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
22 changed files with 1306 additions and 2351 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
-18
View File
@@ -7,19 +7,6 @@ from typing import Any
PROTECTED_BRANCHES = frozenset({"master", "main", "dev"})
# Evidence / preservation branches must never be removed by cleanup tools
# (e.g. chore/issue-681-preserve-review-session-wip).
_PRESERVATION_MARKERS = ("preserve", "preservation", "evidence")
def is_preservation_or_evidence_branch(branch: str | None) -> bool:
"""Return True when *branch* is a preservation/evidence ref that must stay."""
if not branch:
return False
name = str(branch).lower()
return any(marker in name for marker in _PRESERVATION_MARKERS)
_RAW_BRANCH_DELETE_PATTERNS = (
re.compile(r"\bgit(?:\s+-C\s+\S+)?\s+branch\s+-[dD]\b[^\n\r]*", re.I),
re.compile(r"\bgit(?:\s+-C\s+\S+)?\s+push\b[^\n\r]*\s--delete\b[^\n\r]*", re.I),
@@ -85,11 +72,6 @@ def assess_merged_pr_branch_cleanup(
reasons.append("PR head branch is missing")
if head_branch in protected:
reasons.append(f"branch '{head_branch}' is protected")
if is_preservation_or_evidence_branch(head_branch):
reasons.append(
f"branch '{head_branch}' is a preservation/evidence branch and "
"cannot be deleted through merged-PR cleanup"
)
if head_branch in open_pr_heads:
reasons.append("an open PR still references this head branch")
if head_on_target is False:
-185
View File
@@ -238,43 +238,11 @@ narrow operation set:
- `gitea.issue.comment`
- `gitea.issue.close`
- `gitea.pr.close`
- `gitea.branch.delete` (merged-branch cleanup only — see below)
Forbidden on reconciler profiles: `gitea.pr.approve`, `gitea.pr.merge`,
`gitea.pr.review`, `gitea.pr.create`, `gitea.branch.push`, and
`gitea.repo.commit`.
### Merged-branch cleanup ownership (`gitea.branch.delete`)
The reconciler is the repository-supported owner of merged-PR source-branch
cleanup: `task_capability_map` maps `cleanup_merged_pr_branch` (and
`reconciliation_cleanup`) to role `reconciler` with permission
`gitea.branch.delete`. Post-merge branch lifecycle is reconciliation work —
it happens after the author, reviewer, and merger roles have completed, and
it must not be reachable from those roles.
Least-privilege constraints:
- `gitea.branch.delete` is granted **only** to reconciler profiles. Author,
reviewer, and merger profiles must never hold it; `gitea_delete_branch`
and `gitea_cleanup_merged_pr_branch` fail closed on any profile without
the permission.
- Even with the permission, reconciler deletion is only supported through the
guarded `gitea_cleanup_merged_pr_branch` path (#514 / #687): the PR must be
merged, the head an ancestor of the target, the branch not protected
(`master`/`main`/`dev`), the branch not a preservation/evidence ref (e.g.
`chore/issue-681-preserve-review-session-wip`), no open PR may still use the
head, and an explicit `CLEANUP MERGED PR <n> BRANCH <branch>` confirmation is
required. Raw `gitea_delete_branch` is **denied** to reconciler even when
`gitea.branch.delete` is present.
- Raw `git branch -d` / `git push --delete` cleanup remains blocked by
`branch_cleanup_guard` and the final-report validator regardless of
profile permissions.
- `gitea.branch.delete` has no short alias in `GITEA_OPERATION_ALIASES`;
write it fully qualified in `allowed_operations`. Migration must emit
canonical names such as `gitea.pr.close` (never bare `pr.close` /
`issue.close`, which the production normalizer rejects or drops).
Launch a static `gitea-reconciler` MCP namespace with
`GITEA_MCP_PROFILE=prgs-reconciler`. Profile shape is validated by
`reconciler_profile.assess_reconciler_profile` (#304). Use the
@@ -283,159 +251,6 @@ Launch a static `gitea-reconciler` MCP namespace with
fresh target-branch fetch, recorded target SHA, and ancestor proof. PRs whose
heads are not already landed cannot be closed through this path.
### Operational runbook: grant reconciler `gitea.branch.delete` (#687)
Merging a code PR that updates `migrate_profiles.py` / `reconciler_profile.py`
**does not** change the live operator profile on disk. Apply the profile
change deliberately, then reconnect the client-managed namespace.
1. **Approved migration / profile-update command** (from the repo root, using
the project venv if present):
```bash
# Dry-run first (default): validates v2 output, writes nothing
python3 migrate_profiles.py -i ~/.config/gitea-tools/profiles.json
# Apply: creates backup then writes migrated v2 config
python3 migrate_profiles.py -i ~/.config/gitea-tools/profiles.json -w
# Optional explicit paths:
# python3 migrate_profiles.py -i ~/.config/gitea-tools/profiles.json \
# -o ~/.config/gitea-tools/profiles.json \
# --backup ~/.config/gitea-tools/profiles.json.bak -w
```
If the live file is already v2, edit the reconciler identitys
`allowed_operations` / `forbidden_operations` under
`environments.<env>.services.gitea.identities.reconciler` (or the
`prgs-reconciler` alias target) so allowed includes the canonical set
below — then re-validate with a load of the config (see step 3).
2. **Inspect the generated (or edited) profile** — confirm the reconciler
identity, for example:
```bash
python3 - <<'PY'
import json
from pathlib import Path
cfg = json.loads(Path.home().joinpath(".config/gitea-tools/profiles.json").read_text())
# v2 environments shape:
ident = cfg["environments"]["prgs"]["services"]["gitea"]["identities"]["reconciler"]
print("role:", ident.get("role"))
print("allowed:", ident.get("allowed_operations"))
print("forbidden:", ident.get("forbidden_operations"))
PY
```
3. **Validate canonical operation names and least privilege**
Expected canonical **allowed** (defaults after migration):
- `gitea.read`
- `gitea.pr.close` (required)
- `gitea.pr.comment`
- `gitea.issue.comment`
- `gitea.issue.close`
- `gitea.branch.delete` (recommended; cleanup only)
Expected **forbidden** includes at least: `gitea.pr.approve`,
`gitea.pr.merge`, `gitea.pr.review`, `gitea.pr.create`,
`gitea.branch.push`, `gitea.repo.commit`.
No shorthand (`pr.close`, `issue.close`, `pr.comment`) may remain.
Validate with the production loader:
```bash
python3 - <<'PY'
import gitea_config, reconciler_profile
from pathlib import Path
path = str(Path.home() / ".config/gitea-tools/profiles.json")
gitea_config.load_config(path) # fails closed on invalid config
# Or assess the reconciler lists directly after extracting them:
# print(reconciler_profile.assess_reconciler_profile(allowed, forbidden))
PY
```
4. **Merging PR #688 (or any code PR) does not update the live profile.**
Code changes only the migration helper, schema, docs, and tests. The
operator must still run `migrate_profiles.py -w` or an equivalent
authorized edit of `~/.config/gitea-tools/profiles.json`.
5. **Supported apply method:** `python3 migrate_profiles.py … -w` (backup
created automatically) **or** operator-authorized edit of the live
profiles file after backup. Unsupported: silent mtime tricks, manual
process kill to “reload”, or undocumented env overrides.
6. **Backup and validation:** `-w` copies the input to
`<input_path>.bak` (or `--backup PATH`) before writing. Re-run
`load_config` / `assess_reconciler_profile` after write. Keep the
`.bak` until live whoami/capability checks pass.
7. **Client-managed namespace reconnect/reload:** reconnect or reload the
IDE MCP client so `gitea-reconciler` restarts from current `master` and
the updated `GITEA_MCP_PROFILE=prgs-reconciler` config. Do not hand-launch
`mcp_server.py` / `gitea_mcp_server.py` with ad hoc `GITEA_*` env
(see #686 / #630).
8. **Live reverification** (through the client-managed `gitea-reconciler`
namespace only):
- `gitea_whoami` → identity + profile `prgs-reconciler`
- `gitea_assess_master_parity` → `stale=false`, `restart_required=false`
- `gitea_resolve_task_capability(task="cleanup_merged_pr_branch")` →
`allowed_in_current_session=true` only when permission and role match
- `gitea_resolve_task_capability(task="delete_branch")` →
**not** allowed for reconciler (role denial must be enforced)
9. **Guarded cleanup usage** (example for a merged PR whose source branch
remains on the remote):
```text
gitea_cleanup_merged_pr_branch(
pr_number=<N>,
branch=<exact PR head branch>,
confirmation="CLEANUP MERGED PR <N> BRANCH <exact PR head branch>",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path="<path under branches/>",
)
```
The tool refuses unmerged PRs, protected branches, preservation/evidence
branches, open-PR heads, mismatched branch names, and wrong confirmation.
10. **Prohibitions**
- No raw `git push --delete`, `git branch -d` / `-D`, or delete refspecs
- No arbitrary `gitea_delete_branch` from reconciler
- No unsupported profile switching mid-run without full re-preflight
- No ad hoc hand-edits of live profiles **unless** operator-authorized,
backed up, and revalidated as above
Canonical migrated reconciler example:
```json
{
"role": "reconciler",
"allowed_operations": [
"gitea.read",
"gitea.pr.close",
"gitea.pr.comment",
"gitea.issue.comment",
"gitea.issue.close",
"gitea.branch.delete"
],
"forbidden_operations": [
"gitea.pr.approve",
"gitea.pr.merge",
"gitea.pr.review",
"gitea.pr.create",
"gitea.branch.push",
"gitea.repo.commit"
]
}
```
## Identity and fail-closed rules
Before **any** mutating action, a workflow must know both:
+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.
+142 -365
View File
@@ -623,280 +623,101 @@ def verify_preflight_purity(
remote: str | None = None,
worktree_path: str | None = None,
task: str | None = None,
*,
target_issue_number: int | None = None,
require_author_lock: bool = False,
):
"""Verify identity/capability order, then production workspace guards.
#683: pytest/unittest must not skip production root/branches/scope
enforcement when force-on signals request production behavior. The
early return below only skips *preflight-order* purity checks under
pure unit-test isolation never when production guards are active.
"""
"""Verify that identity and capability were verified prior to session edits."""
global _preflight_reviewer_violation_files
in_test = _preflight_in_test_mode()
production_active = workflow_scope_guard.production_guards_active(
in_test_mode=in_test
)
# Pure unit-test isolation: skip purity-order unless legacy dirty/porcelain
# force flags request the dirtiness path. #683 FORCE_PRODUCTION_GUARDS alone
# runs production root/branches/scope without requiring whoami/capability.
skip_purity_order = in_test and not workflow_scope_guard.purity_order_forced()
if not skip_purity_order:
if not _preflight_whoami_called:
raise RuntimeError(
"Pre-flight order violation: Identity (gitea_whoami) has not been verified (fail closed)"
)
if not _preflight_capability_called:
raise RuntimeError(
"Pre-flight order violation: Task capability (gitea_resolve_task_capability) has not been resolved (fail closed)"
)
if (
task is not None
and _preflight_resolved_task is not None
and task != _preflight_resolved_task
):
raise RuntimeError(
"Pre-flight task mismatch: "
f"resolved '{_preflight_resolved_task}' but mutation requires "
f"'{task}' (fail closed)"
)
# #671: block review/merge/close/completion mutations while the session is
# contaminated by a direct stable-branch push attempt (reconciler-exempt).
_enforce_stable_branch_contamination_gate(task, remote)
ctx = _resolve_namespace_mutation_context(worktree_path)
workspace = ctx["workspace_path"]
canonical_root = ctx["canonical_repo_root"]
process_root = ctx["process_project_root"]
real_workspace = os.path.realpath(workspace)
role = ctx.get("workspace_role_kind") or _effective_workspace_role()
if real_workspace != process_root:
if not _preflight_in_test_mode():
membership = author_mutation_worktree.assess_workspace_repo_membership(
workspace_path=workspace,
canonical_repo_root=canonical_root,
)
if membership["block"]:
raise RuntimeError(
author_mutation_worktree.format_workspace_repo_membership_error(
membership
)
)
dirty_files = sorted(
_parse_porcelain_entries(_get_workspace_porcelain(workspace))
)
if dirty_files:
raise RuntimeError(
nwb.format_namespace_workspace_binding_error(
role_kind=role,
workspace_path=workspace,
binding_source=ctx.get("workspace_binding_source")
or "unknown binding source",
dirty_files=dirty_files,
ignored_bindings=ctx.get("ignored_bindings"),
)
)
else:
if _preflight_whoami_violation:
raise RuntimeError(
"Pre-flight order violation: Workspace file edits occurred before "
f"gitea_whoami verification (fail closed). Offending files: "
f"{_format_preflight_files(_preflight_whoami_violation_files)}"
)
if _preflight_capability_violation:
raise RuntimeError(
"Pre-flight order violation: Workspace file edits occurred before "
f"gitea_resolve_task_capability verification (fail closed). Offending files: "
f"{_format_preflight_files(_preflight_capability_violation_files)}"
)
if role in {"reviewer", "merger"}:
current = _get_workspace_porcelain()
baseline = _preflight_capability_baseline_porcelain or ""
reviewer_delta = _new_tracked_changes_since(baseline, current)
_preflight_reviewer_violation_files = reviewer_delta
if reviewer_delta:
raise RuntimeError(
f"{role.title()} role violation: profile is forbidden from modifying "
"tracked workspace files (fail closed). Offending files: "
f"{_format_preflight_files(reviewer_delta)}"
)
# Historical path: root + branches after purity-order when dirty paths live.
_enforce_root_checkout_guard(worktree_path)
_enforce_branches_only_author_mutation(worktree_path)
_enforce_issue_scope_guard(
worktree_path,
task=task,
target_issue_number=target_issue_number,
require_author_lock=require_author_lock,
)
_clear_preflight_capability_state()
if in_test and not (
os.environ.get("GITEA_TEST_FORCE_DIRTY")
or os.environ.get("GITEA_TEST_PORCELAIN") is not None
):
return
# #683: under pytest unit isolation, FORCE_PRODUCTION_GUARDS still runs
# production root + branches + issue scope (no silent no-op of guards).
if production_active:
_enforce_root_checkout_guard(worktree_path)
_enforce_branches_only_author_mutation(worktree_path)
_enforce_issue_scope_guard(
worktree_path,
task=task,
target_issue_number=target_issue_number,
require_author_lock=require_author_lock,
if not _preflight_whoami_called:
raise RuntimeError(
"Pre-flight order violation: Identity (gitea_whoami) has not been verified (fail closed)"
)
if not _preflight_capability_called:
raise RuntimeError(
"Pre-flight order violation: Task capability (gitea_resolve_task_capability) has not been resolved (fail closed)"
)
if (
task is not None
and _preflight_resolved_task is not None
and task != _preflight_resolved_task
):
raise RuntimeError(
"Pre-flight task mismatch: "
f"resolved '{_preflight_resolved_task}' but mutation requires "
f"'{task}' (fail closed)"
)
# #671: block review/merge/close/completion mutations while the session is
# contaminated by a direct stable-branch push attempt (reconciler-exempt).
_enforce_stable_branch_contamination_gate(task, remote)
def _session_issue_lock_snapshot(
workspace_path: str | None = None,
) -> dict:
"""Return session lock fields relevant to #683 scope enforcement.
Branch-vs-lock comparison uses the live workspace branch only when the
lock's worktree matches the mutation workspace. That prevents a foreign
or leftover session lock from poisoning unrelated test worktrees while
still fail-closing when the bound worktree drifts to another issue.
"""
lock = issue_lock_store.read_session_issue_lock() or {}
raw = lock.get("issue_number")
locked: int | None
try:
locked = int(raw) if raw is not None else None
except (TypeError, ValueError):
locked = None
lock_wt = (lock.get("worktree_path") or "").strip()
workspace = (workspace_path or "").strip()
worktrees_match = False
if lock_wt and workspace:
try:
worktrees_match = os.path.realpath(lock_wt) == os.path.realpath(workspace)
except OSError:
worktrees_match = False
return {
"locked_issue_number": locked,
"lock_branch_name": (lock.get("branch_name") or "").strip() or None,
"lock_worktree_path": lock_wt or None,
"worktrees_match": worktrees_match,
}
def _session_locked_issue_number() -> int | None:
"""Return the active session issue lock number when present (#683)."""
return _session_issue_lock_snapshot().get("locked_issue_number")
def _enforce_issue_scope_guard(
worktree_path: str | None = None,
*,
task: str | None = None,
target_issue_number: int | None = None,
require_author_lock: bool = False,
) -> None:
"""#683: fail closed on missing/out-of-scope issue ownership for mutations."""
ctx = _resolve_namespace_mutation_context(worktree_path)
workspace = ctx["workspace_path"]
git_state = issue_lock_worktree.read_worktree_git_state(workspace)
# Honour actual profile role as well as poisoned task role (#540 / #683):
# comment_issue preflight stamps required_role_kind=author, which must not
# strip a genuine reconciler of control-checkout exemptions.
canonical_root = ctx["canonical_repo_root"]
process_root = ctx["process_project_root"]
real_workspace = os.path.realpath(workspace)
role = ctx.get("workspace_role_kind") or _effective_workspace_role()
actual = _actual_profile_role()
if actual in nwb.NON_AUTHOR_ROLES:
role = actual
snap = _session_issue_lock_snapshot(workspace)
# Scope uses the lock's recorded branch for issue-number matching.
# Live workspace branch can inherit the parent control checkout's branch
# name when a temp branches/ dir is not its own worktree tip — that must
# not invent a false out-of-scope failure. Live branch drift is enforced
# by issue_lock_store.verify_lock_for_mutation elsewhere.
branch_for_scope = snap.get("lock_branch_name")
if (
snap.get("worktrees_match")
and workflow_scope_guard.production_guards_forced()
):
live_branch = git_state.get("current_branch")
live_issue = workflow_scope_guard.extract_issue_number_from_branch(
live_branch
)
locked = snap.get("locked_issue_number")
if (
live_issue is not None
and locked is not None
and live_issue != locked
):
branch_for_scope = live_branch
# Author implementation / source-adjacent mutations need ownership when forced.
authorish = role == "author" or (
task
in {
"create_issue",
"comment_issue",
"lock_issue",
"create_pr",
"commit_files",
"gitea_commit_files",
"mark_issue",
}
)
require_lock = bool(require_author_lock) or (
authorish
and workflow_scope_guard.production_guards_forced()
and role == "author"
)
assessment = workflow_scope_guard.assess_production_mutation_guards(
workspace_path=workspace,
canonical_repo_root=ctx["canonical_repo_root"],
porcelain_status=git_state.get("porcelain_status") or "",
current_branch=branch_for_scope,
locked_issue_number=snap.get("locked_issue_number"),
target_issue_number=target_issue_number,
role_kind=role,
require_author_lock=require_lock,
in_test_mode=_preflight_in_test_mode(),
)
workflow_scope_guard.raise_if_blocked(assessment)
if real_workspace != process_root:
if not _preflight_in_test_mode():
membership = author_mutation_worktree.assess_workspace_repo_membership(
workspace_path=workspace,
canonical_repo_root=canonical_root,
)
if membership["block"]:
raise RuntimeError(
author_mutation_worktree.format_workspace_repo_membership_error(
membership
)
)
def _production_guard_block_from_exc(exc: BaseException, **extra) -> dict | None:
"""Map production-guard exceptions to typed tool block responses (#683)."""
if isinstance(exc, workflow_scope_guard.ProductionGuardError):
return workflow_scope_guard.block_response(exc, **extra)
text = str(exc)
if "Workflow scope guard (#683)" in text or "Root checkout guard (#475)" in text:
kind = workflow_scope_guard.BLOCKER_PRODUCTION_GUARD
if "root_diagnostic_edit" in text or "tracked source or test edits" in text:
kind = workflow_scope_guard.BLOCKER_ROOT_DIAGNOSTIC_EDIT
elif "Branches-only mutation guard" in text or "stable control checkout" in text:
kind = workflow_scope_guard.BLOCKER_MISSING_WORKTREE
elif "out-of-scope" in text or "locked to issue" in text:
kind = workflow_scope_guard.BLOCKER_OUT_OF_SCOPE_ISSUE
elif "no owning issue" in text:
kind = workflow_scope_guard.BLOCKER_MISSING_ISSUE_SCOPE
return workflow_scope_guard.block_response(
blocker_kind=kind,
reasons=[text],
**extra,
)
if "Branches-only mutation guard" in text:
return workflow_scope_guard.block_response(
blocker_kind=workflow_scope_guard.BLOCKER_MISSING_WORKTREE,
reasons=[text],
**extra,
)
if "Root checkout guard" in text:
return workflow_scope_guard.block_response(
blocker_kind=workflow_scope_guard.BLOCKER_ROOT_DIAGNOSTIC_EDIT,
reasons=[text],
**extra,
)
return None
dirty_files = sorted(_parse_porcelain_entries(_get_workspace_porcelain(workspace)))
if dirty_files:
raise RuntimeError(
nwb.format_namespace_workspace_binding_error(
role_kind=role,
workspace_path=workspace,
binding_source=ctx.get("workspace_binding_source")
or "unknown binding source",
dirty_files=dirty_files,
ignored_bindings=ctx.get("ignored_bindings"),
)
)
else:
if _preflight_whoami_violation:
raise RuntimeError(
"Pre-flight order violation: Workspace file edits occurred before "
f"gitea_whoami verification (fail closed). Offending files: "
f"{_format_preflight_files(_preflight_whoami_violation_files)}"
)
if _preflight_capability_violation:
raise RuntimeError(
"Pre-flight order violation: Workspace file edits occurred before "
f"gitea_resolve_task_capability verification (fail closed). Offending files: "
f"{_format_preflight_files(_preflight_capability_violation_files)}"
)
if role in {"reviewer", "merger"}:
current = _get_workspace_porcelain()
baseline = _preflight_capability_baseline_porcelain or ""
reviewer_delta = _new_tracked_changes_since(baseline, current)
_preflight_reviewer_violation_files = reviewer_delta
if reviewer_delta:
raise RuntimeError(
f"{role.title()} role violation: profile is forbidden from modifying "
"tracked workspace files (fail closed). Offending files: "
f"{_format_preflight_files(reviewer_delta)}"
)
_enforce_root_checkout_guard(worktree_path)
_enforce_branches_only_author_mutation(worktree_path)
_clear_preflight_capability_state()
def _verify_role_mutation_workspace(
@@ -906,12 +727,7 @@ def _verify_role_mutation_workspace(
worktree: str | None = None,
task: str | None = None,
) -> str:
"""Bind reviewer/merger mutations to the active namespace workspace (#510).
#683: must NOT early-return solely because pytest/unittest is loaded.
Production workspace binding always runs; test isolation uses explicit
env fixtures / force-on flags, never a production short-circuit here.
"""
"""Bind reviewer/merger mutations to the active namespace workspace (#510)."""
# Check running runtimes to prevent stale mutations
try:
@@ -1102,6 +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
@@ -1112,7 +929,6 @@ import merge_approval_gate # noqa: E402
import already_landed_reconcile # noqa: E402
import author_mutation_worktree # noqa: E402
import root_checkout_guard # noqa: E402
import workflow_scope_guard # noqa: E402 # #683 production scope / force-on guards
import stable_branch_push_guard # noqa: E402
import remote_repo_guard # noqa: E402
import issue_claim_heartbeat # noqa: E402
@@ -1962,6 +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,
@@ -2008,6 +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
@@ -2081,15 +1923,7 @@ def gitea_create_issue(
)
if blocked:
return blocked
try:
verify_preflight_purity(
remote, worktree_path=worktree_path, task="create_issue"
)
except Exception as exc:
typed = _production_guard_block_from_exc(exc, number=None)
if typed is not None:
return typed
raise
verify_preflight_purity(remote, worktree_path=worktree_path, task="create_issue")
content_gate = issue_content_gate.pre_create_issue_content_gate(
title,
body,
@@ -5925,65 +5759,6 @@ def gitea_delete_branch(
"permission_report": _permission_block_report("gitea.branch.delete"),
}
# Possessing gitea.branch.delete alone is not enough for arbitrary deletion.
# task_capability_map maps delete_branch → author; reconciler must use the
# guarded cleanup_merged_pr_branch path only (#687 / #514).
profile = get_profile()
active_role = _profile_role_kind(profile)
required_role = task_capability_map.required_role("delete_branch")
if active_role == "reconciler":
return {
"success": False,
"performed": False,
"required_permission": "gitea.branch.delete",
"required_role_kind": required_role,
"active_role_kind": active_role,
"reasons": [
"reconciler profile cannot use raw gitea_delete_branch; "
"use gitea_cleanup_merged_pr_branch for a fully merged PR "
"source branch only (fail closed)"
],
"exact_next_action": (
"Call gitea_cleanup_merged_pr_branch with pr_number, the "
"exact PR head branch, and confirmation "
"'CLEANUP MERGED PR <n> BRANCH <branch>' after capability "
"resolve for cleanup_merged_pr_branch."
),
"permission_report": _permission_block_report("gitea.branch.delete"),
}
if active_role != required_role:
return {
"success": False,
"performed": False,
"required_permission": "gitea.branch.delete",
"required_role_kind": required_role,
"active_role_kind": active_role,
"reasons": [
f"Active profile role '{active_role}' cannot perform "
f"{required_role} task 'delete_branch' even when "
"gitea.branch.delete is present (fail closed)"
],
"permission_report": _permission_block_report("gitea.branch.delete"),
}
if branch_cleanup_guard.is_preservation_or_evidence_branch(branch):
return {
"success": False,
"performed": False,
"required_permission": "gitea.branch.delete",
"reasons": [
f"branch '{branch}' is a preservation/evidence branch and "
"cannot be deleted (fail closed)"
],
}
if branch in branch_cleanup_guard.PROTECTED_BRANCHES:
return {
"success": False,
"performed": False,
"required_permission": "gitea.branch.delete",
"reasons": [f"branch '{branch}' is protected (fail closed)"],
}
audit_allowed, audit_reasons = (
audit_reconciliation_mode.check_audit_mutation_allowed("delete_branch")
)
@@ -6035,20 +5810,18 @@ def gitea_cleanup_merged_pr_branch(
}
profile = get_profile()
active_role = _profile_role_kind(profile)
# cleanup_merged_pr_branch is reconciler-owned (task_capability_map).
# Author/reviewer/merger must not reach this path even if they somehow
# hold gitea.branch.delete.
if active_role != "reconciler":
active_role = _role_kind(
profile.get("allowed_operations", []),
profile.get("forbidden_operations", []),
)
if active_role == "reviewer":
return {
"success": False,
"performed": False,
"required_permission": "gitea.branch.delete",
"required_role_kind": "reconciler",
"active_role_kind": active_role,
"reasons": [
f"profile role '{active_role}' is not authorized for merged "
"branch cleanup; required role is reconciler (fail closed)"
"reviewer profile is not authorized for merged branch cleanup "
"(fail closed)"
],
"permission_report": _permission_block_report("gitea.branch.delete"),
}
@@ -8421,26 +8194,9 @@ def gitea_create_issue_comment(
with the reveal opt-in); on a permission block or empty body,
'success'/'performed' False and 'reasons' with no API call made
(permission blocks also carry a structured 'permission_report',
#142). On production-guard blocks (#683): 'blocker_kind' and
'exact_next_action' with no API side effect.
#142).
"""
try:
# Do not pass target_issue_number: comments on other issues remain
# allowed while an author holds a different implementation lock.
# Scope ownership for source edits is enforced via branch/worktree
# binding + root diagnostic checks (#683).
verify_preflight_purity(
remote,
worktree_path=worktree_path,
task="comment_issue",
)
except Exception as exc:
typed = _production_guard_block_from_exc(
exc, issue_number=issue_number
)
if typed is not None:
return typed
raise
verify_preflight_purity(remote, worktree_path=worktree_path, task="comment_issue")
gate_reasons = _profile_operation_gate("gitea.issue.comment")
reasons = list(gate_reasons)
if not (body or "").strip():
@@ -10225,6 +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
@@ -11330,8 +11091,6 @@ def gitea_resolve_task_capability(
"gitea_commit_files",
"address_pr_change_requests",
"delete_branch",
"cleanup_merged_pr_branch",
"reconciliation_cleanup",
"work_issue",
"work-issue",
}
@@ -12154,6 +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
@@ -12478,4 +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")
+7 -126
View File
@@ -20,114 +20,12 @@ if PROJECT_ROOT not in sys.path:
import gitea_config
# Defaults emit *canonical* operation names only. Shorthand that is not in
# gitea_config.GITEA_OPERATION_ALIASES (e.g. ``pr.close``, ``issue.close``)
# is silently dropped by the production loader and must never appear here.
AUTHOR_DEFAULT_ALLOWED = [
"gitea.read",
"gitea.branch.create",
"gitea.repo.commit",
"gitea.branch.push",
"gitea.pr.create",
"gitea.pr.comment",
]
AUTHOR_DEFAULT_FORBIDDEN = [
"gitea.pr.approve",
"gitea.pr.request_changes",
"gitea.pr.merge",
]
AUTHOR_DEFAULT_ALLOWED = ["read", "branch", "commit", "push", "open_pr", "comment"]
AUTHOR_DEFAULT_FORBIDDEN = ["approve", "request_changes", "merge"]
REVIEWER_DEFAULT_ALLOWED = [
"gitea.read",
"gitea.pr.review",
"gitea.pr.comment",
"gitea.pr.approve",
"gitea.pr.request_changes",
"gitea.pr.merge",
"read", "review", "comment", "approve", "request_changes", "merge"
]
REVIEWER_DEFAULT_FORBIDDEN = [
"gitea.branch.create",
"gitea.repo.commit",
"gitea.branch.push",
"gitea.pr.create",
]
# Required reconciler ops (read + pr.close) plus recommended comment/close and
# branch.delete for guarded merged-PR cleanup. All names must normalize via
# gitea_config.normalize_operation without being dropped.
RECONCILER_DEFAULT_ALLOWED = [
"gitea.read",
"gitea.pr.close",
"gitea.pr.comment",
"gitea.issue.comment",
"gitea.issue.close",
"gitea.branch.delete",
]
RECONCILER_DEFAULT_FORBIDDEN = [
"gitea.pr.approve",
"gitea.pr.merge",
"gitea.pr.review",
"gitea.pr.create",
"gitea.branch.push",
"gitea.repo.commit",
]
# Migration-only expansions for common shorthands that are *not* in
# GITEA_OPERATION_ALIASES. Emitted output is always the canonical form so a
# second canonicalize pass is a no-op (idempotent).
_MIGRATION_ONLY_ALIASES = {
"pr.close": "gitea.pr.close",
"pr.comment": "gitea.pr.comment",
"issue.close": "gitea.issue.close",
"branch.delete": "gitea.branch.delete",
}
# Reconciler required ops that must survive migration (from reconciler_profile).
RECONCILER_REQUIRED_CANONICAL = ("gitea.read", "gitea.pr.close")
def canonicalize_operation(op: str) -> str:
"""Return a canonical operation name accepted by the production loader.
Fail closed on unknown/ambiguous spellings so required permissions cannot
be silently dropped by ``check_operation`` later.
"""
if not isinstance(op, str) or not op.strip():
raise ValueError("operation must be a non-empty string (fail closed)")
op = op.strip()
try:
return gitea_config.normalize_operation(op)
except gitea_config.ConfigError:
pass
if op in _MIGRATION_ONLY_ALIASES:
return _MIGRATION_ONLY_ALIASES[op]
raise ValueError(
f"operation {op!r} cannot be canonicalized for migration "
"(unknown/ambiguous; fail closed — production loader would drop it)"
)
def canonicalize_operations(ops, *, context: str = "operations") -> list[str]:
"""Canonicalize a list of operations; preserve order, drop duplicates."""
if not isinstance(ops, list):
raise ValueError(f"{context} must be a list (fail closed)")
out: list[str] = []
seen: set[str] = set()
for entry in ops:
canon = canonicalize_operation(entry)
if canon not in seen:
seen.add(canon)
out.append(canon)
return out
def _assert_reconciler_required_survive(allowed: list[str], profile_name: str) -> None:
"""Fail visibly when migration would leave a reconciler without required ops."""
missing = [op for op in RECONCILER_REQUIRED_CANONICAL if op not in set(allowed)]
if missing:
raise ValueError(
f"Profile '{profile_name}' (reconciler) is missing required "
f"operation(s) after migration: {missing}. Refusing to emit a "
"profile that would silently fail pr.close / read (fail closed)."
)
REVIEWER_DEFAULT_FORBIDDEN = ["branch", "commit", "push", "open_pr"]
def infer_role(name, execution_profile):
@@ -192,11 +90,9 @@ def migrate_v1_to_v2(v1_data):
ident_name = "reviewer"
elif role == "author":
ident_name = "author"
elif role == "reconciler":
ident_name = "reconciler"
else:
role = prof.get("role")
if role not in (None, "author", "reviewer", "reconciler"):
if role not in (None, "author", "reviewer"):
raise ValueError(
f"Profile '{name}' has unsupported role {role!r}"
)
@@ -228,35 +124,20 @@ def migrate_v1_to_v2(v1_data):
raise ValueError(
f"Profile '{name}' operation fields must be lists"
)
try:
identity_data["allowed_operations"] = canonicalize_operations(
allowed, context=f"profile '{name}' allowed_operations"
)
identity_data["forbidden_operations"] = canonicalize_operations(
forbidden, context=f"profile '{name}' forbidden_operations"
)
except ValueError as exc:
raise ValueError(f"Profile '{name}': {exc}") from exc
identity_data["allowed_operations"] = list(allowed)
identity_data["forbidden_operations"] = list(forbidden)
elif role == "author":
identity_data["allowed_operations"] = list(AUTHOR_DEFAULT_ALLOWED)
identity_data["forbidden_operations"] = list(AUTHOR_DEFAULT_FORBIDDEN)
elif role == "reviewer":
identity_data["allowed_operations"] = list(REVIEWER_DEFAULT_ALLOWED)
identity_data["forbidden_operations"] = list(REVIEWER_DEFAULT_FORBIDDEN)
elif role == "reconciler":
identity_data["allowed_operations"] = list(RECONCILER_DEFAULT_ALLOWED)
identity_data["forbidden_operations"] = list(RECONCILER_DEFAULT_FORBIDDEN)
else:
raise ValueError(
f"Profile '{name}' has no explicit operation lists and no "
"unambiguous author/reviewer role marker (fail closed)"
)
if role == "reconciler":
_assert_reconciler_required_survive(
identity_data["allowed_operations"], name
)
# Nest inside environments/services structure
env = environments.setdefault(env_name, {})
services = env.setdefault("services", {})
-5
View File
@@ -18,11 +18,6 @@ RECONCILER_RECOMMENDED_OPERATIONS = (
"gitea.pr.comment",
"gitea.issue.comment",
"gitea.issue.close",
# Merged-branch cleanup is reconciler-owned (task_capability_map maps
# cleanup_merged_pr_branch -> reconciler). The permission is only
# exercisable through the guarded gitea_cleanup_merged_pr_branch path
# (#514): merged proof, protected-branch refusal, explicit confirmation.
"gitea.branch.delete",
)
RECONCILER_FORBIDDEN_OPERATIONS = (
+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
+1 -7
View File
@@ -27,13 +27,7 @@ from task_capability_map import required_permission, required_role
DELETE_PROFILE = {
"profile_name": "prgs-author-delete",
"role": "author",
"allowed_operations": [
"gitea.read",
"gitea.pr.create",
"gitea.branch.push",
"gitea.branch.delete",
],
"allowed_operations": ["gitea.read", "gitea.branch.delete"],
"forbidden_operations": [],
"audit_label": "prgs-author-delete",
}
+16 -227
View File
@@ -8,33 +8,10 @@ import branch_cleanup_guard as guard # noqa: E402
import mcp_server # noqa: E402
import task_capability_map # noqa: E402
from final_report_validator import assess_final_report_validator # noqa: E402
from mcp_server import gitea_cleanup_merged_pr_branch, gitea_delete_branch # noqa: E402
from mcp_server import gitea_cleanup_merged_pr_branch # noqa: E402
FAKE_AUTH = "token fake"
# Reconciler-shaped profile that holds branch.delete (recommended) plus
# required pr.close/read so _role_kind classifies as reconciler.
RECONCILER_WITH_DELETE = {
"profile_name": "prgs-reconciler",
"role": "reconciler",
"allowed_operations": [
"gitea.read",
"gitea.pr.close",
"gitea.pr.comment",
"gitea.issue.comment",
"gitea.issue.close",
"gitea.branch.delete",
],
"forbidden_operations": [
"gitea.pr.approve",
"gitea.pr.merge",
"gitea.pr.review",
"gitea.pr.create",
"gitea.branch.push",
"gitea.repo.commit",
],
}
class TestRawBranchDeleteGuard(unittest.TestCase):
def test_detects_local_and_remote_raw_git_delete_commands(self):
@@ -116,48 +93,14 @@ class TestMergedPrBranchCleanupTool(unittest.TestCase):
self.assertEqual(res["required_permission"], "gitea.branch.delete")
self.mock_api.assert_not_called()
def test_author_and_merger_without_delete_authority_fail_closed(self):
role_profiles = {
"author": [
"gitea.read",
"gitea.branch.create",
"gitea.branch.push",
"gitea.repo.commit",
"gitea.pr.create",
],
"merger": ["gitea.read", "gitea.pr.merge"],
}
for name, allowed in role_profiles.items():
with self.subTest(role=name):
profile_patch = patch(
"mcp_server.get_profile",
return_value={
"profile_name": name,
"allowed_operations": allowed,
"forbidden_operations": [],
},
)
profile_patch.start()
try:
res = gitea_cleanup_merged_pr_branch(
pr_number=487,
confirmation="CLEANUP MERGED PR 487 BRANCH feat/branch",
branch="feat/branch",
remote="prgs",
worktree_path="/tmp/repo/branches/cleanup",
)
finally:
profile_patch.stop()
self.assertFalse(res["performed"])
self.assertEqual(
res["required_permission"], "gitea.branch.delete"
)
self.mock_api.assert_not_called()
def test_root_checkout_cleanup_fails_closed(self):
patch(
"mcp_server.get_profile",
return_value=dict(RECONCILER_WITH_DELETE),
return_value={
"profile_name": "branch-cleanup",
"allowed_operations": ["gitea.read", "gitea.branch.delete"],
"forbidden_operations": [],
},
).start()
res = gitea_cleanup_merged_pr_branch(
pr_number=487,
@@ -174,7 +117,11 @@ class TestMergedPrBranchCleanupTool(unittest.TestCase):
branch = "feat/issue-485-lease-comments-non-list-guard"
patch(
"mcp_server.get_profile",
return_value=dict(RECONCILER_WITH_DELETE),
return_value={
"profile_name": "branch-cleanup",
"allowed_operations": ["gitea.read", "gitea.branch.delete"],
"forbidden_operations": [],
},
).start()
self.mock_api.side_effect = [
{
@@ -205,7 +152,11 @@ class TestMergedPrBranchCleanupTool(unittest.TestCase):
branch = "feat/issue-485-lease-comments-non-list-guard"
patch(
"mcp_server.get_profile",
return_value=dict(RECONCILER_WITH_DELETE),
return_value={
"profile_name": "branch-cleanup",
"allowed_operations": ["gitea.read", "gitea.branch.delete"],
"forbidden_operations": [],
},
).start()
self.mock_api.side_effect = [
{
@@ -231,168 +182,6 @@ class TestMergedPrBranchCleanupTool(unittest.TestCase):
]
self.assertFalse(delete_calls)
def test_reconciler_with_branch_delete_cannot_raw_delete(self):
"""#687: reconciler + gitea.branch.delete still cannot call raw delete."""
patch(
"mcp_server.get_profile",
return_value=dict(RECONCILER_WITH_DELETE),
).start()
res = gitea_delete_branch(
branch="fix/issue-683-workflow-guard-hardening",
remote="prgs",
)
self.assertFalse(res.get("success", True))
self.assertFalse(res.get("performed", True))
reasons = " ".join(res.get("reasons") or [])
self.assertIn("raw gitea_delete_branch", reasons)
self.assertIn("cleanup_merged_pr_branch", reasons)
self.mock_api.assert_not_called()
def test_reconciler_raw_delete_denies_preservation_branch(self):
patch(
"mcp_server.get_profile",
return_value=dict(RECONCILER_WITH_DELETE),
).start()
res = gitea_delete_branch(
branch="chore/issue-681-preserve-review-session-wip",
remote="prgs",
)
self.assertFalse(res.get("performed", True))
self.mock_api.assert_not_called()
def test_author_with_branch_delete_role_ok_but_preserve_blocked(self):
"""Author role may use raw delete path when permitted; preserve fails closed."""
patch(
"mcp_server.get_profile",
return_value={
"profile_name": "prgs-author",
"role": "author",
"allowed_operations": [
"gitea.read",
"gitea.pr.create",
"gitea.branch.push",
"gitea.branch.delete",
],
"forbidden_operations": ["gitea.pr.approve", "gitea.pr.merge"],
},
).start()
res = gitea_delete_branch(
branch="chore/issue-681-preserve-review-session-wip",
remote="prgs",
)
self.assertFalse(res.get("performed", True))
self.assertIn("preservation", " ".join(res.get("reasons") or []))
self.mock_api.assert_not_called()
def test_unmerged_branch_cleanup_rejected(self):
branch = "feat/unmerged-work"
patch(
"mcp_server.get_profile",
return_value=dict(RECONCILER_WITH_DELETE),
).start()
self.mock_api.side_effect = [
{
"number": 999,
"merged": False,
"merged_at": None,
"head": {"ref": branch, "sha": "b" * 40},
"base": {"ref": "master"},
},
{},
]
res = gitea_cleanup_merged_pr_branch(
pr_number=999,
confirmation=f"CLEANUP MERGED PR 999 BRANCH {branch}",
branch=branch,
remote="prgs",
worktree_path="/tmp/repo/branches/cleanup",
)
self.assertFalse(res["performed"])
self.assertTrue(
any("not merged" in r for r in (res.get("reasons") or []))
)
delete_calls = [
call for call in self.mock_api.call_args_list if call.args[0] == "DELETE"
]
self.assertFalse(delete_calls)
def test_preservation_branch_cleanup_rejected(self):
branch = "chore/issue-681-preserve-review-session-wip"
patch(
"mcp_server.get_profile",
return_value=dict(RECONCILER_WITH_DELETE),
).start()
self.mock_api.side_effect = [
{
"number": 681,
"merged": True,
"merged_at": "2026-07-08T01:00:00Z",
"head": {"ref": branch, "sha": "c" * 40},
"base": {"ref": "master"},
},
{},
]
res = gitea_cleanup_merged_pr_branch(
pr_number=681,
confirmation=f"CLEANUP MERGED PR 681 BRANCH {branch}",
branch=branch,
remote="prgs",
worktree_path="/tmp/repo/branches/cleanup",
)
self.assertFalse(res["performed"])
self.assertTrue(
any("preservation" in r for r in (res.get("reasons") or []))
)
delete_calls = [
call for call in self.mock_api.call_args_list if call.args[0] == "DELETE"
]
self.assertFalse(delete_calls)
def test_non_reconciler_with_delete_denied_cleanup(self):
patch(
"mcp_server.get_profile",
return_value={
"profile_name": "prgs-author",
"role": "author",
"allowed_operations": [
"gitea.read",
"gitea.pr.create",
"gitea.branch.push",
"gitea.branch.delete",
],
"forbidden_operations": [],
},
).start()
res = gitea_cleanup_merged_pr_branch(
pr_number=487,
confirmation="CLEANUP MERGED PR 487 BRANCH feat/branch",
branch="feat/branch",
remote="prgs",
worktree_path="/tmp/repo/branches/cleanup",
)
self.assertFalse(res["performed"])
self.assertEqual(res.get("required_role_kind"), "reconciler")
self.mock_api.assert_not_called()
def test_assess_guard_rejects_preservation_branch(self):
assessment = guard.assess_merged_pr_branch_cleanup(
pr_number=681,
head_branch="chore/issue-681-preserve-review-session-wip",
merged=True,
remote_branch_exists=True,
open_pr_heads=set(),
head_on_target=True,
delete_capability_allowed=True,
confirmation=(
"CLEANUP MERGED PR 681 BRANCH "
"chore/issue-681-preserve-review-session-wip"
),
)
self.assertFalse(assessment["safe_to_delete"])
self.assertTrue(
any("preservation" in r for r in assessment["block_reasons"])
)
if __name__ == "__main__":
unittest.main()
+10 -39
View File
@@ -57,23 +57,9 @@ class TestCreateIssueWorkspaceGuard(unittest.TestCase):
# Without worktree_path/env hints, workspace resolves to PROJECT_ROOT. When that
# path is the stable control checkout (not under branches/), mutation must fail.
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
try:
res = srv.gitea_create_issue(title="Test issue", body="body text")
except RuntimeError as exc:
self.assertIn("stable control checkout", str(exc))
else:
# #683: production guards return typed blockers at entrypoints
self.assertFalse(res.get("success"))
self.assertFalse(res.get("performed"))
blob = " ".join(res.get("reasons") or []) + " " + str(
res.get("blocker_kind") or ""
)
self.assertTrue(
"stable control checkout" in blob
or "missing_issue_worktree" in blob
or "control checkout" in blob.lower()
)
self.assertTrue(res.get("exact_next_action"))
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(title="Test issue", body="body text")
self.assertIn("stable control checkout", str(ctx.exception))
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@patch("gitea_mcp_server._profile_permission_block", return_value=None)
@@ -119,17 +105,11 @@ class TestCreateIssueWorkspaceGuard(unittest.TestCase):
)
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
try:
res = srv.gitea_create_issue(
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(
title="Test issue", body="body", worktree_path=missing_path
)
except RuntimeError as exc:
self.assertIn("does not exist", str(exc))
else:
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or [])
self.assertIn("does not exist", blob)
self.assertTrue(res.get("exact_next_action") or res.get("reasons"))
self.assertIn("does not exist (fail closed)", str(ctx.exception))
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@patch("gitea_mcp_server._profile_permission_block", return_value=None)
@@ -162,20 +142,11 @@ class TestCreateIssueWorkspaceGuard(unittest.TestCase):
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
with patch("gitea_mcp_server._get_workspace_porcelain", return_value=""):
try:
res = srv.gitea_create_issue(
title="Test issue",
body="body",
worktree_path=wrong_repo_path,
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(
title="Test issue", body="body", worktree_path=wrong_repo_path
)
except RuntimeError as exc:
self.assertIn(
"does not belong to the target repository", str(exc)
)
else:
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or [])
self.assertIn("does not belong to the target repository", blob)
self.assertIn("does not belong to the target repository", str(ctx.exception))
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@patch("gitea_mcp_server._profile_permission_block", return_value=None)
+2 -11
View File
@@ -267,19 +267,10 @@ class TestReconcilerCommentThroughCanonicalPath(unittest.TestCase):
with patch.dict(os.environ, {}, clear=False):
os.environ.pop("GITEA_AUTHOR_WORKTREE", None)
os.environ.pop("GITEA_ACTIVE_WORKTREE", None)
try:
res = srv.gitea_create_issue_comment(
with self.assertRaises(RuntimeError):
srv.gitea_create_issue_comment(
515, "author note", remote="prgs"
)
except RuntimeError:
pass # legacy raise path
else:
# #683: typed blocker at mutation entrypoint
self.assertFalse(res.get("success"))
self.assertFalse(res.get("performed"))
self.assertTrue(
res.get("blocker_kind") or res.get("reasons")
)
mock_api.assert_not_called()
@@ -1,472 +0,0 @@
"""#683: block unattributed root WIP; pytest cannot disable production guards.
Regression coverage required by issue #683:
1. Session locked to issue A blocks unrelated target issue B until B is selected.
2. Diagnostic source edit on the root checkout is blocked.
3. Same legitimate edit succeeds after issue ownership + isolated worktree bind.
4. Running under pytest does not deactivate production guards when force-on.
5. Dirty tracked Python files remain visible to porcelain consumers.
6. Monkeypatching one helper cannot silently turn the full guard path into a no-op.
7. Real mutation entrypoint proves production guards run before side effects.
8. Same-issue edits in a valid isolated worktree remain unaffected.
9. Blocker includes stable reason + exact recovery action.
"""
from __future__ import annotations
import os
import sys
import tempfile
import textwrap
import unittest
from pathlib import Path
from unittest.mock import MagicMock, patch
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import gitea_mcp_server as mcp_server # noqa: E402
import issue_lock_worktree # noqa: E402
import workflow_scope_guard as wsg # noqa: E402
CONTROL_ROOT = str(Path(__file__).resolve().parent.parent)
if "branches" in Path(__file__).resolve().parts:
# Running from a worktree under branches/ — parent of branches is control.
parts = Path(__file__).resolve().parts
idx = parts.index("branches")
CONTROL_ROOT = str(Path(*parts[:idx])) if idx > 0 else CONTROL_ROOT
class TestProductionGuardsForceOn(unittest.TestCase):
def tearDown(self):
for key in (
wsg.FORCE_PRODUCTION_GUARDS_ENV,
"GITEA_TEST_FORCE_DIRTY",
"GITEA_TEST_PORCELAIN",
"GITEA_AUTHOR_WORKTREE",
"GITEA_ACTIVE_WORKTREE",
):
os.environ.pop(key, None)
wsg.clear_workflow_failure_ledger()
def test_force_on_under_pytest_keeps_production_active(self):
self.assertTrue(wsg.production_guards_active(in_test_mode=False))
self.assertFalse(wsg.production_guards_active(in_test_mode=True))
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
self.assertTrue(wsg.production_guards_active(in_test_mode=True))
self.assertTrue(wsg.production_guards_forced())
def test_no_early_return_in_verify_role_mutation_workspace_source(self):
src = Path(mcp_server.__file__).read_text(encoding="utf-8")
# Rejected 300a4ca pattern must not exist.
self.assertNotIn(
"if _preflight_in_test_mode():\n return _resolve_preflight_workspace_path",
src,
)
# Docstring contract for #683.
self.assertIn("#683", src)
self.assertIn("must NOT early-return solely because pytest", src)
class TestPorcelainIntegrity(unittest.TestCase):
def test_read_worktree_git_state_surfaces_dirty_py(self):
with tempfile.TemporaryDirectory() as tmp:
# Use a real git repo so porcelain is truthful.
import subprocess
subprocess.run(["git", "init"], cwd=tmp, check=True, capture_output=True)
subprocess.run(
["git", "config", "user.email", "[email protected]"],
cwd=tmp,
check=True,
capture_output=True,
)
subprocess.run(
["git", "config", "user.name", "t"],
cwd=tmp,
check=True,
capture_output=True,
)
py_path = Path(tmp) / "sample_mod.py"
py_path.write_text("x = 1\n", encoding="utf-8")
subprocess.run(["git", "add", "sample_mod.py"], cwd=tmp, check=True)
subprocess.run(
["git", "commit", "-m", "init"],
cwd=tmp,
check=True,
capture_output=True,
)
py_path.write_text("x = 2\n", encoding="utf-8")
state = issue_lock_worktree.read_worktree_git_state(tmp)
porcelain = state.get("porcelain_status") or ""
self.assertIn("sample_mod.py", porcelain)
self.assertTrue(any(line.strip().endswith(".py") for line in porcelain.splitlines()))
def test_production_reader_source_rejects_pytest_py_filter(self):
src = Path(issue_lock_worktree.__file__).read_text(encoding="utf-8")
findings = wsg.assert_no_pytest_porcelain_filter(src)
self.assertEqual(findings, [])
# Negative: the rejected 300a4ca pattern is detected.
rejected = textwrap.dedent(
"""
porcelain = status_res.stdout or ""
import sys
if "pytest" in sys.modules or "unittest" in sys.modules:
porcelain = "\\n".join(
line for line in porcelain.splitlines()
if not line.strip().endswith(".py")
)
"""
)
self.assertTrue(wsg.assert_no_pytest_porcelain_filter(rejected))
class TestIssueScopeOwnership(unittest.TestCase):
def test_out_of_scope_issue_blocked_until_selected(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=100,
target_issue_number=200,
branch_name="fix/issue-100-example",
role_kind="author",
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_OUT_OF_SCOPE_ISSUE)
self.assertIn("exact_next_action", result)
self.assertIn("owning issue", result["exact_next_action"].lower())
self.assertTrue(result["reasons"])
def test_same_issue_scope_allowed(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=100,
target_issue_number=100,
branch_name="fix/issue-100-example",
role_kind="author",
)
self.assertFalse(result["block"])
self.assertEqual(result["exact_next_action"], "proceed")
def test_missing_lock_when_required(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=None,
target_issue_number=None,
role_kind="author",
require_lock_for_author=True,
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_MISSING_ISSUE_SCOPE)
def test_branch_issue_mismatch(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=50,
branch_name="fix/issue-99-other",
role_kind="author",
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_OUT_OF_SCOPE_ISSUE)
class TestRootDiagnosticEdit(unittest.TestCase):
def test_dirty_root_source_blocked(self):
result = wsg.assess_root_source_mutation(
workspace_path=CONTROL_ROOT,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M gitea_mcp_server.py\n M tests/test_x.py\n",
role_kind="author",
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT)
self.assertIn("gitea_mcp_server.py", result["dirty_source_files"])
self.assertIn("exact_next_action", result)
self.assertIn("branches/", result["exact_next_action"])
def test_isolated_worktree_same_issue_unaffected(self):
wt = f"{CONTROL_ROOT}/branches/issue-100-example"
result = wsg.assess_root_source_mutation(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M helper.py\n",
current_branch="fix/issue-100-example",
locked_issue_number=100,
role_kind="author",
)
self.assertFalse(result["block"])
self.assertTrue(result["under_branches"])
def test_legitimate_after_ownership_and_worktree(self):
wt = f"{CONTROL_ROOT}/branches/issue-683-workflow-guard-hardening"
composed = wsg.assess_production_mutation_guards(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M workflow_scope_guard.py\n",
current_branch="fix/issue-683-workflow-guard-hardening",
locked_issue_number=683,
target_issue_number=683,
role_kind="author",
require_author_lock=True,
in_test_mode=True,
)
# Force-on required for production path under pytest.
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
try:
composed = wsg.assess_production_mutation_guards(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M workflow_scope_guard.py\n",
current_branch="fix/issue-683-workflow-guard-hardening",
locked_issue_number=683,
target_issue_number=683,
role_kind="author",
require_author_lock=True,
in_test_mode=True,
)
self.assertFalse(composed["block"])
self.assertFalse(composed.get("skipped"))
finally:
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
class TestTypedBlockerResponse(unittest.TestCase):
def test_block_response_has_stable_kind_and_next_action(self):
assessment = wsg.assess_issue_scope_ownership(
locked_issue_number=1,
target_issue_number=2,
role_kind="author",
)
resp = wsg.block_response(assessment)
self.assertFalse(resp["success"])
self.assertFalse(resp["performed"])
self.assertEqual(resp["blocker_kind"], wsg.BLOCKER_OUT_OF_SCOPE_ISSUE)
self.assertIsInstance(resp["exact_next_action"], str)
self.assertTrue(resp["exact_next_action"])
self.assertTrue(resp["reasons"])
def test_production_guard_error_roundtrip(self):
err = wsg.ProductionGuardError(
"blocked",
blocker_kind=wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT,
reasons=["dirty root"],
)
resp = wsg.block_response(err, issue_number=683)
self.assertEqual(resp["blocker_kind"], wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT)
self.assertEqual(resp["issue_number"], 683)
self.assertIn("exact_next_action", resp)
class TestDurableFailureRecording(unittest.TestCase):
def setUp(self):
wsg.clear_workflow_failure_ledger()
def tearDown(self):
wsg.clear_workflow_failure_ledger()
def test_record_before_source_mutation(self):
pending = wsg.assess_durable_failure_recorded(
require_record=True, pending_source_mutation=True
)
self.assertTrue(pending["block"])
self.assertEqual(pending["blocker_kind"], wsg.BLOCKER_UNRECORDED_FAILURE)
wsg.record_workflow_failure(
kind="transport_eof",
detail="EOF during review session (#584 cluster)",
issue_number=683,
task="comment_issue",
)
after = wsg.assess_durable_failure_recorded(
require_record=True, pending_source_mutation=True
)
self.assertFalse(after["block"])
self.assertEqual(len(wsg.workflow_failure_ledger()), 1)
class TestMonkeypatchCannotNoopFullPath(unittest.TestCase):
def tearDown(self):
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
def test_patching_branches_only_still_blocks_dirty_root_scope(self):
"""Monkeypatching branches-only must not silence root diagnostic block."""
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
with patch.object(
mcp_server, "_enforce_branches_only_author_mutation", lambda *a, **k: None
):
with patch.object(
mcp_server, "_enforce_root_checkout_guard", lambda *a, **k: None
):
# Even if both legacy helpers are patched, issue-scope composition
# still sees dirty root source via assess_production_mutation_guards.
assessment = wsg.assess_production_mutation_guards(
workspace_path=CONTROL_ROOT,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M gitea_mcp_server.py\n",
role_kind="author",
in_test_mode=True,
)
self.assertTrue(assessment["block"])
self.assertEqual(
assessment["blocker_kind"], wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT
)
class TestRealEntrypointProductionGuard(unittest.TestCase):
"""Real mutation entrypoint: production guard before side effects (#683)."""
def setUp(self):
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
for key in ("GITEA_AUTHOR_WORKTREE", "GITEA_ACTIVE_WORKTREE"):
os.environ.pop(key, None)
self._orig_whoami = mcp_server._preflight_whoami_called
self._orig_cap = mcp_server._preflight_capability_called
mcp_server._preflight_whoami_called = False
mcp_server._preflight_capability_called = False
mcp_server._preflight_resolved_role = None
mcp_server._preflight_resolved_task = None
def tearDown(self):
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
for key in ("GITEA_AUTHOR_WORKTREE", "GITEA_ACTIVE_WORKTREE"):
os.environ.pop(key, None)
mcp_server._preflight_whoami_called = self._orig_whoami
mcp_server._preflight_capability_called = self._orig_cap
mcp_server._preflight_resolved_role = None
mcp_server._preflight_resolved_task = None
def test_comment_issue_blocks_dirty_root_before_api(self):
api_mock = MagicMock()
with patch.object(mcp_server, "api_request", api_mock), patch.object(
mcp_server,
"_actual_profile_role",
return_value="author",
), patch.object(
mcp_server,
"_effective_workspace_role",
return_value="author",
), patch.object(
mcp_server,
"get_profile",
return_value={
"profile_name": "prgs-author",
"allowed_operations": [
"gitea.issue.comment",
"gitea.read",
"gitea.pr.create",
"gitea.branch.push",
],
"forbidden_operations": [],
},
), patch.object(
issue_lock_worktree,
"read_worktree_git_state",
side_effect=lambda path, **kw: {
"current_branch": "master",
"porcelain_status": (
" M gitea_mcp_server.py\n"
if os.path.realpath(path) == os.path.realpath(CONTROL_ROOT)
or path == CONTROL_ROOT
else ""
),
"head_sha": "a" * 40,
"base_equivalent": True,
},
), patch.object(
mcp_server,
"_resolve_namespace_mutation_context",
return_value={
"workspace_path": CONTROL_ROOT,
"canonical_repo_root": CONTROL_ROOT,
"process_project_root": CONTROL_ROOT,
"workspace_role_kind": "author",
"workspace_binding_source": "process root",
"ignored_bindings": [],
},
), patch.object(
mcp_server,
"_resolve_author_mutation_context",
return_value={
"workspace_path": CONTROL_ROOT,
"canonical_repo_root": CONTROL_ROOT,
"process_project_root": CONTROL_ROOT,
"roots_aligned": True,
},
), patch.object(
mcp_server,
"_session_locked_issue_number",
return_value=None,
):
result = mcp_server.gitea_create_issue_comment(
issue_number=683,
body="diagnostic note",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path=CONTROL_ROOT,
)
api_mock.assert_not_called()
self.assertFalse(result.get("success"))
self.assertFalse(result.get("performed"))
self.assertIn(result.get("blocker_kind"), wsg.BLOCKER_KINDS)
self.assertTrue(result.get("exact_next_action"))
self.assertTrue(result.get("reasons"))
def test_comment_issue_succeeds_structure_after_worktree_bind(self):
"""Same-issue isolated worktree is not blocked by root diagnostic path."""
wt = f"{CONTROL_ROOT}/branches/issue-683-workflow-guard-hardening"
os.environ["GITEA_AUTHOR_WORKTREE"] = wt
assessment = wsg.assess_production_mutation_guards(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M workflow_scope_guard.py\n",
current_branch="fix/issue-683-workflow-guard-hardening",
locked_issue_number=683,
target_issue_number=683,
role_kind="author",
require_author_lock=True,
in_test_mode=True,
)
self.assertFalse(assessment["block"], assessment)
class TestVerifyPreflightForceOn(unittest.TestCase):
def tearDown(self):
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
for key in ("GITEA_AUTHOR_WORKTREE", "GITEA_ACTIVE_WORKTREE"):
os.environ.pop(key, None)
def test_force_on_runs_production_guards_under_pytest(self):
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
called = {"root": 0, "branches": 0, "scope": 0}
def _root(*a, **k):
called["root"] += 1
def _branches(*a, **k):
called["branches"] += 1
def _scope(*a, **k):
called["scope"] += 1
with patch.object(mcp_server, "_enforce_root_checkout_guard", _root), patch.object(
mcp_server, "_enforce_branches_only_author_mutation", _branches
), patch.object(mcp_server, "_enforce_issue_scope_guard", _scope):
# No whoami/capability — purity-order skipped; production still runs.
mcp_server.verify_preflight_purity(task="comment_issue")
self.assertEqual(called["root"], 1)
self.assertEqual(called["branches"], 1)
self.assertEqual(called["scope"], 1)
def test_without_force_on_pytest_skips_production_only_for_unit_isolation(self):
called = {"root": 0}
def _root(*a, **k):
called["root"] += 1
with patch.object(mcp_server, "_enforce_root_checkout_guard", _root), patch.object(
mcp_server, "_enforce_branches_only_author_mutation", lambda *a, **k: None
), patch.object(mcp_server, "_enforce_issue_scope_guard", lambda *a, **k: None):
mcp_server.verify_preflight_purity(task="comment_issue")
self.assertEqual(called["root"], 0)
if __name__ == "__main__":
unittest.main()
+6 -27
View File
@@ -108,24 +108,13 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
"gitea_mcp_server.issue_lock_worktree.read_worktree_git_state",
side_effect=self._git_state(valid_worktree),
):
try:
res = srv.gitea_create_issue_comment(
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue_comment(
issue_number=557,
body="evidence comment",
remote="prgs",
)
except RuntimeError as exc:
self.assertIn("stable control checkout", str(exc))
else:
# #683 typed blocker at mutation entrypoint
self.assertFalse(res.get("success"))
self.assertFalse(res.get("performed"))
blob = " ".join(res.get("reasons") or [])
self.assertTrue(
"stable control checkout" in blob
or res.get("blocker_kind")
)
self.assertTrue(res.get("exact_next_action") or res.get("reasons"))
self.assertIn("stable control checkout", str(ctx.exception))
mock_api.assert_not_called()
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@@ -195,24 +184,14 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
side_effect=self._subprocess(valid_worktree, outside_worktree),
):
with patch.dict(os.environ, self.AUTHOR_ENV, clear=True):
try:
res = srv.gitea_create_issue_comment(
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue_comment(
issue_number=557,
body="evidence comment",
remote="prgs",
worktree_path=outside_worktree,
)
except RuntimeError as exc:
self.assertIn(
"does not belong to the target repository",
str(exc),
)
else:
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or [])
self.assertIn(
"does not belong to the target repository", blob
)
self.assertIn("does not belong to the target repository", str(ctx.exception))
mock_api.assert_not_called()
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
+3 -9
View File
@@ -1425,16 +1425,10 @@ class TestReviewPR(unittest.TestCase):
class TestDeleteBranch(unittest.TestCase):
DELETE_PROFILE = {
"profile_name": "test-author-deleter",
"role": "author",
"allowed_operations": [
"gitea.read",
"gitea.pr.create",
"gitea.branch.push",
"gitea.branch.delete",
],
"profile_name": "test-deleter",
"allowed_operations": ["gitea.read", "gitea.branch.delete"],
"forbidden_operations": [],
"audit_label": "test-author-deleter",
"audit_label": "test-deleter",
}
@patch("mcp_server.get_profile", return_value=DELETE_PROFILE)
+6 -176
View File
@@ -92,19 +92,14 @@ class TestMigrateProfiles(unittest.TestCase):
author = prgs_gitea["identities"]["author"]
self.assertEqual(author["username"], "jcwalker3")
self.assertEqual(author["auth"]["id"], "redacted-author-ref")
self.assertEqual(
author["allowed_operations"], ["gitea.read", "gitea.pr.comment"]
)
self.assertEqual(
author["forbidden_operations"],
["gitea.pr.approve", "gitea.pr.merge"],
)
self.assertEqual(author["allowed_operations"], ["read", "comment"])
self.assertEqual(author["forbidden_operations"], ["approve", "merge"])
reviewer = prgs_gitea["identities"]["reviewer"]
self.assertEqual(reviewer["role"], "reviewer")
self.assertEqual(reviewer["username"], "sysadmin")
self.assertEqual(reviewer["auth"]["id"], "redacted-reviewer-ref")
self.assertIn("gitea.pr.merge", reviewer["allowed_operations"])
self.assertIn("merge", reviewer["allowed_operations"])
def test_alias_generation(self):
"""Test that aliases are correctly generated to support old profile names."""
@@ -193,7 +188,7 @@ class TestMigrateProfiles(unittest.TestCase):
self.assertNotIn("token", stdout_output.lower())
def test_explicit_operations_are_preserved(self):
"""Explicit v1 permissions are canonicalized, not replaced by role defaults."""
"""Explicit v1 permissions must not be replaced by role defaults."""
v1_data = json.loads(json.dumps(self.v1_content))
v1_data["profiles"]["prgs-reviewer"]["allowed_operations"] = ["read"]
v1_data["profiles"]["prgs-reviewer"]["forbidden_operations"] = ["merge"]
@@ -203,8 +198,8 @@ class TestMigrateProfiles(unittest.TestCase):
v2_data["environments"]["prgs"]["services"]["gitea"]
["identities"]["reviewer"]
)
self.assertEqual(reviewer["allowed_operations"], ["gitea.read"])
self.assertEqual(reviewer["forbidden_operations"], ["gitea.pr.merge"])
self.assertEqual(reviewer["allowed_operations"], ["read"])
self.assertEqual(reviewer["forbidden_operations"], ["merge"])
def test_inferred_role_defaults_only_when_unambiguous(self):
"""Role defaults are allowed only for clear author/reviewer profiles."""
@@ -311,171 +306,6 @@ class TestMigrateProfiles(unittest.TestCase):
migrate_profiles.main()
self.assertEqual(cm.exception.code, 1)
def test_reconciler_profile_migration(self):
"""Legacy reconciler shorthands migrate to valid canonical operations."""
import gitea_config
import reconciler_profile
v1_data = {
"version": 1,
"profiles": {
"prgs-reconciler": {
"base_url": "redacted-prgs-service",
"username": "reconciler-agent",
"auth": {"type": "keychain", "id": "reconciler-ref"},
"execution_profile": "prgs-reconciler",
"allowed_operations": [
"read",
"pr.close",
"pr.comment",
"issue.comment",
"issue.close",
"gitea.branch.delete",
],
"forbidden_operations": [
"merge",
"approve",
"review",
"pr.create",
"branch.push",
"commit",
],
}
}
}
v2_data = migrate_profiles.migrate_v1_to_v2(v1_data)
reconciler = (
v2_data["environments"]["prgs"]["services"]["gitea"]
["identities"]["reconciler"]
)
self.assertEqual(reconciler["role"], "reconciler")
allowed = reconciler["allowed_operations"]
forbidden = reconciler["forbidden_operations"]
# No invalid shorthand remains
for bad in ("pr.close", "pr.comment", "issue.close", "read", "merge"):
self.assertNotIn(bad, allowed)
self.assertNotIn(bad, forbidden)
for required in (
"gitea.read",
"gitea.pr.close",
"gitea.pr.comment",
"gitea.issue.comment",
"gitea.issue.close",
"gitea.branch.delete",
):
self.assertIn(required, allowed)
# Production loader accepts every allowed op
self.assertEqual(
gitea_config.normalize_operation(required), required
)
self.assertEqual(v2_data["aliases"]["prgs-reconciler"], "prgs.gitea.reconciler")
assessment = reconciler_profile.assess_reconciler_profile(allowed, forbidden)
self.assertTrue(assessment["valid"])
self.assertTrue(migrate_profiles.validate_v2_data(v2_data))
def test_reconciler_profile_defaults(self):
"""Reconciler defaults are fully canonical and loader-valid."""
import gitea_config
import reconciler_profile
v1_data = {
"version": 1,
"profiles": {
"prgs-reconciler": {
"base_url": "redacted-prgs-service",
"username": "reconciler-agent",
"auth": {"type": "keychain", "id": "reconciler-ref"},
"execution_profile": "prgs-reconciler",
}
}
}
v2_data = migrate_profiles.migrate_v1_to_v2(v1_data)
reconciler = (
v2_data["environments"]["prgs"]["services"]["gitea"]
["identities"]["reconciler"]
)
self.assertEqual(reconciler["role"], "reconciler")
self.assertEqual(
reconciler["allowed_operations"],
migrate_profiles.RECONCILER_DEFAULT_ALLOWED,
)
self.assertEqual(
reconciler["forbidden_operations"],
migrate_profiles.RECONCILER_DEFAULT_FORBIDDEN,
)
for op in reconciler["allowed_operations"]:
self.assertEqual(gitea_config.normalize_operation(op), op)
self.assertTrue(op.startswith("gitea."))
assessment = reconciler_profile.assess_reconciler_profile(
reconciler["allowed_operations"],
reconciler["forbidden_operations"],
)
self.assertTrue(assessment["valid"])
self.assertNotIn(
"gitea.branch.delete", assessment["missing_recommended_operations"]
)
def test_reconciler_migration_idempotent_canonicalize(self):
"""Second canonicalize of already-canonical ops is a no-op."""
first = migrate_profiles.canonicalize_operations(
list(migrate_profiles.RECONCILER_DEFAULT_ALLOWED)
)
second = migrate_profiles.canonicalize_operations(first)
self.assertEqual(first, second)
self.assertEqual(first, list(migrate_profiles.RECONCILER_DEFAULT_ALLOWED))
def test_reconciler_missing_required_fails_visibly(self):
"""Missing gitea.pr.close after migration fails closed (not silent drop)."""
v1_data = {
"version": 1,
"profiles": {
"prgs-reconciler": {
"base_url": "redacted-prgs-service",
"username": "reconciler-agent",
"auth": {"type": "keychain", "id": "reconciler-ref"},
"execution_profile": "prgs-reconciler",
"allowed_operations": ["read", "gitea.branch.delete"],
"forbidden_operations": ["merge"],
}
},
}
with self.assertRaisesRegex(ValueError, "missing required"):
migrate_profiles.migrate_v1_to_v2(v1_data)
def test_unknown_operation_fails_visibly(self):
v1_data = {
"version": 1,
"profiles": {
"prgs-author": {
"base_url": "redacted-prgs-service",
"username": "jcwalker3",
"auth": {"type": "keychain", "id": "hidden-author-ref"},
"execution_profile": "prgs-author",
"allowed_operations": ["read", "not.a.real.op"],
"forbidden_operations": ["merge"],
}
},
}
with self.assertRaisesRegex(ValueError, "cannot be canonicalized"):
migrate_profiles.migrate_v1_to_v2(v1_data)
def test_role_inference_author_reviewer_merger_reconciler(self):
self.assertEqual(
migrate_profiles.infer_role("prgs-author", "prgs-author"), "author"
)
self.assertEqual(
migrate_profiles.infer_role("prgs-reviewer", "prgs-reviewer"),
"reviewer",
)
self.assertEqual(
migrate_profiles.infer_role("prgs-reconciler", "prgs-reconciler"),
"reconciler",
)
self.assertIsNone(
migrate_profiles.infer_role("prgs-merger", "prgs-merger")
)
if __name__ == "__main__":
unittest.main()
+3 -7
View File
@@ -76,17 +76,13 @@ class TestPreflightReadSurvival(unittest.TestCase):
self.assertIn("task mismatch", str(ctx.exception))
def test_capability_consumed_after_mutation_gate(self):
# Use reconciler/close_pr so this purity-order test does not require a
# branches/ worktree (author create_issue would hit #274/#683 guards).
# Test isolation stays explicit; production author guards remain live
# under force-on (see tests/test_issue_683_workflow_scope_guards.py).
mcp_server.record_preflight_check("whoami")
mcp_server.record_preflight_check(
"capability", resolved_role="reconciler", resolved_task="close_pr"
"capability", resolved_role="author", resolved_task="create_issue"
)
mcp_server.verify_preflight_purity(task="close_pr")
mcp_server.verify_preflight_purity(task="create_issue")
with self.assertRaises(RuntimeError) as ctx:
mcp_server.verify_preflight_purity(task="close_pr")
mcp_server.verify_preflight_purity(task="create_issue")
self.assertIn("has not been resolved", str(ctx.exception))
def test_whoami_recovery_after_violation_clears_capability(self):
+3 -15
View File
@@ -86,21 +86,9 @@ class TestReconcilerCloseWorkspaceGuard(unittest.TestCase):
):
srv._preflight_resolved_role = "author"
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
try:
res = srv.gitea_create_issue(title="Test", body="body")
except RuntimeError as exc:
self.assertIn("stable control checkout", str(exc))
else:
# #683 typed blocker at mutation entrypoint
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or []) + str(
res.get("blocker_kind") or ""
)
self.assertTrue(
"stable control checkout" in blob
or "missing_issue_worktree" in blob
or "control checkout" in blob.lower()
)
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(title="Test", body="body")
self.assertIn("stable control checkout", str(ctx.exception))
if __name__ == "__main__":
-36
View File
@@ -82,42 +82,6 @@ class TestReconcilerProfileModel(unittest.TestCase):
"reconciler",
)
def test_branch_delete_is_recommended_for_reconciler(self):
self.assertIn(
"gitea.branch.delete",
reconciler_profile.RECONCILER_RECOMMENDED_OPERATIONS,
)
self.assertNotIn(
"gitea.branch.delete",
reconciler_profile.RECONCILER_REQUIRED_OPERATIONS,
)
def test_reconciler_with_branch_delete_stays_valid(self):
allowed = PRGS_RECONCILER_ALLOWED + ["gitea.branch.delete"]
result = reconciler_profile.assess_reconciler_profile(
allowed,
PRGS_RECONCILER_FORBIDDEN,
)
self.assertTrue(result["is_reconciler_profile"])
self.assertTrue(result["valid"])
self.assertNotIn(
"gitea.branch.delete", result["missing_recommended_operations"]
)
self.assertEqual(
mcp_server._role_kind(allowed, PRGS_RECONCILER_FORBIDDEN),
"reconciler",
)
def test_reconciler_without_branch_delete_reports_missing_recommended(self):
result = reconciler_profile.assess_reconciler_profile(
PRGS_RECONCILER_ALLOWED,
PRGS_RECONCILER_FORBIDDEN,
)
self.assertTrue(result["valid"])
self.assertIn(
"gitea.branch.delete", result["missing_recommended_operations"]
)
if __name__ == "__main__":
unittest.main()
+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 == []
-626
View File
@@ -1,626 +0,0 @@
"""Workflow scope ownership and production-guard hardening (#683).
Implements fail-closed enforcement so sessions cannot:
* mutate source/tests on the root/control checkout (including temporary
diagnostic edits) without binding an issue-backed ``branches/`` worktree;
* continue out-of-scope source work while locked to a different issue;
* disable, skip, or conceal production root/branches/porcelain guards solely
because pytest/unittest is loaded.
This module is pure assessment + small durable ledger helpers. Callers gather
live facts (lock, branch, porcelain, worktree path) and pass them in. Existing
root_checkout_guard / author_mutation_worktree assessors remain authoritative;
this module composes typed blockers with exact recovery actions.
Do **not** reintroduce the rejected #681 / ``300a4ca`` patterns:
* early-return from workspace verification under ``_preflight_in_test_mode()``
* porcelain filtering that strips ``*.py`` lines under pytest
"""
from __future__ import annotations
import os
import re
import threading
from typing import Any
import author_mutation_worktree
from reviewer_worktree import parse_dirty_tracked_files
# ── force-on / test isolation ────────────────────────────────────────────────
# When set, production root/branches/scope guards MUST run even under pytest.
# Unit tests that only need preflight-order isolation leave this unset and
# use GITEA_TEST_PORCELAIN / fixtures; real-entrypoint proof sets this to "1".
FORCE_PRODUCTION_GUARDS_ENV = "GITEA_TEST_FORCE_PRODUCTION_GUARDS"
# Existing force signals also mean "exercise production dirtiness paths".
_FORCE_DIRTY_ENV = "GITEA_TEST_FORCE_DIRTY"
_FORCE_PORCELAIN_ENV = "GITEA_TEST_PORCELAIN"
# ── typed blocker kinds ──────────────────────────────────────────────────────
BLOCKER_ROOT_DIAGNOSTIC_EDIT = "root_diagnostic_edit"
BLOCKER_MISSING_ISSUE_SCOPE = "missing_issue_scope"
BLOCKER_OUT_OF_SCOPE_ISSUE = "out_of_scope_issue"
BLOCKER_MISSING_WORKTREE = "missing_issue_worktree"
BLOCKER_UNRECORDED_FAILURE = "unrecorded_workflow_failure"
BLOCKER_PRODUCTION_GUARD = "production_guard_violation"
BLOCKER_KINDS = frozenset(
{
BLOCKER_ROOT_DIAGNOSTIC_EDIT,
BLOCKER_MISSING_ISSUE_SCOPE,
BLOCKER_OUT_OF_SCOPE_ISSUE,
BLOCKER_MISSING_WORKTREE,
BLOCKER_UNRECORDED_FAILURE,
BLOCKER_PRODUCTION_GUARD,
}
)
_NEXT_ACTIONS: dict[str, str] = {
BLOCKER_ROOT_DIAGNOSTIC_EDIT: (
"Stop editing the control/root checkout. Preserve or discard root WIP "
"durably, restore root to clean master, lock or create the owning issue, "
"bind branches/issue-<N>-*, set GITEA_AUTHOR_WORKTREE to that worktree, "
"then re-run the mutation."
),
BLOCKER_MISSING_ISSUE_SCOPE: (
"Select or create the owning Gitea issue, claim/lock it "
"(gitea_mark_issue + gitea_lock_issue), bind branches/issue-<N>-* "
"from clean master, then re-run the mutation from that worktree."
),
BLOCKER_OUT_OF_SCOPE_ISSUE: (
"Stop. The active issue lock does not own this work. Release or finish "
"the current issue lease, then select/create and lock the correct "
"owning issue, bind its branches/issue-<N>-* worktree, and re-run."
),
BLOCKER_MISSING_WORKTREE: (
"Bind an issue-backed worktree under branches/ (scripts/worktree-start "
"or git worktree add branches/issue-<N>-*), set GITEA_AUTHOR_WORKTREE / "
"worktree_path to that path, keep the control checkout clean on master, "
"then re-run the mutation."
),
BLOCKER_UNRECORDED_FAILURE: (
"Record the workflow/tool failure durably first (issue comment or "
"workflow_scope_guard.record_workflow_failure), then continue only "
"inside the owning issue-backed worktree."
),
BLOCKER_PRODUCTION_GUARD: (
"Resolve the production guard violation: clean or isolate the control "
"checkout, bind the owning issue worktree under branches/, and re-run "
"with production guards active."
),
}
_ISSUE_IN_BRANCH_RE = re.compile(r"issue-(\d+)", re.IGNORECASE)
# In-process durable failure ledger (also written via optional sink callback).
_ledger_lock = threading.Lock()
_failure_ledger: list[dict[str, Any]] = []
class ProductionGuardError(RuntimeError):
"""Fail-closed production guard with typed blocker metadata (#683)."""
def __init__(
self,
message: str,
*,
blocker_kind: str,
exact_next_action: str | None = None,
reasons: list[str] | None = None,
details: dict[str, Any] | None = None,
) -> None:
super().__init__(message)
kind = (blocker_kind or "").strip()
if kind not in BLOCKER_KINDS:
kind = BLOCKER_PRODUCTION_GUARD
self.blocker_kind = kind
self.exact_next_action = (
(exact_next_action or "").strip() or _NEXT_ACTIONS[kind]
)
self.reasons = list(reasons or [message])
self.details = dict(details or {})
def production_guards_forced() -> bool:
"""True when the explicit #683 force-on flag requests production guards."""
return (os.environ.get(FORCE_PRODUCTION_GUARDS_ENV) or "").strip().lower() in {
"1",
"true",
"yes",
"on",
}
def purity_order_forced() -> bool:
"""True when tests force preflight-order dirtiness paths (legacy flags)."""
if os.environ.get(_FORCE_DIRTY_ENV):
return True
# GITEA_TEST_PORCELAIN present (even empty) means dirtiness paths are live.
if os.environ.get(_FORCE_PORCELAIN_ENV) is not None:
return True
return False
def production_guards_active(*, in_test_mode: bool) -> bool:
"""Whether production root/branches/scope guards must execute.
Production (non-test) always active. Under pytest, active when either the
explicit #683 force-on flag or legacy dirty/porcelain force signals are
set never skip production enforcement solely because tests are running
when force-on is requested.
"""
if production_guards_forced() or purity_order_forced():
return True
return not bool(in_test_mode)
def extract_issue_number_from_branch(branch_name: str | None) -> int | None:
"""Return the first issue-N number embedded in a branch name, if any."""
text = (branch_name or "").strip()
if not text:
return None
match = _ISSUE_IN_BRANCH_RE.search(text)
if not match:
return None
try:
return int(match.group(1))
except ValueError:
return None
def is_source_or_test_path(path: str) -> bool:
"""True for tracked source/test paths that must not land as root WIP."""
p = (path or "").replace("\\", "/").lstrip("./")
if not p:
return False
if p.startswith("tests/") or "/tests/" in f"/{p}":
return True
if p.endswith((".py", ".pyi", ".toml", ".cfg", ".ini", ".sh")):
return True
if p in {"requirements.txt", "pyproject.toml", "setup.py", "setup.cfg"}:
return True
return False
def dirty_source_files(porcelain_status: str) -> list[str]:
"""Tracked dirty paths that count as source/test contamination."""
dirty = parse_dirty_tracked_files(porcelain_status or "")
return [p for p in dirty if is_source_or_test_path(p)]
def assess_issue_scope_ownership(
*,
locked_issue_number: int | None,
target_issue_number: int | None = None,
branch_name: str | None = None,
role_kind: str | None = None,
require_lock_for_author: bool = False,
) -> dict[str, Any]:
"""Fail closed when the session issue lock does not own the attempted work.
* Author sessions that require a lock fail when none is held.
* When a lock exists, the target issue (tool argument) and/or the issue
number embedded in the branch must match the locked issue.
* Reviewer/merger/reconciler roles are not issue-scope owners of author
implementation work and skip the author lock requirement.
"""
role = (role_kind or "").strip().lower()
locked = locked_issue_number
if isinstance(locked, str) and locked.isdigit():
locked = int(locked)
if locked is not None:
try:
locked = int(locked)
except (TypeError, ValueError):
locked = None
target = target_issue_number
if target is not None:
try:
target = int(target)
except (TypeError, ValueError):
target = None
branch_issue = extract_issue_number_from_branch(branch_name)
reasons: list[str] = []
blocker_kind: str | None = None
# Non-author roles do not take author issue locks for implementation.
if role in {"reviewer", "merger", "reconciler"}:
return _scope_ok(locked, target, branch_issue)
if require_lock_for_author and locked is None:
reasons.append(
"no owning issue lock is bound for this author session; "
"source/test mutation requires selecting or creating an owning issue first"
)
blocker_kind = BLOCKER_MISSING_ISSUE_SCOPE
if locked is not None and target is not None and locked != target:
reasons.append(
f"session is locked to issue #{locked} but mutation targets issue "
f"#{target}; out-of-scope until the owning issue is selected"
)
blocker_kind = BLOCKER_OUT_OF_SCOPE_ISSUE
if locked is not None and branch_issue is not None and locked != branch_issue:
reasons.append(
f"session is locked to issue #{locked} but workspace branch is for "
f"issue #{branch_issue}; bind the matching issue-backed worktree"
)
blocker_kind = BLOCKER_OUT_OF_SCOPE_ISSUE
if reasons:
kind = blocker_kind or BLOCKER_MISSING_ISSUE_SCOPE
return {
"proven": False,
"block": True,
"blocker_kind": kind,
"exact_next_action": _NEXT_ACTIONS[kind],
"reasons": reasons,
"locked_issue_number": locked,
"target_issue_number": target,
"branch_issue_number": branch_issue,
}
return _scope_ok(locked, target, branch_issue)
def assess_root_source_mutation(
*,
workspace_path: str,
canonical_repo_root: str,
porcelain_status: str,
current_branch: str | None = None,
locked_issue_number: int | None = None,
role_kind: str | None = None,
) -> dict[str, Any]:
"""Fail closed for diagnostic/source edits on the control/root checkout.
Allowed only when the active workspace is under ``branches/``. Dirty
tracked source/test files on the control checkout always block, including
temporary/diagnostic/test-only intent.
"""
role = (role_kind or "").strip().lower()
if role == "reconciler":
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"dirty_source_files": [],
}
root = os.path.realpath(canonical_repo_root or "")
workspace = os.path.realpath(workspace_path or root or ".")
under_branches = author_mutation_worktree.is_path_under_branches(workspace, root)
dirty_src = dirty_source_files(porcelain_status)
reasons: list[str] = []
blocker_kind: str | None = None
if not under_branches and workspace == root and dirty_src:
# Root workspace with source dirtiness is unattributed root WIP.
# (Clean-root author binding is enforced by branches-only #274.)
reasons.append(
"control/root checkout has tracked source or test edits "
f"(dirty files: {', '.join(dirty_src)}); diagnostic or temporary "
"edits on the root checkout are forbidden"
)
blocker_kind = BLOCKER_ROOT_DIAGNOSTIC_EDIT
if (
not under_branches
and workspace == root
and not dirty_src
and role == "author"
):
# Explicit missing-worktree signal for force-on author entrypoints.
reasons.append(
"author source/test mutation from the stable control checkout is "
"forbidden; bind an issue-backed worktree under branches/ first"
)
blocker_kind = BLOCKER_MISSING_WORKTREE
if reasons:
kind = blocker_kind or BLOCKER_ROOT_DIAGNOSTIC_EDIT
return {
"proven": False,
"block": True,
"blocker_kind": kind,
"exact_next_action": _NEXT_ACTIONS[kind],
"reasons": reasons,
"dirty_source_files": dirty_src,
"workspace_path": workspace,
"canonical_repo_root": root,
"under_branches": under_branches,
"locked_issue_number": locked_issue_number,
}
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"dirty_source_files": dirty_src,
"workspace_path": workspace,
"canonical_repo_root": root,
"under_branches": under_branches,
"locked_issue_number": locked_issue_number,
}
def assess_production_mutation_guards(
*,
workspace_path: str,
canonical_repo_root: str,
porcelain_status: str,
current_branch: str | None = None,
locked_issue_number: int | None = None,
target_issue_number: int | None = None,
role_kind: str | None = None,
require_author_lock: bool = False,
in_test_mode: bool = False,
) -> dict[str, Any]:
"""Compose root + scope production guards when they must be active (#683)."""
if not production_guards_active(in_test_mode=in_test_mode):
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"skipped": True,
"skip_reason": "production guards not active (test isolation without force-on)",
}
root_assess = assess_root_source_mutation(
workspace_path=workspace_path,
canonical_repo_root=canonical_repo_root,
porcelain_status=porcelain_status,
current_branch=current_branch,
locked_issue_number=locked_issue_number,
role_kind=role_kind,
)
if root_assess["block"]:
return {**root_assess, "skipped": False}
scope_assess = assess_issue_scope_ownership(
locked_issue_number=locked_issue_number,
target_issue_number=target_issue_number,
branch_name=current_branch,
role_kind=role_kind,
require_lock_for_author=require_author_lock,
)
if scope_assess["block"]:
return {**scope_assess, "skipped": False}
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"skipped": False,
"root": root_assess,
"scope": scope_assess,
}
def raise_if_blocked(assessment: dict[str, Any]) -> None:
"""Raise :class:`ProductionGuardError` when *assessment* blocks."""
if not assessment or not assessment.get("block"):
return
kind = assessment.get("blocker_kind") or BLOCKER_PRODUCTION_GUARD
reasons = list(assessment.get("reasons") or ["production guard violation"])
message = (
f"Workflow scope guard (#683) [{kind}]: {'; '.join(reasons)}. "
f"exact_next_action: {assessment.get('exact_next_action') or _NEXT_ACTIONS.get(kind, '')}"
)
raise ProductionGuardError(
message,
blocker_kind=kind,
exact_next_action=assessment.get("exact_next_action"),
reasons=reasons,
details={
k: v
for k, v in assessment.items()
if k
not in {
"proven",
"block",
"blocker_kind",
"exact_next_action",
"reasons",
}
},
)
def block_response(
assessment: dict[str, Any] | ProductionGuardError | None = None,
*,
blocker_kind: str | None = None,
reasons: list[str] | None = None,
exact_next_action: str | None = None,
**extra: Any,
) -> dict[str, Any]:
"""Structured fail-closed tool response with typed blocker fields."""
if isinstance(assessment, ProductionGuardError):
kind = assessment.blocker_kind
reason_list = list(assessment.reasons)
next_action = assessment.exact_next_action
extra = {**assessment.details, **extra}
elif isinstance(assessment, dict) and assessment.get("block"):
kind = assessment.get("blocker_kind") or BLOCKER_PRODUCTION_GUARD
reason_list = list(assessment.get("reasons") or [])
next_action = assessment.get("exact_next_action") or _NEXT_ACTIONS.get(
kind, _NEXT_ACTIONS[BLOCKER_PRODUCTION_GUARD]
)
else:
kind = (blocker_kind or BLOCKER_PRODUCTION_GUARD).strip()
if kind not in BLOCKER_KINDS:
kind = BLOCKER_PRODUCTION_GUARD
reason_list = list(reasons or ["production guard violation"])
next_action = exact_next_action or _NEXT_ACTIONS[kind]
if kind not in BLOCKER_KINDS:
kind = BLOCKER_PRODUCTION_GUARD
if not reason_list:
reason_list = ["production guard violation"]
next_action = (next_action or "").strip() or _NEXT_ACTIONS[kind]
out: dict[str, Any] = {
"success": False,
"performed": False,
"blocker_kind": kind,
"exact_next_action": next_action,
"reasons": reason_list,
}
for key, value in extra.items():
if key not in out and value is not None:
out[key] = value
return out
def format_production_guard_error(assessment: dict[str, Any]) -> str:
"""Single RuntimeError string carrying kind + exact next action."""
kind = assessment.get("blocker_kind") or BLOCKER_PRODUCTION_GUARD
reasons = "; ".join(assessment.get("reasons") or ["production guard violation"])
next_action = assessment.get("exact_next_action") or _NEXT_ACTIONS.get(
kind, _NEXT_ACTIONS[BLOCKER_PRODUCTION_GUARD]
)
return (
f"Workflow scope guard (#683) [{kind}]: {reasons}. "
f"exact_next_action: {next_action}"
)
# ── durable failure recording ────────────────────────────────────────────────
def record_workflow_failure(
*,
kind: str,
detail: str,
issue_number: int | None = None,
task: str | None = None,
sink: Any | None = None,
) -> dict[str, Any]:
"""Record a workflow/tool failure before source edits continue (#683 AC8).
*sink* may be a callable ``sink(record)`` (e.g. tests) or omitted for the
in-process ledger only. Returns the durable record.
"""
record = {
"kind": (kind or "workflow_failure").strip() or "workflow_failure",
"detail": (detail or "").strip(),
"issue_number": issue_number,
"task": task,
"pid": os.getpid(),
}
with _ledger_lock:
_failure_ledger.append(dict(record))
if callable(sink):
sink(record)
return record
def clear_workflow_failure_ledger() -> None:
"""Test helper: reset the in-process failure ledger."""
with _ledger_lock:
_failure_ledger.clear()
def workflow_failure_ledger() -> list[dict[str, Any]]:
"""Copy of durable in-process failure records."""
with _ledger_lock:
return [dict(r) for r in _failure_ledger]
def assess_durable_failure_recorded(
*,
require_record: bool,
pending_source_mutation: bool,
) -> dict[str, Any]:
"""Block source mutation when a workflow failure was not recorded first."""
if not require_record or not pending_source_mutation:
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
}
with _ledger_lock:
has_record = bool(_failure_ledger)
if has_record:
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
}
return {
"proven": False,
"block": True,
"blocker_kind": BLOCKER_UNRECORDED_FAILURE,
"exact_next_action": _NEXT_ACTIONS[BLOCKER_UNRECORDED_FAILURE],
"reasons": [
"workflow/tool failure triggered a need for source changes but no "
"durable failure record exists yet"
],
}
def porcelain_preserves_python_paths(porcelain_status: str) -> bool:
"""Regression helper: dirty ``*.py`` lines must remain visible (#683)."""
text = porcelain_status or ""
for line in text.splitlines():
stripped = line.strip()
if stripped.endswith(".py") or ".py " in stripped or stripped.endswith(".py"):
# Any py path present proves no silent strip of all *.py lines.
if " M " in f" {stripped}" or stripped[:1] in "MADRCTU" or len(line) >= 4:
return True
# Empty porcelain is fine; integrity means we did not strip when present.
return ".py" not in text
def assert_no_pytest_porcelain_filter(source_text: str) -> list[str]:
"""Static check: production reader must not strip ``*.py`` under pytest."""
findings: list[str] = []
lowered = source_text or ""
if "endswith(\".py\")" in lowered or "endswith('.py')" in lowered:
if "pytest" in lowered and "porcelain" in lowered.lower():
findings.append(
"production porcelain reader must not filter *.py under pytest "
"(rejected 300a4ca pattern)"
)
if "if \"pytest\" in sys.modules" in lowered and "porcelain" in lowered.lower():
if ".py" in lowered and ("join" in lowered or "endswith" in lowered):
findings.append(
"test-mode porcelain filtering of source files is forbidden (#683)"
)
return findings
def _scope_ok(
locked: int | None,
target: int | None,
branch_issue: int | None,
) -> dict[str, Any]:
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"locked_issue_number": locked,
"target_issue_number": target,
"branch_issue_number": branch_issue,
}