Compare commits

..
16 changed files with 735 additions and 455 deletions
+26
View File
@@ -1568,6 +1568,32 @@ class ControlPlaneDB:
).fetchone() ).fetchone()
return dict(row) if row else None return dict(row) if row else None
def list_incident_links(
self,
*,
provider: str | None = None,
gitea_org: str | None = None,
gitea_repo: str | None = None,
limit: int = 100,
) -> list[dict[str, Any]]:
"""List stored incident_links rows, optionally filtered by provider/repo (#612 / #649)."""
query = "SELECT * FROM incident_links WHERE 1=1"
params: list[Any] = []
if provider:
query += " AND provider = ?"
params.append(provider.strip().lower())
if gitea_org:
query += " AND gitea_org = ?"
params.append(_norm_scope(gitea_org))
if gitea_repo:
query += " AND gitea_repo = ?"
params.append(_norm_scope(gitea_repo))
query += " ORDER BY link_id DESC LIMIT ?"
params.append(max(1, limit))
with self._tx(immediate=False) as conn:
rows = conn.execute(query, params).fetchall()
return [dict(r) for r in rows]
# ── lease lifecycle (#601) ──────────────────────────────────────────── # ── lease lifecycle (#601) ────────────────────────────────────────────
@@ -0,0 +1,35 @@
# Web Console: Sentry/GlitchTip Observability & Incident Bridge Console (#649)
This document describes the Phase 4 observability console surface integrated into the MCP Control Plane Web Console (`webui/`), backed by the #612 incident bridge and the #613 control-plane DB substrate.
## Architectural Authority Model (ADR Alignment)
Per the Web Console Architecture ADR (`docs/architecture/webui-control-plane-console-architecture-adr.md`):
| Layer | Responsibility | Authority |
|---|---|---|
| **Gitea** | Durable work record | Issues, PRs, comments, reviews, labels, merges |
| **Control-plane DB** | Live coordination & linkage | `incident_links` table, session leases, allocations |
| **Sentry / GlitchTip** | Observability input | Unresolved incidents, error events, stack traces |
| **Incident Bridge (#612)** | Reconciliation engine | Reconciles provider observations into Gitea issues |
| **Web Console (`webui/`)** | Read-only projection & gated actions | Projects connection health & correlation links; gates writes |
> **Key Rule:** Raw monitoring incidents are **never** assignable control-plane `work_items`. They remain observation input only.
## Redaction Boundary Invariants
1. **No secrets in returns or rendering:** Auth tokens (`SENTRY_AUTH_TOKEN`, `GLITCHTIP_AUTH_TOKEN`), DSNs, `Authorization` headers, and sensitive local file paths are passed through `webui.console_redaction` before leaving the server.
2. **Safe projection:** Connection objects report `credentials_present: true/false` rather than exposing raw keys or headers.
## Console Endpoints
- **HTML Surface:** `GET /observability` — Renders provider connection cards, error correlation tables, and gated reconcile controls.
- **Versioned API:** `GET /api/v1/observability` — Returns structured JSON snapshot with `schema_version`, `providers`, `links`, and `metrics`.
- **Legacy Compatibility Alias:** `GET /api/observability` — Read-only compatibility alias for Phase 4.
## Gated Actions
- `observability_reconcile_incident` (`gitea_observability_reconcile_incident`): Triggers or previews dry-run issue reconciliation for a provider incident.
- `observability_link_issue` (`gitea_observability_link_issue`): Links a provider incident to an existing Gitea tracking issue.
Both actions require `operator` role and gate through `task_capability_map`. Execution fails closed in read-only MVP mode.
+2
View File
@@ -98,6 +98,8 @@ already define, and a regression test asserts each mapping matches.
| `system.rebind_session_worktree` | operator | gated_write | `gitea.read` | Yes | No | No | 2 | | `system.rebind_session_worktree` | operator | gated_write | `gitea.read` | Yes | No | No | 2 |
| `system.reconcile_cleanups` | controller | privileged | `gitea.pr.close` | Yes | No | No | 2 | | `system.reconcile_cleanups` | controller | privileged | `gitea.pr.close` | Yes | No | No | 2 |
| `initiate_workflow` | operator | gated_write | `gitea.read` | Yes | No | No | 2 | | `initiate_workflow` | operator | gated_write | `gitea.read` | Yes | No | No | 2 |
| `observability_reconcile_incident` | operator | gated_write | `gitea.read` | Yes | No | No | 4 |
| `observability_link_issue` | operator | gated_write | `gitea.read` | Yes | No | No | 4 |
**Dual control** means the acting principal may not be the sole authority: a **Dual control** means the acting principal may not be the sole authority: a
second distinct principal must confirm. **Break-glass** means the action is second distinct principal must confirm. **Break-glass** means the action is
+1 -15
View File
@@ -24,8 +24,6 @@ import subprocess
import uuid import uuid
from datetime import datetime, timedelta, timezone from datetime import datetime, timedelta, timezone
from typing import Any from typing import Any
import hashlib
@@ -2260,12 +2258,7 @@ def _seed_session_context(
expected_username=expected, expected_username=expected,
source=source, source=source,
canonical_repository_root=canonical_root_pin, canonical_repository_root=canonical_root_pin,
cohort_id=_COHORT_ID,
startup_sha=_STARTUP_PARITY.get("startup_head"),
endpoint=host or (profile.get("base_url") or "").strip() or None,
config_fingerprint=_CONFIG_FINGERPRINT,
) )
import issue_work_duplicate_gate # noqa: E402 import issue_work_duplicate_gate # noqa: E402
import issue_workflow_labels # noqa: E402 import issue_workflow_labels # noqa: E402
import terminal_pr_label_cleanup # noqa: E402 # #780 status:pr-open terminal rule import terminal_pr_label_cleanup # noqa: E402 # #780 status:pr-open terminal rule
@@ -2294,11 +2287,6 @@ import stable_control_runtime # noqa: E402
# master has advanced past the running code and fail closed until restart. # master has advanced past the running code and fail closed until restart.
# Read-only operations are never blocked by staleness. # Read-only operations are never blocked by staleness.
_STARTUP_PARITY = master_parity_gate.capture_startup_parity(PROJECT_ROOT) _STARTUP_PARITY = master_parity_gate.capture_startup_parity(PROJECT_ROOT)
_COHORT_ID: str = f"cohort-p{os.getpid()}-{_STARTUP_PARITY.get('startup_head') or 'unknown'}"
_CONFIG_FINGERPRINT: str = hashlib.sha256(
(PROJECT_ROOT + str(_STARTUP_PARITY.get("startup_head"))).encode("utf-8")
).hexdigest()[:16]
# Stable-control runtime facts (#615): which runtime this process serves from. # Stable-control runtime facts (#615): which runtime this process serves from.
# These are the *immutable* facts -- process root, branch, head, checkout-ness -- # These are the *immutable* facts -- process root, branch, head, checkout-ness --
@@ -14209,10 +14197,8 @@ def _current_master_parity() -> dict:
current_head = master_parity_gate.read_git_head(PROJECT_ROOT) current_head = master_parity_gate.read_git_head(PROJECT_ROOT)
live_head = master_parity_gate.read_remote_master_head( live_head = master_parity_gate.read_remote_master_head(
PROJECT_ROOT, remote=_git_default_remote_name(PROJECT_ROOT)) PROJECT_ROOT, remote=_git_default_remote_name(PROJECT_ROOT))
bound_context = session_ctx.get_session_context()
return master_parity_gate.assess_master_parity( return master_parity_gate.assess_master_parity(
_STARTUP_PARITY, current_head, live_remote_head=live_head, bound_cohort=bound_context) _STARTUP_PARITY, current_head, live_remote_head=live_head)
def _current_runtime_mode_report(refresh: bool = False) -> dict: def _current_runtime_mode_report(refresh: bool = False) -> dict:
+9 -70
View File
@@ -183,7 +183,6 @@ def assess_master_parity(
startup: dict | None, startup: dict | None,
current_head: str | None, current_head: str | None,
live_remote_head: str | None = None, live_remote_head: str | None = None,
bound_cohort: dict | None = None,
) -> dict: ) -> dict:
"""Compare the startup baseline against the current on-disk ``HEAD``. """Compare the startup baseline against the current on-disk ``HEAD``.
@@ -193,8 +192,7 @@ def assess_master_parity(
could not be determined, which is not treated as stale). could not be determined, which is not treated as stale).
- ``stale`` -- the on-disk master has definitively advanced past the - ``stale`` -- the on-disk master has definitively advanced past the
running process. running process.
- ``restart_required`` -- ``stale``, ``live_stale``, or ``cohort_stale``; the - ``restart_required`` -- ``stale`` or ``live_stale``; the recovery action.
recovery action.
- ``determinable`` -- whether both local HEADs were known well enough to - ``determinable`` -- whether both local HEADs were known well enough to
compare. compare.
- ``startup_head`` / ``current_head`` / ``reasons``. - ``startup_head`` / ``current_head`` / ``reasons``.
@@ -211,69 +209,24 @@ def assess_master_parity(
- ``live_known`` -- whether the live remote target was resolved. - ``live_known`` -- whether the live remote target was resolved.
- ``live_stale`` -- the live remote master has advanced past the running - ``live_stale`` -- the live remote master has advanced past the running
process (daemon is behind live master) even if local parity is green. process (daemon is behind live master) even if local parity is green.
- ``bound_cohort`` -- metadata describing the bound MCP cohort. - ``mutation_safe`` -- the daemon code, local checkout, and live remote
- ``cohort_parity_match`` -- whether bound cohort startup SHA matches parity. target all agree; the only state in which a mutation may rely on parity.
- ``cohort_stale`` -- bound cohort startup SHA is stale relative to parity.
- ``mutation_safe`` -- the daemon code, local checkout, live remote target,
and bound cohort all agree; the only state in which a mutation may rely
on parity.
""" """
startup_head = (startup or {}).get("startup_head") startup_head = (startup or {}).get("startup_head")
reasons: list[str] = [] reasons: list[str] = []
cohort_info: dict | None = None
cohort_parity_match = True
cohort_stale = False
if bound_cohort:
c_id = str(bound_cohort.get("cohort_id") or "").strip() or None
c_pid = bound_cohort.get("pid")
c_sha = str(
bound_cohort.get("startup_sha")
or bound_cohort.get("git_head")
or ""
).strip() or None
c_endpoint = str(bound_cohort.get("endpoint") or "").strip() or None
c_fingerprint = str(
bound_cohort.get("config_fingerprint") or ""
).strip() or None
cohort_info = {
"cohort_id": c_id,
"pid": c_pid,
"startup_sha": c_sha,
"endpoint": c_endpoint,
"config_fingerprint": c_fingerprint,
}
parity_ref = live_remote_head or current_head or startup_head
if c_sha and parity_ref:
if c_sha.lower() != parity_ref.lower():
cohort_parity_match = False
cohort_stale = True
reasons.append(
f"bound cohort startup SHA '{_short(c_sha)}' does not "
f"match authoritative parity SHA '{_short(parity_ref)}' "
"(stale cohort refused)"
)
if startup_head is None: if startup_head is None:
reasons.append( reasons.append(
"startup commit was not captured; code parity cannot be enforced") "startup commit was not captured; code parity cannot be enforced")
return _result(True, False, False, startup_head, current_head, return _result(True, False, False, startup_head, current_head,
live_remote_head, False, reasons, live_remote_head, False, reasons)
bound_cohort=cohort_info,
cohort_parity_match=cohort_parity_match,
cohort_stale=cohort_stale)
if current_head is None: if current_head is None:
reasons.append( reasons.append(
"current workspace HEAD could not be read; code parity cannot be " "current workspace HEAD could not be read; code parity cannot be "
"enforced") "enforced")
return _result(True, False, False, startup_head, current_head, return _result(True, False, False, startup_head, current_head,
live_remote_head, False, reasons, live_remote_head, False, reasons)
bound_cohort=cohort_info,
cohort_parity_match=cohort_parity_match,
cohort_stale=cohort_stale)
local_in_parity = startup_head == current_head local_in_parity = startup_head == current_head
local_stale = not local_in_parity local_stale = not local_in_parity
@@ -293,28 +246,18 @@ def assess_master_parity(
return _result( return _result(
local_in_parity, local_stale, True, startup_head, current_head, local_in_parity, local_stale, True, startup_head, current_head,
live_remote_head, live_stale, reasons, live_remote_head, live_stale, reasons)
bound_cohort=cohort_info,
cohort_parity_match=cohort_parity_match,
cohort_stale=cohort_stale)
def _result(in_parity, stale, determinable, startup_head, current_head, def _result(in_parity, stale, determinable, startup_head, current_head,
live_remote_head, live_stale, reasons, bound_cohort=None, live_remote_head, live_stale, reasons):
cohort_parity_match=True, cohort_stale=False):
live_known = live_remote_head is not None live_known = live_remote_head is not None
mutation_safe = ( mutation_safe = (
determinable determinable and in_parity and live_known and not live_stale)
and in_parity
and live_known
and not live_stale
and cohort_parity_match
and not cohort_stale
)
return { return {
"in_parity": in_parity, "in_parity": in_parity,
"stale": stale, "stale": stale,
"restart_required": stale or live_stale or cohort_stale, "restart_required": stale or live_stale,
"determinable": determinable, "determinable": determinable,
"startup_head": startup_head, "startup_head": startup_head,
"current_head": current_head, "current_head": current_head,
@@ -324,15 +267,11 @@ def _result(in_parity, stale, determinable, startup_head, current_head,
"live_remote_head": live_remote_head, "live_remote_head": live_remote_head,
"live_known": live_known, "live_known": live_known,
"live_stale": live_stale, "live_stale": live_stale,
"cohort_parity_match": cohort_parity_match,
"cohort_stale": cohort_stale,
"bound_cohort": bound_cohort,
"mutation_safe": mutation_safe, "mutation_safe": mutation_safe,
"reasons": list(reasons), "reasons": list(reasons),
} }
def gate_disabled() -> bool: def gate_disabled() -> bool:
"""Whether the parity gate is disabled by env escape hatch.""" """Whether the parity gate is disabled by env escape hatch."""
return bool((os.environ.get(ENV_DISABLE) or "").strip()) return bool((os.environ.get(ENV_DISABLE) or "").strip())
+3 -45
View File
@@ -104,8 +104,6 @@ def classify_namespace_probe(
profile: str | None = None, profile: str | None = None,
configured: bool = True, configured: bool = True,
probe_source: str | None = None, probe_source: str | None = None,
expected_parity_sha: str | None = None,
bound_cohort: dict[str, Any] | None = None,
) -> dict[str, Any]: ) -> dict[str, Any]:
"""Classify whether a required tool is callable through a live namespace. """Classify whether a required tool is callable through a live namespace.
@@ -137,50 +135,20 @@ def classify_namespace_probe(
else: else:
error_type = "namespace_call_failed" error_type = "namespace_call_failed"
# Extract cohort metadata
cohort_meta = bound_cohort or probe.get("cohort") or probe.get("bound_cohort") or {}
cohort_id = str(
cohort_meta.get("cohort_id") or probe.get("cohort_id") or ""
).strip() or None
startup_sha = str(
cohort_meta.get("startup_sha")
or cohort_meta.get("git_head")
or probe.get("startup_sha")
or probe.get("git_head")
or ""
).strip() or None
endpoint = str(
cohort_meta.get("endpoint") or probe.get("endpoint") or ""
).strip() or None
config_fingerprint = str(
cohort_meta.get("config_fingerprint") or probe.get("config_fingerprint") or ""
).strip() or None
expected_sha = (expected_parity_sha or "").strip().lower() or None
stale_cohort = False
if expected_sha and startup_sha:
if startup_sha.lower() != expected_sha:
stale_cohort = True
error_type = "stale_cohort_refused"
if not configured: if not configured:
error_type = "namespace_not_configured" error_type = "namespace_not_configured"
elif registered is False: elif registered is False:
error_type = "tool_missing" error_type = "tool_missing"
elif not probe_result: elif not probe_result:
error_type = "live_probe_missing" error_type = "live_probe_missing"
elif stale_cohort:
error_type = "stale_cohort_refused"
elif not probe_success and not error_type: elif not probe_success and not error_type:
error_type = "namespace_call_failed" error_type = "namespace_call_failed"
callable_live = bool(configured and probe_result and probe_success and not stale_cohort) callable_live = bool(configured and probe_result and probe_success)
# Probe-path health (spawn or client). IDE-proven only for client path. # Probe-path health (spawn or client). IDE-proven only for client path.
healthy = bool(configured and registered is not False and callable_live) healthy = bool(configured and registered is not False and callable_live)
ide_namespace_proven = bool(healthy and source == PROBE_SOURCE_CLIENT) ide_namespace_proven = bool(healthy and source == PROBE_SOURCE_CLIENT)
process_pid = process.get("pid") if isinstance(process, dict) else ( process_pid = process.get("pid") if isinstance(process, dict) else None
cohort_meta.get("pid") if isinstance(cohort_meta, dict) else None
)
profile_name = profile or ( profile_name = profile or (
process.get("profile") if isinstance(process, dict) else None process.get("profile") if isinstance(process, dict) else None
) )
@@ -193,13 +161,7 @@ def classify_namespace_probe(
reasons.append( reasons.append(
f"Required tool '{tool}' is not registered in namespace '{ns}'." f"Required tool '{tool}' is not registered in namespace '{ns}'."
) )
if error_type == "stale_cohort_refused": if error_type == "live_probe_missing":
reasons.append(
f"Bound cohort startup SHA '{startup_sha[:12] if startup_sha else 'unknown'}' "
f"does not match expected parity SHA '{expected_sha[:12] if expected_sha else 'unknown'}' "
"(stale cohort refused)."
)
elif error_type == "live_probe_missing":
reasons.append( reasons.append(
f"No live client invocation proof was supplied for '{ns}.{tool}'." f"No live client invocation proof was supplied for '{ns}.{tool}'."
) )
@@ -286,10 +248,6 @@ def classify_namespace_probe(
"env": env_summary, "env": env_summary,
"config_path": config_path, "config_path": config_path,
"probe_source": source, "probe_source": source,
"cohort_id": cohort_id,
"startup_sha": startup_sha,
"endpoint": endpoint,
"config_fingerprint": config_fingerprint,
}, },
"blocks_merge_workflow": blocks, "blocks_merge_workflow": blocks,
} }
+1 -22
View File
@@ -151,16 +151,12 @@ class RestartCompletionProof:
unresolved_count: int unresolved_count: int
skipped_count: int skipped_count: int
note: str note: str
binding_unchanged: bool = False
prior_reconcile_id: str | None = None
def as_dict(self) -> dict[str, Any]: def as_dict(self) -> dict[str, Any]:
return { return {
"schema_version": self.schema_version, "schema_version": self.schema_version,
"reconcile_version": self.reconcile_version, "reconcile_version": self.reconcile_version,
"reconcile_id": self.reconcile_id, "reconcile_id": self.reconcile_id,
"binding_unchanged": self.binding_unchanged,
"prior_reconcile_id": self.prior_reconcile_id,
"started_at": self.started_at, "started_at": self.started_at,
"finished_at": self.finished_at, "finished_at": self.finished_at,
"boot_head_sha": self.boot_head_sha, "boot_head_sha": self.boot_head_sha,
@@ -177,7 +173,6 @@ class RestartCompletionProof:
"skipped_count": self.skipped_count, "skipped_count": self.skipped_count,
"note": self.note, "note": self.note,
"links": { "links": {
"umbrella": 655, "umbrella": 655,
"vision": 652, "vision": 652,
"roadmap": 653, "roadmap": 653,
@@ -364,9 +359,7 @@ def reconcile_after_restart(
now: datetime | None = None, now: datetime | None = None,
mode: str = MODE_LOG_ONLY, mode: str = MODE_LOG_ONLY,
reconcile_id: str | None = None, reconcile_id: str | None = None,
prior_reconcile_id: str | None = None,
) -> RestartCompletionProof: ) -> RestartCompletionProof:
"""Classify a post-restart inventory into a completion proof (#662). """Classify a post-restart inventory into a completion proof (#662).
Parameters Parameters
@@ -757,26 +750,12 @@ def reconcile_after_restart(
f"Mode={mode_norm}." f"Mode={mode_norm}."
) )
prior_id = str(
prior_reconcile_id
or inventory.get("prior_reconcile_id")
or ""
).strip() or None
target_rec_id = str(reconcile_id or "").strip() or None
binding_unchanged = bool(
prior_id and target_rec_id and target_rec_id == prior_id
)
final_reconcile_id = target_rec_id or f"reconcile-{uuid4().hex[:12]}"
return RestartCompletionProof( return RestartCompletionProof(
schema_version=SCHEMA_VERSION, schema_version=SCHEMA_VERSION,
reconcile_version=RECONCILE_VERSION, reconcile_version=RECONCILE_VERSION,
reconcile_id=final_reconcile_id, reconcile_id=(reconcile_id or f"reconcile-{uuid4().hex[:12]}"),
binding_unchanged=binding_unchanged,
prior_reconcile_id=prior_id,
started_at=_ts(started), started_at=_ts(started),
finished_at=_ts(finished), finished_at=_ts(finished),
boot_head_sha=( boot_head_sha=(
str(inventory.get("boot_head_sha")).strip() str(inventory.get("boot_head_sha")).strip()
if inventory.get("boot_head_sha") if inventory.get("boot_head_sha")
-50
View File
@@ -33,10 +33,6 @@ class _SessionContext:
source: str source: str
pid: int pid: int
canonical_repository_root: str | None = None canonical_repository_root: str | None = None
cohort_id: str | None = None
startup_sha: str | None = None
endpoint: str | None = None
config_fingerprint: str | None = None
def as_dict(self) -> dict[str, Any]: def as_dict(self) -> dict[str, Any]:
return { return {
@@ -51,14 +47,9 @@ class _SessionContext:
"source": self.source, "source": self.source,
"pid": self.pid, "pid": self.pid,
"canonical_repository_root": self.canonical_repository_root, "canonical_repository_root": self.canonical_repository_root,
"cohort_id": self.cohort_id,
"startup_sha": self.startup_sha,
"endpoint": self.endpoint,
"config_fingerprint": self.config_fingerprint,
} }
# Process-local only — never a shared file (same rationale as mutation authority). # Process-local only — never a shared file (same rationale as mutation authority).
# The frozen value prevents partial mutation, while the lock makes first-bind and # The frozen value prevents partial mutation, while the lock makes first-bind and
# sanctioned rebind atomic across concurrent MCP calls. # sanctioned rebind atomic across concurrent MCP calls.
@@ -81,13 +72,6 @@ def _reset_session_context_for_testing() -> None:
_SESSION_CONTEXT = None _SESSION_CONTEXT = None
def clear_session_context() -> None:
"""Purge process-session context and cohort bindings on disconnect."""
global _SESSION_CONTEXT
with _SESSION_CONTEXT_LOCK:
_SESSION_CONTEXT = None
def get_session_context() -> dict[str, Any] | None: def get_session_context() -> dict[str, Any] | None:
"""Return a detached snapshot of the bound context, or None if unbound.""" """Return a detached snapshot of the bound context, or None if unbound."""
with _SESSION_CONTEXT_LOCK: with _SESSION_CONTEXT_LOCK:
@@ -162,10 +146,6 @@ def bind_session_context(
expected_username: str | None = None, expected_username: str | None = None,
source: str = "bind", source: str = "bind",
canonical_repository_root: str | None = None, canonical_repository_root: str | None = None,
cohort_id: str | None = None,
startup_sha: str | None = None,
endpoint: str | None = None,
config_fingerprint: str | None = None,
) -> dict[str, Any]: ) -> dict[str, Any]:
"""Atomically bind/re-bind context (the explicit activation path).""" """Atomically bind/re-bind context (the explicit activation path)."""
with _SESSION_CONTEXT_LOCK: with _SESSION_CONTEXT_LOCK:
@@ -180,10 +160,6 @@ def bind_session_context(
expected_username=expected_username, expected_username=expected_username,
source=source, source=source,
canonical_repository_root=canonical_repository_root, canonical_repository_root=canonical_repository_root,
cohort_id=cohort_id,
startup_sha=startup_sha,
endpoint=endpoint,
config_fingerprint=config_fingerprint,
) )
@@ -199,10 +175,6 @@ def _bind_session_context_unlocked(
expected_username: str | None, expected_username: str | None,
source: str, source: str,
canonical_repository_root: str | None = None, canonical_repository_root: str | None = None,
cohort_id: str | None = None,
startup_sha: str | None = None,
endpoint: str | None = None,
config_fingerprint: str | None = None,
) -> dict[str, Any]: ) -> dict[str, Any]:
"""Store a complete immutable context while the caller holds the lock.""" """Store a complete immutable context while the caller holds the lock."""
global _SESSION_CONTEXT global _SESSION_CONTEXT
@@ -218,10 +190,6 @@ def _bind_session_context_unlocked(
source=source, source=source,
pid=os.getpid(), pid=os.getpid(),
canonical_repository_root=(canonical_repository_root or "").strip() or None, canonical_repository_root=(canonical_repository_root or "").strip() or None,
cohort_id=(cohort_id or "").strip() or None,
startup_sha=(startup_sha or "").strip() or None,
endpoint=(endpoint or "").strip() or None,
config_fingerprint=(config_fingerprint or "").strip() or None,
) )
return _SESSION_CONTEXT.as_dict() return _SESSION_CONTEXT.as_dict()
@@ -238,10 +206,6 @@ def seed_session_context_if_unbound(
expected_username: str | None = None, expected_username: str | None = None,
source: str = "seed", source: str = "seed",
canonical_repository_root: str | None = None, canonical_repository_root: str | None = None,
cohort_id: str | None = None,
startup_sha: str | None = None,
endpoint: str | None = None,
config_fingerprint: str | None = None,
) -> dict[str, Any]: ) -> dict[str, Any]:
"""Atomically bind only when this process has no current context. """Atomically bind only when this process has no current context.
@@ -263,15 +227,10 @@ def seed_session_context_if_unbound(
expected_username=expected_username, expected_username=expected_username,
source=source, source=source,
canonical_repository_root=canonical_repository_root, canonical_repository_root=canonical_repository_root,
cohort_id=cohort_id,
startup_sha=startup_sha,
endpoint=endpoint,
config_fingerprint=config_fingerprint,
) )
return _SESSION_CONTEXT.as_dict() return _SESSION_CONTEXT.as_dict()
def assess_session_context( def assess_session_context(
*, *,
profile_name: str | None, profile_name: str | None,
@@ -627,10 +586,6 @@ def mutation_context_audit_fields(
"session_identity": None, "session_identity": None,
"session_repository": None, "session_repository": None,
"session_org": None, "session_org": None,
"session_cohort_id": None,
"session_startup_sha": None,
"session_endpoint": None,
"session_config_fingerprint": None,
} }
return { return {
"session_context_bound": True, "session_context_bound": True,
@@ -643,14 +598,9 @@ def mutation_context_audit_fields(
"session_role_kind": data.get("role_kind"), "session_role_kind": data.get("role_kind"),
"session_context_source": data.get("source"), "session_context_source": data.get("source"),
"session_canonical_repository_root": data.get("canonical_repository_root"), "session_canonical_repository_root": data.get("canonical_repository_root"),
"session_cohort_id": data.get("cohort_id"),
"session_startup_sha": data.get("startup_sha"),
"session_endpoint": data.get("endpoint"),
"session_config_fingerprint": data.get("config_fingerprint"),
} }
def _assessment( def _assessment(
proven: bool, reasons: list[str], ctx: Mapping[str, Any] | None proven: bool, reasons: list[str], ctx: Mapping[str, Any] | None
) -> dict[str, Any]: ) -> dict[str, Any]:
@@ -1,253 +0,0 @@
"""Tests for Issue #689: Deterministic MCP namespace attachment.
Verifies cohort identity exposure, stale cohort refusal, parity matching,
reconcile_id freshness, session context cleanup, and regression scenarios.
"""
from __future__ import annotations
import os
import unittest
from unittest.mock import patch
import master_parity_gate
import mcp_namespace_health
import post_restart_reconcile
import session_context_binding as session_ctx
class TestIssue689DeterministicCohortAttachment(unittest.TestCase):
"""Suite covering Issue #689 acceptance criteria."""
def setUp(self) -> None:
session_ctx._reset_session_context_for_testing()
def tearDown(self) -> None:
session_ctx._reset_session_context_for_testing()
def test_ac1_session_context_exposes_cohort_identity(self) -> None:
"""AC1: Session context exposes cohort ID, startup SHA, endpoint, and config fingerprint."""
ctx = session_ctx.bind_session_context(
profile_name="prgs-author",
remote="prgs",
host="gitea.prgs.cc",
identity="jcwalker3",
repository="Gitea-Tools",
org="Scaled-Tech-Consulting",
role_kind="author",
cohort_id="cohort-p1234-abc123456789",
startup_sha="abc123456789def",
endpoint="gitea.prgs.cc",
config_fingerprint="fingerprint12345",
)
self.assertEqual(ctx["cohort_id"], "cohort-p1234-abc123456789")
self.assertEqual(ctx["startup_sha"], "abc123456789def")
self.assertEqual(ctx["endpoint"], "gitea.prgs.cc")
self.assertEqual(ctx["config_fingerprint"], "fingerprint12345")
fetched = session_ctx.get_session_context()
self.assertIsNotNone(fetched)
self.assertEqual(fetched["cohort_id"], "cohort-p1234-abc123456789")
self.assertEqual(fetched["startup_sha"], "abc123456789def")
def test_ac2_stale_cohort_refused_by_probe_classifier(self) -> None:
"""AC2: Probe classifier refuses binding to a stale cohort as stale_cohort_refused."""
probe_res = {
"success": True,
"cohort": {
"cohort_id": "cohort-obsolete-1",
"startup_sha": "22698c1000000000000000000000000000000000",
"endpoint": "gitea.prgs.cc",
"config_fingerprint": "fp-old",
},
}
res = mcp_namespace_health.classify_namespace_probe(
"gitea-author",
probe_result=probe_res,
probe_source="client_namespace",
expected_parity_sha="a4c73766f4b0cc32f7c3808688eceeb6fee74335",
)
self.assertFalse(res["healthy"])
self.assertFalse(res["success"])
self.assertEqual(res["error_type"], "stale_cohort_refused")
self.assertIn("stale cohort refused", " ".join(res["reasons"]))
self.assertEqual(
res["diagnostics"]["startup_sha"],
"22698c1000000000000000000000000000000000",
)
def test_ac3_reconnection_parity_matching_and_fail_closed(self) -> None:
"""AC3: Parity gate fails closed when bound cohort startup SHA mismatches parity."""
startup = {"startup_head": "a4c73766f4b0cc32f7c3808688eceeb6fee74335"}
current = "a4c73766f4b0cc32f7c3808688eceeb6fee74335"
live_remote = "a4c73766f4b0cc32f7c3808688eceeb6fee74335"
# Matching cohort
matching_cohort = {
"cohort_id": "cohort-fresh",
"startup_sha": "a4c73766f4b0cc32f7c3808688eceeb6fee74335",
}
res_matching = master_parity_gate.assess_master_parity(
startup, current, live_remote_head=live_remote, bound_cohort=matching_cohort
)
self.assertTrue(res_matching["cohort_parity_match"])
self.assertFalse(res_matching["cohort_stale"])
self.assertTrue(res_matching["mutation_safe"])
# Mismatched obsolete cohort
obsolete_cohort = {
"cohort_id": "cohort-obsolete-22698c1",
"startup_sha": "22698c1000000000000000000000000000000000",
}
res_stale = master_parity_gate.assess_master_parity(
startup, current, live_remote_head=live_remote, bound_cohort=obsolete_cohort
)
self.assertFalse(res_stale["cohort_parity_match"])
self.assertTrue(res_stale["cohort_stale"])
self.assertTrue(res_stale["restart_required"])
self.assertFalse(res_stale["mutation_safe"])
def test_ac4_reconcile_id_freshness(self) -> None:
"""AC4: Re-attachment distinguishes new reconcile_id from preserved binding."""
inventory = {"inventory_complete": True}
# New attachment generates fresh reconcile_id
proof1 = post_restart_reconcile.reconcile_after_restart(inventory)
self.assertFalse(proof1.binding_unchanged)
self.assertTrue(proof1.reconcile_id.startswith("reconcile-"))
# Preserved binding reports binding_unchanged=True
proof2 = post_restart_reconcile.reconcile_after_restart(
inventory,
reconcile_id=proof1.reconcile_id,
prior_reconcile_id=proof1.reconcile_id,
)
self.assertTrue(proof2.binding_unchanged)
self.assertEqual(proof2.reconcile_id, proof1.reconcile_id)
# Disconnected re-attachment gets new reconcile_id
proof3 = post_restart_reconcile.reconcile_after_restart(
inventory,
prior_reconcile_id=proof1.reconcile_id,
)
self.assertFalse(proof3.binding_unchanged)
self.assertNotEqual(proof3.reconcile_id, proof1.reconcile_id)
def test_ac5_session_disconnect_clears_bindings(self) -> None:
"""AC5: clear_session_context purges session context on disconnect."""
session_ctx.bind_session_context(
profile_name="prgs-author",
remote="prgs",
host="gitea.prgs.cc",
identity="jcwalker3",
cohort_id="cohort-1",
)
self.assertIsNotNone(session_ctx.get_session_context())
session_ctx.clear_session_context()
self.assertIsNone(session_ctx.get_session_context())
def test_ac6_bound_cohort_in_diagnostics(self) -> None:
"""AC6: Bound cohort identity appears in audit diagnostics."""
session_ctx.bind_session_context(
profile_name="prgs-author",
remote="prgs",
host="gitea.prgs.cc",
identity="jcwalker3",
cohort_id="cohort-test-99",
startup_sha="sha99999",
endpoint="gitea.prgs.cc",
config_fingerprint="fp999",
)
audit = session_ctx.mutation_context_audit_fields()
self.assertTrue(audit["session_context_bound"])
self.assertEqual(audit["session_cohort_id"], "cohort-test-99")
self.assertEqual(audit["session_startup_sha"], "sha99999")
self.assertEqual(audit["session_endpoint"], "gitea.prgs.cc")
self.assertEqual(audit["session_config_fingerprint"], "fp999")
def test_ac7_regression_n_reconnects_never_bind_to_obsolete_daemon(self) -> None:
"""AC7: N reconnects against a daemon set containing obsolete daemons never bind obsolete ones."""
live_master = "master-head-latest-12345"
daemons = [
{"id": "d1", "startup_sha": "obsolete-head-11111"},
{"id": "d2", "startup_sha": "obsolete-head-22698c1"},
{"id": "d3", "startup_sha": live_master},
{"id": "d4", "startup_sha": "obsolete-head-33333"},
]
for _ in range(5):
for daemon in daemons:
res = master_parity_gate.assess_master_parity(
{"startup_head": live_master},
live_master,
live_remote_head=live_master,
bound_cohort=daemon,
)
if daemon["startup_sha"] != live_master:
self.assertFalse(res["mutation_safe"])
self.assertTrue(res["cohort_stale"])
else:
self.assertTrue(res["mutation_safe"])
self.assertFalse(res["cohort_stale"])
def test_ac8_regression_incident_shape_reproduction(self) -> None:
"""AC8: Reproduce incident shape — obsolete cohort 22698c1 resident vs newer daemon."""
live_master = "a4c73766f4b0cc32f7c3808688eceeb6fee74335"
obsolete_cohort = {
"cohort_id": "cohort-resident-22698c1",
"startup_sha": "22698c1000000000000000000000000000000000",
}
new_cohort = {
"cohort_id": "cohort-spawned-new",
"startup_sha": live_master,
}
# Obsolete cohort fails parity check
obs_res = mcp_namespace_health.classify_namespace_probe(
"gitea-author",
probe_result={"success": True, "cohort": obsolete_cohort},
probe_source="client_namespace",
expected_parity_sha=live_master,
)
self.assertFalse(obs_res["healthy"])
self.assertEqual(obs_res["error_type"], "stale_cohort_refused")
# Fresh cohort succeeds
new_res = mcp_namespace_health.classify_namespace_probe(
"gitea-author",
probe_result={"success": True, "cohort": new_cohort},
probe_source="client_namespace",
expected_parity_sha=live_master,
)
self.assertTrue(new_res["healthy"])
def test_ac9_regression_bound_cohort_going_stale_detected(self) -> None:
"""AC9: A bound cohort that later goes stale is detected on next attachment check."""
initial_master = "sha-v1-initial"
cohort = {"cohort_id": "c1", "startup_sha": initial_master}
# Initial state: in parity
res1 = master_parity_gate.assess_master_parity(
{"startup_head": initial_master},
initial_master,
live_remote_head=initial_master,
bound_cohort=cohort,
)
self.assertTrue(res1["mutation_safe"])
# Master advances to sha-v2-advanced while cohort remains at sha-v1-initial
advanced_master = "sha-v2-advanced"
res2 = master_parity_gate.assess_master_parity(
{"startup_head": initial_master},
advanced_master,
live_remote_head=advanced_master,
bound_cohort=cohort,
)
self.assertFalse(res2["mutation_safe"])
self.assertTrue(res2["restart_required"])
self.assertTrue(res2["cohort_stale"])
if __name__ == "__main__":
unittest.main()
+190
View File
@@ -0,0 +1,190 @@
"""Tests for Sentry/GlitchTip observability console (#649, Phase 4)."""
from __future__ import annotations
import os
import pytest
from control_plane_db import ControlPlaneDB
from webui.app import create_app
from webui.console_authz import authorize, resolve_principal
from webui.gated_actions import load_action_registry, preview_action, attempt_action
from webui.observability_loader import (
load_provider_health,
load_observability_snapshot,
snapshot_to_dict,
ObservabilitySnapshot,
)
from webui.observability_views import render_observability_page
from tests.webui_testclient import TestClient
@pytest.fixture
def test_db(tmp_path):
db_path = str(tmp_path / "test_control_plane.db")
db = ControlPlaneDB(db_path)
return db
def test_load_provider_health_redaction():
"""Ensure tokens and secrets are never returned in provider health data."""
env = {
"SENTRY_BASE_URL": "https://sentry.prgs.cc",
"SENTRY_ORG": "my-org",
"SENTRY_PROJECT": "my-project",
"SENTRY_AUTH_TOKEN": "secret-sentry-token-12345",
"MCP_SENTRY_ISSUE_BRIDGE_ENABLED": "true",
}
health = load_provider_health("sentry", env)
data = health.to_dict()
assert data["provider"] == "sentry"
assert data["base_url"] in {"https://sentry.prgs.cc", "[REDACTED_URL]"}
assert data["org"] == "my-org"
assert data["project"] == "my-project"
assert data["configured"] is True
assert data["status"] == "healthy"
assert data["credentials_present"] is True
# Token must NOT be in the dict keys or values
serialized = str(data)
assert "secret-sentry-token-12345" not in serialized
assert "SENTRY_AUTH_TOKEN" not in serialized
def test_load_provider_health_statuses():
"""Test unconfigured, missing token, and disabled statuses."""
# Not configured
h1 = load_provider_health("sentry", {})
d1 = h1.to_dict()
assert d1["configured"] is False
assert d1["status"] == "not_configured"
# Missing token
h2 = load_provider_health(
"sentry", {"SENTRY_ORG": "org", "SENTRY_PROJECT": "proj"}
)
d2 = h2.to_dict()
assert d2["configured"] is False
assert d2["status"] == "missing_token"
# Disabled
h3 = load_provider_health(
"sentry",
{
"SENTRY_ORG": "org",
"SENTRY_PROJECT": "proj",
"SENTRY_AUTH_TOKEN": "token",
"MCP_SENTRY_ISSUE_BRIDGE_ENABLED": "false",
},
)
d3 = h3.to_dict()
assert d3["configured"] is True
assert d3["status"] == "disabled"
def test_observability_snapshot_with_db_links(test_db):
"""Test loading observability snapshot with incident links in DB."""
test_db.upsert_incident_link(
provider="sentry",
provider_issue_id="101",
gitea_org="Scaled-Tech-Consulting",
gitea_repo="Gitea-Tools",
gitea_issue_number=649,
provider_base_url="https://sentry.prgs.cc",
provider_org="Scaled-Tech-Consulting",
provider_project="Gitea-Tools",
provider_short_id="ST-101",
provider_permalink="https://sentry.prgs.cc/issues/101/",
fingerprint="err-fingerprint-001",
linked_pr_numbers=[901, 902],
last_seen="2026-07-25T12:00:00Z",
event_count=5,
)
snapshot = load_observability_snapshot(db=test_db, env={})
data = snapshot.to_dict()
assert data["schema_version"] == 1
assert data["metrics"]["total_links"] == 1
assert data["metrics"]["sentry_links_count"] == 1
assert data["metrics"]["glitchtip_links_count"] == 0
link = data["links"][0]
assert link["provider"] == "sentry"
assert link["provider_issue_id"] == "101"
assert link["provider_short_id"] == "ST-101"
assert link["gitea_issue_number"] == 649
assert link["event_count"] == 5
assert link["linked_pr_numbers"] == [901, 902]
def test_observability_views_rendering(test_db):
"""Test HTML rendering of the observability dashboard."""
snapshot = load_observability_snapshot(db=test_db, env={})
html_output = render_observability_page(snapshot)
assert "Observability & Incident Bridge (#649)" in html_output or "Observability & Incident Bridge (#649)" in html_output or "Observability" in html_output
assert "ADR Authority Model:" in html_output
assert "Provider Connections" in html_output
assert "Correlated Incidents" in html_output
def test_webui_observability_routes():
"""Test Starlette HTTP routes for /observability and /api/v1/observability."""
client = TestClient(create_app())
# HTML page route
res_html = client.get("/observability")
assert res_html.status_code == 200
assert "text/html" in res_html.headers["content-type"]
assert "Observability" in res_html.text
# Versioned API route
res_api_v1 = client.get("/api/v1/observability")
assert res_api_v1.status_code == 200
assert "application/json" in res_api_v1.headers["content-type"]
data_v1 = res_api_v1.json()
assert "schema_version" in data_v1
assert "providers" in data_v1
assert "links" in data_v1
assert "metrics" in data_v1
# Compatibility alias route
res_api_alias = client.get("/api/observability")
assert res_api_alias.status_code == 200
assert res_api_alias.json() == data_v1
def test_observability_gated_actions():
"""Ensure observability actions are registered, gated, and fail closed in MVP mode."""
registry = load_action_registry()
action_reconcile = registry.get("observability_reconcile_incident")
assert action_reconcile is not None
assert action_reconcile.task_key == "observability_reconcile_incident"
assert action_reconcile.mcp_tool == "gitea_observability_reconcile_incident"
action_link = registry.get("observability_link_issue")
assert action_link is not None
assert action_link.task_key == "observability_link_issue"
# Preview returns mutation ledger
prev = preview_action("observability_reconcile_incident", provider="sentry", issue_id="101")
assert prev["action_id"] == "observability_reconcile_incident"
assert prev["enabled"] is False
# Execution fails closed in MVP mode
att = attempt_action("observability_reconcile_incident", provider="sentry", issue_id="101")
assert att["success"] is False
assert att["error"] == "action_disabled"
def test_observability_authz_rbac():
"""Test RBAC authorization for observability actions."""
principal = resolve_principal({})
# Check authorize decision
decision = authorize("observability_reconcile_incident", principal)
assert decision.action_id == "observability_reconcile_incident"
# Phase 4 action denies in Phase 1 runtime by default
assert decision.allowed is False
+21
View File
@@ -87,6 +87,11 @@ from webui.notifications import (
from webui.notification_views import render_notifications_page from webui.notification_views import render_notifications_page
from webui import request_service from webui import request_service
from webui.request_views import render_requests_page from webui.request_views import render_requests_page
from webui.observability_loader import (
load_observability_snapshot,
snapshot_to_dict as observability_snapshot_to_dict,
)
from webui.observability_views import render_observability_page
_READ_ONLY_METHODS = frozenset({"GET", "HEAD", "OPTIONS"}) _READ_ONLY_METHODS = frozenset({"GET", "HEAD", "OPTIONS"})
_AUDIT_MUTATION_PATHS = frozenset({"/audit", "/api/audit"}) _AUDIT_MUTATION_PATHS = frozenset({"/audit", "/api/audit"})
@@ -910,6 +915,19 @@ async def api_notifications(request: Request) -> JSONResponse:
data = notifications_snapshot_to_dict(snap) data = notifications_snapshot_to_dict(snap)
return JSONResponse(data) return JSONResponse(data)
async def observability_route(request: Request) -> HTMLResponse:
snap = load_observability_snapshot()
html_content = render_observability_page(snap)
return HTMLResponse(html_content)
async def api_observability(request: Request) -> JSONResponse:
snap = load_observability_snapshot()
data = observability_snapshot_to_dict(snap)
return JSONResponse(data)
def _default_request_scope() -> dict[str, str]: def _default_request_scope() -> dict[str, str]:
"""Resolve remote/org/repo from the project registry for request forms. """Resolve remote/org/repo from the project registry for request forms.
@@ -1075,6 +1093,9 @@ def create_app(*, bind_host: str | None = None) -> Starlette:
Route("/api/analytics", api_v1_analytics, methods=["GET"]), Route("/api/analytics", api_v1_analytics, methods=["GET"]),
Route("/api/v1/analytics", api_v1_analytics, methods=["GET"]), Route("/api/v1/analytics", api_v1_analytics, methods=["GET"]),
Route("/api/v1/analytics/usage", api_v1_analytics_ingest, methods=["POST"]), Route("/api/v1/analytics/usage", api_v1_analytics_ingest, methods=["POST"]),
Route("/observability", observability_route, methods=["GET"]),
Route("/api/observability", api_observability, methods=["GET"]),
Route("/api/v1/observability", api_observability, methods=["GET"]),
Route("/audit", audit, methods=["GET", "POST"]), Route("/audit", audit, methods=["GET", "POST"]),
Route("/api/audit", api_audit, methods=["GET", "POST"]), Route("/api/audit", api_audit, methods=["GET", "POST"]),
Route("/worktrees", worktrees, methods=["GET"]), Route("/worktrees", worktrees, methods=["GET"]),
+23
View File
@@ -317,6 +317,29 @@ _ACTION_SPECS: tuple[ConsoleAction, ...] = (
phase=2, phase=2,
summary="Run reconciler cleanup for merged or superseded PR branches.", summary="Run reconciler cleanup for merged or superseded PR branches.",
), ),
# #649: Phase 4 observability & incident bridge actions.
ConsoleAction(
action_id="observability_reconcile_incident",
task_key="observability_reconcile_incident",
action_class=CLASS_WRITE,
minimum_role=OPERATOR,
requires_confirmation=True,
dual_control=False,
break_glass=False,
phase=4,
summary="Trigger/reconcile durable Gitea issue creation from a provider incident.",
),
ConsoleAction(
action_id="observability_link_issue",
task_key="observability_link_issue",
action_class=CLASS_WRITE,
minimum_role=OPERATOR,
requires_confirmation=True,
dual_control=False,
break_glass=False,
phase=4,
summary="Link a provider incident to an existing Gitea issue.",
),
# #643: submit a work request — desired role, issue/PR, intent — and let # #643: submit a work request — desired role, issue/PR, intent — and let
# the allocator reserve it. This is the one Phase 2 action whose execution # the allocator reserve it. This is the one Phase 2 action whose execution
# path is actually implemented (``webui.request_service``), so it carries # path is actually implemented (``webui.request_service``), so it carries
+5
View File
@@ -185,6 +185,11 @@ def build_action_registry() -> ActionRegistry:
"console.rebind_session_worktree", "Rebind session worktree to verified lease."), "console.rebind_session_worktree", "Rebind session worktree to verified lease."),
("system.reconcile_cleanups", "Reconcile cleanups", "reconcile_cleanups", ("system.reconcile_cleanups", "Reconcile cleanups", "reconcile_cleanups",
"console.reconcile_cleanups", "Run reconciler cleanup for merged or superseded PRs."), "console.reconcile_cleanups", "Run reconciler cleanup for merged or superseded PRs."),
# #649: Phase 4 observability & incident bridge actions.
("observability_reconcile_incident", "Reconcile incident", "observability_reconcile_incident",
"gitea_observability_reconcile_incident", "Trigger or dry-run durable issue reconciliation for a provider incident."),
("observability_link_issue", "Link incident issue", "observability_link_issue",
"gitea_observability_link_issue", "Link a provider incident to a Gitea tracking issue."),
) )
actions = tuple( actions = tuple(
GatedAction( GatedAction(
+1
View File
@@ -73,6 +73,7 @@ NAV_GROUPS: tuple[NavGroup, ...] = (
)), )),
NavGroup("Insights", ( NavGroup("Insights", (
NavItem("/insights", "Insights", "stub"), NavItem("/insights", "Insights", "stub"),
NavItem("/observability", "Observability"),
NavItem("/analytics", "Analytics"), NavItem("/analytics", "Analytics"),
NavItem("/audit", "Audit"), NavItem("/audit", "Audit"),
)), )),
+275
View File
@@ -0,0 +1,275 @@
"""Sentry/GlitchTip observability and incident correlation loader for the console (#649, Phase 4).
Operators need to inspect provider connection status (Sentry/GlitchTip), error
correlations, and durable Gitea issue linkage — without treating raw incidents
as allocator work.
ADR authority model:
* Gitea owns work.
* Providers (Sentry/GlitchTip) observe incidents.
* Control-plane DB coordinates incident links.
* The #612 bridge reconciles observations into durable Gitea issues.
* The web console projects read-only state and gates mutations.
Redaction boundary:
* Provider auth tokens, DSNs, Authorization headers, and sensitive local file
paths are ALWAYS redacted before leaving this module.
"""
from __future__ import annotations
import os
from dataclasses import dataclass
from typing import Any
from control_plane_db import ControlPlaneDB
import sentry_incident_bridge
from webui import console_redaction
OBSERVABILITY_SCHEMA_VERSION = 1
@dataclass(frozen=True)
class ProviderHealth:
"""Connection and health status of an observability provider."""
provider: str
base_url: str
org: str
project: str
configured: bool
status: str
bridge_enabled: bool
lookback: str
min_events_for_issue: int
self_hosted: bool
environment: str | None = None
credentials_present: bool = False
def to_dict(self) -> dict[str, Any]:
data = {
"provider": self.provider,
"base_url": self.base_url,
"org": self.org,
"project": self.project,
"configured": self.configured,
"status": self.status,
"bridge_enabled": self.bridge_enabled,
"lookback": self.lookback,
"min_events_for_issue": self.min_events_for_issue,
"self_hosted": self.self_hosted,
"environment": self.environment,
"credentials_present": self.credentials_present,
}
return console_redaction.redact_payload(data)
@dataclass(frozen=True)
class CorrelatedIncidentLink:
"""One linked provider incident ↔ Gitea issue correlation record."""
link_id: int
provider: str
provider_base_url: str
provider_org: str
provider_project: str
provider_issue_id: str
provider_short_id: str | None
provider_permalink: str | None
fingerprint: str | None
gitea_org: str
gitea_repo: str
gitea_issue_number: int
linked_pr_numbers: list[int]
last_seen: str | None
event_count: int
created_at: str | None
updated_at: str | None
def to_dict(self) -> dict[str, Any]:
data = {
"link_id": self.link_id,
"provider": self.provider,
"provider_base_url": self.provider_base_url,
"provider_org": self.provider_org,
"provider_project": self.provider_project,
"provider_issue_id": self.provider_issue_id,
"provider_short_id": self.provider_short_id,
"provider_permalink": self.provider_permalink,
"fingerprint": self.fingerprint,
"gitea_org": self.gitea_org,
"gitea_repo": self.gitea_repo,
"gitea_issue_number": self.gitea_issue_number,
"linked_pr_numbers": self.linked_pr_numbers,
"last_seen": self.last_seen,
"event_count": self.event_count,
"created_at": self.created_at,
"updated_at": self.updated_at,
}
return console_redaction.redact_payload(data)
@dataclass(frozen=True)
class ObservabilitySnapshot:
"""Read-only snapshot of observability provider status and incident correlations."""
schema_version: int
providers: list[ProviderHealth]
links: list[CorrelatedIncidentLink]
total_links: int
sentry_links_count: int
glitchtip_links_count: int
bridge_active: bool
def to_dict(self) -> dict[str, Any]:
return {
"schema_version": self.schema_version,
"providers": [p.to_dict() for p in self.providers],
"links": [link.to_dict() for link in self.links],
"metrics": {
"total_links": self.total_links,
"sentry_links_count": self.sentry_links_count,
"glitchtip_links_count": self.glitchtip_links_count,
"bridge_active": self.bridge_active,
},
}
def load_provider_health(
provider_name: str = "sentry",
env: dict[str, str] | None = None,
) -> ProviderHealth:
"""Inspect configuration and connection health for an observability provider."""
source_env = dict(env if env is not None else os.environ)
if provider_name.lower() == "sentry":
config = sentry_incident_bridge.load_bridge_config(source_env)
token = sentry_incident_bridge.resolve_token(source_env)
has_token = bool(token)
configured = bool(config.org and config.project and has_token)
if not config.org or not config.project:
status = "not_configured"
elif not has_token:
status = "missing_token"
elif not config.bridge_enabled:
status = "disabled"
else:
status = "healthy"
return ProviderHealth(
provider="sentry",
base_url=config.base_url,
org=config.org or "unconfigured",
project=config.project or "unconfigured",
configured=configured,
status=status,
bridge_enabled=config.bridge_enabled,
lookback=config.lookback,
min_events_for_issue=config.min_events_for_issue,
self_hosted=not config.base_url.rstrip("/").endswith("sentry.io"),
environment=config.environment,
credentials_present=has_token,
)
# GlitchTip or fallback provider configuration
glitchtip_url = (source_env.get("GLITCHTIP_BASE_URL") or "https://glitchtip.prgs.cc").strip()
glitchtip_org = (source_env.get("GLITCHTIP_ORG") or "").strip()
glitchtip_proj = (source_env.get("GLITCHTIP_PROJECT") or "").strip()
glitchtip_token = (source_env.get("GLITCHTIP_AUTH_TOKEN") or "").strip()
has_token = bool(glitchtip_token)
configured = bool(glitchtip_org and glitchtip_proj and has_token)
status = "healthy" if configured else ("missing_token" if glitchtip_org and glitchtip_proj else "not_configured")
return ProviderHealth(
provider="glitchtip",
base_url=glitchtip_url,
org=glitchtip_org or "unconfigured",
project=glitchtip_proj or "unconfigured",
configured=configured,
status=status,
bridge_enabled=configured,
lookback="24h",
min_events_for_issue=2,
self_hosted=True,
environment=source_env.get("GLITCHTIP_ENVIRONMENT"),
credentials_present=has_token,
)
def _parse_pr_numbers(raw: Any) -> list[int]:
if isinstance(raw, list):
return [int(x) for x in raw if str(x).isdigit()]
if isinstance(raw, str) and raw.strip():
import json
try:
parsed = json.loads(raw)
if isinstance(parsed, list):
return [int(x) for x in parsed if str(x).isdigit()]
except Exception:
pass
return []
def load_observability_snapshot(
db: ControlPlaneDB | None = None,
env: dict[str, str] | None = None,
) -> ObservabilitySnapshot:
"""Build a read-only snapshot of observability connection health and incident links."""
sentry_health = load_provider_health("sentry", env)
glitchtip_health = load_provider_health("glitchtip", env)
providers = [sentry_health, glitchtip_health]
target_db = db or ControlPlaneDB()
raw_links = target_db.list_incident_links(limit=100)
links: list[CorrelatedIncidentLink] = []
sentry_cnt = 0
glitchtip_cnt = 0
for r in raw_links:
prov = (r.get("provider") or "sentry").lower()
if prov == "sentry":
sentry_cnt += 1
elif prov == "glitchtip":
glitchtip_cnt += 1
pr_nums = _parse_pr_numbers(r.get("linked_pr_numbers"))
links.append(
CorrelatedIncidentLink(
link_id=int(r.get("link_id", 0)),
provider=prov,
provider_base_url=r.get("provider_base_url") or "",
provider_org=r.get("provider_org") or "",
provider_project=r.get("provider_project") or "",
provider_issue_id=str(r.get("provider_issue_id") or ""),
provider_short_id=r.get("provider_short_id"),
provider_permalink=r.get("provider_permalink"),
fingerprint=r.get("fingerprint"),
gitea_org=r.get("gitea_org") or "Scaled-Tech-Consulting",
gitea_repo=r.get("gitea_repo") or "Gitea-Tools",
gitea_issue_number=int(r.get("gitea_issue_number", 0)),
linked_pr_numbers=pr_nums,
last_seen=r.get("last_seen"),
event_count=int(r.get("event_count", 1)),
created_at=r.get("created_at"),
updated_at=r.get("updated_at"),
)
)
bridge_active = any(p.bridge_enabled for p in providers)
return ObservabilitySnapshot(
schema_version=OBSERVABILITY_SCHEMA_VERSION,
providers=providers,
links=links,
total_links=len(links),
sentry_links_count=sentry_cnt,
glitchtip_links_count=glitchtip_cnt,
bridge_active=bridge_active,
)
def snapshot_to_dict(snapshot: ObservabilitySnapshot) -> dict[str, Any]:
return snapshot.to_dict()
+143
View File
@@ -0,0 +1,143 @@
"""HTML view renderer for the Sentry/GlitchTip observability console (#649, Phase 4).
Renders connection status widgets, error correlation links, and gated issue creation
affordances over the read-only observability snapshot.
"""
from __future__ import annotations
import html
from typing import Any
from webui.layout import render_page
from webui.observability_loader import ObservabilitySnapshot, snapshot_to_dict
def _badge(status: str) -> str:
st = (status or "").lower()
if st == "healthy":
return '<span class="badge badge-success">healthy</span>'
if st == "disabled":
return '<span class="badge badge-warning">disabled (dry-run)</span>'
if st in {"missing_token", "not_configured"}:
return f'<span class="badge badge-muted">{html.escape(st)}</span>'
return f'<span class="badge">{html.escape(st)}</span>'
def _provider_card(p: dict[str, Any]) -> str:
name = html.escape(str(p.get("provider", "provider")).upper())
base_url = html.escape(str(p.get("base_url", "")))
org = html.escape(str(p.get("org", "")))
proj = html.escape(str(p.get("project", "")))
status_badge = _badge(str(p.get("status", "")))
min_events = p.get("min_events_for_issue", 2)
lookback = html.escape(str(p.get("lookback", "24h")))
bridge_enabled = "yes" if p.get("bridge_enabled") else "no"
return f"""
<div class="card" style="margin-bottom: 1rem; padding: 1rem; border: 1px solid #ccc; border-radius: 6px;">
<div style="display: flex; justify-content: space-between; align-items: center;">
<h3 style="margin: 0;">{name} Connection</h3>
<div>{status_badge}</div>
</div>
<table style="width: 100%; margin-top: 0.5rem; border-collapse: collapse;">
<tr><td><strong>Base URL:</strong></td><td><code>{base_url}</code></td></tr>
<tr><td><strong>Scope:</strong></td><td><code>{org} / {proj}</code></td></tr>
<tr><td><strong>Bridge Enabled:</strong></td><td><code>{bridge_enabled}</code></td></tr>
<tr><td><strong>Min Events for Issue:</strong></td><td><code>{min_events}</code></td></tr>
<tr><td><strong>Lookback Window:</strong></td><td><code>{lookback}</code></td></tr>
</table>
</div>
"""
def render_observability_page(snapshot: ObservabilitySnapshot | dict[str, Any]) -> str:
"""Render the observability dashboard HTML page."""
data = snapshot.to_dict() if isinstance(snapshot, ObservabilitySnapshot) else dict(snapshot)
providers_raw = data.get("providers", [])
provider_cards = "".join(_provider_card(p) for p in providers_raw) if providers_raw else "<p>No providers configured.</p>"
links = data.get("links", [])
link_rows = []
for l in links:
prov = html.escape(str(l.get("provider", "")))
p_issue_id = html.escape(str(l.get("provider_issue_id", "")))
fingerprint = html.escape(str(l.get("fingerprint") or ""))
g_issue_num = int(l.get("gitea_issue_number", 0))
g_org = html.escape(str(l.get("gitea_org", "")))
g_repo = html.escape(str(l.get("gitea_repo", "")))
g_issue_link = f'<strong>#{g_issue_num}</strong> ({g_org}/{g_repo})'
event_cnt = int(l.get("event_count", 1))
last_seen = html.escape(str(l.get("last_seen") or ""))
short_id = html.escape(str(l.get("provider_short_id") or p_issue_id))
link_rows.append(f"""
<tr>
<td><code>{prov}</code></td>
<td><strong>{short_id}</strong><br><small style="color: #666;">id: {p_issue_id}</small></td>
<td><code>{fingerprint}</code></td>
<td>{g_issue_link}</td>
<td>{event_cnt}</td>
<td><small>{last_seen}</small></td>
</tr>
""")
table_body = "".join(link_rows) if link_rows else '<tr><td colspan="6" style="text-align: center; padding: 1.5rem; color: #666;">No correlated incident links stored. Bridge operates under dry-run default.</td></tr>'
metrics = data.get("metrics", {})
total_links = metrics.get("total_links", 0)
sentry_cnt = metrics.get("sentry_links_count", 0)
glitchtip_cnt = metrics.get("glitchtip_links_count", 0)
body_html = f"""
<h2>Observability & Incident Bridge (#649)</h2>
<p>Read-only console surface for Sentry/GlitchTip provider connections, error correlation,
and durable Gitea issue linkage.</p>
<div class="alert alert-info" style="background: #f0f4f8; padding: 1rem; border-left: 4px solid #0052cc; margin-bottom: 1.5rem;">
<strong>ADR Authority Model:</strong> Gitea records durable issue history. Control-plane DB coordinates incident links.
Sentry/GlitchTip observe errors. Raw monitoring incidents are <em>never</em> assignable control-plane work items.
Durable issue creation is gated and dry-runable via the <code>#612</code> bridge APIs.
</div>
<h3>Provider Connections</h3>
<div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(300px, 1fr)); gap: 1rem; margin-bottom: 2rem;">
{provider_cards}
</div>
<div style="display: flex; justify-content: space-between; align-items: center; margin-bottom: 1rem;">
<h3 style="margin: 0;">Correlated Incidents ({total_links})</h3>
<div>
<span class="badge" style="margin-right: 0.5rem;">Sentry: {sentry_cnt}</span>
<span class="badge">GlitchTip: {glitchtip_cnt}</span>
</div>
</div>
<table class="table" style="width: 100%; border-collapse: collapse; border: 1px solid #ddd;">
<thead>
<tr style="background: #f9f9f9; text-align: left;">
<th style="padding: 0.5rem; border-bottom: 2px solid #ddd;">Provider</th>
<th style="padding: 0.5rem; border-bottom: 2px solid #ddd;">Incident ID</th>
<th style="padding: 0.5rem; border-bottom: 2px solid #ddd;">Fingerprint</th>
<th style="padding: 0.5rem; border-bottom: 2px solid #ddd;">Gitea Issue Link</th>
<th style="padding: 0.5rem; border-bottom: 2px solid #ddd;">Events</th>
<th style="padding: 0.5rem; border-bottom: 2px solid #ddd;">Last Seen</th>
</tr>
</thead>
<tbody>
{table_body}
</tbody>
</table>
<div style="margin-top: 2rem; padding: 1rem; background: #fafafa; border: 1px solid #eee; border-radius: 4px;">
<h4 style="margin-top: 0;">Reconcile & Link Controls (Gated)</h4>
<p style="margin-bottom: 0.5rem; color: #555;">
Create or reconcile durable Gitea issues from provider observations using the <code>#612</code> incident bridge:
</p>
<code>mcp call gitea_observability_reconcile_incident --provider sentry --apply false</code>
</div>
"""
return render_page(title="Observability", body_html=body_html)