- tool results carry a budget reminder near limits; text before the last tool
call is dropped as report when cut by budget/abort
- usage persisted when a run suspends, so waiting sessions show spent tokens
- task page shows budget_exceeded via business.outcome instead of completed
- budget-exceeded decisions merge by root cause (decision / schedule / goal
template); new summaries added to investigate allowlist
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- 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]>
- PiUpstreamClient: one Models per upstream holding only its provider; credential
store adapter maps to that upstream's secret, so several accounts of one provider
coexist; host env is only read for authKind none (ambient cloud creds)
- provider catalog from builtinProviders() plus static oauth modes, env fields and
subscription terms notes; openai-compatible custom endpoints
- fake upstream provider with mock OAuth (browser paste / device approval)
- PiAgentRuntime accepts an upstream; thinking level clamped to the model
Co-Authored-By: Claude Opus 5.5 <[email protected]>
- POST /approvals and PATCH /approvals/{id} require a console admin session
(EndpointDef auth:"session"); API keys incl. admin scope get 403, so an
organize.execute key can no longer approve its own plan (S1)
- tests for single-use approval checks: expired, revision/payload hash
mismatch, consumed, revoked, pending/rejected, plan mismatch; re-approve
after plan change succeeds once and cannot be replayed (S4)
- one redact key table in @umt/contracts shared by server logger and agent
redactForModel: rsskey, torrent_pass, authkey, downhash, c_secure_pass,
passkey variants, x-api-key, cookie headers, nested objects/arrays (S2)
- TMDB network errors: message and cause redacted via redactUrl (S3)
- web Agent ?mock=1 only in DEV builds or when pi.provider is fake (S7)
- EndpointDef auth annotations for /auth/*, asserted against
PUBLIC_AUTH_PATHS (S10); doc drift fixes (S11)
Co-Authored-By: Claude Opus 5.5 <[email protected]>
