- browser.screenshot returns the page as an image content block (≤1280px wide, JPEG quality
configurable) for vision-capable upstreams; non-vision upstreams get a redacted text snapshot.
Login pages / password fields are marked sensitive and withheld unless a
browser.sensitive_screenshot grant exists and allowSensitive is passed.
- browser.click_at / type_at / scroll / wait act in screenshot pixels; the server converts via
viewport/DPR, requires automation control and an allowlisted host, and writes a thumbnail
evidence file (DATA_DIR/tmp/evidence) referenced from agent_run_event.
- browser.solve_challenge runs a bounded child agent_run (vision caps only, maxSteps ≤ 12,
budget), judges success from page facts, stops immediately on 2FA / SMS / device confirmation,
and otherwise moves the session to waiting with evidence and a takeover link.
- PiAgentRuntime passes modelImage outputs as pi-ai image content when model.input has image;
the ledger never stores image data; coordinate actions use per-invocation idempotency keys.
- Tests: image codec, runtime image content, E14 e2e (login solved, 2FA stop, step limit,
sensitive withheld). Real camofox 1.17.0 check on example.com recorded in the runbook.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
shadcn (web devDependency) pulled a second peer copy of
@modelcontextprotocol/[email protected].1 (zod@3), so the server's zod@4 copy
lived in the npm cache as sdk/1.30.1_1. `deno compile --exclude-unused-npm`
embeds that _1 folder but the pruned snapshot resolves it as sdk/1.30.1,
so every SDK import failed at startup with ERR_MODULE_NOT_FOUND.
- drop the shadcn CLI dependency; vendor its tailwind.css (the only
runtime use) as apps/web/app/shadcn-tailwind.css, removing the duplicate
- scripts/check-compiled-binary.sh: run the compiled binary with an empty
env and `--role preflight`; it must load the full module graph and exit 2
on config validation. Wired into `deno task ci` (check:binary) and the
Dockerfile build stage.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- contracts/mcp.ts: capability stats/tools, MCP server status/config schemas, mcpToolVisible
- api.ts: GET /capabilities/stats, GET /capabilities/tools, GET /mcp/status, PATCH /mcp/config
- migration 0039: mcp_server_config single row + audit_event capability index
- deno.json: npm:@modelcontextprotocol/[email protected].1
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- GET /auth/totp/setup returns the pending secret and otpauth URL (created
on first call, reused on refresh) for the console to render as a QR code.
- Enabling TOTP issues 8 one-time recovery codes (argon2id hashes in
admin_recovery_code); login accepts recoveryCode in place of totpCode,
disable accepts either, and recovery_codes regenerates with the password.
- Passkeys via @simplewebauthn/server: register/list/rename/delete under
the console session, public login options/verify that reuse the login
rate limit and session cookies. Challenges are one-time rows in
webauthn_challenge; RP ID and origins come from WEBAUTHN_RP_ID /
WEBAUTHN_ORIGINS, falling back to the request host. Signature counter
regressions are rejected. SessionInfo gains passkeyEnabled.
- --role rotate-master-key re-encrypts the secret table from
SECRET_MASTER_KEY to SECRET_MASTER_KEY_NEW one row per transaction,
skips rows already on the new key (resumable, swap keys to roll back),
logs progress and audits secret.master_key_rotate. Secrets now record
the master key fingerprint in kdf_params.kid.
- Runbook: recovery codes, passkey configuration, rotation steps and
rollback.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- glossary: 10 punctuation rules (full-width in Chinese, CJK/Latin spacing,
full-width parens around Chinese, single ellipsis, 「」 quotes, period rules)
- scripts/check-copy-punctuation.mjs: checks string literals, templates and JSX
text (not comments, types, keys, match/compare strings); --fix, --strict,
--by-file; wired into deno task ci as check:copy in warn mode
- --fix applied to web, server and contracts; files other lanes were editing
(subscriptions, sites, browser, agent, auth/account, inventory) left for them
- tests updated for the changed messages
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- planImport (sourcePaths mode): when a selected source is a video file,
same-directory subtitles / external audio whose stem (language tags
stripped) matches it join the source list, so the organize wizard, which
expands a directory into individual videos, no longer drops them.
Unrelated sidecars stay out; pathGuard applies to the added files.
- Organize records page honours ?ids= (wizard multi-group redirect): shows
just those records via /files/records, refreshes while running, clear chip.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- GET /dashboard: automation.library {entities, movies, series, seasons,
episodes, assets} and automation.slotSatisfiedRate; home media overview
shows the counts instead of placeholders.
- GET /engine/runs: `status` accepts comma-separated values; new
`triggeredBy` filter (comma-separated) evaluated server-side by scanning
batches and paging with the last inspected row's cursor (scan cap 2000).
- Task stream: source filter and the "active" tab (running,pending) are now
one paginated server query.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- downloads.ts observe: re-read download_task FOR UPDATE inside the tx and merge
from the locked row; qB sync could overwrite imported back to importing when
verifyAndImport committed between the sync read and write (E8 flake).
- agent finalize: accept summaryPrefix so the recovery verdict is written with
the terminal status in one update (E6 read a budget_exceeded run before the
"未恢复:…" annotation landed); recover-summary step kept, now idempotent no-op.
- organize.ts: drop local slotComplete and the once-subscription completion
write; completion/history are decided only by applySlotEvent(verify_passed)
(W5-C follow-up, removes double write). Manual slot organize uses the shared
subscriptions.slotComplete.
- vitest: server split into unit (parallel) and pg (file-serial, groupOrder 1)
projects; packages/tasks file-serial; explicit worker concurrency in e2e.
- docs: W6 stabilization record in 04-v0.1-acceptance.md.
Test expectations unchanged. Full `deno task ci` x3 green: 369s / 341s / 337s.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Logs in, opens every console route (detail routes resolved from list endpoints), fails on
console errors, uncaught exceptions or 4xx/5xx API responses, and screenshots each page.
Uses playwright-core with the local Chromium; documented in README.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
