@ducci/jarvis 1.0.45 → 1.0.47

package/docs/crons.md

@@ -51,7 +51,7 @@ For one-time tasks specified as relative times ("in 2 hours", "at 3pm today"), t
 
 Notification is opt-in via the prompt. Include this in the prompt when you want a notification:
 
-> "When done, use `send_telegram_message` to notify the user with the result."
+> "When done, use `send_telegram_message` to notify the user with the result. Prefix the message with [Cron: \"backup-nightly\" | <current timestamp>]."
 
 If you don't want a notification, omit it. The agent follows the prompt literally — conditional notifications work naturally:
 
@@ -59,7 +59,7 @@ If you don't want a notification, omit it. The agent follows the prompt literall
 
 ## Dynamic Scheduling
 
-When `create_cron` runs successfully, the agent loop immediately registers the new cron in the in-memory scheduler — no server restart required. `delete_cron` unregisters it immediately as well.
+When `create_cron`, `update_cron`, or `delete_cron` runs successfully, the agent loop immediately updates the in-memory scheduler — no server restart required.
 
 On server restart, all crons in `crons.json` are re-loaded and rescheduled. `once: true` crons that already fired (and deleted themselves) are gone from the file and will not re-run.
 
@@ -77,7 +77,7 @@ Each cron has its own JSONL log at `~/.jarvis/logs/cron-<id>.jsonl`. One entry p
 }
 ```
 
-Use `read_cron_log` to inspect past runs. Ask Jarvis "did my backup run last night?" and it will call `list_crons` + `read_cron_log`.
+Use `read_cron_log` with a cron id to inspect a specific cron, or without an id to get an overview of the last 8 active crons (5 entries each), sorted by time. Ask Jarvis "did my backup run last night?" and it will call `list_crons` + `read_cron_log`.
 
 ## Tools
 
@@ -85,8 +85,9 @@ Use `read_cron_log` to inspect past runs. Ask Jarvis "did my backup run last nig
 |---|---|
 | `create_cron` | Schedule a new cron job |
 | `list_crons` | List all active crons |
+| `update_cron` | Modify an existing cron (name, schedule, prompt, once) |
 | `delete_cron` | Remove a cron by name or id |
-| `read_cron_log` | Read execution history for a cron |
+| `read_cron_log` | Read execution history — omit id for cross-cron overview |
 | `get_current_time` | Get current server time for relative scheduling |
 | `send_telegram_message` | Send a proactive message to the Telegram user |
 

package/docs/system-prompt.md

@@ -1,4 +1,4 @@
-# System Prompt (v1)
+# System Prompt (v2)
 
 This is the authoritative system prompt sent to the model at the start of every session. It is stored as the first message (`role: "system"`) in the conversation history.
 
@@ -23,14 +23,7 @@ Only the most recent messages are included in your context (sliding window). Old
 
 ## Crons
 
-You can schedule recurring or one-time tasks using cron jobs.
-
-- Use `create_cron` when the user wants to schedule something — even if they don't say "cron". Triggers: "every night", "every 2 hours", "remind me at 3pm", "notify me in 2 hours", "check X every Monday", etc.
-- Call `get_current_time` first when the user specifies a relative time (e.g. "in 2 hours") so you can calculate the correct cron expression.
-- The `prompt` stored in the cron is executed by a fresh agent with no prior conversation context. Write it as a complete, self-contained instruction.
-- If the user wants to be notified, include "use send_telegram_message to notify the user with the result" in the prompt. If they explicitly don't want a notification, omit it.
-- For one-time tasks, set `once: true` — the cron deletes itself after firing.
-- Use `list_crons` to show active crons, `delete_cron` to remove one, `read_cron_log` to inspect past runs.
+Use `create_cron` when the user wants something scheduled — even without the word "cron". Common triggers: "every night", "every 2 hours", "remind me at 3pm", "notify me in 2 hours", "check X every Monday". See the `create_cron` and `get_current_time` tool descriptions for how to construct the schedule and prompt correctly.
 
 ## Skills
 
@@ -65,42 +58,11 @@ You have access to a set of tools. Each tool has a name and description that tel
 - After a tool call, verify the result before declaring the task done. Always communicate what you did and why — don't just report success, briefly explain the action taken.
 - Stop as soon as the task is complete and verified. Do not do extra work that was not asked for.
 - If a tool fails, record the error in `logSummary` and decide whether to retry with a corrected call or explain the failure to the user.
-- If the user shares personal information, persist it using the appropriate tool.
+- Proactively save user facts with `save_user_info` when the user shares personal details (name, timezone, preferences) — even if not asked.
+- Use `write_file` to create or overwrite files — never `exec` with echo/printf/heredoc (shell escaping silently corrupts content).
+- For processes that may run longer than 5 minutes: use `nohup command > /tmp/out.log 2>&1 &` and poll with `exec`.
 - Prefer using tools over making assumptions about the state of the system.
 
-## exec Safety
-
-The `exec` tool runs real shell commands on the server. Use it responsibly:
-
-- **Never scan from filesystem root.** Commands like `find /`, `find / -name ...`, or `ls -R /` will scan everything including `/proc`, `/sys`, and network mounts. They can saturate CPU and I/O for minutes. Always scope `find` to a specific directory (e.g. `find ~/jarvis -name "*.js"`).
-- **Use known paths.** Prefer `process.cwd()`, `$HOME`, or paths you already know over broad searches. Use `which <binary>` to locate executables.
-- **Prefer targeted reads.** Use `grep`, `head`, or `tail` instead of `cat` on files you haven't seen before. Large file output is truncated anyway — a targeted command gives you better signal.
-- **Avoid commands with unbounded runtime.** If a command could run indefinitely or scan an unknown-size tree, scope it first.
-
-## Writing Files
-
-Use the `write_file` tool to create or overwrite any file. Never use `exec` with `echo`, `printf`, or heredoc to write files.
-
-Shell escaping through `exec` silently corrupts file content: dollar signs become `\$`, backslashes double up, and the resulting file looks correct when printed but is broken at runtime (variables never expand, scripts fail with "command not found"). `write_file` bypasses all shell interpretation — content arrives as a JSON string and lands in the file exactly as written.
-
-- For shell scripts: pass `mode: "755"` to make the file executable in the same call.
-- For any other file: omit `mode` or use `"644"`.
-
-## Execution Timeouts
-
-Every tool call is wrapped in a server-side timeout that the tool's code cannot override:
-
-- **`exec`** — 5-minute cap. Sufficient for scans, builds, and most long-running commands.
-- **`system_install`** — 5-minute cap. Use for installing system binaries via a package manager.
-- **Custom tools via `save_tool`** — default 60s unless you pass `timeout` (in ms, max 600000). If a custom tool wraps a slow operation, set `timeout` explicitly.
-
-**For truly long-running processes (> 5 minutes)**: run in the background and poll for results:
-```sh
-nohup long-running-command > /tmp/output.log 2>&1 & echo $!
-# Check progress later
-cat /tmp/output.log
-```
-
 ## Failure Recovery
 
 When a tool or command fails:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ducci/jarvis",
-  "version": "1.0.45",
+  "version": "1.0.47",
   "description": "A fully automated agent system that lives on a server.",
   "main": "./src/index.js",
   "type": "module",

package/src/server/agent.js

@@ -241,6 +241,9 @@ export async function runAgentLoop(client, config, session, prepareMessages, usa
             if (toolName === 'create_cron') {
               const cronEntry = JSON.parse(resultStr)?.cron;
               if (cronEntry) cronScheduler.schedule(cronEntry);
+            } else if (toolName === 'update_cron') {
+              const cronEntry = JSON.parse(resultStr)?.cron;
+              if (cronEntry) { cronScheduler.unschedule(cronEntry.id); cronScheduler.schedule(cronEntry); }
             } else if (toolName === 'delete_cron') {
               const id = JSON.parse(resultStr)?.id;
               if (id) cronScheduler.unschedule(id);

package/src/server/tools.js

@@ -53,7 +53,7 @@ const SEED_TOOLS = {
       type: 'function',
       function: {
         name: 'exec',
-        description: 'Execute an arbitrary shell command on the server. Returns stdout, stderr, and exit code. Use this for any system operation: running scripts, installing packages, managing files, etc.',
+        description: 'Execute an arbitrary shell command on the server. Returns stdout, stderr, and exit code. Use this for any system operation: running scripts, managing processes, querying files, etc. Has a 5-minute timeout. Safety: never scan from filesystem root (avoid `find /`, `ls -R /`) — always scope to a specific directory. Prefer `grep`, `head`, or `tail` over `cat` on unknown files. Use `which <binary>` to locate executables. Avoid commands with unbounded runtime.',
         parameters: {
           type: 'object',
           properties: {
@@ -364,7 +364,7 @@ const SEED_TOOLS = {
       type: 'function',
       function: {
         name: 'get_current_time',
-        description: 'Returns the current server time. Call this before scheduling a cron job when the user specifies a relative time (e.g. "in 2 hours", "at 3pm today") so you can calculate the correct schedule.',
+        description: 'Returns the current server time. Always call this before creating a cron. Note: returns server time — if you know the user\'s timezone, convert the desired user-local time to server time before computing the cron expression.',
         parameters: { type: 'object', properties: {}, required: [] },
       },
     },
@@ -383,7 +383,7 @@ const SEED_TOOLS = {
       type: 'function',
       function: {
         name: 'create_cron',
-        description: 'Schedule a recurring or one-time task. The prompt is executed by a fresh agent with no prior context — write it as a self-contained task. For one-time tasks (e.g. "remind me in 2 hours"), set once: true. Call get_current_time first when calculating a relative schedule.',
+        description: 'Schedule a recurring or one-time task. The prompt is executed by a fresh agent with no prior context — write it as a self-contained task. For one-time tasks (e.g. "remind me in 2 hours"), set once: true. Always call get_current_time first and convert user-local time to server time before computing the cron expression.',
         parameters: {
           type: 'object',
           properties: {
@@ -429,6 +429,40 @@ const SEED_TOOLS = {
       return { status: 'ok', crons };
     `,
   },
+  update_cron: {
+    definition: {
+      type: 'function',
+      function: {
+        name: 'update_cron',
+        description: 'Update an existing cron job. Only the fields you provide will be changed. If updating the schedule, call get_current_time first and convert user-local time to server time before computing the cron expression.',
+        parameters: {
+          type: 'object',
+          properties: {
+            id: { type: 'string', description: 'The cron id to update.' },
+            name: { type: 'string', description: 'New name.' },
+            schedule: { type: 'string', description: 'New cron expression.' },
+            prompt: { type: 'string', description: 'New prompt.' },
+            once: { type: 'boolean', description: 'New once value.' },
+          },
+          required: ['id'],
+        },
+      },
+    },
+    code: `
+      const cronsFile = path.join(process.env.HOME, '.jarvis/data/crons.json');
+      const crons = JSON.parse(await fs.promises.readFile(cronsFile, 'utf8').catch(() => '[]'));
+      const idx = crons.findIndex(c => c.id === args.id);
+      if (idx === -1) return { status: 'not_found' };
+      const updated = { ...crons[idx] };
+      if (args.name !== undefined) updated.name = args.name;
+      if (args.schedule !== undefined) updated.schedule = args.schedule;
+      if (args.prompt !== undefined) updated.prompt = args.prompt;
+      if (args.once !== undefined) updated.once = args.once;
+      crons[idx] = updated;
+      await fs.promises.writeFile(cronsFile, JSON.stringify(crons, null, 2), 'utf8');
+      return { status: 'ok', cron: updated };
+    `,
+  },
   delete_cron: {
     definition: {
       type: 'function',