mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-05-17 12:31:20 +00:00
daf95ec3ab
Standardize multi-action tools around tool_args.action while keeping parser compatibility for older tool/args, tool_name:action, and method-shaped requests. This keeps new prompts clean without breaking agents that learned the previous dialect. Move A0 connector remote execution/file tools into stable standard prompts, make remote targeting independent of the active chat context, and skill-gate beta computer-use remote so it no longer weighs down the always-on tool list. Align text editor, scheduler, skills, office artifact, memory, notify, and browser prompts/tools around the canonical action contract. Add scheduler update/timezone handling, skills_tool read_file, text editor patch coverage, and fixes for memory_forget, behaviour_adjustment, and code execution progress warnings. Reduce default prompt pressure by compacting browser and scheduler prompts into skill-backed manifests, shortening skill catalog descriptions, and pruning noisy framework knowledge. Remove obsolete connector prompt stubs and root tool-call knowledge examples. Tests: conda run -n a0 pytest tests/test_a0_connector_prompt_gating.py tests/test_tool_action_contracts.py tests/test_task_scheduler_timezone.py tests/test_text_editor_context_patch.py tests/test_tool_request_normalization.py tests/test_office_document_store.py::test_odf_is_advertised_and_docx_remains_explicit_compatibility tests/test_office_document_store.py::test_document_artifact_accepts_method_alias_for_ods_create tests/test_skills_runtime.py tests/test_default_prompt_budget.py::test_a0_small_profile_removed_and_prompt_text_generic -q |
||
|---|---|---|
| .. | ||
| extensions | ||
| helpers | ||
| prompts | ||
| tools | ||
| webui | ||
| default_config.yaml | ||
| plugin.yaml | ||
| README.md | ||
Text Editor
Provide an LLM-friendly file editing tool for reading, writing, and patching text files.
What It Does
This plugin exposes a native text editing tool that agents can use to inspect files, write complete contents, and apply validated patch operations while tracking file freshness between reads and edits.
Main Behavior
- Read
- Reads whole files or line ranges with token-aware limits.
- Records file metadata so later patch operations can detect stale edits.
- Write
- Writes full file contents and then re-reads the resulting file for confirmation.
- Patch
- Validates edit structures before applying them.
- Rejects edits if the file changed since it was last observed.
- Reads back the affected patch region after applying changes.
- Extension hooks
- Exposes before and after extension points for read, write, and patch operations.
Key Files
- Tool
tools/text_editor.pyimplements method dispatch, stale-file checks, patching flow, and prompt responses.
- Helpers
helpers/file_ops.pyprovides file info, read/write helpers, edit validation, and patch application.
- Configuration
default_config.yamldefines read limits and token budgets.
- Prompts
prompts/contains the agent-facing success and error messages.
Configuration Scope
- Settings section:
agent - Per-project config:
true - Per-agent config:
true
Plugin Metadata
- Name:
_text_editor - Title:
Text Editor - Description: Native tool to read, write, and patch text files in an LLM-friendly way.