **only** sanctioned route from an alert back into
Gitea workflow state.
## 7. Non-goals
- Sentry must **not** become the workflow source of truth.
- Sentry must **not** approve, merge, close, or mutate Gitea workflow state.
- Sentry must **not** bypass leases, #332, workflow roles, or the MCP gates.
+53 -282
View File
@@ -619,219 +619,18 @@ def _enforce_branches_only_author_mutation(worktree_path: str | None = None) ->
)
def _anti_stomp_in_test_mode() -> bool:
"""Whether the #604 anti-stomp gate is skipped under pytest.
Mirrors remote-repo / stable-contamination test bypasses so the existing
suite (bare remotes, mocked APIs) stays green. Set
``GITEA_TEST_FORCE_ANTI_STOMP=1`` to exercise the live gate under tests.
"""
if not _preflight_in_test_mode():
return False
return not bool(os.environ.get("GITEA_TEST_FORCE_ANTI_STOMP"))
def _run_anti_stomp_preflight(
task: str | None,
*,
remote: str | None = None,
worktree_path: str | None = None,
host: str | None = None,
org: str | None = None,
repo: str | None = None,
expected_head_sha: str | None = None,
live_head_sha: str | None = None,
require_head_sha: bool = False,
lease_required: bool = False,
foreign_lease: bool | None = None,
lease_reasons: list[str] | None = None,
terminal_lock_blocks: bool | None = None,
terminal_lock_reasons: list[str] | None = None,
workflow_hash_valid: bool | None = None,
workflow_hash_reasons: list[str] | None = None,
raise_on_block: bool = True,
) -> dict | None:
"""Shared #604 anti-stomp preflight for MCP mutation entrypoints.
Gathers live workspace/parity/role/repo facts and invokes the pure
:func:`anti_stomp_preflight.assess_anti_stomp_preflight` assessor. On
block, raises ``RuntimeError`` (default) or returns a structured
:func:`anti_stomp_preflight.block_response` when *raise_on_block* is
False. Returns ``None`` when the mutation may proceed.
"""
if _anti_stomp_in_test_mode():
return None
# Only enforce when the caller names a known mutation task. Read-only
# paths and legacy verify_preflight_purity calls without a task stay
# on the pre-#604 gate chain (whoami/capability/root/worktree).
if not task or not anti_stomp_preflight.is_mutation_task(task):
return None
profile = get_profile()
profile_name = profile.get("profile_name")
profile_role = _actual_profile_role()
allowed_operations = list(profile.get("allowed_operations") or [])
req_role = None
req_perm = None
if task:
try:
req_role = task_capability_map.required_role(task)
except KeyError:
req_role = _preflight_resolved_role
try:
req_perm = task_capability_map.required_permission(task)
except KeyError:
req_perm = None
ctx = _resolve_namespace_mutation_context(worktree_path)
workspace = ctx["workspace_path"]
canonical_root = ctx["canonical_repo_root"]
git_state = issue_lock_worktree.read_worktree_git_state(canonical_root)
remote_master_sha = root_checkout_guard.resolve_remote_master_sha(canonical_root)
# Repo/org facts (best-effort; explicit org/repo when provided).
resolved_org = org
resolved_repo = repo
local_remote_url = None
org_explicit = org is not None
repo_explicit = repo is not None
if remote:
try:
local_remote_url = _local_git_remote_url(remote)
except Exception:
local_remote_url = None
if resolved_org is None or resolved_repo is None:
try:
rem = _effective_remote(remote)
if rem in REMOTES:
if resolved_org is None:
resolved_org = REMOTES[rem]["org"]
if resolved_repo is None:
resolved_repo = REMOTES[rem]["repo"]
except Exception:
pass
parity = _current_master_parity()
startup_head = parity.get("startup_head")
current_code_head = parity.get("current_head")
# Source contamination from durable #671 marker (role-aware).
source_contaminated = None
contamination_reasons = None
try:
marker = _load_stable_contamination_marker(remote)
contaminated, cont_reasons = anti_stomp_preflight.contamination_from_stable_marker(
marker,
task=task,
actual_role=profile_role,
)
if marker is not None:
source_contaminated = contaminated
contamination_reasons = cont_reasons
except Exception:
# Fail soft on marker I/O: existing #671 enforcer still runs separately.
source_contaminated = None
# Workflow-hash facts when the task is review/merge oriented.
if workflow_hash_valid is None and task in {
"review_pr",
"submit_pr_review",
"approve_pr",
"request_changes_pr",
"merge_pr",
}:
try:
wf_reasons = _review_workflow_load_gate_reasons()
workflow_hash_valid = not bool(wf_reasons)
workflow_hash_reasons = list(wf_reasons) if wf_reasons else None
except Exception:
pass
# Mirror remote_repo_guard's pytest bypass: under the unit suite bare
# remote=prgs still defaults to Timesheet, and re-checking here would
# break happy-path reconciler/author tests that already rely on the
# #530 gate being opt-in via GITEA_FORCE_REMOTE_REPO_CHECK.
check_repo = True
if "pytest" in sys.modules and not os.environ.get(
"GITEA_FORCE_REMOTE_REPO_CHECK"
):
check_repo = False
assessment = anti_stomp_preflight.assess_anti_stomp_preflight(
task=task,
remote=remote,
resolved_org=resolved_org,
resolved_repo=resolved_repo,
local_remote_url=local_remote_url,
org_explicit=org_explicit,
repo_explicit=repo_explicit,
check_repo=check_repo,
profile_name=profile_name,
profile_role=profile_role,
required_role=req_role or _preflight_resolved_role,
required_permission=req_perm,
allowed_operations=allowed_operations,
workspace_path=workspace,
project_root=canonical_root,
current_branch=git_state.get("current_branch"),
root_head_sha=git_state.get("head_sha"),
root_porcelain=git_state.get("porcelain_status") or "",
remote_master_sha=remote_master_sha,
startup_head=startup_head,
current_code_head=current_code_head,
lease_required=lease_required,
foreign_lease=foreign_lease,
lease_reasons=lease_reasons,
terminal_lock_blocks=terminal_lock_blocks,
terminal_lock_reasons=terminal_lock_reasons,
require_head_sha=require_head_sha,
expected_head_sha=expected_head_sha,
live_head_sha=live_head_sha,
workflow_hash_valid=workflow_hash_valid,
workflow_hash_reasons=workflow_hash_reasons,
source_contaminated=source_contaminated,
contamination_reasons=contamination_reasons,
manual_bypass_attempted=False,
)
if not assessment.get("block"):
return None
if raise_on_block:
raise RuntimeError(anti_stomp_preflight.format_anti_stomp_error(assessment))
return anti_stomp_preflight.block_response(assessment)
def verify_preflight_purity(
remote: str | None = None,
worktree_path: str | None = None,
task: str | None = None,
*,
expected_head_sha: str | None = None,
live_head_sha: str | None = None,
require_head_sha: bool = False,
lease_required: bool = False,
foreign_lease: bool | None = None,
lease_reasons: list[str] | None = None,
terminal_lock_blocks: bool | None = None,
terminal_lock_reasons: list[str] | None = None,
workflow_hash_valid: bool | None = None,
workflow_hash_reasons: list[str] | None = None,
org: str | None = None,
repo: str | None = None,
):
"""Verify that identity and capability were verified prior to session edits.
Also runs the shared #604 anti-stomp preflight for mutation tasks (typed
blocker + exact next action). Extended lease/head/terminal facts may be
supplied by review/merge callers.
"""
"""Verify that identity and capability were verified prior to session edits."""
global _preflight_reviewer_violation_files
in_test = _preflight_in_test_mode()
if in_test and not (
os.environ.get("GITEA_TEST_FORCE_DIRTY")
or os.environ.get("GITEA_TEST_PORCELAIN") is not None
or os.environ.get("GITEA_TEST_FORCE_ANTI_STOMP")
):
return
@@ -918,30 +717,6 @@ def verify_preflight_purity(
_enforce_root_checkout_guard(worktree_path)
_enforce_branches_only_author_mutation(worktree_path)
# #604: common anti-stomp preflight (typed blocker + exact next action).
# Runs after the legacy enforcers so existing happy paths stay green and
# the shared module remains the single fail-closed composition point for
# repo/role/worktree/lease/terminal-lock/head/stale/workflow/contamination.
_run_anti_stomp_preflight(
task,
remote=remote,
worktree_path=worktree_path,
org=org,
repo=repo,
expected_head_sha=expected_head_sha,
live_head_sha=live_head_sha,
require_head_sha=require_head_sha,
lease_required=lease_required,
foreign_lease=foreign_lease,
lease_reasons=lease_reasons,
terminal_lock_blocks=terminal_lock_blocks,
terminal_lock_reasons=terminal_lock_reasons,
workflow_hash_valid=workflow_hash_valid,
workflow_hash_reasons=workflow_hash_reasons,
raise_on_block=True,
)
_clear_preflight_capability_state()
@@ -1143,6 +918,7 @@ import allocator_service # noqa: E402
import control_plane_db # noqa: E402
import lease_lifecycle # noqa: E402
import incident_bridge # noqa: E402
import sentry_observability # noqa: E402 (#606 optional Sentry observability)
import agent_temp_artifacts
import issue_lock_worktree # noqa: E402
import issue_lock_provenance # noqa: E402
@@ -1155,7 +931,6 @@ import author_mutation_worktree # noqa: E402
import root_checkout_guard # noqa: E402
import stable_branch_push_guard # noqa: E402
import remote_repo_guard # noqa: E402
import anti_stomp_preflight # noqa: E402
import issue_claim_heartbeat # noqa: E402
import issue_work_duplicate_gate # noqa: E402
import issue_workflow_labels # noqa: E402
@@ -2003,6 +1778,18 @@ def _audited(action: str, *, host, remote, org=None, repo=None,
result=gitea_audit.FAILED, reason=_redact(str(exc)),
request_metadata=request_metadata, issue_number=issue_number,
pr_number=pr_number, target_branch=target_branch)
# #606: best-effort Sentry capture of the failing mutation (fail open).
sentry_observability.capture_exception(
exc,
tags={
"mutation_tool": action,
"remote": remote,
"repo": repo,
"org": org,
"issue_number": issue_number,
"pr_number": pr_number,
},
)
raise
_audit(action, host=host, remote=remote, org=org, repo=repo,
result=gitea_audit.SUCCEEDED, request_metadata=request_metadata,
@@ -2049,6 +1836,20 @@ def _audit_pr_result(action: str):
"merge_method": result.get("merge_method"),
},
)
# #606: surface fail-closed blockers / failed mutations to
# Sentry as structured events (best-effort, fail open).
if status in (gitea_audit.BLOCKED, gitea_audit.FAILED):
sentry_observability.capture_workflow_blocker(
action,
message="; ".join(reasons) or action,
next_action=result.get("safe_next_action"),
level="error" if status == gitea_audit.FAILED else "warning",
tags={
"mutation_tool": action,
"pr_number": result.get("pr_number"),
"current_head_sha": result.get("head_sha"),
},
)
except Exception:
pass # best-effort; never break the tool
return result
@@ -4059,30 +3860,6 @@ def _evaluate_pr_review_submission(
result["pr_work_lease"] = lease_block
return result
if live:
# #604: common anti-stomp with live head + lease proof (typed blocker).
anti_task = {
"approve": "approve_pr",
"request_changes": "request_changes_pr",
"comment": "submit_pr_review",
}.get(action, "submit_pr_review")
try:
_run_anti_stomp_preflight(
anti_task,
remote=remote,
worktree_path=worktree_path,
org=org,
repo=repo,
expected_head_sha=pinned_sha,
live_head_sha=actual_sha,
require_head_sha=True,
foreign_lease=False,
terminal_lock_blocks=False,
)
except RuntimeError as exc:
reasons.append(str(exc))
return result
if (body or "").strip():
gate = _canonical_comment_gate(body, context="pr_review")
if gate["blocked"]:
@@ -5037,12 +4814,7 @@ def gitea_edit_pr(
raise ValueError("At least one field to edit (title, body, state, base) must be provided.")
closing = payload.get("state") == "closed"
# Closing uses close_pr; non-closing title/body/base edits use edit_pr so
# the shared #604 anti-stomp inventory stays consistent with wiring.
if closing:
verify_preflight_purity(remote, task="close_pr")
else:
verify_preflight_purity(remote, task="edit_pr")
verify_preflight_purity(remote, task="close_pr" if closing else None)
# PR closure is a first-class capability, distinct from retitling or
# rebasing edits (#216). Gate BEFORE auth/API setup so a blocked close
@@ -5524,25 +5296,6 @@ def gitea_merge_pr(
reasons.extend(lease_block.get("reasons") or [])
result["pr_work_lease"] = lease_block
return result
# #604: common anti-stomp with live head + lease proof (typed blocker).
try:
_run_anti_stomp_preflight(
"merge_pr",
remote=remote,
worktree_path=worktree_path,
org=org,
repo=repo,
expected_head_sha=expected_head_sha,
live_head_sha=actual_sha,
require_head_sha=True,
foreign_lease=False,
terminal_lock_blocks=False,
)
except RuntimeError as exc:
reasons.append(str(exc))
return result
if expected_head_sha and actual_sha and expected_head_sha != actual_sha:
reasons.append(
"expected head SHA does not match current PR head (fail closed)"
@@ -7662,11 +7415,7 @@ def gitea_acquire_reviewer_pr_lease(
"permission_report": _permission_block_report("gitea.pr.comment"),
}
# task=acquire_reviewer_pr_lease so verify_preflight_purity runs shared #604
# anti-stomp for the declared lease-acquire mutation inventory entry.
_verify_role_mutation_workspace(
remote, worktree=worktree, task="acquire_reviewer_pr_lease"
)
_verify_role_mutation_workspace(remote, worktree=worktree, task="review_pr")
h, o, r = _resolve(remote, host, org, repo)
auth = _auth(h)
profile = get_profile()
@@ -7807,7 +7556,6 @@ def gitea_adopt_merger_pr_lease(
"permission_report": _permission_block_report("gitea.pr.merge"),
}
# task=adopt_merger_pr_lease so verify_preflight_purity runs shared #604 anti-stomp.
_verify_role_mutation_workspace(
remote, worktree=worktree, task="adopt_merger_pr_lease"
)
@@ -10233,6 +9981,11 @@ def gitea_assess_mcp_namespace_health(
probe_source=probe_source,
)
_record_live_namespace_health(result)
# #606: namespace-health watchdog check-in (best-effort, fail open).
sentry_observability.monitor_checkin(
"namespace_health",
"ok" if result.get("healthy", result.get("callable", True)) else "error",
)
return result
@@ -12160,6 +11913,18 @@ def gitea_allocate_next_work(
result["inventory_source"] = (
"candidates_json" if candidates_json else "gitea_live"
)
# #606: watchdog check-ins for the recurring jobs this allocator run
# performs — global stale-lease expiry, terminal-lock lookup, and the
# allocator itself. Best-effort; a failed selection reports "error".
_alloc_ok = bool(result.get("success"))
sentry_observability.monitor_checkin(
"allocator_health", "ok" if _alloc_ok else "error"
)
if _alloc_ok:
# These two scans complete inside allocate_next_work before selection;
# a successful result proves both ran.
sentry_observability.monitor_checkin("stale_lease_scan", "ok")
sentry_observability.monitor_checkin("terminal_lock_scan", "ok")
return result
@@ -12484,4 +12249,10 @@ if __name__ == "__main__":
# processes (e.g. review_pr.py) can detect and refuse profile
# side-channel overrides (#199).
_export_session_profile_lock()
# #606: optional self-hosted Sentry observability. No-op unless
# MCP_SENTRY_ENABLED is truthy and SENTRY_DSN is set; never blocks startup.
_sentry_status = sentry_observability.init_sentry()
sys.stderr.write(
f"--- Sentry observability: {_sentry_status.get('reason')} ---\n"
)
mcp.run(transport="stdio")
+1
View File
@@ -31,6 +31,7 @@ python-multipart==0.0.32
referencing==0.37.0
rich==15.0.0
rpds-py==2026.5.1
sentry-sdk==2.20.0
shellingham==1.5.4
sse-starlette==3.4.5
starlette==1.3.1
+535
View File
@@ -0,0 +1,535 @@
"""Optional self-hosted Sentry observability for the Gitea MCP server (#606).
Adds env-var-gated Sentry SDK instrumentation so runtime errors, fail-closed
workflow blockers, lease/terminal-lock/stale-runtime collisions, and recurring
watchdog check-ins are visible in a *self-hosted* Sentry at
``https://sentry.prgs.cc/`` — never Sentry Cloud, and never as the workflow
source of truth (Gitea stays canonical).
Design constraints (mirror ``gitea_audit`` and the #612 incident bridge):
- **Off by default.** With ``MCP_SENTRY_ENABLED`` false/unset *or* ``SENTRY_DSN``
empty, ``init_sentry`` is a no-op and no events are ever sent — existing tool
behaviour and API-call patterns are unchanged (acceptance criterion 1).
- **Fail *open* for observability.** A Sentry outage, a missing ``sentry_sdk``
package, or any capture error must never break an MCP tool success path. Every
public entry point swallows its own exceptions.
- **Fail *closed* for redaction.** If a field cannot be proven safe it is dropped
rather than sent. Tokens, passwords, keychain IDs, DSNs, private config, raw
session-state, full prompt bodies, and full filesystem paths never leave here.
- **No hard dependency.** ``sentry_sdk`` is imported lazily; the module is fully
importable and testable without it installed.
Sentry is observe-only: it must not approve, merge, close, or otherwise mutate
Gitea workflow state, nor bypass leases, #332, or MCP gates. Alerts may only feed
the sanctioned Gitea issue/comment path via the #612 incident bridge.
"""
from __future__ import annotations
import hashlib
import os
import re
from dataclasses import dataclass
from typing import Any
# Reuse the most comprehensive existing scrubber so redaction stays consistent
# with the #612 incident bridge (tokens, DSNs, cookies, bearer/basic, keychain
# ids, session ids, user:pass@host).
from incident_bridge import redact_text as _redact_text
# Second, complementary scrubber: catches bare ``token <value>`` /
# ``Bearer <value>`` / ``Basic <value>`` prefixes and raw URLs that the
# incident-bridge delimiter patterns miss.
from gitea_audit import _redact_str as _redact_prefixes
# ── Optional SDK (lazy, never a hard dependency) ────────────────────────────
try: # pragma: no cover - trivial import guard
import sentry_sdk # type: ignore
except Exception: # pragma: no cover - absence is a supported state
sentry_sdk = None # type: ignore
# ── Env var names (single source of truth) ──────────────────────────────────
ENV_ENABLED = "MCP_SENTRY_ENABLED"
ENV_DSN = "SENTRY_DSN"
ENV_ENVIRONMENT = "SENTRY_ENVIRONMENT"
ENV_RELEASE = "SENTRY_RELEASE"
ENV_TRACES_SAMPLE_RATE = "MCP_SENTRY_TRACES_SAMPLE_RATE"
ENV_ENABLE_LOGS = "MCP_SENTRY_ENABLE_LOGS"
_TRUTHY = frozenset({"1", "true", "yes", "on"})
REDACTED = "[REDACTED]"
REDACTED_PATH = "[REDACTED_PATH]"
# ── Cron / watchdog monitor slugs (acceptance criterion 6) ──────────────────
# Stable slugs for the recurring/watchdog jobs #606 wants check-ins for. The
# slug is the durable monitor identity in Sentry; the wiring call sites pass one
# of these keys (or an explicit slug) to ``monitor_checkin``.
MONITOR_SLUGS: dict[str, str] = {
"stale_lease_scan": "gitea-mcp-stale-lease-scan",
"terminal_lock_scan": "gitea-mcp-terminal-lock-scan",
"allocator_health": "gitea-mcp-allocator-health",
"namespace_health": "gitea-mcp-namespace-health",
"dashboard_freshness": "gitea-mcp-dashboard-freshness",
"reconciler_cleanup": "gitea-mcp-reconciler-cleanup",
}
_CHECKIN_STATUSES = frozenset({"in_progress", "ok", "error"})
# ── Tag allowlist (issue "Suggested Sentry tags/context") ───────────────────
# Only these keys are ever attached as Sentry tags. Anything else is dropped so
# a caller cannot accidentally leak a sensitive value through a tag.
ALLOWED_TAG_KEYS = frozenset({
"role",
"profile",
"namespace",
"repo",
"org",
"issue_number",
"pr_number",
"blocker_type",
"workflow_hash",
"session_id_hash", # hash only — never the raw session id
"pid",
"worktree_category", # category, never the full sensitive path
"lease_comment_id",
"expected_head_sha",
"current_head_sha",
"terminal_lock_state",
"capability",
"mutation_tool",
})
# Absolute-path shapes that must never be sent verbatim (macOS/Linux + temp).
_PATH_RE = re.compile(r"(?:/private)?/(?:Users|home|tmp|var|opt|Volumes)/[^\s\"']*")
# ``extra`` keys whose *full* contents are forbidden by the redaction rules
# (raw session-state, full prompt/comment bodies, private config blobs, raw
# headers).
_FORBIDDEN_EXTRA_KEYS = frozenset({
"prompt",
"prompt_body",
"next_prompt",
"body",
"raw_body",
"session_state",
"session_state_contents",
"config",
"config_contents",
"private_config",
"headers",
"authorization",
})
# ── Configuration ───────────────────────────────────────────────────────────
@dataclass(frozen=True)
class SentryConfig:
"""Immutable snapshot of the Sentry env configuration."""
enabled: bool = False
dsn: str | None = None
environment: str = "development"
release: str | None = None
traces_sample_rate: float = 0.0
enable_logs: bool = False
@property
def active(self) -> bool:
"""True only when the operator both opted in *and* supplied a DSN.
This is the single gate that keeps the feature off by default: enabling
the flag without a DSN (or vice versa) sends nothing.
"""
return bool(self.enabled and self.dsn)
def safe_summary(self) -> dict[str, Any]:
"""Operator-facing status with **no** DSN value (only presence)."""
return {
"enabled": self.enabled,
"dsn_present": bool(self.dsn),
"environment": self.environment,
"release": self.release,
"traces_sample_rate": self.traces_sample_rate,
"enable_logs": self.enable_logs,
"active": self.active,
}
def _env_bool(name: str, env: dict[str, str]) -> bool:
return (env.get(name) or "").strip().lower() in _TRUTHY
def _env_float(name: str, default: float, env: dict[str, str]) -> float:
raw = (env.get(name) or "").strip()
if not raw:
return default
try:
val = float(raw)
except (TypeError, ValueError):
return default
# Clamp to Sentry's valid [0.0, 1.0] sample-rate range.
if val < 0.0:
return 0.0
if val > 1.0:
return 1.0
return val
def load_config(env: dict[str, str] | None = None) -> SentryConfig:
"""Build a :class:`SentryConfig` from the environment (read at call time)."""
env = dict(os.environ if env is None else env)
dsn = (env.get(ENV_DSN) or "").strip() or None
return SentryConfig(
enabled=_env_bool(ENV_ENABLED, env),
dsn=dsn,
environment=(env.get(ENV_ENVIRONMENT) or "").strip() or "development",
release=(env.get(ENV_RELEASE) or "").strip() or None,
traces_sample_rate=_env_float(ENV_TRACES_SAMPLE_RATE, 0.0, env),
enable_logs=_env_bool(ENV_ENABLE_LOGS, env),
)
def sdk_available() -> bool:
"""True when the optional ``sentry_sdk`` package is importable."""
return sentry_sdk is not None
# ── Redaction (fail closed) ─────────────────────────────────────────────────
def sanitize_path(value: Any) -> str:
"""Reduce a filesystem path to a non-sensitive *category* token.
Full local paths must never be sent. We keep only a coarse worktree
category derived from the path shape (author/reviewer/merger/reconciler/
branches/root/other).
"""
text = "" if value is None else str(value)
low = text.lower()
if not text:
return "unknown"
# Order matters: more specific role markers before the generic "branches".
if "reconcile" in low:
return "reconciler"
if "review" in low:
return "reviewer"
if "merge" in low or "merger" in low:
return "merger"
if "author" in low or re.search(r"/branches/(?:feat|fix|docs|chore|issue)", low):
return "author"
if "/branches/" in low:
return "branches"
if low.rstrip("/").endswith("gitea-tools"):
return "root"
return "other"
def redact_value(value: Any) -> Any:
"""Recursively redact a JSON-able value: secret text, absolute paths, and
known-sensitive dict keys are removed. Fail closed — any error drops the
value entirely rather than risk leaking it."""
try:
if isinstance(value, dict):
out: dict[str, Any] = {}
for k, v in value.items():
key = str(k)
low = key.lower()
if low in _FORBIDDEN_EXTRA_KEYS or any(
s in low
for s in ("token", "secret", "password", "cookie", "auth", "dsn", "keychain")
):
out[key] = REDACTED
continue
out[key] = redact_value(v)
return out
if isinstance(value, (list, tuple)):
return [redact_value(v) for v in value]
if isinstance(value, str):
scrubbed = _redact_text(value)
scrubbed = _redact_prefixes(scrubbed)
scrubbed = _PATH_RE.sub(REDACTED_PATH, scrubbed)
return scrubbed
return value
except Exception:
return REDACTED
def hash_session_id(session_id: Any) -> str:
"""Short, stable, non-reversible fingerprint of a session id."""
digest = hashlib.sha256(str(session_id).encode("utf-8", "replace")).hexdigest()
return digest[:12]
def build_tags(**kwargs: Any) -> dict[str, str]:
"""Return a scrubbed, allowlisted tag dict.
``session_id`` is accepted but only ever surfaced as ``session_id_hash``.
``worktree_path`` collapses to ``worktree_category``. Any non-allowlisted
key, or a value that still contains redacted material after scrubbing, is
dropped.
"""
raw: dict[str, Any] = dict(kwargs)
# Hash the session id — never emit it raw.
session_id = raw.pop("session_id", None)
if session_id and "session_id_hash" not in raw:
raw["session_id_hash"] = hash_session_id(session_id)
# A full worktree path collapses to a category tag.
wt = raw.pop("worktree_path", None)
if wt and "worktree_category" not in raw:
raw["worktree_category"] = sanitize_path(wt)
out: dict[str, str] = {}
for key, val in raw.items():
if key not in ALLOWED_TAG_KEYS:
continue
if val is None:
continue
scrubbed = redact_value(val)
text = str(scrubbed)
if not text or REDACTED in text or REDACTED_PATH in text:
continue
if len(text) > 200:
text = text[:200] + ""
out[key] = text
return out
def scrub_event(event: Any, hint: Any = None) -> dict[str, Any] | None:
"""Sentry ``before_send`` / ``before_send_log`` hook.
Recursively redacts the outgoing event. On *any* failure it returns ``None``
so the event is dropped rather than sent unscrubbed (fail closed for
redaction).
"""
try:
if not isinstance(event, dict):
return None
scrubbed = redact_value(event)
# Drop server_name if it leaked a hostname/path; PID is kept via tags.
scrubbed.pop("server_name", None)
return scrubbed
except Exception:
return None
# ── Event builders (pure, independently testable) ───────────────────────────
def build_blocker_event(
blocker_type: str,
*,
message: str | None = None,
next_action: str | None = None,
level: str = "warning",
tags: dict[str, Any] | None = None,
extra: dict[str, Any] | None = None,
) -> dict[str, Any]:
"""Build a redacted, structured Sentry event for a workflow blocker.
``next_action`` maps the issue's "canonical next action when available"
requirement (acceptance criterion 7).
"""
merged_tags = dict(tags or {})
merged_tags.setdefault("blocker_type", blocker_type)
safe_tags = build_tags(**merged_tags)
safe_extra = redact_value(dict(extra or {}))
if next_action:
# A short canonical next action is allowed (it is not a full prompt).
safe_extra["canonical_next_action"] = redact_value(str(next_action)[:500])
event: dict[str, Any] = {
"message": redact_value(message or blocker_type),
"level": level if level in ("debug", "info", "warning", "error", "fatal") else "warning",
"logger": "gitea-mcp.workflow",
"tags": safe_tags,
"extra": safe_extra,
"fingerprint": ["workflow-blocker", blocker_type],
}
return event
def build_checkin_payload(
monitor: str,
status: str,
*,
check_in_id: str | None = None,
duration: float | None = None,
) -> dict[str, Any]:
"""Build a Sentry cron check-in payload for one of :data:`MONITOR_SLUGS`.
``monitor`` may be a registry key (e.g. ``"stale_lease_scan"``) or an
explicit slug. Raises ``ValueError`` on an unknown status so callers cannot
silently send a malformed check-in.
"""
if status not in _CHECKIN_STATUSES:
raise ValueError(
f"invalid check-in status {status!r}; expected one of {sorted(_CHECKIN_STATUSES)}"
)
slug = MONITOR_SLUGS.get(monitor, monitor)
payload: dict[str, Any] = {"monitor_slug": slug, "status": status}
if check_in_id:
payload["check_in_id"] = str(check_in_id)
if duration is not None:
try:
payload["duration"] = float(duration)
except (TypeError, ValueError):
pass
return payload
# ── Runtime init + capture (fail open) ──────────────────────────────────────
_STATE: dict[str, Any] = {"initialized": False, "config": None}
def is_initialized() -> bool:
return bool(_STATE.get("initialized"))
def active_config() -> SentryConfig | None:
return _STATE.get("config")
def reset_for_tests() -> None:
"""Clear module init state. Test-only helper (never called in production)."""
_STATE["initialized"] = False
_STATE["config"] = None
def init_sentry(config: SentryConfig | None = None) -> dict[str, Any]:
"""Initialise the Sentry SDK if (and only if) enabled + DSN + SDK present.
Idempotent and never raises. Returns an operator-safe status dict (no DSN
value). Behaviour is unchanged when the feature is off.
"""
cfg = config or load_config()
status: dict[str, Any] = {"initialized": False, **cfg.safe_summary()}
try:
if not cfg.active:
status["reason"] = "disabled (MCP_SENTRY_ENABLED false or SENTRY_DSN empty)"
_STATE["config"] = cfg
return status
if not sdk_available():
status["reason"] = "sentry_sdk not installed"
_STATE["config"] = cfg
return status
init_kwargs: dict[str, Any] = {
"dsn": cfg.dsn,
"environment": cfg.environment,
"release": cfg.release,
"traces_sample_rate": cfg.traces_sample_rate,
"before_send": scrub_event,
"send_default_pii": False,
}
if cfg.enable_logs:
# sentry-sdk 2.x captures Python logs as structured logs when the
# experimental logs feature is enabled; scrub those too.
init_kwargs["_experiments"] = {
"enable_logs": True,
"before_send_log": scrub_event,
}
sentry_sdk.init(**init_kwargs) # type: ignore[union-attr]
_STATE["initialized"] = True
_STATE["config"] = cfg
status["initialized"] = True
status["reason"] = "sentry initialised"
except Exception as exc: # fail open: observability must not block startup
status["reason"] = f"init failed (ignored): {type(exc).__name__}"
_STATE["initialized"] = False
return status
def _set_scope_tags(scope: Any, tags: dict[str, str]) -> None:
for key, val in tags.items():
try:
scope.set_tag(key, val)
except Exception:
pass
def capture_workflow_blocker(
blocker_type: str,
*,
message: str | None = None,
next_action: str | None = None,
level: str = "warning",
tags: dict[str, Any] | None = None,
extra: dict[str, Any] | None = None,
) -> dict[str, Any]:
"""Capture a fail-closed workflow blocker as a structured Sentry event.
Always returns the redacted event dict (so callers/tests can inspect it),
and sends it to Sentry only when initialised. Fail open.
"""
event = build_blocker_event(
blocker_type,
message=message,
next_action=next_action,
level=level,
tags=tags,
extra=extra,
)
try:
if is_initialized() and sdk_available():
sentry_sdk.capture_event(event) # type: ignore[union-attr]
except Exception:
pass
return event
def capture_exception(
exc: BaseException,
*,
tags: dict[str, Any] | None = None,
extra: dict[str, Any] | None = None,
) -> bool:
"""Capture a runtime exception with scrubbed tags. Fail open.
Returns True only when the event was handed to an initialised SDK.
"""
try:
if not (is_initialized() and sdk_available()):
return False
safe_tags = build_tags(**(tags or {}))
safe_extra = redact_value(dict(extra or {}))
with sentry_sdk.push_scope() as scope: # type: ignore[union-attr]
_set_scope_tags(scope, safe_tags)
for key, val in safe_extra.items():
try:
scope.set_extra(key, val)
except Exception:
pass
sentry_sdk.capture_exception(exc) # type: ignore[union-attr]
return True
except Exception:
return False
def monitor_checkin(
monitor: str,
status: str,
*,
check_in_id: str | None = None,
duration: float | None = None,
) -> dict[str, Any] | None:
"""Send a Sentry cron check-in for a watchdog job. Fail open.
Returns the payload (for inspection/tests), or ``None`` if the status was
invalid. Only transmits when initialised.
"""
try:
payload = build_checkin_payload(
monitor, status, check_in_id=check_in_id, duration=duration
)
except ValueError:
return None
try:
if is_initialized() and sdk_available() and hasattr(sentry_sdk, "capture_checkin"):
sentry_sdk.capture_checkin(**payload) # type: ignore[union-attr]
except Exception:
pass
return payload
-21
View File
@@ -60,15 +60,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"permission": "gitea.pr.close",
"role": "author",
},
# Non-closing PR metadata edits (title/body/base). Closing uses close_pr.
"edit_pr": {
"permission": "gitea.pr.create",
"role": "author",
},
"gitea_edit_pr": {
"permission": "gitea.pr.create",
"role": "author",
},
"address_pr_change_requests": {
"permission": "gitea.branch.push",
"role": "author",
@@ -77,22 +68,10 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"permission": "gitea.pr.review",
"role": "reviewer",
},
"submit_pr_review": {
"permission": "gitea.pr.review",
"role": "reviewer",
},
"merge_pr": {
"permission": "gitea.pr.merge",
"role": "merger",
},
"acquire_reviewer_pr_lease": {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
"gitea_acquire_reviewer_pr_lease": {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
"adopt_merger_pr_lease": {
"permission": "gitea.pr.comment",
"role": "reviewer",
File diff suppressed because it is too large Load Diff
+412
View File
@@ -0,0 +1,412 @@
"""Tests for optional self-hosted Sentry observability (#606).
Covers the pure module (config, redaction, event/check-in builders) and the
runtime capture paths using a fake ``sentry_sdk``, so nothing ever touches the
network. Critically proves the feature is a no-op when disabled or DSN-less
(acceptance criterion 1) and that secrets/paths/session-state are never sent
(criterion 5).
"""
import sys
import contextlib
from pathlib import Path
import pytest
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import sentry_observability as so # noqa: E402
# ── Fake SDK ────────────────────────────────────────────────────────────────
class _FakeScope:
def __init__(self):
self.tags = {}
self.extras = {}
def set_tag(self, k, v):
self.tags[k] = v
def set_extra(self, k, v):
self.extras[k] = v
class FakeSentrySDK:
"""Minimal stand-in exposing the SDK surface sentry_observability uses."""
def __init__(self):
self.init_kwargs = None
self.events = []
self.exceptions = []
self.checkins = []
self.last_scope = None
def init(self, **kwargs):
self.init_kwargs = kwargs
def capture_event(self, event):
self.events.append(event)
def capture_exception(self, exc):
self.exceptions.append(exc)
def capture_checkin(self, **payload):
self.checkins.append(payload)
@contextlib.contextmanager
def push_scope(self):
self.last_scope = _FakeScope()
yield self.last_scope
@pytest.fixture(autouse=True)
def _reset_state():
"""Isolate module init state between tests."""
so.reset_for_tests()
yield
so.reset_for_tests()
@pytest.fixture
def fake_sdk(monkeypatch):
sdk = FakeSentrySDK()
monkeypatch.setattr(so, "sentry_sdk", sdk)
return sdk
# ── Config / gating ─────────────────────────────────────────────────────────
def test_disabled_by_default_empty_env():
cfg = so.load_config(env={})
assert cfg.enabled is False
assert cfg.active is False
def test_enabled_flag_without_dsn_is_not_active():
cfg = so.load_config(env={"MCP_SENTRY_ENABLED": "1"})
assert cfg.enabled is True
assert cfg.dsn is None
assert cfg.active is False # DSN required
def test_dsn_without_enabled_flag_is_not_active():
cfg = so.load_config(env={"SENTRY_DSN": "https://[email protected]/1"})
assert cfg.active is False
def test_active_requires_enabled_and_dsn():
cfg = so.load_config(
env={"MCP_SENTRY_ENABLED": "true", "SENTRY_DSN": "https://[email protected]/1"}
)
assert cfg.active is True
def test_truthy_variants():
for val in ("1", "true", "YES", "On"):
cfg = so.load_config(env={"MCP_SENTRY_ENABLED": val})
assert cfg.enabled is True
for val in ("0", "false", "no", "", "off"):
cfg = so.load_config(env={"MCP_SENTRY_ENABLED": val})
assert cfg.enabled is False
def test_traces_sample_rate_parsed_and_clamped():
assert so.load_config(env={"MCP_SENTRY_TRACES_SAMPLE_RATE": "0.25"}).traces_sample_rate == 0.25
assert so.load_config(env={"MCP_SENTRY_TRACES_SAMPLE_RATE": "5"}).traces_sample_rate == 1.0
assert so.load_config(env={"MCP_SENTRY_TRACES_SAMPLE_RATE": "-1"}).traces_sample_rate == 0.0
assert so.load_config(env={"MCP_SENTRY_TRACES_SAMPLE_RATE": "junk"}).traces_sample_rate == 0.0
def test_safe_summary_has_no_dsn_value():
cfg = so.load_config(
env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
)
summary = cfg.safe_summary()
assert summary["dsn_present"] is True
assert "secret" not in repr(summary)
assert "dsn" not in summary # only presence, never the value
# ── init_sentry ─────────────────────────────────────────────────────────────
def test_init_noop_when_disabled(fake_sdk):
status = so.init_sentry(so.load_config(env={}))
assert status["initialized"] is False
assert fake_sdk.init_kwargs is None # no SDK init
assert so.is_initialized() is False
def test_init_noop_when_enabled_but_missing_dsn(fake_sdk):
status = so.init_sentry(so.load_config(env={"MCP_SENTRY_ENABLED": "1"}))
assert status["initialized"] is False
assert fake_sdk.init_kwargs is None
def test_init_reports_missing_sdk(monkeypatch):
monkeypatch.setattr(so, "sentry_sdk", None)
status = so.init_sentry(
so.load_config(
env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
)
)
assert status["initialized"] is False
assert "not installed" in status["reason"]
def test_init_configures_sdk_with_scrubber(fake_sdk):
status = so.init_sentry(
so.load_config(
env={
"MCP_SENTRY_ENABLED": "1",
"SENTRY_DSN": "https://[email protected]/1",
"SENTRY_ENVIRONMENT": "prod",
"MCP_SENTRY_TRACES_SAMPLE_RATE": "0.1",
}
)
)
assert status["initialized"] is True
assert so.is_initialized() is True
kw = fake_sdk.init_kwargs
assert kw["dsn"] == "https://[email protected]/1"
assert kw["environment"] == "prod"
assert kw["traces_sample_rate"] == 0.1
assert kw["before_send"] is so.scrub_event
assert kw["send_default_pii"] is False
def test_init_enable_logs_wires_log_scrubber(fake_sdk):
so.init_sentry(
so.load_config(
env={
"MCP_SENTRY_ENABLED": "1",
"SENTRY_DSN": "https://[email protected]/1",
"MCP_SENTRY_ENABLE_LOGS": "1",
}
)
)
exp = fake_sdk.init_kwargs["_experiments"]
assert exp["enable_logs"] is True
assert exp["before_send_log"] is so.scrub_event
def test_init_never_raises_on_sdk_failure(monkeypatch):
class Boom:
def init(self, **kwargs):
raise RuntimeError("sentry down")
monkeypatch.setattr(so, "sentry_sdk", Boom())
status = so.init_sentry(
so.load_config(
env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
)
)
assert status["initialized"] is False
assert "init failed" in status["reason"]
# ── Redaction (fail closed) ─────────────────────────────────────────────────
def test_build_tags_allowlist_only():
tags = so.build_tags(role="author", secret_thing="leak", pid=123)
assert tags["role"] == "author"
assert tags["pid"] == "123"
assert "secret_thing" not in tags
def test_build_tags_hashes_session_id():
tags = so.build_tags(session_id="prgs-author-20479-cf9ac178")
assert "session_id" not in tags
assert "session_id_hash" in tags
assert tags["session_id_hash"] != "prgs-author-20479-cf9ac178"
assert len(tags["session_id_hash"]) == 12
def test_build_tags_collapses_worktree_path():
tags = so.build_tags(
worktree_path="/Users/x/Development/Gitea-Tools/branches/issue-606-sentry-observability"
)
assert "worktree_path" not in tags
assert tags["worktree_category"] == "author"
def test_build_tags_drops_value_that_scrubs_to_redacted():
# A tag value that is itself a token gets scrubbed then dropped.
tags = so.build_tags(capability="token abcdef1234567890")
assert "capability" not in tags
def test_sanitize_path_categories():
assert so.sanitize_path("/repo/branches/review-pr-654") == "reviewer"
assert so.sanitize_path("/repo/branches/merge-pr-1") == "merger"
assert so.sanitize_path("/repo/branches/reconcile-pr-1") == "reconciler"
assert so.sanitize_path("/repo/branches/feat-issue-606") == "author"
assert so.sanitize_path("/x/y/Gitea-Tools") == "root"
def test_redact_value_scrubs_secrets_and_paths():
out = so.redact_value(
{
"token": "abc123",
"note": "Authorization: Bearer sk_live_abcdefgh12345",
"path": "/Users/jasonwalker/Development/Gitea-Tools/secret",
"dsn": "https://[email protected]/1",
"safe": "hello",
}
)
assert out["token"] == so.REDACTED
assert out["dsn"] == so.REDACTED
assert "sk_live" not in out["note"]
assert so.REDACTED_PATH in out["path"]
assert "/Users/" not in out["path"]
assert out["safe"] == "hello"
def test_redact_value_forbidden_prompt_and_session_state():
out = so.redact_value(
{"prompt": "full body", "session_state": "{...}", "keep": "ok"}
)
assert out["prompt"] == so.REDACTED
assert out["session_state"] == so.REDACTED
assert out["keep"] == "ok"
def test_scrub_event_redacts_nested_and_drops_server_name():
event = {
"server_name": "some-host",
"message": "boom",
"extra": {"token": "leak", "ok": "1"},
}
scrubbed = so.scrub_event(event)
assert "server_name" not in scrubbed
assert scrubbed["extra"]["token"] == so.REDACTED
assert scrubbed["extra"]["ok"] == "1"
def test_scrub_event_drops_non_dict():
assert so.scrub_event("not a dict") is None
assert so.scrub_event(None) is None
# ── Event builders ──────────────────────────────────────────────────────────
def test_build_blocker_event_structure_and_next_action():
event = so.build_blocker_event(
"active_foreign_lease",
message="blocked by foreign lease",
next_action="wait or adopt via allocator",
level="warning",
tags={"pr_number": 606, "session_id": "s-123"},
)
assert event["tags"]["blocker_type"] == "active_foreign_lease"
assert event["tags"]["pr_number"] == "606"
assert "session_id" not in event["tags"]
assert event["tags"]["session_id_hash"]
assert event["extra"]["canonical_next_action"] == "wait or adopt via allocator"
assert event["fingerprint"] == ["workflow-blocker", "active_foreign_lease"]
def test_build_blocker_event_invalid_level_defaults_warning():
event = so.build_blocker_event("x", level="nonsense")
assert event["level"] == "warning"
def test_build_checkin_payload_maps_slugs():
for key, slug in so.MONITOR_SLUGS.items():
payload = so.build_checkin_payload(key, "ok")
assert payload["monitor_slug"] == slug
assert payload["status"] == "ok"
def test_build_checkin_payload_explicit_slug_passthrough():
payload = so.build_checkin_payload("custom-slug", "in_progress", duration=1.5)
assert payload["monitor_slug"] == "custom-slug"
assert payload["duration"] == 1.5
def test_build_checkin_payload_rejects_bad_status():
with pytest.raises(ValueError):
so.build_checkin_payload("allocator_health", "bogus")
def test_all_six_monitors_registered():
assert set(so.MONITOR_SLUGS) == {
"stale_lease_scan",
"terminal_lock_scan",
"allocator_health",
"namespace_health",
"dashboard_freshness",
"reconciler_cleanup",
}
# ── Capture paths (fail open) ───────────────────────────────────────────────
def test_capture_workflow_blocker_noop_when_disabled(fake_sdk):
# not initialised
event = so.capture_workflow_blocker("some_blocker", message="x")
assert isinstance(event, dict) # still returns redacted event
assert fake_sdk.events == [] # but nothing sent
def test_capture_workflow_blocker_sends_when_initialised(fake_sdk):
so.init_sentry(
so.load_config(
env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
)
)
so.capture_workflow_blocker("terminal_lock_occupied", message="held")
assert len(fake_sdk.events) == 1
assert fake_sdk.events[0]["tags"]["blocker_type"] == "terminal_lock_occupied"
def test_capture_exception_noop_when_disabled(fake_sdk):
assert so.capture_exception(ValueError("x")) is False
assert fake_sdk.exceptions == []
def test_capture_exception_sends_scrubbed_tags(fake_sdk):
so.init_sentry(
so.load_config(
env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
)
)
ok = so.capture_exception(
RuntimeError("bad"), tags={"mutation_tool": "gitea_merge_pr", "leaky": "x"}
)
assert ok is True
assert len(fake_sdk.exceptions) == 1
assert fake_sdk.last_scope.tags["mutation_tool"] == "gitea_merge_pr"
assert "leaky" not in fake_sdk.last_scope.tags
def test_capture_exception_never_raises(monkeypatch, fake_sdk):
so.init_sentry(
so.load_config(
env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
)
)
def boom(exc):
raise RuntimeError("sdk exploded")
monkeypatch.setattr(fake_sdk, "capture_exception", boom)
# Must swallow the SDK failure (fail open).
assert so.capture_exception(ValueError("y")) is False
def test_monitor_checkin_noop_when_disabled(fake_sdk):
payload = so.monitor_checkin("allocator_health", "ok")
assert payload["monitor_slug"] == "gitea-mcp-allocator-health"
assert fake_sdk.checkins == [] # not sent while disabled
def test_monitor_checkin_sends_when_initialised(fake_sdk):
so.init_sentry(
so.load_config(
env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
)
)
so.monitor_checkin("stale_lease_scan", "ok")
assert fake_sdk.checkins == [
{"monitor_slug": "gitea-mcp-stale-lease-scan", "status": "ok"}
]
def test_monitor_checkin_invalid_status_returns_none(fake_sdk):
assert so.monitor_checkin("allocator_health", "bogus") is None
assert fake_sdk.checkins == []