mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-05 06:13:15 +00:00
Alex
636d4d35d1
Rewrite the default/creative/strict presets (classic + agentic) into
structured sections: grounding and cite-by-title guidance, insufficient-
context behavior, current date, respond-in-user-language, scoped mermaid
usage, an untrusted-content guardrail, and a conditional XML-tagged
document context block. A memory directory listing is injected at render
time via the template prefetch mechanism so the model starts oriented
without burning a tool call.
Fixes along the way:
- Agentic preset swap was dead code: _get_prompt_content cached the
classic preset before create_agent's swap check ran, so agentic and
research agents always got the classic preset. The swap now happens
inside _get_prompt_content.
- Jinja autoescape corrupted document content in custom prompts
(< -> <); prompts are not HTML, autoescape is now off.
- Literal {summaries} leaked into the prompt when no docs were
retrieved; the placeholder is now stripped.
- Agentic/research prompts referenced tool names from a dropped naming
scheme (search_internal, reason_think); they now reference the real
names (search, reason).
- The strict preset told the model to "be very creative and use your
imagination" right after "never make up information".
- extract_tool_usages recorded intermediate attribute chains as
bare-tool usages, which meant "run all actions" at prefetch; only
maximal chains are recorded now.
- Headless runs retrieved docs but never rendered them into the
prompt; the prompt is now rendered like the streaming path.
- Default tools were unreachable by name in prompt templates
(prefetch results were keyed by synthetic id only); defaults now
claim the name key unless an explicit row shadows it.
Tool layer: memory/notes/todo actions are namespaced (memory_view,
note_overwrite, todo_create, ...) with legacy unprefixed names still
accepted via prefix stripping; duplicate action names across tools are
disambiguated with the owning tool's name instead of numeric suffixes;
thin tool descriptions rewritten (brave, duckduckgo, telegram, ntfy,
cryptoprice, read_webpage, internal_search, think).
Docs are now wrapped per chunk in <document index>/<source>/<content>
tags for citation-by-title support.
14 lines
854 B
Plaintext
14 lines
854 B
Plaintext
You are a research agent investigating a specific topic. Your goal is to find comprehensive, accurate information.
|
|
|
|
Your current research task: {step_query}
|
|
|
|
Instructions:
|
|
1. Use the available tools to search for and gather relevant information.
|
|
2. If you have a `search` tool, use it to search the knowledge base. You may search multiple times with different queries.
|
|
3. If you have a `reason` tool, use it to analyze what you've found before drawing conclusions.
|
|
4. After gathering sufficient information, provide a detailed summary of your findings.
|
|
5. Cite specific documents and passages you found. Reference sources by their titles or filenames.
|
|
6. If you cannot find relevant information through tools, use your general knowledge but clearly indicate this.
|
|
|
|
Be thorough — prefer completeness over brevity. Include all relevant details you find.
|