Merge pull request #1256 from zknicker/feat/heartbeat-session-target

feat: configurable heartbeat session
This commit is contained in:
Peter Steinberger
2026-01-22 01:50:53 +00:00
committed by GitHub
15 changed files with 256 additions and 182 deletions

View File

@@ -14,6 +14,7 @@ Docs: https://docs.clawd.bot
## 2026.1.21
### Changes
- Heartbeat: allow running heartbeats in an explicit session key. (#1256) Thanks @zknicker.
- CLI: default exec approvals to the local host, add gateway/node targeting flags, and show target details in allowlist output.
- CLI: exec approvals mutations render tables instead of raw JSON.
- Exec approvals: support wildcard agent allowlists (`*`) across all agents.

View File

@@ -334,6 +334,7 @@ WhatsApp sends audio as **voice notes** (PTT bubble).
- `agents.defaults.heartbeat.model` (optional override)
- `agents.defaults.heartbeat.target`
- `agents.defaults.heartbeat.to`
- `agents.defaults.heartbeat.session`
- `agents.list[].heartbeat.*` (per-agent overrides)
- `session.*` (scope, idle, store, mainKey)
- `web.enabled` (disable channel startup when false)

View File

@@ -24,7 +24,7 @@ Unknown keys, malformed types, or invalid values cause the Gateway to **refuse t
When validation fails:
- The Gateway does not boot.
- Only diagnostic commands are allowed (for example: `clawdbot doctor`, `clawdbot logs`, `clawdbot health`, `clawdbot status`, `clawdbot gateway status`, `clawdbot gateway probe`, `clawdbot help`).
- Only diagnostic commands are allowed (for example: `clawdbot doctor`, `clawdbot logs`, `clawdbot health`, `clawdbot status`, `clawdbot service`, `clawdbot help`).
- Run `clawdbot doctor` to see the exact issues.
- Run `clawdbot doctor --fix` (or `--yes`) to apply migrations/repairs.
@@ -1414,7 +1414,7 @@ Each `agents.defaults.models` entry can include:
- `alias` (optional model shortcut, e.g. `/opus`).
- `params` (optional provider-specific API params passed through to the model request).
`params` is also applied to streaming runs (embedded agent + compaction). Supported keys today: `temperature`, `maxTokens`, `cacheControlTtl` (`"5m"` or `"1h"`, Anthropic API + OpenRouter Anthropic models only; ignored for Anthropic OAuth/Claude Code tokens). These merge with call-time options; caller-supplied values win. `temperature` is an advanced knob—leave unset unless you know the models defaults and need a change. Clawdbot includes the `extended-cache-ttl-2025-04-11` beta flag for Anthropic API; keep it if you override provider headers.
`params` is also applied to streaming runs (embedded agent + compaction). Supported keys today: `temperature`, `maxTokens`. These merge with call-time options; caller-supplied values win. `temperature` is an advanced knob—leave unset unless you know the models defaults and need a change.
Example:
@@ -1569,7 +1569,7 @@ Example:
}
```
#### `agents.defaults.contextPruning` (TTL-aware tool-result pruning)
#### `agents.defaults.contextPruning` (tool-result pruning)
`agents.defaults.contextPruning` prunes **old tool results** from the in-memory context right before a request is sent to the LLM.
It does **not** modify the session history on disk (`*.jsonl` remains complete).
@@ -1580,9 +1580,11 @@ High level:
- Never touches user/assistant messages.
- Protects the last `keepLastAssistants` assistant messages (no tool results after that point are pruned).
- Protects the bootstrap prefix (nothing before the first user message is pruned).
- Mode:
- `cache-ttl`: pruning only runs when the last Anthropic call for the session is **older** than `ttl`.
When it runs, it uses the same soft-trim + hard-clear behavior as before.
- Modes:
- `adaptive`: soft-trims oversized tool results (keep head/tail) when the estimated context ratio crosses `softTrimRatio`.
Then hard-clears the oldest eligible tool results when the estimated context ratio crosses `hardClearRatio` **and**
theres enough prunable tool-result bulk (`minPrunableToolChars`).
- `aggressive`: always replaces eligible tool results before the cutoff with the `hardClear.placeholder` (no ratio checks).
Soft vs hard pruning (what changes in the context sent to the LLM):
- **Soft-trim**: only for *oversized* tool results. Keeps the beginning + end and inserts `...` in the middle.
@@ -1596,41 +1598,44 @@ Notes / current limitations:
- Tool results containing **image blocks are skipped** (never trimmed/cleared) right now.
- The estimated “context ratio” is based on **characters** (approximate), not exact tokens.
- If the session doesnt contain at least `keepLastAssistants` assistant messages yet, pruning is skipped.
- `cache-ttl` only activates for Anthropic API calls (and OpenRouter Anthropic models).
- After a prune, the TTL window resets so subsequent requests keep cache until `ttl` expires again.
- For best results, match `contextPruning.ttl` to the model `cacheControlTtl` you set in `agents.defaults.models.*.params`.
- In `aggressive` mode, `hardClear.enabled` is ignored (eligible tool results are always replaced with `hardClear.placeholder`).
Default (off, unless Anthropic auth profiles are detected):
Default (adaptive):
```json5
{
agents: { defaults: { contextPruning: { mode: "adaptive" } } }
}
```
To disable:
```json5
{
agents: { defaults: { contextPruning: { mode: "off" } } }
}
```
Enable TTL-aware pruning:
Defaults (when `mode` is `"adaptive"` or `"aggressive"`):
- `keepLastAssistants`: `3`
- `softTrimRatio`: `0.3` (adaptive only)
- `hardClearRatio`: `0.5` (adaptive only)
- `minPrunableToolChars`: `50000` (adaptive only)
- `softTrim`: `{ maxChars: 4000, headChars: 1500, tailChars: 1500 }` (adaptive only)
- `hardClear`: `{ enabled: true, placeholder: "[Old tool result content cleared]" }`
Example (aggressive, minimal):
```json5
{
agents: { defaults: { contextPruning: { mode: "cache-ttl" } } }
agents: { defaults: { contextPruning: { mode: "aggressive" } } }
}
```
Defaults (when `mode` is `"cache-ttl"`):
- `ttl`: `"5m"`
- `keepLastAssistants`: `3`
- `softTrimRatio`: `0.3`
- `hardClearRatio`: `0.5`
- `minPrunableToolChars`: `50000`
- `softTrim`: `{ maxChars: 4000, headChars: 1500, tailChars: 1500 }`
- `hardClear`: `{ enabled: true, placeholder: "[Old tool result content cleared]" }`
Example (cache-ttl tuned):
Example (adaptive tuned):
```json5
{
agents: {
defaults: {
contextPruning: {
mode: "cache-ttl",
ttl: "5m",
mode: "adaptive",
keepLastAssistants: 3,
softTrimRatio: 0.3,
hardClearRatio: 0.5,
@@ -1737,12 +1742,9 @@ Z.AI models are available as `zai/<model>` (e.g. `zai/glm-4.7`) and require
`30m`. Set `0m` to disable.
- `model`: optional override model for heartbeat runs (`provider/model`).
- `includeReasoning`: when `true`, heartbeats will also deliver the separate `Reasoning:` message when available (same shape as `/reasoning on`). Default: `false`.
- `activeHours`: optional local-time window that controls when heartbeats run.
- `start`: start time (HH:MM, 24h). Inclusive.
- `end`: end time (HH:MM, 24h). Exclusive. Use `"24:00"` for end-of-day.
- `timezone`: `"user"` (default), `"local"`, or an IANA timezone id.
- `target`: optional delivery channel (`last`, `whatsapp`, `telegram`, `discord`, `slack`, `signal`, `imessage`, `none`). Default: `last`.
- `session`: optional session key to control which session the heartbeat runs in. Default: `main`.
- `to`: optional recipient override (channel-specific id, e.g. E.164 for WhatsApp, chat id for Telegram).
- `target`: optional delivery channel (`last`, `whatsapp`, `telegram`, `discord`, `slack`, `msteams`, `signal`, `imessage`, `none`). Default: `last`.
- `prompt`: optional override for the heartbeat body (default: `Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK.`). Overrides are sent verbatim; include a `Read HEARTBEAT.md` line if you still want the file read.
- `ackMaxChars`: max chars allowed after `HEARTBEAT_OK` before delivery (default: 300).
@@ -1773,7 +1775,6 @@ Note: `applyPatch` is only under `tools.exec`.
- `tools.web.fetch.maxChars` (default 50000)
- `tools.web.fetch.timeoutSeconds` (default 30)
- `tools.web.fetch.cacheTtlMinutes` (default 15)
- `tools.web.fetch.maxRedirects` (default 3)
- `tools.web.fetch.userAgent` (optional override)
- `tools.web.fetch.readability` (default true; disable to use basic HTML cleanup only)
- `tools.web.fetch.firecrawl.enabled` (default true when an API key is set)
@@ -1840,7 +1841,7 @@ Example:
`agents.defaults.subagents` configures sub-agent defaults:
- `model`: default model for spawned sub-agents (string or `{ primary, fallbacks }`). If omitted, sub-agents inherit the callers model unless overridden per agent or per call.
- `maxConcurrent`: max concurrent sub-agent runs (default 8)
- `maxConcurrent`: max concurrent sub-agent runs (default 1)
- `archiveAfterMinutes`: auto-archive sub-agent sessions after N minutes (default 60; set `0` to disable)
- Per-subagent tool policy: `tools.subagents.tools.allow` / `tools.subagents.tools.deny` (deny wins)
@@ -1974,7 +1975,7 @@ Notes:
`agents.defaults.maxConcurrent` sets the maximum number of embedded agent runs that can
execute in parallel across sessions. Each session is still serialized (one run
per session key at a time). Default: 4.
per session key at a time). Default: 1.
### `agents.defaults.sandbox`
@@ -2452,9 +2453,6 @@ Controls session scoping, reset policy, reset triggers, and where the session st
dm: { mode: "idle", idleMinutes: 240 },
group: { mode: "idle", idleMinutes: 120 }
},
resetByChannel: {
discord: { mode: "idle", idleMinutes: 10080 }
},
resetTriggers: ["/new", "/reset"],
// Default is already per-agent under ~/.clawdbot/agents/<agentId>/sessions/sessions.json
// You can override with {agentId} templating:
@@ -2490,7 +2488,7 @@ Fields:
- `idleMinutes`: sliding idle window in minutes. When daily + idle are both configured, whichever expires first wins.
- `resetByType`: per-session overrides for `dm`, `group`, and `thread`.
- If you only set legacy `session.idleMinutes` without any `reset`/`resetByType`, Clawdbot stays in idle-only mode for backward compatibility.
- `resetByChannel`: channel-specific reset policy overrides (keyed by channel id, applies to all session types for that channel; overrides `reset`/`resetByType`).
- `heartbeatIdleMinutes`: optional idle override for heartbeat checks (daily reset still applies when enabled).
- `agentToAgent.maxPingPongTurns`: max reply-back turns between requester/target (05, default 5).
- `sendPolicy.default`: `allow` or `deny` fallback when no rule matches.
- `sendPolicy.rules[]`: match by `channel`, `chatType` (`direct|group|room`), or `keyPrefix` (e.g. `cron:`). First deny wins; otherwise allow.
@@ -2617,13 +2615,10 @@ Defaults:
// noSandbox: false,
// executablePath: "/Applications/Brave Browser.app/Contents/MacOS/Brave Browser",
// attachOnly: false, // set true when tunneling a remote CDP to localhost
// snapshotDefaults: { mode: "efficient" }, // tool/CLI default snapshot preset
}
}
```
Note: `browser.snapshotDefaults` only affects Clawdbot's browser tool + CLI. Direct HTTP clients must pass `mode` explicitly.
### `ui` (Appearance)
Optional accent color used by the native apps for UI chrome (e.g. Talk Mode bubble tint).
@@ -2647,13 +2642,6 @@ Defaults:
- bind: `loopback`
- port: `18789` (single port for WS + HTTP)
Bind modes:
- `loopback`: `127.0.0.1` (local-only)
- `lan`: `0.0.0.0` (all interfaces)
- `tailnet`: Tailscale IPv4 address (100.64.0.0/10)
- `auto`: prefer loopback, fall back to LAN if loopback cannot bind
- `custom`: `gateway.customBindHost` (IPv4), fallback to LAN if unavailable
```json5
{
gateway: {
@@ -2684,15 +2672,14 @@ Notes:
- `clawdbot gateway` refuses to start unless `gateway.mode` is set to `local` (or you pass the override flag).
- `gateway.port` controls the single multiplexed port used for WebSocket + HTTP (control UI, hooks, A2UI).
- OpenAI Chat Completions endpoint: **disabled by default**; enable with `gateway.http.endpoints.chatCompletions.enabled: true`.
- OpenResponses endpoint: **disabled by default**; enable with `gateway.http.endpoints.responses.enabled: true`.
- Precedence: `--port` > `CLAWDBOT_GATEWAY_PORT` > `gateway.port` > default `18789`.
- Non-loopback binds (`lan`/`tailnet`/`custom`, or `auto` when loopback is unavailable) require auth. Use `gateway.auth.token` (or `CLAWDBOT_GATEWAY_TOKEN`).
- Non-loopback binds (`lan`/`tailnet`/`auto`) require auth. Use `gateway.auth.token` (or `CLAWDBOT_GATEWAY_TOKEN`).
- The onboarding wizard generates a gateway token by default (even on loopback).
- `gateway.remote.token` is **only** for remote CLI calls; it does not enable local gateway auth. `gateway.token` is ignored.
Auth and Tailscale:
- `gateway.auth.mode` sets the handshake requirements (`token` or `password`).
- `gateway.auth.token` stores the shared token for token auth (used by the CLI on the same machine and as the bootstrap credential for device pairing).
- `gateway.auth.token` stores the shared token for token auth (used by the CLI on the same machine).
- When `gateway.auth.mode` is set, only that method is accepted (plus optional Tailscale headers).
- `gateway.auth.password` can be set here, or via `CLAWDBOT_GATEWAY_PASSWORD` (recommended).
- `gateway.auth.allowTailscale` allows Tailscale Serve identity headers
@@ -2701,9 +2688,6 @@ Auth and Tailscale:
`true`, Serve requests do not need a token/password; set `false` to require
explicit credentials. Defaults to `true` when `tailscale.mode = "serve"` and
auth mode is not `password`.
- After pairing, the Gateway issues **device tokens** scoped to the device role + scopes.
These are returned in `hello-ok.auth.deviceToken`; clients should persist and reuse them
instead of the shared token. Rotate/revoke via `device.token.rotate`/`device.token.revoke`.
- `gateway.tailscale.mode: "serve"` uses Tailscale Serve (tailnet only, loopback bind).
- `gateway.tailscale.mode: "funnel"` exposes the dashboard publicly; requires auth.
- `gateway.tailscale.resetOnExit` resets Serve/Funnel config on shutdown.
@@ -2712,7 +2696,6 @@ Remote client defaults (CLI):
- `gateway.remote.url` sets the default Gateway WebSocket URL for CLI calls when `gateway.mode = "remote"`.
- `gateway.remote.token` supplies the token for remote calls (leave unset for no auth).
- `gateway.remote.password` supplies the password for remote calls (leave unset for no auth).
- `gateway.remote.tlsFingerprint` pins the gateway TLS cert fingerprint (sha256).
macOS app behavior:
- Clawdbot.app watches `~/.clawdbot/clawdbot.json` and switches modes live when `gateway.mode` or `gateway.remote.url` changes.
@@ -2726,36 +2709,12 @@ macOS app behavior:
remote: {
url: "ws://gateway.tailnet:18789",
token: "your-token",
password: "your-password",
tlsFingerprint: "sha256:ab12cd34..."
password: "your-password"
}
}
}
```
### `gateway.nodes` (Node command allowlist)
The Gateway enforces a per-platform command allowlist for `node.invoke`. Nodes must both
**declare** a command and have it **allowed** by the Gateway to run it.
Use this section to extend or deny commands:
```json5
{
gateway: {
nodes: {
allowCommands: ["custom.vendor.command"], // extra commands beyond defaults
denyCommands: ["sms.send"] // block a command even if declared
}
}
}
```
Notes:
- `allowCommands` extends the built-in per-platform defaults.
- `denyCommands` always wins (even if the node claims the command).
- `node.invoke` rejects commands that are not declared by the node.
### `gateway.reload` (Config hot reload)
The Gateway watches `~/.clawdbot/clawdbot.json` (or `CLAWDBOT_CONFIG_PATH`) and applies changes automatically.
@@ -3003,7 +2962,7 @@ Auto-generated certs require `openssl` on PATH; if generation fails, the bridge
### `discovery.wideArea` (Wide-Area Bonjour / unicast DNSSD)
When enabled, the Gateway writes a unicast DNS-SD zone for `_clawdbot-gw._tcp` under `~/.clawdbot/dns/` using the standard discovery domain `clawdbot.internal.`
When enabled, the Gateway writes a unicast DNS-SD zone for `_clawdbot-bridge._tcp` under `~/.clawdbot/dns/` using the standard discovery domain `clawdbot.internal.`
To make iOS/Android discover across networks (Vienna ⇄ London), pair this with:
- a DNS server on the gateway host serving `clawdbot.internal.` (CoreDNS is recommended)
@@ -3033,9 +2992,6 @@ Template placeholders are expanded in `tools.media.*.models[].args` and `tools.m
| `{{From}}` | Sender identifier (E.164 for WhatsApp; may differ per channel) |
| `{{To}}` | Destination identifier |
| `{{MessageSid}}` | Channel message id (when available) |
| `{{MessageSidFull}}` | Provider-specific full message id when `MessageSid` is shortened |
| `{{ReplyToId}}` | Reply-to message id (when available) |
| `{{ReplyToIdFull}}` | Provider-specific full reply-to id when `ReplyToId` is shortened |
| `{{SessionId}}` | Current session UUID |
| `{{IsNewSession}}` | `"true"` when a new session was created |
| `{{MediaUrl}}` | Inbound media pseudo-URL (if present) |

View File

@@ -127,18 +127,26 @@ Example: two agents, only the second agent runs heartbeats.
- `every`: heartbeat interval (duration string; default unit = minutes).
- `model`: optional model override for heartbeat runs (`provider/model`).
- `includeReasoning`: when enabled, also deliver the separate `Reasoning:` message when available (same shape as `/reasoning on`).
- `session`: optional session key for heartbeat runs.
- `main` (default): agent main session.
- Explicit session key (copy from `clawdbot sessions --json` or the [sessions CLI](/cli/sessions)).
- Session key formats: see [Sessions](/concepts/session) and [Groups](/concepts/groups).
- `target`:
- `last` (default): deliver to the last used external channel.
- explicit channel: `whatsapp` / `telegram` / `discord` / `slack` / `signal` / `imessage`.
- explicit channel: `whatsapp` / `telegram` / `discord` / `slack` / `msteams` / `signal` / `imessage`.
- `none`: run the heartbeat but **do not deliver** externally.
- `to`: optional recipient override (E.164 for WhatsApp, chat id for Telegram, etc.).
- `to`: optional recipient override (channel-specific id, e.g. E.164 for WhatsApp or a Telegram chat id).
- `prompt`: overrides the default prompt body (not merged).
- `ackMaxChars`: max chars allowed after `HEARTBEAT_OK` before delivery.
## Delivery behavior
- Heartbeats run in each agents **main session** (`agent:<id>:<mainKey>`), or `global`
when `session.scope = "global"`.
- Heartbeats run in the agents main session by default (`agent:<id>:<mainKey>`),
or `global` when `session.scope = "global"`. Set `session` to override to a
specific channel session (Discord/WhatsApp/etc.).
- `session` only affects the run context; delivery is controlled by `target` and `to`.
- To deliver to a specific channel/recipient, set `target` + `to`. With
`target: "last"`, delivery uses the last external channel for that session.
- If the main queue is busy, the heartbeat is skipped and retried later.
- If `target` resolves to no external destination, the run still happens but no
outbound message is sent.

View File

@@ -60,7 +60,7 @@ describe("directive behavior", () => {
vi.restoreAllMocks();
});
it("moves /model list to /models", async () => {
it("aliases /model list to /models", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockReset();
const storePath = path.join(home, "sessions.json");
@@ -84,13 +84,15 @@ describe("directive behavior", () => {
);
const text = Array.isArray(res) ? res[0]?.text : res?.text;
expect(text).toContain("Model listing moved.");
expect(text).toContain("Use: /models (providers) or /models <provider> (models)");
expect(text).toContain("Providers:");
expect(text).toContain("- anthropic");
expect(text).toContain("- openai");
expect(text).toContain("Use: /models <provider>");
expect(text).toContain("Switch: /model <provider/model>");
expect(runEmbeddedPiAgent).not.toHaveBeenCalled();
});
});
it("shows summary on /model when catalog is unavailable", async () => {
it("shows current model when catalog is unavailable", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockReset();
vi.mocked(loadModelCatalog).mockResolvedValueOnce([]);
@@ -122,10 +124,10 @@ describe("directive behavior", () => {
expect(runEmbeddedPiAgent).not.toHaveBeenCalled();
});
});
it("moves /model list to /models even when no allowlist is set", async () => {
it("includes catalog providers when no allowlist is set", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockReset();
vi.mocked(loadModelCatalog).mockResolvedValueOnce([
vi.mocked(loadModelCatalog).mockResolvedValue([
{ id: "claude-opus-4-5", name: "Opus 4.5", provider: "anthropic" },
{ id: "gpt-4.1-mini", name: "GPT-4.1 Mini", provider: "openai" },
{ id: "grok-4", name: "Grok 4", provider: "xai" },
@@ -151,13 +153,15 @@ describe("directive behavior", () => {
);
const text = Array.isArray(res) ? res[0]?.text : res?.text;
expect(text).toContain("Model listing moved.");
expect(text).toContain("Use: /models (providers) or /models <provider> (models)");
expect(text).toContain("Switch: /model <provider/model>");
expect(text).toContain("Providers:");
expect(text).toContain("- anthropic");
expect(text).toContain("- openai");
expect(text).toContain("- xai");
expect(text).toContain("Use: /models <provider>");
expect(runEmbeddedPiAgent).not.toHaveBeenCalled();
});
});
it("moves /model list to /models even when catalog is present", async () => {
it("lists config-only providers when catalog is present", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockReset();
// Catalog present but missing custom providers: /model should still include
@@ -173,7 +177,7 @@ describe("directive behavior", () => {
const storePath = path.join(home, "sessions.json");
const res = await getReplyFromConfig(
{ Body: "/model list", From: "+1222", To: "+1222", CommandAuthorized: true },
{ Body: "/models minimax", From: "+1222", To: "+1222", CommandAuthorized: true },
{},
{
agents: {
@@ -202,13 +206,12 @@ describe("directive behavior", () => {
);
const text = Array.isArray(res) ? res[0]?.text : res?.text;
expect(text).toContain("Model listing moved.");
expect(text).toContain("Use: /models (providers) or /models <provider> (models)");
expect(text).toContain("Switch: /model <provider/model>");
expect(text).toContain("Model set to minimax");
expect(text).toContain("minimax/MiniMax-M2.1");
expect(runEmbeddedPiAgent).not.toHaveBeenCalled();
});
});
it("moves /model list to /models without listing auth labels", async () => {
it("does not repeat missing auth labels on /model list", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockReset();
const storePath = path.join(home, "sessions.json");
@@ -231,9 +234,7 @@ describe("directive behavior", () => {
);
const text = Array.isArray(res) ? res[0]?.text : res?.text;
expect(text).toContain("Model listing moved.");
expect(text).toContain("Use: /models (providers) or /models <provider> (models)");
expect(text).toContain("Switch: /model <provider/model>");
expect(text).toContain("Providers:");
expect(text).not.toContain("missing (missing)");
expect(runEmbeddedPiAgent).not.toHaveBeenCalled();
});

View File

@@ -215,6 +215,7 @@ describe("directive behavior", () => {
expect(text).toContain("Switch: /model <provider/model>");
expect(text).toContain("Browse: /models (providers) or /models <provider> (models)");
expect(text).toContain("More: /model status");
expect(text).not.toContain("openai/gpt-4.1-mini");
expect(runEmbeddedPiAgent).not.toHaveBeenCalled();
});
});

View File

@@ -123,7 +123,7 @@ describe("trigger handling", () => {
expect(normalized).not.toContain("image");
});
});
it("moves /model list to /models", async () => {
it("aliases /model list to /models", async () => {
await withTempHome(async (home) => {
const cfg = makeCfg(home);
const res = await getReplyFromConfig(
@@ -143,8 +143,8 @@ describe("trigger handling", () => {
const text = Array.isArray(res) ? res[0]?.text : res?.text;
const normalized = normalizeTestText(text ?? "");
expect(normalized).toContain("Model listing moved.");
expect(normalized).toContain("Use: /models (providers) or /models <provider> (models)");
expect(normalized).toContain("Providers:");
expect(normalized).toContain("Use: /models <provider>");
expect(normalized).toContain("Switch: /model <provider/model>");
});
});

View File

@@ -7,6 +7,7 @@ import {
resolveModelRefFromString,
} from "../../agents/model-selection.js";
import { DEFAULT_MODEL, DEFAULT_PROVIDER } from "../../agents/defaults.js";
import type { ClawdbotConfig } from "../../config/config.js";
import type { ReplyPayload } from "../types.js";
import type { CommandHandler } from "./commands-types.js";
@@ -68,10 +69,11 @@ function parseModelsArgs(raw: string): {
};
}
export const handleModelsCommand: CommandHandler = async (params, allowTextCommands) => {
if (!allowTextCommands) return null;
const body = params.command.commandBodyNormalized.trim();
export async function resolveModelsCommandReply(params: {
cfg: ClawdbotConfig;
commandBodyNormalized: string;
}): Promise<ReplyPayload | null> {
const body = params.commandBodyNormalized.trim();
if (!body.startsWith("/models")) return null;
const argText = body.replace(/^\/models\b/i, "").trim();
@@ -164,7 +166,7 @@ export const handleModelsCommand: CommandHandler = async (params, allowTextComma
"Use: /models <provider>",
"Switch: /model <provider/model>",
];
return { reply: { text: lines.join("\n") }, shouldContinue: false };
return { text: lines.join("\n") };
}
if (!byProvider.has(provider)) {
@@ -176,7 +178,7 @@ export const handleModelsCommand: CommandHandler = async (params, allowTextComma
"",
"Use: /models <provider>",
];
return { reply: { text: lines.join("\n") }, shouldContinue: false };
return { text: lines.join("\n") };
}
const models = [...(byProvider.get(provider) ?? new Set<string>())].sort();
@@ -189,7 +191,7 @@ export const handleModelsCommand: CommandHandler = async (params, allowTextComma
"Browse: /models",
"Switch: /model <provider/model>",
];
return { reply: { text: lines.join("\n") }, shouldContinue: false };
return { text: lines.join("\n") };
}
const effectivePageSize = all ? total : pageSize;
@@ -203,7 +205,7 @@ export const handleModelsCommand: CommandHandler = async (params, allowTextComma
`Try: /models ${provider} ${safePage}`,
`All: /models ${provider} all`,
];
return { reply: { text: lines.join("\n") }, shouldContinue: false };
return { text: lines.join("\n") };
}
const startIndex = (safePage - 1) * effectivePageSize;
@@ -226,5 +228,16 @@ export const handleModelsCommand: CommandHandler = async (params, allowTextComma
}
const payload: ReplyPayload = { text: lines.join("\n") };
return { reply: payload, shouldContinue: false };
return payload;
}
export const handleModelsCommand: CommandHandler = async (params, allowTextCommands) => {
if (!allowTextCommands) return null;
const reply = await resolveModelsCommandReply({
cfg: params.cfg,
commandBodyNormalized: params.command.commandBodyNormalized,
});
if (!reply) return null;
return { reply, shouldContinue: false };
};

View File

@@ -36,7 +36,7 @@ describe("/model chat UX", () => {
expect(reply?.text).toContain("Switch: /model <provider/model>");
});
it("suggests closest match for typos without switching", () => {
it("auto-applies closest match for typos", () => {
const directives = parseInlineDirectives("/model anthropic/claud-opus-4-5");
const cfg = { commands: { text: true } } as unknown as ClawdbotConfig;
@@ -52,9 +52,11 @@ describe("/model chat UX", () => {
provider: "anthropic",
});
expect(resolved.modelSelection).toBeUndefined();
expect(resolved.errorText).toContain("Did you mean:");
expect(resolved.errorText).toContain("anthropic/claude-opus-4-5");
expect(resolved.errorText).toContain("Try: /model anthropic/claude-opus-4-5");
expect(resolved.modelSelection).toEqual({
provider: "anthropic",
model: "claude-opus-4-5",
isDefault: true,
});
expect(resolved.errorText).toBeUndefined();
});
});

View File

@@ -20,6 +20,7 @@ import {
resolveProviderEndpointLabel,
} from "./directive-handling.model-picker.js";
import type { InlineDirectives } from "./directive-handling.parse.js";
import { resolveModelsCommandReply } from "./commands-models.js";
import { type ModelDirectiveSelection, resolveModelDirectiveSelection } from "./model-selection.js";
function buildModelPickerCatalog(params: {
@@ -185,14 +186,11 @@ export async function maybeHandleModelDirectiveInfo(params: {
});
if (wantsLegacyList) {
return {
text: [
"Model listing moved.",
"",
"Use: /models (providers) or /models <provider> (models)",
"Switch: /model <provider/model>",
].join("\n"),
};
const reply = await resolveModelsCommandReply({
cfg: params.cfg,
commandBodyNormalized: "/models",
});
return reply ?? { text: "No models available." };
}
if (wantsSummary) {
@@ -340,42 +338,7 @@ export function resolveModelSelectionFromDirective(params: {
}
if (resolved.selection) {
const suggestion = `${resolved.selection.provider}/${resolved.selection.model}`;
const rawHasSlash = raw.includes("/");
const shouldAutoSelect = (() => {
if (!rawHasSlash) return true;
const slash = raw.indexOf("/");
if (slash <= 0) return true;
const rawProvider = normalizeProviderId(raw.slice(0, slash));
const rawFragment = raw
.slice(slash + 1)
.trim()
.toLowerCase();
if (!rawFragment) return false;
const resolvedProvider = normalizeProviderId(resolved.selection.provider);
if (rawProvider !== resolvedProvider) return false;
const resolvedModel = resolved.selection.model.toLowerCase();
return (
resolvedModel.startsWith(rawFragment) ||
resolvedModel.includes(rawFragment) ||
rawFragment.startsWith(resolvedModel)
);
})();
if (shouldAutoSelect) {
modelSelection = resolved.selection;
} else {
return {
errorText: [
`Unrecognized model: ${raw}`,
"",
`Did you mean: ${suggestion}`,
`Try: /model ${suggestion}`,
"",
"Browse: /models or /models <provider>",
].join("\n"),
};
}
modelSelection = resolved.selection;
}
}

View File

@@ -173,6 +173,8 @@ export type AgentDefaultsConfig = {
};
/** Heartbeat model override (provider/model). */
model?: string;
/** Session key for heartbeat runs ("main" or explicit session key). */
session?: string;
/** Delivery target (last|whatsapp|telegram|discord|slack|msteams|signal|imessage|none). */
target?:
| "last"

View File

@@ -20,6 +20,7 @@ export const HeartbeatSchema = z
.strict()
.optional(),
model: z.string().optional(),
session: z.string().optional(),
includeReasoning: z.boolean().optional(),
target: z
.union([

View File

@@ -41,7 +41,6 @@ describe("resolveHeartbeatIntervalMs", () => {
heartbeat: {
every: "5m",
target: "whatsapp",
to: "+1555",
ackMaxChars: 0,
},
},
@@ -58,6 +57,7 @@ describe("resolveHeartbeatIntervalMs", () => {
[sessionKey]: {
sessionId: "sid",
updatedAt: Date.now(),
lastChannel: "whatsapp",
lastProvider: "whatsapp",
lastTo: "+1555",
},
@@ -102,7 +102,6 @@ describe("resolveHeartbeatIntervalMs", () => {
heartbeat: {
every: "5m",
target: "whatsapp",
to: "+1555",
},
},
},
@@ -118,6 +117,7 @@ describe("resolveHeartbeatIntervalMs", () => {
[sessionKey]: {
sessionId: "sid",
updatedAt: Date.now(),
lastChannel: "whatsapp",
lastProvider: "whatsapp",
lastTo: "+1555",
},
@@ -164,7 +164,6 @@ describe("resolveHeartbeatIntervalMs", () => {
heartbeat: {
every: "5m",
target: "whatsapp",
to: "+1555",
},
},
},
@@ -180,6 +179,7 @@ describe("resolveHeartbeatIntervalMs", () => {
[sessionKey]: {
sessionId: "sid",
updatedAt: originalUpdatedAt,
lastChannel: "whatsapp",
lastProvider: "whatsapp",
lastTo: "+1555",
},
@@ -231,7 +231,7 @@ describe("resolveHeartbeatIntervalMs", () => {
const cfg: ClawdbotConfig = {
agents: {
defaults: {
heartbeat: { every: "5m", target: "whatsapp", to: "+1555" },
heartbeat: { every: "5m", target: "whatsapp" },
},
},
channels: { whatsapp: { allowFrom: ["*"] } },
@@ -246,6 +246,7 @@ describe("resolveHeartbeatIntervalMs", () => {
[sessionKey]: {
sessionId: "sid",
updatedAt: Date.now(),
lastChannel: "whatsapp",
lastProvider: "whatsapp",
lastTo: "+1555",
},
@@ -291,7 +292,7 @@ describe("resolveHeartbeatIntervalMs", () => {
const cfg: ClawdbotConfig = {
agents: {
defaults: {
heartbeat: { every: "5m", target: "telegram", to: "123456" },
heartbeat: { every: "5m", target: "telegram" },
},
},
channels: { telegram: { botToken: "test-bot-token-123" } },
@@ -306,6 +307,7 @@ describe("resolveHeartbeatIntervalMs", () => {
[sessionKey]: {
sessionId: "sid",
updatedAt: Date.now(),
lastChannel: "telegram",
lastProvider: "telegram",
lastTo: "123456",
},
@@ -357,7 +359,7 @@ describe("resolveHeartbeatIntervalMs", () => {
const cfg: ClawdbotConfig = {
agents: {
defaults: {
heartbeat: { every: "5m", target: "telegram", to: "123456" },
heartbeat: { every: "5m", target: "telegram" },
},
},
channels: {
@@ -378,6 +380,7 @@ describe("resolveHeartbeatIntervalMs", () => {
[sessionKey]: {
sessionId: "sid",
updatedAt: Date.now(),
lastChannel: "telegram",
lastProvider: "telegram",
lastTo: "123456",
},

View File

@@ -11,6 +11,7 @@ import {
resolveMainSessionKey,
resolveStorePath,
} from "../config/sessions.js";
import { buildAgentPeerSessionKey } from "../routing/session-key.js";
import {
isHeartbeatEnabledForAgent,
resolveHeartbeatIntervalMs,
@@ -332,7 +333,7 @@ describe("runHeartbeatOnce", () => {
const cfg: ClawdbotConfig = {
agents: {
defaults: {
heartbeat: { every: "5m", target: "whatsapp", to: "+1555" },
heartbeat: { every: "5m", target: "whatsapp" },
},
},
channels: { whatsapp: { allowFrom: ["*"] } },
@@ -395,7 +396,7 @@ describe("runHeartbeatOnce", () => {
{ id: "main", default: true },
{
id: "ops",
heartbeat: { every: "5m", target: "whatsapp", to: "+1555", prompt: "Ops check" },
heartbeat: { every: "5m", target: "whatsapp", prompt: "Ops check" },
},
],
},
@@ -451,6 +452,88 @@ describe("runHeartbeatOnce", () => {
}
});
it("runs heartbeats in the explicit session key when configured", async () => {
const tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-hb-"));
const storePath = path.join(tmpDir, "sessions.json");
const replySpy = vi.spyOn(replyModule, "getReplyFromConfig");
try {
const groupId = "120363401234567890@g.us";
const cfg: ClawdbotConfig = {
agents: {
defaults: {
heartbeat: {
every: "5m",
target: "last",
},
},
},
channels: { whatsapp: { allowFrom: ["*"] } },
session: { store: storePath },
};
const mainSessionKey = resolveMainSessionKey(cfg);
const agentId = resolveAgentIdFromSessionKey(mainSessionKey);
const groupSessionKey = buildAgentPeerSessionKey({
agentId,
channel: "whatsapp",
peerKind: "group",
peerId: groupId,
});
if (cfg.agents?.defaults?.heartbeat) {
cfg.agents.defaults.heartbeat.session = groupSessionKey;
}
await fs.writeFile(
storePath,
JSON.stringify(
{
[mainSessionKey]: {
sessionId: "sid-main",
updatedAt: Date.now(),
lastChannel: "whatsapp",
lastTo: "+1555",
},
[groupSessionKey]: {
sessionId: "sid-group",
updatedAt: Date.now() + 10_000,
lastChannel: "whatsapp",
lastTo: groupId,
},
},
null,
2,
),
);
replySpy.mockResolvedValue([{ text: "Group alert" }]);
const sendWhatsApp = vi.fn().mockResolvedValue({
messageId: "m1",
toJid: "jid",
});
await runHeartbeatOnce({
cfg,
deps: {
sendWhatsApp,
getQueueSize: () => 0,
nowMs: () => 0,
webAuthExists: async () => true,
hasActiveWebListener: () => true,
},
});
expect(sendWhatsApp).toHaveBeenCalledTimes(1);
expect(sendWhatsApp).toHaveBeenCalledWith(groupId, "Group alert", expect.any(Object));
expect(replySpy).toHaveBeenCalledWith(
expect.objectContaining({ SessionKey: groupSessionKey }),
{ isHeartbeat: true },
cfg,
);
} finally {
replySpy.mockRestore();
await fs.rm(tmpDir, { recursive: true, force: true });
}
});
it("suppresses duplicate heartbeat payloads within 24h", async () => {
const tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), "clawdbot-hb-"));
const storePath = path.join(tmpDir, "sessions.json");
@@ -459,7 +542,7 @@ describe("runHeartbeatOnce", () => {
const cfg: ClawdbotConfig = {
agents: {
defaults: {
heartbeat: { every: "5m", target: "whatsapp", to: "+1555" },
heartbeat: { every: "5m", target: "whatsapp" },
},
},
channels: { whatsapp: { allowFrom: ["*"] } },
@@ -517,7 +600,6 @@ describe("runHeartbeatOnce", () => {
heartbeat: {
every: "5m",
target: "whatsapp",
to: "+1555",
includeReasoning: true,
},
},
@@ -534,6 +616,7 @@ describe("runHeartbeatOnce", () => {
[sessionKey]: {
sessionId: "sid",
updatedAt: Date.now(),
lastChannel: "whatsapp",
lastProvider: "whatsapp",
lastTo: "+1555",
},
@@ -588,7 +671,6 @@ describe("runHeartbeatOnce", () => {
heartbeat: {
every: "5m",
target: "whatsapp",
to: "+1555",
includeReasoning: true,
},
},
@@ -605,6 +687,7 @@ describe("runHeartbeatOnce", () => {
[sessionKey]: {
sessionId: "sid",
updatedAt: Date.now(),
lastChannel: "whatsapp",
lastProvider: "whatsapp",
lastTo: "+1555",
},
@@ -672,6 +755,7 @@ describe("runHeartbeatOnce", () => {
[sessionKey]: {
sessionId: "sid",
updatedAt: Date.now(),
lastChannel: "whatsapp",
lastProvider: "whatsapp",
lastTo: "+1555",
},

View File

@@ -15,7 +15,9 @@ import { parseDurationMs } from "../cli/parse-duration.js";
import type { ClawdbotConfig } from "../config/config.js";
import { loadConfig } from "../config/config.js";
import {
canonicalizeMainSessionAlias,
loadSessionStore,
resolveAgentIdFromSessionKey,
resolveAgentMainSessionKey,
resolveStorePath,
saveSessionStore,
@@ -27,7 +29,7 @@ import { createSubsystemLogger } from "../logging/subsystem.js";
import { getQueueSize } from "../process/command-queue.js";
import { CommandLane } from "../process/lanes.js";
import { defaultRuntime, type RuntimeEnv } from "../runtime.js";
import { normalizeAgentId } from "../routing/session-key.js";
import { normalizeAgentId, toAgentStoreSessionKey } from "../routing/session-key.js";
import { emitHeartbeatEvent } from "./heartbeat-events.js";
import {
type HeartbeatRunResult,
@@ -286,17 +288,53 @@ function resolveHeartbeatAckMaxChars(cfg: ClawdbotConfig, heartbeat?: HeartbeatC
);
}
function resolveHeartbeatSession(cfg: ClawdbotConfig, agentId?: string) {
function resolveHeartbeatSession(
cfg: ClawdbotConfig,
agentId?: string,
heartbeat?: HeartbeatConfig,
) {
const sessionCfg = cfg.session;
const scope = sessionCfg?.scope ?? "per-sender";
const resolvedAgentId = normalizeAgentId(agentId ?? resolveDefaultAgentId(cfg));
const sessionKey =
const mainSessionKey =
scope === "global" ? "global" : resolveAgentMainSessionKey({ cfg, agentId: resolvedAgentId });
const storeAgentId = scope === "global" ? resolveDefaultAgentId(cfg) : resolvedAgentId;
const storePath = resolveStorePath(sessionCfg?.store, { agentId: storeAgentId });
const store = loadSessionStore(storePath);
const entry = store[sessionKey];
return { sessionKey, storePath, store, entry };
const mainEntry = store[mainSessionKey];
if (scope === "global") {
return { sessionKey: mainSessionKey, storePath, store, entry: mainEntry };
}
const trimmed = heartbeat?.session?.trim() ?? "";
if (!trimmed) {
return { sessionKey: mainSessionKey, storePath, store, entry: mainEntry };
}
const normalized = trimmed.toLowerCase();
if (normalized === "main" || normalized === "global") {
return { sessionKey: mainSessionKey, storePath, store, entry: mainEntry };
}
const candidate = toAgentStoreSessionKey({
agentId: resolvedAgentId,
requestKey: trimmed,
mainKey: cfg.session?.mainKey,
});
const canonical = canonicalizeMainSessionAlias({
cfg,
agentId: resolvedAgentId,
sessionKey: candidate,
});
if (canonical !== "global") {
const sessionAgentId = resolveAgentIdFromSessionKey(canonical);
if (sessionAgentId === normalizeAgentId(resolvedAgentId)) {
return { sessionKey: canonical, storePath, store, entry: store[canonical] };
}
}
return { sessionKey: mainSessionKey, storePath, store, entry: mainEntry };
}
function resolveHeartbeatReplyPayload(
@@ -427,7 +465,7 @@ export async function runHeartbeatOnce(opts: {
return { status: "skipped", reason: "requests-in-flight" };
}
const { entry, sessionKey, storePath } = resolveHeartbeatSession(cfg, agentId);
const { entry, sessionKey, storePath } = resolveHeartbeatSession(cfg, agentId, heartbeat);
const previousUpdatedAt = entry?.updatedAt;
const delivery = resolveHeartbeatDeliveryTarget({ cfg, entry, heartbeat });
const lastChannel = delivery.lastChannel;