Embeddings timeout was 120s, causing multi-minute hangs when Ollama was
down during F4/F6/F7 solved-search. Now: connect_timeout=5s across all
HTTP clients (REST + Ollama), read_timeout reduced to 30s for embeddings,
and OllamaEmbeddings auto-restarts the server on ConnectionError before
degrading gracefully.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The model sometimes stops after receiving 'Fase approvata' without calling
`tht session finalize`, leaving the session open. Now the gate itself calls
finalize after advancing the max phase (F8), making session closure
deterministic regardless of model behavior.
- reviewer_confirm kind:phase: after phase advance at max_phase, gate calls
`tht session finalize <session>` (best-effort with recovery message)
- SKILL.md updated: model no longer needs to call finalize itself
- Tests: 2 new JS tests (auto-finalize at max phase; no-finalize at non-max)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- PROJECT_STATE.md: section on three deployed levers (FK annotations, context-pack, recap v2)
with setup instructions for new workspaces; psd pre-configured
- README.md: one-time setup for workspace (tht schema suggest-fks); note that levers 2+3 auto-activate
- Updated 'How to run' with explicit command and prereq checklist
- Last-updated timestamp: 2026-07-08
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Lever 1: Join-graph via FK logics in annotations + suggest-fks command
- TableAnnotation.foreign_keys field stores curated logical FKs (DWH has no FK constraints)
- tht schema suggest-fks: mine from approved SQL, heuristics (time_key → dim_time),
same-name discovery + explicit --assume flag for multi-owner PKs
- mschema renders 【Foreign keys】 section populated; validation in merge.py
- SKILL.md F4 now reads FKs from mschema-text, no custom data_time_key logic
Lever 2: Context-pack consolidation at kickoff (tht search pack)
- Single embedding of question, reused for schema + evidence + solved searches
- One command: tht search pack <question> --session <id> → retrieval_pack.md
- Graceful degradation when Ollama/vector store unreachable (exit 0, empty sections)
- SKILL.md F1 prescribes as first call; reduces model thinking turns via pre-retrieval
Lever 3: Phase-summary recap v2 auto-construction from session ledger
- tht session show --json includes full decisions ledger
- tht phase meta --json exports 'emits' (substantive decision types per phase)
- Gate appends deterministic 【Decisioni registrate in questa fase】 section (appendLedgerSection)
- Model authors only summary + checks; recap table comes from persisted state (exact by construction)
- SKILL.md Disciplina 6: brief model output, gate fills the rest
Tests: 358 Python (including 10 FK + 3 pack + 1 session-ledger tests) + 111 JS gate tests, all pass.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
extract.mjs now emits a schema-linking ui_request descriptor (columns rendered
from the model's suggested_columns, since the live catalog enrichment needs the
DWH) and parses the reviewer's "N tabelle" outcome; when neither the manifest
nor question.md is reachable, the NL question is approximated by de-slugging
the session id. replay.json regenerated from the 2026-07-06-175012 session
(18 answered gates, includes the F4 schema-linking gate).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Transcript analysis (session 2026-07-06-175012, GLM 5.2) showed F1 at 567s:
182s wasted on a useless `tht schema introspect` (re-introspecting the remote
DWH although physical.yaml was already materialized) plus ~220s of model
thinking inflated by ~7 exploratory turns (--help/find/cat). The actual
searches cost ~15s; reviewer gates (~145s, untouched) are the quality contract.
- schema_cmd.py: introspect now exits 0 with "OK (cache)" in ~1s when
physical.yaml exists; --refresh forces the real re-introspection.
Deterministic cross-model guarantee, verified live on psd (163 tables, 1.2s).
- SKILL.md: F1 toolbox (only `tht search find` + `tht schema render`; no
introspect/--help/filesystem browsing; batch all searches in one turn);
F4 step 1 is render-only with a one-shot introspect fallback.
- tht-gate.js: `tht schema introspect ... --refresh` added to FORBIDDEN
(maintenance stays shell-only, never in-session).
- tests: 4 new pytest cases (cache hit placement proven with fake credentials,
refresh bypass, corrupt-catalog fall-through, render fallback message) and
2 gate anti-bypass JS cases.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The original doc only covered search_similar; the write functions also need
solved_question in their kind whitelist for the memory table.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
- Extract shared statusBadgeClass() helper (src/viewers/statusBadge.ts) so
SqlViewer, CteResultViewer and PhaseSummaryViewer can't drift: ok/success/
passed/promoted render green (--success), warn renders amber (--warning),
error/failed stay destructive red, everything else stays neutral outline.
Previously CteResultViewer/PhaseSummaryViewer mapped "ok"/"promoted" to the
default badge variant, which is bg-primary (GSD red) — success states
rendered red.
- enrich.js: buildCteResultV2 now falls back preview.rows to [] instead of
null when last_test.preview_rows is missing (pre-upgrade ok records), and
CteResultViewer reads result.preview?.rows?.length with a null-safe
fallback so it degrades to the "No preview rows" empty state instead of
crashing.
- PhaseSummaryViewer: section.items is optional (model-authored sections can
be prose-only); render (section.items ?? []) instead of crashing.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Regenerated demo fixture output with augment-schema-linking.mjs +
augment-review-gates.mjs applied, so the F6 cte_plan gate, CTE 1 cte_result
gate, and Fase 5 phase-summary gate carry v2 schema_version payloads and
render via CtePlanViewer/CteResultViewer/PhaseSummaryViewer in the replay
server. Regenerable; committed so the replay server serves it without a
build step.
Add cte-plan-fixture.json, cte-result-fixture.json, and
phase-summary-fixture.json — realistic Italian-language payloads for the
cardiology DWH replay session, conforming exactly to contracts.md (A/B/C).
Add augment-review-gates.mjs (pattern of augment-schema-linking.mjs): finds
the F6 cte_plan gate, first CTE 1 cte_result gate, and Fase 5 phase-summary
gate by title regex and swaps in the v2 artifact.data, so CtePlanViewer,
CteResultViewer, and PhaseSummaryViewer render in the offline replay.
Idempotent; exits 1 if an expected gate is missing.
Document the augment scripts and re-extract note in tools/replay/README.md.
Add CtePlanViewer, CteResultViewer, and PhaseSummaryViewer to render the
structured v2 payloads (schema_version: 2) the harness now emits for
artifact-gate widgets, per contracts.md. Extract PreviewGrid from
ResultsPanel as a reusable AG Grid component shared by CteResultViewer.
ArtifactView dispatches to the new viewers on a schema_version/shape
guard, falling back to the existing legacy renderers unchanged for
older sessions and replay fixtures.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The tht-gate.js reviewer_confirm now builds structured v2 artifacts before the
widget so the reviewer approves gate-derived data, not raw model text:
- new pure modules gate/artifact-contracts.js (soft validators, {ok,errors},
legacy-passthrough) and gate/enrich.js (index/description enrichment,
buildCteResultV2 fusing thin model data with `tht cte info`, phase enrichment)
- cte_plan v2: validate + enrich + persist via `tht cte plan --name … --doc -`
(names derived from data.ctes[]); legacy `names` param kept as fallback
- cte_result v2: rebuild from `tht cte next`/`tht cte info` (sql + preview from
the persisted test record); null/error last_test -> actionable textResult
- phase v2: soft-validate + fill phase from meta + catalog descriptions
- prepareReviewerArguments coerces artifact.data too (GLM double-stringify);
legacy markdown strings pass through unchanged
- SKILL.md: Phase 6 cte_plan payload A + thin cte_result guidance; Discipline 6
payload C example; Discipline 7 reworded for gate-rebuilt cte_result
Legacy (non-v2) paths unchanged. TypeBox stays Type.Any() for artifact.data;
validation is soft (textResult) so models self-correct instead of looping.
All 102 gate JS tests green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
WS1 of review-gates-v2: gives the JS gate (WS2) deterministic data to build the
cte_result v2 payload.
- CteTestRecord gains optional preview_rows (JSON-coerced, truncated cells);
test_cmd populates it from the bounded result rows.
- New read-only `tht cte info <name> --session <id> [--json]`: plan
index/total, persisted .sql, cte_plan_doc.json entry (if any), last
CteTestRecord. Exits 1 with a clean stderr message on missing
session/plan/name/sql.
- `tht cte plan --doc -` validates a chain-doc JSON (ctes[].name must match
--name, same order) and writes it to cte_plan_doc.json; cte_plan.json stays
a plain list[str] (load-bearing for tht.phase.next_cte). --doc is optional.
Regenerated demo fixture output of extract.mjs (WorkflowBar phase tags) with the
F4 gate-7 augment applied (tools/replay/augment-schema-linking.mjs, on the F4
branch). Regenerable; committed so the replay server serves it without a build step.
- ArtifactGateWidget: gate modal 90%→70% of viewport, larger heading, more padding.
- ArtifactView StructuredValue: depth-aware hierarchy (top-level hairline dividers,
warm bg-muted card surfaces + shadow for object-array items).
- index.css: .thot-label micro-labels switched to the mono register (SF Mono) with
tightened tracking, distinguishing labels/meta from sans body prose.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wide tables (e.g. 116 columns, 3 suggested) made curation a scroll hunt. Now the
modal lists suggested columns first (stable sort on the descriptor flag, so
toggling never reorders rows) and adds a filter box matching name + description,
with a "shown/total" count. Selection stays keyed by column name, so the response
column order is unchanged (catalog order). Applies to read-only (excluded) tables too.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Bite-sized TDD tasks: schema-linking types + columns modal, gate widget with
staged per-table column selection, registry/summary wiring, and a replay
fixture generated from the real physical.yaml catalog. Offline-verifiable in
the replay server; harness wiring is Plan 2.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reviewer curates, per promoted table, which columns to use over the full
catalog list (suggested pre-selected + bold); selection persists into
schema_linking.json + the decision ledger and softly guides SQL generation
(Option 1). Dedicated structured schema-linking gate widget (Approach A),
staged commit, inline gate + single columns modal. Hard SQL enforcement is
an explicit follow-up.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Improves how reviewer gates render their content, and adds two small
hooks that make the frontend cooperate with the standalone replay server
(also useful as generic primitives).
Gate body rendering:
- IntroBody: gate intros now render paragraphs plus real bullet lists
with a hanging indent and emphasised bullet lead term, filling the
card width (no narrow measure cap). Backed by introFormat (parser) +
IntroBody (renderer), with tests.
- GateArtifactBody: artifact-review gates whose artifact is a bare file
reference (e.g. {kind:"phase", data:{file:"question.md"}}) now fetch
the referenced session document and render its full content, instead
of showing the file reference as text. Falls back to ArtifactView for
inline-content artifacts and unmapped files. Backed by gateArtifact
(resolver) with tests. ArtifactGateWidget passes sessionId through.
- SelectWidget renders intros via IntroBody.
Replay-friendly session exit:
- AppShell: a system_event {event:"session_exit"} now triggers
stopSession(), returning to the landing view. Generic primitive (the
real backend can emit it too); used by the replay server's "Esci".
- SessionMenu: the ⋮ trigger is now always visible (was opacity-0 /
group-hover only), so Resume is reachable without hovering.
Verified offline against the replay server (no VPN needed); tsc clean.
Reproduces the real reviewer UI for any recorded session, with no VPN/Pi/
Python/DWH. The server (node:http, zero deps) serves the built SPA and a
tiny SSE/REST shim that re-emits the reviewer gates captured in a Pi
transcript, in their original order, with the reviewer's real 3-Jul
choices shown as comparison badges.
- tools/replay/extract.mjs: extracts gates from one or many transcripts
(session-id, file, or directory). Handles sessions split across resume
re-entries by sorting on message timestamp and dropping unanswered
gates. Reads the question from session_manifest.yaml, resolving the
sessions dir from any workspace yaml (no hardcoded paths).
- tools/replay/server.mjs: same-origin :5333. SSE streams gates; POST
/response advances the cursor and pushes info badges (scelta reale).
POST /resume and the final "Ripeti/Esci" widget close the SSE so the
browser EventSource reconnects (cursor resets, gate 1 re-emitted) — the
replay is re-runnable any number of times. GET /sessions/:id/documents
reads the real session files so GateArtifactBody resolves file-reference
artifacts. Exit emits system_event {event:"session_exit"} to return to
the landing.
- scripts/replay.sh: launcher (extract / build / run / all).
- tools/replay/README.md: data flow, commands, fidelity notes.
- .gitignore: ignore tools/replay/web/ (built artifact, like dist/).
A render error in one viewer or gate widget unmounted the whole React root
(white screen). Add a reusable ErrorBoundary (class component, no new dep) with
resetKeys + an on-brand fallback, and wire it at two surfaces:
- WidgetHost: isolates the gate widget (reset on descriptor id) so a malformed
gate payload no longer blanks the conversation
- SessionDocumentsPanel: wraps each document (reset on doc key/content) so one
crashing viewer degrades only its section; siblings and the panel survive
The observed crash: a schema-linking doc that parses but lacks `candidates`
makes SchemaLinkingViewer throw. Verified live via Playwright against the mock
backend. TDD throughout; tsc clean, 123/123 vitest (+8 new tests).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- present() = presentBlockingWidget: transport + no-limbo loop + response
validation; both branches share validateUiResponse; the id invariant must be
validated explicitly in the TUI branch (emitAndWait no longer runs there)
- TUI renderer uses numbered options + index parsing, never label mapping
(frontend already answers with ids); artifact-gate editor is viewer-only,
returned content ignored
- guards resolved: both TUI-only notices now ctx.mode === "tui"
- interactive-render.js as two layers (renderTuiDescriptor +
validateSyntheticResponse); add negative test cases + a real TUI smoke
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The "respond with gate widgets; use '!' for free text" notice is terminal-
flavored. Like the reLoop Esc guard, it used ctx.hasUI, which on pi >=0.80 is
true in RPC too, so it leaked to the browser. Now guarded on ctx.mode === "tui".
The plain text is still swallowed by the `handled` return in all modes; only the
warning is dropped in RPC. No functional ctx.hasUI guard remains in the gate.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Fix six GUI defects, verified live against the real stack:
- NavSessions: mark the in-progress (active) session in yellow (warning
token) — both its status dot and its row background.
- SteerInput: the composer is now an auto-growing textarea that wraps and
grows vertically (caps at 160px, then scrolls); Enter sends, Shift+Enter
inserts a newline.
- WorkflowBar: show a synthetic title of the current phase under the 8 dots
from static EN/IT strings (no LLM); English is displayed to match the chrome.
- CentralStatus: reformat the 5-line system-message tail as a structured,
monospace list with per-line markers and an emphasized last line.
- AppShell + CentralStatus: move the left Model-activity panel toggle off the
working spinner (now a pure status indicator) onto a dedicated arrow button
(→ opens, ← closes).
- gate: rename the phase-confirm button "Conferma e prosegui" → "Salva e
procedi" (builders.js + its L1 test).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
reLoop's "Esc non chiude il gate..." warning is terminal-specific. On pi 0.73
ctx.hasUI was false in RPC, so `if (ctx.hasUI)` effectively meant "TUI only". On
pi >=0.80 hasUI is true in RPC too (dialog-capable UI via the bridge), so the
notice leaked to the browser on any invalid gate response. Guard on
ctx.mode === "tui" to restore the original intent. The fake pi runtime gains
mode:"tui" so the roundtrip test still exercises the notice.
Audit of the other 5 ctx.ui.notify: left as-is. They are valid in both live
modes (TUI and RPC, both hasUI=true) and the gate cannot run headless
(emitAndWait needs a UI), so a guard would be dead code. Their dual-mode
rationalization belongs with the future present() work (tracked in the eval doc).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- #1 hasUI: real 0.80.3 comment is "true in TUI and RPC modes" (doc had the old
0.73.1 "false in print/RPC"). hasUI no longer distinguishes TUI from RPC, so it
is NOT a fallback for the interactive branch — only ctx.mode === "tui" is.
- #2 info/freetext: buildInfoRequest exists in builders.js but is NOT wired into
tht-gate.js (imports only select/multiselect/artifact-gate). info notices are
hand-written ctx.ui.notify; freetext is a control, not a descriptor. Table now
lists only the 3 real present() descriptors.
- #3 cite the REWRITE banner (tht-gate.js:8-10), not :227; id-match quoted verbatim.
- #4 new "Note implementative": 227 comment, 4/6 unguarded notify, and the
ctx.hasUI guard migration side-effect (now fires in RPC on 0.80.3).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- aritmolab-provider.js: import pi-ai from @earendil-works (was @mariozechner).
Verified live that the aritmolab/qwen provider still registers under pi 0.80.3
(get_available_models -> aritmolab, deepseek, zai). Removes the dual-package
reliance on the frozen @mariozechner install still on disk for rollback.
- docs/general/pi-configuration.md: built-in models package is @earendil-works/pi-ai
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Some models (GLM 5.2) send object params (reviewer_confirm's artifact,
write_schema_linking's schema_linking) as JSON-encoded strings. These failed
TypeBox validation before execute(), making the model retry in an unbounded loop
(observed ~2100s hang). jsonObjectOrSelf() coerces them back to objects in
prepareReviewerArguments and write_schema_linking.
Also close an anti-bypass gap: pi's write/edit tools were unrestricted on the gate
code, so a looping model actually patched tht-gate.js. GATE_CODE_FILES now blocks
any write under .pi/extensions. Requires a pi restart to take effect.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Left panels 30vw / central 55% / right rail 15vw, minimal padding. Model-activity
log and documents render via .thot-prose; decisions become hairline rows with
semantic type chips. Resume switches the view optimistically (instant feedback).
The Stop button now asks for confirmation before interrupting.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
ArtifactView's fallback (StructuredValue) turns any object/array into labelled
sections, bullet lists and paragraphs (strings as markdown). Verified against the
real F1 gate (kind:"text", {recap, chiarimenti_risolti[], ...}). MarkdownView
uses the real .thot-prose class (Tailwind Typography is not installed).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Titles + intro read as a clear prompt (comfortable line length), options as
spaced choice rows, Other/Back/Exit as discreet secondary controls under a
divider. Multiselect gets a prominent Select all/Deselect all at the head of the
list with a live count.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Timer now accumulates only while the harness works, pausing while a gate awaits
the reviewer and freezing when finalized (keyed per session, in-memory). Resume
now colours the re-entry phase immediately from the manifest's phase (1..8),
mirroring the F1 paint for new questions.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
erDiagram reads data_type/type from the candidate (top-level or signals),
falling back to the generic 'col' token Mermaid needs — real types render as
soon as schema_linking.json carries them. ArtifactView gains a defensive
{content} fallback for sql-kind artifacts, verified against real session shapes.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
marcopan
