菜单
Teaches the model how to manage stateful discussions, track conversational trees/branches, navigate alternative sibling replies, and execute context-aware generation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Teaches how to build, discover, and execute local, zero-configuration Python tools in Lollms using AST schema parsing and context injection. Includes step-by-step tool file construction guide and code examples.
Teaches the model about the persistent tiered memory system (Level 1 Working, Level 2 Deep, Level 3 Archive), proactive keyword pulling, and the required tagging protocols.
Teaches the model how to formulate strategic <coding_plan> blocks, apply indentation-agnostic Aider search/replace patches, manage Git-like version logs, and control in-message status reporting.
Teaches how to import, parse, and process PDF, DOCX, PPTX, and image files using anchor-mapped and OCR import modes in LollmsDiscussion.
Teaches how to coordinate multiple specialized agents, distribute tasks, establish consensus, and manage role-based multi-agent swarms using LollmsSwarm.
Guides the model on performing basic text generation, counting tokens, detokenizing lists, and generating structurally validated JSON outputs with LollmsClient.
| name | Lollms Discussion and Chat |
| description | Teaches the model how to manage stateful discussions, track conversational trees/branches, navigate alternative sibling replies, and execute context-aware generation. |
| author | ParisNeo |
| version | 1.0.0 |
| category | lollms_client/discussion |
| created | "2026-05-24T00:00:00.000Z" |
Instead of maintaining a simple list of message dicts, LollmsDiscussion organizes conversations as a hierarchical tree, allowing first-class support for branching, alternative model replies, and session persistence.
A discussion represents a stateful chat session. It can be fully in-memory or persisted to a local SQLite database.
from lollms_client import LollmsClient
from lollms_client.lollms_discussion import LollmsDiscussion
client = LollmsClient(llm_binding_name="ollama", llm_binding_config={"model_name": "gemma4:e2b"})
# Create an in-memory, stateful discussion
discussion = LollmsDiscussion(lollmsClient=client)
discussion.system_prompt = "You are a helpful software engineering companion."
Messages are stored in the tree. When adding a message, it automatically attaches to the current active branch tip.
# Add user message
msg_user = discussion.add_message(sender="user", content="What is an RPC?")
# Add assistant response
msg_assistant = discussion.add_message(sender="assistant", content="Remote Procedure Call.")
print(f"Active Branch Tip Message ID: {discussion.active_branch_id}")
A branch represents a conversational path from the root message to a leaf. If the user or system wants to explore an alternative path, we "fork" the conversation.
# Fork an alternative branch starting from the first user question
fork_msg = discussion.fork_from(
message_id=msg_user.id,
label="Alternative Topic Branch",
initial_content="Actually, tell me about REST instead."
)
# Switch back and forth between branches
discussion.switch_branch(msg_assistant.id) # Returns to the original RPC branch
The high-level chat() method automatically assembles all context zones (system instructions, memory, active artifacts, discussion history) and sends a correctly formatted template to the model.
# High-level chat execution
response = discussion.chat(
user_message="Explain REST constraints",
enable_memory=True,
enable_artefacts=True
)
print(response)