Two fixes:
1. Revert tool_execution_* forwarding: these cluttered the UI with raw
bash/read output the user never asked for. Only text_delta, system_event
and ui_request are forwarded, as before.
2. tht ignores THT_CONFIG env var and always looks for config/tht.yaml
relative to CWD. Create a symlink so the PI agent can run tht commands
without -c flag.
The SessionBridge only forwarded text_delta and system_event types.
All tool_execution_*, agent_start, and turn_end events from the Pi
process were silently dropped, so the user saw a blank session even
though the agent was actively running (calling tools, querying the DB).
Forward:
- tool_execution_start/end as info events (visible in stepMessages)
- agent_start, turn_end as system_event (lifecycle tracking)
Also: log Pi stderr instead of draining silently, for debugging.
The Pi process produces events immediately after session creation, but
the browser's SSE connection may not be open yet (React re-render delay,
navigation). The hub discarded events with no subscribers, so the user
saw a blank session.
- Ring-buffer up to 200 events per session; replay on subscribe
- hub.clear(id) on POST /sessions/:id/close frees memory
Unisce gli internals di Codex (secret-bundle, provider-credentials, auth upstream,
security hardening, CI multiarch) mantenendo le fix portal-specific:
- backend: configPath da THT_CONFIG (fix sessioni) + dataRoot di Codex; authMode 'upstream'
- Docker/compose: TENUTO il mio (verificato live: omics_network+alias, env_file, pi npm-g)
perche' il compose/Dockerfile/entrypoint di Codex sono accoppiati al suo modello
secret-bundle (tht doctor inesistente, secret-policy.sh). Adottabile in futuro.
- config.test.ts: preso Codex (superset)
Verificato: tsc clean, 132/132 vitest.
app.ts hardcodava configPath='config/tht.yaml' (symlink solo in dev). Nel container
i route che non passano workspace esplicito (sessionList/sessionShow/documents)
cercavano config/tht.yaml inesistente -> 500. Ora legge THT_CONFIG (entrypoint lo
setta a workspaces/local.yaml), fallback al default per dev. Compose lo esplicita.
Verificato: GET /sessions ora ritorna la lista.
The FE derived 'working' purely as activeSession && !pendingWidget, so the
final workflow turn — the only one that ends without a follow-up gate —
left the spinner on forever (observed live: 21592s after F8 approve).
- SessionBridge maps Pi's agent_end -> SSE system_event {event: agent_end}
- PiProcessManager notifies the client (info error + synthetic agent_end)
when the child dies unexpectedly; expected teardowns stay silent
- sessionStore tracks agentActive (on: user entry/text_delta/ui_request,
off: agent_end); AppShell working now requires it; resume sets it
optimistically
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
ctx.ui.input in `pi --mode rpc` correlates extension_ui_response on its own
top-level RPC id (crypto.randomUUID), not the descriptor id the gate carries
in `title`. SessionBridge replied with the descriptor id, so Pi silently
dropped the response and the model never resumed — every reviewer widget hung
after the human answered.
SessionBridge now stores Pi's top-level m.id (pendingPiId) and replies
extension_ui_response{ id: pendingPiId, value: <uiResponse> }; value still
carries the descriptor id so the gate's internal resp.id === descriptor.id
check still holds.
The fake-pi double had masked the bug by forcing m.id == descriptor.id; it now
mirrors real Pi (distinct randomUUID, correlate on it, drop unknown ids), with
a negative regression test. SKILL.md Phase 1 also now steers multi-answer
disambiguation to reviewer_decide (multiselect).
Tests: backend 67/67, tsc clean, fake-pi contract 2/2.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
pi 0.73 rpc mode is headless and runs tools without an approval gate; the
removed --approve flag made pi exit with 'Unknown option: --approve', breaking
every session spawn. Spawn args are now just --mode rpc. +regression test.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
User
marcopan