@xhulz/nina 0.57.0 → 0.58.1

package/releases/0.58.1/surfaces/money/tree/.claude/patterns.md

@@ -0,0 +1,49 @@
+<!-- nina:slot money.1 -->
+
+---
+
+## Monetary values & percentages
+
+- **Money is an integer of the currency's minor unit**, end to end — {{MINOR_UNIT}}, never a float, never a type that can hold a fraction of one. Source of precision: `{{MONEY_MODULE}}`.
+- **Percentages are basis points** (`40% → 4000`, `100% → 10000`) so a distribution is exact without floating point.
+- **Parsing, formatting and percentage arithmetic live in one module and nowhere else.** A second place that turns a string into money is a second rounding rule, and the two will disagree on a value somebody is owed.
+- **Never** convert to a floating-point type before formatting, and never let a display format round a stored value.
+- Monetary database columns are integer. JSON responses serialize them as **strings**, not numbers, so no client parses them into a float. The service owns the conversion.
+
+<!-- nina:slot money.2 -->
+
+---
+
+## Distribution invariants (enforced by reviewer + unit tests)
+
+The distribution engine lives in `{{CORE_PKG}}`. It is pure and total over integer {{MINOR_UNIT}}:
+
+- A destination is either a percentage (basis points of the amount) or a fixed value.
+- `total = Σ destinations`, computed in {{MINOR_UNIT}}.
+- `total > amount` → **reject.** Never clamp, never distribute what is not there.
+- `total < amount` → **allow**, surface the shortfall, and leave the remainder **parked**. Silence is the defect here: an unexplained remainder is indistinguishable from a bug.
+- `total = amount` → OK.
+- A retention is just another destination — the same arithmetic applies to it, with no special case.
+
+<!-- nina:slot money.3 -->
+
+---
+
+## State machines & idempotency (enforced by reviewer)
+
+- **Every money-moving entity is a state machine.** Its states and legal transitions are declared in `.claude/architecture.md`; the code follows the declaration, not the other way round. Illegal transitions throw; they are never silently coerced.
+- **Every transition writes an audit row** (entity type, entity id, from, to, actor). No transition without a trail — the trail is what makes a money bug diagnosable after the money has moved.
+- **Outbound transfers are idempotent.** Each carries a unique key, and dedupe happens before the side effect, at the serialization point.
+- **One serialization point per balance.** Whatever computes and dispatches against a single balance never runs concurrently with itself. Two concurrent runs over one balance is how a double send happens even when every individual write is correct.
+
+<!-- nina:slot money.4 -->
+- **Money computation and dispatch go through the serialization point.** Routes, queue consumers and tools never run a distribution or a transfer synchronously in the request path.
+
+<!-- nina:slot money.5 -->
+- **The distribution engine lives in `{{CORE_PKG}}`.** Services call it as a pure function; they do not embed money logic inline.
+
+<!-- nina:slot money.6 -->
+- Idempotency on money-moving writes: the record carries an idempotency key, and the serialization point refuses the second attempt *before* the side effect.
+
+<!-- nina:slot money.7 -->
+- `{{CORE_PKG}}` is the most-tested package — pure functions over fixtures. Cover the distribution invariants exhaustively: over, under, exact, mixed percentage and fixed, and rounding.

package/releases/0.58.1/surfaces/money/tree/.claude/pipeline.md

@@ -0,0 +1,2 @@
+<!-- nina:slot money.1 -->
+  - **Money invariants respected** — a distribution never exceeds the amount; a shortfall is parked, not distributed; transfers idempotent; every transition audited.

package/releases/0.58.1/surfaces/money/tree/.claude/retrieval.md

@@ -0,0 +1,2 @@
+<!-- nina:slot money.1 -->
+| New distribution / transfer logic | `.claude/architecture.md` § *Money*, `.claude/patterns.md` § *Distribution invariants*, `{{CORE_PKG}}/` | architect → implementer → reviewer → qa |

package/releases/0.58.1/surfaces/money/tree/CLAUDE.md

@@ -0,0 +1,11 @@
+<!-- nina:slot money.1 -->
+3. **An outbound transfer is idempotent — it is NEVER sent twice.** Every transfer carries an idempotency key, and deduplication happens at a single serialization point **before** the side effect, never after it. A retry, a re-delivered queue message, a double-click and a replayed webhook must all collapse to one transfer. This is the highest-blast-radius invariant in the system: almost everything else can be corrected afterwards, and a duplicated transfer cannot.
+
+<!-- nina:slot money.2 -->
+4. **Conservation — what comes in equals what goes out plus what is retained.** A distribution may NEVER exceed the amount it distributes → **block**. If it is **less**, **alert** and leave the remainder **parked** and visible — never silently distributed, never silently absorbed. All arithmetic is integer {{MINOR_UNIT}}; percentages are basis points. The LLM never computes a monetary value.
+
+<!-- nina:slot money.3 -->
+5. **State-machine integrity.** Every money-moving entity has an explicit set of states and legal transitions, declared in `.claude/architecture.md` § *State machines* — not inferred from whatever code happens to exist. Only declared transitions are legal; an illegal one throws and is never silently coerced. **Every transition writes an audit row** (entity, id, from → to, actor, when). Skipping a state, inventing one, or landing a transition with no audit row is a hard reject.
+
+<!-- nina:slot money.4 -->
+- **money movement**: anything that creates, moves, settles or records a balance

package/releases/0.58.1/surfaces/pii/tree/.claude/agents/dba.md

@@ -0,0 +1,2 @@
+<!-- nina:slot pii.1 -->
+- **Privacy.** No sensitive value in clear text where it must not be. The categories are declared in `.claude/architecture.md` § *Privacy* — they are not decided per query, and not decided by you. **Document bytes live only in the object store, referenced by key: the column holds the key, never the bytes.** Any column the architect's spec flagged for masking must be encrypted at rest. Reject a schema that widens what is stored in the clear.

package/releases/0.58.1/surfaces/pii/tree/.claude/agents/devops.md

@@ -0,0 +1,8 @@
+<!-- nina:slot pii.1 -->
+
+**Point it at an UNAUTHENTICATED route — a sign-in page is the right one.** Never sign in, and never
+screenshot a signed-in page. Accounts on deployed environments hold real personal data, and a
+screenshot or a console dump pulls it into agent transcripts and logs, where it persists and nobody
+ever looks for it again. That is a privacy leak with no upside here: the sign-in page proves
+everything this check is for. It renders from the same bundle, it exercises the same build-time env
+inlining (a missing variable blanks it identically), and it needs no session.

package/releases/0.58.1/surfaces/pii/tree/.claude/agents/reviewer.md

@@ -0,0 +1,8 @@
+<!-- nina:slot pii.1 -->
+- Check for privacy regressions: **no sensitive value in a log, an error message — a library's own included — a URL or a test fixture**, per the categories in `.claude/architecture.md` § *Privacy*; document bytes only in the object store, never plaintext in the database; no leaked secret.
+
+<!-- nina:slot pii.2 -->
+- **privacy** — the privacy check above, in full: no sensitive value in a log, an error message, a
+  URL or a test fixture; document bytes only in the object store; no leaked secret. Where
+  **tenant-and-privacy** is dispatched, its reviewer owns this too and there is no separate one; where
+  it is not, this is a dimension of its own. Either way it is never nobody's.

package/releases/0.58.1/surfaces/pii/tree/.claude/agents/secops.md

@@ -0,0 +1,2 @@
+<!-- nina:slot pii.1 -->
+- **Privacy (Hard Rule #8)** — the categories declared in `.claude/architecture.md` § *Privacy* must never appear in logs, in responses that do not need them, in error paths, or in the database in clear text. Check every endpoint that returns a person's record for fields it includes by accident: a `select` that quietly grew a column is the usual way this leaks. Check the error paths too — they are written last and reviewed least — and what the libraries on them print or carry in their own errors, bound values included.

package/releases/0.58.1/surfaces/pii/tree/.claude/agents/solidity-auditor.md

@@ -0,0 +1,5 @@
+<!-- nina:slot pii.1 -->
+- **Nothing personal reaches the chain.** What is written on-chain is public, permanent, and beyond
+  deletion by anyone — including by you, and including after a subject asks. A hash of a personal
+  identifier is not a protection: it is a lookup table for whoever holds the input set. Reject a
+  personal datum stored in state, emitted in an event, or passed as calldata.

package/releases/0.58.1/surfaces/pii/tree/CLAUDE.md

@@ -0,0 +1,5 @@
+<!-- nina:slot pii.1 -->
+8. **Sensitive personal data is classified, and the classification is enforced.** What counts as sensitive here — identity documents, financial identifiers, anything a person would not expect to be readable by whoever can read a log — is declared in `.claude/architecture.md` § *Privacy*, along with the regime that governs it ({{PRIVACY_REGIME}}). Encrypted at rest. **No sensitive value in a log, an error message, a URL, an analytics event, or an agent transcript** — the places nobody thinks about are exactly the ones that persist. That includes what a library puts in its own errors and prints itself: a database client's error can carry the query and every bound value, and a framework can log a whole error past the logger it was given. A database error is mapped at the data layer to a typed error from a closed list before anything logs or returns it, and a test proves that a bound value it writes reaches no thrown error. Document bytes live only in the object store, referenced by key, never in the database in clear text.
+
+<!-- nina:slot pii.2 -->
+- **personal data**: where it is collected, stored, logged or sent

package/releases/0.58.1/surfaces/prisma/tree/.claude/agents/architect.md

@@ -0,0 +1,2 @@
+<!-- nina:slot prisma.1 -->
+| `prisma-client-api` | a new or changed Prisma query |

package/releases/0.58.1/surfaces/prisma/tree/.claude/agents/dba.md

@@ -0,0 +1,42 @@
+<!-- nina:slot prisma.1 -->
+| `prisma-cli` | **before ANY `prisma` CLI command** — `validate`, `format`, `migrate dev`, `migrate diff`, `migrate deploy`. Flags differ between versions, and one of them (`migrate diff --shadow-database-url` against a live database) destroys the database it points at |
+| `prisma-client-api` | auditing a new or changed query — filters, operators, `$transaction` semantics. Through a driver adapter, cite the adapter's installed source for what a transaction does: the skill describes the default engine, and an adapter can roll back less |
+
+<!-- nina:slot prisma.2 -->
+Neither skill covers a **caching or edge layer sitting on top of the client** — cache strategy,
+edge-client behaviour and the rule about never caching a read that authorizes a write belong to that
+layer's own integration doc, declared like any other integration. A skill does not replace it.
+
+<!-- nina:slot prisma.3 -->
+- **With Prisma, both offline.** Run `pnpm --filter {{DB_PKG_NAME}} exec prisma validate`; it must pass. Then run `prisma migrate diff` in its **offline, file-only form** and read the generated SQL, not just the Prisma delta. Its flags changed in Prisma 7, so read the installed major (`prisma --version`) before writing the command:
+
+   ```
+   # Prisma 6. Compare the PREVIOUS schema against the working one — pure file-to-file, no database.
+   git show HEAD:{{DB_PKG}}/prisma/schema.prisma > /tmp/schema-head.prisma
+   pnpm --filter {{DB_PKG_NAME}} exec prisma migrate diff \
+     --from-schema-datamodel /tmp/schema-head.prisma \
+     --to-schema-datamodel prisma/schema.prisma \
+     --script
+   ```
+
+   From Prisma 7 the two flags are `--from-schema` and `--to-schema`, and the schema engine starts from the
+   datasource in `prisma.config.ts` even for this diff: with none there, it prints nothing and exits 0. For
+   SQLite a placeholder the diff never opens is enough, a `file:` URL under a gitignored directory; for any
+   other provider, find out what the diff opens before you give it one. Never a real database's URL. A first schema has nothing at `HEAD`: diff it `--from-empty`. Compare the output against the
+   hand-written `migration.sql` to confirm the declarative parts match.
+
+   ⚠️ **Do NOT reach for `--from-migrations`.** It looks like the natural choice and it is a trap:
+   Prisma refuses it without a shadow database (`--shadow-database-url`, or from Prisma 7 a
+   `shadowDatabaseUrl` in `prisma.config.ts`), which pushes you toward supplying a database URL — the exact move that destroys databases (below). The file-to-file form above answers the
+   same question with no database involved.
+
+   ⛔ **NEVER point `--shadow-database-url`, `--from-url`, `--to-url`, `--from-schema-datasource` — or, from Prisma 7, a `shadowDatabaseUrl` or the config datasource behind `--from-config-datasource` — at a real database, most of all not the one `{{SECRETS_LOCAL}}` names.** Prisma **executes** the entire migration history against whatever database those flags name, which **DESTROYS ALL DATA** in it. A shadow database must be a disposable, empty database and nothing else. It does not announce itself: the command completes with a reassuring "empty migration" result and no error, having already destroyed everything in the database it was pointed at. If the offline form above cannot answer your question, **STOP and report that to the orchestrator** instead of reaching for a database URL.
+
+<!-- nina:slot prisma.4 -->
+- **Where reads are cached through Prisma Accelerate,** every `findUnique` / `findMany` on a hot read path names its `cacheStrategy` (`ttl` / `swr`), and one that feeds a correctness-critical write names none.
+
+<!-- nina:slot prisma.5 -->
+- **On an edge runtime,** new Prisma code paths use the edge client of the installed major: `@prisma/client/edge` up to Prisma 6; from 7, the client the `prisma-client` generator writes with the platform's `runtime` set, imported from where it is generated — `@prisma/client/edge` fails there with `MODULE_NOT_FOUND`.
+
+<!-- nina:slot prisma.6 -->
+- Run a Prisma command that writes to a real database — `prisma migrate dev`, `migrate deploy`, `migrate reset`, `migrate resolve`, `db push`, `db execute`, `$executeRaw*` — or **any `prisma migrate diff` variant carrying a database URL**, which silently wipes the database it points at.

package/releases/0.58.1/surfaces/prisma/tree/.claude/agents/devops.md

@@ -0,0 +1,11 @@
+<!-- nina:slot prisma.1 -->
+- **`prisma-cli`** — before `migrate deploy` or any other Prisma CLI command against a real database.
+
+<!-- nina:slot prisma.2 -->
+- **Prisma migrations go out with `prisma migrate deploy`**, and nothing else changes a shared database's schema.
+
+<!-- nina:slot prisma.3 -->
+- Run `prisma migrate diff --shadow-database-url <url>` against any live database. It **executes** the migration history against that database, destroying everything in it, and reports success. Use a disposable shadow database or don't run it.
+
+<!-- nina:slot prisma.4 -->
+- Run `prisma migrate reset` against a shared database, ever.

package/releases/0.58.1/surfaces/prisma/tree/.claude/agents/implementer.md

@@ -0,0 +1,2 @@
+<!-- nina:slot prisma.1 -->
+| `prisma-client-api` | a new or changed Prisma query |

package/releases/0.58.1/surfaces/prisma/tree/.claude/agents/integration-tester.md

@@ -0,0 +1,2 @@
+<!-- nina:slot prisma.1 -->
+| `prisma-cli` | a Prisma CLI command |

package/releases/0.58.1/surfaces/prisma/tree/.claude/agents/reviewer.md

@@ -0,0 +1,2 @@
+<!-- nina:slot prisma.1 -->
+| `prisma-client-api` | a new or changed Prisma query |

package/releases/0.58.1/surfaces/prisma/tree/.claude/patterns.md

@@ -0,0 +1,15 @@
+<!-- nina:slot prisma.1 -->
+- **Database table/column names** (Prisma `@map` / `@@map`): `snake_case` in SQL, `camelCase` in TS.
+
+<!-- nina:slot prisma.2 -->
+- Where Prisma reads are cached through Accelerate, `cacheStrategy` lives in `{{DB_PKG}}`: services do not add, strip, or override cache policies.
+
+<!-- nina:slot prisma.3 -->
+
+### Prisma
+
+- Schema lives in `{{DB_PKG}}/prisma/schema.prisma`. Nowhere else.
+- **Never write raw SQL** unless justified in a code comment with perf data.
+- N+1 is solved with `include` / `select`, chosen deliberately.
+- Where reads are cached through Accelerate, every `findUnique` / `findMany` on a hot path defines its `cacheStrategy`, and no direct connection string is embedded in code.
+- Tests run a real Prisma client against a real database; the client is never mocked.

package/releases/0.58.1/surfaces/prisma/tree/CLAUDE.md

@@ -0,0 +1,5 @@
+<!-- nina:slot prisma.1 -->
+| Run any `prisma` CLI command (the database gate, devops, and the integration gate where there is one) | `prisma-cli` | flags differ between versions; `migrate diff --shadow-database-url` against a live DB wiped dev/staging once |
+
+<!-- nina:slot prisma.2 -->
+| Write or audit a Prisma query (architect, implementer, the database gate, reviewer) | `prisma-client-api` | filters, operators, `$transaction` semantics. a caching or edge layer on top of the client is **NOT covered** — its cache strategy belongs to that layer's own integration doc |

package/src/gate.mjs

@@ -18,6 +18,7 @@
  *   PreToolUse / PostToolUse on Agent, Task, SendMessage
  *                                     a dispatch launched, and the agent it launched
  *   UserPromptSubmit (human text only) the owner spoke, and every open loop gets one round more
+ *   PostToolUse on TaskStop           the orchestrator stopped a run, which will report nothing: for the office
  *   PreToolUse / PostToolUse on AskUserQuestion
  *                                     the orchestrator asked the owner, and was answered: when, for the office
  *   PreToolUse on Agent, Task, SendMessage
@@ -612,6 +613,13 @@ function onPost(input, project, path, at) {
     append(path, { k: 'answered', at });
     return null;
   }
+  if (tool === 'TaskStop') {
+    // By its agent id, or the name it was launched with; anything else it stops — a shell — is not a stage's run.
+    const named = input.tool_input?.task_id;
+    const launched = readLedger(path).findLast((e) => e.k === 'dispatch' && e.agent && (e.agent === named || e.name === named));
+    if (launched) append(path, { k: 'stop', at, agent: launched.agent, role: launched.role });
+    return null;
+  }
   if (!DISPATCH.has(tool)) return null;
   const response = input.tool_response && typeof input.tool_response === 'object' ? input.tool_response : {};
   let role;

package/src/office.html

@@ -644,7 +644,14 @@ function onBeat(b) {
     return;
   }
   if (b.type === 'party') {
-    if (b.instant) return;
+    // The work is done: once the cheering ends, everyone whose report is in goes home, so a room with nothing in hand
+    // is empty rather than holding the last to report. Decided then, not queued now: one sent back to work meanwhile
+    // has nothing waiting in its queue.
+    if (b.instant) {
+      dismissReported([], true);
+      return;
+    }
+    setTimeout(() => dismissReported([], false), 3200);
     note(b.at, `${b.role} ${b.verdict} — done`);
     banner = { text: `${b.role} ${b.verdict}`, until: performance.now() + 3500 };
     const now = performance.now();

package/src/office.mjs

@@ -110,6 +110,9 @@ function readStarts(ledger) {
   // What launched a start: its `dispatch` entry, or — until that is written — what its `pre` says of a message.
   const launchOf = (e) => (e.k === 'pre' ? (dispatches.get(e.id) ?? (e.via ? { via: e.via, agent: e.agent ?? null } : undefined)) : e);
   const verdicts = entries.filter((e) => e.k === 'verdict' && e.declared && e.agent && e.role);
+  // A run the orchestrator stopped (`TaskStop`) reports nothing; read only by its verdict, it sat at its desk for
+  // hours after the session had moved on, and kept the work it was part of from ending.
+  const stops = entries.filter((e) => e.k === 'stop' && e.agent);
 
   // Each start, and how it ends: by a verdict from its agent, or from its stage while its agent is not known yet —
   // the page binds them the same way; refused, when the gate asked, no dispatch was written, and the orchestrator
@@ -121,7 +124,8 @@ function readStarts(ledger) {
     const at = time(e);
     const ranBefore = (agent) => {
       const last = starts.findLast((s) => s.agent === agent && !s.message);
-      return last && !verdicts.some((v) => v.agent === agent && time(v) >= last.at && time(v) <= at);
+      const ended = (x) => x.agent === agent && time(x) >= last.at && time(x) <= at;
+      return last && !verdicts.some(ended) && !stops.some(ended);
     };
     // A message to an agent still running adds to its run; known for certain from the dispatch, before that from
     // whether the agent it names had reported since it last started.
@@ -130,7 +134,14 @@ function readStarts(ledger) {
     starts.push({ i, at, role: e.role, agent: launched?.agent ?? null, message, refusedAt: after ? time(after) : null });
   });
   const verdictOf = (s) => verdicts.find((x) => time(x) >= s.at && (s.agent ? x.agent === s.agent : x.role === s.role)) ?? null;
-  for (const s of starts) s.end = s.message ? s.at : verdictOf(s) ? time(verdictOf(s)) : null;
+  for (const s of starts) {
+    const verdict = verdictOf(s);
+    // A stop ends the run it fell in: an agent run again after it is a run of its own, which a later stop ends.
+    const next = s.agent ? starts.find((x) => x.at > s.at && x.agent === s.agent && !x.message) : null;
+    const stop = !s.message && s.agent ? stops.find((x) => x.agent === s.agent && time(x) >= s.at && (!next || time(x) < next.at)) : null;
+    s.stopped = stop && (!verdict || time(stop) < time(verdict)) ? time(stop) : null;
+    s.end = s.message ? s.at : (s.stopped ?? (verdict ? time(verdict) : null));
+  }
   return { entries, time, startsWork, launchOf, starts, verdictOf };
 }
 
@@ -183,6 +194,7 @@ export function officeBeats(ledger, graph, now = Date.now()) {
       const work = start.message ? `${id}:message` : id;
       beats.push({ id: work, at, type: 'work', role: e.role, agent: start.agent, resumed: launched?.via === 'SendMessage' && !start.message, message: start.message, from: handed ? reported : null });
       if (start.refusedAt !== null) beats.push({ id: `refused:${id}`, at: start.refusedAt, type: 'refused', role: e.role, work });
+      else if (start.stopped !== null) beats.push({ id: `stale:${id}`, at: start.stopped, type: 'stale', role: e.role, agent: start.agent, work: id });
       else if (!start.message && (start.end === null || start.end - start.at >= STALE_MS) && now >= start.at + STALE_MS) {
         beats.push({ id: `stale:${id}`, at: start.at + STALE_MS, type: 'stale', role: e.role, agent: start.agent, work: id });
       }

package/src/wiring.mjs

@@ -130,7 +130,7 @@ const HOOKS = [
     event: 'PreToolUse', matcher: 'Agent|Task|SendMessage|AskUserQuestion', script: GATE, timeout: 10, why: 'the caps in .claude/graph.md stay instructions nothing holds, and the office never sees a question asked',
     crash: (cannot) => ({ systemMessage: `NINA: the loop gate could not start, so the caps in .claude/graph.md are not held — ${cannot}` }),
   },
-  { event: 'PostToolUse', matcher: 'Agent|Task|SendMessage|AskUserQuestion|SubagentHandback', script: GATE, timeout: 10, why: 'the gate never learns which rounds went out, or that the owner answered' },
+  { event: 'PostToolUse', matcher: 'Agent|Task|SendMessage|AskUserQuestion|SubagentHandback|TaskStop', script: GATE, timeout: 10, why: 'the gate never learns which rounds went out, that the owner answered, or that a run was stopped' },
   { event: 'SubagentStop', script: GATE, timeout: 10, why: 'the gate misses the verdict of a stage that wrote its report as its last message' },
   { event: 'SubagentStart', script: GATE, timeout: 10, why: 'a stage is not handed its lessons, and opens every shared pill to find them, or none' },
   { event: 'SessionStart', matcher: 'compact', script: GATE, timeout: 10, why: 'after a compaction the orchestrator has lost the graph, the router and its open loops, and nothing gives them back' },