mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-09 08:21:50 +00:00
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
GitHub
parent
f66a929a6b
commit
e3313c50a7
8 changed files with 696 additions and 65 deletions
|
|
@ -17,11 +17,13 @@ import logging
|
|||
import os
|
||||
import platform
|
||||
import re
|
||||
import shutil
|
||||
import stat
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import threading
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Dict, Any, Optional, List, Tuple
|
||||
|
|
@ -36,6 +38,60 @@ logger = logging.getLogger(__name__)
|
|||
_CONFIG_PARSE_WARNED: set = set()
|
||||
|
||||
|
||||
def _backup_corrupt_config(config_path: Path) -> Optional[Path]:
|
||||
"""Preserve a corrupted ``config.yaml`` by copying it to a timestamped ``.bak``.
|
||||
|
||||
When the YAML can't be parsed, ``load_config()`` silently falls back to
|
||||
``DEFAULT_CONFIG`` and the user's broken file stays on disk untouched.
|
||||
That file is still the user's only copy of their intended overrides — if
|
||||
they re-run the setup wizard or ``hermes config set`` (which rewrites
|
||||
``config.yaml``), the broken-but-recoverable content is gone for good.
|
||||
|
||||
This snapshots the corrupted file to ``config.yaml.corrupt.<ts>.bak`` so
|
||||
the user can diff/repair it. Unlike Gemini CLI's policy-file recovery
|
||||
(which resets the live file to a clean state), we deliberately leave
|
||||
``config.yaml`` in place: hermes never silently mutates the user's config,
|
||||
and leaving it means a hand-fixed file is re-read on the next load. The
|
||||
backup is best-effort — any failure (permissions, symlink, disk full) is
|
||||
swallowed so config loading is never blocked by backup problems.
|
||||
|
||||
Returns the backup path on success, else ``None``. Symlinks are not
|
||||
followed/copied (mirrors the Gemini #21541 lstat guard) to avoid
|
||||
clobbering whatever a malicious/misconfigured symlink points at.
|
||||
"""
|
||||
try:
|
||||
if config_path.is_symlink():
|
||||
return None
|
||||
st = config_path.stat()
|
||||
if st.st_size == 0:
|
||||
# Empty file isn't worth preserving and yaml.safe_load returns {}
|
||||
# for it anyway (so it wouldn't reach here), but guard regardless.
|
||||
return None
|
||||
ts = time.strftime("%Y%m%d-%H%M%S")
|
||||
backup_path = config_path.with_name(f"{config_path.name}.corrupt.{ts}.bak")
|
||||
# Don't clobber an existing backup from the same second; if there's
|
||||
# already a corrupt backup for this exact mtime, assume we've snapshotted
|
||||
# this corruption already and skip (the dedup cache normally prevents a
|
||||
# second call, but a process restart can clear it).
|
||||
sibling_baks = list(
|
||||
config_path.parent.glob(f"{config_path.name}.corrupt.*.bak")
|
||||
)
|
||||
for existing in sibling_baks:
|
||||
try:
|
||||
if existing.stat().st_size == st.st_size:
|
||||
# Same size as the current broken file — likely the same
|
||||
# corruption already preserved. Avoid backup churn.
|
||||
return None
|
||||
except OSError:
|
||||
continue
|
||||
if backup_path.exists():
|
||||
return None
|
||||
shutil.copy2(config_path, backup_path)
|
||||
return backup_path
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def _warn_config_parse_failure(config_path: Path, exc: Exception) -> None:
|
||||
"""Surface a config.yaml parse failure to user, log, and stderr.
|
||||
|
||||
|
|
@ -48,7 +104,11 @@ def _warn_config_parse_failure(config_path: Path, exc: Exception) -> None:
|
|||
Now: warn once per (path, mtime_ns, size) on stderr **and** in
|
||||
``agent.log`` / ``errors.log`` at WARNING level so ``hermes logs``
|
||||
surfaces it. Re-warns automatically if the file changes (different
|
||||
mtime/size), so users editing the config see the next failure.
|
||||
mtime/size), so users editing the config see the next failure. On the
|
||||
first warning for a given broken file we also snapshot it to a
|
||||
timestamped ``.bak`` (best-effort) so the user's recoverable content
|
||||
survives any later rewrite of ``config.yaml`` by the setup wizard or
|
||||
``hermes config set``.
|
||||
"""
|
||||
try:
|
||||
st = config_path.stat()
|
||||
|
|
@ -59,12 +119,16 @@ def _warn_config_parse_failure(config_path: Path, exc: Exception) -> None:
|
|||
return
|
||||
_CONFIG_PARSE_WARNED.add(key)
|
||||
|
||||
backup_path = _backup_corrupt_config(config_path)
|
||||
|
||||
msg = (
|
||||
f"Failed to parse {config_path}: {exc}. "
|
||||
f"Falling back to default config — every user override "
|
||||
f"(auxiliary providers, fallback chain, model settings) is being IGNORED. "
|
||||
f"Fix the YAML and restart."
|
||||
)
|
||||
if backup_path is not None:
|
||||
msg += f" A copy of the corrupted file was saved to {backup_path}."
|
||||
logger.warning(msg)
|
||||
try:
|
||||
sys.stderr.write(f"⚠️ hermes config: {msg}\n")
|
||||
|
|
|
|||
|
|
@ -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>")
|
||||
|
|
|
|||
|
|
@ -1016,6 +1016,51 @@ async def run_config_migrate():
|
|||
return {"ok": True, "pid": proc.pid, "name": "config-migrate"}
|
||||
|
||||
|
||||
class DebugShareRequest(BaseModel):
|
||||
# Redaction is ON by default — force-mode scrubs credential-shaped tokens
|
||||
# out of log content before it leaves the machine. The toggle exists so an
|
||||
# operator who knows the logs are clean can opt out for fuller fidelity.
|
||||
redact: bool = True
|
||||
# Recent log lines included in the summary tail (full logs are separate).
|
||||
lines: int = 200
|
||||
|
||||
|
||||
@app.post("/api/ops/debug-share")
|
||||
async def run_debug_share_endpoint(body: DebugShareRequest | None = None):
|
||||
"""Upload a redacted debug report + full logs and return the paste URLs.
|
||||
|
||||
Unlike the other diagnostics actions (doctor, dump, prompt-size) this is
|
||||
*synchronous*: the whole point of ``debug share`` is the set of shareable
|
||||
URLs it produces, so we run the upload in a worker thread and return the
|
||||
structured ``{urls, failures, redacted, ...}`` payload directly. The
|
||||
dashboard renders those as real, copyable links instead of scraping a log
|
||||
tail. Pastes auto-delete after 6 hours (handled inside the share core).
|
||||
"""
|
||||
from hermes_cli.debug import build_debug_share
|
||||
|
||||
req = body or DebugShareRequest()
|
||||
try:
|
||||
result = await asyncio.to_thread(
|
||||
build_debug_share,
|
||||
log_lines=max(1, min(int(req.lines), 5000)),
|
||||
redact=bool(req.redact),
|
||||
)
|
||||
except RuntimeError as exc:
|
||||
# Required summary-report upload failed (offline / paste service down).
|
||||
raise HTTPException(status_code=502, detail=f"Upload failed: {exc}")
|
||||
except Exception as exc:
|
||||
_log.exception("debug share failed")
|
||||
raise HTTPException(status_code=500, detail=f"Failed: {exc}")
|
||||
|
||||
return {
|
||||
"ok": True,
|
||||
"urls": result.urls,
|
||||
"failures": result.failures,
|
||||
"redacted": result.redacted,
|
||||
"auto_delete_seconds": result.auto_delete_seconds,
|
||||
}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Gateway + update actions (invoked from the Status page).
|
||||
#
|
||||
|
|
|
|||
|
|
@ -157,6 +157,70 @@ class TestLoadConfigParseFailure:
|
|||
after_edit = capsys.readouterr().err
|
||||
assert "hermes config:" in after_edit, "edited file should re-warn"
|
||||
|
||||
def test_corrupt_config_is_backed_up(self, tmp_path, capsys):
|
||||
"""A broken config.yaml is snapshotted to a timestamped .bak so the
|
||||
user's recoverable overrides survive a later wizard/config-set rewrite.
|
||||
|
||||
Ported from google-gemini/gemini-cli#21541 (policy-file TOML recovery),
|
||||
adapted: we back up but deliberately do NOT reset config.yaml.
|
||||
"""
|
||||
from hermes_cli import config as cfg_mod
|
||||
cfg_mod._CONFIG_PARSE_WARNED.clear()
|
||||
|
||||
with patch.dict(os.environ, {"HERMES_HOME": str(tmp_path)}):
|
||||
broken = "\tmodel: test/custom\nbroken indent:\n"
|
||||
(tmp_path / "config.yaml").write_text(broken)
|
||||
|
||||
load_config()
|
||||
err = capsys.readouterr().err
|
||||
|
||||
baks = list(tmp_path.glob("config.yaml.corrupt.*.bak"))
|
||||
assert len(baks) == 1, f"expected one backup, got {baks}"
|
||||
# Backup preserves the original broken content verbatim
|
||||
assert baks[0].read_text() == broken
|
||||
# Original config.yaml is left untouched (not reset to clean state)
|
||||
assert (tmp_path / "config.yaml").read_text() == broken
|
||||
# User is told where the backup landed
|
||||
assert str(baks[0]) in err
|
||||
|
||||
def test_backup_skips_when_same_size_bak_exists(self, tmp_path, capsys):
|
||||
"""Don't churn backups: if a corrupt backup of the same size already
|
||||
exists (same corruption already preserved), skip making another."""
|
||||
from hermes_cli import config as cfg_mod
|
||||
cfg_mod._CONFIG_PARSE_WARNED.clear()
|
||||
|
||||
with patch.dict(os.environ, {"HERMES_HOME": str(tmp_path)}):
|
||||
broken = "\tbroken:\n"
|
||||
cfg = tmp_path / "config.yaml"
|
||||
cfg.write_text(broken)
|
||||
|
||||
# Pre-existing backup of identical size simulates an earlier snapshot.
|
||||
(tmp_path / "config.yaml.corrupt.20260101-000000.bak").write_text(broken)
|
||||
|
||||
load_config()
|
||||
|
||||
baks = list(tmp_path.glob("config.yaml.corrupt.*.bak"))
|
||||
assert len(baks) == 1, f"should not add a second same-size backup, got {baks}"
|
||||
|
||||
def test_corrupt_symlink_config_not_backed_up(self, tmp_path):
|
||||
"""Symlinked config.yaml is not copied (mirrors Gemini #21541 lstat
|
||||
guard) — avoids clobbering whatever the symlink points at."""
|
||||
import sys as _sys
|
||||
if _sys.platform == "win32":
|
||||
pytest.skip("symlink creation requires privileges on Windows")
|
||||
from hermes_cli import config as cfg_mod
|
||||
cfg_mod._CONFIG_PARSE_WARNED.clear()
|
||||
|
||||
with patch.dict(os.environ, {"HERMES_HOME": str(tmp_path)}):
|
||||
real = tmp_path / "real_config.yaml"
|
||||
real.write_text("\tbroken:\n")
|
||||
link = tmp_path / "config.yaml"
|
||||
link.symlink_to(real)
|
||||
|
||||
load_config()
|
||||
|
||||
assert not list(tmp_path.glob("config.yaml.corrupt.*.bak"))
|
||||
|
||||
|
||||
class TestSaveAndLoadRoundtrip:
|
||||
def test_roundtrip(self, tmp_path):
|
||||
|
|
|
|||
|
|
@ -498,3 +498,96 @@ class TestUpdateCheckEndpoint:
|
|||
assert body["update_available"] is False
|
||||
assert body["message"]
|
||||
|
||||
|
||||
class TestDebugShareEndpoint:
|
||||
"""POST /api/ops/debug-share returns the paste URLs synchronously so the
|
||||
dashboard can render them as copyable links (not a backgrounded log tail)."""
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _setup(self, _isolate_hermes_home):
|
||||
self.client, self.header = _client()
|
||||
from hermes_constants import get_hermes_home
|
||||
|
||||
logs = get_hermes_home() / "logs"
|
||||
logs.mkdir(parents=True, exist_ok=True)
|
||||
(logs / "agent.log").write_text("agent line\n")
|
||||
(logs / "errors.log").write_text("err line\n")
|
||||
(logs / "gateway.log").write_text("gw line\n")
|
||||
|
||||
def test_returns_structured_urls(self, monkeypatch):
|
||||
import hermes_cli.debug as dbg
|
||||
|
||||
count = [0]
|
||||
|
||||
def _upload(content, expiry_days=7):
|
||||
count[0] += 1
|
||||
return f"https://paste.rs/p{count[0]}"
|
||||
|
||||
monkeypatch.setattr(dbg, "upload_to_pastebin", _upload)
|
||||
monkeypatch.setattr(dbg, "_schedule_auto_delete", lambda *a, **k: None)
|
||||
monkeypatch.setattr(dbg, "_best_effort_sweep_expired_pastes", lambda: None)
|
||||
monkeypatch.setattr("hermes_cli.dump.run_dump", lambda a: None)
|
||||
|
||||
r = self.client.post("/api/ops/debug-share", json={"redact": True})
|
||||
assert r.status_code == 200
|
||||
body = r.json()
|
||||
assert body["ok"] is True
|
||||
assert "Report" in body["urls"]
|
||||
assert body["redacted"] is True
|
||||
assert body["auto_delete_seconds"] == 21600
|
||||
assert isinstance(body["failures"], list)
|
||||
|
||||
def test_redact_false_is_honored(self, monkeypatch):
|
||||
import hermes_cli.debug as dbg
|
||||
|
||||
monkeypatch.setattr(
|
||||
dbg, "upload_to_pastebin", lambda c, expiry_days=7: "https://paste.rs/x"
|
||||
)
|
||||
monkeypatch.setattr(dbg, "_schedule_auto_delete", lambda *a, **k: None)
|
||||
monkeypatch.setattr(dbg, "_best_effort_sweep_expired_pastes", lambda: None)
|
||||
monkeypatch.setattr("hermes_cli.dump.run_dump", lambda a: None)
|
||||
|
||||
r = self.client.post("/api/ops/debug-share", json={"redact": False})
|
||||
assert r.status_code == 200
|
||||
assert r.json()["redacted"] is False
|
||||
|
||||
def test_default_body_redacts(self, monkeypatch):
|
||||
import hermes_cli.debug as dbg
|
||||
|
||||
monkeypatch.setattr(
|
||||
dbg, "upload_to_pastebin", lambda c, expiry_days=7: "https://paste.rs/x"
|
||||
)
|
||||
monkeypatch.setattr(dbg, "_schedule_auto_delete", lambda *a, **k: None)
|
||||
monkeypatch.setattr(dbg, "_best_effort_sweep_expired_pastes", lambda: None)
|
||||
monkeypatch.setattr("hermes_cli.dump.run_dump", lambda a: None)
|
||||
|
||||
# No JSON body at all — should default redact=True.
|
||||
r = self.client.post("/api/ops/debug-share")
|
||||
assert r.status_code == 200
|
||||
assert r.json()["redacted"] is True
|
||||
|
||||
def test_upload_failure_returns_502(self, monkeypatch):
|
||||
import hermes_cli.debug as dbg
|
||||
|
||||
monkeypatch.setattr(
|
||||
dbg,
|
||||
"upload_to_pastebin",
|
||||
lambda c, expiry_days=7: (_ for _ in ()).throw(RuntimeError("down")),
|
||||
)
|
||||
monkeypatch.setattr(dbg, "_schedule_auto_delete", lambda *a, **k: None)
|
||||
monkeypatch.setattr(dbg, "_best_effort_sweep_expired_pastes", lambda: None)
|
||||
monkeypatch.setattr("hermes_cli.dump.run_dump", lambda a: None)
|
||||
|
||||
r = self.client.post("/api/ops/debug-share", json={"redact": True})
|
||||
assert r.status_code == 502
|
||||
|
||||
def test_requires_session_token(self):
|
||||
# Drop the token header and confirm the global auth gate rejects it.
|
||||
bare = self.client
|
||||
r = bare.post(
|
||||
"/api/ops/debug-share",
|
||||
json={"redact": True},
|
||||
headers={self.header: "wrong-token"},
|
||||
)
|
||||
assert r.status_code == 401
|
||||
|
||||
|
|
|
|||
|
|
@ -1273,3 +1273,110 @@ class TestShareIncludesAutoDelete:
|
|||
|
||||
out = capsys.readouterr().out
|
||||
assert "public paste service" not in out
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# build_debug_share — structured core used by the dashboard endpoint
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestBuildDebugShare:
|
||||
"""The shared core that returns structured paste URLs (not printed text).
|
||||
|
||||
Backs both ``hermes debug share`` (CLI) and ``POST /api/ops/debug-share``
|
||||
(dashboard). The dashboard renders ``urls`` as real, copyable links, so the
|
||||
contract here is the return value, not stdout.
|
||||
"""
|
||||
|
||||
def test_returns_structured_urls(self, hermes_home):
|
||||
from hermes_cli.debug import build_debug_share, DebugShareResult
|
||||
|
||||
count = [0]
|
||||
|
||||
def _upload(content, expiry_days=7):
|
||||
count[0] += 1
|
||||
return f"https://paste.rs/p{count[0]}"
|
||||
|
||||
with patch("hermes_cli.dump.run_dump"), patch(
|
||||
"hermes_cli.debug.upload_to_pastebin", side_effect=_upload
|
||||
), patch("hermes_cli.debug._schedule_auto_delete"):
|
||||
result = build_debug_share(log_lines=50, redact=True)
|
||||
|
||||
assert isinstance(result, DebugShareResult)
|
||||
# All four seeded logs (agent/gateway/desktop) + the summary report.
|
||||
assert "Report" in result.urls
|
||||
assert "agent.log" in result.urls
|
||||
assert "gateway.log" in result.urls
|
||||
assert "desktop.log" in result.urls
|
||||
assert result.failures == []
|
||||
assert result.redacted is True
|
||||
assert result.auto_delete_seconds == 21600
|
||||
|
||||
def test_skips_missing_logs_without_failure(self, hermes_home):
|
||||
from hermes_cli.debug import build_debug_share
|
||||
|
||||
# Remove desktop.log so it should be neither uploaded nor reported failed.
|
||||
(hermes_home / "logs" / "desktop.log").unlink()
|
||||
|
||||
with patch("hermes_cli.dump.run_dump"), patch(
|
||||
"hermes_cli.debug.upload_to_pastebin",
|
||||
side_effect=lambda c, expiry_days=7: "https://paste.rs/x",
|
||||
), patch("hermes_cli.debug._schedule_auto_delete"):
|
||||
result = build_debug_share(log_lines=50, redact=True)
|
||||
|
||||
assert "desktop.log" not in result.urls
|
||||
assert result.failures == []
|
||||
|
||||
def test_redaction_keeps_secrets_out_of_payload(self, hermes_home):
|
||||
from hermes_cli.debug import build_debug_share
|
||||
|
||||
secret = "sk-proj-SUPERSECRETtoken1234567890"
|
||||
(hermes_home / "logs" / "agent.log").write_text(
|
||||
f"line one\nauthorization token={secret}\nline three\n"
|
||||
)
|
||||
|
||||
uploaded = []
|
||||
|
||||
def _upload(content, expiry_days=7):
|
||||
uploaded.append(content)
|
||||
return "https://paste.rs/x"
|
||||
|
||||
with patch("hermes_cli.dump.run_dump"), patch(
|
||||
"hermes_cli.debug.upload_to_pastebin", side_effect=_upload
|
||||
), patch("hermes_cli.debug._schedule_auto_delete"):
|
||||
result = build_debug_share(log_lines=50, redact=True)
|
||||
|
||||
assert result.redacted is True
|
||||
joined = "\n".join(uploaded)
|
||||
assert secret not in joined, "secret leaked into upload payload"
|
||||
|
||||
def test_optional_log_failure_is_collected_not_raised(self, hermes_home):
|
||||
from hermes_cli.debug import build_debug_share
|
||||
|
||||
count = [0]
|
||||
|
||||
def _upload(content, expiry_days=7):
|
||||
count[0] += 1
|
||||
# First call (the required Report) succeeds; a later one fails.
|
||||
if count[0] == 2:
|
||||
raise RuntimeError("paste service hiccup")
|
||||
return f"https://paste.rs/p{count[0]}"
|
||||
|
||||
with patch("hermes_cli.dump.run_dump"), patch(
|
||||
"hermes_cli.debug.upload_to_pastebin", side_effect=_upload
|
||||
), patch("hermes_cli.debug._schedule_auto_delete"):
|
||||
result = build_debug_share(log_lines=50, redact=True)
|
||||
|
||||
assert "Report" in result.urls
|
||||
assert len(result.failures) == 1
|
||||
assert "paste service hiccup" in result.failures[0]
|
||||
|
||||
def test_required_report_failure_raises(self, hermes_home):
|
||||
from hermes_cli.debug import build_debug_share
|
||||
|
||||
with patch("hermes_cli.dump.run_dump"), patch(
|
||||
"hermes_cli.debug.upload_to_pastebin",
|
||||
side_effect=RuntimeError("all paste services down"),
|
||||
), patch("hermes_cli.debug._schedule_auto_delete"):
|
||||
with pytest.raises(RuntimeError, match="all paste services down"):
|
||||
build_debug_share(log_lines=50, redact=True)
|
||||
|
|
|
|||
|
|
@ -853,6 +853,15 @@ export const api = {
|
|||
runDump: () => fetchJSON<ActionResponse>("/api/ops/dump", { method: "POST" }),
|
||||
runConfigMigrate: () =>
|
||||
fetchJSON<ActionResponse>("/api/ops/config-migrate", { method: "POST" }),
|
||||
runDebugShare: (opts?: { redact?: boolean; lines?: number }) =>
|
||||
fetchJSON<DebugShareResponse>("/api/ops/debug-share", {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({
|
||||
redact: opts?.redact ?? true,
|
||||
lines: opts?.lines ?? 200,
|
||||
}),
|
||||
}),
|
||||
|
||||
|
||||
getCheckpoints: () => fetchJSON<CheckpointsResponse>("/api/ops/checkpoints"),
|
||||
|
|
@ -906,6 +915,16 @@ export interface ActionResponse {
|
|||
update_command?: string;
|
||||
}
|
||||
|
||||
export interface DebugShareResponse {
|
||||
ok: boolean;
|
||||
// label -> paste URL, e.g. { Report: "https://paste.rs/abc", "agent.log": "..." }
|
||||
urls: Record<string, string>;
|
||||
// "label: error" strings for optional full-log uploads that failed.
|
||||
failures: string[];
|
||||
redacted: boolean;
|
||||
auto_delete_seconds: number;
|
||||
}
|
||||
|
||||
export interface SessionStoreStats {
|
||||
total: number;
|
||||
active_store: number;
|
||||
|
|
|
|||
|
|
@ -3,17 +3,22 @@ import { Link } from "react-router-dom";
|
|||
import {
|
||||
Activity,
|
||||
Brain,
|
||||
Check,
|
||||
Clock,
|
||||
Copy,
|
||||
Cpu,
|
||||
Database,
|
||||
Download,
|
||||
Globe,
|
||||
HardDrive,
|
||||
KeyRound,
|
||||
Link2,
|
||||
Play,
|
||||
Plus,
|
||||
Power,
|
||||
RotateCw,
|
||||
Server,
|
||||
Share2,
|
||||
ShieldCheck,
|
||||
Sparkles,
|
||||
Stethoscope,
|
||||
|
|
@ -48,6 +53,7 @@ import type {
|
|||
UpdateCheckResponse,
|
||||
CuratorStatus,
|
||||
PortalStatus,
|
||||
DebugShareResponse,
|
||||
} from "@/lib/api";
|
||||
|
||||
function formatBytes(n: number): string {
|
||||
|
|
@ -324,6 +330,54 @@ export default function SystemPage() {
|
|||
}
|
||||
};
|
||||
|
||||
// ── Debug share ────────────────────────────────────────────────────
|
||||
// Unlike the fire-and-forget ops above, `debug share` produces shareable
|
||||
// paste URLs that are the whole point — so we surface them as real,
|
||||
// copyable links rather than a log tail.
|
||||
const [shareRedact, setShareRedact] = useState(true);
|
||||
const [sharing, setSharing] = useState(false);
|
||||
const [shareResult, setShareResult] = useState<DebugShareResponse | null>(
|
||||
null,
|
||||
);
|
||||
const [copiedLabel, setCopiedLabel] = useState<string | null>(null);
|
||||
|
||||
const copyToClipboard = useCallback(
|
||||
async (text: string, label: string) => {
|
||||
try {
|
||||
await navigator.clipboard.writeText(text);
|
||||
setCopiedLabel(label);
|
||||
setTimeout(
|
||||
() => setCopiedLabel((cur) => (cur === label ? null : cur)),
|
||||
1500,
|
||||
);
|
||||
} catch {
|
||||
showToast("Couldn't copy to clipboard", "error");
|
||||
}
|
||||
},
|
||||
[showToast],
|
||||
);
|
||||
|
||||
const runDebugShare = useCallback(async () => {
|
||||
setSharing(true);
|
||||
setShareResult(null);
|
||||
try {
|
||||
const res = await api.runDebugShare({ redact: shareRedact });
|
||||
setShareResult(res);
|
||||
const n = Object.keys(res.urls).length;
|
||||
showToast(
|
||||
`Uploaded ${n} paste${n === 1 ? "" : "s"}${
|
||||
res.redacted ? " (redacted)" : ""
|
||||
}`,
|
||||
"success",
|
||||
);
|
||||
} catch (e) {
|
||||
showToast(`Debug share failed: ${e}`, "error");
|
||||
} finally {
|
||||
setSharing(false);
|
||||
}
|
||||
}, [shareRedact, showToast]);
|
||||
|
||||
|
||||
// ── Update check / apply ───────────────────────────────────────────
|
||||
const checkForUpdate = useCallback(
|
||||
async (force = false) => {
|
||||
|
|
@ -992,6 +1046,129 @@ export default function SystemPage() {
|
|||
</Button>
|
||||
</CardContent>
|
||||
</Card>
|
||||
|
||||
{/* Debug share — uploads a redacted report + logs, returns shareable
|
||||
links. Separated from the buttons above because its output is
|
||||
persistent, copyable URLs, not a fire-and-forget log tail. */}
|
||||
<Card>
|
||||
<CardContent className="flex flex-col gap-3 py-4">
|
||||
<div className="flex flex-wrap items-center justify-between gap-3">
|
||||
<div className="flex items-start gap-2">
|
||||
<Share2 className="h-4 w-4 mt-0.5 text-muted-foreground" />
|
||||
<div className="flex flex-col">
|
||||
<span className="text-sm font-medium">Share debug report</span>
|
||||
<span className="text-xs text-muted-foreground max-w-prose">
|
||||
Uploads system info + logs to a public paste service and
|
||||
returns links to send the Hermes team. Pastes auto-delete
|
||||
after 6 hours.
|
||||
</span>
|
||||
</div>
|
||||
</div>
|
||||
<Button
|
||||
size="sm"
|
||||
disabled={sharing}
|
||||
prefix={
|
||||
sharing ? (
|
||||
<Spinner className="h-3.5 w-3.5" />
|
||||
) : (
|
||||
<Share2 className="h-3.5 w-3.5" />
|
||||
)
|
||||
}
|
||||
onClick={() => void runDebugShare()}
|
||||
>
|
||||
{sharing ? "Uploading…" : "Generate share link"}
|
||||
</Button>
|
||||
</div>
|
||||
|
||||
<label className="flex items-center gap-2 text-xs text-muted-foreground select-none">
|
||||
<input
|
||||
type="checkbox"
|
||||
className="accent-current"
|
||||
checked={shareRedact}
|
||||
disabled={sharing}
|
||||
onChange={(e) => setShareRedact(e.target.checked)}
|
||||
/>
|
||||
Redact credential-shaped tokens before upload (recommended)
|
||||
</label>
|
||||
|
||||
{shareResult && (
|
||||
<div className="flex flex-col gap-2 border-t border-border pt-3">
|
||||
<div className="flex items-center justify-between">
|
||||
<div className="flex items-center gap-2">
|
||||
<Badge tone="success">uploaded</Badge>
|
||||
{shareResult.redacted ? (
|
||||
<Badge tone="outline">redacted</Badge>
|
||||
) : (
|
||||
<Badge tone="warning">not redacted</Badge>
|
||||
)}
|
||||
<span className="flex items-center gap-1 text-xs text-muted-foreground">
|
||||
<Clock className="h-3 w-3" />
|
||||
auto-deletes in{" "}
|
||||
{Math.round(shareResult.auto_delete_seconds / 3600)}h
|
||||
</span>
|
||||
</div>
|
||||
{Object.keys(shareResult.urls).length > 1 && (
|
||||
<Button
|
||||
size="sm"
|
||||
ghost
|
||||
prefix={
|
||||
copiedLabel === "__all__" ? (
|
||||
<Check className="h-3.5 w-3.5" />
|
||||
) : (
|
||||
<Copy className="h-3.5 w-3.5" />
|
||||
)
|
||||
}
|
||||
onClick={() =>
|
||||
void copyToClipboard(
|
||||
Object.entries(shareResult.urls)
|
||||
.map(([label, url]) => `${label}: ${url}`)
|
||||
.join("\n"),
|
||||
"__all__",
|
||||
)
|
||||
}
|
||||
>
|
||||
Copy all
|
||||
</Button>
|
||||
)}
|
||||
</div>
|
||||
|
||||
{Object.entries(shareResult.urls).map(([label, url]) => (
|
||||
<div
|
||||
key={label}
|
||||
className="flex items-center gap-2 bg-background/50 border border-border px-3 py-2"
|
||||
>
|
||||
<Link2 className="h-3.5 w-3.5 shrink-0 text-muted-foreground" />
|
||||
<span className="font-mono text-xs shrink-0 w-24 truncate text-muted-foreground">
|
||||
{label}
|
||||
</span>
|
||||
<a
|
||||
href={url}
|
||||
target="_blank"
|
||||
rel="noreferrer"
|
||||
className="font-mono text-xs truncate flex-1 text-primary hover:underline"
|
||||
>
|
||||
{url}
|
||||
</a>
|
||||
<Button
|
||||
ghost
|
||||
size="icon"
|
||||
aria-label={`Copy ${label} link`}
|
||||
onClick={() => void copyToClipboard(url, label)}
|
||||
>
|
||||
{copiedLabel === label ? <Check /> : <Copy />}
|
||||
</Button>
|
||||
</div>
|
||||
))}
|
||||
|
||||
{shareResult.failures.length > 0 && (
|
||||
<span className="text-xs text-destructive">
|
||||
Some logs failed to upload: {shareResult.failures.join("; ")}
|
||||
</span>
|
||||
)}
|
||||
</div>
|
||||
)}
|
||||
</CardContent>
|
||||
</Card>
|
||||
<Card>
|
||||
<CardContent className="flex flex-col gap-3 py-4 sm:flex-row sm:items-end">
|
||||
<div className="grid gap-2 flex-1">
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue