A worker hitting a wall only a human can clear (captcha, email/SMS OTP, 2FA,
a decision) calls ask_operator with a precise question and an optional
screenshot. The question lands in the intent's transcript as a user-role turn
with an attachment card (the same {text, attachments} shape chat uploads use,
so the existing transcript UI renders it natively), and the intent pauses. The
operator replies through the existing message-to-worker flow; the reply resumes
the run with the answer as the next input. Images are whitelisted (png/jpg/
jpeg/webp/gif), capped at 10MB, and copied into the task uploads dir.
Closes#41
Every connect attempt (discovery, refresh, and the per-agent-run wiring) now
records its outcome on the server row: last_connect_at/ok/err, written through
a change-deduped update so per-run wiring does not amplify writes. The MCP page
shows a health chip per card (ok with time, or the failure reason), and a new
read-only mcp_status tool (bound to auto, worker and pentest) lets a worker
notice that a server it expected is down and say so instead of silently
degrading while the cached tool count keeps the card looking healthy.
Closes#38
scripts/backup.sh dumps the Postgres database through the postgres compose
service (no host psql needed) into timestamped gzip files under backups/,
keeping the newest N (default 14). --with-data additionally tars the
bind-mounted data directory and fails loudly when files written by the
container are unreadable instead of shipping a partial archive. README gains
a Backups section with the restore one-liner and a cron example.
Closes#40
Descriptions written through the API were interpolated raw into the SKILL.md
frontmatter, so a value containing a colon+space made the whole frontmatter
unparseable: every field silently stayed empty, the skill loaded under its
directory name, and a skill-gated MCP server was silently skipped. The same
applied to updates through the meta rewrite, and the shipped scopesentry skill
had a malformed name line all along.
- yamlScalar: plain-safe tokens stay bare, everything else single-quoted
- fsCreateSkill/fsUpdateSkillMeta emit safe values and re-verify the written
file with the real skill parser (name + mcps must survive), rejecting the
write otherwise
- warnBrokenSkills at startup logs skills whose name fell back to the
directory (the signature of broken frontmatter)
- fix skills/scopesentry/SKILL.md name line
Closes#39
A plain YAML scalar cannot contain a colon followed by a space; the unquoted
description had one, so yaml.Unmarshal failed and every frontmatter field
(including mcps) stayed empty. The skill then loaded with its directory name
but never gated its MCP server, and the server was silently skipped.
Add a rea skill (skill-gated MCP): agents get binary and application package
reverse engineering through a rea MCP server, with tools kept deferred so the
172-tool catalog never bloats the prompt until the skill loads.
Remote MCP servers now take timeout_seconds (default 120): analysis servers
with minutes-long tool calls were cut off mid-call by the fixed 120s client
timeout. Applies to the Streamable HTTP transport; wired through discovery,
the ScopeSentry sync client, the API and the MCP dialog.
Closes#8
The original ARTEX repository no longer exists upstream, so both clone
URLs and both Releases links pointed at 404s: they now point at this
fork, which is the maintained source. The live demo lines and the
WeChat community group section (with its QR code screenshot) belonged
to the original author's channels and are removed. The References,
ScopeSentry, norma and AegisHook links stay (all alive, all
meaningful).
The repo is public now, so the header no longer says it is kept
private. The usage terms still described a learning-only toy, which
contradicted what the tool is; they now require explicit
authorization (own systems, labs, or bounty program scope) and drop
the mainland-China-specific law list for a general jurisdiction line.
All em dashes are replaced with standard punctuation.
Closes#33. The MITM proxy only sees the agent's own actions, so
anything behind a human gate (signup captcha, email OTP, 2FA, SSO)
left the authenticated surface dark. The operator's browser becomes a
capture source instead:
- traffic: exported RecordExternal storing an externally captured
exchange through the same spill/blob/FTS path as proxy traffic
(insert logic shared with record()); rejects unparsable URLs and
empty methods
- server: POST /api/traffic/ingest inside the authenticated API group,
batch capped at 50 entries, bodies truncated at 256 KiB, per-entry
ingested/failed counts
- extension/: Manifest V3 Chrome/Edge extension driving the
chrome.debugger Network domain on the chosen tab, batching text
exchanges to the ingest endpoint with the operator's URL + JWT in
chrome.storage.local; binary bodies skipped; flush on batch/stop
- tests for both layers, README section
--argjson requires strict JSON; the unquoted-key object made jq fail,
sent an empty request body, and the triage died with 'model returned
nothing'. Also log the raw API response when choices is missing so the
next failure shows its cause immediately.
The trailing-line LABELS contract was unreliable at temperature 0.2:
a raw A/B run showed both deepseek-chat and deepseek-flash emit the
line correctly at temperature 0 but drop it nondeterministically at
0.2 (five failed live runs, one lucky success). Structural fix: the
triage now requests response_format json_object, temperature 0, and
parses the reply with jq (comment field for the reply, labels array
for labeling). The label whitelist still drops invented names and the
raw JSON is logged before parsing. Model switched to deepseek-flash:
the A/B showed JSON compliance on both models and flash is the
cheaper line. Mentions and PR first-looks keep text mode at
temperature 0.
The reworded instruction from #20 ("plain text with no markdown
formatting, characters, or emphasis") made models stop emitting the
LABELS line entirely; the original quoted phrasing had 100 percent
compliance. Tolerant parser and debug logging stay.
deepseek-flash dropped the LABELS instruction twice in live tests
(decorated once, absent once); deepseek-chat followed it exactly on
the first try. The price difference is fractions of a cent per call,
reliability wins. The tolerant parser from #20 stays: it is harmless
and protects against any model formatting quirks.
deepseek-flash sometimes bolds or backticks the LABELS marker and the
individual names. Accept any decoration around the marker line and
strip markdown characters from each name before the whitelist check.
Also log the parsed label line for easier triage of future misses.
DeepSeek's current recommendation: V4.1-Flash replaces V4-Pro and is
the efficient line (new encoder-decoder MoE, quarter-size KV cache,
off-peak at half price). Plenty for triage work; the API name is
deepseek-flash.
Closes#15. Issues opened by the maintainer now go through the same
classification and label application but without the triage comment
or reaction. Visitors keep the full behavior; mentions and PR
first-looks stay maintainer-off.
Closes#13. The triage prompt now ends with a LABELS line (bug,
question, feature, plus P1/P2/P3 for bugs). The script strips that
line from the posted comment, filters it against a fixed whitelist,
creates the labels with stable colors if missing, and applies them.
Mentions and PR first-looks stay comment-only.
The go test -skip flag proved unreliable in the full-suite CI shape
(the same pattern skipped correctly in isolation but ran on the
runner), so each of the four tests now carries an explicit t.Skip with
the reason and a pointer to issue #9. The CI workflow drops the -skip
argument and keeps serial package execution.
The rotating agent-package failures were cross-package database
interference: go test runs package binaries in parallel and they all
share the one postgres service, so fixtures delete each other's rows.
-p 1 makes package execution serial and the database deterministic.
First CI run caught a typo in the skip list (the test name is
TestGraphOverviewExpands, with a d) and exposed that
TestSideUsageRecordedOnceOnConsumerCancellation is timing-sensitive
on 2-core runners: it passes locally, fails on CI. Both noted in #9.
Closes#10. A GitHub Action bot with no server: one triage comment per
new issue (classification, missing-info list, grounded first answer),
answers comments that @artex-bot, and a first-look summary checklist on
opened pull requests. Comment-only, never an approving review. Skips
the maintainer, bots, and itself; exits cleanly without the API key;
all model inputs are size-capped.
Closes#9. Go job runs the test suite against a postgres:16 service
container, skipping the three tests that fail on unmodified upstream
code with a fresh database (documented in the issue). Web job runs
tsc --noEmit and the static export build.
Bug bounty alias accounts are nearly always emails, so a bare
"username" placeholder read like a handle only. Say "email or
username" in both the creation dialog and the task detail tab.
The agent tool description already said "login name / email used".
The test accounts section was mounted after the scrollable field area
of the New task sheet, so it sat pinned under the scrollbar instead of
scrolling with the other fields, and its Add account button floated in
a header row instead of sitting in the field content like Add row.
Move it inside the scroll container as a proper Field with the add
button below the rows, matching the intercept rules editor pattern.
Also place the credentials TabsContent after assets in the task detail
page to match the TABS array order and use the local id variable.
Task credentials (#3): declare test accounts at task creation, and never
lose the accounts the agent registers on its own.
- task_credentials table (unique per task+domain+username; upsert
overwrites the password in place), idempotent schema migration
- POST /api/tasks accepts credentials; GET/POST/DELETE
/api/tasks/{id}/credentials serve the UI (manual add, e.g. relaying an
OTP-verified account; delete)
- empty password = the "agent generates" mode: the entry surfaces in the
worker's graph overview with an explicit instruction to register that
account with a strong password and record it
- new tools save_task_credential / list_task_credentials for worker and
pentest; the graph overview injects the task's credentials each round
with a standing note: reuse matching entries, always record accounts
you register
- New Task dialog: optional credentials section (domain, username,
password, note) with a dedicated-test-accounts hint
- task detail: Credentials tab, passwords masked with explicit
reveal/copy, agent-recorded badge, light polling so mid-run recordings
appear
One-shot binding migration (settings-flag-guarded, same pattern as the
other seeds) grants the two tools to worker+pentest on databases seeded
before this change; fresh DBs get them via WorkerTools()/the pentest
catalog.
Closes#3
deadline_at is a wall-clock timestamp, so pause time counted against the
task timeout: pausing overnight (or shutting the machine down while
paused) made the deadline ring while parked, and resuming landed
straight into the settle sequence and a timeout terminal state.
ApplyTaskPause now stamps paused_at, and ApplyTaskAdmission credits the
paused interval back onto deadline_at in the same atomic UPDATE that
ends the pause (paused_at is cleared there too). The shifted deadline
flows to the live handle via the existing RETURNING mirror, so the
engine clock context picks it up. Matches the re-basing the
archive-restore path already did for paused tasks.
Migration is an idempotent ADD COLUMN; tasks paused before the upgrade
have no paused_at and keep the old behavior.
Fixes#1
BaaRai