Tier 1 (clean-room first-turn harness, harness/scripts/model-matrix.mjs):
kickoff + resume chain in-turn on ALL available models — zai/glm-5.2,
deepseek/deepseek-v4-{pro,flash}, aritmolab/qwen3.6-35b-a3b, zai/glm-4.5-air.
The resume cold-start stall recurs on none (closes A's cross-model robustness).
aritmolab/gemma4-26b-a4b is a 404 at the endpoint (listed but not served) — an
availability gap classified as MODEL_ERROR, not a workflow issue.
Tier 2 (live, baseline zai/glm-5.2): F single-select auto-confirm verified
end-to-end — answering the first reviewer_select persisted a concept_clarified
decision (review_decisions.jsonl 0->1) with no follow-up confirmation gate.
Closes F's deferred live check.
No prompt hardening needed. Results in the G plan doc + memory. Throwaway psd
sessions used and deleted; real sessions untouched.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Actionable scoping for the final workstream: a two-tier method (clean-room
first-turn harness generalised from the A2 repro-driver for cheap kickoff/resume
signals; sparing full Playwright F1 runs for the gate round-trip) over the
configured models (GLM 5.2 baseline, Deepseek V4, Qwen3.6, + breadth). Folds in
F's deferred single-select live check and A's resume-on-weaker-models check.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A1 — SessionMenu gains a Resume item, gated to status!=="finalized" && !archived
(matching the backend's 409 read-only guard), wired in AppShell to doResume ->
POST /sessions/:id/resume. SessionMenu.test.tsx (3 tests); frontend 96/96, tsc clean.
A2 — diagnosis-first clean-room repro driving `pi --mode rpc` with the backend's
exact resume handshake shows the cold-start stall NO LONGER reproduces on pi
0.79.4 (8/8 chained into `tht session show` + `read SKILL.md` in-turn, fresh and
partway sessions). The earlier narrate-and-stop predates the pi upgrade.
Defense-in-depth anyway: RIPRENDI_KICKOFF hardened to force the in-turn tool call
(gate_resume_kickoff.test.js + live regression 2/2). Gate JS 34/34.
PROJECT_STATE open-item #1 (resume stall) flipped to RESOLVED; cross-model resume
robustness folded into workstream G.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
F — reviewer_select options may now carry a `decision` payload {type, subject,
detail?, rationale?} plus an optional `advance`. Picking such an option IS the
confirmation: the gate persists it directly (tht decision add) and optionally
advances, with no redundant reviewer_decide/reviewer_confirm follow-up gate.
Options without a payload stay ask-only; back/exit/Other never persist.
Pure logic extracted + exported for unit tests: resolveSelectOutcome (classifies
the response) and decisionAddArgs (shared with reviewer_decide, DRY). Gate JS
suite 33/33 (gate_select_decision.test.js, +5); harness pytest 269 unchanged.
Contract docs updated together: reviewer_select tool description, SKILL.md
(widget summary, disciplines 2-3, Phase-1 single-pick), and the CLAUDE.md gate
note. Live verification (model truly emits reviewer_select+decision, decision in
review_decisions.jsonl, no follow-up gate) deferred to workstream G — it is
model-behavior-dependent.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
B — WorkflowBar renders F1..F8 as colored ring-dots (no phase-name text):
green=done, amber=running (subtle pulse), red=error, gray=pending; green
connectors lead the active dot, each dot carries data-state. Lightweight
error signal: sessionStore gains `phaseError`, set when an info event has
level=error during the active phase, cleared on the next ui_request.
C — denser single-line session rows (inline status dot + name, py-1), a
3-level type hierarchy (L1 SESSIONS / L2 section+group headers / L3 names),
and the "No group" label removed (ungrouped render after the last group,
guarded so the empty-state still teaches when there are zero groups).
Live-verified with Playwright (all four dot states, sidebar hierarchy, and
E's deferred activity-panel check). Frontend 93/93, tsc -b clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- CentralStatus: replace the red pulsing dot at the start of the "working" line
with the rotating WorkingSpinner, now a button that opens the model-activity
panel (onOpenActivity). WorkingSpinner is extracted to its own module (was
local to AppShell).
- ModelActivityPanel: show the last 5 lines of the model-stream tail (refreshing
as the stream grows) with an expand toggle to the full stream, replacing the
unbounded full transcript.
- AppShell: drop the separate spinner button (the inline icon is now the single
trigger) and the local WorkingSpinner def.
- Remove the now-orphaned Transcript.tsx (its only consumer was the panel).
TDD: CentralStatus + ModelActivityPanel tests RED->GREEN; frontend suite 87/87;
tsc clean. Live visual verification pending (to do with the B/C frontend pass).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
New sessions get a concise Italian-keyword `name` instead of the truncated
question. `tht session new` (when no --name is given) derives it via a new
`_extract_name` helper using YAKE (pure-Python, unsupervised, Italian, no LLM),
dropping generic query verbs and keeping the top keywords in reading order;
falls back to `_summarize` if YAKE is unavailable. `create_session` core keeps
its `name=None` default — the policy lives at the CLI layer.
TDD: tests/test_session_name.py (unit + CliRunner integration). Full harness
suite 269 passed; ruff clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The frontend's reviewer widgets uniformly send the picked option in a `choices`
array (SelectWidget/ArtifactGateWidget: `choices: [optionId]`), but the gate's
reviewer_select and reviewer_confirm(reject) handlers read `resp.choice`
(singular). Result: every single-select gate saw an undefined choice, answered
"Nessuna scelta ricevuta", and re-presented forever — the workflow could never
pass F1. (reviewer_decide/multiselect already read `resp.choices`, so it worked.)
Add a shared selectedChoice(resp) helper reading choices[0] (falling back to the
legacy singular choice); both handlers use it.
TDD: gate/__tests__/gate_choice.test.js RED->GREEN; full gate suite 28/28.
Verified LIVE (Playwright -> real Pi -> GLM 5.2): a single-select F1 answer is
now accepted and the workflow advances (clarification 2/4 -> 3/4). The same run
also live-verified the F1 hang fix (418187a).
Co-Authored-By: Claude Opus 4.8 <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>
While the model works (active session, no pending widget), CentralStatus shows
a Claude-Code-style live status: a pulsing dot, elapsed seconds (ticking), and a
short tail of the model's current output — so the centre no longer looks stuck
during the long F1 loop. Verbose stream stays in the left panel. No tokens yet
(would need the SessionBridge to forward Pi usage).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Active/Archive accordions; rename group (client-side reassign); central
area shows only last user entry + gate notify/info + active widget; the
verbose model stream moves to a left on-demand panel toggled by the WIP
icon (moved above the composer). Frontend-only; fine thinking-separation
deferred.
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>
Hard-fail preflight at session create/restart: ensure Ollama up + warm the
configured embedding model, refuse the session if embeddings unavailable.
Parameterized ollama bin/start_cmd; tht ollama ensure command + backend 503.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- SessionMenu: anglicize all Italian labels (Vista divisa → Split view, etc.)
- RenameDialog: add empty-name guard + change title to "Rename session"
- DeleteConfirmDialog: translate title and description to English
- SessionActions.test: add 2 new tests (empty name guard, cancel on DeleteConfirmDialog)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
marcopanandClaude Opus 4.8