@quantumclaw/quantumclaw 2026.3.22

package/docs/concepts/typebox.md

@@ -0,0 +1,291 @@
+---
+summary: "TypeBox schemas as the single source of truth for the gateway protocol"
+read_when:
+  - Updating protocol schemas or codegen
+title: "TypeBox"
+---
+
+# TypeBox as protocol source of truth
+
+Last updated: 2026-01-10
+
+TypeBox is a TypeScript-first schema library. We use it to define the **Gateway
+WebSocket protocol** (handshake, request/response, server events). Those schemas
+drive **runtime validation**, **JSON Schema export**, and **Swift codegen** for
+the macOS app. One source of truth; everything else is generated.
+
+If you want the higher-level protocol context, start with
+[Gateway architecture](/concepts/architecture).
+
+## Mental model (30 seconds)
+
+Every Gateway WS message is one of three frames:
+
+- **Request**: `{ type: "req", id, method, params }`
+- **Response**: `{ type: "res", id, ok, payload | error }`
+- **Event**: `{ type: "event", event, payload, seq?, stateVersion? }`
+
+The first frame **must** be a `connect` request. After that, clients can call
+methods (e.g. `health`, `send`, `chat.send`) and subscribe to events (e.g.
+`presence`, `tick`, `agent`).
+
+Connection flow (minimal):
+
+```
+Client                    Gateway
+  |---- req:connect -------->|
+  |<---- res:hello-ok --------|
+  |<---- event:tick ----------|
+  |---- req:health ---------->|
+  |<---- res:health ----------|
+```
+
+Common methods + events:
+
+| Category  | Examples                                                  | Notes                              |
+| --------- | --------------------------------------------------------- | ---------------------------------- |
+| Core      | `connect`, `health`, `status`                             | `connect` must be first            |
+| Messaging | `send`, `poll`, `agent`, `agent.wait`                     | side-effects need `idempotencyKey` |
+| Chat      | `chat.history`, `chat.send`, `chat.abort`, `chat.inject`  | WebChat uses these                 |
+| Sessions  | `sessions.list`, `sessions.patch`, `sessions.delete`      | session admin                      |
+| Nodes     | `node.list`, `node.invoke`, `node.pair.*`                 | Gateway WS + node actions          |
+| Events    | `tick`, `presence`, `agent`, `chat`, `health`, `shutdown` | server push                        |
+
+Authoritative list lives in `src/gateway/server.ts` (`METHODS`, `EVENTS`).
+
+## Where the schemas live
+
+- Source: `src/gateway/protocol/schema.ts`
+- Runtime validators (AJV): `src/gateway/protocol/index.ts`
+- Server handshake + method dispatch: `src/gateway/server.ts`
+- Node client: `src/gateway/client.ts`
+- Generated JSON Schema: `dist/protocol.schema.json`
+- Generated Swift models: `apps/macos/Sources/QuantumClawProtocol/GatewayModels.swift`
+
+## Current pipeline
+
+- `pnpm protocol:gen`
+  - writes JSON Schema (draft‑07) to `dist/protocol.schema.json`
+- `pnpm protocol:gen:swift`
+  - generates Swift gateway models
+- `pnpm protocol:check`
+  - runs both generators and verifies the output is committed
+
+## How the schemas are used at runtime
+
+- **Server side**: every inbound frame is validated with AJV. The handshake only
+  accepts a `connect` request whose params match `ConnectParams`.
+- **Client side**: the JS client validates event and response frames before
+  using them.
+- **Method surface**: the Gateway advertises the supported `methods` and
+  `events` in `hello-ok`.
+
+## Example frames
+
+Connect (first message):
+
+```json
+{
+  "type": "req",
+  "id": "c1",
+  "method": "connect",
+  "params": {
+    "minProtocol": 2,
+    "maxProtocol": 2,
+    "client": {
+      "id": "quantumclaw-macos",
+      "displayName": "macos",
+      "version": "1.0.0",
+      "platform": "macos 15.1",
+      "mode": "ui",
+      "instanceId": "A1B2"
+    }
+  }
+}
+```
+
+Hello-ok response:
+
+```json
+{
+  "type": "res",
+  "id": "c1",
+  "ok": true,
+  "payload": {
+    "type": "hello-ok",
+    "protocol": 2,
+    "server": { "version": "dev", "connId": "ws-1" },
+    "features": { "methods": ["health"], "events": ["tick"] },
+    "snapshot": {
+      "presence": [],
+      "health": {},
+      "stateVersion": { "presence": 0, "health": 0 },
+      "uptimeMs": 0
+    },
+    "policy": { "maxPayload": 1048576, "maxBufferedBytes": 1048576, "tickIntervalMs": 30000 }
+  }
+}
+```
+
+Request + response:
+
+```json
+{ "type": "req", "id": "r1", "method": "health" }
+```
+
+```json
+{ "type": "res", "id": "r1", "ok": true, "payload": { "ok": true } }
+```
+
+Event:
+
+```json
+{ "type": "event", "event": "tick", "payload": { "ts": 1730000000 }, "seq": 12 }
+```
+
+## Minimal client (Node.js)
+
+Smallest useful flow: connect + health.
+
+```ts
+import { WebSocket } from "ws";
+
+const ws = new WebSocket("ws://127.0.0.1:18789");
+
+ws.on("open", () => {
+  ws.send(
+    JSON.stringify({
+      type: "req",
+      id: "c1",
+      method: "connect",
+      params: {
+        minProtocol: 3,
+        maxProtocol: 3,
+        client: {
+          id: "cli",
+          displayName: "example",
+          version: "dev",
+          platform: "node",
+          mode: "cli",
+        },
+      },
+    }),
+  );
+});
+
+ws.on("message", (data) => {
+  const msg = JSON.parse(String(data));
+  if (msg.type === "res" && msg.id === "c1" && msg.ok) {
+    ws.send(JSON.stringify({ type: "req", id: "h1", method: "health" }));
+  }
+  if (msg.type === "res" && msg.id === "h1") {
+    console.log("health:", msg.payload);
+    ws.close();
+  }
+});
+```
+
+## Worked example: add a method end-to-end
+
+Example: add a new `system.echo` request that returns `{ ok: true, text }`.
+
+1. **Schema (source of truth)**
+
+Add to `src/gateway/protocol/schema.ts`:
+
+```ts
+export const SystemEchoParamsSchema = Type.Object(
+  { text: NonEmptyString },
+  { additionalProperties: false },
+);
+
+export const SystemEchoResultSchema = Type.Object(
+  { ok: Type.Boolean(), text: NonEmptyString },
+  { additionalProperties: false },
+);
+```
+
+Add both to `ProtocolSchemas` and export types:
+
+```ts
+  SystemEchoParams: SystemEchoParamsSchema,
+  SystemEchoResult: SystemEchoResultSchema,
+```
+
+```ts
+export type SystemEchoParams = Static<typeof SystemEchoParamsSchema>;
+export type SystemEchoResult = Static<typeof SystemEchoResultSchema>;
+```
+
+2. **Validation**
+
+In `src/gateway/protocol/index.ts`, export an AJV validator:
+
+```ts
+export const validateSystemEchoParams = ajv.compile<SystemEchoParams>(SystemEchoParamsSchema);
+```
+
+3. **Server behavior**
+
+Add a handler in `src/gateway/server-methods/system.ts`:
+
+```ts
+export const systemHandlers: GatewayRequestHandlers = {
+  "system.echo": ({ params, respond }) => {
+    const text = String(params.text ?? "");
+    respond(true, { ok: true, text });
+  },
+};
+```
+
+Register it in `src/gateway/server-methods.ts` (already merges `systemHandlers`),
+then add `"system.echo"` to `METHODS` in `src/gateway/server.ts`.
+
+4. **Regenerate**
+
+```bash
+pnpm protocol:check
+```
+
+5. **Tests + docs**
+
+Add a server test in `src/gateway/server.*.test.ts` and note the method in docs.
+
+## Swift codegen behavior
+
+The Swift generator emits:
+
+- `GatewayFrame` enum with `req`, `res`, `event`, and `unknown` cases
+- Strongly typed payload structs/enums
+- `ErrorCode` values and `GATEWAY_PROTOCOL_VERSION`
+
+Unknown frame types are preserved as raw payloads for forward compatibility.
+
+## Versioning + compatibility
+
+- `PROTOCOL_VERSION` lives in `src/gateway/protocol/schema.ts`.
+- Clients send `minProtocol` + `maxProtocol`; the server rejects mismatches.
+- The Swift models keep unknown frame types to avoid breaking older clients.
+
+## Schema patterns and conventions
+
+- Most objects use `additionalProperties: false` for strict payloads.
+- `NonEmptyString` is the default for IDs and method/event names.
+- The top-level `GatewayFrame` uses a **discriminator** on `type`.
+- Methods with side effects usually require an `idempotencyKey` in params
+  (example: `send`, `poll`, `agent`, `chat.send`).
+- `agent` accepts optional `internalEvents` for runtime-generated orchestration context
+  (for example subagent/cron task completion handoff); treat this as internal API surface.
+
+## Live schema JSON
+
+Generated JSON Schema is in the repo at `dist/protocol.schema.json`. The
+published raw file is typically available at:
+
+- [https://raw.githubusercontent.com/quantumclaw/quantumclaw/main/dist/protocol.schema.json](https://raw.githubusercontent.com/quantumclaw/quantumclaw/main/dist/protocol.schema.json)
+
+## When you change schemas
+
+1. Update the TypeBox schemas.
+2. Run `pnpm protocol:check`.
+3. Commit the regenerated schema + Swift models.

package/docs/concepts/typing-indicators.md

@@ -0,0 +1,68 @@
+---
+summary: "When QuantumClaw shows typing indicators and how to tune them"
+read_when:
+  - Changing typing indicator behavior or defaults
+title: "Typing Indicators"
+---
+
+# Typing indicators
+
+Typing indicators are sent to the chat channel while a run is active. Use
+`agents.defaults.typingMode` to control **when** typing starts and `typingIntervalSeconds`
+to control **how often** it refreshes.
+
+## Defaults
+
+When `agents.defaults.typingMode` is **unset**, QuantumClaw keeps the legacy behavior:
+
+- **Direct chats**: typing starts immediately once the model loop begins.
+- **Group chats with a mention**: typing starts immediately.
+- **Group chats without a mention**: typing starts only when message text begins streaming.
+- **Heartbeat runs**: typing is disabled.
+
+## Modes
+
+Set `agents.defaults.typingMode` to one of:
+
+- `never` — no typing indicator, ever.
+- `instant` — start typing **as soon as the model loop begins**, even if the run
+  later returns only the silent reply token.
+- `thinking` — start typing on the **first reasoning delta** (requires
+  `reasoningLevel: "stream"` for the run).
+- `message` — start typing on the **first non-silent text delta** (ignores
+  the `NO_REPLY` silent token).
+
+Order of “how early it fires”:
+`never` → `message` → `thinking` → `instant`
+
+## Configuration
+
+```json5
+{
+  agent: {
+    typingMode: "thinking",
+    typingIntervalSeconds: 6,
+  },
+}
+```
+
+You can override mode or cadence per session:
+
+```json5
+{
+  session: {
+    typingMode: "message",
+    typingIntervalSeconds: 4,
+  },
+}
+```
+
+## Notes
+
+- `message` mode won’t show typing for silent-only replies (e.g. the `NO_REPLY`
+  token used to suppress output).
+- `thinking` only fires if the run streams reasoning (`reasoningLevel: "stream"`).
+  If the model doesn’t emit reasoning deltas, typing won’t start.
+- Heartbeats never show typing, regardless of mode.
+- `typingIntervalSeconds` controls the **refresh cadence**, not the start time.
+  The default is 6 seconds.

package/docs/concepts/usage-tracking.md

@@ -0,0 +1,35 @@
+---
+summary: "Usage tracking surfaces and credential requirements"
+read_when:
+  - You are wiring provider usage/quota surfaces
+  - You need to explain usage tracking behavior or auth requirements
+title: "Usage Tracking"
+---
+
+# Usage tracking
+
+## What it is
+
+- Pulls provider usage/quota directly from their usage endpoints.
+- No estimated costs; only the provider-reported windows.
+
+## Where it shows up
+
+- `/status` in chats: emoji‑rich status card with session tokens + estimated cost (API key only). Provider usage shows for the **current model provider** when available.
+- `/usage off|tokens|full` in chats: per-response usage footer (OAuth shows tokens only).
+- `/usage cost` in chats: local cost summary aggregated from QuantumClaw session logs.
+- CLI: `quantumclaw status --usage` prints a full per-provider breakdown.
+- CLI: `quantumclaw channels list` prints the same usage snapshot alongside provider config (use `--no-usage` to skip).
+- macOS menu bar: “Usage” section under Context (only if available).
+
+## Providers + credentials
+
+- **Anthropic (Claude)**: OAuth tokens in auth profiles.
+- **GitHub Copilot**: OAuth tokens in auth profiles.
+- **Gemini CLI**: OAuth tokens in auth profiles.
+- **Antigravity**: OAuth tokens in auth profiles.
+- **OpenAI Codex**: OAuth tokens in auth profiles (accountId used when present).
+- **MiniMax**: API key (coding plan key; `MINIMAX_CODE_PLAN_KEY` or `MINIMAX_API_KEY`); uses the 5‑hour coding plan window.
+- **z.ai**: API key via env/config/auth store.
+
+Usage is hidden if no matching OAuth/API credentials exist.

package/docs/date-time.md

@@ -0,0 +1,128 @@
+---
+summary: "Date and time handling across envelopes, prompts, tools, and connectors"
+read_when:
+  - You are changing how timestamps are shown to the model or users
+  - You are debugging time formatting in messages or system prompt output
+title: "Date and Time"
+---
+
+# Date & Time
+
+QuantumClaw defaults to **host-local time for transport timestamps** and **user timezone only in the system prompt**.
+Provider timestamps are preserved so tools keep their native semantics (current time is available via `session_status`).
+
+## Message envelopes (local by default)
+
+Inbound messages are wrapped with a timestamp (minute precision):
+
+```
+[Provider ... 2026-01-05 16:26 PST] message text
+```
+
+This envelope timestamp is **host-local by default**, regardless of the provider timezone.
+
+You can override this behavior:
+
+```json5
+{
+  agents: {
+    defaults: {
+      envelopeTimezone: "local", // "utc" | "local" | "user" | IANA timezone
+      envelopeTimestamp: "on", // "on" | "off"
+      envelopeElapsed: "on", // "on" | "off"
+    },
+  },
+}
+```
+
+- `envelopeTimezone: "utc"` uses UTC.
+- `envelopeTimezone: "local"` uses the host timezone.
+- `envelopeTimezone: "user"` uses `agents.defaults.userTimezone` (falls back to host timezone).
+- Use an explicit IANA timezone (e.g., `"America/Chicago"`) for a fixed zone.
+- `envelopeTimestamp: "off"` removes absolute timestamps from envelope headers.
+- `envelopeElapsed: "off"` removes elapsed time suffixes (the `+2m` style).
+
+### Examples
+
+**Local (default):**
+
+```
+[WhatsApp +1555 2026-01-18 00:19 PST] hello
+```
+
+**User timezone:**
+
+```
+[WhatsApp +1555 2026-01-18 00:19 CST] hello
+```
+
+**Elapsed time enabled:**
+
+```
+[WhatsApp +1555 +30s 2026-01-18T05:19Z] follow-up
+```
+
+## System prompt: Current Date & Time
+
+If the user timezone is known, the system prompt includes a dedicated
+**Current Date & Time** section with the **time zone only** (no clock/time format)
+to keep prompt caching stable:
+
+```
+Time zone: America/Chicago
+```
+
+When the agent needs the current time, use the `session_status` tool; the status
+card includes a timestamp line.
+
+## System event lines (local by default)
+
+Queued system events inserted into agent context are prefixed with a timestamp using the
+same timezone selection as message envelopes (default: host-local).
+
+```
+System: [2026-01-12 12:19:17 PST] Model switched.
+```
+
+### Configure user timezone + format
+
+```json5
+{
+  agents: {
+    defaults: {
+      userTimezone: "America/Chicago",
+      timeFormat: "auto", // auto | 12 | 24
+    },
+  },
+}
+```
+
+- `userTimezone` sets the **user-local timezone** for prompt context.
+- `timeFormat` controls **12h/24h display** in the prompt. `auto` follows OS prefs.
+
+## Time format detection (auto)
+
+When `timeFormat: "auto"`, QuantumClaw inspects the OS preference (macOS/Windows)
+and falls back to locale formatting. The detected value is **cached per process**
+to avoid repeated system calls.
+
+## Tool payloads + connectors (raw provider time + normalized fields)
+
+Channel tools return **provider-native timestamps** and add normalized fields for consistency:
+
+- `timestampMs`: epoch milliseconds (UTC)
+- `timestampUtc`: ISO 8601 UTC string
+
+Raw provider fields are preserved so nothing is lost.
+
+- Slack: epoch-like strings from the API
+- Discord: UTC ISO timestamps
+- Telegram/WhatsApp: provider-specific numeric/ISO timestamps
+
+If you need local time, convert it downstream using the known timezone.
+
+## Related docs
+
+- [System Prompt](/concepts/system-prompt)
+- [Timezones](/concepts/timezone)
+- [Messages](/concepts/messages)

package/docs/debug/node-issue.md

@@ -0,0 +1,85 @@
+---
+summary: Node + tsx "__name is not a function" crash notes and workarounds
+read_when:
+  - Debugging Node-only dev scripts or watch mode failures
+  - Investigating tsx/esbuild loader crashes in QuantumClaw
+title: "Node + tsx Crash"
+---
+
+# Node + tsx "\_\_name is not a function" crash
+
+## Summary
+
+Running QuantumClaw via Node with `tsx` fails at startup with:
+
+```
+[quantumclaw] Failed to start CLI: TypeError: __name is not a function
+    at createSubsystemLogger (.../src/logging/subsystem.ts:203:25)
+    at .../src/agents/auth-profiles/constants.ts:25:20
+```
+
+This began after switching dev scripts from Bun to `tsx` (commit `2871657e`, 2026-01-06). The same runtime path worked with Bun.
+
+## Environment
+
+- Node: v25.x (observed on v25.3.0)
+- tsx: 4.21.0
+- OS: macOS (repro also likely on other platforms that run Node 25)
+
+## Repro (Node-only)
+
+```bash
+# in repo root
+node --version
+pnpm install
+node --import tsx src/entry.ts status
+```
+
+## Minimal repro in repo
+
+```bash
+node --import tsx scripts/repro/tsx-name-repro.ts
+```
+
+## Node version check
+
+- Node 25.3.0: fails
+- Node 22.22.0 (Homebrew `node@22`): fails
+- Node 24: not installed here yet; needs verification
+
+## Notes / hypothesis
+
+- `tsx` uses esbuild to transform TS/ESM. esbuild’s `keepNames` emits a `__name` helper and wraps function definitions with `__name(...)`.
+- The crash indicates `__name` exists but is not a function at runtime, which implies the helper is missing or overwritten for this module in the Node 25 loader path.
+- Similar `__name` helper issues have been reported in other esbuild consumers when the helper is missing or rewritten.
+
+## Regression history
+
+- `2871657e` (2026-01-06): scripts changed from Bun to tsx to make Bun optional.
+- Before that (Bun path), `quantumclaw status` and `gateway:watch` worked.
+
+## Workarounds
+
+- Use Bun for dev scripts (current temporary revert).
+- Use Node + tsc watch, then run compiled output:
+
+  ```bash
+  pnpm exec tsc --watch --preserveWatchOutput
+  node --watch quantumclaw.mjs status
+  ```
+
+- Confirmed locally: `pnpm exec tsc -p tsconfig.json` + `node quantumclaw.mjs status` works on Node 25.
+- Disable esbuild keepNames in the TS loader if possible (prevents `__name` helper insertion); tsx does not currently expose this.
+- Test Node LTS (22/24) with `tsx` to see if the issue is Node 25–specific.
+
+## References
+
+- [https://opennext.js.org/cloudflare/howtos/keep_names](https://opennext.js.org/cloudflare/howtos/keep_names)
+- [https://esbuild.github.io/api/#keep-names](https://esbuild.github.io/api/#keep-names)
+- [https://github.com/evanw/esbuild/issues/1031](https://github.com/evanw/esbuild/issues/1031)
+
+## Next steps
+
+- Repro on Node 22/24 to confirm Node 25 regression.
+- Test `tsx` nightly or pin to earlier version if a known regression exists.
+- If reproduces on Node LTS, file a minimal repro upstream with the `__name` stack trace.

package/docs/diagnostics/flags.md

@@ -0,0 +1,91 @@
+---
+summary: "Diagnostics flags for targeted debug logs"
+read_when:
+  - You need targeted debug logs without raising global logging levels
+  - You need to capture subsystem-specific logs for support
+title: "Diagnostics Flags"
+---
+
+# Diagnostics Flags
+
+Diagnostics flags let you enable targeted debug logs without turning on verbose logging everywhere. Flags are opt-in and have no effect unless a subsystem checks them.
+
+## How it works
+
+- Flags are strings (case-insensitive).
+- You can enable flags in config or via an env override.
+- Wildcards are supported:
+  - `telegram.*` matches `telegram.http`
+  - `*` enables all flags
+
+## Enable via config
+
+```json
+{
+  "diagnostics": {
+    "flags": ["telegram.http"]
+  }
+}
+```
+
+Multiple flags:
+
+```json
+{
+  "diagnostics": {
+    "flags": ["telegram.http", "gateway.*"]
+  }
+}
+```
+
+Restart the gateway after changing flags.
+
+## Env override (one-off)
+
+```bash
+QUANTUMCLAW_DIAGNOSTICS=telegram.http,telegram.payload
+```
+
+Disable all flags:
+
+```bash
+QUANTUMCLAW_DIAGNOSTICS=0
+```
+
+## Where logs go
+
+Flags emit logs into the standard diagnostics log file. By default:
+
+```
+/tmp/quantumclaw/quantumclaw-YYYY-MM-DD.log
+```
+
+If you set `logging.file`, use that path instead. Logs are JSONL (one JSON object per line). Redaction still applies based on `logging.redactSensitive`.
+
+## Extract logs
+
+Pick the latest log file:
+
+```bash
+ls -t /tmp/quantumclaw/quantumclaw-*.log | head -n 1
+```
+
+Filter for Telegram HTTP diagnostics:
+
+```bash
+rg "telegram http error" /tmp/quantumclaw/quantumclaw-*.log
+```
+
+Or tail while reproducing:
+
+```bash
+tail -f /tmp/quantumclaw/quantumclaw-$(date +%F).log | rg "telegram http error"
+```
+
+For remote gateways, you can also use `quantumclaw logs --follow` (see [/cli/logs](/cli/logs)).
+
+## Notes
+
+- If `logging.level` is set higher than `warn`, these logs may be suppressed. Default `info` is fine.
+- Flags are safe to leave enabled; they only affect log volume for the specific subsystem.
+- Use [/logging](/logging) to change log destinations, levels, and redaction.