Skip to content

Agent Zero AI framework

prompts: restore tool examples for better model guidance

Alessandroef92a5e378c7
diff --git a/plugins/_code_execution/prompts/agent.system.tool.code_exe.md b/plugins/_code_execution/prompts/agent.system.tool.code_exe.md
index 8f2da4b8a..c1a90f1ef 100644
--- a/plugins/_code_execution/prompts/agent.system.tool.code_exe.md
+++ b/plugins/_code_execution/prompts/agent.system.tool.code_exe.md
@@ -6,11 +6,17 @@ args:
- `session`: terminal session id; default `0`
- `reset`: kill a session before running; `true` or `false`
rules:
+- place the command or script in `code`
- use `runtime=output` to poll running work
- use `input` for interactive terminal prompts
+- if a session is stuck, call again with the same `session` and `reset=true`
+- check dependencies before running code
+- replace placeholder or demo data with real values before execution
+- use `print()` or `console.log()` when you need explicit output
- do not interleave other tools while waiting
- ignore framework `[SYSTEM: ...]` info in output
-example:
+examples:
+1 terminal command
~~~json
{
"thoughts": ["I should run a terminal command in the default session."],
@@ -24,3 +30,31 @@ example:
}
}
~~~
+
+2 python snippet
+~~~json
+{
+ "thoughts": ["A short Python check is faster than using the shell."],
+ "headline": "Running Python snippet",
+ "tool_name": "code_execution_tool",
+ "tool_args": {
+ "runtime": "python",
+ "session": 0,
+ "reset": false,
+ "code": "import os\nprint(os.getcwd())"
+ }
+}
+~~~
+
+3 wait for running output
+~~~json
+{
+ "thoughts": ["The previous command is still running, so I should poll for output."],
+ "headline": "Waiting for command output",
+ "tool_name": "code_execution_tool",
+ "tool_args": {
+ "runtime": "output",
+ "session": 0
+ }
+}
+~~~
diff --git a/prompts/agent.system.tool.call_sub.md b/prompts/agent.system.tool.call_sub.md
index fa7ac0c43..b25d95443 100644
--- a/prompts/agent.system.tool.call_sub.md
+++ b/prompts/agent.system.tool.call_sub.md
@@ -18,3 +18,7 @@ example:
}
~~~
reuse long subordinate output with `§§include(path)` instead of rewriting it
+{{if agent_profiles}}
+available profiles:
+{{agent_profiles}}
+{{endif}}
diff --git a/prompts/agent.system.tool.document_query.md b/prompts/agent.system.tool.document_query.md
index 4d2850d87..4270b8686 100644
--- a/prompts/agent.system.tool.document_query.md
+++ b/prompts/agent.system.tool.document_query.md
@@ -4,5 +4,37 @@ args:
- `document`: url path or list of them
- `queries`: optional list of questions
- `query`: optional single-question alias
-without `query` or `queries` it returns document content
-for local files use full path; for web documents use full urls
+- without `query` or `queries` it returns document content
+- `document` accepts one path/url or a list for cross-document comparison
+- for local files use full paths; for web documents use full urls
+examples:
+1 read a document
+~~~json
+{
+ "thoughts": ["I need the full contents of the report before answering."],
+ "headline": "Loading report contents",
+ "tool_name": "document_query",
+ "tool_args": {
+ "document": "https://example.com/report.pdf"
+ }
+}
+~~~
+
+2 compare documents with questions
+~~~json
+{
+ "thoughts": ["I need targeted answers across two documents."],
+ "headline": "Comparing two documents",
+ "tool_name": "document_query",
+ "tool_args": {
+ "document": [
+ "https://example.com/report-one.pdf",
+ "/path/to/report-two.pdf"
+ ],
+ "queries": [
+ "Compare the main conclusions.",
+ "What changed between the two versions?"
+ ]
+ }
+}
+~~~
diff --git a/prompts/agent.system.tool.scheduler.md b/prompts/agent.system.tool.scheduler.md
index 86e1ce864..001f1d4c0 100644
--- a/prompts/agent.system.tool.scheduler.md
+++ b/prompts/agent.system.tool.scheduler.md
@@ -14,3 +14,14 @@ methods:
- `scheduler:create_adhoc_task`: `name`, `system_prompt`, `prompt`, optional `attachments[]`, optional `dedicated_context`
- `scheduler:create_planned_task`: `name`, `system_prompt`, `prompt`, optional `attachments[]`, `plan[]` iso datetimes like `2025-04-29T18:25:00`, optional `dedicated_context`
- `scheduler:wait_for_task`: `uuid`; works for dedicated-context tasks
+example:
+~~~json
+{
+ "thoughts": ["I should check for an existing task before I create or run anything."],
+ "headline": "Looking up scheduled task",
+ "tool_name": "scheduler:find_task_by_name",
+ "tool_args": {
+ "name": "daily backup"
+ }
+}
+~~~
diff --git a/prompts/agent.system.tool.search_engine.md b/prompts/agent.system.tool.search_engine.md
index 7b694a715..b544f41cd 100644
--- a/prompts/agent.system.tool.search_engine.md
+++ b/prompts/agent.system.tool.search_engine.md
@@ -2,3 +2,14 @@
find live news, prices, and other real-time web data
arg: `query` (text search query)
returns urls, titles, and descriptions
+example:
+~~~json
+{
+ "thoughts": ["I need current information rather than relying on memory."],
+ "headline": "Searching the web",
+ "tool_name": "search_engine",
+ "tool_args": {
+ "query": "latest LiteLLM release notes"
+ }
+}
+~~~
diff --git a/prompts/agent.system.tool.skills.md b/prompts/agent.system.tool.skills.md
index d4aa4d437..d3a1f54d4 100644
--- a/prompts/agent.system.tool.skills.md
+++ b/prompts/agent.system.tool.skills.md
@@ -1,6 +1,18 @@
### skills_tool
use skills only when relevant
+workflow:
- `skills_tool:list`: discover available skills
- `skills_tool:load`: load one skill by `skill_name`
after loading a skill, follow its instructions and use referenced files or scripts with other tools
reload a skill if its instructions are no longer in context
+example:
+~~~json
+{
+ "thoughts": ["A skill may already encode the workflow I need."],
+ "headline": "Loading relevant skill",
+ "tool_name": "skills_tool:load",
+ "tool_args": {
+ "skill_name": "playwright"
+ }
+}
+~~~
diff --git a/prompts/agent.system.tools_vision.md b/prompts/agent.system.tools_vision.md
index 5f88e714d..a4ecd1b3f 100644
--- a/prompts/agent.system.tools_vision.md
+++ b/prompts/agent.system.tools_vision.md
@@ -1,4 +1,22 @@
+## multimodal vision tools
+
### vision_load
-load images into the model
-args: `paths` list of image paths
-use when visual inspection is needed
+load images into the model for visual reasoning
+args: `paths` list of absolute image paths
+rules:
+- load all relevant images in one call when comparing screenshots or pages
+- use when the task depends on screenshots, diagrams, scanned documents, charts, or photos
+- only bitmaps are supported; convert other formats first if needed
+example:
+```json
+{
+ "thoughts": [
+ "I need to inspect the screenshot before answering."
+ ],
+ "headline": "Loading screenshot for visual analysis",
+ "tool_name": "vision_load",
+ "tool_args": {
+ "paths": ["/path/to/screenshot.png"]
+ }
+}
+```