Subagent / vision subflow prompts (audience=agent) get a dedicated section:
report goes to the parent session, and thinking, step notes and reports stay
in Chinese even when the goal, tool results or web pages are in English.
Prompt regression test covers both the shared hard rule and the new section.
Child reports reaching the user are already humanized: the child session page
uses the same FIX-7 report-humanize path, and the parent's final report resolves
child run IDs to their goal titles; agent.spawn/await tool rows show no raw summary.
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]>
