feat(dashboard): add Debug Share to the System page (#38600)
* Port from google-gemini/gemini-cli#21541: back up corrupted config.yaml When config.yaml fails to parse, load_config() silently falls back to DEFAULT_CONFIG and leaves the broken file on disk. If the user then re-runs the setup wizard or hermes config set (both rewrite config.yaml), their broken-but-recoverable overrides are lost for good. Adapts the policy-file recovery from gemini-cli#21541: on the first parse warning for a given broken file, snapshot it to config.yaml.corrupt.<ts>.bak (best-effort, symlink-guarded, size-deduped) and tell the user where it landed. Unlike Gemini's version we deliberately do NOT reset config.yaml to a clean state — hermes never silently mutates user config, and leaving it means a hand-fixed file is re-read on the next load. Tests: 3 new cases (backup created + content preserved + original untouched; same-size backup dedup; symlink not copied). E2E verified with isolated HERMES_HOME and a real tab-indented broken config. * feat(dashboard): add Debug Share to the System page Surface `hermes debug share` in the dashboard. The System > Operations section gets a dedicated card that uploads a redacted report + full logs and returns the paste URLs as real, copyable links instead of a log tail. - debug.py: factor a pure build_debug_share() returning structured {urls, failures, redacted, auto_delete_seconds}; run_debug_share now calls it (CLI output unchanged). - web_server.py: POST /api/ops/debug-share runs the share core in a worker thread and returns the structured payload synchronously (the URLs are the whole point — not a backgrounded action). - api.ts: runDebugShare() + DebugShareResponse. - SystemPage.tsx: share card with a redaction toggle (on by default), per-link + copy-all buttons, and the 6h auto-delete countdown. - tests: build_debug_share core + endpoint (redact toggle, failure 502, token gate).
This commit is contained in:
Teknium
+126
-64
@@ -585,20 +585,41 @@ def collect_debug_report(
|
||||
# CLI entry points
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def run_debug_share(args):
|
||||
"""Collect debug report + full logs, upload each, print URLs."""
|
||||
@dataclass
|
||||
class DebugShareResult:
|
||||
"""Structured outcome of a ``debug share`` upload.
|
||||
|
||||
Returned by :func:`build_debug_share` so non-CLI callers (the dashboard
|
||||
web server, gateway) can render the uploaded paste URLs as real links
|
||||
instead of scraping printed text.
|
||||
"""
|
||||
|
||||
urls: dict # label -> paste URL (e.g. {"Report": "...", "agent.log": "..."})
|
||||
failures: list # human-readable "label: error" strings for optional uploads
|
||||
redacted: bool # whether force-mode redaction was applied before upload
|
||||
auto_delete_seconds: int # how long until the pastes auto-delete
|
||||
report: str = "" # the summary report text (kept for local fallback)
|
||||
|
||||
|
||||
def build_debug_share(
|
||||
*,
|
||||
log_lines: int = 200,
|
||||
expiry: int = 7,
|
||||
redact: bool = True,
|
||||
) -> DebugShareResult:
|
||||
"""Collect the debug report + full logs, upload each, return the URLs.
|
||||
|
||||
This is the shared core behind ``hermes debug share`` (CLI) and the
|
||||
dashboard ``POST /api/ops/debug-share`` endpoint. It performs blocking
|
||||
network I/O (paste uploads) — callers inside an event loop must run it in
|
||||
a worker thread.
|
||||
|
||||
The summary report upload is required: on failure this raises
|
||||
``RuntimeError``. Full-log uploads are best-effort; their errors are
|
||||
collected into ``failures`` rather than raised.
|
||||
"""
|
||||
_best_effort_sweep_expired_pastes()
|
||||
|
||||
log_lines = getattr(args, "lines", 200)
|
||||
expiry = getattr(args, "expire", 7)
|
||||
local_only = getattr(args, "local", False)
|
||||
redact = not getattr(args, "no_redact", False)
|
||||
|
||||
if not local_only:
|
||||
print(_PRIVACY_NOTICE)
|
||||
|
||||
print("Collecting debug report...")
|
||||
|
||||
# Capture dump once — prepended to every paste for context.
|
||||
# The dump is already redacted at extract time via dump.py:_redact;
|
||||
# log_snapshots are redacted by _capture_default_log_snapshots when
|
||||
@@ -639,71 +660,112 @@ def run_debug_share(args):
|
||||
if desktop_log:
|
||||
desktop_log = _REDACTION_BANNER + desktop_log
|
||||
|
||||
if local_only:
|
||||
print(report)
|
||||
if agent_log:
|
||||
print(f"\n\n{'=' * 60}")
|
||||
print("FULL agent.log")
|
||||
print(f"{'=' * 60}\n")
|
||||
print(agent_log)
|
||||
if gateway_log:
|
||||
print(f"\n\n{'=' * 60}")
|
||||
print("FULL gateway.log")
|
||||
print(f"{'=' * 60}\n")
|
||||
print(gateway_log)
|
||||
if desktop_log:
|
||||
print(f"\n\n{'=' * 60}")
|
||||
print("FULL desktop.log")
|
||||
print(f"{'=' * 60}\n")
|
||||
print(desktop_log)
|
||||
return
|
||||
|
||||
print("Uploading...")
|
||||
urls: dict[str, str] = {}
|
||||
failures: list[str] = []
|
||||
|
||||
# 1. Summary report (required)
|
||||
# 1. Summary report (required — raises on failure so callers can fall back)
|
||||
urls["Report"] = upload_to_pastebin(report, expiry_days=expiry)
|
||||
|
||||
# 2-4. Full logs (optional — failures are collected, not raised)
|
||||
for label, content in (
|
||||
("agent.log", agent_log),
|
||||
("gateway.log", gateway_log),
|
||||
("desktop.log", desktop_log),
|
||||
):
|
||||
if not content:
|
||||
continue
|
||||
try:
|
||||
urls[label] = upload_to_pastebin(content, expiry_days=expiry)
|
||||
except Exception as exc:
|
||||
failures.append(f"{label}: {exc}")
|
||||
|
||||
# Schedule auto-deletion after 6 hours.
|
||||
_schedule_auto_delete(list(urls.values()))
|
||||
|
||||
return DebugShareResult(
|
||||
urls=urls,
|
||||
failures=failures,
|
||||
redacted=redact,
|
||||
auto_delete_seconds=_AUTO_DELETE_SECONDS,
|
||||
report=report,
|
||||
)
|
||||
|
||||
|
||||
def run_debug_share(args):
|
||||
"""Collect debug report + full logs, upload each, print URLs."""
|
||||
log_lines = getattr(args, "lines", 200)
|
||||
expiry = getattr(args, "expire", 7)
|
||||
local_only = getattr(args, "local", False)
|
||||
redact = not getattr(args, "no_redact", False)
|
||||
|
||||
if local_only:
|
||||
# Local-only path never uploads — render the report to stdout and bail
|
||||
# before any network I/O. Mirrors the upload path's collection logic.
|
||||
_best_effort_sweep_expired_pastes()
|
||||
print("Collecting debug report...")
|
||||
dump_text = _capture_dump()
|
||||
log_snapshots = _capture_default_log_snapshots(log_lines, redact=redact)
|
||||
report = collect_debug_report(
|
||||
log_lines=log_lines,
|
||||
dump_text=dump_text,
|
||||
log_snapshots=log_snapshots,
|
||||
)
|
||||
agent_log = log_snapshots["agent"].full_text
|
||||
gateway_log = log_snapshots["gateway"].full_text
|
||||
desktop_log = log_snapshots["desktop"].full_text
|
||||
if agent_log:
|
||||
agent_log = dump_text + "\n\n--- full agent.log ---\n" + agent_log
|
||||
if gateway_log:
|
||||
gateway_log = dump_text + "\n\n--- full gateway.log ---\n" + gateway_log
|
||||
if desktop_log:
|
||||
desktop_log = dump_text + "\n\n--- full desktop.log ---\n" + desktop_log
|
||||
if redact:
|
||||
report = _REDACTION_BANNER + report
|
||||
if agent_log:
|
||||
agent_log = _REDACTION_BANNER + agent_log
|
||||
if gateway_log:
|
||||
gateway_log = _REDACTION_BANNER + gateway_log
|
||||
if desktop_log:
|
||||
desktop_log = _REDACTION_BANNER + desktop_log
|
||||
print(report)
|
||||
for title, body in (
|
||||
("FULL agent.log", agent_log),
|
||||
("FULL gateway.log", gateway_log),
|
||||
("FULL desktop.log", desktop_log),
|
||||
):
|
||||
if body:
|
||||
print(f"\n\n{'=' * 60}")
|
||||
print(title)
|
||||
print(f"{'=' * 60}\n")
|
||||
print(body)
|
||||
return
|
||||
|
||||
print(_PRIVACY_NOTICE)
|
||||
print("Collecting debug report...")
|
||||
print("Uploading...")
|
||||
|
||||
try:
|
||||
urls["Report"] = upload_to_pastebin(report, expiry_days=expiry)
|
||||
result = build_debug_share(
|
||||
log_lines=log_lines,
|
||||
expiry=expiry,
|
||||
redact=redact,
|
||||
)
|
||||
except RuntimeError as exc:
|
||||
print(f"\nUpload failed: {exc}", file=sys.stderr)
|
||||
print("\nFull report printed below — copy-paste it manually:\n")
|
||||
print(report)
|
||||
print("\nRun `hermes debug share --local` to print the report instead.\n")
|
||||
sys.exit(1)
|
||||
|
||||
# 2. Full agent.log (optional)
|
||||
if agent_log:
|
||||
try:
|
||||
urls["agent.log"] = upload_to_pastebin(agent_log, expiry_days=expiry)
|
||||
except Exception as exc:
|
||||
failures.append(f"agent.log: {exc}")
|
||||
|
||||
# 3. Full gateway.log (optional)
|
||||
if gateway_log:
|
||||
try:
|
||||
urls["gateway.log"] = upload_to_pastebin(gateway_log, expiry_days=expiry)
|
||||
except Exception as exc:
|
||||
failures.append(f"gateway.log: {exc}")
|
||||
|
||||
# 4. Full desktop.log (optional — Electron app boot + backend output)
|
||||
if desktop_log:
|
||||
try:
|
||||
urls["desktop.log"] = upload_to_pastebin(desktop_log, expiry_days=expiry)
|
||||
except Exception as exc:
|
||||
failures.append(f"desktop.log: {exc}")
|
||||
|
||||
# Print results
|
||||
label_width = max(len(k) for k in urls)
|
||||
label_width = max(len(k) for k in result.urls)
|
||||
print(f"\nDebug report uploaded:")
|
||||
for label, url in urls.items():
|
||||
for label, url in result.urls.items():
|
||||
print(f" {label:<{label_width}} {url}")
|
||||
|
||||
if failures:
|
||||
print(f"\n (failed to upload: {', '.join(failures)})")
|
||||
if result.failures:
|
||||
print(f"\n (failed to upload: {', '.join(result.failures)})")
|
||||
|
||||
# Schedule auto-deletion after 6 hours
|
||||
_schedule_auto_delete(list(urls.values()))
|
||||
print(f"\n⏱ Pastes will auto-delete in 6 hours.")
|
||||
hours = result.auto_delete_seconds // 3600
|
||||
print(f"\n⏱ Pastes will auto-delete in {hours} hours.")
|
||||
|
||||
# Manual delete fallback
|
||||
print(f"To delete now: hermes debug delete <url>")
|
||||
|
||||
Reference in New Issue
Block a user